zhongwei/gh-henkisdabro-wookstar-claude-code-plugins-documents-toolkit
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial commit

Browse Source
This commit is contained in:
Zhongwei Li
2025-11-29 18:32:37 +08:00
commit 7822766a14
70 changed files with 27471 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
.claude-plugin/plugin.json Normal file
View File

@@ -0,0 +1,12 @@
{
"name": "documents-toolkit",
"description": "Professional document processing suite: 3 comprehensive skills for Word (.docx), Excel (.xlsx), and PDF files - create, edit, analyze, and process documents with advanced features like tracked changes, forms, tables, OCR, and formulas",
"version": "1.0.0",
"author": {
"name": "Henrik Soederlund",
"email": "whom-wealthy.2z@icloud.com"
},
"skills": [
"./skills"
]
}

3
README.md Normal file
View File

@@ -0,0 +1,3 @@
# documents-toolkit
Professional document processing suite: 3 comprehensive skills for Word (.docx), Excel (.xlsx), and PDF files - create, edit, analyze, and process documents with advanced features like tracked changes, forms, tables, OCR, and formulas

309
plugin.lock.json Normal file
View File

@@ -0,0 +1,309 @@
{
"$schema": "internal://schemas/plugin.lock.v1.json",
"pluginId": "gh:henkisdabro/wookstar-claude-code-plugins:documents-toolkit",
"normalized": {
"repo": null,
"ref": "refs/tags/v20251128.0",
"commit": "39e40e72af1df0afbe9b0a2a57f1fc595469a729",
"treeHash": "f808d3f3630fe716d9de3440bc29ee7c567ed6358c7c6a9cefd38a0c34cb2218",
"generatedAt": "2025-11-28T10:17:24.432429Z",
"toolVersion": "publish_plugins.py@0.2.0"
},
"origin": {
"remote": "git@github.com:zhongweili/42plugin-data.git",
"branch": "master",
"commit": "aa1497ed0949fd50e99e70d6324a29c5b34f9390",
"repoRoot": "/Users/zhongweili/projects/openmind/42plugin-data"
},
"manifest": {
"name": "documents-toolkit",
"description": "Professional document processing suite: 3 comprehensive skills for Word (.docx), Excel (.xlsx), and PDF files - create, edit, analyze, and process documents with advanced features like tracked changes, forms, tables, OCR, and formulas",
"version": "1.0.0"
},
"content": {
"files": [
{
"path": "README.md",
"sha256": "2530d0681548436bcaac4d4117ed0222b3f4457aaf9673601f48f9f95e0b9222"
},
{
"path": ".claude-plugin/plugin.json",
"sha256": "f5ccb425121a713ba93599d78392f89f6dfb2ff84a04706868519eb63c4c38a5"
},
{
"path": "skills/xlsx/recalc.py",
"sha256": "ab1ef0c94536bb23b6c6a3d32769b0401ec3cc85e73c247d574dd84ec73af15d"
},
{
"path": "skills/xlsx/SKILL.md",
"sha256": "020ccdb5932257b66c638ec1157ea248d57fa52c8c01f1f68b559b5970c7df35"
},
{
"path": "skills/xlsx/LICENSE.txt",
"sha256": "79f6d8f5b427252fa3b1c11ecdbdb6bf610b944f7530b4de78f770f38741cfaa"
},
{
"path": "skills/pdf-processing-pro/TABLES.md",
"sha256": "ae2b4c9fc07a724f25415aa19d061477e52565ad50c7cb10a9b3bdc069dfe94f"
},
{
"path": "skills/pdf-processing-pro/FORMS.md",
"sha256": "ea43f2930d53347e0cf19a205bf94315737cbb034153181ebdff6d037bac8d24"
},
{
"path": "skills/pdf-processing-pro/OCR.md",
"sha256": "f28c254d9f15eed42233a3e806f722f3a92c35d429df0b50641e7ef0efda10fb"
},
{
"path": "skills/pdf-processing-pro/SKILL.md",
"sha256": "0e07e0c87b7189911b91f35da0b3aaad6678ff2b2781334bfc217a5432a3fe6f"
},
{
"path": "skills/pdf-processing-pro/scripts/analyze_form.py",
"sha256": "694c93c3e1dec5dc6a6e4ebdc2548c8a9200c52a9b261399893d0592831f4395"
},
{
"path": "skills/docx/ooxml.md",
"sha256": "a16f922797eeaa3670ea31c1e49d15b799613d03f39445c857a5dd3221aa3597"
},
{
"path": "skills/docx/docx-js.md",
"sha256": "83b4a2f88d058a10509fbc0b3b12b6933c407805f4d4afc955cd3fb939c16428"
},
{
"path": "skills/docx/SKILL.md",
"sha256": "0bd90681fcab2e282025ee14acf508b60bbd6c41ac6c3bf83c0dc14d52c37933"
},
{
"path": "skills/docx/LICENSE.txt",
"sha256": "79f6d8f5b427252fa3b1c11ecdbdb6bf610b944f7530b4de78f770f38741cfaa"
},
{
"path": "skills/docx/ooxml/schemas/microsoft/wml-sdtdatahash-2020.xsd",
"sha256": "842e7163409c8d74f4d7088a8bc99500d80bc75332681a0980055b08f374a604"
},
{
"path": "skills/docx/ooxml/schemas/microsoft/wml-2012.xsd",
"sha256": "0fa75578a000439a7988ba0c59fdc69f774bbd416cbacc14d07125b3f686cb74"
},
{
"path": "skills/docx/ooxml/schemas/microsoft/wml-2010.xsd",
"sha256": "568b26ee156cb9549aa439ca2158965f77b7c1602b7e0316f40ac6cf586e35f2"
},
{
"path": "skills/docx/ooxml/schemas/microsoft/wml-cid-2016.xsd",
"sha256": "127ca209fa73d7cb708449cb355c871867948a96e4a74f7bf5811ef62d17991d"
},
{
"path": "skills/docx/ooxml/schemas/microsoft/wml-symex-2015.xsd",
"sha256": "16f6f8072249f431370723c2cd8974672e0d9c897e00e97dd918079df934871b"
},
{
"path": "skills/docx/ooxml/schemas/microsoft/wml-cex-2018.xsd",
"sha256": "fddc2b880cabb9005aebbc7e783e53c19fec1c03df7d0e2f2076a33a0fdfd081"
},
{
"path": "skills/docx/ooxml/schemas/microsoft/wml-2018.xsd",
"sha256": "be0ff793a22dd31384650c3a4da14c2fa8062751c2e97b0e5ee852bda13c60ad"
},
{
"path": "skills/docx/ooxml/schemas/mce/mc.xsd",
"sha256": "3a37e461ecf5a8670fdec34029703401f8728ab9c96ec1739a6ae58d55212413"
},
{
"path": "skills/docx/ooxml/schemas/ecma/fouth-edition/opc-coreProperties.xsd",
"sha256": "71d4844b6e31d108d1324708f1897843ef54deebe78869e7e15edac8b5495780"
},
{
"path": "skills/docx/ooxml/schemas/ecma/fouth-edition/opc-relationships.xsd",
"sha256": "ef23284866e5e1dd69eddc4f42b4efa58a9c4c4f7d94b21949887c02534c1ab4"
},
{
"path": "skills/docx/ooxml/schemas/ecma/fouth-edition/opc-contentTypes.xsd",
"sha256": "5083a39fd5ade6790c291513d5b2a0447087424b04ae02d5f320edce2c5db158"
},
{
"path": "skills/docx/ooxml/schemas/ecma/fouth-edition/opc-digSig.xsd",
"sha256": "6de111e11403f7cd49027400755bae0ea1cabef2815f09bd40a24f0017613b24"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd",
"sha256": "133c9f64a5c5d573b78d0a474122b22506d8eadb5e063f67cdbbb8fa2f161d0e"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd",
"sha256": "585bedc1313b40888dcc544cb74cd939a105ee674f3b1d3aa1cc6d34f70ff155"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd",
"sha256": "0d103b99a4a8652f8871552a69d42d2a3760ac6a5e3ef02d979c4273257ff6a4"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/pml.xsd",
"sha256": "d173c3e5d61e42e2e3a97226c632fd2ab7cc481fc4e492365b87024ab546daff"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd",
"sha256": "5cb76dabd8b97d1e9308a1700b90c20139be4d50792d21a7f09789f5cccd6026"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chart.xsd",
"sha256": "41b93bd8857cc68b1e43be2806a872d736a9bdd6566900062d8fdb57d7bbb354"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd",
"sha256": "3fd0586f2637b98bb9886f0e0b67d89e1cc987c2d158cc7deb5f5b9890ced412"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/sml.xsd",
"sha256": "beffeed56945c22a77440122c8bdc426f3fcbe7f3b12ea0976c770d1f8d54578"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd",
"sha256": "6bdeb169c3717eb01108853bd9fc5a3750fb1fa5b82abbdd854d49855a40f519"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/wml.xsd",
"sha256": "c2dd9f61f892deae6acd8d20771ea79b12018af25f3bf8d06639c8542d218cfd"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-picture.xsd",
"sha256": "5d389d42befbebd91945d620242347caecd3367f9a3a7cf8d97949507ae1f53c"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd",
"sha256": "29b254ee0d10414a8504b5a08149c7baec35a60d5ff607d6b3f492aa36815f40"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-main.xsd",
"sha256": "5375417f0f5394b8dd1a7035b9679151f19a6b65df309dec10cfb4a420cb00e9"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd",
"sha256": "9c085407751b9061c1f996f6c39ce58451be22a8d334f09175f0e89e42736285"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd",
"sha256": "b4532b6d258832953fbb3ee4c711f4fe25d3faf46a10644b2505f17010d01e88"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd",
"sha256": "e2abacbb9a55ce1365f8961bc1b1395bbc811e512b111000d8c333f98458dece"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd",
"sha256": "bdad416b096b61d37b71603b2c949484f9070c830bdaeba93bf35e15c8900614"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd",
"sha256": "475dcae1e7d1ea46232db6f8481040c15e53a52a3c256831d3df204212b0e831"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd",
"sha256": "0b364451dc36a48dd6dae0f3b6ada05fd9b71e5208211f8ee5537d7e51a587e2"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd",
"sha256": "bc92e36ccd233722d4c5869bec71ddc7b12e2df56059942cce5a39065cc9c368"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-main.xsd",
"sha256": "f5ee623b08b6a66935e5aced2f5d8ad0fc71bf9e8e833cd490150c0fa94b8763"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/xml.xsd",
"sha256": "a539aa2fb154fa50e0f5cc97e6ad7cbc66f8ec3e3746f61ec6a8b0d5d15ecdf2"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd",
"sha256": "12264f3c03d738311cd9237d212f1c07479e70f0cbe1ae725d29b36539aef637"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd",
"sha256": "0ef4bb354ff44b923564c4ddbdda5987919d220225129ec94614a618ceafc281"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd",
"sha256": "7b5b7413e2c895b1e148e82e292a117d53c7ec65b0696c992edca57b61b4a74b"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-math.xsd",
"sha256": "3213ef1631606250f5010b42cad7ef716f7c59426367798e33c374c0ec391d3a"
},
{
"path": "skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd",
"sha256": "3c6709101c6aaa82888df5d8795c33f9e857196790eb320d9194e64be2b6bdd8"
},
{
"path": "skills/docx/ooxml/scripts/pack.py",
"sha256": "6fe762f45aff8c63fd95b9fcb1337b28921d6fa454e18a0e8158d4c8708d6d00"
},
{
"path": "skills/docx/ooxml/scripts/validate.py",
"sha256": "1ec252de8b14b07d16966c48906ccb1c45c68bcd23557ad31d8c50a27f5f8c0f"
},
{
"path": "skills/docx/ooxml/scripts/unpack.py",
"sha256": "0bd17f76a1a4c388aba42c6d1d39015fa84e405c3e0692397fe12762bd632b58"
},
{
"path": "skills/docx/ooxml/scripts/validation/docx.py",
"sha256": "e65d6cda0525866a24cc847b2e883bd2416ae6f87b3f5b9e2784dfbb0ec13093"
},
{
"path": "skills/docx/ooxml/scripts/validation/__init__.py",
"sha256": "83e0f035c5abea238d3f2c3968afbd511ed022b527b7c9cb60a9434cc34ff987"
},
{
"path": "skills/docx/ooxml/scripts/validation/redlining.py",
"sha256": "97abfdff4f08f43f9a4bb5c8a2f8fd483398b5b339592724e8635153b5507967"
},
{
"path": "skills/docx/ooxml/scripts/validation/pptx.py",
"sha256": "00bf2623da1177b3948143a4ade2f1cda7cb389dee31960861913fa42ef1b00f"
},
{
"path": "skills/docx/ooxml/scripts/validation/base.py",
"sha256": "f2c70d481613456e32b43869d1604b05c236c8da34b5b3967677a661cac7ba63"
},
{
"path": "skills/docx/scripts/__init__.py",
"sha256": "83e262a425814b72add701272b99ddcf9635251c5d4672bf9fc38d2b03f00d85"
},
{
"path": "skills/docx/scripts/document.py",
"sha256": "65f8569034a5893bd5ef0654be5168774fe81c0407b0c4ec80992db9fff91c0c"
},
{
"path": "skills/docx/scripts/utilities.py",
"sha256": "62a4b689056501b91e2df2d1f4e6335818e421c7390e48050717ea8f461a0ed0"
},
{
"path": "skills/docx/scripts/templates/comments.xml",
"sha256": "87e218a3a295016ec855f2cd74495c416072f29c4846e86b527aec0a4d93ba21"
},
{
"path": "skills/docx/scripts/templates/commentsExtensible.xml",
"sha256": "af5d057e16462ca172cea845e502bafb4f3e1b474a8d5848ffe92214853a4935"
},
{
"path": "skills/docx/scripts/templates/commentsExtended.xml",
"sha256": "86bf401354c111102033ed147763faccb82479598f17777a3384c2f3e9fa0014"
},
{
"path": "skills/docx/scripts/templates/commentsIds.xml",
"sha256": "20168f7b237af091332f8348c548eb7f755f583185bb198359c5978155099d67"
},
{
"path": "skills/docx/scripts/templates/people.xml",
"sha256": "61db9900b579acd4c4f84ff7f40df47e77e9e780c40d5f5ef6a7beba41d62ec5"
}
],
"dirSha256": "f808d3f3630fe716d9de3440bc29ee7c567ed6358c7c6a9cefd38a0c34cb2218"
},
"security": {
"scannedAt": null,
"scannerVersion": null,
"flags": []
}
}

30
skills/docx/LICENSE.txt Normal file
View File

@@ -0,0 +1,30 @@
© 2025 Anthropic, PBC. All rights reserved.
LICENSE: Use of these materials (including all code, prompts, assets, files,
and other components of this Skill) is governed by your agreement with
Anthropic regarding use of Anthropic's services. If no separate agreement
exists, use is governed by Anthropic's Consumer Terms of Service or
Commercial Terms of Service, as applicable:
https://www.anthropic.com/legal/consumer-terms
https://www.anthropic.com/legal/commercial-terms
Your applicable agreement is referred to as the "Agreement." "Services" are
as defined in the Agreement.
ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the
contrary, users may not:
- Extract these materials from the Services or retain copies of these
materials outside the Services
- Reproduce or copy these materials, except for temporary copies created
automatically during authorized use of the Services
- Create derivative works based on these materials
- Distribute, sublicense, or transfer these materials to any third party
- Make, offer to sell, sell, or import any inventions embodied in these
materials
- Reverse engineer, decompile, or disassemble these materials
The receipt, viewing, or possession of these materials does not convey or
imply any license or right beyond those expressly granted above.
Anthropic retains all right, title, and interest in these materials,
including all copyrights, patents, and other intellectual property rights.

197
skills/docx/SKILL.md Normal file
View File

@@ -0,0 +1,197 @@
---
name: docx
description: "Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks"
license: Proprietary. LICENSE.txt has complete terms
---
# DOCX creation, editing, and analysis
## Overview
A user may ask you to create, edit, or analyze the contents of a .docx file. A .docx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks.
## Workflow Decision Tree
### Reading/Analyzing Content
Use "Text extraction" or "Raw XML access" sections below
### Creating New Document
Use "Creating a new Word document" workflow
### Editing Existing Document
- **Your own document + simple changes**
Use "Basic OOXML editing" workflow
- **Someone else's document**
Use **"Redlining workflow"** (recommended default)
- **Legal, academic, business, or government docs**
Use **"Redlining workflow"** (required)
## Reading and analyzing content
### Text extraction
If you just need to read the text contents of a document, you should convert the document to markdown using pandoc. Pandoc provides excellent support for preserving document structure and can show tracked changes:
```bash
# Convert document to markdown with tracked changes
pandoc --track-changes=all path-to-file.docx -o output.md
# Options: --track-changes=accept/reject/all
```
### Raw XML access
You need raw XML access for: comments, complex formatting, document structure, embedded media, and metadata. For any of these features, you'll need to unpack a document and read its raw XML contents.
#### Unpacking a file
`python ooxml/scripts/unpack.py <office_file> <output_directory>`
#### Key file structures
* `word/document.xml` - Main document contents
* `word/comments.xml` - Comments referenced in document.xml
* `word/media/` - Embedded images and media files
* Tracked changes use `<w:ins>` (insertions) and `<w:del>` (deletions) tags
## Creating a new Word document
When creating a new Word document from scratch, use **docx-js**, which allows you to create Word documents using JavaScript/TypeScript.
### Workflow
1. **MANDATORY - READ ENTIRE FILE**: Read [`docx-js.md`](docx-js.md) (~500 lines) completely from start to finish. **NEVER set any range limits when reading this file.** Read the full file content for detailed syntax, critical formatting rules, and best practices before proceeding with document creation.
2. Create a JavaScript/TypeScript file using Document, Paragraph, TextRun components (You can assume all dependencies are installed, but if not, refer to the dependencies section below)
3. Export as .docx using Packer.toBuffer()
## Editing an existing Word document
When editing an existing Word document, use the **Document library** (a Python library for OOXML manipulation). The library automatically handles infrastructure setup and provides methods for document manipulation. For complex scenarios, you can access the underlying DOM directly through the library.
### Workflow
1. **MANDATORY - READ ENTIRE FILE**: Read [`ooxml.md`](ooxml.md) (~600 lines) completely from start to finish. **NEVER set any range limits when reading this file.** Read the full file content for the Document library API and XML patterns for directly editing document files.
2. Unpack the document: `python ooxml/scripts/unpack.py <office_file> <output_directory>`
3. Create and run a Python script using the Document library (see "Document Library" section in ooxml.md)
4. Pack the final document: `python ooxml/scripts/pack.py <input_directory> <office_file>`
The Document library provides both high-level methods for common operations and direct DOM access for complex scenarios.
## Redlining workflow for document review
This workflow allows you to plan comprehensive tracked changes using markdown before implementing them in OOXML. **CRITICAL**: For complete tracked changes, you must implement ALL changes systematically.
**Batching Strategy**: Group related changes into batches of 3-10 changes. This makes debugging manageable while maintaining efficiency. Test each batch before moving to the next.
**Principle: Minimal, Precise Edits**
When implementing tracked changes, only mark text that actually changes. Repeating unchanged text makes edits harder to review and appears unprofessional. Break replacements into: [unchanged text] + [deletion] + [insertion] + [unchanged text]. Preserve the original run's RSID for unchanged text by extracting the `<w:r>` element from the original and reusing it.
Example - Changing "30 days" to "60 days" in a sentence:
```python
# BAD - Replaces entire sentence
'<w:del><w:r><w:delText>The term is 30 days.</w:delText></w:r></w:del><w:ins><w:r><w:t>The term is 60 days.</w:t></w:r></w:ins>'
# GOOD - Only marks what changed, preserves original <w:r> for unchanged text
'<w:r w:rsidR="00AB12CD"><w:t>The term is </w:t></w:r><w:del><w:r><w:delText>30</w:delText></w:r></w:del><w:ins><w:r><w:t>60</w:t></w:r></w:ins><w:r w:rsidR="00AB12CD"><w:t> days.</w:t></w:r>'
```
### Tracked changes workflow
1. **Get markdown representation**: Convert document to markdown with tracked changes preserved:
```bash
pandoc --track-changes=all path-to-file.docx -o current.md
```
2. **Identify and group changes**: Review the document and identify ALL changes needed, organizing them into logical batches:
**Location methods** (for finding changes in XML):
- Section/heading numbers (e.g., "Section 3.2", "Article IV")
- Paragraph identifiers if numbered
- Grep patterns with unique surrounding text
- Document structure (e.g., "first paragraph", "signature block")
- **DO NOT use markdown line numbers** - they don't map to XML structure
**Batch organization** (group 3-10 related changes per batch):
- By section: "Batch 1: Section 2 amendments", "Batch 2: Section 5 updates"
- By type: "Batch 1: Date corrections", "Batch 2: Party name changes"
- By complexity: Start with simple text replacements, then tackle complex structural changes
- Sequential: "Batch 1: Pages 1-3", "Batch 2: Pages 4-6"
3. **Read documentation and unpack**:
- **MANDATORY - READ ENTIRE FILE**: Read [`ooxml.md`](ooxml.md) (~600 lines) completely from start to finish. **NEVER set any range limits when reading this file.** Pay special attention to the "Document Library" and "Tracked Change Patterns" sections.
- **Unpack the document**: `python ooxml/scripts/unpack.py <file.docx> <dir>`
- **Note the suggested RSID**: The unpack script will suggest an RSID to use for your tracked changes. Copy this RSID for use in step 4b.
4. **Implement changes in batches**: Group changes logically (by section, by type, or by proximity) and implement them together in a single script. This approach:
- Makes debugging easier (smaller batch = easier to isolate errors)
- Allows incremental progress
- Maintains efficiency (batch size of 3-10 changes works well)
**Suggested batch groupings:**
- By document section (e.g., "Section 3 changes", "Definitions", "Termination clause")
- By change type (e.g., "Date changes", "Party name updates", "Legal term replacements")
- By proximity (e.g., "Changes on pages 1-3", "Changes in first half of document")
For each batch of related changes:
**a. Map text to XML**: Grep for text in `word/document.xml` to verify how text is split across `<w:r>` elements.
**b. Create and run script**: Use `get_node` to find nodes, implement changes, then `doc.save()`. See **"Document Library"** section in ooxml.md for patterns.
**Note**: Always grep `word/document.xml` immediately before writing a script to get current line numbers and verify text content. Line numbers change after each script run.
5. **Pack the document**: After all batches are complete, convert the unpacked directory back to .docx:
```bash
python ooxml/scripts/pack.py unpacked reviewed-document.docx
```
6. **Final verification**: Do a comprehensive check of the complete document:
- Convert final document to markdown:
```bash
pandoc --track-changes=all reviewed-document.docx -o verification.md
```
- Verify ALL changes were applied correctly:
```bash
grep "original phrase" verification.md # Should NOT find it
grep "replacement phrase" verification.md # Should find it
```
- Check that no unintended changes were introduced
## Converting Documents to Images
To visually analyze Word documents, convert them to images using a two-step process:
1. **Convert DOCX to PDF**:
```bash
soffice --headless --convert-to pdf document.docx
```
2. **Convert PDF pages to JPEG images**:
```bash
pdftoppm -jpeg -r 150 document.pdf page
```
This creates files like `page-1.jpg`, `page-2.jpg`, etc.
Options:
- `-r 150`: Sets resolution to 150 DPI (adjust for quality/size balance)
- `-jpeg`: Output JPEG format (use `-png` for PNG if preferred)
- `-f N`: First page to convert (e.g., `-f 2` starts from page 2)
- `-l N`: Last page to convert (e.g., `-l 5` stops at page 5)
- `page`: Prefix for output files
Example for specific range:
```bash
pdftoppm -jpeg -r 150 -f 2 -l 5 document.pdf page # Converts only pages 2-5
```
## Code Style Guidelines
**IMPORTANT**: When generating code for DOCX operations:
- Write concise code
- Avoid verbose variable names and redundant operations
- Avoid unnecessary print statements
## Dependencies
Required dependencies (install if not available):
- **pandoc**: `sudo apt-get install pandoc` (for text extraction)
- **docx**: `npm install -g docx` (for creating new documents)
- **LibreOffice**: `sudo apt-get install libreoffice` (for PDF conversion)
- **Poppler**: `sudo apt-get install poppler-utils` (for pdftoppm to convert PDF to images)
- **defusedxml**: `pip install defusedxml` (for secure XML parsing)

350
skills/docx/docx-js.md Normal file
View File

@@ -0,0 +1,350 @@
# DOCX Library Tutorial
Generate .docx files with JavaScript/TypeScript.
**Important: Read this entire document before starting.** Critical formatting rules and common pitfalls are covered throughout - skipping sections may result in corrupted files or rendering issues.
## Setup
Assumes docx is already installed globally
If not installed: `npm install -g docx`
```javascript
const { Document, Packer, Paragraph, TextRun, Table, TableRow, TableCell, ImageRun, Media,
Header, Footer, AlignmentType, PageOrientation, LevelFormat, ExternalHyperlink,
InternalHyperlink, TableOfContents, HeadingLevel, BorderStyle, WidthType, TabStopType,
TabStopPosition, UnderlineType, ShadingType, VerticalAlign, SymbolRun, PageNumber,
FootnoteReferenceRun, Footnote, PageBreak } = require('docx');
// Create & Save
const doc = new Document({ sections: [{ children: [/* content */] }] });
Packer.toBuffer(doc).then(buffer => fs.writeFileSync("doc.docx", buffer)); // Node.js
Packer.toBlob(doc).then(blob => { /* download logic */ }); // Browser
```
## Text & Formatting
```javascript
// IMPORTANT: Never use \n for line breaks - always use separate Paragraph elements
// ❌ WRONG: new TextRun("Line 1\nLine 2")
// ✅ CORRECT: new Paragraph({ children: [new TextRun("Line 1")] }), new Paragraph({ children: [new TextRun("Line 2")] })
// Basic text with all formatting options
new Paragraph({
alignment: AlignmentType.CENTER,
spacing: { before: 200, after: 200 },
indent: { left: 720, right: 720 },
children: [
new TextRun({ text: "Bold", bold: true }),
new TextRun({ text: "Italic", italics: true }),
new TextRun({ text: "Underlined", underline: { type: UnderlineType.DOUBLE, color: "FF0000" } }),
new TextRun({ text: "Colored", color: "FF0000", size: 28, font: "Arial" }), // Arial default
new TextRun({ text: "Highlighted", highlight: "yellow" }),
new TextRun({ text: "Strikethrough", strike: true }),
new TextRun({ text: "x2", superScript: true }),
new TextRun({ text: "H2O", subScript: true }),
new TextRun({ text: "SMALL CAPS", smallCaps: true }),
new SymbolRun({ char: "2022", font: "Symbol" }), // Bullet •
new SymbolRun({ char: "00A9", font: "Arial" }) // Copyright © - Arial for symbols
]
})
```
## Styles & Professional Formatting
```javascript
const doc = new Document({
styles: {
default: { document: { run: { font: "Arial", size: 24 } } }, // 12pt default
paragraphStyles: [
// Document title style - override built-in Title style
{ id: "Title", name: "Title", basedOn: "Normal",
run: { size: 56, bold: true, color: "000000", font: "Arial" },
paragraph: { spacing: { before: 240, after: 120 }, alignment: AlignmentType.CENTER } },
// IMPORTANT: Override built-in heading styles by using their exact IDs
{ id: "Heading1", name: "Heading 1", basedOn: "Normal", next: "Normal", quickFormat: true,
run: { size: 32, bold: true, color: "000000", font: "Arial" }, // 16pt
paragraph: { spacing: { before: 240, after: 240 }, outlineLevel: 0 } }, // Required for TOC
{ id: "Heading2", name: "Heading 2", basedOn: "Normal", next: "Normal", quickFormat: true,
run: { size: 28, bold: true, color: "000000", font: "Arial" }, // 14pt
paragraph: { spacing: { before: 180, after: 180 }, outlineLevel: 1 } },
// Custom styles use your own IDs
{ id: "myStyle", name: "My Style", basedOn: "Normal",
run: { size: 28, bold: true, color: "000000" },
paragraph: { spacing: { after: 120 }, alignment: AlignmentType.CENTER } }
],
characterStyles: [{ id: "myCharStyle", name: "My Char Style",
run: { color: "FF0000", bold: true, underline: { type: UnderlineType.SINGLE } } }]
},
sections: [{
properties: { page: { margin: { top: 1440, right: 1440, bottom: 1440, left: 1440 } } },
children: [
new Paragraph({ heading: HeadingLevel.TITLE, children: [new TextRun("Document Title")] }), // Uses overridden Title style
new Paragraph({ heading: HeadingLevel.HEADING_1, children: [new TextRun("Heading 1")] }), // Uses overridden Heading1 style
new Paragraph({ style: "myStyle", children: [new TextRun("Custom paragraph style")] }),
new Paragraph({ children: [
new TextRun("Normal with "),
new TextRun({ text: "custom char style", style: "myCharStyle" })
]})
]
}]
});
```
**Professional Font Combinations:**
- **Arial (Headers) + Arial (Body)** - Most universally supported, clean and professional
- **Times New Roman (Headers) + Arial (Body)** - Classic serif headers with modern sans-serif body
- **Georgia (Headers) + Verdana (Body)** - Optimized for screen reading, elegant contrast
**Key Styling Principles:**
- **Override built-in styles**: Use exact IDs like "Heading1", "Heading2", "Heading3" to override Word's built-in heading styles
- **HeadingLevel constants**: `HeadingLevel.HEADING_1` uses "Heading1" style, `HeadingLevel.HEADING_2` uses "Heading2" style, etc.
- **Include outlineLevel**: Set `outlineLevel: 0` for H1, `outlineLevel: 1` for H2, etc. to ensure TOC works correctly
- **Use custom styles** instead of inline formatting for consistency
- **Set a default font** using `styles.default.document.run.font` - Arial is universally supported
- **Establish visual hierarchy** with different font sizes (titles > headers > body)
- **Add proper spacing** with `before` and `after` paragraph spacing
- **Use colors sparingly**: Default to black (000000) and shades of gray for titles and headings (heading 1, heading 2, etc.)
- **Set consistent margins** (1440 = 1 inch is standard)
## Lists (ALWAYS USE PROPER LISTS - NEVER USE UNICODE BULLETS)
```javascript
// Bullets - ALWAYS use the numbering config, NOT unicode symbols
// CRITICAL: Use LevelFormat.BULLET constant, NOT the string "bullet"
const doc = new Document({
numbering: {
config: [
{ reference: "bullet-list",
levels: [{ level: 0, format: LevelFormat.BULLET, text: "•", alignment: AlignmentType.LEFT,
style: { paragraph: { indent: { left: 720, hanging: 360 } } } }] },
{ reference: "first-numbered-list",
levels: [{ level: 0, format: LevelFormat.DECIMAL, text: "%1.", alignment: AlignmentType.LEFT,
style: { paragraph: { indent: { left: 720, hanging: 360 } } } }] },
{ reference: "second-numbered-list", // Different reference = restarts at 1
levels: [{ level: 0, format: LevelFormat.DECIMAL, text: "%1.", alignment: AlignmentType.LEFT,
style: { paragraph: { indent: { left: 720, hanging: 360 } } } }] }
]
},
sections: [{
children: [
// Bullet list items
new Paragraph({ numbering: { reference: "bullet-list", level: 0 },
children: [new TextRun("First bullet point")] }),
new Paragraph({ numbering: { reference: "bullet-list", level: 0 },
children: [new TextRun("Second bullet point")] }),
// Numbered list items
new Paragraph({ numbering: { reference: "first-numbered-list", level: 0 },
children: [new TextRun("First numbered item")] }),
new Paragraph({ numbering: { reference: "first-numbered-list", level: 0 },
children: [new TextRun("Second numbered item")] }),
// ⚠️ CRITICAL: Different reference = INDEPENDENT list that restarts at 1
// Same reference = CONTINUES previous numbering
new Paragraph({ numbering: { reference: "second-numbered-list", level: 0 },
children: [new TextRun("Starts at 1 again (because different reference)")] })
]
}]
});
// ⚠️ CRITICAL NUMBERING RULE: Each reference creates an INDEPENDENT numbered list
// - Same reference = continues numbering (1, 2, 3... then 4, 5, 6...)
// - Different reference = restarts at 1 (1, 2, 3... then 1, 2, 3...)
// Use unique reference names for each separate numbered section!
// ⚠️ CRITICAL: NEVER use unicode bullets - they create fake lists that don't work properly
// new TextRun("• Item") // WRONG
// new SymbolRun({ char: "2022" }) // WRONG
// ✅ ALWAYS use numbering config with LevelFormat.BULLET for real Word lists
```
## Tables
```javascript
// Complete table with margins, borders, headers, and bullet points
const tableBorder = { style: BorderStyle.SINGLE, size: 1, color: "CCCCCC" };
const cellBorders = { top: tableBorder, bottom: tableBorder, left: tableBorder, right: tableBorder };
new Table({
columnWidths: [4680, 4680], // ⚠️ CRITICAL: Set column widths at table level - values in DXA (twentieths of a point)
margins: { top: 100, bottom: 100, left: 180, right: 180 }, // Set once for all cells
rows: [
new TableRow({
tableHeader: true,
children: [
new TableCell({
borders: cellBorders,
width: { size: 4680, type: WidthType.DXA }, // ALSO set width on each cell
// ⚠️ CRITICAL: Always use ShadingType.CLEAR to prevent black backgrounds in Word.
shading: { fill: "D5E8F0", type: ShadingType.CLEAR },
verticalAlign: VerticalAlign.CENTER,
children: [new Paragraph({
alignment: AlignmentType.CENTER,
children: [new TextRun({ text: "Header", bold: true, size: 22 })]
})]
}),
new TableCell({
borders: cellBorders,
width: { size: 4680, type: WidthType.DXA }, // ALSO set width on each cell
shading: { fill: "D5E8F0", type: ShadingType.CLEAR },
children: [new Paragraph({
alignment: AlignmentType.CENTER,
children: [new TextRun({ text: "Bullet Points", bold: true, size: 22 })]
})]
})
]
}),
new TableRow({
children: [
new TableCell({
borders: cellBorders,
width: { size: 4680, type: WidthType.DXA }, // ALSO set width on each cell
children: [new Paragraph({ children: [new TextRun("Regular data")] })]
}),
new TableCell({
borders: cellBorders,
width: { size: 4680, type: WidthType.DXA }, // ALSO set width on each cell
children: [
new Paragraph({
numbering: { reference: "bullet-list", level: 0 },
children: [new TextRun("First bullet point")]
}),
new Paragraph({
numbering: { reference: "bullet-list", level: 0 },
children: [new TextRun("Second bullet point")]
})
]
})
]
})
]
})
```
**IMPORTANT: Table Width & Borders**
- Use BOTH `columnWidths: [width1, width2, ...]` array AND `width: { size: X, type: WidthType.DXA }` on each cell
- Values in DXA (twentieths of a point): 1440 = 1 inch, Letter usable width = 9360 DXA (with 1" margins)
- Apply borders to individual `TableCell` elements, NOT the `Table` itself
**Precomputed Column Widths (Letter size with 1" margins = 9360 DXA total):**
- **2 columns:** `columnWidths: [4680, 4680]` (equal width)
- **3 columns:** `columnWidths: [3120, 3120, 3120]` (equal width)
## Links & Navigation
```javascript
// TOC (requires headings) - CRITICAL: Use HeadingLevel only, NOT custom styles
// ❌ WRONG: new Paragraph({ heading: HeadingLevel.HEADING_1, style: "customHeader", children: [new TextRun("Title")] })
// ✅ CORRECT: new Paragraph({ heading: HeadingLevel.HEADING_1, children: [new TextRun("Title")] })
new TableOfContents("Table of Contents", { hyperlink: true, headingStyleRange: "1-3" }),
// External link
new Paragraph({
children: [new ExternalHyperlink({
children: [new TextRun({ text: "Google", style: "Hyperlink" })],
link: "https://www.google.com"
})]
}),
// Internal link & bookmark
new Paragraph({
children: [new InternalHyperlink({
children: [new TextRun({ text: "Go to Section", style: "Hyperlink" })],
anchor: "section1"
})]
}),
new Paragraph({
children: [new TextRun("Section Content")],
bookmark: { id: "section1", name: "section1" }
}),
```
## Images & Media
```javascript
// Basic image with sizing & positioning
// CRITICAL: Always specify 'type' parameter - it's REQUIRED for ImageRun
new Paragraph({
alignment: AlignmentType.CENTER,
children: [new ImageRun({
type: "png", // NEW REQUIREMENT: Must specify image type (png, jpg, jpeg, gif, bmp, svg)
data: fs.readFileSync("image.png"),
transformation: { width: 200, height: 150, rotation: 0 }, // rotation in degrees
altText: { title: "Logo", description: "Company logo", name: "Name" } // IMPORTANT: All three fields are required
})]
})
```
## Page Breaks
```javascript
// Manual page break
new Paragraph({ children: [new PageBreak()] }),
// Page break before paragraph
new Paragraph({
pageBreakBefore: true,
children: [new TextRun("This starts on a new page")]
})
// ⚠️ CRITICAL: NEVER use PageBreak standalone - it will create invalid XML that Word cannot open
// ❌ WRONG: new PageBreak()
// ✅ CORRECT: new Paragraph({ children: [new PageBreak()] })
```
## Headers/Footers & Page Setup
```javascript
const doc = new Document({
sections: [{
properties: {
page: {
margin: { top: 1440, right: 1440, bottom: 1440, left: 1440 }, // 1440 = 1 inch
size: { orientation: PageOrientation.LANDSCAPE },
pageNumbers: { start: 1, formatType: "decimal" } // "upperRoman", "lowerRoman", "upperLetter", "lowerLetter"
}
},
headers: {
default: new Header({ children: [new Paragraph({
alignment: AlignmentType.RIGHT,
children: [new TextRun("Header Text")]
})] })
},
footers: {
default: new Footer({ children: [new Paragraph({
alignment: AlignmentType.CENTER,
children: [new TextRun("Page "), new TextRun({ children: [PageNumber.CURRENT] }), new TextRun(" of "), new TextRun({ children: [PageNumber.TOTAL_PAGES] })]
})] })
},
children: [/* content */]
}]
});
```
## Tabs
```javascript
new Paragraph({
tabStops: [
{ type: TabStopType.LEFT, position: TabStopPosition.MAX / 4 },
{ type: TabStopType.CENTER, position: TabStopPosition.MAX / 2 },
{ type: TabStopType.RIGHT, position: TabStopPosition.MAX * 3 / 4 }
],
children: [new TextRun("Left\tCenter\tRight")]
})
```
## Constants & Quick Reference
- **Underlines:** `SINGLE`, `DOUBLE`, `WAVY`, `DASH`
- **Borders:** `SINGLE`, `DOUBLE`, `DASHED`, `DOTTED`
- **Numbering:** `DECIMAL` (1,2,3), `UPPER_ROMAN` (I,II,III), `LOWER_LETTER` (a,b,c)
- **Tabs:** `LEFT`, `CENTER`, `RIGHT`, `DECIMAL`
- **Symbols:** `"2022"` (•), `"00A9"` (©), `"00AE"` (®), `"2122"` (™), `"00B0"` (°), `"F070"` (✓), `"F0FC"` (✗)
## Critical Issues & Common Mistakes
- **CRITICAL: PageBreak must ALWAYS be inside a Paragraph** - standalone PageBreak creates invalid XML that Word cannot open
- **ALWAYS use ShadingType.CLEAR for table cell shading** - Never use ShadingType.SOLID (causes black background).
- Measurements in DXA (1440 = 1 inch) | Each table cell needs ≥1 Paragraph | TOC requires HeadingLevel styles only
- **ALWAYS use custom styles** with Arial font for professional appearance and proper visual hierarchy
- **ALWAYS set a default font** using `styles.default.document.run.font` - Arial recommended
- **ALWAYS use columnWidths array for tables** + individual cell widths for compatibility
- **NEVER use unicode symbols for bullets** - always use proper numbering configuration with `LevelFormat.BULLET` constant (NOT the string "bullet")
- **NEVER use \n for line breaks anywhere** - always use separate Paragraph elements for each line
- **ALWAYS use TextRun objects within Paragraph children** - never use text property directly on Paragraph
- **CRITICAL for images**: ImageRun REQUIRES `type` parameter - always specify "png", "jpg", "jpeg", "gif", "bmp", or "svg"
- **CRITICAL for bullets**: Must use `LevelFormat.BULLET` constant, not string "bullet", and include `text: "•"` for the bullet character
- **CRITICAL for numbering**: Each numbering reference creates an INDEPENDENT list. Same reference = continues numbering (1,2,3 then 4,5,6). Different reference = restarts at 1 (1,2,3 then 1,2,3). Use unique reference names for each separate numbered section!
- **CRITICAL for TOC**: When using TableOfContents, headings must use HeadingLevel ONLY - do NOT add custom styles to heading paragraphs or TOC will break
- **Tables**: Set `columnWidths` array + individual cell widths, apply borders to cells not table
- **Set table margins at TABLE level** for consistent cell padding (avoids repetition per cell)

610
skills/docx/ooxml.md Normal file
View File

@@ -0,0 +1,610 @@
# Office Open XML Technical Reference
**Important: Read this entire document before starting.** This document covers:
- [Technical Guidelines](#technical-guidelines) - Schema compliance rules and validation requirements
- [Document Content Patterns](#document-content-patterns) - XML patterns for headings, lists, tables, formatting, etc.
- [Document Library (Python)](#document-library-python) - Recommended approach for OOXML manipulation with automatic infrastructure setup
- [Tracked Changes (Redlining)](#tracked-changes-redlining) - XML patterns for implementing tracked changes
## Technical Guidelines
### Schema Compliance
- **Element ordering in `<w:pPr>`**: `<w:pStyle>`, `<w:numPr>`, `<w:spacing>`, `<w:ind>`, `<w:jc>`
- **Whitespace**: Add `xml:space='preserve'` to `<w:t>` elements with leading/trailing spaces
- **Unicode**: Escape characters in ASCII content: `"` becomes `&#8220;`
- **Character encoding reference**: Curly quotes `""` become `&#8220;&#8221;`, apostrophe `'` becomes `&#8217;`, em-dash `—` becomes `&#8212;`
- **Tracked changes**: Use `<w:del>` and `<w:ins>` tags with `w:author="Claude"` outside `<w:r>` elements
- **Critical**: `<w:ins>` closes with `</w:ins>`, `<w:del>` closes with `</w:del>` - never mix
- **RSIDs must be 8-digit hex**: Use values like `00AB1234` (only 0-9, A-F characters)
- **trackRevisions placement**: Add `<w:trackRevisions/>` after `<w:proofState>` in settings.xml
- **Images**: Add to `word/media/`, reference in `document.xml`, set dimensions to prevent overflow
## Document Content Patterns
### Basic Structure
```xml
<w:p>
<w:r><w:t>Text content</w:t></w:r>
</w:p>
```
### Headings and Styles
```xml
<w:p>
<w:pPr>
<w:pStyle w:val="Title"/>
<w:jc w:val="center"/>
</w:pPr>
<w:r><w:t>Document Title</w:t></w:r>
</w:p>
<w:p>
<w:pPr><w:pStyle w:val="Heading2"/></w:pPr>
<w:r><w:t>Section Heading</w:t></w:r>
</w:p>
```
### Text Formatting
```xml
<!-- Bold -->
<w:r><w:rPr><w:b/><w:bCs/></w:rPr><w:t>Bold</w:t></w:r>
<!-- Italic -->
<w:r><w:rPr><w:i/><w:iCs/></w:rPr><w:t>Italic</w:t></w:r>
<!-- Underline -->
<w:r><w:rPr><w:u w:val="single"/></w:rPr><w:t>Underlined</w:t></w:r>
<!-- Highlight -->
<w:r><w:rPr><w:highlight w:val="yellow"/></w:rPr><w:t>Highlighted</w:t></w:r>
```
### Lists
```xml
<!-- Numbered list -->
<w:p>
<w:pPr>
<w:pStyle w:val="ListParagraph"/>
<w:numPr><w:ilvl w:val="0"/><w:numId w:val="1"/></w:numPr>
<w:spacing w:before="240"/>
</w:pPr>
<w:r><w:t>First item</w:t></w:r>
</w:p>
<!-- Restart numbered list at 1 - use different numId -->
<w:p>
<w:pPr>
<w:pStyle w:val="ListParagraph"/>
<w:numPr><w:ilvl w:val="0"/><w:numId w:val="2"/></w:numPr>
<w:spacing w:before="240"/>
</w:pPr>
<w:r><w:t>New list item 1</w:t></w:r>
</w:p>
<!-- Bullet list (level 2) -->
<w:p>
<w:pPr>
<w:pStyle w:val="ListParagraph"/>
<w:numPr><w:ilvl w:val="1"/><w:numId w:val="1"/></w:numPr>
<w:spacing w:before="240"/>
<w:ind w:left="900"/>
</w:pPr>
<w:r><w:t>Bullet item</w:t></w:r>
</w:p>
```
### Tables
```xml
<w:tbl>
<w:tblPr>
<w:tblStyle w:val="TableGrid"/>
<w:tblW w:w="0" w:type="auto"/>
</w:tblPr>
<w:tblGrid>
<w:gridCol w:w="4675"/><w:gridCol w:w="4675"/>
</w:tblGrid>
<w:tr>
<w:tc>
<w:tcPr><w:tcW w:w="4675" w:type="dxa"/></w:tcPr>
<w:p><w:r><w:t>Cell 1</w:t></w:r></w:p>
</w:tc>
<w:tc>
<w:tcPr><w:tcW w:w="4675" w:type="dxa"/></w:tcPr>
<w:p><w:r><w:t>Cell 2</w:t></w:r></w:p>
</w:tc>
</w:tr>
</w:tbl>
```
### Layout
```xml
<!-- Page break before new section (common pattern) -->
<w:p>
<w:r>
<w:br w:type="page"/>
</w:r>
</w:p>
<w:p>
<w:pPr>
<w:pStyle w:val="Heading1"/>
</w:pPr>
<w:r>
<w:t>New Section Title</w:t>
</w:r>
</w:p>
<!-- Centered paragraph -->
<w:p>
<w:pPr>
<w:spacing w:before="240" w:after="0"/>
<w:jc w:val="center"/>
</w:pPr>
<w:r><w:t>Centered text</w:t></w:r>
</w:p>
<!-- Font change - paragraph level (applies to all runs) -->
<w:p>
<w:pPr>
<w:rPr><w:rFonts w:ascii="Courier New" w:hAnsi="Courier New"/></w:rPr>
</w:pPr>
<w:r><w:t>Monospace text</w:t></w:r>
</w:p>
<!-- Font change - run level (specific to this text) -->
<w:p>
<w:r>
<w:rPr><w:rFonts w:ascii="Courier New" w:hAnsi="Courier New"/></w:rPr>
<w:t>This text is Courier New</w:t>
</w:r>
<w:r><w:t> and this text uses default font</w:t></w:r>
</w:p>
```
## File Updates
When adding content, update these files:
**`word/_rels/document.xml.rels`:**
```xml
<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/numbering" Target="numbering.xml"/>
<Relationship Id="rId5" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/image" Target="media/image1.png"/>
```
**`[Content_Types].xml`:**
```xml
<Default Extension="png" ContentType="image/png"/>
<Override PartName="/word/numbering.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.numbering+xml"/>
```
### Images
**CRITICAL**: Calculate dimensions to prevent page overflow and maintain aspect ratio.
```xml
<!-- Minimal required structure -->
<w:p>
<w:r>
<w:drawing>
<wp:inline>
<wp:extent cx="2743200" cy="1828800"/>
<wp:docPr id="1" name="Picture 1"/>
<a:graphic xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main">
<a:graphicData uri="http://schemas.openxmlformats.org/drawingml/2006/picture">
<pic:pic xmlns:pic="http://schemas.openxmlformats.org/drawingml/2006/picture">
<pic:nvPicPr>
<pic:cNvPr id="0" name="image1.png"/>
<pic:cNvPicPr/>
</pic:nvPicPr>
<pic:blipFill>
<a:blip r:embed="rId5"/>
<!-- Add for stretch fill with aspect ratio preservation -->
<a:stretch>
<a:fillRect/>
</a:stretch>
</pic:blipFill>
<pic:spPr>
<a:xfrm>
<a:ext cx="2743200" cy="1828800"/>
</a:xfrm>
<a:prstGeom prst="rect"/>
</pic:spPr>
</pic:pic>
</a:graphicData>
</a:graphic>
</wp:inline>
</w:drawing>
</w:r>
</w:p>
```
### Links (Hyperlinks)
**IMPORTANT**: All hyperlinks (both internal and external) require the Hyperlink style to be defined in styles.xml. Without this style, links will look like regular text instead of blue underlined clickable links.
**External Links:**
```xml
<!-- In document.xml -->
<w:hyperlink r:id="rId5">
<w:r>
<w:rPr><w:rStyle w:val="Hyperlink"/></w:rPr>
<w:t>Link Text</w:t>
</w:r>
</w:hyperlink>
<!-- In word/_rels/document.xml.rels -->
<Relationship Id="rId5" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/hyperlink"
Target="https://www.example.com/" TargetMode="External"/>
```
**Internal Links:**
```xml
<!-- Link to bookmark -->
<w:hyperlink w:anchor="myBookmark">
<w:r>
<w:rPr><w:rStyle w:val="Hyperlink"/></w:rPr>
<w:t>Link Text</w:t>
</w:r>
</w:hyperlink>
<!-- Bookmark target -->
<w:bookmarkStart w:id="0" w:name="myBookmark"/>
<w:r><w:t>Target content</w:t></w:r>
<w:bookmarkEnd w:id="0"/>
```
**Hyperlink Style (required in styles.xml):**
```xml
<w:style w:type="character" w:styleId="Hyperlink">
<w:name w:val="Hyperlink"/>
<w:basedOn w:val="DefaultParagraphFont"/>
<w:uiPriority w:val="99"/>
<w:unhideWhenUsed/>
<w:rPr>
<w:color w:val="467886" w:themeColor="hyperlink"/>
<w:u w:val="single"/>
</w:rPr>
</w:style>
```
## Document Library (Python)
Use the Document class from `scripts/document.py` for all tracked changes and comments. It automatically handles infrastructure setup (people.xml, RSIDs, settings.xml, comment files, relationships, content types). Only use direct XML manipulation for complex scenarios not supported by the library.
**Working with Unicode and Entities:**
- **Searching**: Both entity notation and Unicode characters work - `contains="&#8220;Company"` and `contains="\u201cCompany"` find the same text
- **Replacing**: Use either entities (`&#8220;`) or Unicode (`\u201c`) - both work and will be converted appropriately based on the file's encoding (ascii → entities, utf-8 → Unicode)
### Initialization
**Find the docx skill root** (directory containing `scripts/` and `ooxml/`):
```bash
# Search for document.py to locate the skill root
# Note: /mnt/skills is used here as an example; check your context for the actual location
find /mnt/skills -name "document.py" -path "*/docx/scripts/*" 2>/dev/null | head -1
# Example output: /mnt/skills/docx/scripts/document.py
# Skill root is: /mnt/skills/docx
```
**Run your script with PYTHONPATH** set to the docx skill root:
```bash
PYTHONPATH=/mnt/skills/docx python your_script.py
```
**In your script**, import from the skill root:
```python
from scripts.document import Document, DocxXMLEditor
# Basic initialization (automatically creates temp copy and sets up infrastructure)
doc = Document('unpacked')
# Customize author and initials
doc = Document('unpacked', author="John Doe", initials="JD")
# Enable track revisions mode
doc = Document('unpacked', track_revisions=True)
# Specify custom RSID (auto-generated if not provided)
doc = Document('unpacked', rsid="07DC5ECB")
```
### Creating Tracked Changes
**CRITICAL**: Only mark text that actually changes. Keep ALL unchanged text outside `<w:del>`/`<w:ins>` tags. Marking unchanged text makes edits unprofessional and harder to review.
**Attribute Handling**: The Document class auto-injects attributes (w:id, w:date, w:rsidR, w:rsidDel, w16du:dateUtc, xml:space) into new elements. When preserving unchanged text from the original document, copy the original `<w:r>` element with its existing attributes to maintain document integrity.
**Method Selection Guide**:
- **Adding your own changes to regular text**: Use `replace_node()` with `<w:del>`/`<w:ins>` tags, or `suggest_deletion()` for removing entire `<w:r>` or `<w:p>` elements
- **Partially modifying another author's tracked change**: Use `replace_node()` to nest your changes inside their `<w:ins>`/`<w:del>`
- **Completely rejecting another author's insertion**: Use `revert_insertion()` on the `<w:ins>` element (NOT `suggest_deletion()`)
- **Completely rejecting another author's deletion**: Use `revert_deletion()` on the `<w:del>` element to restore deleted content using tracked changes
```python
# Minimal edit - change one word: "The report is monthly" → "The report is quarterly"
# Original: <w:r w:rsidR="00AB12CD"><w:rPr><w:rFonts w:ascii="Calibri"/></w:rPr><w:t>The report is monthly</w:t></w:r>
node = doc["word/document.xml"].get_node(tag="w:r", contains="The report is monthly")
rpr = tags[0].toxml() if (tags := node.getElementsByTagName("w:rPr")) else ""
replacement = f'<w:r w:rsidR="00AB12CD">{rpr}<w:t>The report is </w:t></w:r><w:del><w:r>{rpr}<w:delText>monthly</w:delText></w:r></w:del><w:ins><w:r>{rpr}<w:t>quarterly</w:t></w:r></w:ins>'
doc["word/document.xml"].replace_node(node, replacement)
# Minimal edit - change number: "within 30 days" → "within 45 days"
# Original: <w:r w:rsidR="00XYZ789"><w:rPr><w:rFonts w:ascii="Calibri"/></w:rPr><w:t>within 30 days</w:t></w:r>
node = doc["word/document.xml"].get_node(tag="w:r", contains="within 30 days")
rpr = tags[0].toxml() if (tags := node.getElementsByTagName("w:rPr")) else ""
replacement = f'<w:r w:rsidR="00XYZ789">{rpr}<w:t>within </w:t></w:r><w:del><w:r>{rpr}<w:delText>30</w:delText></w:r></w:del><w:ins><w:r>{rpr}<w:t>45</w:t></w:r></w:ins><w:r w:rsidR="00XYZ789">{rpr}<w:t> days</w:t></w:r>'
doc["word/document.xml"].replace_node(node, replacement)
# Complete replacement - preserve formatting even when replacing all text
node = doc["word/document.xml"].get_node(tag="w:r", contains="apple")
rpr = tags[0].toxml() if (tags := node.getElementsByTagName("w:rPr")) else ""
replacement = f'<w:del><w:r>{rpr}<w:delText>apple</w:delText></w:r></w:del><w:ins><w:r>{rpr}<w:t>banana orange</w:t></w:r></w:ins>'
doc["word/document.xml"].replace_node(node, replacement)
# Insert new content (no attributes needed - auto-injected)
node = doc["word/document.xml"].get_node(tag="w:r", contains="existing text")
doc["word/document.xml"].insert_after(node, '<w:ins><w:r><w:t>new text</w:t></w:r></w:ins>')
# Partially delete another author's insertion
# Original: <w:ins w:author="Jane Smith" w:date="..."><w:r><w:t>quarterly financial report</w:t></w:r></w:ins>
# Goal: Delete only "financial" to make it "quarterly report"
node = doc["word/document.xml"].get_node(tag="w:ins", attrs={"w:id": "5"})
# IMPORTANT: Preserve w:author="Jane Smith" on the outer <w:ins> to maintain authorship
replacement = '''<w:ins w:author="Jane Smith" w:date="2025-01-15T10:00:00Z">
<w:r><w:t>quarterly </w:t></w:r>
<w:del><w:r><w:delText>financial </w:delText></w:r></w:del>
<w:r><w:t>report</w:t></w:r>
</w:ins>'''
doc["word/document.xml"].replace_node(node, replacement)
# Change part of another author's insertion
# Original: <w:ins w:author="Jane Smith"><w:r><w:t>in silence, safe and sound</w:t></w:r></w:ins>
# Goal: Change "safe and sound" to "soft and unbound"
node = doc["word/document.xml"].get_node(tag="w:ins", attrs={"w:id": "8"})
replacement = f'''<w:ins w:author="Jane Smith" w:date="2025-01-15T10:00:00Z">
<w:r><w:t>in silence, </w:t></w:r>
</w:ins>
<w:ins>
<w:r><w:t>soft and unbound</w:t></w:r>
</w:ins>
<w:ins w:author="Jane Smith" w:date="2025-01-15T10:00:00Z">
<w:del><w:r><w:delText>safe and sound</w:delText></w:r></w:del>
</w:ins>'''
doc["word/document.xml"].replace_node(node, replacement)
# Delete entire run (use only when deleting all content; use replace_node for partial deletions)
node = doc["word/document.xml"].get_node(tag="w:r", contains="text to delete")
doc["word/document.xml"].suggest_deletion(node)
# Delete entire paragraph (in-place, handles both regular and numbered list paragraphs)
para = doc["word/document.xml"].get_node(tag="w:p", contains="paragraph to delete")
doc["word/document.xml"].suggest_deletion(para)
# Add new numbered list item
target_para = doc["word/document.xml"].get_node(tag="w:p", contains="existing list item")
pPr = tags[0].toxml() if (tags := target_para.getElementsByTagName("w:pPr")) else ""
new_item = f'<w:p>{pPr}<w:r><w:t>New item</w:t></w:r></w:p>'
tracked_para = DocxXMLEditor.suggest_paragraph(new_item)
doc["word/document.xml"].insert_after(target_para, tracked_para)
# Optional: add spacing paragraph before content for better visual separation
# spacing = DocxXMLEditor.suggest_paragraph('<w:p><w:pPr><w:pStyle w:val="ListParagraph"/></w:pPr></w:p>')
# doc["word/document.xml"].insert_after(target_para, spacing + tracked_para)
```
### Adding Comments
```python
# Add comment spanning two existing tracked changes
# Note: w:id is auto-generated. Only search by w:id if you know it from XML inspection
start_node = doc["word/document.xml"].get_node(tag="w:del", attrs={"w:id": "1"})
end_node = doc["word/document.xml"].get_node(tag="w:ins", attrs={"w:id": "2"})
doc.add_comment(start=start_node, end=end_node, text="Explanation of this change")
# Add comment on a paragraph
para = doc["word/document.xml"].get_node(tag="w:p", contains="paragraph text")
doc.add_comment(start=para, end=para, text="Comment on this paragraph")
# Add comment on newly created tracked change
# First create the tracked change
node = doc["word/document.xml"].get_node(tag="w:r", contains="old")
new_nodes = doc["word/document.xml"].replace_node(
node,
'<w:del><w:r><w:delText>old</w:delText></w:r></w:del><w:ins><w:r><w:t>new</w:t></w:r></w:ins>'
)
# Then add comment on the newly created elements
# new_nodes[0] is the <w:del>, new_nodes[1] is the <w:ins>
doc.add_comment(start=new_nodes[0], end=new_nodes[1], text="Changed old to new per requirements")
# Reply to existing comment
doc.reply_to_comment(parent_comment_id=0, text="I agree with this change")
```
### Rejecting Tracked Changes
**IMPORTANT**: Use `revert_insertion()` to reject insertions and `revert_deletion()` to restore deletions using tracked changes. Use `suggest_deletion()` only for regular unmarked content.
```python
# Reject insertion (wraps it in deletion)
# Use this when another author inserted text that you want to delete
ins = doc["word/document.xml"].get_node(tag="w:ins", attrs={"w:id": "5"})
nodes = doc["word/document.xml"].revert_insertion(ins) # Returns [ins]
# Reject deletion (creates insertion to restore deleted content)
# Use this when another author deleted text that you want to restore
del_elem = doc["word/document.xml"].get_node(tag="w:del", attrs={"w:id": "3"})
nodes = doc["word/document.xml"].revert_deletion(del_elem) # Returns [del_elem, new_ins]
# Reject all insertions in a paragraph
para = doc["word/document.xml"].get_node(tag="w:p", contains="paragraph text")
nodes = doc["word/document.xml"].revert_insertion(para) # Returns [para]
# Reject all deletions in a paragraph
para = doc["word/document.xml"].get_node(tag="w:p", contains="paragraph text")
nodes = doc["word/document.xml"].revert_deletion(para) # Returns [para]
```
### Inserting Images
**CRITICAL**: The Document class works with a temporary copy at `doc.unpacked_path`. Always copy images to this temp directory, not the original unpacked folder.
```python
from PIL import Image
import shutil, os
# Initialize document first
doc = Document('unpacked')
# Copy image and calculate full-width dimensions with aspect ratio
media_dir = os.path.join(doc.unpacked_path, 'word/media')
os.makedirs(media_dir, exist_ok=True)
shutil.copy('image.png', os.path.join(media_dir, 'image1.png'))
img = Image.open(os.path.join(media_dir, 'image1.png'))
width_emus = int(6.5 * 914400) # 6.5" usable width, 914400 EMUs/inch
height_emus = int(width_emus * img.size[1] / img.size[0])
# Add relationship and content type
rels_editor = doc['word/_rels/document.xml.rels']
next_rid = rels_editor.get_next_rid()
rels_editor.append_to(rels_editor.dom.documentElement,
f'<Relationship Id="{next_rid}" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/image" Target="media/image1.png"/>')
doc['[Content_Types].xml'].append_to(doc['[Content_Types].xml'].dom.documentElement,
'<Default Extension="png" ContentType="image/png"/>')
# Insert image
node = doc["word/document.xml"].get_node(tag="w:p", line_number=100)
doc["word/document.xml"].insert_after(node, f'''<w:p>
<w:r>
<w:drawing>
<wp:inline distT="0" distB="0" distL="0" distR="0">
<wp:extent cx="{width_emus}" cy="{height_emus}"/>
<wp:docPr id="1" name="Picture 1"/>
<a:graphic xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main">
<a:graphicData uri="http://schemas.openxmlformats.org/drawingml/2006/picture">
<pic:pic xmlns:pic="http://schemas.openxmlformats.org/drawingml/2006/picture">
<pic:nvPicPr><pic:cNvPr id="1" name="image1.png"/><pic:cNvPicPr/></pic:nvPicPr>
<pic:blipFill><a:blip r:embed="{next_rid}"/><a:stretch><a:fillRect/></a:stretch></pic:blipFill>
<pic:spPr><a:xfrm><a:ext cx="{width_emus}" cy="{height_emus}"/></a:xfrm><a:prstGeom prst="rect"><a:avLst/></a:prstGeom></pic:spPr>
</pic:pic>
</a:graphicData>
</a:graphic>
</wp:inline>
</w:drawing>
</w:r>
</w:p>''')
```
### Getting Nodes
```python
# By text content
node = doc["word/document.xml"].get_node(tag="w:p", contains="specific text")
# By line range
para = doc["word/document.xml"].get_node(tag="w:p", line_number=range(100, 150))
# By attributes
node = doc["word/document.xml"].get_node(tag="w:del", attrs={"w:id": "1"})
# By exact line number (must be line number where tag opens)
para = doc["word/document.xml"].get_node(tag="w:p", line_number=42)
# Combine filters
node = doc["word/document.xml"].get_node(tag="w:r", line_number=range(40, 60), contains="text")
# Disambiguate when text appears multiple times - add line_number range
node = doc["word/document.xml"].get_node(tag="w:r", contains="Section", line_number=range(2400, 2500))
```
### Saving
```python
# Save with automatic validation (copies back to original directory)
doc.save() # Validates by default, raises error if validation fails
# Save to different location
doc.save('modified-unpacked')
# Skip validation (debugging only - needing this in production indicates XML issues)
doc.save(validate=False)
```
### Direct DOM Manipulation
For complex scenarios not covered by the library:
```python
# Access any XML file
editor = doc["word/document.xml"]
editor = doc["word/comments.xml"]
# Direct DOM access (defusedxml.minidom.Document)
node = doc["word/document.xml"].get_node(tag="w:p", line_number=5)
parent = node.parentNode
parent.removeChild(node)
parent.appendChild(node) # Move to end
# General document manipulation (without tracked changes)
old_node = doc["word/document.xml"].get_node(tag="w:p", contains="original text")
doc["word/document.xml"].replace_node(old_node, "<w:p><w:r><w:t>replacement text</w:t></w:r></w:p>")
# Multiple insertions - use return value to maintain order
node = doc["word/document.xml"].get_node(tag="w:r", line_number=100)
nodes = doc["word/document.xml"].insert_after(node, "<w:r><w:t>A</w:t></w:r>")
nodes = doc["word/document.xml"].insert_after(nodes[-1], "<w:r><w:t>B</w:t></w:r>")
nodes = doc["word/document.xml"].insert_after(nodes[-1], "<w:r><w:t>C</w:t></w:r>")
# Results in: original_node, A, B, C
```
## Tracked Changes (Redlining)
**Use the Document class above for all tracked changes.** The patterns below are for reference when constructing replacement XML strings.
### Validation Rules
The validator checks that the document text matches the original after reverting Claude's changes. This means:
- **NEVER modify text inside another author's `<w:ins>` or `<w:del>` tags**
- **ALWAYS use nested deletions** to remove another author's insertions
- **Every edit must be properly tracked** with `<w:ins>` or `<w:del>` tags
### Tracked Change Patterns
**CRITICAL RULES**:
1. Never modify the content inside another author's tracked changes. Always use nested deletions.
2. **XML Structure**: Always place `<w:del>` and `<w:ins>` at paragraph level containing complete `<w:r>` elements. Never nest inside `<w:r>` elements - this creates invalid XML that breaks document processing.
**Text Insertion:**
```xml
<w:ins w:id="1" w:author="Claude" w:date="2025-07-30T23:05:00Z" w16du:dateUtc="2025-07-31T06:05:00Z">
<w:r w:rsidR="00792858">
<w:t>inserted text</w:t>
</w:r>
</w:ins>
```
**Text Deletion:**
```xml
<w:del w:id="2" w:author="Claude" w:date="2025-07-30T23:05:00Z" w16du:dateUtc="2025-07-31T06:05:00Z">
<w:r w:rsidDel="00792858">
<w:delText>deleted text</w:delText>
</w:r>
</w:del>
```
**Deleting Another Author's Insertion (MUST use nested structure):**
```xml
<!-- Nest deletion inside the original insertion -->
<w:ins w:author="Jane Smith" w:id="16">
<w:del w:author="Claude" w:id="40">
<w:r><w:delText>monthly</w:delText></w:r>
</w:del>
</w:ins>
<w:ins w:author="Claude" w:id="41">
<w:r><w:t>weekly</w:t></w:r>
</w:ins>
```
**Restoring Another Author's Deletion:**
```xml
<!-- Leave their deletion unchanged, add new insertion after it -->
<w:del w:author="Jane Smith" w:id="50">
<w:r><w:delText>within 30 days</w:delText></w:r>
</w:del>
<w:ins w:author="Claude" w:id="51">
<w:r><w:t>within 30 days</w:t></w:r>
</w:ins>
```

1499
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chart.xsd Normal file
View File

File diff suppressed because it is too large Load Diff

146
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd Normal file
View File

@@ -0,0 +1,146 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main"
xmlns="http://schemas.openxmlformats.org/drawingml/2006/chartDrawing"
targetNamespace="http://schemas.openxmlformats.org/drawingml/2006/chartDrawing"
elementFormDefault="qualified">
<xsd:import namespace="http://schemas.openxmlformats.org/drawingml/2006/main"
schemaLocation="dml-main.xsd"/>
<xsd:complexType name="CT_ShapeNonVisual">
<xsd:sequence>
<xsd:element name="cNvPr" type="a:CT_NonVisualDrawingProps" minOccurs="1" maxOccurs="1"/>
<xsd:element name="cNvSpPr" type="a:CT_NonVisualDrawingShapeProps" minOccurs="1" maxOccurs="1"
/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Shape">
<xsd:sequence>
<xsd:element name="nvSpPr" type="CT_ShapeNonVisual" minOccurs="1" maxOccurs="1"/>
<xsd:element name="spPr" type="a:CT_ShapeProperties" minOccurs="1" maxOccurs="1"/>
<xsd:element name="style" type="a:CT_ShapeStyle" minOccurs="0" maxOccurs="1"/>
<xsd:element name="txBody" type="a:CT_TextBody" minOccurs="0" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="macro" type="xsd:string" use="optional"/>
<xsd:attribute name="textlink" type="xsd:string" use="optional"/>
<xsd:attribute name="fLocksText" type="xsd:boolean" use="optional" default="true"/>
<xsd:attribute name="fPublished" type="xsd:boolean" use="optional" default="false"/>
</xsd:complexType>
<xsd:complexType name="CT_ConnectorNonVisual">
<xsd:sequence>
<xsd:element name="cNvPr" type="a:CT_NonVisualDrawingProps" minOccurs="1" maxOccurs="1"/>
<xsd:element name="cNvCxnSpPr" type="a:CT_NonVisualConnectorProperties" minOccurs="1"
maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Connector">
<xsd:sequence>
<xsd:element name="nvCxnSpPr" type="CT_ConnectorNonVisual" minOccurs="1" maxOccurs="1"/>
<xsd:element name="spPr" type="a:CT_ShapeProperties" minOccurs="1" maxOccurs="1"/>
<xsd:element name="style" type="a:CT_ShapeStyle" minOccurs="0" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="macro" type="xsd:string" use="optional"/>
<xsd:attribute name="fPublished" type="xsd:boolean" use="optional" default="false"/>
</xsd:complexType>
<xsd:complexType name="CT_PictureNonVisual">
<xsd:sequence>
<xsd:element name="cNvPr" type="a:CT_NonVisualDrawingProps" minOccurs="1" maxOccurs="1"/>
<xsd:element name="cNvPicPr" type="a:CT_NonVisualPictureProperties" minOccurs="1"
maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Picture">
<xsd:sequence>
<xsd:element name="nvPicPr" type="CT_PictureNonVisual" minOccurs="1" maxOccurs="1"/>
<xsd:element name="blipFill" type="a:CT_BlipFillProperties" minOccurs="1" maxOccurs="1"/>
<xsd:element name="spPr" type="a:CT_ShapeProperties" minOccurs="1" maxOccurs="1"/>
<xsd:element name="style" type="a:CT_ShapeStyle" minOccurs="0" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="macro" type="xsd:string" use="optional" default=""/>
<xsd:attribute name="fPublished" type="xsd:boolean" use="optional" default="false"/>
</xsd:complexType>
<xsd:complexType name="CT_GraphicFrameNonVisual">
<xsd:sequence>
<xsd:element name="cNvPr" type="a:CT_NonVisualDrawingProps" minOccurs="1" maxOccurs="1"/>
<xsd:element name="cNvGraphicFramePr" type="a:CT_NonVisualGraphicFrameProperties"
minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_GraphicFrame">
<xsd:sequence>
<xsd:element name="nvGraphicFramePr" type="CT_GraphicFrameNonVisual" minOccurs="1"
maxOccurs="1"/>
<xsd:element name="xfrm" type="a:CT_Transform2D" minOccurs="1" maxOccurs="1"/>
<xsd:element ref="a:graphic" minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="macro" type="xsd:string" use="optional"/>
<xsd:attribute name="fPublished" type="xsd:boolean" use="optional" default="false"/>
</xsd:complexType>
<xsd:complexType name="CT_GroupShapeNonVisual">
<xsd:sequence>
<xsd:element name="cNvPr" type="a:CT_NonVisualDrawingProps" minOccurs="1" maxOccurs="1"/>
<xsd:element name="cNvGrpSpPr" type="a:CT_NonVisualGroupDrawingShapeProps" minOccurs="1"
maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_GroupShape">
<xsd:sequence>
<xsd:element name="nvGrpSpPr" type="CT_GroupShapeNonVisual" minOccurs="1" maxOccurs="1"/>
<xsd:element name="grpSpPr" type="a:CT_GroupShapeProperties" minOccurs="1" maxOccurs="1"/>
<xsd:choice minOccurs="0" maxOccurs="unbounded">
<xsd:element name="sp" type="CT_Shape"/>
<xsd:element name="grpSp" type="CT_GroupShape"/>
<xsd:element name="graphicFrame" type="CT_GraphicFrame"/>
<xsd:element name="cxnSp" type="CT_Connector"/>
<xsd:element name="pic" type="CT_Picture"/>
</xsd:choice>
</xsd:sequence>
</xsd:complexType>
<xsd:group name="EG_ObjectChoices">
<xsd:sequence>
<xsd:choice minOccurs="1" maxOccurs="1">
<xsd:element name="sp" type="CT_Shape"/>
<xsd:element name="grpSp" type="CT_GroupShape"/>
<xsd:element name="graphicFrame" type="CT_GraphicFrame"/>
<xsd:element name="cxnSp" type="CT_Connector"/>
<xsd:element name="pic" type="CT_Picture"/>
</xsd:choice>
</xsd:sequence>
</xsd:group>
<xsd:simpleType name="ST_MarkerCoordinate">
<xsd:restriction base="xsd:double">
<xsd:minInclusive value="0.0"/>
<xsd:maxInclusive value="1.0"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_Marker">
<xsd:sequence>
<xsd:element name="x" type="ST_MarkerCoordinate" minOccurs="1" maxOccurs="1"/>
<xsd:element name="y" type="ST_MarkerCoordinate" minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_RelSizeAnchor">
<xsd:sequence>
<xsd:element name="from" type="CT_Marker"/>
<xsd:element name="to" type="CT_Marker"/>
<xsd:group ref="EG_ObjectChoices"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_AbsSizeAnchor">
<xsd:sequence>
<xsd:element name="from" type="CT_Marker"/>
<xsd:element name="ext" type="a:CT_PositiveSize2D"/>
<xsd:group ref="EG_ObjectChoices"/>
</xsd:sequence>
</xsd:complexType>
<xsd:group name="EG_Anchor">
<xsd:choice>
<xsd:element name="relSizeAnchor" type="CT_RelSizeAnchor"/>
<xsd:element name="absSizeAnchor" type="CT_AbsSizeAnchor"/>
</xsd:choice>
</xsd:group>
<xsd:complexType name="CT_Drawing">
<xsd:sequence>
<xsd:group ref="EG_Anchor" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
</xsd:schema>

1085
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd Normal file
View File

File diff suppressed because it is too large Load Diff

11
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd Normal file
View File

@@ -0,0 +1,11 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns="http://schemas.openxmlformats.org/drawingml/2006/lockedCanvas"
xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main"
xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships"
elementFormDefault="qualified"
targetNamespace="http://schemas.openxmlformats.org/drawingml/2006/lockedCanvas">
<xsd:import namespace="http://schemas.openxmlformats.org/drawingml/2006/main"
schemaLocation="dml-main.xsd"/>
<xsd:element name="lockedCanvas" type="a:CT_GvmlGroupShape"/>
</xsd:schema>

3081
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-main.xsd Normal file
View File

File diff suppressed because it is too large Load Diff

23
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-picture.xsd Normal file
View File

@@ -0,0 +1,23 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns="http://schemas.openxmlformats.org/drawingml/2006/picture"
xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main" elementFormDefault="qualified"
targetNamespace="http://schemas.openxmlformats.org/drawingml/2006/picture">
<xsd:import namespace="http://schemas.openxmlformats.org/drawingml/2006/main"
schemaLocation="dml-main.xsd"/>
<xsd:complexType name="CT_PictureNonVisual">
<xsd:sequence>
<xsd:element name="cNvPr" type="a:CT_NonVisualDrawingProps" minOccurs="1" maxOccurs="1"/>
<xsd:element name="cNvPicPr" type="a:CT_NonVisualPictureProperties" minOccurs="1"
maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Picture">
<xsd:sequence minOccurs="1" maxOccurs="1">
<xsd:element name="nvPicPr" type="CT_PictureNonVisual" minOccurs="1" maxOccurs="1"/>
<xsd:element name="blipFill" type="a:CT_BlipFillProperties" minOccurs="1" maxOccurs="1"/>
<xsd:element name="spPr" type="a:CT_ShapeProperties" minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:element name="pic" type="CT_Picture"/>
</xsd:schema>

185
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd Normal file
View File

@@ -0,0 +1,185 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main"
xmlns="http://schemas.openxmlformats.org/drawingml/2006/spreadsheetDrawing"
xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships"
targetNamespace="http://schemas.openxmlformats.org/drawingml/2006/spreadsheetDrawing"
elementFormDefault="qualified">
<xsd:import namespace="http://schemas.openxmlformats.org/drawingml/2006/main"
schemaLocation="dml-main.xsd"/>
<xsd:import schemaLocation="shared-relationshipReference.xsd"
namespace="http://schemas.openxmlformats.org/officeDocument/2006/relationships"/>
<xsd:element name="from" type="CT_Marker"/>
<xsd:element name="to" type="CT_Marker"/>
<xsd:complexType name="CT_AnchorClientData">
<xsd:attribute name="fLocksWithSheet" type="xsd:boolean" use="optional" default="true"/>
<xsd:attribute name="fPrintsWithSheet" type="xsd:boolean" use="optional" default="true"/>
</xsd:complexType>
<xsd:complexType name="CT_ShapeNonVisual">
<xsd:sequence>
<xsd:element name="cNvPr" type="a:CT_NonVisualDrawingProps" minOccurs="1" maxOccurs="1"/>
<xsd:element name="cNvSpPr" type="a:CT_NonVisualDrawingShapeProps" minOccurs="1" maxOccurs="1"
/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Shape">
<xsd:sequence>
<xsd:element name="nvSpPr" type="CT_ShapeNonVisual" minOccurs="1" maxOccurs="1"/>
<xsd:element name="spPr" type="a:CT_ShapeProperties" minOccurs="1" maxOccurs="1"/>
<xsd:element name="style" type="a:CT_ShapeStyle" minOccurs="0" maxOccurs="1"/>
<xsd:element name="txBody" type="a:CT_TextBody" minOccurs="0" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="macro" type="xsd:string" use="optional"/>
<xsd:attribute name="textlink" type="xsd:string" use="optional"/>
<xsd:attribute name="fLocksText" type="xsd:boolean" use="optional" default="true"/>
<xsd:attribute name="fPublished" type="xsd:boolean" use="optional" default="false"/>
</xsd:complexType>
<xsd:complexType name="CT_ConnectorNonVisual">
<xsd:sequence>
<xsd:element name="cNvPr" type="a:CT_NonVisualDrawingProps" minOccurs="1" maxOccurs="1"/>
<xsd:element name="cNvCxnSpPr" type="a:CT_NonVisualConnectorProperties" minOccurs="1"
maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Connector">
<xsd:sequence>
<xsd:element name="nvCxnSpPr" type="CT_ConnectorNonVisual" minOccurs="1" maxOccurs="1"/>
<xsd:element name="spPr" type="a:CT_ShapeProperties" minOccurs="1" maxOccurs="1"/>
<xsd:element name="style" type="a:CT_ShapeStyle" minOccurs="0" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="macro" type="xsd:string" use="optional"/>
<xsd:attribute name="fPublished" type="xsd:boolean" use="optional" default="false"/>
</xsd:complexType>
<xsd:complexType name="CT_PictureNonVisual">
<xsd:sequence>
<xsd:element name="cNvPr" type="a:CT_NonVisualDrawingProps" minOccurs="1" maxOccurs="1"/>
<xsd:element name="cNvPicPr" type="a:CT_NonVisualPictureProperties" minOccurs="1"
maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Picture">
<xsd:sequence>
<xsd:element name="nvPicPr" type="CT_PictureNonVisual" minOccurs="1" maxOccurs="1"/>
<xsd:element name="blipFill" type="a:CT_BlipFillProperties" minOccurs="1" maxOccurs="1"/>
<xsd:element name="spPr" type="a:CT_ShapeProperties" minOccurs="1" maxOccurs="1"/>
<xsd:element name="style" type="a:CT_ShapeStyle" minOccurs="0" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="macro" type="xsd:string" use="optional" default=""/>
<xsd:attribute name="fPublished" type="xsd:boolean" use="optional" default="false"/>
</xsd:complexType>
<xsd:complexType name="CT_GraphicalObjectFrameNonVisual">
<xsd:sequence>
<xsd:element name="cNvPr" type="a:CT_NonVisualDrawingProps" minOccurs="1" maxOccurs="1"/>
<xsd:element name="cNvGraphicFramePr" type="a:CT_NonVisualGraphicFrameProperties"
minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_GraphicalObjectFrame">
<xsd:sequence>
<xsd:element name="nvGraphicFramePr" type="CT_GraphicalObjectFrameNonVisual" minOccurs="1"
maxOccurs="1"/>
<xsd:element name="xfrm" type="a:CT_Transform2D" minOccurs="1" maxOccurs="1"/>
<xsd:element ref="a:graphic" minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="macro" type="xsd:string" use="optional"/>
<xsd:attribute name="fPublished" type="xsd:boolean" use="optional" default="false"/>
</xsd:complexType>
<xsd:complexType name="CT_GroupShapeNonVisual">
<xsd:sequence>
<xsd:element name="cNvPr" type="a:CT_NonVisualDrawingProps" minOccurs="1" maxOccurs="1"/>
<xsd:element name="cNvGrpSpPr" type="a:CT_NonVisualGroupDrawingShapeProps" minOccurs="1"
maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_GroupShape">
<xsd:sequence>
<xsd:element name="nvGrpSpPr" type="CT_GroupShapeNonVisual" minOccurs="1" maxOccurs="1"/>
<xsd:element name="grpSpPr" type="a:CT_GroupShapeProperties" minOccurs="1" maxOccurs="1"/>
<xsd:choice minOccurs="0" maxOccurs="unbounded">
<xsd:element name="sp" type="CT_Shape"/>
<xsd:element name="grpSp" type="CT_GroupShape"/>
<xsd:element name="graphicFrame" type="CT_GraphicalObjectFrame"/>
<xsd:element name="cxnSp" type="CT_Connector"/>
<xsd:element name="pic" type="CT_Picture"/>
</xsd:choice>
</xsd:sequence>
</xsd:complexType>
<xsd:group name="EG_ObjectChoices">
<xsd:sequence>
<xsd:choice minOccurs="1" maxOccurs="1">
<xsd:element name="sp" type="CT_Shape"/>
<xsd:element name="grpSp" type="CT_GroupShape"/>
<xsd:element name="graphicFrame" type="CT_GraphicalObjectFrame"/>
<xsd:element name="cxnSp" type="CT_Connector"/>
<xsd:element name="pic" type="CT_Picture"/>
<xsd:element name="contentPart" type="CT_Rel"/>
</xsd:choice>
</xsd:sequence>
</xsd:group>
<xsd:complexType name="CT_Rel">
<xsd:attribute ref="r:id" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_ColID">
<xsd:restriction base="xsd:int">
<xsd:minInclusive value="0"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_RowID">
<xsd:restriction base="xsd:int">
<xsd:minInclusive value="0"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_Marker">
<xsd:sequence>
<xsd:element name="col" type="ST_ColID"/>
<xsd:element name="colOff" type="a:ST_Coordinate"/>
<xsd:element name="row" type="ST_RowID"/>
<xsd:element name="rowOff" type="a:ST_Coordinate"/>
</xsd:sequence>
</xsd:complexType>
<xsd:simpleType name="ST_EditAs">
<xsd:restriction base="xsd:token">
<xsd:enumeration value="twoCell"/>
<xsd:enumeration value="oneCell"/>
<xsd:enumeration value="absolute"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_TwoCellAnchor">
<xsd:sequence>
<xsd:element name="from" type="CT_Marker"/>
<xsd:element name="to" type="CT_Marker"/>
<xsd:group ref="EG_ObjectChoices"/>
<xsd:element name="clientData" type="CT_AnchorClientData" minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="editAs" type="ST_EditAs" use="optional" default="twoCell"/>
</xsd:complexType>
<xsd:complexType name="CT_OneCellAnchor">
<xsd:sequence>
<xsd:element name="from" type="CT_Marker"/>
<xsd:element name="ext" type="a:CT_PositiveSize2D"/>
<xsd:group ref="EG_ObjectChoices"/>
<xsd:element name="clientData" type="CT_AnchorClientData" minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_AbsoluteAnchor">
<xsd:sequence>
<xsd:element name="pos" type="a:CT_Point2D"/>
<xsd:element name="ext" type="a:CT_PositiveSize2D"/>
<xsd:group ref="EG_ObjectChoices"/>
<xsd:element name="clientData" type="CT_AnchorClientData" minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:group name="EG_Anchor">
<xsd:choice>
<xsd:element name="twoCellAnchor" type="CT_TwoCellAnchor"/>
<xsd:element name="oneCellAnchor" type="CT_OneCellAnchor"/>
<xsd:element name="absoluteAnchor" type="CT_AbsoluteAnchor"/>
</xsd:choice>
</xsd:group>
<xsd:complexType name="CT_Drawing">
<xsd:sequence>
<xsd:group ref="EG_Anchor" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:element name="wsDr" type="CT_Drawing"/>
</xsd:schema>

287
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd Normal file
View File

@@ -0,0 +1,287 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main"
xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"
xmlns:dpct="http://schemas.openxmlformats.org/drawingml/2006/picture"
xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships"
xmlns="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing"
targetNamespace="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing"
elementFormDefault="qualified">
<xsd:import namespace="http://schemas.openxmlformats.org/drawingml/2006/main"
schemaLocation="dml-main.xsd"/>
<xsd:import schemaLocation="wml.xsd"
namespace="http://schemas.openxmlformats.org/wordprocessingml/2006/main"/>
<xsd:import namespace="http://schemas.openxmlformats.org/drawingml/2006/picture"
schemaLocation="dml-picture.xsd"/>
<xsd:import namespace="http://schemas.openxmlformats.org/officeDocument/2006/relationships"
schemaLocation="shared-relationshipReference.xsd"/>
<xsd:complexType name="CT_EffectExtent">
<xsd:attribute name="l" type="a:ST_Coordinate" use="required"/>
<xsd:attribute name="t" type="a:ST_Coordinate" use="required"/>
<xsd:attribute name="r" type="a:ST_Coordinate" use="required"/>
<xsd:attribute name="b" type="a:ST_Coordinate" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_WrapDistance">
<xsd:restriction base="xsd:unsignedInt"/>
</xsd:simpleType>
<xsd:complexType name="CT_Inline">
<xsd:sequence>
<xsd:element name="extent" type="a:CT_PositiveSize2D"/>
<xsd:element name="effectExtent" type="CT_EffectExtent" minOccurs="0"/>
<xsd:element name="docPr" type="a:CT_NonVisualDrawingProps" minOccurs="1" maxOccurs="1"/>
<xsd:element name="cNvGraphicFramePr" type="a:CT_NonVisualGraphicFrameProperties"
minOccurs="0" maxOccurs="1"/>
<xsd:element ref="a:graphic" minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="distT" type="ST_WrapDistance" use="optional"/>
<xsd:attribute name="distB" type="ST_WrapDistance" use="optional"/>
<xsd:attribute name="distL" type="ST_WrapDistance" use="optional"/>
<xsd:attribute name="distR" type="ST_WrapDistance" use="optional"/>
</xsd:complexType>
<xsd:simpleType name="ST_WrapText">
<xsd:restriction base="xsd:token">
<xsd:enumeration value="bothSides"/>
<xsd:enumeration value="left"/>
<xsd:enumeration value="right"/>
<xsd:enumeration value="largest"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_WrapPath">
<xsd:sequence>
<xsd:element name="start" type="a:CT_Point2D" minOccurs="1" maxOccurs="1"/>
<xsd:element name="lineTo" type="a:CT_Point2D" minOccurs="2" maxOccurs="unbounded"/>
</xsd:sequence>
<xsd:attribute name="edited" type="xsd:boolean" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_WrapNone"/>
<xsd:complexType name="CT_WrapSquare">
<xsd:sequence>
<xsd:element name="effectExtent" type="CT_EffectExtent" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="wrapText" type="ST_WrapText" use="required"/>
<xsd:attribute name="distT" type="ST_WrapDistance" use="optional"/>
<xsd:attribute name="distB" type="ST_WrapDistance" use="optional"/>
<xsd:attribute name="distL" type="ST_WrapDistance" use="optional"/>
<xsd:attribute name="distR" type="ST_WrapDistance" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_WrapTight">
<xsd:sequence>
<xsd:element name="wrapPolygon" type="CT_WrapPath" minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="wrapText" type="ST_WrapText" use="required"/>
<xsd:attribute name="distL" type="ST_WrapDistance" use="optional"/>
<xsd:attribute name="distR" type="ST_WrapDistance" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_WrapThrough">
<xsd:sequence>
<xsd:element name="wrapPolygon" type="CT_WrapPath" minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="wrapText" type="ST_WrapText" use="required"/>
<xsd:attribute name="distL" type="ST_WrapDistance" use="optional"/>
<xsd:attribute name="distR" type="ST_WrapDistance" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_WrapTopBottom">
<xsd:sequence>
<xsd:element name="effectExtent" type="CT_EffectExtent" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="distT" type="ST_WrapDistance" use="optional"/>
<xsd:attribute name="distB" type="ST_WrapDistance" use="optional"/>
</xsd:complexType>
<xsd:group name="EG_WrapType">
<xsd:sequence>
<xsd:choice minOccurs="1" maxOccurs="1">
<xsd:element name="wrapNone" type="CT_WrapNone" minOccurs="1" maxOccurs="1"/>
<xsd:element name="wrapSquare" type="CT_WrapSquare" minOccurs="1" maxOccurs="1"/>
<xsd:element name="wrapTight" type="CT_WrapTight" minOccurs="1" maxOccurs="1"/>
<xsd:element name="wrapThrough" type="CT_WrapThrough" minOccurs="1" maxOccurs="1"/>
<xsd:element name="wrapTopAndBottom" type="CT_WrapTopBottom" minOccurs="1" maxOccurs="1"/>
</xsd:choice>
</xsd:sequence>
</xsd:group>
<xsd:simpleType name="ST_PositionOffset">
<xsd:restriction base="xsd:int"/>
</xsd:simpleType>
<xsd:simpleType name="ST_AlignH">
<xsd:restriction base="xsd:token">
<xsd:enumeration value="left"/>
<xsd:enumeration value="right"/>
<xsd:enumeration value="center"/>
<xsd:enumeration value="inside"/>
<xsd:enumeration value="outside"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_RelFromH">
<xsd:restriction base="xsd:token">
<xsd:enumeration value="margin"/>
<xsd:enumeration value="page"/>
<xsd:enumeration value="column"/>
<xsd:enumeration value="character"/>
<xsd:enumeration value="leftMargin"/>
<xsd:enumeration value="rightMargin"/>
<xsd:enumeration value="insideMargin"/>
<xsd:enumeration value="outsideMargin"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_PosH">
<xsd:sequence>
<xsd:choice minOccurs="1" maxOccurs="1">
<xsd:element name="align" type="ST_AlignH" minOccurs="1" maxOccurs="1"/>
<xsd:element name="posOffset" type="ST_PositionOffset" minOccurs="1" maxOccurs="1"/>
</xsd:choice>
</xsd:sequence>
<xsd:attribute name="relativeFrom" type="ST_RelFromH" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_AlignV">
<xsd:restriction base="xsd:token">
<xsd:enumeration value="top"/>
<xsd:enumeration value="bottom"/>
<xsd:enumeration value="center"/>
<xsd:enumeration value="inside"/>
<xsd:enumeration value="outside"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_RelFromV">
<xsd:restriction base="xsd:token">
<xsd:enumeration value="margin"/>
<xsd:enumeration value="page"/>
<xsd:enumeration value="paragraph"/>
<xsd:enumeration value="line"/>
<xsd:enumeration value="topMargin"/>
<xsd:enumeration value="bottomMargin"/>
<xsd:enumeration value="insideMargin"/>
<xsd:enumeration value="outsideMargin"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_PosV">
<xsd:sequence>
<xsd:choice minOccurs="1" maxOccurs="1">
<xsd:element name="align" type="ST_AlignV" minOccurs="1" maxOccurs="1"/>
<xsd:element name="posOffset" type="ST_PositionOffset" minOccurs="1" maxOccurs="1"/>
</xsd:choice>
</xsd:sequence>
<xsd:attribute name="relativeFrom" type="ST_RelFromV" use="required"/>
</xsd:complexType>
<xsd:complexType name="CT_Anchor">
<xsd:sequence>
<xsd:element name="simplePos" type="a:CT_Point2D"/>
<xsd:element name="positionH" type="CT_PosH"/>
<xsd:element name="positionV" type="CT_PosV"/>
<xsd:element name="extent" type="a:CT_PositiveSize2D"/>
<xsd:element name="effectExtent" type="CT_EffectExtent" minOccurs="0"/>
<xsd:group ref="EG_WrapType"/>
<xsd:element name="docPr" type="a:CT_NonVisualDrawingProps" minOccurs="1" maxOccurs="1"/>
<xsd:element name="cNvGraphicFramePr" type="a:CT_NonVisualGraphicFrameProperties"
minOccurs="0" maxOccurs="1"/>
<xsd:element ref="a:graphic" minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="distT" type="ST_WrapDistance" use="optional"/>
<xsd:attribute name="distB" type="ST_WrapDistance" use="optional"/>
<xsd:attribute name="distL" type="ST_WrapDistance" use="optional"/>
<xsd:attribute name="distR" type="ST_WrapDistance" use="optional"/>
<xsd:attribute name="simplePos" type="xsd:boolean"/>
<xsd:attribute name="relativeHeight" type="xsd:unsignedInt" use="required"/>
<xsd:attribute name="behindDoc" type="xsd:boolean" use="required"/>
<xsd:attribute name="locked" type="xsd:boolean" use="required"/>
<xsd:attribute name="layoutInCell" type="xsd:boolean" use="required"/>
<xsd:attribute name="hidden" type="xsd:boolean" use="optional"/>
<xsd:attribute name="allowOverlap" type="xsd:boolean" use="required"/>
</xsd:complexType>
<xsd:complexType name="CT_TxbxContent">
<xsd:group ref="w:EG_BlockLevelElts" minOccurs="1" maxOccurs="unbounded"/>
</xsd:complexType>
<xsd:complexType name="CT_TextboxInfo">
<xsd:sequence>
<xsd:element name="txbxContent" type="CT_TxbxContent" minOccurs="1" maxOccurs="1"/>
<xsd:element name="extLst" type="a:CT_OfficeArtExtensionList" minOccurs="0" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="id" type="xsd:unsignedShort" use="optional" default="0"/>
</xsd:complexType>
<xsd:complexType name="CT_LinkedTextboxInformation">
<xsd:sequence>
<xsd:element name="extLst" type="a:CT_OfficeArtExtensionList" minOccurs="0" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="id" type="xsd:unsignedShort" use="required"/>
<xsd:attribute name="seq" type="xsd:unsignedShort" use="required"/>
</xsd:complexType>
<xsd:complexType name="CT_WordprocessingShape">
<xsd:sequence minOccurs="1" maxOccurs="1">
<xsd:element name="cNvPr" type="a:CT_NonVisualDrawingProps" minOccurs="0" maxOccurs="1"/>
<xsd:choice minOccurs="1" maxOccurs="1">
<xsd:element name="cNvSpPr" type="a:CT_NonVisualDrawingShapeProps" minOccurs="1"
maxOccurs="1"/>
<xsd:element name="cNvCnPr" type="a:CT_NonVisualConnectorProperties" minOccurs="1"
maxOccurs="1"/>
</xsd:choice>
<xsd:element name="spPr" type="a:CT_ShapeProperties" minOccurs="1" maxOccurs="1"/>
<xsd:element name="style" type="a:CT_ShapeStyle" minOccurs="0" maxOccurs="1"/>
<xsd:element name="extLst" type="a:CT_OfficeArtExtensionList" minOccurs="0" maxOccurs="1"/>
<xsd:choice minOccurs="0" maxOccurs="1">
<xsd:element name="txbx" type="CT_TextboxInfo" minOccurs="1" maxOccurs="1"/>
<xsd:element name="linkedTxbx" type="CT_LinkedTextboxInformation" minOccurs="1"
maxOccurs="1"/>
</xsd:choice>
<xsd:element name="bodyPr" type="a:CT_TextBodyProperties" minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="normalEastAsianFlow" type="xsd:boolean" use="optional" default="false"/>
</xsd:complexType>
<xsd:complexType name="CT_GraphicFrame">
<xsd:sequence>
<xsd:element name="cNvPr" type="a:CT_NonVisualDrawingProps" minOccurs="1" maxOccurs="1"/>
<xsd:element name="cNvFrPr" type="a:CT_NonVisualGraphicFrameProperties" minOccurs="1"
maxOccurs="1"/>
<xsd:element name="xfrm" type="a:CT_Transform2D" minOccurs="1" maxOccurs="1"/>
<xsd:element ref="a:graphic" minOccurs="1" maxOccurs="1"/>
<xsd:element name="extLst" type="a:CT_OfficeArtExtensionList" minOccurs="0" maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_WordprocessingContentPartNonVisual">
<xsd:sequence>
<xsd:element name="cNvPr" type="a:CT_NonVisualDrawingProps" minOccurs="0" maxOccurs="1"/>
<xsd:element name="cNvContentPartPr" type="a:CT_NonVisualContentPartProperties" minOccurs="0" maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_WordprocessingContentPart">
<xsd:sequence>
<xsd:element name="nvContentPartPr" type="CT_WordprocessingContentPartNonVisual" minOccurs="0" maxOccurs="1"/>
<xsd:element name="xfrm" type="a:CT_Transform2D" minOccurs="0" maxOccurs="1"/>
<xsd:element name="extLst" type="a:CT_OfficeArtExtensionList" minOccurs="0" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="bwMode" type="a:ST_BlackWhiteMode" use="optional"/>
<xsd:attribute ref="r:id" use="required"/>
</xsd:complexType>
<xsd:complexType name="CT_WordprocessingGroup">
<xsd:sequence minOccurs="1" maxOccurs="1">
<xsd:element name="cNvPr" type="a:CT_NonVisualDrawingProps" minOccurs="0" maxOccurs="1"/>
<xsd:element name="cNvGrpSpPr" type="a:CT_NonVisualGroupDrawingShapeProps" minOccurs="1"
maxOccurs="1"/>
<xsd:element name="grpSpPr" type="a:CT_GroupShapeProperties" minOccurs="1" maxOccurs="1"/>
<xsd:choice minOccurs="0" maxOccurs="unbounded">
<xsd:element ref="wsp"/>
<xsd:element name="grpSp" type="CT_WordprocessingGroup"/>
<xsd:element name="graphicFrame" type="CT_GraphicFrame"/>
<xsd:element ref="dpct:pic"/>
<xsd:element name="contentPart" type="CT_WordprocessingContentPart"/>
</xsd:choice>
<xsd:element name="extLst" type="a:CT_OfficeArtExtensionList" minOccurs="0" maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_WordprocessingCanvas">
<xsd:sequence minOccurs="1" maxOccurs="1">
<xsd:element name="bg" type="a:CT_BackgroundFormatting" minOccurs="0" maxOccurs="1"/>
<xsd:element name="whole" type="a:CT_WholeE2oFormatting" minOccurs="0" maxOccurs="1"/>
<xsd:choice minOccurs="0" maxOccurs="unbounded">
<xsd:element ref="wsp"/>
<xsd:element ref="dpct:pic"/>
<xsd:element name="contentPart" type="CT_WordprocessingContentPart"/>
<xsd:element ref="wgp"/>
<xsd:element name="graphicFrame" type="CT_GraphicFrame"/>
</xsd:choice>
<xsd:element name="extLst" type="a:CT_OfficeArtExtensionList" minOccurs="0" maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:element name="wpc" type="CT_WordprocessingCanvas"/>
<xsd:element name="wgp" type="CT_WordprocessingGroup"/>
<xsd:element name="wsp" type="CT_WordprocessingShape"/>
<xsd:element name="inline" type="CT_Inline"/>
<xsd:element name="anchor" type="CT_Anchor"/>
</xsd:schema>

1676
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/pml.xsd Normal file
View File

File diff suppressed because it is too large Load Diff

28
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd Normal file
View File

@@ -0,0 +1,28 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns="http://schemas.openxmlformats.org/officeDocument/2006/characteristics"
targetNamespace="http://schemas.openxmlformats.org/officeDocument/2006/characteristics"
elementFormDefault="qualified">
<xsd:complexType name="CT_AdditionalCharacteristics">
<xsd:sequence>
<xsd:element name="characteristic" type="CT_Characteristic" minOccurs="0"
maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Characteristic">
<xsd:attribute name="name" type="xsd:string" use="required"/>
<xsd:attribute name="relation" type="ST_Relation" use="required"/>
<xsd:attribute name="val" type="xsd:string" use="required"/>
<xsd:attribute name="vocabulary" type="xsd:anyURI" use="optional"/>
</xsd:complexType>
<xsd:simpleType name="ST_Relation">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="ge"/>
<xsd:enumeration value="le"/>
<xsd:enumeration value="gt"/>
<xsd:enumeration value="lt"/>
<xsd:enumeration value="eq"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:element name="additionalCharacteristics" type="CT_AdditionalCharacteristics"/>
</xsd:schema>

144
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd Normal file
View File

@@ -0,0 +1,144 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns="http://schemas.openxmlformats.org/officeDocument/2006/bibliography"
xmlns:s="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
targetNamespace="http://schemas.openxmlformats.org/officeDocument/2006/bibliography"
elementFormDefault="qualified">
<xsd:import namespace="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
schemaLocation="shared-commonSimpleTypes.xsd"/>
<xsd:simpleType name="ST_SourceType">
<xsd:restriction base="s:ST_String">
<xsd:enumeration value="ArticleInAPeriodical"/>
<xsd:enumeration value="Book"/>
<xsd:enumeration value="BookSection"/>
<xsd:enumeration value="JournalArticle"/>
<xsd:enumeration value="ConferenceProceedings"/>
<xsd:enumeration value="Report"/>
<xsd:enumeration value="SoundRecording"/>
<xsd:enumeration value="Performance"/>
<xsd:enumeration value="Art"/>
<xsd:enumeration value="DocumentFromInternetSite"/>
<xsd:enumeration value="InternetSite"/>
<xsd:enumeration value="Film"/>
<xsd:enumeration value="Interview"/>
<xsd:enumeration value="Patent"/>
<xsd:enumeration value="ElectronicSource"/>
<xsd:enumeration value="Case"/>
<xsd:enumeration value="Misc"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_NameListType">
<xsd:sequence>
<xsd:element name="Person" type="CT_PersonType" minOccurs="1" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_PersonType">
<xsd:sequence>
<xsd:element name="Last" type="s:ST_String" minOccurs="0" maxOccurs="unbounded"/>
<xsd:element name="First" type="s:ST_String" minOccurs="0" maxOccurs="unbounded"/>
<xsd:element name="Middle" type="s:ST_String" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_NameType">
<xsd:sequence>
<xsd:element name="NameList" type="CT_NameListType" minOccurs="1" maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_NameOrCorporateType">
<xsd:sequence>
<xsd:choice minOccurs="0" maxOccurs="1">
<xsd:element name="NameList" type="CT_NameListType" minOccurs="1" maxOccurs="1"/>
<xsd:element name="Corporate" minOccurs="1" maxOccurs="1" type="s:ST_String"/>
</xsd:choice>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_AuthorType">
<xsd:sequence>
<xsd:choice minOccurs="0" maxOccurs="unbounded">
<xsd:element name="Artist" type="CT_NameType"/>
<xsd:element name="Author" type="CT_NameOrCorporateType"/>
<xsd:element name="BookAuthor" type="CT_NameType"/>
<xsd:element name="Compiler" type="CT_NameType"/>
<xsd:element name="Composer" type="CT_NameType"/>
<xsd:element name="Conductor" type="CT_NameType"/>
<xsd:element name="Counsel" type="CT_NameType"/>
<xsd:element name="Director" type="CT_NameType"/>
<xsd:element name="Editor" type="CT_NameType"/>
<xsd:element name="Interviewee" type="CT_NameType"/>
<xsd:element name="Interviewer" type="CT_NameType"/>
<xsd:element name="Inventor" type="CT_NameType"/>
<xsd:element name="Performer" type="CT_NameOrCorporateType"/>
<xsd:element name="ProducerName" type="CT_NameType"/>
<xsd:element name="Translator" type="CT_NameType"/>
<xsd:element name="Writer" type="CT_NameType"/>
</xsd:choice>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_SourceType">
<xsd:sequence>
<xsd:choice minOccurs="0" maxOccurs="unbounded">
<xsd:element name="AbbreviatedCaseNumber" type="s:ST_String"/>
<xsd:element name="AlbumTitle" type="s:ST_String"/>
<xsd:element name="Author" type="CT_AuthorType"/>
<xsd:element name="BookTitle" type="s:ST_String"/>
<xsd:element name="Broadcaster" type="s:ST_String"/>
<xsd:element name="BroadcastTitle" type="s:ST_String"/>
<xsd:element name="CaseNumber" type="s:ST_String"/>
<xsd:element name="ChapterNumber" type="s:ST_String"/>
<xsd:element name="City" type="s:ST_String"/>
<xsd:element name="Comments" type="s:ST_String"/>
<xsd:element name="ConferenceName" type="s:ST_String"/>
<xsd:element name="CountryRegion" type="s:ST_String"/>
<xsd:element name="Court" type="s:ST_String"/>
<xsd:element name="Day" type="s:ST_String"/>
<xsd:element name="DayAccessed" type="s:ST_String"/>
<xsd:element name="Department" type="s:ST_String"/>
<xsd:element name="Distributor" type="s:ST_String"/>
<xsd:element name="Edition" type="s:ST_String"/>
<xsd:element name="Guid" type="s:ST_String"/>
<xsd:element name="Institution" type="s:ST_String"/>
<xsd:element name="InternetSiteTitle" type="s:ST_String"/>
<xsd:element name="Issue" type="s:ST_String"/>
<xsd:element name="JournalName" type="s:ST_String"/>
<xsd:element name="LCID" type="s:ST_Lang"/>
<xsd:element name="Medium" type="s:ST_String"/>
<xsd:element name="Month" type="s:ST_String"/>
<xsd:element name="MonthAccessed" type="s:ST_String"/>
<xsd:element name="NumberVolumes" type="s:ST_String"/>
<xsd:element name="Pages" type="s:ST_String"/>
<xsd:element name="PatentNumber" type="s:ST_String"/>
<xsd:element name="PeriodicalTitle" type="s:ST_String"/>
<xsd:element name="ProductionCompany" type="s:ST_String"/>
<xsd:element name="PublicationTitle" type="s:ST_String"/>
<xsd:element name="Publisher" type="s:ST_String"/>
<xsd:element name="RecordingNumber" type="s:ST_String"/>
<xsd:element name="RefOrder" type="s:ST_String"/>
<xsd:element name="Reporter" type="s:ST_String"/>
<xsd:element name="SourceType" type="ST_SourceType"/>
<xsd:element name="ShortTitle" type="s:ST_String"/>
<xsd:element name="StandardNumber" type="s:ST_String"/>
<xsd:element name="StateProvince" type="s:ST_String"/>
<xsd:element name="Station" type="s:ST_String"/>
<xsd:element name="Tag" type="s:ST_String"/>
<xsd:element name="Theater" type="s:ST_String"/>
<xsd:element name="ThesisType" type="s:ST_String"/>
<xsd:element name="Title" type="s:ST_String"/>
<xsd:element name="Type" type="s:ST_String"/>
<xsd:element name="URL" type="s:ST_String"/>
<xsd:element name="Version" type="s:ST_String"/>
<xsd:element name="Volume" type="s:ST_String"/>
<xsd:element name="Year" type="s:ST_String"/>
<xsd:element name="YearAccessed" type="s:ST_String"/>
</xsd:choice>
</xsd:sequence>
</xsd:complexType>
<xsd:element name="Sources" type="CT_Sources"/>
<xsd:complexType name="CT_Sources">
<xsd:sequence>
<xsd:element name="Source" type="CT_SourceType" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
<xsd:attribute name="SelectedStyle" type="s:ST_String"/>
<xsd:attribute name="StyleName" type="s:ST_String"/>
<xsd:attribute name="URI" type="s:ST_String"/>
</xsd:complexType>
</xsd:schema>

174
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd Normal file
View File

@@ -0,0 +1,174 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
targetNamespace="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
elementFormDefault="qualified">
<xsd:simpleType name="ST_Lang">
<xsd:restriction base="xsd:string"/>
</xsd:simpleType>
<xsd:simpleType name="ST_HexColorRGB">
<xsd:restriction base="xsd:hexBinary">
<xsd:length value="3" fixed="true"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_Panose">
<xsd:restriction base="xsd:hexBinary">
<xsd:length value="10"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_CalendarType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="gregorian"/>
<xsd:enumeration value="gregorianUs"/>
<xsd:enumeration value="gregorianMeFrench"/>
<xsd:enumeration value="gregorianArabic"/>
<xsd:enumeration value="hijri"/>
<xsd:enumeration value="hebrew"/>
<xsd:enumeration value="taiwan"/>
<xsd:enumeration value="japan"/>
<xsd:enumeration value="thai"/>
<xsd:enumeration value="korea"/>
<xsd:enumeration value="saka"/>
<xsd:enumeration value="gregorianXlitEnglish"/>
<xsd:enumeration value="gregorianXlitFrench"/>
<xsd:enumeration value="none"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_AlgClass">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="hash"/>
<xsd:enumeration value="custom"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_CryptProv">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="rsaAES"/>
<xsd:enumeration value="rsaFull"/>
<xsd:enumeration value="custom"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_AlgType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="typeAny"/>
<xsd:enumeration value="custom"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_ColorType">
<xsd:restriction base="xsd:string"/>
</xsd:simpleType>
<xsd:simpleType name="ST_Guid">
<xsd:restriction base="xsd:token">
<xsd:pattern value="\{[0-9A-F]{8}-[0-9A-F]{4}-[0-9A-F]{4}-[0-9A-F]{4}-[0-9A-F]{12}\}"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_OnOff">
<xsd:union memberTypes="xsd:boolean ST_OnOff1"/>
</xsd:simpleType>
<xsd:simpleType name="ST_OnOff1">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="on"/>
<xsd:enumeration value="off"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_String">
<xsd:restriction base="xsd:string"/>
</xsd:simpleType>
<xsd:simpleType name="ST_XmlName">
<xsd:restriction base="xsd:NCName">
<xsd:minLength value="1"/>
<xsd:maxLength value="255"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_TrueFalse">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="t"/>
<xsd:enumeration value="f"/>
<xsd:enumeration value="true"/>
<xsd:enumeration value="false"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_TrueFalseBlank">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="t"/>
<xsd:enumeration value="f"/>
<xsd:enumeration value="true"/>
<xsd:enumeration value="false"/>
<xsd:enumeration value=""/>
<xsd:enumeration value="True"/>
<xsd:enumeration value="False"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_UnsignedDecimalNumber">
<xsd:restriction base="xsd:decimal">
<xsd:minInclusive value="0"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_TwipsMeasure">
<xsd:union memberTypes="ST_UnsignedDecimalNumber ST_PositiveUniversalMeasure"/>
</xsd:simpleType>
<xsd:simpleType name="ST_VerticalAlignRun">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="baseline"/>
<xsd:enumeration value="superscript"/>
<xsd:enumeration value="subscript"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_Xstring">
<xsd:restriction base="xsd:string"/>
</xsd:simpleType>
<xsd:simpleType name="ST_XAlign">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="left"/>
<xsd:enumeration value="center"/>
<xsd:enumeration value="right"/>
<xsd:enumeration value="inside"/>
<xsd:enumeration value="outside"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_YAlign">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="inline"/>
<xsd:enumeration value="top"/>
<xsd:enumeration value="center"/>
<xsd:enumeration value="bottom"/>
<xsd:enumeration value="inside"/>
<xsd:enumeration value="outside"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_ConformanceClass">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="strict"/>
<xsd:enumeration value="transitional"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_UniversalMeasure">
<xsd:restriction base="xsd:string">
<xsd:pattern value="-?[0-9]+(\.[0-9]+)?(mm|cm|in|pt|pc|pi)"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_PositiveUniversalMeasure">
<xsd:restriction base="ST_UniversalMeasure">
<xsd:pattern value="[0-9]+(\.[0-9]+)?(mm|cm|in|pt|pc|pi)"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_Percentage">
<xsd:restriction base="xsd:string">
<xsd:pattern value="-?[0-9]+(\.[0-9]+)?%"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_FixedPercentage">
<xsd:restriction base="ST_Percentage">
<xsd:pattern value="-?((100)|([0-9][0-9]?))(\.[0-9][0-9]?)?%"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_PositivePercentage">
<xsd:restriction base="ST_Percentage">
<xsd:pattern value="[0-9]+(\.[0-9]+)?%"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_PositiveFixedPercentage">
<xsd:restriction base="ST_Percentage">
<xsd:pattern value="((100)|([0-9][0-9]?))(\.[0-9][0-9]?)?%"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:schema>

25
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd Normal file
View File

@@ -0,0 +1,25 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns="http://schemas.openxmlformats.org/officeDocument/2006/customXml"
xmlns:s="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
targetNamespace="http://schemas.openxmlformats.org/officeDocument/2006/customXml"
elementFormDefault="qualified" attributeFormDefault="qualified" blockDefault="#all">
<xsd:import namespace="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
schemaLocation="shared-commonSimpleTypes.xsd"/>
<xsd:complexType name="CT_DatastoreSchemaRef">
<xsd:attribute name="uri" type="xsd:string" use="required"/>
</xsd:complexType>
<xsd:complexType name="CT_DatastoreSchemaRefs">
<xsd:sequence>
<xsd:element name="schemaRef" type="CT_DatastoreSchemaRef" minOccurs="0" maxOccurs="unbounded"
/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_DatastoreItem">
<xsd:sequence>
<xsd:element name="schemaRefs" type="CT_DatastoreSchemaRefs" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="itemID" type="s:ST_Guid" use="required"/>
</xsd:complexType>
<xsd:element name="datastoreItem" type="CT_DatastoreItem"/>
</xsd:schema>

18
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd Normal file
View File

@@ -0,0 +1,18 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns="http://schemas.openxmlformats.org/schemaLibrary/2006/main"
targetNamespace="http://schemas.openxmlformats.org/schemaLibrary/2006/main"
attributeFormDefault="qualified" elementFormDefault="qualified">
<xsd:complexType name="CT_Schema">
<xsd:attribute name="uri" type="xsd:string" default=""/>
<xsd:attribute name="manifestLocation" type="xsd:string"/>
<xsd:attribute name="schemaLocation" type="xsd:string"/>
<xsd:attribute name="schemaLanguage" type="xsd:token"/>
</xsd:complexType>
<xsd:complexType name="CT_SchemaLibrary">
<xsd:sequence>
<xsd:element name="schema" type="CT_Schema" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:element name="schemaLibrary" type="CT_SchemaLibrary"/>
</xsd:schema>

59
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd Normal file
View File

@@ -0,0 +1,59 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns="http://schemas.openxmlformats.org/officeDocument/2006/custom-properties"
xmlns:vt="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes"
xmlns:s="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
targetNamespace="http://schemas.openxmlformats.org/officeDocument/2006/custom-properties"
blockDefault="#all" elementFormDefault="qualified">
<xsd:import namespace="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes"
schemaLocation="shared-documentPropertiesVariantTypes.xsd"/>
<xsd:import namespace="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
schemaLocation="shared-commonSimpleTypes.xsd"/>
<xsd:element name="Properties" type="CT_Properties"/>
<xsd:complexType name="CT_Properties">
<xsd:sequence>
<xsd:element name="property" minOccurs="0" maxOccurs="unbounded" type="CT_Property"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Property">
<xsd:choice minOccurs="1" maxOccurs="1">
<xsd:element ref="vt:vector"/>
<xsd:element ref="vt:array"/>
<xsd:element ref="vt:blob"/>
<xsd:element ref="vt:oblob"/>
<xsd:element ref="vt:empty"/>
<xsd:element ref="vt:null"/>
<xsd:element ref="vt:i1"/>
<xsd:element ref="vt:i2"/>
<xsd:element ref="vt:i4"/>
<xsd:element ref="vt:i8"/>
<xsd:element ref="vt:int"/>
<xsd:element ref="vt:ui1"/>
<xsd:element ref="vt:ui2"/>
<xsd:element ref="vt:ui4"/>
<xsd:element ref="vt:ui8"/>
<xsd:element ref="vt:uint"/>
<xsd:element ref="vt:r4"/>
<xsd:element ref="vt:r8"/>
<xsd:element ref="vt:decimal"/>
<xsd:element ref="vt:lpstr"/>
<xsd:element ref="vt:lpwstr"/>
<xsd:element ref="vt:bstr"/>
<xsd:element ref="vt:date"/>
<xsd:element ref="vt:filetime"/>
<xsd:element ref="vt:bool"/>
<xsd:element ref="vt:cy"/>
<xsd:element ref="vt:error"/>
<xsd:element ref="vt:stream"/>
<xsd:element ref="vt:ostream"/>
<xsd:element ref="vt:storage"/>
<xsd:element ref="vt:ostorage"/>
<xsd:element ref="vt:vstream"/>
<xsd:element ref="vt:clsid"/>
</xsd:choice>
<xsd:attribute name="fmtid" use="required" type="s:ST_Guid"/>
<xsd:attribute name="pid" use="required" type="xsd:int"/>
<xsd:attribute name="name" use="optional" type="xsd:string"/>
<xsd:attribute name="linkTarget" use="optional" type="xsd:string"/>
</xsd:complexType>
</xsd:schema>

56
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd Normal file
View File

@@ -0,0 +1,56 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns="http://schemas.openxmlformats.org/officeDocument/2006/extended-properties"
xmlns:vt="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes"
targetNamespace="http://schemas.openxmlformats.org/officeDocument/2006/extended-properties"
elementFormDefault="qualified" blockDefault="#all">
<xsd:import namespace="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes"
schemaLocation="shared-documentPropertiesVariantTypes.xsd"/>
<xsd:element name="Properties" type="CT_Properties"/>
<xsd:complexType name="CT_Properties">
<xsd:all>
<xsd:element name="Template" minOccurs="0" maxOccurs="1" type="xsd:string"/>
<xsd:element name="Manager" minOccurs="0" maxOccurs="1" type="xsd:string"/>
<xsd:element name="Company" minOccurs="0" maxOccurs="1" type="xsd:string"/>
<xsd:element name="Pages" minOccurs="0" maxOccurs="1" type="xsd:int"/>
<xsd:element name="Words" minOccurs="0" maxOccurs="1" type="xsd:int"/>
<xsd:element name="Characters" minOccurs="0" maxOccurs="1" type="xsd:int"/>
<xsd:element name="PresentationFormat" minOccurs="0" maxOccurs="1" type="xsd:string"/>
<xsd:element name="Lines" minOccurs="0" maxOccurs="1" type="xsd:int"/>
<xsd:element name="Paragraphs" minOccurs="0" maxOccurs="1" type="xsd:int"/>
<xsd:element name="Slides" minOccurs="0" maxOccurs="1" type="xsd:int"/>
<xsd:element name="Notes" minOccurs="0" maxOccurs="1" type="xsd:int"/>
<xsd:element name="TotalTime" minOccurs="0" maxOccurs="1" type="xsd:int"/>
<xsd:element name="HiddenSlides" minOccurs="0" maxOccurs="1" type="xsd:int"/>
<xsd:element name="MMClips" minOccurs="0" maxOccurs="1" type="xsd:int"/>
<xsd:element name="ScaleCrop" minOccurs="0" maxOccurs="1" type="xsd:boolean"/>
<xsd:element name="HeadingPairs" minOccurs="0" maxOccurs="1" type="CT_VectorVariant"/>
<xsd:element name="TitlesOfParts" minOccurs="0" maxOccurs="1" type="CT_VectorLpstr"/>
<xsd:element name="LinksUpToDate" minOccurs="0" maxOccurs="1" type="xsd:boolean"/>
<xsd:element name="CharactersWithSpaces" minOccurs="0" maxOccurs="1" type="xsd:int"/>
<xsd:element name="SharedDoc" minOccurs="0" maxOccurs="1" type="xsd:boolean"/>
<xsd:element name="HyperlinkBase" minOccurs="0" maxOccurs="1" type="xsd:string"/>
<xsd:element name="HLinks" minOccurs="0" maxOccurs="1" type="CT_VectorVariant"/>
<xsd:element name="HyperlinksChanged" minOccurs="0" maxOccurs="1" type="xsd:boolean"/>
<xsd:element name="DigSig" minOccurs="0" maxOccurs="1" type="CT_DigSigBlob"/>
<xsd:element name="Application" minOccurs="0" maxOccurs="1" type="xsd:string"/>
<xsd:element name="AppVersion" minOccurs="0" maxOccurs="1" type="xsd:string"/>
<xsd:element name="DocSecurity" minOccurs="0" maxOccurs="1" type="xsd:int"/>
</xsd:all>
</xsd:complexType>
<xsd:complexType name="CT_VectorVariant">
<xsd:sequence minOccurs="1" maxOccurs="1">
<xsd:element ref="vt:vector"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_VectorLpstr">
<xsd:sequence minOccurs="1" maxOccurs="1">
<xsd:element ref="vt:vector"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_DigSigBlob">
<xsd:sequence minOccurs="1" maxOccurs="1">
<xsd:element ref="vt:blob"/>
</xsd:sequence>
</xsd:complexType>
</xsd:schema>

195
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd Normal file
View File

@@ -0,0 +1,195 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes"
xmlns:s="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
targetNamespace="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes"
blockDefault="#all" elementFormDefault="qualified">
<xsd:import namespace="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
schemaLocation="shared-commonSimpleTypes.xsd"/>
<xsd:simpleType name="ST_VectorBaseType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="variant"/>
<xsd:enumeration value="i1"/>
<xsd:enumeration value="i2"/>
<xsd:enumeration value="i4"/>
<xsd:enumeration value="i8"/>
<xsd:enumeration value="ui1"/>
<xsd:enumeration value="ui2"/>
<xsd:enumeration value="ui4"/>
<xsd:enumeration value="ui8"/>
<xsd:enumeration value="r4"/>
<xsd:enumeration value="r8"/>
<xsd:enumeration value="lpstr"/>
<xsd:enumeration value="lpwstr"/>
<xsd:enumeration value="bstr"/>
<xsd:enumeration value="date"/>
<xsd:enumeration value="filetime"/>
<xsd:enumeration value="bool"/>
<xsd:enumeration value="cy"/>
<xsd:enumeration value="error"/>
<xsd:enumeration value="clsid"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_ArrayBaseType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="variant"/>
<xsd:enumeration value="i1"/>
<xsd:enumeration value="i2"/>
<xsd:enumeration value="i4"/>
<xsd:enumeration value="int"/>
<xsd:enumeration value="ui1"/>
<xsd:enumeration value="ui2"/>
<xsd:enumeration value="ui4"/>
<xsd:enumeration value="uint"/>
<xsd:enumeration value="r4"/>
<xsd:enumeration value="r8"/>
<xsd:enumeration value="decimal"/>
<xsd:enumeration value="bstr"/>
<xsd:enumeration value="date"/>
<xsd:enumeration value="bool"/>
<xsd:enumeration value="cy"/>
<xsd:enumeration value="error"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_Cy">
<xsd:restriction base="xsd:string">
<xsd:pattern value="\s*[0-9]*\.[0-9]{4}\s*"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_Error">
<xsd:restriction base="xsd:string">
<xsd:pattern value="\s*0x[0-9A-Za-z]{8}\s*"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_Empty"/>
<xsd:complexType name="CT_Null"/>
<xsd:complexType name="CT_Vector">
<xsd:choice minOccurs="1" maxOccurs="unbounded">
<xsd:element ref="variant"/>
<xsd:element ref="i1"/>
<xsd:element ref="i2"/>
<xsd:element ref="i4"/>
<xsd:element ref="i8"/>
<xsd:element ref="ui1"/>
<xsd:element ref="ui2"/>
<xsd:element ref="ui4"/>
<xsd:element ref="ui8"/>
<xsd:element ref="r4"/>
<xsd:element ref="r8"/>
<xsd:element ref="lpstr"/>
<xsd:element ref="lpwstr"/>
<xsd:element ref="bstr"/>
<xsd:element ref="date"/>
<xsd:element ref="filetime"/>
<xsd:element ref="bool"/>
<xsd:element ref="cy"/>
<xsd:element ref="error"/>
<xsd:element ref="clsid"/>
</xsd:choice>
<xsd:attribute name="baseType" type="ST_VectorBaseType" use="required"/>
<xsd:attribute name="size" type="xsd:unsignedInt" use="required"/>
</xsd:complexType>
<xsd:complexType name="CT_Array">
<xsd:choice minOccurs="1" maxOccurs="unbounded">
<xsd:element ref="variant"/>
<xsd:element ref="i1"/>
<xsd:element ref="i2"/>
<xsd:element ref="i4"/>
<xsd:element ref="int"/>
<xsd:element ref="ui1"/>
<xsd:element ref="ui2"/>
<xsd:element ref="ui4"/>
<xsd:element ref="uint"/>
<xsd:element ref="r4"/>
<xsd:element ref="r8"/>
<xsd:element ref="decimal"/>
<xsd:element ref="bstr"/>
<xsd:element ref="date"/>
<xsd:element ref="bool"/>
<xsd:element ref="error"/>
<xsd:element ref="cy"/>
</xsd:choice>
<xsd:attribute name="lBounds" type="xsd:int" use="required"/>
<xsd:attribute name="uBounds" type="xsd:int" use="required"/>
<xsd:attribute name="baseType" type="ST_ArrayBaseType" use="required"/>
</xsd:complexType>
<xsd:complexType name="CT_Variant">
<xsd:choice minOccurs="1" maxOccurs="1">
<xsd:element ref="variant"/>
<xsd:element ref="vector"/>
<xsd:element ref="array"/>
<xsd:element ref="blob"/>
<xsd:element ref="oblob"/>
<xsd:element ref="empty"/>
<xsd:element ref="null"/>
<xsd:element ref="i1"/>
<xsd:element ref="i2"/>
<xsd:element ref="i4"/>
<xsd:element ref="i8"/>
<xsd:element ref="int"/>
<xsd:element ref="ui1"/>
<xsd:element ref="ui2"/>
<xsd:element ref="ui4"/>
<xsd:element ref="ui8"/>
<xsd:element ref="uint"/>
<xsd:element ref="r4"/>
<xsd:element ref="r8"/>
<xsd:element ref="decimal"/>
<xsd:element ref="lpstr"/>
<xsd:element ref="lpwstr"/>
<xsd:element ref="bstr"/>
<xsd:element ref="date"/>
<xsd:element ref="filetime"/>
<xsd:element ref="bool"/>
<xsd:element ref="cy"/>
<xsd:element ref="error"/>
<xsd:element ref="stream"/>
<xsd:element ref="ostream"/>
<xsd:element ref="storage"/>
<xsd:element ref="ostorage"/>
<xsd:element ref="vstream"/>
<xsd:element ref="clsid"/>
</xsd:choice>
</xsd:complexType>
<xsd:complexType name="CT_Vstream">
<xsd:simpleContent>
<xsd:extension base="xsd:base64Binary">
<xsd:attribute name="version" type="s:ST_Guid"/>
</xsd:extension>
</xsd:simpleContent>
</xsd:complexType>
<xsd:element name="variant" type="CT_Variant"/>
<xsd:element name="vector" type="CT_Vector"/>
<xsd:element name="array" type="CT_Array"/>
<xsd:element name="blob" type="xsd:base64Binary"/>
<xsd:element name="oblob" type="xsd:base64Binary"/>
<xsd:element name="empty" type="CT_Empty"/>
<xsd:element name="null" type="CT_Null"/>
<xsd:element name="i1" type="xsd:byte"/>
<xsd:element name="i2" type="xsd:short"/>
<xsd:element name="i4" type="xsd:int"/>
<xsd:element name="i8" type="xsd:long"/>
<xsd:element name="int" type="xsd:int"/>
<xsd:element name="ui1" type="xsd:unsignedByte"/>
<xsd:element name="ui2" type="xsd:unsignedShort"/>
<xsd:element name="ui4" type="xsd:unsignedInt"/>
<xsd:element name="ui8" type="xsd:unsignedLong"/>
<xsd:element name="uint" type="xsd:unsignedInt"/>
<xsd:element name="r4" type="xsd:float"/>
<xsd:element name="r8" type="xsd:double"/>
<xsd:element name="decimal" type="xsd:decimal"/>
<xsd:element name="lpstr" type="xsd:string"/>
<xsd:element name="lpwstr" type="xsd:string"/>
<xsd:element name="bstr" type="xsd:string"/>
<xsd:element name="date" type="xsd:dateTime"/>
<xsd:element name="filetime" type="xsd:dateTime"/>
<xsd:element name="bool" type="xsd:boolean"/>
<xsd:element name="cy" type="ST_Cy"/>
<xsd:element name="error" type="ST_Error"/>
<xsd:element name="stream" type="xsd:base64Binary"/>
<xsd:element name="ostream" type="xsd:base64Binary"/>
<xsd:element name="storage" type="xsd:base64Binary"/>
<xsd:element name="ostorage" type="xsd:base64Binary"/>
<xsd:element name="vstream" type="CT_Vstream"/>
<xsd:element name="clsid" type="s:ST_Guid"/>
</xsd:schema>

582
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-math.xsd Normal file
View File

@@ -0,0 +1,582 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns="http://schemas.openxmlformats.org/officeDocument/2006/math"
xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math"
xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"
xmlns:s="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
elementFormDefault="qualified" attributeFormDefault="qualified" blockDefault="#all"
targetNamespace="http://schemas.openxmlformats.org/officeDocument/2006/math">
<xsd:import namespace="http://schemas.openxmlformats.org/wordprocessingml/2006/main"
schemaLocation="wml.xsd"/>
<xsd:import namespace="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
schemaLocation="shared-commonSimpleTypes.xsd"/>
<xsd:import namespace="http://www.w3.org/XML/1998/namespace" schemaLocation="xml.xsd"/>
<xsd:simpleType name="ST_Integer255">
<xsd:restriction base="xsd:integer">
<xsd:minInclusive value="1"/>
<xsd:maxInclusive value="255"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_Integer255">
<xsd:attribute name="val" type="ST_Integer255" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_Integer2">
<xsd:restriction base="xsd:integer">
<xsd:minInclusive value="-2"/>
<xsd:maxInclusive value="2"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_Integer2">
<xsd:attribute name="val" type="ST_Integer2" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_SpacingRule">
<xsd:restriction base="xsd:integer">
<xsd:minInclusive value="0"/>
<xsd:maxInclusive value="4"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_SpacingRule">
<xsd:attribute name="val" type="ST_SpacingRule" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_UnSignedInteger">
<xsd:restriction base="xsd:unsignedInt"/>
</xsd:simpleType>
<xsd:complexType name="CT_UnSignedInteger">
<xsd:attribute name="val" type="ST_UnSignedInteger" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_Char">
<xsd:restriction base="xsd:string">
<xsd:maxLength value="1"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_Char">
<xsd:attribute name="val" type="ST_Char" use="required"/>
</xsd:complexType>
<xsd:complexType name="CT_OnOff">
<xsd:attribute name="val" type="s:ST_OnOff"/>
</xsd:complexType>
<xsd:complexType name="CT_String">
<xsd:attribute name="val" type="s:ST_String"/>
</xsd:complexType>
<xsd:complexType name="CT_XAlign">
<xsd:attribute name="val" type="s:ST_XAlign" use="required"/>
</xsd:complexType>
<xsd:complexType name="CT_YAlign">
<xsd:attribute name="val" type="s:ST_YAlign" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_Shp">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="centered"/>
<xsd:enumeration value="match"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_Shp">
<xsd:attribute name="val" type="ST_Shp" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_FType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="bar"/>
<xsd:enumeration value="skw"/>
<xsd:enumeration value="lin"/>
<xsd:enumeration value="noBar"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_FType">
<xsd:attribute name="val" type="ST_FType" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_LimLoc">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="undOvr"/>
<xsd:enumeration value="subSup"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_LimLoc">
<xsd:attribute name="val" type="ST_LimLoc" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_TopBot">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="top"/>
<xsd:enumeration value="bot"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_TopBot">
<xsd:attribute name="val" type="ST_TopBot" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_Script">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="roman"/>
<xsd:enumeration value="script"/>
<xsd:enumeration value="fraktur"/>
<xsd:enumeration value="double-struck"/>
<xsd:enumeration value="sans-serif"/>
<xsd:enumeration value="monospace"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_Script">
<xsd:attribute name="val" type="ST_Script"/>
</xsd:complexType>
<xsd:simpleType name="ST_Style">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="p"/>
<xsd:enumeration value="b"/>
<xsd:enumeration value="i"/>
<xsd:enumeration value="bi"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_Style">
<xsd:attribute name="val" type="ST_Style"/>
</xsd:complexType>
<xsd:complexType name="CT_ManualBreak">
<xsd:attribute name="alnAt" type="ST_Integer255"/>
</xsd:complexType>
<xsd:group name="EG_ScriptStyle">
<xsd:sequence>
<xsd:element name="scr" minOccurs="0" type="CT_Script"/>
<xsd:element name="sty" minOccurs="0" type="CT_Style"/>
</xsd:sequence>
</xsd:group>
<xsd:complexType name="CT_RPR">
<xsd:sequence>
<xsd:element name="lit" minOccurs="0" type="CT_OnOff"/>
<xsd:choice>
<xsd:element name="nor" minOccurs="0" type="CT_OnOff"/>
<xsd:sequence>
<xsd:group ref="EG_ScriptStyle"/>
</xsd:sequence>
</xsd:choice>
<xsd:element name="brk" minOccurs="0" type="CT_ManualBreak"/>
<xsd:element name="aln" minOccurs="0" type="CT_OnOff"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Text">
<xsd:simpleContent>
<xsd:extension base="s:ST_String">
<xsd:attribute ref="xml:space" use="optional"/>
</xsd:extension>
</xsd:simpleContent>
</xsd:complexType>
<xsd:complexType name="CT_R">
<xsd:sequence>
<xsd:element name="rPr" type="CT_RPR" minOccurs="0"/>
<xsd:group ref="w:EG_RPr" minOccurs="0"/>
<xsd:choice minOccurs="0" maxOccurs="unbounded">
<xsd:group ref="w:EG_RunInnerContent"/>
<xsd:element name="t" type="CT_Text" minOccurs="0"/>
</xsd:choice>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_CtrlPr">
<xsd:sequence>
<xsd:group ref="w:EG_RPrMath" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_AccPr">
<xsd:sequence>
<xsd:element name="chr" type="CT_Char" minOccurs="0"/>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Acc">
<xsd:sequence>
<xsd:element name="accPr" type="CT_AccPr" minOccurs="0"/>
<xsd:element name="e" type="CT_OMathArg"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_BarPr">
<xsd:sequence>
<xsd:element name="pos" type="CT_TopBot" minOccurs="0"/>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Bar">
<xsd:sequence>
<xsd:element name="barPr" type="CT_BarPr" minOccurs="0"/>
<xsd:element name="e" type="CT_OMathArg"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_BoxPr">
<xsd:sequence>
<xsd:element name="opEmu" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="noBreak" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="diff" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="brk" type="CT_ManualBreak" minOccurs="0"/>
<xsd:element name="aln" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Box">
<xsd:sequence>
<xsd:element name="boxPr" type="CT_BoxPr" minOccurs="0"/>
<xsd:element name="e" type="CT_OMathArg"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_BorderBoxPr">
<xsd:sequence>
<xsd:element name="hideTop" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="hideBot" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="hideLeft" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="hideRight" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="strikeH" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="strikeV" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="strikeBLTR" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="strikeTLBR" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_BorderBox">
<xsd:sequence>
<xsd:element name="borderBoxPr" type="CT_BorderBoxPr" minOccurs="0"/>
<xsd:element name="e" type="CT_OMathArg"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_DPr">
<xsd:sequence>
<xsd:element name="begChr" type="CT_Char" minOccurs="0"/>
<xsd:element name="sepChr" type="CT_Char" minOccurs="0"/>
<xsd:element name="endChr" type="CT_Char" minOccurs="0"/>
<xsd:element name="grow" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="shp" type="CT_Shp" minOccurs="0"/>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_D">
<xsd:sequence>
<xsd:element name="dPr" type="CT_DPr" minOccurs="0"/>
<xsd:element name="e" type="CT_OMathArg" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_EqArrPr">
<xsd:sequence>
<xsd:element name="baseJc" type="CT_YAlign" minOccurs="0"/>
<xsd:element name="maxDist" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="objDist" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="rSpRule" type="CT_SpacingRule" minOccurs="0"/>
<xsd:element name="rSp" type="CT_UnSignedInteger" minOccurs="0"/>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_EqArr">
<xsd:sequence>
<xsd:element name="eqArrPr" type="CT_EqArrPr" minOccurs="0"/>
<xsd:element name="e" type="CT_OMathArg" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_FPr">
<xsd:sequence>
<xsd:element name="type" type="CT_FType" minOccurs="0"/>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_F">
<xsd:sequence>
<xsd:element name="fPr" type="CT_FPr" minOccurs="0"/>
<xsd:element name="num" type="CT_OMathArg"/>
<xsd:element name="den" type="CT_OMathArg"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_FuncPr">
<xsd:sequence>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Func">
<xsd:sequence>
<xsd:element name="funcPr" type="CT_FuncPr" minOccurs="0"/>
<xsd:element name="fName" type="CT_OMathArg"/>
<xsd:element name="e" type="CT_OMathArg"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_GroupChrPr">
<xsd:sequence>
<xsd:element name="chr" type="CT_Char" minOccurs="0"/>
<xsd:element name="pos" type="CT_TopBot" minOccurs="0"/>
<xsd:element name="vertJc" type="CT_TopBot" minOccurs="0"/>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_GroupChr">
<xsd:sequence>
<xsd:element name="groupChrPr" type="CT_GroupChrPr" minOccurs="0"/>
<xsd:element name="e" type="CT_OMathArg"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_LimLowPr">
<xsd:sequence>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_LimLow">
<xsd:sequence>
<xsd:element name="limLowPr" type="CT_LimLowPr" minOccurs="0"/>
<xsd:element name="e" type="CT_OMathArg"/>
<xsd:element name="lim" type="CT_OMathArg"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_LimUppPr">
<xsd:sequence>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_LimUpp">
<xsd:sequence>
<xsd:element name="limUppPr" type="CT_LimUppPr" minOccurs="0"/>
<xsd:element name="e" type="CT_OMathArg"/>
<xsd:element name="lim" type="CT_OMathArg"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_MCPr">
<xsd:sequence>
<xsd:element name="count" type="CT_Integer255" minOccurs="0"/>
<xsd:element name="mcJc" type="CT_XAlign" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_MC">
<xsd:sequence>
<xsd:element name="mcPr" type="CT_MCPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_MCS">
<xsd:sequence>
<xsd:element name="mc" type="CT_MC" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_MPr">
<xsd:sequence>
<xsd:element name="baseJc" type="CT_YAlign" minOccurs="0"/>
<xsd:element name="plcHide" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="rSpRule" type="CT_SpacingRule" minOccurs="0"/>
<xsd:element name="cGpRule" type="CT_SpacingRule" minOccurs="0"/>
<xsd:element name="rSp" type="CT_UnSignedInteger" minOccurs="0"/>
<xsd:element name="cSp" type="CT_UnSignedInteger" minOccurs="0"/>
<xsd:element name="cGp" type="CT_UnSignedInteger" minOccurs="0"/>
<xsd:element name="mcs" type="CT_MCS" minOccurs="0"/>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_MR">
<xsd:sequence>
<xsd:element name="e" type="CT_OMathArg" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_M">
<xsd:sequence>
<xsd:element name="mPr" type="CT_MPr" minOccurs="0"/>
<xsd:element name="mr" type="CT_MR" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_NaryPr">
<xsd:sequence>
<xsd:element name="chr" type="CT_Char" minOccurs="0"/>
<xsd:element name="limLoc" type="CT_LimLoc" minOccurs="0"/>
<xsd:element name="grow" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="subHide" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="supHide" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Nary">
<xsd:sequence>
<xsd:element name="naryPr" type="CT_NaryPr" minOccurs="0"/>
<xsd:element name="sub" type="CT_OMathArg"/>
<xsd:element name="sup" type="CT_OMathArg"/>
<xsd:element name="e" type="CT_OMathArg"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_PhantPr">
<xsd:sequence>
<xsd:element name="show" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="zeroWid" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="zeroAsc" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="zeroDesc" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="transp" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Phant">
<xsd:sequence>
<xsd:element name="phantPr" type="CT_PhantPr" minOccurs="0"/>
<xsd:element name="e" type="CT_OMathArg"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_RadPr">
<xsd:sequence>
<xsd:element name="degHide" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Rad">
<xsd:sequence>
<xsd:element name="radPr" type="CT_RadPr" minOccurs="0"/>
<xsd:element name="deg" type="CT_OMathArg"/>
<xsd:element name="e" type="CT_OMathArg"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_SPrePr">
<xsd:sequence>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_SPre">
<xsd:sequence>
<xsd:element name="sPrePr" type="CT_SPrePr" minOccurs="0"/>
<xsd:element name="sub" type="CT_OMathArg"/>
<xsd:element name="sup" type="CT_OMathArg"/>
<xsd:element name="e" type="CT_OMathArg"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_SSubPr">
<xsd:sequence>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_SSub">
<xsd:sequence>
<xsd:element name="sSubPr" type="CT_SSubPr" minOccurs="0"/>
<xsd:element name="e" type="CT_OMathArg"/>
<xsd:element name="sub" type="CT_OMathArg"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_SSubSupPr">
<xsd:sequence>
<xsd:element name="alnScr" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_SSubSup">
<xsd:sequence>
<xsd:element name="sSubSupPr" type="CT_SSubSupPr" minOccurs="0"/>
<xsd:element name="e" type="CT_OMathArg"/>
<xsd:element name="sub" type="CT_OMathArg"/>
<xsd:element name="sup" type="CT_OMathArg"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_SSupPr">
<xsd:sequence>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_SSup">
<xsd:sequence>
<xsd:element name="sSupPr" type="CT_SSupPr" minOccurs="0"/>
<xsd:element name="e" type="CT_OMathArg"/>
<xsd:element name="sup" type="CT_OMathArg"/>
</xsd:sequence>
</xsd:complexType>
<xsd:group name="EG_OMathMathElements">
<xsd:choice>
<xsd:element name="acc" type="CT_Acc"/>
<xsd:element name="bar" type="CT_Bar"/>
<xsd:element name="box" type="CT_Box"/>
<xsd:element name="borderBox" type="CT_BorderBox"/>
<xsd:element name="d" type="CT_D"/>
<xsd:element name="eqArr" type="CT_EqArr"/>
<xsd:element name="f" type="CT_F"/>
<xsd:element name="func" type="CT_Func"/>
<xsd:element name="groupChr" type="CT_GroupChr"/>
<xsd:element name="limLow" type="CT_LimLow"/>
<xsd:element name="limUpp" type="CT_LimUpp"/>
<xsd:element name="m" type="CT_M"/>
<xsd:element name="nary" type="CT_Nary"/>
<xsd:element name="phant" type="CT_Phant"/>
<xsd:element name="rad" type="CT_Rad"/>
<xsd:element name="sPre" type="CT_SPre"/>
<xsd:element name="sSub" type="CT_SSub"/>
<xsd:element name="sSubSup" type="CT_SSubSup"/>
<xsd:element name="sSup" type="CT_SSup"/>
<xsd:element name="r" type="CT_R"/>
</xsd:choice>
</xsd:group>
<xsd:group name="EG_OMathElements">
<xsd:choice>
<xsd:group ref="EG_OMathMathElements"/>
<xsd:group ref="w:EG_PContentMath"/>
</xsd:choice>
</xsd:group>
<xsd:complexType name="CT_OMathArgPr">
<xsd:sequence>
<xsd:element name="argSz" type="CT_Integer2" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_OMathArg">
<xsd:sequence>
<xsd:element name="argPr" type="CT_OMathArgPr" minOccurs="0"/>
<xsd:group ref="EG_OMathElements" minOccurs="0" maxOccurs="unbounded"/>
<xsd:element name="ctrlPr" type="CT_CtrlPr" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:simpleType name="ST_Jc">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="left"/>
<xsd:enumeration value="right"/>
<xsd:enumeration value="center"/>
<xsd:enumeration value="centerGroup"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_OMathJc">
<xsd:attribute name="val" type="ST_Jc"/>
</xsd:complexType>
<xsd:complexType name="CT_OMathParaPr">
<xsd:sequence>
<xsd:element name="jc" type="CT_OMathJc" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_TwipsMeasure">
<xsd:attribute name="val" type="s:ST_TwipsMeasure" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_BreakBin">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="before"/>
<xsd:enumeration value="after"/>
<xsd:enumeration value="repeat"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_BreakBin">
<xsd:attribute name="val" type="ST_BreakBin"/>
</xsd:complexType>
<xsd:simpleType name="ST_BreakBinSub">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="--"/>
<xsd:enumeration value="-+"/>
<xsd:enumeration value="+-"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_BreakBinSub">
<xsd:attribute name="val" type="ST_BreakBinSub"/>
</xsd:complexType>
<xsd:complexType name="CT_MathPr">
<xsd:sequence>
<xsd:element name="mathFont" type="CT_String" minOccurs="0"/>
<xsd:element name="brkBin" type="CT_BreakBin" minOccurs="0"/>
<xsd:element name="brkBinSub" type="CT_BreakBinSub" minOccurs="0"/>
<xsd:element name="smallFrac" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="dispDef" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="lMargin" type="CT_TwipsMeasure" minOccurs="0"/>
<xsd:element name="rMargin" type="CT_TwipsMeasure" minOccurs="0"/>
<xsd:element name="defJc" type="CT_OMathJc" minOccurs="0"/>
<xsd:element name="preSp" type="CT_TwipsMeasure" minOccurs="0"/>
<xsd:element name="postSp" type="CT_TwipsMeasure" minOccurs="0"/>
<xsd:element name="interSp" type="CT_TwipsMeasure" minOccurs="0"/>
<xsd:element name="intraSp" type="CT_TwipsMeasure" minOccurs="0"/>
<xsd:choice minOccurs="0">
<xsd:element name="wrapIndent" type="CT_TwipsMeasure"/>
<xsd:element name="wrapRight" type="CT_OnOff"/>
</xsd:choice>
<xsd:element name="intLim" type="CT_LimLoc" minOccurs="0"/>
<xsd:element name="naryLim" type="CT_LimLoc" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:element name="mathPr" type="CT_MathPr"/>
<xsd:complexType name="CT_OMathPara">
<xsd:sequence>
<xsd:element name="oMathParaPr" type="CT_OMathParaPr" minOccurs="0"/>
<xsd:element name="oMath" type="CT_OMath" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_OMath">
<xsd:sequence>
<xsd:group ref="EG_OMathElements" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:element name="oMathPara" type="CT_OMathPara"/>
<xsd:element name="oMath" type="CT_OMath"/>
</xsd:schema>

25
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd Normal file
View File

@@ -0,0 +1,25 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns="http://schemas.openxmlformats.org/officeDocument/2006/relationships"
xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships"
elementFormDefault="qualified"
targetNamespace="http://schemas.openxmlformats.org/officeDocument/2006/relationships"
blockDefault="#all">
<xsd:simpleType name="ST_RelationshipId">
<xsd:restriction base="xsd:string"/>
</xsd:simpleType>
<xsd:attribute name="id" type="ST_RelationshipId"/>
<xsd:attribute name="embed" type="ST_RelationshipId"/>
<xsd:attribute name="link" type="ST_RelationshipId"/>
<xsd:attribute name="dm" type="ST_RelationshipId" default=""/>
<xsd:attribute name="lo" type="ST_RelationshipId" default=""/>
<xsd:attribute name="qs" type="ST_RelationshipId" default=""/>
<xsd:attribute name="cs" type="ST_RelationshipId" default=""/>
<xsd:attribute name="blip" type="ST_RelationshipId" default=""/>
<xsd:attribute name="pict" type="ST_RelationshipId"/>
<xsd:attribute name="href" type="ST_RelationshipId"/>
<xsd:attribute name="topLeft" type="ST_RelationshipId"/>
<xsd:attribute name="topRight" type="ST_RelationshipId"/>
<xsd:attribute name="bottomLeft" type="ST_RelationshipId"/>
<xsd:attribute name="bottomRight" type="ST_RelationshipId"/>
</xsd:schema>

4439
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/sml.xsd Normal file
View File

File diff suppressed because it is too large Load Diff

570
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-main.xsd Normal file
View File

@@ -0,0 +1,570 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns="urn:schemas-microsoft-com:vml"
xmlns:pvml="urn:schemas-microsoft-com:office:powerpoint"
xmlns:o="urn:schemas-microsoft-com:office:office"
xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"
xmlns:w10="urn:schemas-microsoft-com:office:word"
xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships"
xmlns:x="urn:schemas-microsoft-com:office:excel"
xmlns:s="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
targetNamespace="urn:schemas-microsoft-com:vml" elementFormDefault="qualified"
attributeFormDefault="unqualified">
<xsd:import namespace="urn:schemas-microsoft-com:office:office"
schemaLocation="vml-officeDrawing.xsd"/>
<xsd:import namespace="http://schemas.openxmlformats.org/wordprocessingml/2006/main"
schemaLocation="wml.xsd"/>
<xsd:import namespace="urn:schemas-microsoft-com:office:word"
schemaLocation="vml-wordprocessingDrawing.xsd"/>
<xsd:import namespace="http://schemas.openxmlformats.org/officeDocument/2006/relationships"
schemaLocation="shared-relationshipReference.xsd"/>
<xsd:import namespace="urn:schemas-microsoft-com:office:excel"
schemaLocation="vml-spreadsheetDrawing.xsd"/>
<xsd:import namespace="urn:schemas-microsoft-com:office:powerpoint"
schemaLocation="vml-presentationDrawing.xsd"/>
<xsd:import namespace="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
schemaLocation="shared-commonSimpleTypes.xsd"/>
<xsd:attributeGroup name="AG_Id">
<xsd:attribute name="id" type="xsd:string" use="optional"/>
</xsd:attributeGroup>
<xsd:attributeGroup name="AG_Style">
<xsd:attribute name="style" type="xsd:string" use="optional"/>
</xsd:attributeGroup>
<xsd:attributeGroup name="AG_Type">
<xsd:attribute name="type" type="xsd:string" use="optional"/>
</xsd:attributeGroup>
<xsd:attributeGroup name="AG_Adj">
<xsd:attribute name="adj" type="xsd:string" use="optional"/>
</xsd:attributeGroup>
<xsd:attributeGroup name="AG_Path">
<xsd:attribute name="path" type="xsd:string" use="optional"/>
</xsd:attributeGroup>
<xsd:attributeGroup name="AG_Fill">
<xsd:attribute name="filled" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="fillcolor" type="s:ST_ColorType" use="optional"/>
</xsd:attributeGroup>
<xsd:attributeGroup name="AG_Chromakey">
<xsd:attribute name="chromakey" type="s:ST_ColorType" use="optional"/>
</xsd:attributeGroup>
<xsd:attributeGroup name="AG_Ext">
<xsd:attribute name="ext" form="qualified" type="ST_Ext"/>
</xsd:attributeGroup>
<xsd:attributeGroup name="AG_CoreAttributes">
<xsd:attributeGroup ref="AG_Id"/>
<xsd:attributeGroup ref="AG_Style"/>
<xsd:attribute name="href" type="xsd:string" use="optional"/>
<xsd:attribute name="target" type="xsd:string" use="optional"/>
<xsd:attribute name="class" type="xsd:string" use="optional"/>
<xsd:attribute name="title" type="xsd:string" use="optional"/>
<xsd:attribute name="alt" type="xsd:string" use="optional"/>
<xsd:attribute name="coordsize" type="xsd:string" use="optional"/>
<xsd:attribute name="coordorigin" type="xsd:string" use="optional"/>
<xsd:attribute name="wrapcoords" type="xsd:string" use="optional"/>
<xsd:attribute name="print" type="s:ST_TrueFalse" use="optional"/>
</xsd:attributeGroup>
<xsd:attributeGroup name="AG_ShapeAttributes">
<xsd:attributeGroup ref="AG_Chromakey"/>
<xsd:attributeGroup ref="AG_Fill"/>
<xsd:attribute name="opacity" type="xsd:string" use="optional"/>
<xsd:attribute name="stroked" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="strokecolor" type="s:ST_ColorType" use="optional"/>
<xsd:attribute name="strokeweight" type="xsd:string" use="optional"/>
<xsd:attribute name="insetpen" type="s:ST_TrueFalse" use="optional"/>
</xsd:attributeGroup>
<xsd:attributeGroup name="AG_OfficeCoreAttributes">
<xsd:attribute ref="o:spid"/>
<xsd:attribute ref="o:oned"/>
<xsd:attribute ref="o:regroupid"/>
<xsd:attribute ref="o:doubleclicknotify"/>
<xsd:attribute ref="o:button"/>
<xsd:attribute ref="o:userhidden"/>
<xsd:attribute ref="o:bullet"/>
<xsd:attribute ref="o:hr"/>
<xsd:attribute ref="o:hrstd"/>
<xsd:attribute ref="o:hrnoshade"/>
<xsd:attribute ref="o:hrpct"/>
<xsd:attribute ref="o:hralign"/>
<xsd:attribute ref="o:allowincell"/>
<xsd:attribute ref="o:allowoverlap"/>
<xsd:attribute ref="o:userdrawn"/>
<xsd:attribute ref="o:bordertopcolor"/>
<xsd:attribute ref="o:borderleftcolor"/>
<xsd:attribute ref="o:borderbottomcolor"/>
<xsd:attribute ref="o:borderrightcolor"/>
<xsd:attribute ref="o:dgmlayout"/>
<xsd:attribute ref="o:dgmnodekind"/>
<xsd:attribute ref="o:dgmlayoutmru"/>
<xsd:attribute ref="o:insetmode"/>
</xsd:attributeGroup>
<xsd:attributeGroup name="AG_OfficeShapeAttributes">
<xsd:attribute ref="o:spt"/>
<xsd:attribute ref="o:connectortype"/>
<xsd:attribute ref="o:bwmode"/>
<xsd:attribute ref="o:bwpure"/>
<xsd:attribute ref="o:bwnormal"/>
<xsd:attribute ref="o:forcedash"/>
<xsd:attribute ref="o:oleicon"/>
<xsd:attribute ref="o:ole"/>
<xsd:attribute ref="o:preferrelative"/>
<xsd:attribute ref="o:cliptowrap"/>
<xsd:attribute ref="o:clip"/>
</xsd:attributeGroup>
<xsd:attributeGroup name="AG_AllCoreAttributes">
<xsd:attributeGroup ref="AG_CoreAttributes"/>
<xsd:attributeGroup ref="AG_OfficeCoreAttributes"/>
</xsd:attributeGroup>
<xsd:attributeGroup name="AG_AllShapeAttributes">
<xsd:attributeGroup ref="AG_ShapeAttributes"/>
<xsd:attributeGroup ref="AG_OfficeShapeAttributes"/>
</xsd:attributeGroup>
<xsd:attributeGroup name="AG_ImageAttributes">
<xsd:attribute name="src" type="xsd:string" use="optional"/>
<xsd:attribute name="cropleft" type="xsd:string" use="optional"/>
<xsd:attribute name="croptop" type="xsd:string" use="optional"/>
<xsd:attribute name="cropright" type="xsd:string" use="optional"/>
<xsd:attribute name="cropbottom" type="xsd:string" use="optional"/>
<xsd:attribute name="gain" type="xsd:string" use="optional"/>
<xsd:attribute name="blacklevel" type="xsd:string" use="optional"/>
<xsd:attribute name="gamma" type="xsd:string" use="optional"/>
<xsd:attribute name="grayscale" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="bilevel" type="s:ST_TrueFalse" use="optional"/>
</xsd:attributeGroup>
<xsd:attributeGroup name="AG_StrokeAttributes">
<xsd:attribute name="on" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="weight" type="xsd:string" use="optional"/>
<xsd:attribute name="color" type="s:ST_ColorType" use="optional"/>
<xsd:attribute name="opacity" type="xsd:string" use="optional"/>
<xsd:attribute name="linestyle" type="ST_StrokeLineStyle" use="optional"/>
<xsd:attribute name="miterlimit" type="xsd:decimal" use="optional"/>
<xsd:attribute name="joinstyle" type="ST_StrokeJoinStyle" use="optional"/>
<xsd:attribute name="endcap" type="ST_StrokeEndCap" use="optional"/>
<xsd:attribute name="dashstyle" type="xsd:string" use="optional"/>
<xsd:attribute name="filltype" type="ST_FillType" use="optional"/>
<xsd:attribute name="src" type="xsd:string" use="optional"/>
<xsd:attribute name="imageaspect" type="ST_ImageAspect" use="optional"/>
<xsd:attribute name="imagesize" type="xsd:string" use="optional"/>
<xsd:attribute name="imagealignshape" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="color2" type="s:ST_ColorType" use="optional"/>
<xsd:attribute name="startarrow" type="ST_StrokeArrowType" use="optional"/>
<xsd:attribute name="startarrowwidth" type="ST_StrokeArrowWidth" use="optional"/>
<xsd:attribute name="startarrowlength" type="ST_StrokeArrowLength" use="optional"/>
<xsd:attribute name="endarrow" type="ST_StrokeArrowType" use="optional"/>
<xsd:attribute name="endarrowwidth" type="ST_StrokeArrowWidth" use="optional"/>
<xsd:attribute name="endarrowlength" type="ST_StrokeArrowLength" use="optional"/>
<xsd:attribute ref="o:href"/>
<xsd:attribute ref="o:althref"/>
<xsd:attribute ref="o:title"/>
<xsd:attribute ref="o:forcedash"/>
<xsd:attribute ref="r:id" use="optional"/>
<xsd:attribute name="insetpen" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute ref="o:relid"/>
</xsd:attributeGroup>
<xsd:group name="EG_ShapeElements">
<xsd:choice>
<xsd:element ref="path"/>
<xsd:element ref="formulas"/>
<xsd:element ref="handles"/>
<xsd:element ref="fill"/>
<xsd:element ref="stroke"/>
<xsd:element ref="shadow"/>
<xsd:element ref="textbox"/>
<xsd:element ref="textpath"/>
<xsd:element ref="imagedata"/>
<xsd:element ref="o:skew"/>
<xsd:element ref="o:extrusion"/>
<xsd:element ref="o:callout"/>
<xsd:element ref="o:lock"/>
<xsd:element ref="o:clippath"/>
<xsd:element ref="o:signatureline"/>
<xsd:element ref="w10:wrap"/>
<xsd:element ref="w10:anchorlock"/>
<xsd:element ref="w10:bordertop"/>
<xsd:element ref="w10:borderbottom"/>
<xsd:element ref="w10:borderleft"/>
<xsd:element ref="w10:borderright"/>
<xsd:element ref="x:ClientData" minOccurs="0"/>
<xsd:element ref="pvml:textdata" minOccurs="0"/>
</xsd:choice>
</xsd:group>
<xsd:element name="shape" type="CT_Shape"/>
<xsd:element name="shapetype" type="CT_Shapetype"/>
<xsd:element name="group" type="CT_Group"/>
<xsd:element name="background" type="CT_Background"/>
<xsd:complexType name="CT_Shape">
<xsd:choice maxOccurs="unbounded">
<xsd:group ref="EG_ShapeElements"/>
<xsd:element ref="o:ink"/>
<xsd:element ref="pvml:iscomment"/>
<xsd:element ref="o:equationxml"/>
</xsd:choice>
<xsd:attributeGroup ref="AG_AllCoreAttributes"/>
<xsd:attributeGroup ref="AG_AllShapeAttributes"/>
<xsd:attributeGroup ref="AG_Type"/>
<xsd:attributeGroup ref="AG_Adj"/>
<xsd:attributeGroup ref="AG_Path"/>
<xsd:attribute ref="o:gfxdata"/>
<xsd:attribute name="equationxml" type="xsd:string" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_Shapetype">
<xsd:sequence>
<xsd:group ref="EG_ShapeElements" minOccurs="0" maxOccurs="unbounded"/>
<xsd:element ref="o:complex" minOccurs="0"/>
</xsd:sequence>
<xsd:attributeGroup ref="AG_AllCoreAttributes"/>
<xsd:attributeGroup ref="AG_AllShapeAttributes"/>
<xsd:attributeGroup ref="AG_Adj"/>
<xsd:attributeGroup ref="AG_Path"/>
<xsd:attribute ref="o:master"/>
</xsd:complexType>
<xsd:complexType name="CT_Group">
<xsd:choice maxOccurs="unbounded">
<xsd:group ref="EG_ShapeElements"/>
<xsd:element ref="group"/>
<xsd:element ref="shape"/>
<xsd:element ref="shapetype"/>
<xsd:element ref="arc"/>
<xsd:element ref="curve"/>
<xsd:element ref="image"/>
<xsd:element ref="line"/>
<xsd:element ref="oval"/>
<xsd:element ref="polyline"/>
<xsd:element ref="rect"/>
<xsd:element ref="roundrect"/>
<xsd:element ref="o:diagram"/>
</xsd:choice>
<xsd:attributeGroup ref="AG_AllCoreAttributes"/>
<xsd:attributeGroup ref="AG_Fill"/>
<xsd:attribute name="editas" type="ST_EditAs" use="optional"/>
<xsd:attribute ref="o:tableproperties"/>
<xsd:attribute ref="o:tablelimits"/>
</xsd:complexType>
<xsd:complexType name="CT_Background">
<xsd:sequence>
<xsd:element ref="fill" minOccurs="0"/>
</xsd:sequence>
<xsd:attributeGroup ref="AG_Id"/>
<xsd:attributeGroup ref="AG_Fill"/>
<xsd:attribute ref="o:bwmode"/>
<xsd:attribute ref="o:bwpure"/>
<xsd:attribute ref="o:bwnormal"/>
<xsd:attribute ref="o:targetscreensize"/>
</xsd:complexType>
<xsd:element name="fill" type="CT_Fill"/>
<xsd:element name="formulas" type="CT_Formulas"/>
<xsd:element name="handles" type="CT_Handles"/>
<xsd:element name="imagedata" type="CT_ImageData"/>
<xsd:element name="path" type="CT_Path"/>
<xsd:element name="textbox" type="CT_Textbox"/>
<xsd:element name="shadow" type="CT_Shadow"/>
<xsd:element name="stroke" type="CT_Stroke"/>
<xsd:element name="textpath" type="CT_TextPath"/>
<xsd:complexType name="CT_Fill">
<xsd:sequence>
<xsd:element ref="o:fill" minOccurs="0"/>
</xsd:sequence>
<xsd:attributeGroup ref="AG_Id"/>
<xsd:attribute name="type" type="ST_FillType" use="optional"/>
<xsd:attribute name="on" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="color" type="s:ST_ColorType" use="optional"/>
<xsd:attribute name="opacity" type="xsd:string" use="optional"/>
<xsd:attribute name="color2" type="s:ST_ColorType" use="optional"/>
<xsd:attribute name="src" type="xsd:string" use="optional"/>
<xsd:attribute ref="o:href"/>
<xsd:attribute ref="o:althref"/>
<xsd:attribute name="size" type="xsd:string" use="optional"/>
<xsd:attribute name="origin" type="xsd:string" use="optional"/>
<xsd:attribute name="position" type="xsd:string" use="optional"/>
<xsd:attribute name="aspect" type="ST_ImageAspect" use="optional"/>
<xsd:attribute name="colors" type="xsd:string" use="optional"/>
<xsd:attribute name="angle" type="xsd:decimal" use="optional"/>
<xsd:attribute name="alignshape" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="focus" type="xsd:string" use="optional"/>
<xsd:attribute name="focussize" type="xsd:string" use="optional"/>
<xsd:attribute name="focusposition" type="xsd:string" use="optional"/>
<xsd:attribute name="method" type="ST_FillMethod" use="optional"/>
<xsd:attribute ref="o:detectmouseclick"/>
<xsd:attribute ref="o:title"/>
<xsd:attribute ref="o:opacity2"/>
<xsd:attribute name="recolor" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="rotate" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute ref="r:id" use="optional"/>
<xsd:attribute ref="o:relid" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_Formulas">
<xsd:sequence>
<xsd:element name="f" type="CT_F" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_F">
<xsd:attribute name="eqn" type="xsd:string"/>
</xsd:complexType>
<xsd:complexType name="CT_Handles">
<xsd:sequence>
<xsd:element name="h" type="CT_H" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_H">
<xsd:attribute name="position" type="xsd:string"/>
<xsd:attribute name="polar" type="xsd:string"/>
<xsd:attribute name="map" type="xsd:string"/>
<xsd:attribute name="invx" type="s:ST_TrueFalse"/>
<xsd:attribute name="invy" type="s:ST_TrueFalse"/>
<xsd:attribute name="switch" type="s:ST_TrueFalseBlank"/>
<xsd:attribute name="xrange" type="xsd:string"/>
<xsd:attribute name="yrange" type="xsd:string"/>
<xsd:attribute name="radiusrange" type="xsd:string"/>
</xsd:complexType>
<xsd:complexType name="CT_ImageData">
<xsd:attributeGroup ref="AG_Id"/>
<xsd:attributeGroup ref="AG_ImageAttributes"/>
<xsd:attributeGroup ref="AG_Chromakey"/>
<xsd:attribute name="embosscolor" type="s:ST_ColorType" use="optional"/>
<xsd:attribute name="recolortarget" type="s:ST_ColorType"/>
<xsd:attribute ref="o:href"/>
<xsd:attribute ref="o:althref"/>
<xsd:attribute ref="o:title"/>
<xsd:attribute ref="o:oleid"/>
<xsd:attribute ref="o:detectmouseclick"/>
<xsd:attribute ref="o:movie"/>
<xsd:attribute ref="o:relid"/>
<xsd:attribute ref="r:id"/>
<xsd:attribute ref="r:pict"/>
<xsd:attribute ref="r:href"/>
</xsd:complexType>
<xsd:complexType name="CT_Path">
<xsd:attributeGroup ref="AG_Id"/>
<xsd:attribute name="v" type="xsd:string" use="optional"/>
<xsd:attribute name="limo" type="xsd:string" use="optional"/>
<xsd:attribute name="textboxrect" type="xsd:string" use="optional"/>
<xsd:attribute name="fillok" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="strokeok" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="shadowok" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="arrowok" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="gradientshapeok" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="textpathok" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="insetpenok" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute ref="o:connecttype"/>
<xsd:attribute ref="o:connectlocs"/>
<xsd:attribute ref="o:connectangles"/>
<xsd:attribute ref="o:extrusionok"/>
</xsd:complexType>
<xsd:complexType name="CT_Shadow">
<xsd:attributeGroup ref="AG_Id"/>
<xsd:attribute name="on" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="type" type="ST_ShadowType" use="optional"/>
<xsd:attribute name="obscured" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="color" type="s:ST_ColorType" use="optional"/>
<xsd:attribute name="opacity" type="xsd:string" use="optional"/>
<xsd:attribute name="offset" type="xsd:string" use="optional"/>
<xsd:attribute name="color2" type="s:ST_ColorType" use="optional"/>
<xsd:attribute name="offset2" type="xsd:string" use="optional"/>
<xsd:attribute name="origin" type="xsd:string" use="optional"/>
<xsd:attribute name="matrix" type="xsd:string" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_Stroke">
<xsd:sequence>
<xsd:element ref="o:left" minOccurs="0"/>
<xsd:element ref="o:top" minOccurs="0"/>
<xsd:element ref="o:right" minOccurs="0"/>
<xsd:element ref="o:bottom" minOccurs="0"/>
<xsd:element ref="o:column" minOccurs="0"/>
</xsd:sequence>
<xsd:attributeGroup ref="AG_Id"/>
<xsd:attributeGroup ref="AG_StrokeAttributes"/>
</xsd:complexType>
<xsd:complexType name="CT_Textbox">
<xsd:choice>
<xsd:element ref="w:txbxContent" minOccurs="0"/>
<xsd:any namespace="##local" processContents="skip"/>
</xsd:choice>
<xsd:attributeGroup ref="AG_Id"/>
<xsd:attributeGroup ref="AG_Style"/>
<xsd:attribute name="inset" type="xsd:string" use="optional"/>
<xsd:attribute ref="o:singleclick"/>
<xsd:attribute ref="o:insetmode"/>
</xsd:complexType>
<xsd:complexType name="CT_TextPath">
<xsd:attributeGroup ref="AG_Id"/>
<xsd:attributeGroup ref="AG_Style"/>
<xsd:attribute name="on" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="fitshape" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="fitpath" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="trim" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="xscale" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="string" type="xsd:string" use="optional"/>
</xsd:complexType>
<xsd:element name="arc" type="CT_Arc"/>
<xsd:element name="curve" type="CT_Curve"/>
<xsd:element name="image" type="CT_Image"/>
<xsd:element name="line" type="CT_Line"/>
<xsd:element name="oval" type="CT_Oval"/>
<xsd:element name="polyline" type="CT_PolyLine"/>
<xsd:element name="rect" type="CT_Rect"/>
<xsd:element name="roundrect" type="CT_RoundRect"/>
<xsd:complexType name="CT_Arc">
<xsd:sequence>
<xsd:group ref="EG_ShapeElements" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
<xsd:attributeGroup ref="AG_AllCoreAttributes"/>
<xsd:attributeGroup ref="AG_AllShapeAttributes"/>
<xsd:attribute name="startAngle" type="xsd:decimal" use="optional"/>
<xsd:attribute name="endAngle" type="xsd:decimal" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_Curve">
<xsd:sequence>
<xsd:group ref="EG_ShapeElements" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
<xsd:attributeGroup ref="AG_AllCoreAttributes"/>
<xsd:attributeGroup ref="AG_AllShapeAttributes"/>
<xsd:attribute name="from" type="xsd:string" use="optional"/>
<xsd:attribute name="control1" type="xsd:string" use="optional"/>
<xsd:attribute name="control2" type="xsd:string" use="optional"/>
<xsd:attribute name="to" type="xsd:string" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_Image">
<xsd:sequence>
<xsd:group ref="EG_ShapeElements" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
<xsd:attributeGroup ref="AG_AllCoreAttributes"/>
<xsd:attributeGroup ref="AG_AllShapeAttributes"/>
<xsd:attributeGroup ref="AG_ImageAttributes"/>
</xsd:complexType>
<xsd:complexType name="CT_Line">
<xsd:sequence>
<xsd:group ref="EG_ShapeElements" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
<xsd:attributeGroup ref="AG_AllCoreAttributes"/>
<xsd:attributeGroup ref="AG_AllShapeAttributes"/>
<xsd:attribute name="from" type="xsd:string" use="optional"/>
<xsd:attribute name="to" type="xsd:string" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_Oval">
<xsd:choice maxOccurs="unbounded">
<xsd:group ref="EG_ShapeElements" minOccurs="0" maxOccurs="unbounded"/>
</xsd:choice>
<xsd:attributeGroup ref="AG_AllCoreAttributes"/>
<xsd:attributeGroup ref="AG_AllShapeAttributes"/>
</xsd:complexType>
<xsd:complexType name="CT_PolyLine">
<xsd:choice minOccurs="0" maxOccurs="unbounded">
<xsd:group ref="EG_ShapeElements"/>
<xsd:element ref="o:ink"/>
</xsd:choice>
<xsd:attributeGroup ref="AG_AllCoreAttributes"/>
<xsd:attributeGroup ref="AG_AllShapeAttributes"/>
<xsd:attribute name="points" type="xsd:string" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_Rect">
<xsd:choice maxOccurs="unbounded">
<xsd:group ref="EG_ShapeElements" minOccurs="0" maxOccurs="unbounded"/>
</xsd:choice>
<xsd:attributeGroup ref="AG_AllCoreAttributes"/>
<xsd:attributeGroup ref="AG_AllShapeAttributes"/>
</xsd:complexType>
<xsd:complexType name="CT_RoundRect">
<xsd:choice maxOccurs="unbounded">
<xsd:group ref="EG_ShapeElements" minOccurs="0" maxOccurs="unbounded"/>
</xsd:choice>
<xsd:attributeGroup ref="AG_AllCoreAttributes"/>
<xsd:attributeGroup ref="AG_AllShapeAttributes"/>
<xsd:attribute name="arcsize" type="xsd:string" use="optional"/>
</xsd:complexType>
<xsd:simpleType name="ST_Ext">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="view"/>
<xsd:enumeration value="edit"/>
<xsd:enumeration value="backwardCompatible"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_FillType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="solid"/>
<xsd:enumeration value="gradient"/>
<xsd:enumeration value="gradientRadial"/>
<xsd:enumeration value="tile"/>
<xsd:enumeration value="pattern"/>
<xsd:enumeration value="frame"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_FillMethod">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="none"/>
<xsd:enumeration value="linear"/>
<xsd:enumeration value="sigma"/>
<xsd:enumeration value="any"/>
<xsd:enumeration value="linear sigma"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_ShadowType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="single"/>
<xsd:enumeration value="double"/>
<xsd:enumeration value="emboss"/>
<xsd:enumeration value="perspective"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_StrokeLineStyle">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="single"/>
<xsd:enumeration value="thinThin"/>
<xsd:enumeration value="thinThick"/>
<xsd:enumeration value="thickThin"/>
<xsd:enumeration value="thickBetweenThin"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_StrokeJoinStyle">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="round"/>
<xsd:enumeration value="bevel"/>
<xsd:enumeration value="miter"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_StrokeEndCap">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="flat"/>
<xsd:enumeration value="square"/>
<xsd:enumeration value="round"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_StrokeArrowLength">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="short"/>
<xsd:enumeration value="medium"/>
<xsd:enumeration value="long"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_StrokeArrowWidth">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="narrow"/>
<xsd:enumeration value="medium"/>
<xsd:enumeration value="wide"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_StrokeArrowType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="none"/>
<xsd:enumeration value="block"/>
<xsd:enumeration value="classic"/>
<xsd:enumeration value="oval"/>
<xsd:enumeration value="diamond"/>
<xsd:enumeration value="open"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_ImageAspect">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="ignore"/>
<xsd:enumeration value="atMost"/>
<xsd:enumeration value="atLeast"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_EditAs">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="canvas"/>
<xsd:enumeration value="orgchart"/>
<xsd:enumeration value="radial"/>
<xsd:enumeration value="cycle"/>
<xsd:enumeration value="stacked"/>
<xsd:enumeration value="venn"/>
<xsd:enumeration value="bullseye"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:schema>

509
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd Normal file
View File

@@ -0,0 +1,509 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns="urn:schemas-microsoft-com:office:office" xmlns:v="urn:schemas-microsoft-com:vml"
xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships"
xmlns:s="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
targetNamespace="urn:schemas-microsoft-com:office:office" elementFormDefault="qualified"
attributeFormDefault="unqualified">
<xsd:import namespace="urn:schemas-microsoft-com:vml" schemaLocation="vml-main.xsd"/>
<xsd:import namespace="http://schemas.openxmlformats.org/officeDocument/2006/relationships"
schemaLocation="shared-relationshipReference.xsd"/>
<xsd:import namespace="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
schemaLocation="shared-commonSimpleTypes.xsd"/>
<xsd:attribute name="bwmode" type="ST_BWMode"/>
<xsd:attribute name="bwpure" type="ST_BWMode"/>
<xsd:attribute name="bwnormal" type="ST_BWMode"/>
<xsd:attribute name="targetscreensize" type="ST_ScreenSize"/>
<xsd:attribute name="insetmode" type="ST_InsetMode" default="custom"/>
<xsd:attribute name="spt" type="xsd:float"/>
<xsd:attribute name="wrapcoords" type="xsd:string"/>
<xsd:attribute name="oned" type="s:ST_TrueFalse"/>
<xsd:attribute name="regroupid" type="xsd:integer"/>
<xsd:attribute name="doubleclicknotify" type="s:ST_TrueFalse"/>
<xsd:attribute name="connectortype" type="ST_ConnectorType" default="straight"/>
<xsd:attribute name="button" type="s:ST_TrueFalse"/>
<xsd:attribute name="userhidden" type="s:ST_TrueFalse"/>
<xsd:attribute name="forcedash" type="s:ST_TrueFalse"/>
<xsd:attribute name="oleicon" type="s:ST_TrueFalse"/>
<xsd:attribute name="ole" type="s:ST_TrueFalseBlank"/>
<xsd:attribute name="preferrelative" type="s:ST_TrueFalse"/>
<xsd:attribute name="cliptowrap" type="s:ST_TrueFalse"/>
<xsd:attribute name="clip" type="s:ST_TrueFalse"/>
<xsd:attribute name="bullet" type="s:ST_TrueFalse"/>
<xsd:attribute name="hr" type="s:ST_TrueFalse"/>
<xsd:attribute name="hrstd" type="s:ST_TrueFalse"/>
<xsd:attribute name="hrnoshade" type="s:ST_TrueFalse"/>
<xsd:attribute name="hrpct" type="xsd:float"/>
<xsd:attribute name="hralign" type="ST_HrAlign" default="left"/>
<xsd:attribute name="allowincell" type="s:ST_TrueFalse"/>
<xsd:attribute name="allowoverlap" type="s:ST_TrueFalse"/>
<xsd:attribute name="userdrawn" type="s:ST_TrueFalse"/>
<xsd:attribute name="bordertopcolor" type="xsd:string"/>
<xsd:attribute name="borderleftcolor" type="xsd:string"/>
<xsd:attribute name="borderbottomcolor" type="xsd:string"/>
<xsd:attribute name="borderrightcolor" type="xsd:string"/>
<xsd:attribute name="connecttype" type="ST_ConnectType"/>
<xsd:attribute name="connectlocs" type="xsd:string"/>
<xsd:attribute name="connectangles" type="xsd:string"/>
<xsd:attribute name="master" type="xsd:string"/>
<xsd:attribute name="extrusionok" type="s:ST_TrueFalse"/>
<xsd:attribute name="href" type="xsd:string"/>
<xsd:attribute name="althref" type="xsd:string"/>
<xsd:attribute name="title" type="xsd:string"/>
<xsd:attribute name="singleclick" type="s:ST_TrueFalse"/>
<xsd:attribute name="oleid" type="xsd:float"/>
<xsd:attribute name="detectmouseclick" type="s:ST_TrueFalse"/>
<xsd:attribute name="movie" type="xsd:float"/>
<xsd:attribute name="spid" type="xsd:string"/>
<xsd:attribute name="opacity2" type="xsd:string"/>
<xsd:attribute name="relid" type="r:ST_RelationshipId"/>
<xsd:attribute name="dgmlayout" type="ST_DiagramLayout"/>
<xsd:attribute name="dgmnodekind" type="xsd:integer"/>
<xsd:attribute name="dgmlayoutmru" type="ST_DiagramLayout"/>
<xsd:attribute name="gfxdata" type="xsd:base64Binary"/>
<xsd:attribute name="tableproperties" type="xsd:string"/>
<xsd:attribute name="tablelimits" type="xsd:string"/>
<xsd:element name="shapedefaults" type="CT_ShapeDefaults"/>
<xsd:element name="shapelayout" type="CT_ShapeLayout"/>
<xsd:element name="signatureline" type="CT_SignatureLine"/>
<xsd:element name="ink" type="CT_Ink"/>
<xsd:element name="diagram" type="CT_Diagram"/>
<xsd:element name="equationxml" type="CT_EquationXml"/>
<xsd:complexType name="CT_ShapeDefaults">
<xsd:all minOccurs="0">
<xsd:element ref="v:fill" minOccurs="0"/>
<xsd:element ref="v:stroke" minOccurs="0"/>
<xsd:element ref="v:textbox" minOccurs="0"/>
<xsd:element ref="v:shadow" minOccurs="0"/>
<xsd:element ref="skew" minOccurs="0"/>
<xsd:element ref="extrusion" minOccurs="0"/>
<xsd:element ref="callout" minOccurs="0"/>
<xsd:element ref="lock" minOccurs="0"/>
<xsd:element name="colormru" minOccurs="0" type="CT_ColorMru"/>
<xsd:element name="colormenu" minOccurs="0" type="CT_ColorMenu"/>
</xsd:all>
<xsd:attributeGroup ref="v:AG_Ext"/>
<xsd:attribute name="spidmax" type="xsd:integer" use="optional"/>
<xsd:attribute name="style" type="xsd:string" use="optional"/>
<xsd:attribute name="fill" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="fillcolor" type="s:ST_ColorType" use="optional"/>
<xsd:attribute name="stroke" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="strokecolor" type="s:ST_ColorType"/>
<xsd:attribute name="allowincell" form="qualified" type="s:ST_TrueFalse"/>
</xsd:complexType>
<xsd:complexType name="CT_Ink">
<xsd:sequence/>
<xsd:attribute name="i" type="xsd:string"/>
<xsd:attribute name="annotation" type="s:ST_TrueFalse"/>
<xsd:attribute name="contentType" type="ST_ContentType" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_SignatureLine">
<xsd:attributeGroup ref="v:AG_Ext"/>
<xsd:attribute name="issignatureline" type="s:ST_TrueFalse"/>
<xsd:attribute name="id" type="s:ST_Guid"/>
<xsd:attribute name="provid" type="s:ST_Guid"/>
<xsd:attribute name="signinginstructionsset" type="s:ST_TrueFalse"/>
<xsd:attribute name="allowcomments" type="s:ST_TrueFalse"/>
<xsd:attribute name="showsigndate" type="s:ST_TrueFalse"/>
<xsd:attribute name="suggestedsigner" type="xsd:string" form="qualified"/>
<xsd:attribute name="suggestedsigner2" type="xsd:string" form="qualified"/>
<xsd:attribute name="suggestedsigneremail" type="xsd:string" form="qualified"/>
<xsd:attribute name="signinginstructions" type="xsd:string"/>
<xsd:attribute name="addlxml" type="xsd:string"/>
<xsd:attribute name="sigprovurl" type="xsd:string"/>
</xsd:complexType>
<xsd:complexType name="CT_ShapeLayout">
<xsd:all>
<xsd:element name="idmap" type="CT_IdMap" minOccurs="0"/>
<xsd:element name="regrouptable" type="CT_RegroupTable" minOccurs="0"/>
<xsd:element name="rules" type="CT_Rules" minOccurs="0"/>
</xsd:all>
<xsd:attributeGroup ref="v:AG_Ext"/>
</xsd:complexType>
<xsd:complexType name="CT_IdMap">
<xsd:attributeGroup ref="v:AG_Ext"/>
<xsd:attribute name="data" type="xsd:string" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_RegroupTable">
<xsd:sequence>
<xsd:element name="entry" type="CT_Entry" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
<xsd:attributeGroup ref="v:AG_Ext"/>
</xsd:complexType>
<xsd:complexType name="CT_Entry">
<xsd:attribute name="new" type="xsd:int" use="optional"/>
<xsd:attribute name="old" type="xsd:int" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_Rules">
<xsd:sequence>
<xsd:element name="r" type="CT_R" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
<xsd:attributeGroup ref="v:AG_Ext"/>
</xsd:complexType>
<xsd:complexType name="CT_R">
<xsd:sequence>
<xsd:element name="proxy" type="CT_Proxy" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
<xsd:attribute name="id" type="xsd:string" use="required"/>
<xsd:attribute name="type" type="ST_RType" use="optional"/>
<xsd:attribute name="how" type="ST_How" use="optional"/>
<xsd:attribute name="idref" type="xsd:string" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_Proxy">
<xsd:attribute name="start" type="s:ST_TrueFalseBlank" use="optional" default="false"/>
<xsd:attribute name="end" type="s:ST_TrueFalseBlank" use="optional" default="false"/>
<xsd:attribute name="idref" type="xsd:string" use="optional"/>
<xsd:attribute name="connectloc" type="xsd:int" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_Diagram">
<xsd:sequence>
<xsd:element name="relationtable" type="CT_RelationTable" minOccurs="0"/>
</xsd:sequence>
<xsd:attributeGroup ref="v:AG_Ext"/>
<xsd:attribute name="dgmstyle" type="xsd:integer" use="optional"/>
<xsd:attribute name="autoformat" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="reverse" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="autolayout" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="dgmscalex" type="xsd:integer" use="optional"/>
<xsd:attribute name="dgmscaley" type="xsd:integer" use="optional"/>
<xsd:attribute name="dgmfontsize" type="xsd:integer" use="optional"/>
<xsd:attribute name="constrainbounds" type="xsd:string" use="optional"/>
<xsd:attribute name="dgmbasetextscale" type="xsd:integer" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_EquationXml">
<xsd:sequence>
<xsd:any namespace="##any"/>
</xsd:sequence>
<xsd:attribute name="contentType" type="ST_AlternateMathContentType" use="optional"/>
</xsd:complexType>
<xsd:simpleType name="ST_AlternateMathContentType">
<xsd:restriction base="xsd:string"/>
</xsd:simpleType>
<xsd:complexType name="CT_RelationTable">
<xsd:sequence>
<xsd:element name="rel" type="CT_Relation" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
<xsd:attributeGroup ref="v:AG_Ext"/>
</xsd:complexType>
<xsd:complexType name="CT_Relation">
<xsd:attributeGroup ref="v:AG_Ext"/>
<xsd:attribute name="idsrc" type="xsd:string" use="optional"/>
<xsd:attribute name="iddest" type="xsd:string" use="optional"/>
<xsd:attribute name="idcntr" type="xsd:string" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_ColorMru">
<xsd:attributeGroup ref="v:AG_Ext"/>
<xsd:attribute name="colors" type="xsd:string"/>
</xsd:complexType>
<xsd:complexType name="CT_ColorMenu">
<xsd:attributeGroup ref="v:AG_Ext"/>
<xsd:attribute name="strokecolor" type="s:ST_ColorType"/>
<xsd:attribute name="fillcolor" type="s:ST_ColorType"/>
<xsd:attribute name="shadowcolor" type="s:ST_ColorType"/>
<xsd:attribute name="extrusioncolor" type="s:ST_ColorType"/>
</xsd:complexType>
<xsd:element name="skew" type="CT_Skew"/>
<xsd:element name="extrusion" type="CT_Extrusion"/>
<xsd:element name="callout" type="CT_Callout"/>
<xsd:element name="lock" type="CT_Lock"/>
<xsd:element name="OLEObject" type="CT_OLEObject"/>
<xsd:element name="complex" type="CT_Complex"/>
<xsd:element name="left" type="CT_StrokeChild"/>
<xsd:element name="top" type="CT_StrokeChild"/>
<xsd:element name="right" type="CT_StrokeChild"/>
<xsd:element name="bottom" type="CT_StrokeChild"/>
<xsd:element name="column" type="CT_StrokeChild"/>
<xsd:element name="clippath" type="CT_ClipPath"/>
<xsd:element name="fill" type="CT_Fill"/>
<xsd:complexType name="CT_Skew">
<xsd:attributeGroup ref="v:AG_Ext"/>
<xsd:attribute name="id" type="xsd:string" use="optional"/>
<xsd:attribute name="on" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="offset" type="xsd:string" use="optional"/>
<xsd:attribute name="origin" type="xsd:string" use="optional"/>
<xsd:attribute name="matrix" type="xsd:string" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_Extrusion">
<xsd:attributeGroup ref="v:AG_Ext"/>
<xsd:attribute name="on" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="type" type="ST_ExtrusionType" default="parallel" use="optional"/>
<xsd:attribute name="render" type="ST_ExtrusionRender" default="solid" use="optional"/>
<xsd:attribute name="viewpointorigin" type="xsd:string" use="optional"/>
<xsd:attribute name="viewpoint" type="xsd:string" use="optional"/>
<xsd:attribute name="plane" type="ST_ExtrusionPlane" default="XY" use="optional"/>
<xsd:attribute name="skewangle" type="xsd:float" use="optional"/>
<xsd:attribute name="skewamt" type="xsd:string" use="optional"/>
<xsd:attribute name="foredepth" type="xsd:string" use="optional"/>
<xsd:attribute name="backdepth" type="xsd:string" use="optional"/>
<xsd:attribute name="orientation" type="xsd:string" use="optional"/>
<xsd:attribute name="orientationangle" type="xsd:float" use="optional"/>
<xsd:attribute name="lockrotationcenter" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="autorotationcenter" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="rotationcenter" type="xsd:string" use="optional"/>
<xsd:attribute name="rotationangle" type="xsd:string" use="optional"/>
<xsd:attribute name="colormode" type="ST_ColorMode" use="optional"/>
<xsd:attribute name="color" type="s:ST_ColorType" use="optional"/>
<xsd:attribute name="shininess" type="xsd:float" use="optional"/>
<xsd:attribute name="specularity" type="xsd:string" use="optional"/>
<xsd:attribute name="diffusity" type="xsd:string" use="optional"/>
<xsd:attribute name="metal" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="edge" type="xsd:string" use="optional"/>
<xsd:attribute name="facet" type="xsd:string" use="optional"/>
<xsd:attribute name="lightface" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="brightness" type="xsd:string" use="optional"/>
<xsd:attribute name="lightposition" type="xsd:string" use="optional"/>
<xsd:attribute name="lightlevel" type="xsd:string" use="optional"/>
<xsd:attribute name="lightharsh" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="lightposition2" type="xsd:string" use="optional"/>
<xsd:attribute name="lightlevel2" type="xsd:string" use="optional"/>
<xsd:attribute name="lightharsh2" type="s:ST_TrueFalse" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_Callout">
<xsd:attributeGroup ref="v:AG_Ext"/>
<xsd:attribute name="on" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="type" type="xsd:string" use="optional"/>
<xsd:attribute name="gap" type="xsd:string" use="optional"/>
<xsd:attribute name="angle" type="ST_Angle" use="optional"/>
<xsd:attribute name="dropauto" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="drop" type="ST_CalloutDrop" use="optional"/>
<xsd:attribute name="distance" type="xsd:string" use="optional"/>
<xsd:attribute name="lengthspecified" type="s:ST_TrueFalse" default="f" use="optional"/>
<xsd:attribute name="length" type="xsd:string" use="optional"/>
<xsd:attribute name="accentbar" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="textborder" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="minusx" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="minusy" type="s:ST_TrueFalse" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_Lock">
<xsd:attributeGroup ref="v:AG_Ext"/>
<xsd:attribute name="position" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="selection" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="grouping" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="ungrouping" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="rotation" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="cropping" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="verticies" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="adjusthandles" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="text" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="aspectratio" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="shapetype" type="s:ST_TrueFalse" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_OLEObject">
<xsd:sequence>
<xsd:element name="LinkType" type="ST_OLELinkType" minOccurs="0"/>
<xsd:element name="LockedField" type="s:ST_TrueFalseBlank" minOccurs="0"/>
<xsd:element name="FieldCodes" type="xsd:string" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="Type" type="ST_OLEType" use="optional"/>
<xsd:attribute name="ProgID" type="xsd:string" use="optional"/>
<xsd:attribute name="ShapeID" type="xsd:string" use="optional"/>
<xsd:attribute name="DrawAspect" type="ST_OLEDrawAspect" use="optional"/>
<xsd:attribute name="ObjectID" type="xsd:string" use="optional"/>
<xsd:attribute ref="r:id" use="optional"/>
<xsd:attribute name="UpdateMode" type="ST_OLEUpdateMode" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_Complex">
<xsd:attributeGroup ref="v:AG_Ext"/>
</xsd:complexType>
<xsd:complexType name="CT_StrokeChild">
<xsd:attributeGroup ref="v:AG_Ext"/>
<xsd:attribute name="on" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="weight" type="xsd:string" use="optional"/>
<xsd:attribute name="color" type="s:ST_ColorType" use="optional"/>
<xsd:attribute name="color2" type="s:ST_ColorType" use="optional"/>
<xsd:attribute name="opacity" type="xsd:string" use="optional"/>
<xsd:attribute name="linestyle" type="v:ST_StrokeLineStyle" use="optional"/>
<xsd:attribute name="miterlimit" type="xsd:decimal" use="optional"/>
<xsd:attribute name="joinstyle" type="v:ST_StrokeJoinStyle" use="optional"/>
<xsd:attribute name="endcap" type="v:ST_StrokeEndCap" use="optional"/>
<xsd:attribute name="dashstyle" type="xsd:string" use="optional"/>
<xsd:attribute name="insetpen" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="filltype" type="v:ST_FillType" use="optional"/>
<xsd:attribute name="src" type="xsd:string" use="optional"/>
<xsd:attribute name="imageaspect" type="v:ST_ImageAspect" use="optional"/>
<xsd:attribute name="imagesize" type="xsd:string" use="optional"/>
<xsd:attribute name="imagealignshape" type="s:ST_TrueFalse" use="optional"/>
<xsd:attribute name="startarrow" type="v:ST_StrokeArrowType" use="optional"/>
<xsd:attribute name="startarrowwidth" type="v:ST_StrokeArrowWidth" use="optional"/>
<xsd:attribute name="startarrowlength" type="v:ST_StrokeArrowLength" use="optional"/>
<xsd:attribute name="endarrow" type="v:ST_StrokeArrowType" use="optional"/>
<xsd:attribute name="endarrowwidth" type="v:ST_StrokeArrowWidth" use="optional"/>
<xsd:attribute name="endarrowlength" type="v:ST_StrokeArrowLength" use="optional"/>
<xsd:attribute ref="href"/>
<xsd:attribute ref="althref"/>
<xsd:attribute ref="title"/>
<xsd:attribute ref="forcedash"/>
</xsd:complexType>
<xsd:complexType name="CT_ClipPath">
<xsd:attribute name="v" type="xsd:string" use="required" form="qualified"/>
</xsd:complexType>
<xsd:complexType name="CT_Fill">
<xsd:attributeGroup ref="v:AG_Ext"/>
<xsd:attribute name="type" type="ST_FillType"/>
</xsd:complexType>
<xsd:simpleType name="ST_RType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="arc"/>
<xsd:enumeration value="callout"/>
<xsd:enumeration value="connector"/>
<xsd:enumeration value="align"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_How">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="top"/>
<xsd:enumeration value="middle"/>
<xsd:enumeration value="bottom"/>
<xsd:enumeration value="left"/>
<xsd:enumeration value="center"/>
<xsd:enumeration value="right"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_BWMode">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="color"/>
<xsd:enumeration value="auto"/>
<xsd:enumeration value="grayScale"/>
<xsd:enumeration value="lightGrayscale"/>
<xsd:enumeration value="inverseGray"/>
<xsd:enumeration value="grayOutline"/>
<xsd:enumeration value="highContrast"/>
<xsd:enumeration value="black"/>
<xsd:enumeration value="white"/>
<xsd:enumeration value="hide"/>
<xsd:enumeration value="undrawn"/>
<xsd:enumeration value="blackTextAndLines"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_ScreenSize">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="544,376"/>
<xsd:enumeration value="640,480"/>
<xsd:enumeration value="720,512"/>
<xsd:enumeration value="800,600"/>
<xsd:enumeration value="1024,768"/>
<xsd:enumeration value="1152,862"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_InsetMode">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="auto"/>
<xsd:enumeration value="custom"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_ColorMode">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="auto"/>
<xsd:enumeration value="custom"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_ContentType">
<xsd:restriction base="xsd:string"/>
</xsd:simpleType>
<xsd:simpleType name="ST_DiagramLayout">
<xsd:restriction base="xsd:integer">
<xsd:enumeration value="0"/>
<xsd:enumeration value="1"/>
<xsd:enumeration value="2"/>
<xsd:enumeration value="3"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_ExtrusionType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="perspective"/>
<xsd:enumeration value="parallel"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_ExtrusionRender">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="solid"/>
<xsd:enumeration value="wireFrame"/>
<xsd:enumeration value="boundingCube"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_ExtrusionPlane">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="XY"/>
<xsd:enumeration value="ZX"/>
<xsd:enumeration value="YZ"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_Angle">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="any"/>
<xsd:enumeration value="30"/>
<xsd:enumeration value="45"/>
<xsd:enumeration value="60"/>
<xsd:enumeration value="90"/>
<xsd:enumeration value="auto"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_CalloutDrop">
<xsd:restriction base="xsd:string"/>
</xsd:simpleType>
<xsd:simpleType name="ST_CalloutPlacement">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="top"/>
<xsd:enumeration value="center"/>
<xsd:enumeration value="bottom"/>
<xsd:enumeration value="user"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_ConnectorType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="none"/>
<xsd:enumeration value="straight"/>
<xsd:enumeration value="elbow"/>
<xsd:enumeration value="curved"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_HrAlign">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="left"/>
<xsd:enumeration value="right"/>
<xsd:enumeration value="center"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_ConnectType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="none"/>
<xsd:enumeration value="rect"/>
<xsd:enumeration value="segments"/>
<xsd:enumeration value="custom"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_OLELinkType">
<xsd:restriction base="xsd:string"/>
</xsd:simpleType>
<xsd:simpleType name="ST_OLEType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="Embed"/>
<xsd:enumeration value="Link"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_OLEDrawAspect">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="Content"/>
<xsd:enumeration value="Icon"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_OLEUpdateMode">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="Always"/>
<xsd:enumeration value="OnCall"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_FillType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="gradientCenter"/>
<xsd:enumeration value="solid"/>
<xsd:enumeration value="pattern"/>
<xsd:enumeration value="tile"/>
<xsd:enumeration value="frame"/>
<xsd:enumeration value="gradientUnscaled"/>
<xsd:enumeration value="gradientRadial"/>
<xsd:enumeration value="gradient"/>
<xsd:enumeration value="background"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:schema>

12
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd Normal file
View File

@@ -0,0 +1,12 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns="urn:schemas-microsoft-com:office:powerpoint"
targetNamespace="urn:schemas-microsoft-com:office:powerpoint" elementFormDefault="qualified"
attributeFormDefault="unqualified">
<xsd:element name="iscomment" type="CT_Empty"/>
<xsd:element name="textdata" type="CT_Rel"/>
<xsd:complexType name="CT_Empty"/>
<xsd:complexType name="CT_Rel">
<xsd:attribute name="id" type="xsd:string"/>
</xsd:complexType>
</xsd:schema>

108
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd Normal file
View File

@@ -0,0 +1,108 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns="urn:schemas-microsoft-com:office:excel"
xmlns:s="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
targetNamespace="urn:schemas-microsoft-com:office:excel" elementFormDefault="qualified"
attributeFormDefault="unqualified">
<xsd:import namespace="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes"
schemaLocation="shared-commonSimpleTypes.xsd"/>
<xsd:element name="ClientData" type="CT_ClientData"/>
<xsd:complexType name="CT_ClientData">
<xsd:choice minOccurs="0" maxOccurs="unbounded">
<xsd:element name="MoveWithCells" type="s:ST_TrueFalseBlank"/>
<xsd:element name="SizeWithCells" type="s:ST_TrueFalseBlank"/>
<xsd:element name="Anchor" type="xsd:string"/>
<xsd:element name="Locked" type="s:ST_TrueFalseBlank"/>
<xsd:element name="DefaultSize" type="s:ST_TrueFalseBlank"/>
<xsd:element name="PrintObject" type="s:ST_TrueFalseBlank"/>
<xsd:element name="Disabled" type="s:ST_TrueFalseBlank"/>
<xsd:element name="AutoFill" type="s:ST_TrueFalseBlank"/>
<xsd:element name="AutoLine" type="s:ST_TrueFalseBlank"/>
<xsd:element name="AutoPict" type="s:ST_TrueFalseBlank"/>
<xsd:element name="FmlaMacro" type="xsd:string"/>
<xsd:element name="TextHAlign" type="xsd:string"/>
<xsd:element name="TextVAlign" type="xsd:string"/>
<xsd:element name="LockText" type="s:ST_TrueFalseBlank"/>
<xsd:element name="JustLastX" type="s:ST_TrueFalseBlank"/>
<xsd:element name="SecretEdit" type="s:ST_TrueFalseBlank"/>
<xsd:element name="Default" type="s:ST_TrueFalseBlank"/>
<xsd:element name="Help" type="s:ST_TrueFalseBlank"/>
<xsd:element name="Cancel" type="s:ST_TrueFalseBlank"/>
<xsd:element name="Dismiss" type="s:ST_TrueFalseBlank"/>
<xsd:element name="Accel" type="xsd:integer"/>
<xsd:element name="Accel2" type="xsd:integer"/>
<xsd:element name="Row" type="xsd:integer"/>
<xsd:element name="Column" type="xsd:integer"/>
<xsd:element name="Visible" type="s:ST_TrueFalseBlank"/>
<xsd:element name="RowHidden" type="s:ST_TrueFalseBlank"/>
<xsd:element name="ColHidden" type="s:ST_TrueFalseBlank"/>
<xsd:element name="VTEdit" type="xsd:integer"/>
<xsd:element name="MultiLine" type="s:ST_TrueFalseBlank"/>
<xsd:element name="VScroll" type="s:ST_TrueFalseBlank"/>
<xsd:element name="ValidIds" type="s:ST_TrueFalseBlank"/>
<xsd:element name="FmlaRange" type="xsd:string"/>
<xsd:element name="WidthMin" type="xsd:integer"/>
<xsd:element name="Sel" type="xsd:integer"/>
<xsd:element name="NoThreeD2" type="s:ST_TrueFalseBlank"/>
<xsd:element name="SelType" type="xsd:string"/>
<xsd:element name="MultiSel" type="xsd:string"/>
<xsd:element name="LCT" type="xsd:string"/>
<xsd:element name="ListItem" type="xsd:string"/>
<xsd:element name="DropStyle" type="xsd:string"/>
<xsd:element name="Colored" type="s:ST_TrueFalseBlank"/>
<xsd:element name="DropLines" type="xsd:integer"/>
<xsd:element name="Checked" type="xsd:integer"/>
<xsd:element name="FmlaLink" type="xsd:string"/>
<xsd:element name="FmlaPict" type="xsd:string"/>
<xsd:element name="NoThreeD" type="s:ST_TrueFalseBlank"/>
<xsd:element name="FirstButton" type="s:ST_TrueFalseBlank"/>
<xsd:element name="FmlaGroup" type="xsd:string"/>
<xsd:element name="Val" type="xsd:integer"/>
<xsd:element name="Min" type="xsd:integer"/>
<xsd:element name="Max" type="xsd:integer"/>
<xsd:element name="Inc" type="xsd:integer"/>
<xsd:element name="Page" type="xsd:integer"/>
<xsd:element name="Horiz" type="s:ST_TrueFalseBlank"/>
<xsd:element name="Dx" type="xsd:integer"/>
<xsd:element name="MapOCX" type="s:ST_TrueFalseBlank"/>
<xsd:element name="CF" type="ST_CF"/>
<xsd:element name="Camera" type="s:ST_TrueFalseBlank"/>
<xsd:element name="RecalcAlways" type="s:ST_TrueFalseBlank"/>
<xsd:element name="AutoScale" type="s:ST_TrueFalseBlank"/>
<xsd:element name="DDE" type="s:ST_TrueFalseBlank"/>
<xsd:element name="UIObj" type="s:ST_TrueFalseBlank"/>
<xsd:element name="ScriptText" type="xsd:string"/>
<xsd:element name="ScriptExtended" type="xsd:string"/>
<xsd:element name="ScriptLanguage" type="xsd:nonNegativeInteger"/>
<xsd:element name="ScriptLocation" type="xsd:nonNegativeInteger"/>
<xsd:element name="FmlaTxbx" type="xsd:string"/>
</xsd:choice>
<xsd:attribute name="ObjectType" type="ST_ObjectType" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_CF">
<xsd:restriction base="xsd:string"/>
</xsd:simpleType>
<xsd:simpleType name="ST_ObjectType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="Button"/>
<xsd:enumeration value="Checkbox"/>
<xsd:enumeration value="Dialog"/>
<xsd:enumeration value="Drop"/>
<xsd:enumeration value="Edit"/>
<xsd:enumeration value="GBox"/>
<xsd:enumeration value="Label"/>
<xsd:enumeration value="LineA"/>
<xsd:enumeration value="List"/>
<xsd:enumeration value="Movie"/>
<xsd:enumeration value="Note"/>
<xsd:enumeration value="Pict"/>
<xsd:enumeration value="Radio"/>
<xsd:enumeration value="RectA"/>
<xsd:enumeration value="Scroll"/>
<xsd:enumeration value="Spin"/>
<xsd:enumeration value="Shape"/>
<xsd:enumeration value="Group"/>
<xsd:enumeration value="Rect"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:schema>

96
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd Normal file
View File

@@ -0,0 +1,96 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns="urn:schemas-microsoft-com:office:word"
targetNamespace="urn:schemas-microsoft-com:office:word" elementFormDefault="qualified"
attributeFormDefault="unqualified">
<xsd:element name="bordertop" type="CT_Border"/>
<xsd:element name="borderleft" type="CT_Border"/>
<xsd:element name="borderright" type="CT_Border"/>
<xsd:element name="borderbottom" type="CT_Border"/>
<xsd:complexType name="CT_Border">
<xsd:attribute name="type" type="ST_BorderType" use="optional"/>
<xsd:attribute name="width" type="xsd:positiveInteger" use="optional"/>
<xsd:attribute name="shadow" type="ST_BorderShadow" use="optional"/>
</xsd:complexType>
<xsd:element name="wrap" type="CT_Wrap"/>
<xsd:complexType name="CT_Wrap">
<xsd:attribute name="type" type="ST_WrapType" use="optional"/>
<xsd:attribute name="side" type="ST_WrapSide" use="optional"/>
<xsd:attribute name="anchorx" type="ST_HorizontalAnchor" use="optional"/>
<xsd:attribute name="anchory" type="ST_VerticalAnchor" use="optional"/>
</xsd:complexType>
<xsd:element name="anchorlock" type="CT_AnchorLock"/>
<xsd:complexType name="CT_AnchorLock"/>
<xsd:simpleType name="ST_BorderType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="none"/>
<xsd:enumeration value="single"/>
<xsd:enumeration value="thick"/>
<xsd:enumeration value="double"/>
<xsd:enumeration value="hairline"/>
<xsd:enumeration value="dot"/>
<xsd:enumeration value="dash"/>
<xsd:enumeration value="dotDash"/>
<xsd:enumeration value="dashDotDot"/>
<xsd:enumeration value="triple"/>
<xsd:enumeration value="thinThickSmall"/>
<xsd:enumeration value="thickThinSmall"/>
<xsd:enumeration value="thickBetweenThinSmall"/>
<xsd:enumeration value="thinThick"/>
<xsd:enumeration value="thickThin"/>
<xsd:enumeration value="thickBetweenThin"/>
<xsd:enumeration value="thinThickLarge"/>
<xsd:enumeration value="thickThinLarge"/>
<xsd:enumeration value="thickBetweenThinLarge"/>
<xsd:enumeration value="wave"/>
<xsd:enumeration value="doubleWave"/>
<xsd:enumeration value="dashedSmall"/>
<xsd:enumeration value="dashDotStroked"/>
<xsd:enumeration value="threeDEmboss"/>
<xsd:enumeration value="threeDEngrave"/>
<xsd:enumeration value="HTMLOutset"/>
<xsd:enumeration value="HTMLInset"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_BorderShadow">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="t"/>
<xsd:enumeration value="true"/>
<xsd:enumeration value="f"/>
<xsd:enumeration value="false"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_WrapType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="topAndBottom"/>
<xsd:enumeration value="square"/>
<xsd:enumeration value="none"/>
<xsd:enumeration value="tight"/>
<xsd:enumeration value="through"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_WrapSide">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="both"/>
<xsd:enumeration value="left"/>
<xsd:enumeration value="right"/>
<xsd:enumeration value="largest"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_HorizontalAnchor">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="margin"/>
<xsd:enumeration value="page"/>
<xsd:enumeration value="text"/>
<xsd:enumeration value="char"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_VerticalAnchor">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="margin"/>
<xsd:enumeration value="page"/>
<xsd:enumeration value="text"/>
<xsd:enumeration value="line"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:schema>

3646
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/wml.xsd Normal file
View File

File diff suppressed because it is too large Load Diff

116
skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/xml.xsd Normal file
View File

@@ -0,0 +1,116 @@
<?xml version='1.0'?>
<xs:schema targetNamespace="http://www.w3.org/XML/1998/namespace" xmlns:xs="http://www.w3.org/2001/XMLSchema" xml:lang="en">
<xs:annotation>
<xs:documentation>
See http://www.w3.org/XML/1998/namespace.html and
http://www.w3.org/TR/REC-xml for information about this namespace.
This schema document describes the XML namespace, in a form
suitable for import by other schema documents.
Note that local names in this namespace are intended to be defined
only by the World Wide Web Consortium or its subgroups. The
following names are currently defined in this namespace and should
not be used with conflicting semantics by any Working Group,
specification, or document instance:
base (as an attribute name): denotes an attribute whose value
provides a URI to be used as the base for interpreting any
relative URIs in the scope of the element on which it
appears; its value is inherited. This name is reserved
by virtue of its definition in the XML Base specification.
lang (as an attribute name): denotes an attribute whose value
is a language code for the natural language of the content of
any element; its value is inherited. This name is reserved
by virtue of its definition in the XML specification.
space (as an attribute name): denotes an attribute whose
value is a keyword indicating what whitespace processing
discipline is intended for the content of the element; its
value is inherited. This name is reserved by virtue of its
definition in the XML specification.
Father (in any context at all): denotes Jon Bosak, the chair of
the original XML Working Group. This name is reserved by
the following decision of the W3C XML Plenary and
XML Coordination groups:
In appreciation for his vision, leadership and dedication
the W3C XML Plenary on this 10th day of February, 2000
reserves for Jon Bosak in perpetuity the XML name
xml:Father
</xs:documentation>
</xs:annotation>
<xs:annotation>
<xs:documentation>This schema defines attributes and an attribute group
suitable for use by
schemas wishing to allow xml:base, xml:lang or xml:space attributes
on elements they define.
To enable this, such a schema must import this schema
for the XML namespace, e.g. as follows:
&lt;schema . . .>
. . .
&lt;import namespace="http://www.w3.org/XML/1998/namespace"
schemaLocation="http://www.w3.org/2001/03/xml.xsd"/>
Subsequently, qualified reference to any of the attributes
or the group defined below will have the desired effect, e.g.
&lt;type . . .>
. . .
&lt;attributeGroup ref="xml:specialAttrs"/>
will define a type which will schema-validate an instance
element with any of those attributes</xs:documentation>
</xs:annotation>
<xs:annotation>
<xs:documentation>In keeping with the XML Schema WG's standard versioning
policy, this schema document will persist at
http://www.w3.org/2001/03/xml.xsd.
At the date of issue it can also be found at
http://www.w3.org/2001/xml.xsd.
The schema document at that URI may however change in the future,
in order to remain compatible with the latest version of XML Schema
itself. In other words, if the XML Schema namespace changes, the version
of this document at
http://www.w3.org/2001/xml.xsd will change
accordingly; the version at
http://www.w3.org/2001/03/xml.xsd will not change.
</xs:documentation>
</xs:annotation>
<xs:attribute name="lang" type="xs:language">
<xs:annotation>
<xs:documentation>In due course, we should install the relevant ISO 2- and 3-letter
codes as the enumerated possible values . . .</xs:documentation>
</xs:annotation>
</xs:attribute>
<xs:attribute name="space" default="preserve">
<xs:simpleType>
<xs:restriction base="xs:NCName">
<xs:enumeration value="default"/>
<xs:enumeration value="preserve"/>
</xs:restriction>
</xs:simpleType>
</xs:attribute>
<xs:attribute name="base" type="xs:anyURI">
<xs:annotation>
<xs:documentation>See http://www.w3.org/TR/xmlbase/ for
information about this attribute.</xs:documentation>
</xs:annotation>
</xs:attribute>
<xs:attributeGroup name="specialAttrs">
<xs:attribute ref="xml:base"/>
<xs:attribute ref="xml:lang"/>
<xs:attribute ref="xml:space"/>
</xs:attributeGroup>
</xs:schema>

42
skills/docx/ooxml/schemas/ecma/fouth-edition/opc-contentTypes.xsd Normal file
View File

@@ -0,0 +1,42 @@
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<xs:schema xmlns="http://schemas.openxmlformats.org/package/2006/content-types"
xmlns:xs="http://www.w3.org/2001/XMLSchema"
targetNamespace="http://schemas.openxmlformats.org/package/2006/content-types"
elementFormDefault="qualified" attributeFormDefault="unqualified" blockDefault="#all">
<xs:element name="Types" type="CT_Types"/>
<xs:element name="Default" type="CT_Default"/>
<xs:element name="Override" type="CT_Override"/>
<xs:complexType name="CT_Types">
<xs:choice minOccurs="0" maxOccurs="unbounded">
<xs:element ref="Default"/>
<xs:element ref="Override"/>
</xs:choice>
</xs:complexType>
<xs:complexType name="CT_Default">
<xs:attribute name="Extension" type="ST_Extension" use="required"/>
<xs:attribute name="ContentType" type="ST_ContentType" use="required"/>
</xs:complexType>
<xs:complexType name="CT_Override">
<xs:attribute name="ContentType" type="ST_ContentType" use="required"/>
<xs:attribute name="PartName" type="xs:anyURI" use="required"/>
</xs:complexType>
<xs:simpleType name="ST_ContentType">
<xs:restriction base="xs:string">
<xs:pattern
value="(((([\p{IsBasicLatin}-[\p{Cc}&#127;\(\)&lt;&gt;@,;:\\&quot;/\[\]\?=\{\}\s\t]])+))/((([\p{IsBasicLatin}-[\p{Cc}&#127;\(\)&lt;&gt;@,;:\\&quot;/\[\]\?=\{\}\s\t]])+))((\s+)*;(\s+)*(((([\p{IsBasicLatin}-[\p{Cc}&#127;\(\)&lt;&gt;@,;:\\&quot;/\[\]\?=\{\}\s\t]])+))=((([\p{IsBasicLatin}-[\p{Cc}&#127;\(\)&lt;&gt;@,;:\\&quot;/\[\]\?=\{\}\s\t]])+)|(&quot;(([\p{IsLatin-1Supplement}\p{IsBasicLatin}-[\p{Cc}&#127;&quot;\n\r]]|(\s+))|(\\[\p{IsBasicLatin}]))*&quot;))))*)"
/>
</xs:restriction>
</xs:simpleType>
<xs:simpleType name="ST_Extension">
<xs:restriction base="xs:string">
<xs:pattern
value="([!$&amp;'\(\)\*\+,:=]|(%[0-9a-fA-F][0-9a-fA-F])|[:@]|[a-zA-Z0-9\-_~])+"/>
</xs:restriction>
</xs:simpleType>
</xs:schema>

50
skills/docx/ooxml/schemas/ecma/fouth-edition/opc-coreProperties.xsd Normal file
View File

@@ -0,0 +1,50 @@
<?xml version="1.0" encoding="UTF-8"?>
<xs:schema targetNamespace="http://schemas.openxmlformats.org/package/2006/metadata/core-properties"
xmlns="http://schemas.openxmlformats.org/package/2006/metadata/core-properties"
xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:dcterms="http://purl.org/dc/terms/" elementFormDefault="qualified" blockDefault="#all">
<xs:import namespace="http://purl.org/dc/elements/1.1/"
schemaLocation="http://dublincore.org/schemas/xmls/qdc/2003/04/02/dc.xsd"/>
<xs:import namespace="http://purl.org/dc/terms/"
schemaLocation="http://dublincore.org/schemas/xmls/qdc/2003/04/02/dcterms.xsd"/>
<xs:import id="xml" namespace="http://www.w3.org/XML/1998/namespace"/>
<xs:element name="coreProperties" type="CT_CoreProperties"/>
<xs:complexType name="CT_CoreProperties">
<xs:all>
<xs:element name="category" minOccurs="0" maxOccurs="1" type="xs:string"/>
<xs:element name="contentStatus" minOccurs="0" maxOccurs="1" type="xs:string"/>
<xs:element ref="dcterms:created" minOccurs="0" maxOccurs="1"/>
<xs:element ref="dc:creator" minOccurs="0" maxOccurs="1"/>
<xs:element ref="dc:description" minOccurs="0" maxOccurs="1"/>
<xs:element ref="dc:identifier" minOccurs="0" maxOccurs="1"/>
<xs:element name="keywords" minOccurs="0" maxOccurs="1" type="CT_Keywords"/>
<xs:element ref="dc:language" minOccurs="0" maxOccurs="1"/>
<xs:element name="lastModifiedBy" minOccurs="0" maxOccurs="1" type="xs:string"/>
<xs:element name="lastPrinted" minOccurs="0" maxOccurs="1" type="xs:dateTime"/>
<xs:element ref="dcterms:modified" minOccurs="0" maxOccurs="1"/>
<xs:element name="revision" minOccurs="0" maxOccurs="1" type="xs:string"/>
<xs:element ref="dc:subject" minOccurs="0" maxOccurs="1"/>
<xs:element ref="dc:title" minOccurs="0" maxOccurs="1"/>
<xs:element name="version" minOccurs="0" maxOccurs="1" type="xs:string"/>
</xs:all>
</xs:complexType>
<xs:complexType name="CT_Keywords" mixed="true">
<xs:sequence>
<xs:element name="value" minOccurs="0" maxOccurs="unbounded" type="CT_Keyword"/>
</xs:sequence>
<xs:attribute ref="xml:lang" use="optional"/>
</xs:complexType>
<xs:complexType name="CT_Keyword">
<xs:simpleContent>
<xs:extension base="xs:string">
<xs:attribute ref="xml:lang" use="optional"/>
</xs:extension>
</xs:simpleContent>
</xs:complexType>
</xs:schema>

49
skills/docx/ooxml/schemas/ecma/fouth-edition/opc-digSig.xsd Normal file
View File

@@ -0,0 +1,49 @@
<?xml version="1.0" encoding="UTF-8"?>
<xsd:schema xmlns="http://schemas.openxmlformats.org/package/2006/digital-signature"
xmlns:xsd="http://www.w3.org/2001/XMLSchema"
targetNamespace="http://schemas.openxmlformats.org/package/2006/digital-signature"
elementFormDefault="qualified" attributeFormDefault="unqualified" blockDefault="#all">
<xsd:element name="SignatureTime" type="CT_SignatureTime"/>
<xsd:element name="RelationshipReference" type="CT_RelationshipReference"/>
<xsd:element name="RelationshipsGroupReference" type="CT_RelationshipsGroupReference"/>
<xsd:complexType name="CT_SignatureTime">
<xsd:sequence>
<xsd:element name="Format" type="ST_Format"/>
<xsd:element name="Value" type="ST_Value"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_RelationshipReference">
<xsd:simpleContent>
<xsd:extension base="xsd:string">
<xsd:attribute name="SourceId" type="xsd:string" use="required"/>
</xsd:extension>
</xsd:simpleContent>
</xsd:complexType>
<xsd:complexType name="CT_RelationshipsGroupReference">
<xsd:simpleContent>
<xsd:extension base="xsd:string">
<xsd:attribute name="SourceType" type="xsd:anyURI" use="required"/>
</xsd:extension>
</xsd:simpleContent>
</xsd:complexType>
<xsd:simpleType name="ST_Format">
<xsd:restriction base="xsd:string">
<xsd:pattern
value="(YYYY)|(YYYY-MM)|(YYYY-MM-DD)|(YYYY-MM-DDThh:mmTZD)|(YYYY-MM-DDThh:mm:ssTZD)|(YYYY-MM-DDThh:mm:ss.sTZD)"
/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_Value">
<xsd:restriction base="xsd:string">
<xsd:pattern
value="(([0-9][0-9][0-9][0-9]))|(([0-9][0-9][0-9][0-9])-((0[1-9])|(1(0|1|2))))|(([0-9][0-9][0-9][0-9])-((0[1-9])|(1(0|1|2)))-((0[1-9])|(1[0-9])|(2[0-9])|(3(0|1))))|(([0-9][0-9][0-9][0-9])-((0[1-9])|(1(0|1|2)))-((0[1-9])|(1[0-9])|(2[0-9])|(3(0|1)))T((0[0-9])|(1[0-9])|(2(0|1|2|3))):((0[0-9])|(1[0-9])|(2[0-9])|(3[0-9])|(4[0-9])|(5[0-9]))(((\+|-)((0[0-9])|(1[0-9])|(2(0|1|2|3))):((0[0-9])|(1[0-9])|(2[0-9])|(3[0-9])|(4[0-9])|(5[0-9])))|Z))|(([0-9][0-9][0-9][0-9])-((0[1-9])|(1(0|1|2)))-((0[1-9])|(1[0-9])|(2[0-9])|(3(0|1)))T((0[0-9])|(1[0-9])|(2(0|1|2|3))):((0[0-9])|(1[0-9])|(2[0-9])|(3[0-9])|(4[0-9])|(5[0-9])):((0[0-9])|(1[0-9])|(2[0-9])|(3[0-9])|(4[0-9])|(5[0-9]))(((\+|-)((0[0-9])|(1[0-9])|(2(0|1|2|3))):((0[0-9])|(1[0-9])|(2[0-9])|(3[0-9])|(4[0-9])|(5[0-9])))|Z))|(([0-9][0-9][0-9][0-9])-((0[1-9])|(1(0|1|2)))-((0[1-9])|(1[0-9])|(2[0-9])|(3(0|1)))T((0[0-9])|(1[0-9])|(2(0|1|2|3))):((0[0-9])|(1[0-9])|(2[0-9])|(3[0-9])|(4[0-9])|(5[0-9])):(((0[0-9])|(1[0-9])|(2[0-9])|(3[0-9])|(4[0-9])|(5[0-9]))\.[0-9])(((\+|-)((0[0-9])|(1[0-9])|(2(0|1|2|3))):((0[0-9])|(1[0-9])|(2[0-9])|(3[0-9])|(4[0-9])|(5[0-9])))|Z))"
/>
</xsd:restriction>
</xsd:simpleType>
</xsd:schema>

33
skills/docx/ooxml/schemas/ecma/fouth-edition/opc-relationships.xsd Normal file
View File

@@ -0,0 +1,33 @@
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<xsd:schema xmlns="http://schemas.openxmlformats.org/package/2006/relationships"
xmlns:xsd="http://www.w3.org/2001/XMLSchema"
targetNamespace="http://schemas.openxmlformats.org/package/2006/relationships"
elementFormDefault="qualified" attributeFormDefault="unqualified" blockDefault="#all">
<xsd:element name="Relationships" type="CT_Relationships"/>
<xsd:element name="Relationship" type="CT_Relationship"/>
<xsd:complexType name="CT_Relationships">
<xsd:sequence>
<xsd:element ref="Relationship" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Relationship">
<xsd:simpleContent>
<xsd:extension base="xsd:string">
<xsd:attribute name="TargetMode" type="ST_TargetMode" use="optional"/>
<xsd:attribute name="Target" type="xsd:anyURI" use="required"/>
<xsd:attribute name="Type" type="xsd:anyURI" use="required"/>
<xsd:attribute name="Id" type="xsd:ID" use="required"/>
</xsd:extension>
</xsd:simpleContent>
</xsd:complexType>
<xsd:simpleType name="ST_TargetMode">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="External"/>
<xsd:enumeration value="Internal"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:schema>

75
skills/docx/ooxml/schemas/mce/mc.xsd Normal file
View File

@@ -0,0 +1,75 @@
<?xml version="1.0" encoding="utf-8"?>
<xsd:schema xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006"
attributeFormDefault="unqualified" elementFormDefault="qualified"
targetNamespace="http://schemas.openxmlformats.org/markup-compatibility/2006"
xmlns:xsd="http://www.w3.org/2001/XMLSchema">
<!--
This XSD is a modified version of the one found at:
https://github.com/plutext/docx4j/blob/master/xsd/mce/markup-compatibility-2006-MINIMAL.xsd
This XSD has 2 objectives:
1. round tripping @mc:Ignorable
<w:document
xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006"
xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"
mc:Ignorable="w14 w15 wp14">
2. enabling AlternateContent to be manipulated in certain elements
(in the unusual case where the content model is xsd:any, it doesn't have to be explicitly added)
See further ECMA-376, 4th Edition, Office Open XML File Formats
Part 3 : Markup Compatibility and Extensibility
-->
<!-- Objective 1 -->
<xsd:attribute name="Ignorable" type="xsd:string" />
<!-- Objective 2 -->
<xsd:attribute name="MustUnderstand" type="xsd:string" />
<xsd:attribute name="ProcessContent" type="xsd:string" />
<!-- An AlternateContent element shall contain one or more Choice child elements, optionally followed by a
Fallback child element. If present, there shall be only one Fallback element, and it shall follow all Choice
elements. -->
<xsd:element name="AlternateContent">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="Choice" minOccurs="0" maxOccurs="unbounded">
<xsd:complexType>
<xsd:sequence>
<xsd:any minOccurs="0" maxOccurs="unbounded"
processContents="strict">
</xsd:any>
</xsd:sequence>
<xsd:attribute name="Requires" type="xsd:string" use="required" />
<xsd:attribute ref="mc:Ignorable" use="optional" />
<xsd:attribute ref="mc:MustUnderstand" use="optional" />
<xsd:attribute ref="mc:ProcessContent" use="optional" />
</xsd:complexType>
</xsd:element>
<xsd:element name="Fallback" minOccurs="0" maxOccurs="1">
<xsd:complexType>
<xsd:sequence>
<xsd:any minOccurs="0" maxOccurs="unbounded"
processContents="strict">
</xsd:any>
</xsd:sequence>
<xsd:attribute ref="mc:Ignorable" use="optional" />
<xsd:attribute ref="mc:MustUnderstand" use="optional" />
<xsd:attribute ref="mc:ProcessContent" use="optional" />
</xsd:complexType>
</xsd:element>
</xsd:sequence>
<!-- AlternateContent elements might include the attributes Ignorable,
MustUnderstand and ProcessContent described in this Part of ECMA-376. These
attributes’ qualified names shall be prefixed when associated with an AlternateContent
element. -->
<xsd:attribute ref="mc:Ignorable" use="optional" />
<xsd:attribute ref="mc:MustUnderstand" use="optional" />
<xsd:attribute ref="mc:ProcessContent" use="optional" />
</xsd:complexType>
</xsd:element>
</xsd:schema>

560
skills/docx/ooxml/schemas/microsoft/wml-2010.xsd Normal file
View File

@@ -0,0 +1,560 @@
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:w12="http://schemas.openxmlformats.org/wordprocessingml/2006/main" elementFormDefault="qualified" attributeFormDefault="qualified" blockDefault="#all" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:s="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes" xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main" xmlns="http://schemas.microsoft.com/office/word/2010/wordml" targetNamespace="http://schemas.microsoft.com/office/word/2010/wordml">
<!-- <xsd:import id="rel" namespace="http://schemas.openxmlformats.org/officeDocument/2006/relationships" schemaLocation="orel.xsd"/> -->
<xsd:import id="w" namespace="http://schemas.openxmlformats.org/wordprocessingml/2006/main" schemaLocation="../ISO-IEC29500-4_2016/wml.xsd"/>
<!-- <xsd:import namespace="http://schemas.openxmlformats.org/drawingml/2006/main" schemaLocation="oartbasetypes.xsd"/>
<xsd:import namespace="http://schemas.openxmlformats.org/drawingml/2006/main" schemaLocation="oartsplineproperties.xsd"/> -->
<xsd:complexType name="CT_LongHexNumber">
<xsd:attribute name="val" type="w:ST_LongHexNumber" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_OnOff">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="true"/>
<xsd:enumeration value="false"/>
<xsd:enumeration value="0"/>
<xsd:enumeration value="1"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_OnOff">
<xsd:attribute name="val" type="ST_OnOff"/>
</xsd:complexType>
<xsd:element name="docId" type="CT_LongHexNumber"/>
<xsd:element name="conflictMode" type="CT_OnOff"/>
<xsd:attributeGroup name="AG_Parids">
<xsd:attribute name="paraId" type="w:ST_LongHexNumber"/>
<xsd:attribute name="textId" type="w:ST_LongHexNumber"/>
</xsd:attributeGroup>
<xsd:attribute name="anchorId" type="w:ST_LongHexNumber"/>
<xsd:attribute name="noSpellErr" type="ST_OnOff"/>
<xsd:element name="customXmlConflictInsRangeStart" type="w:CT_TrackChange"/>
<xsd:element name="customXmlConflictInsRangeEnd" type="w:CT_Markup"/>
<xsd:element name="customXmlConflictDelRangeStart" type="w:CT_TrackChange"/>
<xsd:element name="customXmlConflictDelRangeEnd" type="w:CT_Markup"/>
<xsd:group name="EG_RunLevelConflicts">
<xsd:sequence>
<xsd:element name="conflictIns" type="w:CT_RunTrackChange" minOccurs="0"/>
<xsd:element name="conflictDel" type="w:CT_RunTrackChange" minOccurs="0"/>
</xsd:sequence>
</xsd:group>
<xsd:group name="EG_Conflicts">
<xsd:choice>
<xsd:element name="conflictIns" type="w:CT_TrackChange" minOccurs="0"/>
<xsd:element name="conflictDel" type="w:CT_TrackChange" minOccurs="0"/>
</xsd:choice>
</xsd:group>
<xsd:complexType name="CT_Percentage">
<xsd:attribute name="val" type="a:ST_Percentage" use="required"/>
</xsd:complexType>
<xsd:complexType name="CT_PositiveFixedPercentage">
<xsd:attribute name="val" type="a:ST_PositiveFixedPercentage" use="required"/>
</xsd:complexType>
<xsd:complexType name="CT_PositivePercentage">
<xsd:attribute name="val" type="a:ST_PositivePercentage" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_SchemeColorVal">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="bg1"/>
<xsd:enumeration value="tx1"/>
<xsd:enumeration value="bg2"/>
<xsd:enumeration value="tx2"/>
<xsd:enumeration value="accent1"/>
<xsd:enumeration value="accent2"/>
<xsd:enumeration value="accent3"/>
<xsd:enumeration value="accent4"/>
<xsd:enumeration value="accent5"/>
<xsd:enumeration value="accent6"/>
<xsd:enumeration value="hlink"/>
<xsd:enumeration value="folHlink"/>
<xsd:enumeration value="dk1"/>
<xsd:enumeration value="lt1"/>
<xsd:enumeration value="dk2"/>
<xsd:enumeration value="lt2"/>
<xsd:enumeration value="phClr"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_RectAlignment">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="none"/>
<xsd:enumeration value="tl"/>
<xsd:enumeration value="t"/>
<xsd:enumeration value="tr"/>
<xsd:enumeration value="l"/>
<xsd:enumeration value="ctr"/>
<xsd:enumeration value="r"/>
<xsd:enumeration value="bl"/>
<xsd:enumeration value="b"/>
<xsd:enumeration value="br"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_PathShadeType">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="shape"/>
<xsd:enumeration value="circle"/>
<xsd:enumeration value="rect"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_LineCap">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="rnd"/>
<xsd:enumeration value="sq"/>
<xsd:enumeration value="flat"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_PresetLineDashVal">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="solid"/>
<xsd:enumeration value="dot"/>
<xsd:enumeration value="sysDot"/>
<xsd:enumeration value="dash"/>
<xsd:enumeration value="sysDash"/>
<xsd:enumeration value="lgDash"/>
<xsd:enumeration value="dashDot"/>
<xsd:enumeration value="sysDashDot"/>
<xsd:enumeration value="lgDashDot"/>
<xsd:enumeration value="lgDashDotDot"/>
<xsd:enumeration value="sysDashDotDot"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_PenAlignment">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="ctr"/>
<xsd:enumeration value="in"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_CompoundLine">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="sng"/>
<xsd:enumeration value="dbl"/>
<xsd:enumeration value="thickThin"/>
<xsd:enumeration value="thinThick"/>
<xsd:enumeration value="tri"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_RelativeRect">
<xsd:attribute name="l" use="optional" type="a:ST_Percentage"/>
<xsd:attribute name="t" use="optional" type="a:ST_Percentage"/>
<xsd:attribute name="r" use="optional" type="a:ST_Percentage"/>
<xsd:attribute name="b" use="optional" type="a:ST_Percentage"/>
</xsd:complexType>
<xsd:group name="EG_ColorTransform">
<xsd:choice>
<xsd:element name="tint" type="CT_PositiveFixedPercentage"/>
<xsd:element name="shade" type="CT_PositiveFixedPercentage"/>
<xsd:element name="alpha" type="CT_PositiveFixedPercentage"/>
<xsd:element name="hueMod" type="CT_PositivePercentage"/>
<xsd:element name="sat" type="CT_Percentage"/>
<xsd:element name="satOff" type="CT_Percentage"/>
<xsd:element name="satMod" type="CT_Percentage"/>
<xsd:element name="lum" type="CT_Percentage"/>
<xsd:element name="lumOff" type="CT_Percentage"/>
<xsd:element name="lumMod" type="CT_Percentage"/>
</xsd:choice>
</xsd:group>
<xsd:complexType name="CT_SRgbColor">
<xsd:sequence>
<xsd:group ref="EG_ColorTransform" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
<xsd:attribute name="val" type="s:ST_HexColorRGB" use="required"/>
</xsd:complexType>
<xsd:complexType name="CT_SchemeColor">
<xsd:sequence>
<xsd:group ref="EG_ColorTransform" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
<xsd:attribute name="val" type="ST_SchemeColorVal" use="required"/>
</xsd:complexType>
<xsd:group name="EG_ColorChoice">
<xsd:choice>
<xsd:element name="srgbClr" type="CT_SRgbColor"/>
<xsd:element name="schemeClr" type="CT_SchemeColor"/>
</xsd:choice>
</xsd:group>
<xsd:complexType name="CT_Color">
<xsd:sequence>
<xsd:group ref="EG_ColorChoice"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_GradientStop">
<xsd:sequence>
<xsd:group ref="EG_ColorChoice"/>
</xsd:sequence>
<xsd:attribute name="pos" type="a:ST_PositiveFixedPercentage" use="required"/>
</xsd:complexType>
<xsd:complexType name="CT_GradientStopList">
<xsd:sequence>
<xsd:element name="gs" type="CT_GradientStop" minOccurs="2" maxOccurs="10"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_LinearShadeProperties">
<xsd:attribute name="ang" type="a:ST_PositiveFixedAngle" use="optional"/>
<xsd:attribute name="scaled" type="ST_OnOff" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_PathShadeProperties">
<xsd:sequence>
<xsd:element name="fillToRect" type="CT_RelativeRect" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="path" type="ST_PathShadeType" use="optional"/>
</xsd:complexType>
<xsd:group name="EG_ShadeProperties">
<xsd:choice>
<xsd:element name="lin" type="CT_LinearShadeProperties"/>
<xsd:element name="path" type="CT_PathShadeProperties"/>
</xsd:choice>
</xsd:group>
<xsd:complexType name="CT_SolidColorFillProperties">
<xsd:sequence>
<xsd:group ref="EG_ColorChoice" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_GradientFillProperties">
<xsd:sequence>
<xsd:element name="gsLst" type="CT_GradientStopList" minOccurs="0"/>
<xsd:group ref="EG_ShadeProperties" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:group name="EG_FillProperties">
<xsd:choice>
<xsd:element name="noFill" type="w:CT_Empty"/>
<xsd:element name="solidFill" type="CT_SolidColorFillProperties"/>
<xsd:element name="gradFill" type="CT_GradientFillProperties"/>
</xsd:choice>
</xsd:group>
<xsd:complexType name="CT_PresetLineDashProperties">
<xsd:attribute name="val" type="ST_PresetLineDashVal" use="optional"/>
</xsd:complexType>
<xsd:group name="EG_LineDashProperties">
<xsd:choice>
<xsd:element name="prstDash" type="CT_PresetLineDashProperties"/>
</xsd:choice>
</xsd:group>
<xsd:complexType name="CT_LineJoinMiterProperties">
<xsd:attribute name="lim" type="a:ST_PositivePercentage" use="optional"/>
</xsd:complexType>
<xsd:group name="EG_LineJoinProperties">
<xsd:choice>
<xsd:element name="round" type="w:CT_Empty"/>
<xsd:element name="bevel" type="w:CT_Empty"/>
<xsd:element name="miter" type="CT_LineJoinMiterProperties"/>
</xsd:choice>
</xsd:group>
<xsd:simpleType name="ST_PresetCameraType">
<xsd:restriction base="xsd:token">
<xsd:enumeration value="legacyObliqueTopLeft"/>
<xsd:enumeration value="legacyObliqueTop"/>
<xsd:enumeration value="legacyObliqueTopRight"/>
<xsd:enumeration value="legacyObliqueLeft"/>
<xsd:enumeration value="legacyObliqueFront"/>
<xsd:enumeration value="legacyObliqueRight"/>
<xsd:enumeration value="legacyObliqueBottomLeft"/>
<xsd:enumeration value="legacyObliqueBottom"/>
<xsd:enumeration value="legacyObliqueBottomRight"/>
<xsd:enumeration value="legacyPerspectiveTopLeft"/>
<xsd:enumeration value="legacyPerspectiveTop"/>
<xsd:enumeration value="legacyPerspectiveTopRight"/>
<xsd:enumeration value="legacyPerspectiveLeft"/>
<xsd:enumeration value="legacyPerspectiveFront"/>
<xsd:enumeration value="legacyPerspectiveRight"/>
<xsd:enumeration value="legacyPerspectiveBottomLeft"/>
<xsd:enumeration value="legacyPerspectiveBottom"/>
<xsd:enumeration value="legacyPerspectiveBottomRight"/>
<xsd:enumeration value="orthographicFront"/>
<xsd:enumeration value="isometricTopUp"/>
<xsd:enumeration value="isometricTopDown"/>
<xsd:enumeration value="isometricBottomUp"/>
<xsd:enumeration value="isometricBottomDown"/>
<xsd:enumeration value="isometricLeftUp"/>
<xsd:enumeration value="isometricLeftDown"/>
<xsd:enumeration value="isometricRightUp"/>
<xsd:enumeration value="isometricRightDown"/>
<xsd:enumeration value="isometricOffAxis1Left"/>
<xsd:enumeration value="isometricOffAxis1Right"/>
<xsd:enumeration value="isometricOffAxis1Top"/>
<xsd:enumeration value="isometricOffAxis2Left"/>
<xsd:enumeration value="isometricOffAxis2Right"/>
<xsd:enumeration value="isometricOffAxis2Top"/>
<xsd:enumeration value="isometricOffAxis3Left"/>
<xsd:enumeration value="isometricOffAxis3Right"/>
<xsd:enumeration value="isometricOffAxis3Bottom"/>
<xsd:enumeration value="isometricOffAxis4Left"/>
<xsd:enumeration value="isometricOffAxis4Right"/>
<xsd:enumeration value="isometricOffAxis4Bottom"/>
<xsd:enumeration value="obliqueTopLeft"/>
<xsd:enumeration value="obliqueTop"/>
<xsd:enumeration value="obliqueTopRight"/>
<xsd:enumeration value="obliqueLeft"/>
<xsd:enumeration value="obliqueRight"/>
<xsd:enumeration value="obliqueBottomLeft"/>
<xsd:enumeration value="obliqueBottom"/>
<xsd:enumeration value="obliqueBottomRight"/>
<xsd:enumeration value="perspectiveFront"/>
<xsd:enumeration value="perspectiveLeft"/>
<xsd:enumeration value="perspectiveRight"/>
<xsd:enumeration value="perspectiveAbove"/>
<xsd:enumeration value="perspectiveBelow"/>
<xsd:enumeration value="perspectiveAboveLeftFacing"/>
<xsd:enumeration value="perspectiveAboveRightFacing"/>
<xsd:enumeration value="perspectiveContrastingLeftFacing"/>
<xsd:enumeration value="perspectiveContrastingRightFacing"/>
<xsd:enumeration value="perspectiveHeroicLeftFacing"/>
<xsd:enumeration value="perspectiveHeroicRightFacing"/>
<xsd:enumeration value="perspectiveHeroicExtremeLeftFacing"/>
<xsd:enumeration value="perspectiveHeroicExtremeRightFacing"/>
<xsd:enumeration value="perspectiveRelaxed"/>
<xsd:enumeration value="perspectiveRelaxedModerately"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_Camera">
<xsd:attribute name="prst" use="required" type="ST_PresetCameraType"/>
</xsd:complexType>
<xsd:complexType name="CT_SphereCoords">
<xsd:attribute name="lat" type="a:ST_PositiveFixedAngle" use="required"/>
<xsd:attribute name="lon" type="a:ST_PositiveFixedAngle" use="required"/>
<xsd:attribute name="rev" type="a:ST_PositiveFixedAngle" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_LightRigType">
<xsd:restriction base="xsd:token">
<xsd:enumeration value="legacyFlat1"/>
<xsd:enumeration value="legacyFlat2"/>
<xsd:enumeration value="legacyFlat3"/>
<xsd:enumeration value="legacyFlat4"/>
<xsd:enumeration value="legacyNormal1"/>
<xsd:enumeration value="legacyNormal2"/>
<xsd:enumeration value="legacyNormal3"/>
<xsd:enumeration value="legacyNormal4"/>
<xsd:enumeration value="legacyHarsh1"/>
<xsd:enumeration value="legacyHarsh2"/>
<xsd:enumeration value="legacyHarsh3"/>
<xsd:enumeration value="legacyHarsh4"/>
<xsd:enumeration value="threePt"/>
<xsd:enumeration value="balanced"/>
<xsd:enumeration value="soft"/>
<xsd:enumeration value="harsh"/>
<xsd:enumeration value="flood"/>
<xsd:enumeration value="contrasting"/>
<xsd:enumeration value="morning"/>
<xsd:enumeration value="sunrise"/>
<xsd:enumeration value="sunset"/>
<xsd:enumeration value="chilly"/>
<xsd:enumeration value="freezing"/>
<xsd:enumeration value="flat"/>
<xsd:enumeration value="twoPt"/>
<xsd:enumeration value="glow"/>
<xsd:enumeration value="brightRoom"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:simpleType name="ST_LightRigDirection">
<xsd:restriction base="xsd:token">
<xsd:enumeration value="tl"/>
<xsd:enumeration value="t"/>
<xsd:enumeration value="tr"/>
<xsd:enumeration value="l"/>
<xsd:enumeration value="r"/>
<xsd:enumeration value="bl"/>
<xsd:enumeration value="b"/>
<xsd:enumeration value="br"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_LightRig">
<xsd:sequence>
<xsd:element name="rot" type="CT_SphereCoords" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="rig" type="ST_LightRigType" use="required"/>
<xsd:attribute name="dir" type="ST_LightRigDirection" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_BevelPresetType">
<xsd:restriction base="xsd:token">
<xsd:enumeration value="relaxedInset"/>
<xsd:enumeration value="circle"/>
<xsd:enumeration value="slope"/>
<xsd:enumeration value="cross"/>
<xsd:enumeration value="angle"/>
<xsd:enumeration value="softRound"/>
<xsd:enumeration value="convex"/>
<xsd:enumeration value="coolSlant"/>
<xsd:enumeration value="divot"/>
<xsd:enumeration value="riblet"/>
<xsd:enumeration value="hardEdge"/>
<xsd:enumeration value="artDeco"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_Bevel">
<xsd:attribute name="w" type="a:ST_PositiveCoordinate" use="optional"/>
<xsd:attribute name="h" type="a:ST_PositiveCoordinate" use="optional"/>
<xsd:attribute name="prst" type="ST_BevelPresetType" use="optional"/>
</xsd:complexType>
<xsd:simpleType name="ST_PresetMaterialType">
<xsd:restriction base="xsd:token">
<xsd:enumeration value="legacyMatte"/>
<xsd:enumeration value="legacyPlastic"/>
<xsd:enumeration value="legacyMetal"/>
<xsd:enumeration value="legacyWireframe"/>
<xsd:enumeration value="matte"/>
<xsd:enumeration value="plastic"/>
<xsd:enumeration value="metal"/>
<xsd:enumeration value="warmMatte"/>
<xsd:enumeration value="translucentPowder"/>
<xsd:enumeration value="powder"/>
<xsd:enumeration value="dkEdge"/>
<xsd:enumeration value="softEdge"/>
<xsd:enumeration value="clear"/>
<xsd:enumeration value="flat"/>
<xsd:enumeration value="softmetal"/>
<xsd:enumeration value="none"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_Glow">
<xsd:sequence>
<xsd:group ref="EG_ColorChoice"/>
</xsd:sequence>
<xsd:attribute name="rad" use="optional" type="a:ST_PositiveCoordinate"/>
</xsd:complexType>
<xsd:complexType name="CT_Shadow">
<xsd:sequence>
<xsd:group ref="EG_ColorChoice"/>
</xsd:sequence>
<xsd:attribute name="blurRad" use="optional" type="a:ST_PositiveCoordinate"/>
<xsd:attribute name="dist" use="optional" type="a:ST_PositiveCoordinate"/>
<xsd:attribute name="dir" use="optional" type="a:ST_PositiveFixedAngle"/>
<xsd:attribute name="sx" use="optional" type="a:ST_Percentage"/>
<xsd:attribute name="sy" use="optional" type="a:ST_Percentage"/>
<xsd:attribute name="kx" use="optional" type="a:ST_FixedAngle"/>
<xsd:attribute name="ky" use="optional" type="a:ST_FixedAngle"/>
<xsd:attribute name="algn" use="optional" type="ST_RectAlignment"/>
</xsd:complexType>
<xsd:complexType name="CT_Reflection">
<xsd:attribute name="blurRad" use="optional" type="a:ST_PositiveCoordinate"/>
<xsd:attribute name="stA" use="optional" type="a:ST_PositiveFixedPercentage"/>
<xsd:attribute name="stPos" use="optional" type="a:ST_PositiveFixedPercentage"/>
<xsd:attribute name="endA" use="optional" type="a:ST_PositiveFixedPercentage"/>
<xsd:attribute name="endPos" use="optional" type="a:ST_PositiveFixedPercentage"/>
<xsd:attribute name="dist" use="optional" type="a:ST_PositiveCoordinate"/>
<xsd:attribute name="dir" use="optional" type="a:ST_PositiveFixedAngle"/>
<xsd:attribute name="fadeDir" use="optional" type="a:ST_PositiveFixedAngle"/>
<xsd:attribute name="sx" use="optional" type="a:ST_Percentage"/>
<xsd:attribute name="sy" use="optional" type="a:ST_Percentage"/>
<xsd:attribute name="kx" use="optional" type="a:ST_FixedAngle"/>
<xsd:attribute name="ky" use="optional" type="a:ST_FixedAngle"/>
<xsd:attribute name="algn" use="optional" type="ST_RectAlignment"/>
</xsd:complexType>
<xsd:complexType name="CT_FillTextEffect">
<xsd:sequence>
<xsd:group ref="EG_FillProperties" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_TextOutlineEffect">
<xsd:sequence>
<xsd:group ref="EG_FillProperties" minOccurs="0"/>
<xsd:group ref="EG_LineDashProperties" minOccurs="0"/>
<xsd:group ref="EG_LineJoinProperties" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="w" use="optional" type="a:ST_LineWidth"/>
<xsd:attribute name="cap" use="optional" type="ST_LineCap"/>
<xsd:attribute name="cmpd" use="optional" type="ST_CompoundLine"/>
<xsd:attribute name="algn" use="optional" type="ST_PenAlignment"/>
</xsd:complexType>
<xsd:complexType name="CT_Scene3D">
<xsd:sequence>
<xsd:element name="camera" type="CT_Camera"/>
<xsd:element name="lightRig" type="CT_LightRig"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_Props3D">
<xsd:sequence>
<xsd:element name="bevelT" type="CT_Bevel" minOccurs="0"/>
<xsd:element name="bevelB" type="CT_Bevel" minOccurs="0"/>
<xsd:element name="extrusionClr" type="CT_Color" minOccurs="0"/>
<xsd:element name="contourClr" type="CT_Color" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="extrusionH" type="a:ST_PositiveCoordinate" use="optional"/>
<xsd:attribute name="contourW" type="a:ST_PositiveCoordinate" use="optional"/>
<xsd:attribute name="prstMaterial" type="ST_PresetMaterialType" use="optional"/>
</xsd:complexType>
<xsd:group name="EG_RPrTextEffects">
<xsd:sequence>
<xsd:element name="glow" minOccurs="0" type="CT_Glow"/>
<xsd:element name="shadow" minOccurs="0" type="CT_Shadow"/>
<xsd:element name="reflection" minOccurs="0" type="CT_Reflection"/>
<xsd:element name="textOutline" minOccurs="0" type="CT_TextOutlineEffect"/>
<xsd:element name="textFill" minOccurs="0" type="CT_FillTextEffect"/>
<xsd:element name="scene3d" minOccurs="0" type="CT_Scene3D"/>
<xsd:element name="props3d" minOccurs="0" type="CT_Props3D"/>
</xsd:sequence>
</xsd:group>
<xsd:simpleType name="ST_Ligatures">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="none"/>
<xsd:enumeration value="standard"/>
<xsd:enumeration value="contextual"/>
<xsd:enumeration value="historical"/>
<xsd:enumeration value="discretional"/>
<xsd:enumeration value="standardContextual"/>
<xsd:enumeration value="standardHistorical"/>
<xsd:enumeration value="contextualHistorical"/>
<xsd:enumeration value="standardDiscretional"/>
<xsd:enumeration value="contextualDiscretional"/>
<xsd:enumeration value="historicalDiscretional"/>
<xsd:enumeration value="standardContextualHistorical"/>
<xsd:enumeration value="standardContextualDiscretional"/>
<xsd:enumeration value="standardHistoricalDiscretional"/>
<xsd:enumeration value="contextualHistoricalDiscretional"/>
<xsd:enumeration value="all"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_Ligatures">
<xsd:attribute name="val" type="ST_Ligatures" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_NumForm">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="default"/>
<xsd:enumeration value="lining"/>
<xsd:enumeration value="oldStyle"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_NumForm">
<xsd:attribute name="val" type="ST_NumForm" use="required"/>
</xsd:complexType>
<xsd:simpleType name="ST_NumSpacing">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="default"/>
<xsd:enumeration value="proportional"/>
<xsd:enumeration value="tabular"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_NumSpacing">
<xsd:attribute name="val" type="ST_NumSpacing" use="required"/>
</xsd:complexType>
<xsd:complexType name="CT_StyleSet">
<xsd:attribute name="id" type="s:ST_UnsignedDecimalNumber" use="required"/>
<xsd:attribute name="val" type="ST_OnOff" use="optional"/>
</xsd:complexType>
<xsd:complexType name="CT_StylisticSets">
<xsd:sequence minOccurs="0">
<xsd:element name="styleSet" minOccurs="0" maxOccurs="unbounded" type="CT_StyleSet"/>
</xsd:sequence>
</xsd:complexType>
<xsd:group name="EG_RPrOpenType">
<xsd:sequence>
<xsd:element name="ligatures" minOccurs="0" type="CT_Ligatures"/>
<xsd:element name="numForm" minOccurs="0" type="CT_NumForm"/>
<xsd:element name="numSpacing" minOccurs="0" type="CT_NumSpacing"/>
<xsd:element name="stylisticSets" minOccurs="0" type="CT_StylisticSets"/>
<xsd:element name="cntxtAlts" minOccurs="0" type="CT_OnOff"/>
</xsd:sequence>
</xsd:group>
<xsd:element name="discardImageEditingData" type="CT_OnOff"/>
<xsd:element name="defaultImageDpi" type="CT_DefaultImageDpi"/>
<xsd:complexType name="CT_DefaultImageDpi">
<xsd:attribute name="val" type="w:ST_DecimalNumber" use="required"/>
</xsd:complexType>
<xsd:element name="entityPicker" type="w:CT_Empty"/>
<xsd:complexType name="CT_SdtCheckboxSymbol">
<xsd:attribute name="font" type="s:ST_String"/>
<xsd:attribute name="val" type="w:ST_ShortHexNumber"/>
</xsd:complexType>
<xsd:complexType name="CT_SdtCheckbox">
<xsd:sequence>
<xsd:element name="checked" type="CT_OnOff" minOccurs="0"/>
<xsd:element name="checkedState" type="CT_SdtCheckboxSymbol" minOccurs="0"/>
<xsd:element name="uncheckedState" type="CT_SdtCheckboxSymbol" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:element name="checkbox" type="CT_SdtCheckbox"/>
</xsd:schema>

67
skills/docx/ooxml/schemas/microsoft/wml-2012.xsd Normal file
View File

@@ -0,0 +1,67 @@
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:w12="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:s="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes" elementFormDefault="qualified" attributeFormDefault="qualified" blockDefault="#all" xmlns="http://schemas.microsoft.com/office/word/2012/wordml" targetNamespace="http://schemas.microsoft.com/office/word/2012/wordml">
<xsd:import id="w12" namespace="http://schemas.openxmlformats.org/wordprocessingml/2006/main" schemaLocation="../ISO-IEC29500-4_2016/wml.xsd"/>
<xsd:import namespace="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes" schemaLocation="../ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd"/>
<xsd:element name="color" type="w12:CT_Color"/>
<xsd:simpleType name="ST_SdtAppearance">
<xsd:restriction base="xsd:string">
<xsd:enumeration value="boundingBox"/>
<xsd:enumeration value="tags"/>
<xsd:enumeration value="hidden"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:element name="dataBinding" type="w12:CT_DataBinding"/>
<xsd:complexType name="CT_SdtAppearance">
<xsd:attribute name="val" type="ST_SdtAppearance"/>
</xsd:complexType>
<xsd:element name="appearance" type="CT_SdtAppearance"/>
<xsd:complexType name="CT_CommentsEx">
<xsd:sequence>
<xsd:element name="commentEx" type="CT_CommentEx" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_CommentEx">
<xsd:attribute name="paraId" type="w12:ST_LongHexNumber" use="required"/>
<xsd:attribute name="paraIdParent" type="w12:ST_LongHexNumber" use="optional"/>
<xsd:attribute name="done" type="s:ST_OnOff" use="optional"/>
</xsd:complexType>
<xsd:element name="commentsEx" type="CT_CommentsEx"/>
<xsd:complexType name="CT_People">
<xsd:sequence>
<xsd:element name="person" type="CT_Person" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_PresenceInfo">
<xsd:attribute name="providerId" type="xsd:string" use="required"/>
<xsd:attribute name="userId" type="xsd:string" use="required"/>
</xsd:complexType>
<xsd:complexType name="CT_Person">
<xsd:sequence>
<xsd:element name="presenceInfo" type="CT_PresenceInfo" minOccurs="0" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="author" type="s:ST_String" use="required"/>
</xsd:complexType>
<xsd:element name="people" type="CT_People"/>
<xsd:complexType name="CT_SdtRepeatedSection">
<xsd:sequence>
<xsd:element name="sectionTitle" type="w12:CT_String" minOccurs="0"/>
<xsd:element name="doNotAllowInsertDeleteSection" type="w12:CT_OnOff" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:simpleType name="ST_Guid">
<xsd:restriction base="xsd:token">
<xsd:pattern value="\{[0-9A-F]{8}-[0-9A-F]{4}-[0-9A-F]{4}-[0-9A-F]{4}-[0-9A-F]{12}\}"/>
</xsd:restriction>
</xsd:simpleType>
<xsd:complexType name="CT_Guid">
<xsd:attribute name="val" type="ST_Guid"/>
</xsd:complexType>
<xsd:element name="repeatingSection" type="CT_SdtRepeatedSection"/>
<xsd:element name="repeatingSectionItem" type="w12:CT_Empty"/>
<xsd:element name="chartTrackingRefBased" type="w12:CT_OnOff"/>
<xsd:element name="collapsed" type="w12:CT_OnOff"/>
<xsd:element name="docId" type="CT_Guid"/>
<xsd:element name="footnoteColumns" type="w12:CT_DecimalNumber"/>
<xsd:element name="webExtensionLinked" type="w12:CT_OnOff"/>
<xsd:element name="webExtensionCreated" type="w12:CT_OnOff"/>
<xsd:attribute name="restartNumberingAfterBreak" type="s:ST_OnOff"/>
</xsd:schema>

14
skills/docx/ooxml/schemas/microsoft/wml-2018.xsd Normal file
View File

@@ -0,0 +1,14 @@
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:w12="http://schemas.openxmlformats.org/wordprocessingml/2006/main" elementFormDefault="qualified" attributeFormDefault="qualified" blockDefault="#all" xmlns="http://schemas.microsoft.com/office/word/2018/wordml" targetNamespace="http://schemas.microsoft.com/office/word/2018/wordml">
<xsd:import id="w12" namespace="http://schemas.openxmlformats.org/wordprocessingml/2006/main" schemaLocation="../ISO-IEC29500-4_2016/wml.xsd"/>
<xsd:complexType name="CT_Extension">
<xsd:sequence>
<xsd:any processContents="lax"/>
</xsd:sequence>
<xsd:attribute name="uri" type="xsd:token"/>
</xsd:complexType>
<xsd:complexType name="CT_ExtensionList">
<xsd:sequence>
<xsd:element name="ext" type="CT_Extension" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
</xsd:schema>

20
skills/docx/ooxml/schemas/microsoft/wml-cex-2018.xsd Normal file
View File

@@ -0,0 +1,20 @@
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:s="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes" xmlns:w16="http://schemas.microsoft.com/office/word/2018/wordml" elementFormDefault="qualified" attributeFormDefault="qualified" blockDefault="#all" xmlns="http://schemas.microsoft.com/office/word/2018/wordml/cex" targetNamespace="http://schemas.microsoft.com/office/word/2018/wordml/cex">
<xsd:import id="w16" namespace="http://schemas.microsoft.com/office/word/2018/wordml" schemaLocation="wml-2018.xsd"/>
<xsd:import id="w" namespace="http://schemas.openxmlformats.org/wordprocessingml/2006/main" schemaLocation="../ISO-IEC29500-4_2016/wml.xsd"/>
<xsd:import id="s" namespace="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes" schemaLocation="../ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd"/>
<xsd:complexType name="CT_CommentsExtensible">
<xsd:sequence>
<xsd:element name="commentExtensible" type="CT_CommentExtensible" minOccurs="0" maxOccurs="unbounded"/>
<xsd:element name="extLst" type="w16:CT_ExtensionList" minOccurs="0" maxOccurs="1"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_CommentExtensible">
<xsd:sequence>
<xsd:element name="extLst" type="w16:CT_ExtensionList" minOccurs="0" maxOccurs="1"/>
</xsd:sequence>
<xsd:attribute name="durableId" type="w:ST_LongHexNumber" use="required"/>
<xsd:attribute name="dateUtc" type="w:ST_DateTime" use="optional"/>
<xsd:attribute name="intelligentPlaceholder" type="s:ST_OnOff" use="optional"/>
</xsd:complexType>
<xsd:element name="commentsExtensible" type="CT_CommentsExtensible"/>
</xsd:schema>

13
skills/docx/ooxml/schemas/microsoft/wml-cid-2016.xsd Normal file
View File

@@ -0,0 +1,13 @@
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:w12="http://schemas.openxmlformats.org/wordprocessingml/2006/main" elementFormDefault="qualified" attributeFormDefault="qualified" blockDefault="#all" xmlns="http://schemas.microsoft.com/office/word/2016/wordml/cid" targetNamespace="http://schemas.microsoft.com/office/word/2016/wordml/cid">
<xsd:import id="w12" namespace="http://schemas.openxmlformats.org/wordprocessingml/2006/main" schemaLocation="../ISO-IEC29500-4_2016/wml.xsd"/>
<xsd:complexType name="CT_CommentsIds">
<xsd:sequence>
<xsd:element name="commentId" type="CT_CommentId" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="CT_CommentId">
<xsd:attribute name="paraId" type="w12:ST_LongHexNumber" use="required"/>
<xsd:attribute name="durableId" type="w12:ST_LongHexNumber" use="required"/>
</xsd:complexType>
<xsd:element name="commentsIds" type="CT_CommentsIds"/>
</xsd:schema>

4
skills/docx/ooxml/schemas/microsoft/wml-sdtdatahash-2020.xsd Normal file
View File

@@ -0,0 +1,4 @@
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:w12="http://schemas.openxmlformats.org/wordprocessingml/2006/main" elementFormDefault="qualified" attributeFormDefault="qualified" blockDefault="#all" xmlns="http://schemas.microsoft.com/office/word/2020/wordml/sdtdatahash" targetNamespace="http://schemas.microsoft.com/office/word/2020/wordml/sdtdatahash">
<xsd:import id="w12" namespace="http://schemas.openxmlformats.org/wordprocessingml/2006/main" schemaLocation="../ISO-IEC29500-4_2016/wml.xsd"/>
<xsd:attribute name="storeItemChecksum" type="w12:ST_String"/>
</xsd:schema>

8
skills/docx/ooxml/schemas/microsoft/wml-symex-2015.xsd Normal file
View File

@@ -0,0 +1,8 @@
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:w12="http://schemas.openxmlformats.org/wordprocessingml/2006/main" elementFormDefault="qualified" attributeFormDefault="qualified" blockDefault="#all" xmlns="http://schemas.microsoft.com/office/word/2015/wordml/symex" targetNamespace="http://schemas.microsoft.com/office/word/2015/wordml/symex">
<xsd:import id="w12" namespace="http://schemas.openxmlformats.org/wordprocessingml/2006/main" schemaLocation="../ISO-IEC29500-4_2016/wml.xsd"/>
<xsd:complexType name="CT_SymEx">
<xsd:attribute name="font" type="w12:ST_String"/>
<xsd:attribute name="char" type="w12:ST_LongHexNumber"/>
</xsd:complexType>
<xsd:element name="symEx" type="CT_SymEx"/>
</xsd:schema>

159
skills/docx/ooxml/scripts/pack.py Normal file
View File

@@ -0,0 +1,159 @@
#!/usr/bin/env python3
"""
Tool to pack a directory into a .docx, .pptx, or .xlsx file with XML formatting undone.
Example usage:
python pack.py <input_directory> <office_file> [--force]
"""
import argparse
import shutil
import subprocess
import sys
import tempfile
import defusedxml.minidom
import zipfile
from pathlib import Path
def main():
parser = argparse.ArgumentParser(description="Pack a directory into an Office file")
parser.add_argument("input_directory", help="Unpacked Office document directory")
parser.add_argument("output_file", help="Output Office file (.docx/.pptx/.xlsx)")
parser.add_argument("--force", action="store_true", help="Skip validation")
args = parser.parse_args()
try:
success = pack_document(
args.input_directory, args.output_file, validate=not args.force
)
# Show warning if validation was skipped
if args.force:
print("Warning: Skipped validation, file may be corrupt", file=sys.stderr)
# Exit with error if validation failed
elif not success:
print("Contents would produce a corrupt file.", file=sys.stderr)
print("Please validate XML before repacking.", file=sys.stderr)
print("Use --force to skip validation and pack anyway.", file=sys.stderr)
sys.exit(1)
except ValueError as e:
sys.exit(f"Error: {e}")
def pack_document(input_dir, output_file, validate=False):
"""Pack a directory into an Office file (.docx/.pptx/.xlsx).
Args:
input_dir: Path to unpacked Office document directory
output_file: Path to output Office file
validate: If True, validates with soffice (default: False)
Returns:
bool: True if successful, False if validation failed
"""
input_dir = Path(input_dir)
output_file = Path(output_file)
if not input_dir.is_dir():
raise ValueError(f"{input_dir} is not a directory")
if output_file.suffix.lower() not in {".docx", ".pptx", ".xlsx"}:
raise ValueError(f"{output_file} must be a .docx, .pptx, or .xlsx file")
# Work in temporary directory to avoid modifying original
with tempfile.TemporaryDirectory() as temp_dir:
temp_content_dir = Path(temp_dir) / "content"
shutil.copytree(input_dir, temp_content_dir)
# Process XML files to remove pretty-printing whitespace
for pattern in ["*.xml", "*.rels"]:
for xml_file in temp_content_dir.rglob(pattern):
condense_xml(xml_file)
# Create final Office file as zip archive
output_file.parent.mkdir(parents=True, exist_ok=True)
with zipfile.ZipFile(output_file, "w", zipfile.ZIP_DEFLATED) as zf:
for f in temp_content_dir.rglob("*"):
if f.is_file():
zf.write(f, f.relative_to(temp_content_dir))
# Validate if requested
if validate:
if not validate_document(output_file):
output_file.unlink() # Delete the corrupt file
return False
return True
def validate_document(doc_path):
"""Validate document by converting to HTML with soffice."""
# Determine the correct filter based on file extension
match doc_path.suffix.lower():
case ".docx":
filter_name = "html:HTML"
case ".pptx":
filter_name = "html:impress_html_Export"
case ".xlsx":
filter_name = "html:HTML (StarCalc)"
with tempfile.TemporaryDirectory() as temp_dir:
try:
result = subprocess.run(
[
"soffice",
"--headless",
"--convert-to",
filter_name,
"--outdir",
temp_dir,
str(doc_path),
],
capture_output=True,
timeout=10,
text=True,
)
if not (Path(temp_dir) / f"{doc_path.stem}.html").exists():
error_msg = result.stderr.strip() or "Document validation failed"
print(f"Validation error: {error_msg}", file=sys.stderr)
return False
return True
except FileNotFoundError:
print("Warning: soffice not found. Skipping validation.", file=sys.stderr)
return True
except subprocess.TimeoutExpired:
print("Validation error: Timeout during conversion", file=sys.stderr)
return False
except Exception as e:
print(f"Validation error: {e}", file=sys.stderr)
return False
def condense_xml(xml_file):
"""Strip unnecessary whitespace and remove comments."""
with open(xml_file, "r", encoding="utf-8") as f:
dom = defusedxml.minidom.parse(f)
# Process each element to remove whitespace and comments
for element in dom.getElementsByTagName("*"):
# Skip w:t elements and their processing
if element.tagName.endswith(":t"):
continue
# Remove whitespace-only text nodes and comment nodes
for child in list(element.childNodes):
if (
child.nodeType == child.TEXT_NODE
and child.nodeValue
and child.nodeValue.strip() == ""
) or child.nodeType == child.COMMENT_NODE:
element.removeChild(child)
# Write back the condensed XML
with open(xml_file, "wb") as f:
f.write(dom.toxml(encoding="UTF-8"))
if __name__ == "__main__":
main()

29
skills/docx/ooxml/scripts/unpack.py Normal file
View File

@@ -0,0 +1,29 @@
#!/usr/bin/env python3
"""Unpack and format XML contents of Office files (.docx, .pptx, .xlsx)"""
import random
import sys
import defusedxml.minidom
import zipfile
from pathlib import Path
# Get command line arguments
assert len(sys.argv) == 3, "Usage: python unpack.py <office_file> <output_dir>"
input_file, output_dir = sys.argv[1], sys.argv[2]
# Extract and format
output_path = Path(output_dir)
output_path.mkdir(parents=True, exist_ok=True)
zipfile.ZipFile(input_file).extractall(output_path)
# Pretty print all XML files
xml_files = list(output_path.rglob("*.xml")) + list(output_path.rglob("*.rels"))
for xml_file in xml_files:
content = xml_file.read_text(encoding="utf-8")
dom = defusedxml.minidom.parseString(content)
xml_file.write_bytes(dom.toprettyxml(indent=" ", encoding="ascii"))
# For .docx files, suggest an RSID for tracked changes
if input_file.endswith(".docx"):
suggested_rsid = "".join(random.choices("0123456789ABCDEF", k=8))
print(f"Suggested RSID for edit session: {suggested_rsid}")

69
skills/docx/ooxml/scripts/validate.py Normal file
View File

@@ -0,0 +1,69 @@
#!/usr/bin/env python3
"""
Command line tool to validate Office document XML files against XSD schemas and tracked changes.
Usage:
python validate.py <dir> --original <original_file>
"""
import argparse
import sys
from pathlib import Path
from validation import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator
def main():
parser = argparse.ArgumentParser(description="Validate Office document XML files")
parser.add_argument(
"unpacked_dir",
help="Path to unpacked Office document directory",
)
parser.add_argument(
"--original",
required=True,
help="Path to original file (.docx/.pptx/.xlsx)",
)
parser.add_argument(
"-v",
"--verbose",
action="store_true",
help="Enable verbose output",
)
args = parser.parse_args()
# Validate paths
unpacked_dir = Path(args.unpacked_dir)
original_file = Path(args.original)
file_extension = original_file.suffix.lower()
assert unpacked_dir.is_dir(), f"Error: {unpacked_dir} is not a directory"
assert original_file.is_file(), f"Error: {original_file} is not a file"
assert file_extension in [".docx", ".pptx", ".xlsx"], (
f"Error: {original_file} must be a .docx, .pptx, or .xlsx file"
)
# Run validations
match file_extension:
case ".docx":
validators = [DOCXSchemaValidator, RedliningValidator]
case ".pptx":
validators = [PPTXSchemaValidator]
case _:
print(f"Error: Validation not supported for file type {file_extension}")
sys.exit(1)
# Run validators
success = True
for V in validators:
validator = V(unpacked_dir, original_file, verbose=args.verbose)
if not validator.validate():
success = False
if success:
print("All validations PASSED!")
sys.exit(0 if success else 1)
if __name__ == "__main__":
main()

15
skills/docx/ooxml/scripts/validation/__init__.py Normal file
View File

@@ -0,0 +1,15 @@
"""
Validation modules for Word document processing.
"""
from .base import BaseSchemaValidator
from .docx import DOCXSchemaValidator
from .pptx import PPTXSchemaValidator
from .redlining import RedliningValidator
__all__ = [
"BaseSchemaValidator",
"DOCXSchemaValidator",
"PPTXSchemaValidator",
"RedliningValidator",
]

951
skills/docx/ooxml/scripts/validation/base.py Normal file
View File

@@ -0,0 +1,951 @@
"""
Base validator with common validation logic for document files.
"""
import re
from pathlib import Path
import lxml.etree
class BaseSchemaValidator:
"""Base validator with common validation logic for document files."""
# Elements whose 'id' attributes must be unique within their file
# Format: element_name -> (attribute_name, scope)
# scope can be 'file' (unique within file) or 'global' (unique across all files)
UNIQUE_ID_REQUIREMENTS = {
# Word elements
"comment": ("id", "file"), # Comment IDs in comments.xml
"commentrangestart": ("id", "file"), # Must match comment IDs
"commentrangeend": ("id", "file"), # Must match comment IDs
"bookmarkstart": ("id", "file"), # Bookmark start IDs
"bookmarkend": ("id", "file"), # Bookmark end IDs
# Note: ins and del (track changes) can share IDs when part of same revision
# PowerPoint elements
"sldid": ("id", "file"), # Slide IDs in presentation.xml
"sldmasterid": ("id", "global"), # Slide master IDs must be globally unique
"sldlayoutid": ("id", "global"), # Slide layout IDs must be globally unique
"cm": ("authorid", "file"), # Comment author IDs
# Excel elements
"sheet": ("sheetid", "file"), # Sheet IDs in workbook.xml
"definedname": ("id", "file"), # Named range IDs
# Drawing/Shape elements (all formats)
"cxnsp": ("id", "file"), # Connection shape IDs
"sp": ("id", "file"), # Shape IDs
"pic": ("id", "file"), # Picture IDs
"grpsp": ("id", "file"), # Group shape IDs
}
# Mapping of element names to expected relationship types
# Subclasses should override this with format-specific mappings
ELEMENT_RELATIONSHIP_TYPES = {}
# Unified schema mappings for all Office document types
SCHEMA_MAPPINGS = {
# Document type specific schemas
"word": "ISO-IEC29500-4_2016/wml.xsd", # Word documents
"ppt": "ISO-IEC29500-4_2016/pml.xsd", # PowerPoint presentations
"xl": "ISO-IEC29500-4_2016/sml.xsd", # Excel spreadsheets
# Common file types
"[Content_Types].xml": "ecma/fouth-edition/opc-contentTypes.xsd",
"app.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd",
"core.xml": "ecma/fouth-edition/opc-coreProperties.xsd",
"custom.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd",
".rels": "ecma/fouth-edition/opc-relationships.xsd",
# Word-specific files
"people.xml": "microsoft/wml-2012.xsd",
"commentsIds.xml": "microsoft/wml-cid-2016.xsd",
"commentsExtensible.xml": "microsoft/wml-cex-2018.xsd",
"commentsExtended.xml": "microsoft/wml-2012.xsd",
# Chart files (common across document types)
"chart": "ISO-IEC29500-4_2016/dml-chart.xsd",
# Theme files (common across document types)
"theme": "ISO-IEC29500-4_2016/dml-main.xsd",
# Drawing and media files
"drawing": "ISO-IEC29500-4_2016/dml-main.xsd",
}
# Unified namespace constants
MC_NAMESPACE = "http://schemas.openxmlformats.org/markup-compatibility/2006"
XML_NAMESPACE = "http://www.w3.org/XML/1998/namespace"
# Common OOXML namespaces used across validators
PACKAGE_RELATIONSHIPS_NAMESPACE = (
"http://schemas.openxmlformats.org/package/2006/relationships"
)
OFFICE_RELATIONSHIPS_NAMESPACE = (
"http://schemas.openxmlformats.org/officeDocument/2006/relationships"
)
CONTENT_TYPES_NAMESPACE = (
"http://schemas.openxmlformats.org/package/2006/content-types"
)
# Folders where we should clean ignorable namespaces
MAIN_CONTENT_FOLDERS = {"word", "ppt", "xl"}
# All allowed OOXML namespaces (superset of all document types)
OOXML_NAMESPACES = {
"http://schemas.openxmlformats.org/officeDocument/2006/math",
"http://schemas.openxmlformats.org/officeDocument/2006/relationships",
"http://schemas.openxmlformats.org/schemaLibrary/2006/main",
"http://schemas.openxmlformats.org/drawingml/2006/main",
"http://schemas.openxmlformats.org/drawingml/2006/chart",
"http://schemas.openxmlformats.org/drawingml/2006/chartDrawing",
"http://schemas.openxmlformats.org/drawingml/2006/diagram",
"http://schemas.openxmlformats.org/drawingml/2006/picture",
"http://schemas.openxmlformats.org/drawingml/2006/spreadsheetDrawing",
"http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing",
"http://schemas.openxmlformats.org/wordprocessingml/2006/main",
"http://schemas.openxmlformats.org/presentationml/2006/main",
"http://schemas.openxmlformats.org/spreadsheetml/2006/main",
"http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes",
"http://www.w3.org/XML/1998/namespace",
}
def __init__(self, unpacked_dir, original_file, verbose=False):
self.unpacked_dir = Path(unpacked_dir).resolve()
self.original_file = Path(original_file)
self.verbose = verbose
# Set schemas directory
self.schemas_dir = Path(__file__).parent.parent.parent / "schemas"
# Get all XML and .rels files
patterns = ["*.xml", "*.rels"]
self.xml_files = [
f for pattern in patterns for f in self.unpacked_dir.rglob(pattern)
]
if not self.xml_files:
print(f"Warning: No XML files found in {self.unpacked_dir}")
def validate(self):
"""Run all validation checks and return True if all pass."""
raise NotImplementedError("Subclasses must implement the validate method")
def validate_xml(self):
"""Validate that all XML files are well-formed."""
errors = []
for xml_file in self.xml_files:
try:
# Try to parse the XML file
lxml.etree.parse(str(xml_file))
except lxml.etree.XMLSyntaxError as e:
errors.append(
f" {xml_file.relative_to(self.unpacked_dir)}: "
f"Line {e.lineno}: {e.msg}"
)
except Exception as e:
errors.append(
f" {xml_file.relative_to(self.unpacked_dir)}: "
f"Unexpected error: {str(e)}"
)
if errors:
print(f"FAILED - Found {len(errors)} XML violations:")
for error in errors:
print(error)
return False
else:
if self.verbose:
print("PASSED - All XML files are well-formed")
return True
def validate_namespaces(self):
"""Validate that namespace prefixes in Ignorable attributes are declared."""
errors = []
for xml_file in self.xml_files:
try:
root = lxml.etree.parse(str(xml_file)).getroot()
declared = set(root.nsmap.keys()) - {None} # Exclude default namespace
for attr_val in [
v for k, v in root.attrib.items() if k.endswith("Ignorable")
]:
undeclared = set(attr_val.split()) - declared
errors.extend(
f" {xml_file.relative_to(self.unpacked_dir)}: "
f"Namespace '{ns}' in Ignorable but not declared"
for ns in undeclared
)
except lxml.etree.XMLSyntaxError:
continue
if errors:
print(f"FAILED - {len(errors)} namespace issues:")
for error in errors:
print(error)
return False
if self.verbose:
print("PASSED - All namespace prefixes properly declared")
return True
def validate_unique_ids(self):
"""Validate that specific IDs are unique according to OOXML requirements."""
errors = []
global_ids = {} # Track globally unique IDs across all files
for xml_file in self.xml_files:
try:
root = lxml.etree.parse(str(xml_file)).getroot()
file_ids = {} # Track IDs that must be unique within this file
# Remove all mc:AlternateContent elements from the tree
mc_elements = root.xpath(
".//mc:AlternateContent", namespaces={"mc": self.MC_NAMESPACE}
)
for elem in mc_elements:
elem.getparent().remove(elem)
# Now check IDs in the cleaned tree
for elem in root.iter():
# Get the element name without namespace
tag = (
elem.tag.split("}")[-1].lower()
if "}" in elem.tag
else elem.tag.lower()
)
# Check if this element type has ID uniqueness requirements
if tag in self.UNIQUE_ID_REQUIREMENTS:
attr_name, scope = self.UNIQUE_ID_REQUIREMENTS[tag]
# Look for the specified attribute
id_value = None
for attr, value in elem.attrib.items():
attr_local = (
attr.split("}")[-1].lower()
if "}" in attr
else attr.lower()
)
if attr_local == attr_name:
id_value = value
break
if id_value is not None:
if scope == "global":
# Check global uniqueness
if id_value in global_ids:
prev_file, prev_line, prev_tag = global_ids[
id_value
]
errors.append(
f" {xml_file.relative_to(self.unpacked_dir)}: "
f"Line {elem.sourceline}: Global ID '{id_value}' in <{tag}> "
f"already used in {prev_file} at line {prev_line} in <{prev_tag}>"
)
else:
global_ids[id_value] = (
xml_file.relative_to(self.unpacked_dir),
elem.sourceline,
tag,
)
elif scope == "file":
# Check file-level uniqueness
key = (tag, attr_name)
if key not in file_ids:
file_ids[key] = {}
if id_value in file_ids[key]:
prev_line = file_ids[key][id_value]
errors.append(
f" {xml_file.relative_to(self.unpacked_dir)}: "
f"Line {elem.sourceline}: Duplicate {attr_name}='{id_value}' in <{tag}> "
f"(first occurrence at line {prev_line})"
)
else:
file_ids[key][id_value] = elem.sourceline
except (lxml.etree.XMLSyntaxError, Exception) as e:
errors.append(
f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}"
)
if errors:
print(f"FAILED - Found {len(errors)} ID uniqueness violations:")
for error in errors:
print(error)
return False
else:
if self.verbose:
print("PASSED - All required IDs are unique")
return True
def validate_file_references(self):
"""
Validate that all .rels files properly reference files and that all files are referenced.
"""
errors = []
# Find all .rels files
rels_files = list(self.unpacked_dir.rglob("*.rels"))
if not rels_files:
if self.verbose:
print("PASSED - No .rels files found")
return True
# Get all files in the unpacked directory (excluding reference files)
all_files = []
for file_path in self.unpacked_dir.rglob("*"):
if (
file_path.is_file()
and file_path.name != "[Content_Types].xml"
and not file_path.name.endswith(".rels")
): # This file is not referenced by .rels
all_files.append(file_path.resolve())
# Track all files that are referenced by any .rels file
all_referenced_files = set()
if self.verbose:
print(
f"Found {len(rels_files)} .rels files and {len(all_files)} target files"
)
# Check each .rels file
for rels_file in rels_files:
try:
# Parse relationships file
rels_root = lxml.etree.parse(str(rels_file)).getroot()
# Get the directory where this .rels file is located
rels_dir = rels_file.parent
# Find all relationships and their targets
referenced_files = set()
broken_refs = []
for rel in rels_root.findall(
".//ns:Relationship",
namespaces={"ns": self.PACKAGE_RELATIONSHIPS_NAMESPACE},
):
target = rel.get("Target")
if target and not target.startswith(
("http", "mailto:")
): # Skip external URLs
# Resolve the target path relative to the .rels file location
if rels_file.name == ".rels":
# Root .rels file - targets are relative to unpacked_dir
target_path = self.unpacked_dir / target
else:
# Other .rels files - targets are relative to their parent's parent
# e.g., word/_rels/document.xml.rels -> targets relative to word/
base_dir = rels_dir.parent
target_path = base_dir / target
# Normalize the path and check if it exists
try:
target_path = target_path.resolve()
if target_path.exists() and target_path.is_file():
referenced_files.add(target_path)
all_referenced_files.add(target_path)
else:
broken_refs.append((target, rel.sourceline))
except (OSError, ValueError):
broken_refs.append((target, rel.sourceline))
# Report broken references
if broken_refs:
rel_path = rels_file.relative_to(self.unpacked_dir)
for broken_ref, line_num in broken_refs:
errors.append(
f" {rel_path}: Line {line_num}: Broken reference to {broken_ref}"
)
except Exception as e:
rel_path = rels_file.relative_to(self.unpacked_dir)
errors.append(f" Error parsing {rel_path}: {e}")
# Check for unreferenced files (files that exist but are not referenced anywhere)
unreferenced_files = set(all_files) - all_referenced_files
if unreferenced_files:
for unref_file in sorted(unreferenced_files):
unref_rel_path = unref_file.relative_to(self.unpacked_dir)
errors.append(f" Unreferenced file: {unref_rel_path}")
if errors:
print(f"FAILED - Found {len(errors)} relationship validation errors:")
for error in errors:
print(error)
print(
"CRITICAL: These errors will cause the document to appear corrupt. "
+ "Broken references MUST be fixed, "
+ "and unreferenced files MUST be referenced or removed."
)
return False
else:
if self.verbose:
print(
"PASSED - All references are valid and all files are properly referenced"
)
return True
def validate_all_relationship_ids(self):
"""
Validate that all r:id attributes in XML files reference existing IDs
in their corresponding .rels files, and optionally validate relationship types.
"""
import lxml.etree
errors = []
# Process each XML file that might contain r:id references
for xml_file in self.xml_files:
# Skip .rels files themselves
if xml_file.suffix == ".rels":
continue
# Determine the corresponding .rels file
# For dir/file.xml, it's dir/_rels/file.xml.rels
rels_dir = xml_file.parent / "_rels"
rels_file = rels_dir / f"{xml_file.name}.rels"
# Skip if there's no corresponding .rels file (that's okay)
if not rels_file.exists():
continue
try:
# Parse the .rels file to get valid relationship IDs and their types
rels_root = lxml.etree.parse(str(rels_file)).getroot()
rid_to_type = {}
for rel in rels_root.findall(
f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship"
):
rid = rel.get("Id")
rel_type = rel.get("Type", "")
if rid:
# Check for duplicate rIds
if rid in rid_to_type:
rels_rel_path = rels_file.relative_to(self.unpacked_dir)
errors.append(
f" {rels_rel_path}: Line {rel.sourceline}: "
f"Duplicate relationship ID '{rid}' (IDs must be unique)"
)
# Extract just the type name from the full URL
type_name = (
rel_type.split("/")[-1] if "/" in rel_type else rel_type
)
rid_to_type[rid] = type_name
# Parse the XML file to find all r:id references
xml_root = lxml.etree.parse(str(xml_file)).getroot()
# Find all elements with r:id attributes
for elem in xml_root.iter():
# Check for r:id attribute (relationship ID)
rid_attr = elem.get(f"{{{self.OFFICE_RELATIONSHIPS_NAMESPACE}}}id")
if rid_attr:
xml_rel_path = xml_file.relative_to(self.unpacked_dir)
elem_name = (
elem.tag.split("}")[-1] if "}" in elem.tag else elem.tag
)
# Check if the ID exists
if rid_attr not in rid_to_type:
errors.append(
f" {xml_rel_path}: Line {elem.sourceline}: "
f"<{elem_name}> references non-existent relationship '{rid_attr}' "
f"(valid IDs: {', '.join(sorted(rid_to_type.keys())[:5])}{'...' if len(rid_to_type) > 5 else ''})"
)
# Check if we have type expectations for this element
elif self.ELEMENT_RELATIONSHIP_TYPES:
expected_type = self._get_expected_relationship_type(
elem_name
)
if expected_type:
actual_type = rid_to_type[rid_attr]
# Check if the actual type matches or contains the expected type
if expected_type not in actual_type.lower():
errors.append(
f" {xml_rel_path}: Line {elem.sourceline}: "
f"<{elem_name}> references '{rid_attr}' which points to '{actual_type}' "
f"but should point to a '{expected_type}' relationship"
)
except Exception as e:
xml_rel_path = xml_file.relative_to(self.unpacked_dir)
errors.append(f" Error processing {xml_rel_path}: {e}")
if errors:
print(f"FAILED - Found {len(errors)} relationship ID reference errors:")
for error in errors:
print(error)
print("\nThese ID mismatches will cause the document to appear corrupt!")
return False
else:
if self.verbose:
print("PASSED - All relationship ID references are valid")
return True
def _get_expected_relationship_type(self, element_name):
"""
Get the expected relationship type for an element.
First checks the explicit mapping, then tries pattern detection.
"""
# Normalize element name to lowercase
elem_lower = element_name.lower()
# Check explicit mapping first
if elem_lower in self.ELEMENT_RELATIONSHIP_TYPES:
return self.ELEMENT_RELATIONSHIP_TYPES[elem_lower]
# Try pattern detection for common patterns
# Pattern 1: Elements ending in "Id" often expect a relationship of the prefix type
if elem_lower.endswith("id") and len(elem_lower) > 2:
# e.g., "sldId" -> "sld", "sldMasterId" -> "sldMaster"
prefix = elem_lower[:-2] # Remove "id"
# Check if this might be a compound like "sldMasterId"
if prefix.endswith("master"):
return prefix.lower()
elif prefix.endswith("layout"):
return prefix.lower()
else:
# Simple case like "sldId" -> "slide"
# Common transformations
if prefix == "sld":
return "slide"
return prefix.lower()
# Pattern 2: Elements ending in "Reference" expect a relationship of the prefix type
if elem_lower.endswith("reference") and len(elem_lower) > 9:
prefix = elem_lower[:-9] # Remove "reference"
return prefix.lower()
return None
def validate_content_types(self):
"""Validate that all content files are properly declared in [Content_Types].xml."""
errors = []
# Find [Content_Types].xml file
content_types_file = self.unpacked_dir / "[Content_Types].xml"
if not content_types_file.exists():
print("FAILED - [Content_Types].xml file not found")
return False
try:
# Parse and get all declared parts and extensions
root = lxml.etree.parse(str(content_types_file)).getroot()
declared_parts = set()
declared_extensions = set()
# Get Override declarations (specific files)
for override in root.findall(
f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Override"
):
part_name = override.get("PartName")
if part_name is not None:
declared_parts.add(part_name.lstrip("/"))
# Get Default declarations (by extension)
for default in root.findall(
f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Default"
):
extension = default.get("Extension")
if extension is not None:
declared_extensions.add(extension.lower())
# Root elements that require content type declaration
declarable_roots = {
"sld",
"sldLayout",
"sldMaster",
"presentation", # PowerPoint
"document", # Word
"workbook",
"worksheet", # Excel
"theme", # Common
}
# Common media file extensions that should be declared
media_extensions = {
"png": "image/png",
"jpg": "image/jpeg",
"jpeg": "image/jpeg",
"gif": "image/gif",
"bmp": "image/bmp",
"tiff": "image/tiff",
"wmf": "image/x-wmf",
"emf": "image/x-emf",
}
# Get all files in the unpacked directory
all_files = list(self.unpacked_dir.rglob("*"))
all_files = [f for f in all_files if f.is_file()]
# Check all XML files for Override declarations
for xml_file in self.xml_files:
path_str = str(xml_file.relative_to(self.unpacked_dir)).replace(
"\\", "/"
)
# Skip non-content files
if any(
skip in path_str
for skip in [".rels", "[Content_Types]", "docProps/", "_rels/"]
):
continue
try:
root_tag = lxml.etree.parse(str(xml_file)).getroot().tag
root_name = root_tag.split("}")[-1] if "}" in root_tag else root_tag
if root_name in declarable_roots and path_str not in declared_parts:
errors.append(
f" {path_str}: File with <{root_name}> root not declared in [Content_Types].xml"
)
except Exception:
continue # Skip unparseable files
# Check all non-XML files for Default extension declarations
for file_path in all_files:
# Skip XML files and metadata files (already checked above)
if file_path.suffix.lower() in {".xml", ".rels"}:
continue
if file_path.name == "[Content_Types].xml":
continue
if "_rels" in file_path.parts or "docProps" in file_path.parts:
continue
extension = file_path.suffix.lstrip(".").lower()
if extension and extension not in declared_extensions:
# Check if it's a known media extension that should be declared
if extension in media_extensions:
relative_path = file_path.relative_to(self.unpacked_dir)
errors.append(
f' {relative_path}: File with extension \'{extension}\' not declared in [Content_Types].xml - should add: <Default Extension="{extension}" ContentType="{media_extensions[extension]}"/>'
)
except Exception as e:
errors.append(f" Error parsing [Content_Types].xml: {e}")
if errors:
print(f"FAILED - Found {len(errors)} content type declaration errors:")
for error in errors:
print(error)
return False
else:
if self.verbose:
print(
"PASSED - All content files are properly declared in [Content_Types].xml"
)
return True
def validate_file_against_xsd(self, xml_file, verbose=False):
"""Validate a single XML file against XSD schema, comparing with original.
Args:
xml_file: Path to XML file to validate
verbose: Enable verbose output
Returns:
tuple: (is_valid, new_errors_set) where is_valid is True/False/None (skipped)
"""
# Resolve both paths to handle symlinks
xml_file = Path(xml_file).resolve()
unpacked_dir = self.unpacked_dir.resolve()
# Validate current file
is_valid, current_errors = self._validate_single_file_xsd(
xml_file, unpacked_dir
)
if is_valid is None:
return None, set() # Skipped
elif is_valid:
return True, set() # Valid, no errors
# Get errors from original file for this specific file
original_errors = self._get_original_file_errors(xml_file)
# Compare with original (both are guaranteed to be sets here)
assert current_errors is not None
new_errors = current_errors - original_errors
if new_errors:
if verbose:
relative_path = xml_file.relative_to(unpacked_dir)
print(f"FAILED - {relative_path}: {len(new_errors)} new error(s)")
for error in list(new_errors)[:3]:
truncated = error[:250] + "..." if len(error) > 250 else error
print(f" - {truncated}")
return False, new_errors
else:
# All errors existed in original
if verbose:
print(
f"PASSED - No new errors (original had {len(current_errors)} errors)"
)
return True, set()
def validate_against_xsd(self):
"""Validate XML files against XSD schemas, showing only new errors compared to original."""
new_errors = []
original_error_count = 0
valid_count = 0
skipped_count = 0
for xml_file in self.xml_files:
relative_path = str(xml_file.relative_to(self.unpacked_dir))
is_valid, new_file_errors = self.validate_file_against_xsd(
xml_file, verbose=False
)
if is_valid is None:
skipped_count += 1
continue
elif is_valid and not new_file_errors:
valid_count += 1
continue
elif is_valid:
# Had errors but all existed in original
original_error_count += 1
valid_count += 1
continue
# Has new errors
new_errors.append(f" {relative_path}: {len(new_file_errors)} new error(s)")
for error in list(new_file_errors)[:3]: # Show first 3 errors
new_errors.append(
f" - {error[:250]}..." if len(error) > 250 else f" - {error}"
)
# Print summary
if self.verbose:
print(f"Validated {len(self.xml_files)} files:")
print(f" - Valid: {valid_count}")
print(f" - Skipped (no schema): {skipped_count}")
if original_error_count:
print(f" - With original errors (ignored): {original_error_count}")
print(
f" - With NEW errors: {len(new_errors) > 0 and len([e for e in new_errors if not e.startswith(' ')]) or 0}"
)
if new_errors:
print("\nFAILED - Found NEW validation errors:")
for error in new_errors:
print(error)
return False
else:
if self.verbose:
print("\nPASSED - No new XSD validation errors introduced")
return True
def _get_schema_path(self, xml_file):
"""Determine the appropriate schema path for an XML file."""
# Check exact filename match
if xml_file.name in self.SCHEMA_MAPPINGS:
return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.name]
# Check .rels files
if xml_file.suffix == ".rels":
return self.schemas_dir / self.SCHEMA_MAPPINGS[".rels"]
# Check chart files
if "charts/" in str(xml_file) and xml_file.name.startswith("chart"):
return self.schemas_dir / self.SCHEMA_MAPPINGS["chart"]
# Check theme files
if "theme/" in str(xml_file) and xml_file.name.startswith("theme"):
return self.schemas_dir / self.SCHEMA_MAPPINGS["theme"]
# Check if file is in a main content folder and use appropriate schema
if xml_file.parent.name in self.MAIN_CONTENT_FOLDERS:
return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.parent.name]
return None
def _clean_ignorable_namespaces(self, xml_doc):
"""Remove attributes and elements not in allowed namespaces."""
# Create a clean copy
xml_string = lxml.etree.tostring(xml_doc, encoding="unicode")
xml_copy = lxml.etree.fromstring(xml_string)
# Remove attributes not in allowed namespaces
for elem in xml_copy.iter():
attrs_to_remove = []
for attr in elem.attrib:
# Check if attribute is from a namespace other than allowed ones
if "{" in attr:
ns = attr.split("}")[0][1:]
if ns not in self.OOXML_NAMESPACES:
attrs_to_remove.append(attr)
# Remove collected attributes
for attr in attrs_to_remove:
del elem.attrib[attr]
# Remove elements not in allowed namespaces
self._remove_ignorable_elements(xml_copy)
return lxml.etree.ElementTree(xml_copy)
def _remove_ignorable_elements(self, root):
"""Recursively remove all elements not in allowed namespaces."""
elements_to_remove = []
# Find elements to remove
for elem in list(root):
# Skip non-element nodes (comments, processing instructions, etc.)
if not hasattr(elem, "tag") or callable(elem.tag):
continue
tag_str = str(elem.tag)
if tag_str.startswith("{"):
ns = tag_str.split("}")[0][1:]
if ns not in self.OOXML_NAMESPACES:
elements_to_remove.append(elem)
continue
# Recursively clean child elements
self._remove_ignorable_elements(elem)
# Remove collected elements
for elem in elements_to_remove:
root.remove(elem)
def _preprocess_for_mc_ignorable(self, xml_doc):
"""Preprocess XML to handle mc:Ignorable attribute properly."""
# Remove mc:Ignorable attributes before validation
root = xml_doc.getroot()
# Remove mc:Ignorable attribute from root
if f"{{{self.MC_NAMESPACE}}}Ignorable" in root.attrib:
del root.attrib[f"{{{self.MC_NAMESPACE}}}Ignorable"]
return xml_doc
def _validate_single_file_xsd(self, xml_file, base_path):
"""Validate a single XML file against XSD schema. Returns (is_valid, errors_set)."""
schema_path = self._get_schema_path(xml_file)
if not schema_path:
return None, None # Skip file
try:
# Load schema
with open(schema_path, "rb") as xsd_file:
parser = lxml.etree.XMLParser()
xsd_doc = lxml.etree.parse(
xsd_file, parser=parser, base_url=str(schema_path)
)
schema = lxml.etree.XMLSchema(xsd_doc)
# Load and preprocess XML
with open(xml_file, "r") as f:
xml_doc = lxml.etree.parse(f)
xml_doc, _ = self._remove_template_tags_from_text_nodes(xml_doc)
xml_doc = self._preprocess_for_mc_ignorable(xml_doc)
# Clean ignorable namespaces if needed
relative_path = xml_file.relative_to(base_path)
if (
relative_path.parts
and relative_path.parts[0] in self.MAIN_CONTENT_FOLDERS
):
xml_doc = self._clean_ignorable_namespaces(xml_doc)
# Validate
if schema.validate(xml_doc):
return True, set()
else:
errors = set()
for error in schema.error_log:
# Store normalized error message (without line numbers for comparison)
errors.add(error.message)
return False, errors
except Exception as e:
return False, {str(e)}
def _get_original_file_errors(self, xml_file):
"""Get XSD validation errors from a single file in the original document.
Args:
xml_file: Path to the XML file in unpacked_dir to check
Returns:
set: Set of error messages from the original file
"""
import tempfile
import zipfile
# Resolve both paths to handle symlinks (e.g., /var vs /private/var on macOS)
xml_file = Path(xml_file).resolve()
unpacked_dir = self.unpacked_dir.resolve()
relative_path = xml_file.relative_to(unpacked_dir)
with tempfile.TemporaryDirectory() as temp_dir:
temp_path = Path(temp_dir)
# Extract original file
with zipfile.ZipFile(self.original_file, "r") as zip_ref:
zip_ref.extractall(temp_path)
# Find corresponding file in original
original_xml_file = temp_path / relative_path
if not original_xml_file.exists():
# File didn't exist in original, so no original errors
return set()
# Validate the specific file in original
is_valid, errors = self._validate_single_file_xsd(
original_xml_file, temp_path
)
return errors if errors else set()
def _remove_template_tags_from_text_nodes(self, xml_doc):
"""Remove template tags from XML text nodes and collect warnings.
Template tags follow the pattern {{ ... }} and are used as placeholders
for content replacement. They should be removed from text content before
XSD validation while preserving XML structure.
Returns:
tuple: (cleaned_xml_doc, warnings_list)
"""
warnings = []
template_pattern = re.compile(r"\{\{[^}]*\}\}")
# Create a copy of the document to avoid modifying the original
xml_string = lxml.etree.tostring(xml_doc, encoding="unicode")
xml_copy = lxml.etree.fromstring(xml_string)
def process_text_content(text, content_type):
if not text:
return text
matches = list(template_pattern.finditer(text))
if matches:
for match in matches:
warnings.append(
f"Found template tag in {content_type}: {match.group()}"
)
return template_pattern.sub("", text)
return text
# Process all text nodes in the document
for elem in xml_copy.iter():
# Skip processing if this is a w:t element
if not hasattr(elem, "tag") or callable(elem.tag):
continue
tag_str = str(elem.tag)
if tag_str.endswith("}t") or tag_str == "t":
continue
elem.text = process_text_content(elem.text, "text content")
elem.tail = process_text_content(elem.tail, "tail content")
return lxml.etree.ElementTree(xml_copy), warnings
if __name__ == "__main__":
raise RuntimeError("This module should not be run directly.")

274
skills/docx/ooxml/scripts/validation/docx.py Normal file
View File

@@ -0,0 +1,274 @@
"""
Validator for Word document XML files against XSD schemas.
"""
import re
import tempfile
import zipfile
import lxml.etree
from .base import BaseSchemaValidator
class DOCXSchemaValidator(BaseSchemaValidator):
"""Validator for Word document XML files against XSD schemas."""
# Word-specific namespace
WORD_2006_NAMESPACE = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
# Word-specific element to relationship type mappings
# Start with empty mapping - add specific cases as we discover them
ELEMENT_RELATIONSHIP_TYPES = {}
def validate(self):
"""Run all validation checks and return True if all pass."""
# Test 0: XML well-formedness
if not self.validate_xml():
return False
# Test 1: Namespace declarations
all_valid = True
if not self.validate_namespaces():
all_valid = False
# Test 2: Unique IDs
if not self.validate_unique_ids():
all_valid = False
# Test 3: Relationship and file reference validation
if not self.validate_file_references():
all_valid = False
# Test 4: Content type declarations
if not self.validate_content_types():
all_valid = False
# Test 5: XSD schema validation
if not self.validate_against_xsd():
all_valid = False
# Test 6: Whitespace preservation
if not self.validate_whitespace_preservation():
all_valid = False
# Test 7: Deletion validation
if not self.validate_deletions():
all_valid = False
# Test 8: Insertion validation
if not self.validate_insertions():
all_valid = False
# Test 9: Relationship ID reference validation
if not self.validate_all_relationship_ids():
all_valid = False
# Count and compare paragraphs
self.compare_paragraph_counts()
return all_valid
def validate_whitespace_preservation(self):
"""
Validate that w:t elements with whitespace have xml:space='preserve'.
"""
errors = []
for xml_file in self.xml_files:
# Only check document.xml files
if xml_file.name != "document.xml":
continue
try:
root = lxml.etree.parse(str(xml_file)).getroot()
# Find all w:t elements
for elem in root.iter(f"{{{self.WORD_2006_NAMESPACE}}}t"):
if elem.text:
text = elem.text
# Check if text starts or ends with whitespace
if re.match(r"^\s.*", text) or re.match(r".*\s$", text):
# Check if xml:space="preserve" attribute exists
xml_space_attr = f"{{{self.XML_NAMESPACE}}}space"
if (
xml_space_attr not in elem.attrib
or elem.attrib[xml_space_attr] != "preserve"
):
# Show a preview of the text
text_preview = (
repr(text)[:50] + "..."
if len(repr(text)) > 50
else repr(text)
)
errors.append(
f" {xml_file.relative_to(self.unpacked_dir)}: "
f"Line {elem.sourceline}: w:t element with whitespace missing xml:space='preserve': {text_preview}"
)
except (lxml.etree.XMLSyntaxError, Exception) as e:
errors.append(
f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}"
)
if errors:
print(f"FAILED - Found {len(errors)} whitespace preservation violations:")
for error in errors:
print(error)
return False
else:
if self.verbose:
print("PASSED - All whitespace is properly preserved")
return True
def validate_deletions(self):
"""
Validate that w:t elements are not within w:del elements.
For some reason, XSD validation does not catch this, so we do it manually.
"""
errors = []
for xml_file in self.xml_files:
# Only check document.xml files
if xml_file.name != "document.xml":
continue
try:
root = lxml.etree.parse(str(xml_file)).getroot()
# Find all w:t elements that are descendants of w:del elements
namespaces = {"w": self.WORD_2006_NAMESPACE}
xpath_expression = ".//w:del//w:t"
problematic_t_elements = root.xpath(
xpath_expression, namespaces=namespaces
)
for t_elem in problematic_t_elements:
if t_elem.text:
# Show a preview of the text
text_preview = (
repr(t_elem.text)[:50] + "..."
if len(repr(t_elem.text)) > 50
else repr(t_elem.text)
)
errors.append(
f" {xml_file.relative_to(self.unpacked_dir)}: "
f"Line {t_elem.sourceline}: <w:t> found within <w:del>: {text_preview}"
)
except (lxml.etree.XMLSyntaxError, Exception) as e:
errors.append(
f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}"
)
if errors:
print(f"FAILED - Found {len(errors)} deletion validation violations:")
for error in errors:
print(error)
return False
else:
if self.verbose:
print("PASSED - No w:t elements found within w:del elements")
return True
def count_paragraphs_in_unpacked(self):
"""Count the number of paragraphs in the unpacked document."""
count = 0
for xml_file in self.xml_files:
# Only check document.xml files
if xml_file.name != "document.xml":
continue
try:
root = lxml.etree.parse(str(xml_file)).getroot()
# Count all w:p elements
paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p")
count = len(paragraphs)
except Exception as e:
print(f"Error counting paragraphs in unpacked document: {e}")
return count
def count_paragraphs_in_original(self):
"""Count the number of paragraphs in the original docx file."""
count = 0
try:
# Create temporary directory to unpack original
with tempfile.TemporaryDirectory() as temp_dir:
# Unpack original docx
with zipfile.ZipFile(self.original_file, "r") as zip_ref:
zip_ref.extractall(temp_dir)
# Parse document.xml
doc_xml_path = temp_dir + "/word/document.xml"
root = lxml.etree.parse(doc_xml_path).getroot()
# Count all w:p elements
paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p")
count = len(paragraphs)
except Exception as e:
print(f"Error counting paragraphs in original document: {e}")
return count
def validate_insertions(self):
"""
Validate that w:delText elements are not within w:ins elements.
w:delText is only allowed in w:ins if nested within a w:del.
"""
errors = []
for xml_file in self.xml_files:
if xml_file.name != "document.xml":
continue
try:
root = lxml.etree.parse(str(xml_file)).getroot()
namespaces = {"w": self.WORD_2006_NAMESPACE}
# Find w:delText in w:ins that are NOT within w:del
invalid_elements = root.xpath(
".//w:ins//w:delText[not(ancestor::w:del)]",
namespaces=namespaces
)
for elem in invalid_elements:
text_preview = (
repr(elem.text or "")[:50] + "..."
if len(repr(elem.text or "")) > 50
else repr(elem.text or "")
)
errors.append(
f" {xml_file.relative_to(self.unpacked_dir)}: "
f"Line {elem.sourceline}: <w:delText> within <w:ins>: {text_preview}"
)
except (lxml.etree.XMLSyntaxError, Exception) as e:
errors.append(
f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}"
)
if errors:
print(f"FAILED - Found {len(errors)} insertion validation violations:")
for error in errors:
print(error)
return False
else:
if self.verbose:
print("PASSED - No w:delText elements within w:ins elements")
return True
def compare_paragraph_counts(self):
"""Compare paragraph counts between original and new document."""
original_count = self.count_paragraphs_in_original()
new_count = self.count_paragraphs_in_unpacked()
diff = new_count - original_count
diff_str = f"+{diff}" if diff > 0 else str(diff)
print(f"\nParagraphs: {original_count} → {new_count} ({diff_str})")
if __name__ == "__main__":
raise RuntimeError("This module should not be run directly.")

315
skills/docx/ooxml/scripts/validation/pptx.py Normal file
View File

@@ -0,0 +1,315 @@
"""
Validator for PowerPoint presentation XML files against XSD schemas.
"""
import re
from .base import BaseSchemaValidator
class PPTXSchemaValidator(BaseSchemaValidator):
"""Validator for PowerPoint presentation XML files against XSD schemas."""
# PowerPoint presentation namespace
PRESENTATIONML_NAMESPACE = (
"http://schemas.openxmlformats.org/presentationml/2006/main"
)
# PowerPoint-specific element to relationship type mappings
ELEMENT_RELATIONSHIP_TYPES = {
"sldid": "slide",
"sldmasterid": "slidemaster",
"notesmasterid": "notesmaster",
"sldlayoutid": "slidelayout",
"themeid": "theme",
"tablestyleid": "tablestyles",
}
def validate(self):
"""Run all validation checks and return True if all pass."""
# Test 0: XML well-formedness
if not self.validate_xml():
return False
# Test 1: Namespace declarations
all_valid = True
if not self.validate_namespaces():
all_valid = False
# Test 2: Unique IDs
if not self.validate_unique_ids():
all_valid = False
# Test 3: UUID ID validation
if not self.validate_uuid_ids():
all_valid = False
# Test 4: Relationship and file reference validation
if not self.validate_file_references():
all_valid = False
# Test 5: Slide layout ID validation
if not self.validate_slide_layout_ids():
all_valid = False
# Test 6: Content type declarations
if not self.validate_content_types():
all_valid = False
# Test 7: XSD schema validation
if not self.validate_against_xsd():
all_valid = False
# Test 8: Notes slide reference validation
if not self.validate_notes_slide_references():
all_valid = False
# Test 9: Relationship ID reference validation
if not self.validate_all_relationship_ids():
all_valid = False
# Test 10: Duplicate slide layout references validation
if not self.validate_no_duplicate_slide_layouts():
all_valid = False
return all_valid
def validate_uuid_ids(self):
"""Validate that ID attributes that look like UUIDs contain only hex values."""
import lxml.etree
errors = []
# UUID pattern: 8-4-4-4-12 hex digits with optional braces/hyphens
uuid_pattern = re.compile(
r"^[\{\(]?[0-9A-Fa-f]{8}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{12}[\}\)]?$"
)
for xml_file in self.xml_files:
try:
root = lxml.etree.parse(str(xml_file)).getroot()
# Check all elements for ID attributes
for elem in root.iter():
for attr, value in elem.attrib.items():
# Check if this is an ID attribute
attr_name = attr.split("}")[-1].lower()
if attr_name == "id" or attr_name.endswith("id"):
# Check if value looks like a UUID (has the right length and pattern structure)
if self._looks_like_uuid(value):
# Validate that it contains only hex characters in the right positions
if not uuid_pattern.match(value):
errors.append(
f" {xml_file.relative_to(self.unpacked_dir)}: "
f"Line {elem.sourceline}: ID '{value}' appears to be a UUID but contains invalid hex characters"
)
except (lxml.etree.XMLSyntaxError, Exception) as e:
errors.append(
f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}"
)
if errors:
print(f"FAILED - Found {len(errors)} UUID ID validation errors:")
for error in errors:
print(error)
return False
else:
if self.verbose:
print("PASSED - All UUID-like IDs contain valid hex values")
return True
def _looks_like_uuid(self, value):
"""Check if a value has the general structure of a UUID."""
# Remove common UUID delimiters
clean_value = value.strip("{}()").replace("-", "")
# Check if it's 32 hex-like characters (could include invalid hex chars)
return len(clean_value) == 32 and all(c.isalnum() for c in clean_value)
def validate_slide_layout_ids(self):
"""Validate that sldLayoutId elements in slide masters reference valid slide layouts."""
import lxml.etree
errors = []
# Find all slide master files
slide_masters = list(self.unpacked_dir.glob("ppt/slideMasters/*.xml"))
if not slide_masters:
if self.verbose:
print("PASSED - No slide masters found")
return True
for slide_master in slide_masters:
try:
# Parse the slide master file
root = lxml.etree.parse(str(slide_master)).getroot()
# Find the corresponding _rels file for this slide master
rels_file = slide_master.parent / "_rels" / f"{slide_master.name}.rels"
if not rels_file.exists():
errors.append(
f" {slide_master.relative_to(self.unpacked_dir)}: "
f"Missing relationships file: {rels_file.relative_to(self.unpacked_dir)}"
)
continue
# Parse the relationships file
rels_root = lxml.etree.parse(str(rels_file)).getroot()
# Build a set of valid relationship IDs that point to slide layouts
valid_layout_rids = set()
for rel in rels_root.findall(
f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship"
):
rel_type = rel.get("Type", "")
if "slideLayout" in rel_type:
valid_layout_rids.add(rel.get("Id"))
# Find all sldLayoutId elements in the slide master
for sld_layout_id in root.findall(
f".//{{{self.PRESENTATIONML_NAMESPACE}}}sldLayoutId"
):
r_id = sld_layout_id.get(
f"{{{self.OFFICE_RELATIONSHIPS_NAMESPACE}}}id"
)
layout_id = sld_layout_id.get("id")
if r_id and r_id not in valid_layout_rids:
errors.append(
f" {slide_master.relative_to(self.unpacked_dir)}: "
f"Line {sld_layout_id.sourceline}: sldLayoutId with id='{layout_id}' "
f"references r:id='{r_id}' which is not found in slide layout relationships"
)
except (lxml.etree.XMLSyntaxError, Exception) as e:
errors.append(
f" {slide_master.relative_to(self.unpacked_dir)}: Error: {e}"
)
if errors:
print(f"FAILED - Found {len(errors)} slide layout ID validation errors:")
for error in errors:
print(error)
print(
"Remove invalid references or add missing slide layouts to the relationships file."
)
return False
else:
if self.verbose:
print("PASSED - All slide layout IDs reference valid slide layouts")
return True
def validate_no_duplicate_slide_layouts(self):
"""Validate that each slide has exactly one slideLayout reference."""
import lxml.etree
errors = []
slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels"))
for rels_file in slide_rels_files:
try:
root = lxml.etree.parse(str(rels_file)).getroot()
# Find all slideLayout relationships
layout_rels = [
rel
for rel in root.findall(
f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship"
)
if "slideLayout" in rel.get("Type", "")
]
if len(layout_rels) > 1:
errors.append(
f" {rels_file.relative_to(self.unpacked_dir)}: has {len(layout_rels)} slideLayout references"
)
except Exception as e:
errors.append(
f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}"
)
if errors:
print("FAILED - Found slides with duplicate slideLayout references:")
for error in errors:
print(error)
return False
else:
if self.verbose:
print("PASSED - All slides have exactly one slideLayout reference")
return True
def validate_notes_slide_references(self):
"""Validate that each notesSlide file is referenced by only one slide."""
import lxml.etree
errors = []
notes_slide_references = {} # Track which slides reference each notesSlide
# Find all slide relationship files
slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels"))
if not slide_rels_files:
if self.verbose:
print("PASSED - No slide relationship files found")
return True
for rels_file in slide_rels_files:
try:
# Parse the relationships file
root = lxml.etree.parse(str(rels_file)).getroot()
# Find all notesSlide relationships
for rel in root.findall(
f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship"
):
rel_type = rel.get("Type", "")
if "notesSlide" in rel_type:
target = rel.get("Target", "")
if target:
# Normalize the target path to handle relative paths
normalized_target = target.replace("../", "")
# Track which slide references this notesSlide
slide_name = rels_file.stem.replace(
".xml", ""
) # e.g., "slide1"
if normalized_target not in notes_slide_references:
notes_slide_references[normalized_target] = []
notes_slide_references[normalized_target].append(
(slide_name, rels_file)
)
except (lxml.etree.XMLSyntaxError, Exception) as e:
errors.append(
f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}"
)
# Check for duplicate references
for target, references in notes_slide_references.items():
if len(references) > 1:
slide_names = [ref[0] for ref in references]
errors.append(
f" Notes slide '{target}' is referenced by multiple slides: {', '.join(slide_names)}"
)
for slide_name, rels_file in references:
errors.append(f" - {rels_file.relative_to(self.unpacked_dir)}")
if errors:
print(
f"FAILED - Found {len([e for e in errors if not e.startswith(' ')])} notes slide reference validation errors:"
)
for error in errors:
print(error)
print("Each slide may optionally have its own slide file.")
return False
else:
if self.verbose:
print("PASSED - All notes slide references are unique")
return True
if __name__ == "__main__":
raise RuntimeError("This module should not be run directly.")

279
skills/docx/ooxml/scripts/validation/redlining.py Normal file
View File

@@ -0,0 +1,279 @@
"""
Validator for tracked changes in Word documents.
"""
import subprocess
import tempfile
import zipfile
from pathlib import Path
class RedliningValidator:
"""Validator for tracked changes in Word documents."""
def __init__(self, unpacked_dir, original_docx, verbose=False):
self.unpacked_dir = Path(unpacked_dir)
self.original_docx = Path(original_docx)
self.verbose = verbose
self.namespaces = {
"w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
}
def validate(self):
"""Main validation method that returns True if valid, False otherwise."""
# Verify unpacked directory exists and has correct structure
modified_file = self.unpacked_dir / "word" / "document.xml"
if not modified_file.exists():
print(f"FAILED - Modified document.xml not found at {modified_file}")
return False
# First, check if there are any tracked changes by Claude to validate
try:
import xml.etree.ElementTree as ET
tree = ET.parse(modified_file)
root = tree.getroot()
# Check for w:del or w:ins tags authored by Claude
del_elements = root.findall(".//w:del", self.namespaces)
ins_elements = root.findall(".//w:ins", self.namespaces)
# Filter to only include changes by Claude
claude_del_elements = [
elem
for elem in del_elements
if elem.get(f"{{{self.namespaces['w']}}}author") == "Claude"
]
claude_ins_elements = [
elem
for elem in ins_elements
if elem.get(f"{{{self.namespaces['w']}}}author") == "Claude"
]
# Redlining validation is only needed if tracked changes by Claude have been used.
if not claude_del_elements and not claude_ins_elements:
if self.verbose:
print("PASSED - No tracked changes by Claude found.")
return True
except Exception:
# If we can't parse the XML, continue with full validation
pass
# Create temporary directory for unpacking original docx
with tempfile.TemporaryDirectory() as temp_dir:
temp_path = Path(temp_dir)
# Unpack original docx
try:
with zipfile.ZipFile(self.original_docx, "r") as zip_ref:
zip_ref.extractall(temp_path)
except Exception as e:
print(f"FAILED - Error unpacking original docx: {e}")
return False
original_file = temp_path / "word" / "document.xml"
if not original_file.exists():
print(
f"FAILED - Original document.xml not found in {self.original_docx}"
)
return False
# Parse both XML files using xml.etree.ElementTree for redlining validation
try:
import xml.etree.ElementTree as ET
modified_tree = ET.parse(modified_file)
modified_root = modified_tree.getroot()
original_tree = ET.parse(original_file)
original_root = original_tree.getroot()
except ET.ParseError as e:
print(f"FAILED - Error parsing XML files: {e}")
return False
# Remove Claude's tracked changes from both documents
self._remove_claude_tracked_changes(original_root)
self._remove_claude_tracked_changes(modified_root)
# Extract and compare text content
modified_text = self._extract_text_content(modified_root)
original_text = self._extract_text_content(original_root)
if modified_text != original_text:
# Show detailed character-level differences for each paragraph
error_message = self._generate_detailed_diff(
original_text, modified_text
)
print(error_message)
return False
if self.verbose:
print("PASSED - All changes by Claude are properly tracked")
return True
def _generate_detailed_diff(self, original_text, modified_text):
"""Generate detailed word-level differences using git word diff."""
error_parts = [
"FAILED - Document text doesn't match after removing Claude's tracked changes",
"",
"Likely causes:",
" 1. Modified text inside another author's <w:ins> or <w:del> tags",
" 2. Made edits without proper tracked changes",
" 3. Didn't nest <w:del> inside <w:ins> when deleting another's insertion",
"",
"For pre-redlined documents, use correct patterns:",
" - To reject another's INSERTION: Nest <w:del> inside their <w:ins>",
" - To restore another's DELETION: Add new <w:ins> AFTER their <w:del>",
"",
]
# Show git word diff
git_diff = self._get_git_word_diff(original_text, modified_text)
if git_diff:
error_parts.extend(["Differences:", "============", git_diff])
else:
error_parts.append("Unable to generate word diff (git not available)")
return "\n".join(error_parts)
def _get_git_word_diff(self, original_text, modified_text):
"""Generate word diff using git with character-level precision."""
try:
with tempfile.TemporaryDirectory() as temp_dir:
temp_path = Path(temp_dir)
# Create two files
original_file = temp_path / "original.txt"
modified_file = temp_path / "modified.txt"
original_file.write_text(original_text, encoding="utf-8")
modified_file.write_text(modified_text, encoding="utf-8")
# Try character-level diff first for precise differences
result = subprocess.run(
[
"git",
"diff",
"--word-diff=plain",
"--word-diff-regex=.", # Character-by-character diff
"-U0", # Zero lines of context - show only changed lines
"--no-index",
str(original_file),
str(modified_file),
],
capture_output=True,
text=True,
)
if result.stdout.strip():
# Clean up the output - remove git diff header lines
lines = result.stdout.split("\n")
# Skip the header lines (diff --git, index, +++, ---, @@)
content_lines = []
in_content = False
for line in lines:
if line.startswith("@@"):
in_content = True
continue
if in_content and line.strip():
content_lines.append(line)
if content_lines:
return "\n".join(content_lines)
# Fallback to word-level diff if character-level is too verbose
result = subprocess.run(
[
"git",
"diff",
"--word-diff=plain",
"-U0", # Zero lines of context
"--no-index",
str(original_file),
str(modified_file),
],
capture_output=True,
text=True,
)
if result.stdout.strip():
lines = result.stdout.split("\n")
content_lines = []
in_content = False
for line in lines:
if line.startswith("@@"):
in_content = True
continue
if in_content and line.strip():
content_lines.append(line)
return "\n".join(content_lines)
except (subprocess.CalledProcessError, FileNotFoundError, Exception):
# Git not available or other error, return None to use fallback
pass
return None
def _remove_claude_tracked_changes(self, root):
"""Remove tracked changes authored by Claude from the XML root."""
ins_tag = f"{{{self.namespaces['w']}}}ins"
del_tag = f"{{{self.namespaces['w']}}}del"
author_attr = f"{{{self.namespaces['w']}}}author"
# Remove w:ins elements
for parent in root.iter():
to_remove = []
for child in parent:
if child.tag == ins_tag and child.get(author_attr) == "Claude":
to_remove.append(child)
for elem in to_remove:
parent.remove(elem)
# Unwrap content in w:del elements where author is "Claude"
deltext_tag = f"{{{self.namespaces['w']}}}delText"
t_tag = f"{{{self.namespaces['w']}}}t"
for parent in root.iter():
to_process = []
for child in parent:
if child.tag == del_tag and child.get(author_attr) == "Claude":
to_process.append((child, list(parent).index(child)))
# Process in reverse order to maintain indices
for del_elem, del_index in reversed(to_process):
# Convert w:delText to w:t before moving
for elem in del_elem.iter():
if elem.tag == deltext_tag:
elem.tag = t_tag
# Move all children of w:del to its parent before removing w:del
for child in reversed(list(del_elem)):
parent.insert(del_index, child)
parent.remove(del_elem)
def _extract_text_content(self, root):
"""Extract text content from Word XML, preserving paragraph structure.
Empty paragraphs are skipped to avoid false positives when tracked
insertions add only structural elements without text content.
"""
p_tag = f"{{{self.namespaces['w']}}}p"
t_tag = f"{{{self.namespaces['w']}}}t"
paragraphs = []
for p_elem in root.findall(f".//{p_tag}"):
# Get all text elements within this paragraph
text_parts = []
for t_elem in p_elem.findall(f".//{t_tag}"):
if t_elem.text:
text_parts.append(t_elem.text)
paragraph_text = "".join(text_parts)
# Skip empty paragraphs - they don't affect content validation
if paragraph_text:
paragraphs.append(paragraph_text)
return "\n".join(paragraphs)
if __name__ == "__main__":
raise RuntimeError("This module should not be run directly.")

1
skills/docx/scripts/__init__.py Normal file
View File

@@ -0,0 +1 @@
# Make scripts directory a package for relative imports in tests

1276
skills/docx/scripts/document.py Normal file
View File

File diff suppressed because it is too large Load Diff

3
skills/docx/scripts/templates/comments.xml Normal file
View File

@@ -0,0 +1,3 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<w:comments xmlns:wpc="http://schemas.microsoft.com/office/word/2010/wordprocessingCanvas" xmlns:cx="http://schemas.microsoft.com/office/drawing/2014/chartex" xmlns:cx1="http://schemas.microsoft.com/office/drawing/2015/9/8/chartex" xmlns:cx2="http://schemas.microsoft.com/office/drawing/2015/10/21/chartex" xmlns:cx3="http://schemas.microsoft.com/office/drawing/2016/5/9/chartex" xmlns:cx4="http://schemas.microsoft.com/office/drawing/2016/5/10/chartex" xmlns:cx5="http://schemas.microsoft.com/office/drawing/2016/5/11/chartex" xmlns:cx6="http://schemas.microsoft.com/office/drawing/2016/5/12/chartex" xmlns:cx7="http://schemas.microsoft.com/office/drawing/2016/5/13/chartex" xmlns:cx8="http://schemas.microsoft.com/office/drawing/2016/5/14/chartex" xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006" xmlns:aink="http://schemas.microsoft.com/office/drawing/2016/ink" xmlns:am3d="http://schemas.microsoft.com/office/drawing/2017/model3d" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:oel="http://schemas.microsoft.com/office/2019/extlst" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math" xmlns:v="urn:schemas-microsoft-com:vml" xmlns:wp14="http://schemas.microsoft.com/office/word/2010/wordprocessingDrawing" xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing" xmlns:w10="urn:schemas-microsoft-com:office:word" xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:w14="http://schemas.microsoft.com/office/word/2010/wordml" xmlns:w15="http://schemas.microsoft.com/office/word/2012/wordml" xmlns:w16cex="http://schemas.microsoft.com/office/word/2018/wordml/cex" xmlns:w16cid="http://schemas.microsoft.com/office/word/2016/wordml/cid" xmlns:w16="http://schemas.microsoft.com/office/word/2018/wordml" xmlns:w16du="http://schemas.microsoft.com/office/word/2023/wordml/word16du" xmlns:w16sdtdh="http://schemas.microsoft.com/office/word/2020/wordml/sdtdatahash" xmlns:w16sdtfl="http://schemas.microsoft.com/office/word/2024/wordml/sdtformatlock" xmlns:w16se="http://schemas.microsoft.com/office/word/2015/wordml/symex" xmlns:wpg="http://schemas.microsoft.com/office/word/2010/wordprocessingGroup" xmlns:wpi="http://schemas.microsoft.com/office/word/2010/wordprocessingInk" xmlns:wne="http://schemas.microsoft.com/office/word/2006/wordml" xmlns:wps="http://schemas.microsoft.com/office/word/2010/wordprocessingShape" mc:Ignorable="w14 w15 w16se w16cid w16 w16cex w16sdtdh w16sdtfl w16du wp14">
</w:comments>

3
skills/docx/scripts/templates/commentsExtended.xml Normal file
View File

@@ -0,0 +1,3 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<w15:commentsEx xmlns:wpc="http://schemas.microsoft.com/office/word/2010/wordprocessingCanvas" xmlns:cx="http://schemas.microsoft.com/office/drawing/2014/chartex" xmlns:cx1="http://schemas.microsoft.com/office/drawing/2015/9/8/chartex" xmlns:cx2="http://schemas.microsoft.com/office/drawing/2015/10/21/chartex" xmlns:cx3="http://schemas.microsoft.com/office/drawing/2016/5/9/chartex" xmlns:cx4="http://schemas.microsoft.com/office/drawing/2016/5/10/chartex" xmlns:cx5="http://schemas.microsoft.com/office/drawing/2016/5/11/chartex" xmlns:cx6="http://schemas.microsoft.com/office/drawing/2016/5/12/chartex" xmlns:cx7="http://schemas.microsoft.com/office/drawing/2016/5/13/chartex" xmlns:cx8="http://schemas.microsoft.com/office/drawing/2016/5/14/chartex" xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006" xmlns:aink="http://schemas.microsoft.com/office/drawing/2016/ink" xmlns:am3d="http://schemas.microsoft.com/office/drawing/2017/model3d" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:oel="http://schemas.microsoft.com/office/2019/extlst" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math" xmlns:v="urn:schemas-microsoft-com:vml" xmlns:wp14="http://schemas.microsoft.com/office/word/2010/wordprocessingDrawing" xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing" xmlns:w10="urn:schemas-microsoft-com:office:word" xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:w14="http://schemas.microsoft.com/office/word/2010/wordml" xmlns:w15="http://schemas.microsoft.com/office/word/2012/wordml" xmlns:w16cex="http://schemas.microsoft.com/office/word/2018/wordml/cex" xmlns:w16cid="http://schemas.microsoft.com/office/word/2016/wordml/cid" xmlns:w16="http://schemas.microsoft.com/office/word/2018/wordml" xmlns:w16du="http://schemas.microsoft.com/office/word/2023/wordml/word16du" xmlns:w16sdtdh="http://schemas.microsoft.com/office/word/2020/wordml/sdtdatahash" xmlns:w16sdtfl="http://schemas.microsoft.com/office/word/2024/wordml/sdtformatlock" xmlns:w16se="http://schemas.microsoft.com/office/word/2015/wordml/symex" xmlns:wpg="http://schemas.microsoft.com/office/word/2010/wordprocessingGroup" xmlns:wpi="http://schemas.microsoft.com/office/word/2010/wordprocessingInk" xmlns:wne="http://schemas.microsoft.com/office/word/2006/wordml" xmlns:wps="http://schemas.microsoft.com/office/word/2010/wordprocessingShape" mc:Ignorable="w14 w15 w16se w16cid w16 w16cex w16sdtdh w16sdtfl w16du wp14">
</w15:commentsEx>

3
skills/docx/scripts/templates/commentsExtensible.xml Normal file
View File

@@ -0,0 +1,3 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<w16cex:commentsExtensible xmlns:wpc="http://schemas.microsoft.com/office/word/2010/wordprocessingCanvas" xmlns:cx="http://schemas.microsoft.com/office/drawing/2014/chartex" xmlns:cx1="http://schemas.microsoft.com/office/drawing/2015/9/8/chartex" xmlns:cx2="http://schemas.microsoft.com/office/drawing/2015/10/21/chartex" xmlns:cx3="http://schemas.microsoft.com/office/drawing/2016/5/9/chartex" xmlns:cx4="http://schemas.microsoft.com/office/drawing/2016/5/10/chartex" xmlns:cx5="http://schemas.microsoft.com/office/drawing/2016/5/11/chartex" xmlns:cx6="http://schemas.microsoft.com/office/drawing/2016/5/12/chartex" xmlns:cx7="http://schemas.microsoft.com/office/drawing/2016/5/13/chartex" xmlns:cx8="http://schemas.microsoft.com/office/drawing/2016/5/14/chartex" xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006" xmlns:aink="http://schemas.microsoft.com/office/drawing/2016/ink" xmlns:am3d="http://schemas.microsoft.com/office/drawing/2017/model3d" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:oel="http://schemas.microsoft.com/office/2019/extlst" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math" xmlns:v="urn:schemas-microsoft-com:vml" xmlns:wp14="http://schemas.microsoft.com/office/word/2010/wordprocessingDrawing" xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing" xmlns:w10="urn:schemas-microsoft-com:office:word" xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:w14="http://schemas.microsoft.com/office/word/2010/wordml" xmlns:w15="http://schemas.microsoft.com/office/word/2012/wordml" xmlns:w16cex="http://schemas.microsoft.com/office/word/2018/wordml/cex" xmlns:w16cid="http://schemas.microsoft.com/office/word/2016/wordml/cid" xmlns:w16="http://schemas.microsoft.com/office/word/2018/wordml" xmlns:w16du="http://schemas.microsoft.com/office/word/2023/wordml/word16du" xmlns:w16sdtdh="http://schemas.microsoft.com/office/word/2020/wordml/sdtdatahash" xmlns:w16sdtfl="http://schemas.microsoft.com/office/word/2024/wordml/sdtformatlock" xmlns:w16se="http://schemas.microsoft.com/office/word/2015/wordml/symex" xmlns:wpg="http://schemas.microsoft.com/office/word/2010/wordprocessingGroup" xmlns:wpi="http://schemas.microsoft.com/office/word/2010/wordprocessingInk" xmlns:wne="http://schemas.microsoft.com/office/word/2006/wordml" xmlns:wps="http://schemas.microsoft.com/office/word/2010/wordprocessingShape" xmlns:cr="http://schemas.microsoft.com/office/comments/2020/reactions" mc:Ignorable="w14 w15 w16se w16cid w16 w16cex w16sdtdh w16sdtfl cr w16du wp14">
</w16cex:commentsExtensible>

3
skills/docx/scripts/templates/commentsIds.xml Normal file
View File

@@ -0,0 +1,3 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<w16cid:commentsIds xmlns:wpc="http://schemas.microsoft.com/office/word/2010/wordprocessingCanvas" xmlns:cx="http://schemas.microsoft.com/office/drawing/2014/chartex" xmlns:cx1="http://schemas.microsoft.com/office/drawing/2015/9/8/chartex" xmlns:cx2="http://schemas.microsoft.com/office/drawing/2015/10/21/chartex" xmlns:cx3="http://schemas.microsoft.com/office/drawing/2016/5/9/chartex" xmlns:cx4="http://schemas.microsoft.com/office/drawing/2016/5/10/chartex" xmlns:cx5="http://schemas.microsoft.com/office/drawing/2016/5/11/chartex" xmlns:cx6="http://schemas.microsoft.com/office/drawing/2016/5/12/chartex" xmlns:cx7="http://schemas.microsoft.com/office/drawing/2016/5/13/chartex" xmlns:cx8="http://schemas.microsoft.com/office/drawing/2016/5/14/chartex" xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006" xmlns:aink="http://schemas.microsoft.com/office/drawing/2016/ink" xmlns:am3d="http://schemas.microsoft.com/office/drawing/2017/model3d" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:oel="http://schemas.microsoft.com/office/2019/extlst" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math" xmlns:v="urn:schemas-microsoft-com:vml" xmlns:wp14="http://schemas.microsoft.com/office/word/2010/wordprocessingDrawing" xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing" xmlns:w10="urn:schemas-microsoft-com:office:word" xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:w14="http://schemas.microsoft.com/office/word/2010/wordml" xmlns:w15="http://schemas.microsoft.com/office/word/2012/wordml" xmlns:w16cex="http://schemas.microsoft.com/office/word/2018/wordml/cex" xmlns:w16cid="http://schemas.microsoft.com/office/word/2016/wordml/cid" xmlns:w16="http://schemas.microsoft.com/office/word/2018/wordml" xmlns:w16du="http://schemas.microsoft.com/office/word/2023/wordml/word16du" xmlns:w16sdtdh="http://schemas.microsoft.com/office/word/2020/wordml/sdtdatahash" xmlns:w16sdtfl="http://schemas.microsoft.com/office/word/2024/wordml/sdtformatlock" xmlns:w16se="http://schemas.microsoft.com/office/word/2015/wordml/symex" xmlns:wpg="http://schemas.microsoft.com/office/word/2010/wordprocessingGroup" xmlns:wpi="http://schemas.microsoft.com/office/word/2010/wordprocessingInk" xmlns:wne="http://schemas.microsoft.com/office/word/2006/wordml" xmlns:wps="http://schemas.microsoft.com/office/word/2010/wordprocessingShape" mc:Ignorable="w14 w15 w16se w16cid w16 w16cex w16sdtdh w16sdtfl w16du wp14">
</w16cid:commentsIds>

3
skills/docx/scripts/templates/people.xml Normal file
View File

@@ -0,0 +1,3 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<w15:people xmlns:w15="http://schemas.microsoft.com/office/word/2012/wordml">
</w15:people>

374
skills/docx/scripts/utilities.py Normal file
View File

@@ -0,0 +1,374 @@
#!/usr/bin/env python3
"""
Utilities for editing OOXML documents.
This module provides XMLEditor, a tool for manipulating XML files with support for
line-number-based node finding and DOM manipulation. Each element is automatically
annotated with its original line and column position during parsing.
Example usage:
editor = XMLEditor("document.xml")
# Find node by line number or range
elem = editor.get_node(tag="w:r", line_number=519)
elem = editor.get_node(tag="w:p", line_number=range(100, 200))
# Find node by text content
elem = editor.get_node(tag="w:p", contains="specific text")
# Find node by attributes
elem = editor.get_node(tag="w:r", attrs={"w:id": "target"})
# Combine filters
elem = editor.get_node(tag="w:p", line_number=range(1, 50), contains="text")
# Replace, insert, or manipulate
new_elem = editor.replace_node(elem, "<w:r><w:t>new text</w:t></w:r>")
editor.insert_after(new_elem, "<w:r><w:t>more</w:t></w:r>")
# Save changes
editor.save()
"""
import html
from pathlib import Path
from typing import Optional, Union
import defusedxml.minidom
import defusedxml.sax
class XMLEditor:
"""
Editor for manipulating OOXML XML files with line-number-based node finding.
This class parses XML files and tracks the original line and column position
of each element. This enables finding nodes by their line number in the original
file, which is useful when working with Read tool output.
Attributes:
xml_path: Path to the XML file being edited
encoding: Detected encoding of the XML file ('ascii' or 'utf-8')
dom: Parsed DOM tree with parse_position attributes on elements
"""
def __init__(self, xml_path):
"""
Initialize with path to XML file and parse with line number tracking.
Args:
xml_path: Path to XML file to edit (str or Path)
Raises:
ValueError: If the XML file does not exist
"""
self.xml_path = Path(xml_path)
if not self.xml_path.exists():
raise ValueError(f"XML file not found: {xml_path}")
with open(self.xml_path, "rb") as f:
header = f.read(200).decode("utf-8", errors="ignore")
self.encoding = "ascii" if 'encoding="ascii"' in header else "utf-8"
parser = _create_line_tracking_parser()
self.dom = defusedxml.minidom.parse(str(self.xml_path), parser)
def get_node(
self,
tag: str,
attrs: Optional[dict[str, str]] = None,
line_number: Optional[Union[int, range]] = None,
contains: Optional[str] = None,
):
"""
Get a DOM element by tag and identifier.
Finds an element by either its line number in the original file or by
matching attribute values. Exactly one match must be found.
Args:
tag: The XML tag name (e.g., "w:del", "w:ins", "w:r")
attrs: Dictionary of attribute name-value pairs to match (e.g., {"w:id": "1"})
line_number: Line number (int) or line range (range) in original XML file (1-indexed)
contains: Text string that must appear in any text node within the element.
Supports both entity notation (&#8220;) and Unicode characters (\u201c).
Returns:
defusedxml.minidom.Element: The matching DOM element
Raises:
ValueError: If node not found or multiple matches found
Example:
elem = editor.get_node(tag="w:r", line_number=519)
elem = editor.get_node(tag="w:r", line_number=range(100, 200))
elem = editor.get_node(tag="w:del", attrs={"w:id": "1"})
elem = editor.get_node(tag="w:p", attrs={"w14:paraId": "12345678"})
elem = editor.get_node(tag="w:commentRangeStart", attrs={"w:id": "0"})
elem = editor.get_node(tag="w:p", contains="specific text")
elem = editor.get_node(tag="w:t", contains="&#8220;Agreement") # Entity notation
elem = editor.get_node(tag="w:t", contains="\u201cAgreement") # Unicode character
"""
matches = []
for elem in self.dom.getElementsByTagName(tag):
# Check line_number filter
if line_number is not None:
parse_pos = getattr(elem, "parse_position", (None,))
elem_line = parse_pos[0]
# Handle both single line number and range
if isinstance(line_number, range):
if elem_line not in line_number:
continue
else:
if elem_line != line_number:
continue
# Check attrs filter
if attrs is not None:
if not all(
elem.getAttribute(attr_name) == attr_value
for attr_name, attr_value in attrs.items()
):
continue
# Check contains filter
if contains is not None:
elem_text = self._get_element_text(elem)
# Normalize the search string: convert HTML entities to Unicode characters
# This allows searching for both "&#8220;Rowan" and ""Rowan"
normalized_contains = html.unescape(contains)
if normalized_contains not in elem_text:
continue
# If all applicable filters passed, this is a match
matches.append(elem)
if not matches:
# Build descriptive error message
filters = []
if line_number is not None:
line_str = (
f"lines {line_number.start}-{line_number.stop - 1}"
if isinstance(line_number, range)
else f"line {line_number}"
)
filters.append(f"at {line_str}")
if attrs is not None:
filters.append(f"with attributes {attrs}")
if contains is not None:
filters.append(f"containing '{contains}'")
filter_desc = " ".join(filters) if filters else ""
base_msg = f"Node not found: <{tag}> {filter_desc}".strip()
# Add helpful hint based on filters used
if contains:
hint = "Text may be split across elements or use different wording."
elif line_number:
hint = "Line numbers may have changed if document was modified."
elif attrs:
hint = "Verify attribute values are correct."
else:
hint = "Try adding filters (attrs, line_number, or contains)."
raise ValueError(f"{base_msg}. {hint}")
if len(matches) > 1:
raise ValueError(
f"Multiple nodes found: <{tag}>. "
f"Add more filters (attrs, line_number, or contains) to narrow the search."
)
return matches[0]
def _get_element_text(self, elem):
"""
Recursively extract all text content from an element.
Skips text nodes that contain only whitespace (spaces, tabs, newlines),
which typically represent XML formatting rather than document content.
Args:
elem: defusedxml.minidom.Element to extract text from
Returns:
str: Concatenated text from all non-whitespace text nodes within the element
"""
text_parts = []
for node in elem.childNodes:
if node.nodeType == node.TEXT_NODE:
# Skip whitespace-only text nodes (XML formatting)
if node.data.strip():
text_parts.append(node.data)
elif node.nodeType == node.ELEMENT_NODE:
text_parts.append(self._get_element_text(node))
return "".join(text_parts)
def replace_node(self, elem, new_content):
"""
Replace a DOM element with new XML content.
Args:
elem: defusedxml.minidom.Element to replace
new_content: String containing XML to replace the node with
Returns:
List[defusedxml.minidom.Node]: All inserted nodes
Example:
new_nodes = editor.replace_node(old_elem, "<w:r><w:t>text</w:t></w:r>")
"""
parent = elem.parentNode
nodes = self._parse_fragment(new_content)
for node in nodes:
parent.insertBefore(node, elem)
parent.removeChild(elem)
return nodes
def insert_after(self, elem, xml_content):
"""
Insert XML content after a DOM element.
Args:
elem: defusedxml.minidom.Element to insert after
xml_content: String containing XML to insert
Returns:
List[defusedxml.minidom.Node]: All inserted nodes
Example:
new_nodes = editor.insert_after(elem, "<w:r><w:t>text</w:t></w:r>")
"""
parent = elem.parentNode
next_sibling = elem.nextSibling
nodes = self._parse_fragment(xml_content)
for node in nodes:
if next_sibling:
parent.insertBefore(node, next_sibling)
else:
parent.appendChild(node)
return nodes
def insert_before(self, elem, xml_content):
"""
Insert XML content before a DOM element.
Args:
elem: defusedxml.minidom.Element to insert before
xml_content: String containing XML to insert
Returns:
List[defusedxml.minidom.Node]: All inserted nodes
Example:
new_nodes = editor.insert_before(elem, "<w:r><w:t>text</w:t></w:r>")
"""
parent = elem.parentNode
nodes = self._parse_fragment(xml_content)
for node in nodes:
parent.insertBefore(node, elem)
return nodes
def append_to(self, elem, xml_content):
"""
Append XML content as a child of a DOM element.
Args:
elem: defusedxml.minidom.Element to append to
xml_content: String containing XML to append
Returns:
List[defusedxml.minidom.Node]: All inserted nodes
Example:
new_nodes = editor.append_to(elem, "<w:r><w:t>text</w:t></w:r>")
"""
nodes = self._parse_fragment(xml_content)
for node in nodes:
elem.appendChild(node)
return nodes
def get_next_rid(self):
"""Get the next available rId for relationships files."""
max_id = 0
for rel_elem in self.dom.getElementsByTagName("Relationship"):
rel_id = rel_elem.getAttribute("Id")
if rel_id.startswith("rId"):
try:
max_id = max(max_id, int(rel_id[3:]))
except ValueError:
pass
return f"rId{max_id + 1}"
def save(self):
"""
Save the edited XML back to the file.
Serializes the DOM tree and writes it back to the original file path,
preserving the original encoding (ascii or utf-8).
"""
content = self.dom.toxml(encoding=self.encoding)
self.xml_path.write_bytes(content)
def _parse_fragment(self, xml_content):
"""
Parse XML fragment and return list of imported nodes.
Args:
xml_content: String containing XML fragment
Returns:
List of defusedxml.minidom.Node objects imported into this document
Raises:
AssertionError: If fragment contains no element nodes
"""
# Extract namespace declarations from the root document element
root_elem = self.dom.documentElement
namespaces = []
if root_elem and root_elem.attributes:
for i in range(root_elem.attributes.length):
attr = root_elem.attributes.item(i)
if attr.name.startswith("xmlns"): # type: ignore
namespaces.append(f'{attr.name}="{attr.value}"') # type: ignore
ns_decl = " ".join(namespaces)
wrapper = f"<root {ns_decl}>{xml_content}</root>"
fragment_doc = defusedxml.minidom.parseString(wrapper)
nodes = [
self.dom.importNode(child, deep=True)
for child in fragment_doc.documentElement.childNodes # type: ignore
]
elements = [n for n in nodes if n.nodeType == n.ELEMENT_NODE]
assert elements, "Fragment must contain at least one element"
return nodes
def _create_line_tracking_parser():
"""
Create a SAX parser that tracks line and column numbers for each element.
Monkey patches the SAX content handler to store the current line and column
position from the underlying expat parser onto each element as a parse_position
attribute (line, column) tuple.
Returns:
defusedxml.sax.xmlreader.XMLReader: Configured SAX parser
"""
def set_content_handler(dom_handler):
def startElementNS(name, tagName, attrs):
orig_start_cb(name, tagName, attrs)
cur_elem = dom_handler.elementStack[-1]
cur_elem.parse_position = (
parser._parser.CurrentLineNumber, # type: ignore
parser._parser.CurrentColumnNumber, # type: ignore
)
orig_start_cb = dom_handler.startElementNS
dom_handler.startElementNS = startElementNS
orig_set_content_handler(dom_handler)
parser = defusedxml.sax.make_parser()
orig_set_content_handler = parser.setContentHandler
parser.setContentHandler = set_content_handler # type: ignore
return parser

610
skills/pdf-processing-pro/FORMS.md Normal file
View File

@@ -0,0 +1,610 @@
# PDF Form Processing Guide
Complete guide for processing PDF forms in production environments.
## Table of contents
- Form analysis and field detection
- Form filling workflows
- Validation strategies
- Field types and handling
- Multi-page forms
- Flattening and finalization
- Error handling patterns
- Production examples
## Form analysis
### Analyze form structure
Use `analyze_form.py` to extract complete form information:
```bash
python scripts/analyze_form.py application.pdf --output schema.json
```
Output format:
```json
{
"full_name": {
"type": "text",
"required": true,
"max_length": 100,
"x": 120.5,
"y": 450.2,
"width": 300,
"height": 20
},
"date_of_birth": {
"type": "text",
"required": true,
"format": "MM/DD/YYYY",
"x": 120.5,
"y": 400.8,
"width": 150,
"height": 20
},
"email_newsletter": {
"type": "checkbox",
"required": false,
"x": 120.5,
"y": 350.4,
"width": 15,
"height": 15
},
"preferred_contact": {
"type": "radio",
"required": true,
"options": ["email", "phone", "mail"],
"x": 120.5,
"y": 300.0,
"width": 200,
"height": 60
}
}
```
### Programmatic analysis
```python
from pypdf import PdfReader
reader = PdfReader("form.pdf")
fields = reader.get_fields()
for field_name, field_info in fields.items():
print(f"Field: {field_name}")
print(f" Type: {field_info.get('/FT')}")
print(f" Value: {field_info.get('/V')}")
print(f" Flags: {field_info.get('/Ff', 0)}")
print()
```
## Form filling workflows
### Basic workflow
```bash
# 1. Analyze form
python scripts/analyze_form.py template.pdf --output schema.json
# 2. Prepare data
cat > data.json << EOF
{
"full_name": "John Doe",
"date_of_birth": "01/15/1990",
"email": "john@example.com",
"email_newsletter": true,
"preferred_contact": "email"
}
EOF
# 3. Validate data
python scripts/validate_form.py data.json schema.json
# 4. Fill form
python scripts/fill_form.py template.pdf data.json filled.pdf
# 5. Flatten (optional - makes fields non-editable)
python scripts/flatten_form.py filled.pdf final.pdf
```
### Programmatic filling
```python
from pypdf import PdfReader, PdfWriter
reader = PdfReader("template.pdf")
writer = PdfWriter()
# Clone all pages
for page in reader.pages:
writer.add_page(page)
# Fill form fields
writer.update_page_form_field_values(
writer.pages[0],
{
"full_name": "John Doe",
"date_of_birth": "01/15/1990",
"email": "john@example.com",
"email_newsletter": "/Yes", # Checkbox value
"preferred_contact": "/email" # Radio value
}
)
# Save filled form
with open("filled.pdf", "wb") as output:
writer.write(output)
```
## Field types and handling
### Text fields
```python
# Simple text
field_values["customer_name"] = "Jane Smith"
# Formatted text (dates)
field_values["date"] = "12/25/2024"
# Numbers
field_values["amount"] = "1234.56"
# Multi-line text
field_values["comments"] = "Line 1\nLine 2\nLine 3"
```
### Checkboxes
Checkboxes typically use `/Yes` for checked, `/Off` for unchecked:
```python
# Check checkbox
field_values["agree_to_terms"] = "/Yes"
# Uncheck checkbox
field_values["newsletter_opt_out"] = "/Off"
```
**Note**: Some PDFs use different values. Check with `analyze_form.py`:
```json
{
"some_checkbox": {
"type": "checkbox",
"on_value": "/On", # ← Check this
"off_value": "/Off"
}
}
```
### Radio buttons
Radio buttons are mutually exclusive options:
```python
# Select one option from radio group
field_values["preferred_contact"] = "/email"
# Other options in same group
# field_values["preferred_contact"] = "/phone"
# field_values["preferred_contact"] = "/mail"
```
### Dropdown/List boxes
```python
# Single selection
field_values["country"] = "United States"
# List of available options in schema
"country": {
"type": "dropdown",
"options": ["United States", "Canada", "Mexico", ...]
}
```
## Validation strategies
### Schema-based validation
```python
import json
from jsonschema import validate, ValidationError
# Load schema from analyze_form.py output
with open("schema.json") as f:
schema = json.load(f)
# Load form data
with open("data.json") as f:
data = json.load(f)
# Validate all fields
errors = []
for field_name, field_schema in schema.items():
value = data.get(field_name)
# Check required fields
if field_schema.get("required") and not value:
errors.append(f"Missing required field: {field_name}")
# Check field type
if value and field_schema.get("type") == "text":
if not isinstance(value, str):
errors.append(f"Field {field_name} must be string")
# Check max length
max_length = field_schema.get("max_length")
if value and max_length and len(str(value)) > max_length:
errors.append(f"Field {field_name} exceeds max length {max_length}")
# Check format (dates, emails, etc)
format_type = field_schema.get("format")
if value and format_type:
if not validate_format(value, format_type):
errors.append(f"Field {field_name} has invalid format")
if errors:
print("Validation errors:")
for error in errors:
print(f" - {error}")
exit(1)
print("Validation passed")
```
### Format validation
```python
import re
from datetime import datetime
def validate_format(value, format_type):
"""Validate field format."""
if format_type == "email":
pattern = r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'
return re.match(pattern, value) is not None
elif format_type == "phone":
# US phone: (555) 123-4567 or 555-123-4567
pattern = r'^\(?\d{3}\)?[-.\s]?\d{3}[-.\s]?\d{4}$'
return re.match(pattern, value) is not None
elif format_type == "MM/DD/YYYY":
try:
datetime.strptime(value, "%m/%d/%Y")
return True
except ValueError:
return False
elif format_type == "SSN":
# XXX-XX-XXXX
pattern = r'^\d{3}-\d{2}-\d{4}$'
return re.match(pattern, value) is not None
elif format_type == "ZIP":
# XXXXX or XXXXX-XXXX
pattern = r'^\d{5}(-\d{4})?$'
return re.match(pattern, value) is not None
return True # Unknown format, skip validation
```
## Multi-page forms
### Handling multi-page forms
```python
from pypdf import PdfReader, PdfWriter
reader = PdfReader("multi_page_form.pdf")
writer = PdfWriter()
# Clone all pages
for page in reader.pages:
writer.add_page(page)
# Fill fields on page 1
writer.update_page_form_field_values(
writer.pages[0],
{
"name_page1": "John Doe",
"email_page1": "john@example.com"
}
)
# Fill fields on page 2
writer.update_page_form_field_values(
writer.pages[1],
{
"address_page2": "123 Main St",
"city_page2": "Springfield"
}
)
# Fill fields on page 3
writer.update_page_form_field_values(
writer.pages[2],
{
"signature_page3": "John Doe",
"date_page3": "12/25/2024"
}
)
with open("filled_multi_page.pdf", "wb") as output:
writer.write(output)
```
### Identifying page-specific fields
```python
# Analyze which fields are on which pages
for page_num, page in enumerate(reader.pages, 1):
fields = page.get("/Annots", [])
if fields:
print(f"\nPage {page_num} fields:")
for field_ref in fields:
field = field_ref.get_object()
field_name = field.get("/T", "Unknown")
print(f" - {field_name}")
```
## Flattening forms
### Why flatten
Flattening makes form fields non-editable, embedding values permanently:
- **Security**: Prevent modifications
- **Distribution**: Share read-only forms
- **Printing**: Ensure correct appearance
- **Archival**: Long-term storage
### Flatten with pypdf
```python
from pypdf import PdfReader, PdfWriter
reader = PdfReader("filled.pdf")
writer = PdfWriter()
# Add all pages
for page in reader.pages:
writer.add_page(page)
# Flatten all form fields
writer.flatten_fields()
# Save flattened PDF
with open("flattened.pdf", "wb") as output:
writer.write(output)
```
### Using included script
```bash
python scripts/flatten_form.py filled.pdf flattened.pdf
```
## Error handling patterns
### Robust form filling
```python
import logging
from pathlib import Path
from pypdf import PdfReader, PdfWriter
from pypdf.errors import PdfReadError
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
def fill_form_safe(template_path, data, output_path):
"""Fill form with comprehensive error handling."""
try:
# Validate inputs
template = Path(template_path)
if not template.exists():
raise FileNotFoundError(f"Template not found: {template_path}")
# Read template
logger.info(f"Reading template: {template_path}")
reader = PdfReader(template_path)
if not reader.pages:
raise ValueError("PDF has no pages")
# Check if form has fields
fields = reader.get_fields()
if not fields:
logger.warning("PDF has no form fields")
return False
# Create writer
writer = PdfWriter()
for page in reader.pages:
writer.add_page(page)
# Validate data against schema
missing_required = []
invalid_fields = []
for field_name, field_info in fields.items():
# Check required fields
is_required = field_info.get("/Ff", 0) & 2 == 2
if is_required and field_name not in data:
missing_required.append(field_name)
# Check invalid field names in data
if field_name in data:
value = data[field_name]
# Add type validation here if needed
if missing_required:
raise ValueError(f"Missing required fields: {missing_required}")
# Fill fields
logger.info("Filling form fields")
writer.update_page_form_field_values(
writer.pages[0],
data
)
# Write output
logger.info(f"Writing output: {output_path}")
with open(output_path, "wb") as output:
writer.write(output)
logger.info("Form filled successfully")
return True
except PdfReadError as e:
logger.error(f"PDF read error: {e}")
return False
except FileNotFoundError as e:
logger.error(f"File error: {e}")
return False
except ValueError as e:
logger.error(f"Validation error: {e}")
return False
except Exception as e:
logger.error(f"Unexpected error: {e}")
return False
# Usage
success = fill_form_safe(
"template.pdf",
{"name": "John", "email": "john@example.com"},
"filled.pdf"
)
if not success:
exit(1)
```
## Production examples
### Example 1: Batch form processing
```python
import json
import glob
from pathlib import Path
from fill_form_safe import fill_form_safe
# Process multiple submissions
submissions_dir = Path("submissions")
template = "application_template.pdf"
output_dir = Path("completed")
output_dir.mkdir(exist_ok=True)
for submission_file in submissions_dir.glob("*.json"):
print(f"Processing: {submission_file.name}")
# Load submission data
with open(submission_file) as f:
data = json.load(f)
# Fill form
applicant_id = data.get("id", "unknown")
output_file = output_dir / f"application_{applicant_id}.pdf"
success = fill_form_safe(template, data, output_file)
if success:
print(f" ✓ Completed: {output_file}")
else:
print(f" ✗ Failed: {submission_file.name}")
```
### Example 2: Form with conditional logic
```python
def prepare_form_data(raw_data):
"""Prepare form data with conditional logic."""
form_data = {}
# Basic fields
form_data["full_name"] = raw_data["name"]
form_data["email"] = raw_data["email"]
# Conditional fields
if raw_data.get("is_student"):
form_data["student_id"] = raw_data["student_id"]
form_data["school_name"] = raw_data["school"]
else:
form_data["employer"] = raw_data.get("employer", "")
# Checkbox logic
form_data["newsletter"] = "/Yes" if raw_data.get("opt_in") else "/Off"
# Calculated fields
total = sum(raw_data.get("items", []))
form_data["total_amount"] = f"${total:.2f}"
return form_data
# Usage
raw_input = {
"name": "Jane Smith",
"email": "jane@example.com",
"is_student": True,
"student_id": "12345",
"school": "State University",
"opt_in": True,
"items": [10.00, 25.50, 15.75]
}
form_data = prepare_form_data(raw_input)
fill_form_safe("template.pdf", form_data, "output.pdf")
```
## Best practices
1. **Always analyze before filling**: Use `analyze_form.py` to understand structure
2. **Validate early**: Check data before attempting to fill
3. **Use logging**: Track operations for debugging
4. **Handle errors gracefully**: Don't crash on invalid data
5. **Test with samples**: Verify with small datasets first
6. **Flatten when distributing**: Make read-only for recipients
7. **Keep templates versioned**: Track form template changes
8. **Document field mappings**: Maintain data-to-field documentation
## Troubleshooting
### Fields not filling
1. Check field names match exactly (case-sensitive)
2. Verify checkbox/radio values (`/Yes`, `/On`, etc.)
3. Ensure PDF is not encrypted or protected
4. Check if form uses XFA format (not supported by pypdf)
### Encoding issues
```python
# Handle special characters
field_values["name"] = "José García" # UTF-8 encoded
```
### Large batch processing
```python
# Process in chunks to avoid memory issues
chunk_size = 100
for i in range(0, len(submissions), chunk_size):
chunk = submissions[i:i + chunk_size]
process_batch(chunk)
```

137
skills/pdf-processing-pro/OCR.md Normal file
View File

@@ -0,0 +1,137 @@
# PDF OCR Processing Guide
Extract text from scanned PDFs and image-based documents.
## Quick start
```python
import pytesseract
from pdf2image import convert_from_path
from PIL import Image
# Convert PDF to images
images = convert_from_path("scanned.pdf")
# Extract text from each page
for i, image in enumerate(images):
text = pytesseract.image_to_string(image)
print(f"Page {i+1}:\n{text}\n")
```
## Installation
### Install Tesseract
**macOS:**
```bash
brew install tesseract
```
**Ubuntu/Debian:**
```bash
sudo apt-get install tesseract-ocr
```
**Windows:**
Download from: https://github.com/UB-Mannheim/tesseract/wiki
### Install Python packages
```bash
pip install pytesseract pdf2image pillow
```
## Language support
```python
# English (default)
text = pytesseract.image_to_string(image, lang="eng")
# Spanish
text = pytesseract.image_to_string(image, lang="spa")
# Multiple languages
text = pytesseract.image_to_string(image, lang="eng+spa+fra")
```
Install additional languages:
```bash
# macOS
brew install tesseract-lang
# Ubuntu
sudo apt-get install tesseract-ocr-spa tesseract-ocr-fra
```
## Image preprocessing
```python
from PIL import Image, ImageEnhance, ImageFilter
def preprocess_for_ocr(image):
"""Optimize image for better OCR accuracy."""
# Convert to grayscale
image = image.convert("L")
# Increase contrast
enhancer = ImageEnhance.Contrast(image)
image = enhancer.enhance(2.0)
# Denoise
image = image.filter(ImageFilter.MedianFilter())
# Sharpen
image = image.filter(ImageFilter.SHARPEN)
return image
# Usage
image = Image.open("scanned_page.png")
processed = preprocess_for_ocr(image)
text = pytesseract.image_to_string(processed)
```
## Best practices
1. **Preprocess images** for better accuracy
2. **Use appropriate language** models
3. **Batch process** large documents
4. **Cache results** to avoid re-processing
5. **Validate output** - OCR is not 100% accurate
6. **Consider confidence scores** for quality checks
## Production example
```python
import pytesseract
from pdf2image import convert_from_path
from PIL import Image
def ocr_pdf(pdf_path, output_path):
"""OCR PDF and save to text file."""
# Convert to images
images = convert_from_path(pdf_path, dpi=300)
full_text = []
for i, image in enumerate(images, 1):
print(f"Processing page {i}/{len(images)}")
# Preprocess
processed = preprocess_for_ocr(image)
# OCR
text = pytesseract.image_to_string(processed, lang="eng")
full_text.append(f"--- Page {i} ---\n{text}\n")
# Save
with open(output_path, "w", encoding="utf-8") as f:
f.write("\n".join(full_text))
print(f"Saved to {output_path}")
# Usage
ocr_pdf("scanned_document.pdf", "extracted_text.txt")
```

296
skills/pdf-processing-pro/SKILL.md Normal file
View File

@@ -0,0 +1,296 @@
---
name: PDF Processing Pro
description: Production-ready PDF processing with forms, tables, OCR, validation, and batch operations. Use when working with complex PDF workflows in production environments, processing large volumes of PDFs, or requiring robust error handling and validation.
---
# PDF Processing Pro
Production-ready PDF processing toolkit with pre-built scripts, comprehensive error handling, and support for complex workflows.
## Quick start
### Extract text from PDF
```python
import pdfplumber
with pdfplumber.open("document.pdf") as pdf:
text = pdf.pages[0].extract_text()
print(text)
```
### Analyze PDF form (using included script)
```bash
python scripts/analyze_form.py input.pdf --output fields.json
# Returns: JSON with all form fields, types, and positions
```
### Fill PDF form with validation
```bash
python scripts/fill_form.py input.pdf data.json output.pdf
# Validates all fields before filling, includes error reporting
```
### Extract tables from PDF
```bash
python scripts/extract_tables.py report.pdf --output tables.csv
# Extracts all tables with automatic column detection
```
## Features
### ✅ Production-ready scripts
All scripts include:
- **Error handling**: Graceful failures with detailed error messages
- **Validation**: Input validation and type checking
- **Logging**: Configurable logging with timestamps
- **Type hints**: Full type annotations for IDE support
- **CLI interface**: `--help` flag for all scripts
- **Exit codes**: Proper exit codes for automation
### ✅ Comprehensive workflows
- **PDF Forms**: Complete form processing pipeline
- **Table Extraction**: Advanced table detection and extraction
- **OCR Processing**: Scanned PDF text extraction
- **Batch Operations**: Process multiple PDFs efficiently
- **Validation**: Pre and post-processing validation
## Advanced topics
### PDF Form Processing
For complete form workflows including:
- Field analysis and detection
- Dynamic form filling
- Validation rules
- Multi-page forms
- Checkbox and radio button handling
See [FORMS.md](FORMS.md)
### Table Extraction
For complex table extraction:
- Multi-page tables
- Merged cells
- Nested tables
- Custom table detection
- Export to CSV/Excel
See [TABLES.md](TABLES.md)
### OCR Processing
For scanned PDFs and image-based documents:
- Tesseract integration
- Language support
- Image preprocessing
- Confidence scoring
- Batch OCR
See [OCR.md](OCR.md)
## Included scripts
### Form processing
**analyze_form.py** - Extract form field information
```bash
python scripts/analyze_form.py input.pdf [--output fields.json] [--verbose]
```
**fill_form.py** - Fill PDF forms with data
```bash
python scripts/fill_form.py input.pdf data.json output.pdf [--validate]
```
**validate_form.py** - Validate form data before filling
```bash
python scripts/validate_form.py data.json schema.json
```
### Table extraction
**extract_tables.py** - Extract tables to CSV/Excel
```bash
python scripts/extract_tables.py input.pdf [--output tables.csv] [--format csv|excel]
```
### Text extraction
**extract_text.py** - Extract text with formatting preservation
```bash
python scripts/extract_text.py input.pdf [--output text.txt] [--preserve-formatting]
```
### Utilities
**merge_pdfs.py** - Merge multiple PDFs
```bash
python scripts/merge_pdfs.py file1.pdf file2.pdf file3.pdf --output merged.pdf
```
**split_pdf.py** - Split PDF into individual pages
```bash
python scripts/split_pdf.py input.pdf --output-dir pages/
```
**validate_pdf.py** - Validate PDF integrity
```bash
python scripts/validate_pdf.py input.pdf
```
## Common workflows
### Workflow 1: Process form submissions
```bash
# 1. Analyze form structure
python scripts/analyze_form.py template.pdf --output schema.json
# 2. Validate submission data
python scripts/validate_form.py submission.json schema.json
# 3. Fill form
python scripts/fill_form.py template.pdf submission.json completed.pdf
# 4. Validate output
python scripts/validate_pdf.py completed.pdf
```
### Workflow 2: Extract data from reports
```bash
# 1. Extract tables
python scripts/extract_tables.py monthly_report.pdf --output data.csv
# 2. Extract text for analysis
python scripts/extract_text.py monthly_report.pdf --output report.txt
```
### Workflow 3: Batch processing
```python
import glob
from pathlib import Path
import subprocess
# Process all PDFs in directory
for pdf_file in glob.glob("invoices/*.pdf"):
output_file = Path("processed") / Path(pdf_file).name
result = subprocess.run([
"python", "scripts/extract_text.py",
pdf_file,
"--output", str(output_file)
], capture_output=True)
if result.returncode == 0:
print(f"✓ Processed: {pdf_file}")
else:
print(f"✗ Failed: {pdf_file} - {result.stderr}")
```
## Error handling
All scripts follow consistent error patterns:
```python
# Exit codes
# 0 - Success
# 1 - File not found
# 2 - Invalid input
# 3 - Processing error
# 4 - Validation error
# Example usage in automation
result = subprocess.run(["python", "scripts/fill_form.py", ...])
if result.returncode == 0:
print("Success")
elif result.returncode == 4:
print("Validation failed - check input data")
else:
print(f"Error occurred: {result.returncode}")
```
## Dependencies
All scripts require:
```bash
pip install pdfplumber pypdf pillow pytesseract pandas
```
Optional for OCR:
```bash
# Install tesseract-ocr system package
# macOS: brew install tesseract
# Ubuntu: apt-get install tesseract-ocr
# Windows: Download from GitHub releases
```
## Performance tips
- **Use batch processing** for multiple PDFs
- **Enable multiprocessing** with `--parallel` flag (where supported)
- **Cache extracted data** to avoid re-processing
- **Validate inputs early** to fail fast
- **Use streaming** for large PDFs (>50MB)
## Best practices
1. **Always validate inputs** before processing
2. **Use try-except** in custom scripts
3. **Log all operations** for debugging
4. **Test with sample PDFs** before production
5. **Set timeouts** for long-running operations
6. **Check exit codes** in automation
7. **Backup originals** before modification
## Troubleshooting
### Common issues
**"Module not found" errors**:
```bash
pip install -r requirements.txt
```
**Tesseract not found**:
```bash
# Install tesseract system package (see Dependencies)
```
**Memory errors with large PDFs**:
```python
# Process page by page instead of loading entire PDF
with pdfplumber.open("large.pdf") as pdf:
for page in pdf.pages:
text = page.extract_text()
# Process page immediately
```
**Permission errors**:
```bash
chmod +x scripts/*.py
```
## Getting help
All scripts support `--help`:
```bash
python scripts/analyze_form.py --help
python scripts/extract_tables.py --help
```
For detailed documentation on specific topics, see:
- [FORMS.md](FORMS.md) - Complete form processing guide
- [TABLES.md](TABLES.md) - Advanced table extraction
- [OCR.md](OCR.md) - Scanned PDF processing

626
skills/pdf-processing-pro/TABLES.md Normal file
View File

@@ -0,0 +1,626 @@
# PDF Table Extraction Guide
Advanced table extraction strategies for production environments.
## Table of contents
- Basic table extraction
- Multi-page tables
- Complex table structures
- Export formats
- Table detection algorithms
- Custom extraction rules
- Performance optimization
- Production examples
## Basic table extraction
### Using pdfplumber (recommended)
```python
import pdfplumber
with pdfplumber.open("report.pdf") as pdf:
page = pdf.pages[0]
tables = page.extract_tables()
for i, table in enumerate(tables):
print(f"\nTable {i + 1}:")
for row in table:
print(row)
```
### Using included script
```bash
python scripts/extract_tables.py report.pdf --output tables.csv
```
Output:
```csv
Name,Age,City
John Doe,30,New York
Jane Smith,25,Los Angeles
Bob Johnson,35,Chicago
```
## Table extraction strategies
### Strategy 1: Automatic detection
Let pdfplumber auto-detect tables:
```python
import pdfplumber
with pdfplumber.open("document.pdf") as pdf:
for page_num, page in enumerate(pdf.pages, 1):
tables = page.extract_tables()
if tables:
print(f"Found {len(tables)} table(s) on page {page_num}")
for table_num, table in enumerate(tables, 1):
print(f"\nTable {table_num}:")
# First row is usually headers
headers = table[0]
print(f"Columns: {headers}")
# Data rows
for row in table[1:]:
print(row)
```
### Strategy 2: Custom table settings
Fine-tune detection with custom settings:
```python
import pdfplumber
table_settings = {
"vertical_strategy": "lines", # or "text", "lines_strict"
"horizontal_strategy": "lines",
"explicit_vertical_lines": [],
"explicit_horizontal_lines": [],
"snap_tolerance": 3,
"join_tolerance": 3,
"edge_min_length": 3,
"min_words_vertical": 3,
"min_words_horizontal": 1,
"keep_blank_chars": False,
"text_tolerance": 3,
"text_x_tolerance": 3,
"text_y_tolerance": 3,
"intersection_tolerance": 3
}
with pdfplumber.open("document.pdf") as pdf:
page = pdf.pages[0]
tables = page.extract_tables(table_settings=table_settings)
```
### Strategy 3: Explicit boundaries
Define table boundaries manually:
```python
import pdfplumber
with pdfplumber.open("document.pdf") as pdf:
page = pdf.pages[0]
# Define bounding box (x0, top, x1, bottom)
bbox = (50, 100, 550, 700)
# Extract table within bounding box
cropped = page.within_bbox(bbox)
tables = cropped.extract_tables()
```
## Multi-page tables
### Detect and merge multi-page tables
```python
import pdfplumber
def extract_multipage_table(pdf_path, start_page=0, end_page=None):
"""Extract table that spans multiple pages."""
all_rows = []
headers = None
with pdfplumber.open(pdf_path) as pdf:
pages = pdf.pages[start_page:end_page]
for page_num, page in enumerate(pages):
tables = page.extract_tables()
if not tables:
continue
# Assume first table on page
table = tables[0]
if page_num == 0:
# First page: capture headers and data
headers = table[0]
all_rows.extend(table[1:])
else:
# Subsequent pages: skip headers if they repeat
if table[0] == headers:
all_rows.extend(table[1:])
else:
all_rows.extend(table)
return [headers] + all_rows if headers else all_rows
# Usage
table = extract_multipage_table("report.pdf", start_page=2, end_page=5)
print(f"Extracted {len(table) - 1} rows")
print(f"Columns: {table[0]}")
```
## Complex table structures
### Handling merged cells
```python
import pdfplumber
def handle_merged_cells(table):
"""Process table with merged cells."""
processed = []
for row in table:
new_row = []
last_value = None
for cell in row:
if cell is None or cell == "":
# Merged cell - use value from left
new_row.append(last_value)
else:
new_row.append(cell)
last_value = cell
processed.append(new_row)
return processed
# Usage
with pdfplumber.open("document.pdf") as pdf:
table = pdf.pages[0].extract_tables()[0]
clean_table = handle_merged_cells(table)
```
### Nested tables
```python
def extract_nested_tables(page, bbox):
"""Extract nested tables from a region."""
cropped = page.within_bbox(bbox)
# Try to detect sub-regions with tables
tables = cropped.extract_tables()
result = []
for table in tables:
# Process each nested table
if table:
result.append({
"type": "nested",
"data": table
})
return result
```
### Tables with varying column counts
```python
def normalize_table_columns(table):
"""Normalize table with inconsistent column counts."""
if not table:
return table
# Find max column count
max_cols = max(len(row) for row in table)
# Pad short rows
normalized = []
for row in table:
if len(row) < max_cols:
# Pad with empty strings
row = row + [""] * (max_cols - len(row))
normalized.append(row)
return normalized
```
## Export formats
### Export to CSV
```python
import csv
def export_to_csv(table, output_path):
"""Export table to CSV."""
with open(output_path, "w", newline="", encoding="utf-8") as f:
writer = csv.writer(f)
writer.writerows(table)
# Usage
table = extract_table("report.pdf")
export_to_csv(table, "output.csv")
```
### Export to Excel
```python
import pandas as pd
def export_to_excel(tables, output_path):
"""Export multiple tables to Excel with sheets."""
with pd.ExcelWriter(output_path, engine="openpyxl") as writer:
for i, table in enumerate(tables):
if not table:
continue
# Convert to DataFrame
headers = table[0]
data = table[1:]
df = pd.DataFrame(data, columns=headers)
# Write to sheet
sheet_name = f"Table_{i + 1}"
df.to_excel(writer, sheet_name=sheet_name, index=False)
# Auto-adjust column widths
worksheet = writer.sheets[sheet_name]
for column in worksheet.columns:
max_length = 0
column_letter = column[0].column_letter
for cell in column:
if len(str(cell.value)) > max_length:
max_length = len(str(cell.value))
worksheet.column_dimensions[column_letter].width = max_length + 2
# Usage
tables = extract_all_tables("report.pdf")
export_to_excel(tables, "output.xlsx")
```
### Export to JSON
```python
import json
def export_to_json(table, output_path):
"""Export table to JSON."""
if not table:
return
headers = table[0]
data = table[1:]
# Convert to list of dictionaries
records = []
for row in data:
record = {}
for i, header in enumerate(headers):
value = row[i] if i < len(row) else None
record[header] = value
records.append(record)
# Save to JSON
with open(output_path, "w", encoding="utf-8") as f:
json.dump(records, f, indent=2)
# Usage
table = extract_table("report.pdf")
export_to_json(table, "output.json")
```
## Table detection algorithms
### Visual debugging
```python
import pdfplumber
def visualize_table_detection(pdf_path, page_num=0, output_path="debug.png"):
"""Visualize detected table structure."""
with pdfplumber.open(pdf_path) as pdf:
page = pdf.pages[page_num]
# Draw detected table lines
im = page.to_image(resolution=150)
im = im.debug_tablefinder()
im.save(output_path)
print(f"Saved debug image to {output_path}")
# Usage
visualize_table_detection("document.pdf", page_num=0)
```
### Algorithm: Line-based detection
Best for tables with visible borders:
```python
table_settings = {
"vertical_strategy": "lines",
"horizontal_strategy": "lines"
}
tables = page.extract_tables(table_settings=table_settings)
```
### Algorithm: Text-based detection
Best for tables without borders:
```python
table_settings = {
"vertical_strategy": "text",
"horizontal_strategy": "text"
}
tables = page.extract_tables(table_settings=table_settings)
```
### Algorithm: Explicit lines
For complex layouts, define lines manually:
```python
# Define vertical lines at x-coordinates
vertical_lines = [50, 150, 250, 350, 450, 550]
# Define horizontal lines at y-coordinates
horizontal_lines = [100, 130, 160, 190, 220, 250]
table_settings = {
"explicit_vertical_lines": vertical_lines,
"explicit_horizontal_lines": horizontal_lines
}
tables = page.extract_tables(table_settings=table_settings)
```
## Custom extraction rules
### Rule-based extraction
```python
def extract_with_rules(page, rules):
"""Extract table using custom rules."""
# Rule: "Headers are bold"
if rules.get("bold_headers"):
chars = page.chars
bold_chars = [c for c in chars if "Bold" in c.get("fontname", "")]
# Use bold chars to identify header row
pass
# Rule: "First column is always left-aligned"
if rules.get("left_align_first_col"):
# Adjust extraction to respect alignment
pass
# Rule: "Currency values in last column"
if rules.get("currency_last_col"):
# Parse currency format
pass
# Extract with adjusted settings
return page.extract_tables()
```
### Post-processing rules
```python
def apply_post_processing(table, rules):
"""Apply post-processing rules to extracted table."""
processed = []
for row in table:
new_row = []
for i, cell in enumerate(row):
value = cell
# Rule: Strip whitespace
if rules.get("strip_whitespace"):
value = value.strip() if value else value
# Rule: Convert currency to float
if rules.get("parse_currency") and i == len(row) - 1:
if value and "$" in value:
value = float(value.replace("$", "").replace(",", ""))
# Rule: Parse dates
if rules.get("parse_dates") and i == 0:
# Convert to datetime
pass
new_row.append(value)
processed.append(new_row)
return processed
```
## Performance optimization
### Process large PDFs efficiently
```python
def extract_tables_optimized(pdf_path):
"""Extract tables with memory optimization."""
import gc
results = []
with pdfplumber.open(pdf_path) as pdf:
for page_num, page in enumerate(pdf.pages):
print(f"Processing page {page_num + 1}/{len(pdf.pages)}")
# Extract tables from current page
tables = page.extract_tables()
results.extend(tables)
# Force garbage collection
gc.collect()
return results
```
### Parallel processing
```python
from concurrent.futures import ProcessPoolExecutor
import pdfplumber
def extract_page_tables(args):
"""Extract tables from a single page."""
pdf_path, page_num = args
with pdfplumber.open(pdf_path) as pdf:
page = pdf.pages[page_num]
return page.extract_tables()
def extract_tables_parallel(pdf_path, max_workers=4):
"""Extract tables using multiple processes."""
with pdfplumber.open(pdf_path) as pdf:
page_count = len(pdf.pages)
# Create tasks
tasks = [(pdf_path, i) for i in range(page_count)]
# Process in parallel
with ProcessPoolExecutor(max_workers=max_workers) as executor:
results = list(executor.map(extract_page_tables, tasks))
# Flatten results
all_tables = []
for page_tables in results:
all_tables.extend(page_tables)
return all_tables
```
## Production examples
### Example 1: Financial report extraction
```python
import pdfplumber
import pandas as pd
from decimal import Decimal
def extract_financial_tables(pdf_path):
"""Extract financial data with proper number formatting."""
tables = []
with pdfplumber.open(pdf_path) as pdf:
for page in pdf.pages:
page_tables = page.extract_tables()
for table in page_tables:
# Convert to DataFrame
df = pd.DataFrame(table[1:], columns=table[0])
# Parse currency columns
for col in df.columns:
if df[col].str.contains("$", na=False).any():
df[col] = df[col].str.replace(r"[$,()]", "", regex=True)
df[col] = pd.to_numeric(df[col], errors="coerce")
tables.append(df)
return tables
```
### Example 2: Batch table extraction
```python
import glob
from pathlib import Path
def batch_extract_tables(input_dir, output_dir):
"""Extract tables from all PDFs in directory."""
input_path = Path(input_dir)
output_path = Path(output_dir)
output_path.mkdir(exist_ok=True)
for pdf_file in input_path.glob("*.pdf"):
print(f"Processing: {pdf_file.name}")
try:
# Extract tables
tables = extract_all_tables(str(pdf_file))
# Export to Excel
output_file = output_path / f"{pdf_file.stem}_tables.xlsx"
export_to_excel(tables, str(output_file))
print(f" ✓ Extracted {len(tables)} table(s)")
except Exception as e:
print(f" ✗ Error: {e}")
# Usage
batch_extract_tables("invoices/", "extracted/")
```
## Best practices
1. **Visualize first**: Use debug mode to understand table structure
2. **Test settings**: Try different strategies for best results
3. **Handle errors**: PDFs vary widely in quality
4. **Validate output**: Check extracted data makes sense
5. **Post-process**: Clean and normalize extracted data
6. **Use pandas**: Leverage DataFrame operations for analysis
7. **Cache results**: Avoid re-processing large files
8. **Monitor performance**: Profile for bottlenecks
## Troubleshooting
### Tables not detected
1. Try different detection strategies
2. Use visual debugging to see structure
3. Define explicit lines manually
4. Check if table is actually an image
### Incorrect cell values
1. Adjust snap/join tolerance
2. Check text extraction quality
3. Use post-processing to clean data
4. Verify PDF is not scanned image
### Performance issues
1. Process pages individually
2. Use parallel processing
3. Reduce image resolution
4. Extract only needed pages

307
skills/pdf-processing-pro/scripts/analyze_form.py Normal file
View File

@@ -0,0 +1,307 @@
#!/usr/bin/env python3
"""
Analyze PDF form fields and structure.
Usage:
python analyze_form.py input.pdf [--output fields.json] [--verbose]
Returns:
JSON with all form fields, types, positions, and metadata
Exit codes:
0 - Success
1 - File not found
2 - Invalid PDF
3 - Processing error
"""
import sys
import json
import logging
import argparse
from pathlib import Path
from typing import Dict, List, Optional, Any
try:
from pypdf import PdfReader
except ImportError:
print("Error: pypdf not installed. Run: pip install pypdf", file=sys.stderr)
sys.exit(3)
# Configure logging
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(levelname)s - %(message)s'
)
logger = logging.getLogger(__name__)
class FormField:
"""Represents a PDF form field."""
def __init__(self, name: str, field_dict: Dict[str, Any]):
self.name = name
self.raw_data = field_dict
@property
def field_type(self) -> str:
"""Get field type."""
ft = self.raw_data.get('/FT', '')
type_map = {
'/Tx': 'text',
'/Btn': 'button', # checkbox or radio
'/Ch': 'choice', # dropdown or list
'/Sig': 'signature'
}
return type_map.get(ft, 'unknown')
@property
def value(self) -> Optional[str]:
"""Get current field value."""
val = self.raw_data.get('/V')
return str(val) if val else None
@property
def default_value(self) -> Optional[str]:
"""Get default field value."""
dv = self.raw_data.get('/DV')
return str(dv) if dv else None
@property
def is_required(self) -> bool:
"""Check if field is required."""
flags = self.raw_data.get('/Ff', 0)
# Bit 2 indicates required
return bool(flags & 2)
@property
def is_readonly(self) -> bool:
"""Check if field is read-only."""
flags = self.raw_data.get('/Ff', 0)
# Bit 1 indicates read-only
return bool(flags & 1)
@property
def options(self) -> List[str]:
"""Get options for choice fields."""
if self.field_type != 'choice':
return []
opts = self.raw_data.get('/Opt', [])
if isinstance(opts, list):
return [str(opt) for opt in opts]
return []
@property
def max_length(self) -> Optional[int]:
"""Get max length for text fields."""
if self.field_type == 'text':
return self.raw_data.get('/MaxLen')
return None
@property
def rect(self) -> Optional[List[float]]:
"""Get field position and size [x0, y0, x1, y1]."""
return self.raw_data.get('/Rect')
def to_dict(self) -> Dict[str, Any]:
"""Convert to dictionary."""
result = {
'name': self.name,
'type': self.field_type,
'required': self.is_required,
'readonly': self.is_readonly
}
if self.value is not None:
result['value'] = self.value
if self.default_value is not None:
result['default_value'] = self.default_value
if self.options:
result['options'] = self.options
if self.max_length is not None:
result['max_length'] = self.max_length
if self.rect:
result['position'] = {
'x0': float(self.rect[0]),
'y0': float(self.rect[1]),
'x1': float(self.rect[2]),
'y1': float(self.rect[3]),
'width': float(self.rect[2] - self.rect[0]),
'height': float(self.rect[3] - self.rect[1])
}
return result
class PDFFormAnalyzer:
"""Analyzes PDF forms and extracts field information."""
def __init__(self, pdf_path: str):
self.pdf_path = Path(pdf_path)
self.reader: Optional[PdfReader] = None
self._validate_file()
def _validate_file(self) -> None:
"""Validate PDF file exists and is readable."""
if not self.pdf_path.exists():
logger.error(f"PDF not found: {self.pdf_path}")
raise FileNotFoundError(f"PDF not found: {self.pdf_path}")
if not self.pdf_path.is_file():
logger.error(f"Not a file: {self.pdf_path}")
raise ValueError(f"Not a file: {self.pdf_path}")
if self.pdf_path.suffix.lower() != '.pdf':
logger.error(f"Not a PDF file: {self.pdf_path}")
raise ValueError(f"Not a PDF file: {self.pdf_path}")
def analyze(self) -> Dict[str, Dict[str, Any]]:
"""
Analyze PDF and extract all form fields.
Returns:
Dictionary mapping field names to field information
"""
try:
self.reader = PdfReader(str(self.pdf_path))
if not self.reader.pages:
logger.warning("PDF has no pages")
return {}
logger.info(f"Analyzing PDF with {len(self.reader.pages)} pages")
# Get form fields
raw_fields = self.reader.get_fields()
if not raw_fields:
logger.warning("PDF has no form fields")
return {}
logger.info(f"Found {len(raw_fields)} form fields")
# Process fields
fields = {}
for field_name, field_dict in raw_fields.items():
try:
field = FormField(field_name, field_dict)
fields[field_name] = field.to_dict()
except Exception as e:
logger.warning(f"Error processing field {field_name}: {e}")
continue
return fields
except Exception as e:
logger.error(f"Error analyzing PDF: {e}")
raise
def get_summary(self) -> Dict[str, Any]:
"""Get summary statistics."""
fields = self.analyze()
summary = {
'total_fields': len(fields),
'field_types': {},
'required_fields': [],
'readonly_fields': [],
'fields_with_values': []
}
for field_name, field_data in fields.items():
# Count by type
field_type = field_data['type']
summary['field_types'][field_type] = summary['field_types'].get(field_type, 0) + 1
# Required fields
if field_data.get('required'):
summary['required_fields'].append(field_name)
# Read-only fields
if field_data.get('readonly'):
summary['readonly_fields'].append(field_name)
# Fields with values
if field_data.get('value'):
summary['fields_with_values'].append(field_name)
return summary
def main():
"""Main entry point."""
parser = argparse.ArgumentParser(
description='Analyze PDF form fields',
formatter_class=argparse.RawDescriptionHelpFormatter,
epilog='''
Examples:
%(prog)s form.pdf
%(prog)s form.pdf --output fields.json
%(prog)s form.pdf --output fields.json --verbose
%(prog)s form.pdf --summary
Exit codes:
0 - Success
1 - File not found
2 - Invalid PDF
3 - Processing error
'''
)
parser.add_argument('input', help='Input PDF file')
parser.add_argument('--output', '-o', help='Output JSON file (default: stdout)')
parser.add_argument('--summary', '-s', action='store_true', help='Show summary only')
parser.add_argument('--verbose', '-v', action='store_true', help='Verbose output')
args = parser.parse_args()
# Set log level
if args.verbose:
logger.setLevel(logging.DEBUG)
else:
logger.setLevel(logging.WARNING)
try:
# Analyze form
analyzer = PDFFormAnalyzer(args.input)
if args.summary:
result = analyzer.get_summary()
else:
result = analyzer.analyze()
# Output
json_output = json.dumps(result, indent=2)
if args.output:
with open(args.output, 'w', encoding='utf-8') as f:
f.write(json_output)
logger.info(f"Saved to {args.output}")
else:
print(json_output)
return 0
except FileNotFoundError:
logger.error(f"File not found: {args.input}")
return 1
except ValueError as e:
logger.error(f"Invalid input: {e}")
return 2
except Exception as e:
logger.error(f"Error: {e}")
if args.verbose:
import traceback
traceback.print_exc()
return 3
if __name__ == '__main__':
sys.exit(main())

30
skills/xlsx/LICENSE.txt Normal file
View File

@@ -0,0 +1,30 @@
© 2025 Anthropic, PBC. All rights reserved.
LICENSE: Use of these materials (including all code, prompts, assets, files,
and other components of this Skill) is governed by your agreement with
Anthropic regarding use of Anthropic's services. If no separate agreement
exists, use is governed by Anthropic's Consumer Terms of Service or
Commercial Terms of Service, as applicable:
https://www.anthropic.com/legal/consumer-terms
https://www.anthropic.com/legal/commercial-terms
Your applicable agreement is referred to as the "Agreement." "Services" are
as defined in the Agreement.
ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the
contrary, users may not:
- Extract these materials from the Services or retain copies of these
materials outside the Services
- Reproduce or copy these materials, except for temporary copies created
automatically during authorized use of the Services
- Create derivative works based on these materials
- Distribute, sublicense, or transfer these materials to any third party
- Make, offer to sell, sell, or import any inventions embodied in these
materials
- Reverse engineer, decompile, or disassemble these materials
The receipt, viewing, or possession of these materials does not convey or
imply any license or right beyond those expressly granted above.
Anthropic retains all right, title, and interest in these materials,
including all copyrights, patents, and other intellectual property rights.

289
skills/xlsx/SKILL.md Normal file
View File

@@ -0,0 +1,289 @@
---
name: xlsx
description: "Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas"
license: Proprietary. LICENSE.txt has complete terms
---
# Requirements for Outputs
## All Excel files
### Zero Formula Errors
- Every Excel model MUST be delivered with ZERO formula errors (#REF!, #DIV/0!, #VALUE!, #N/A, #NAME?)
### Preserve Existing Templates (when updating templates)
- Study and EXACTLY match existing format, style, and conventions when modifying files
- Never impose standardized formatting on files with established patterns
- Existing template conventions ALWAYS override these guidelines
## Financial models
### Color Coding Standards
Unless otherwise stated by the user or existing template
#### Industry-Standard Color Conventions
- **Blue text (RGB: 0,0,255)**: Hardcoded inputs, and numbers users will change for scenarios
- **Black text (RGB: 0,0,0)**: ALL formulas and calculations
- **Green text (RGB: 0,128,0)**: Links pulling from other worksheets within same workbook
- **Red text (RGB: 255,0,0)**: External links to other files
- **Yellow background (RGB: 255,255,0)**: Key assumptions needing attention or cells that need to be updated
### Number Formatting Standards
#### Required Format Rules
- **Years**: Format as text strings (e.g., "2024" not "2,024")
- **Currency**: Use $#,##0 format; ALWAYS specify units in headers ("Revenue ($mm)")
- **Zeros**: Use number formatting to make all zeros "-", including percentages (e.g., "$#,##0;($#,##0);-")
- **Percentages**: Default to 0.0% format (one decimal)
- **Multiples**: Format as 0.0x for valuation multiples (EV/EBITDA, P/E)
- **Negative numbers**: Use parentheses (123) not minus -123
### Formula Construction Rules
#### Assumptions Placement
- Place ALL assumptions (growth rates, margins, multiples, etc.) in separate assumption cells
- Use cell references instead of hardcoded values in formulas
- Example: Use =B5*(1+$B$6) instead of =B5*1.05
#### Formula Error Prevention
- Verify all cell references are correct
- Check for off-by-one errors in ranges
- Ensure consistent formulas across all projection periods
- Test with edge cases (zero values, negative numbers)
- Verify no unintended circular references
#### Documentation Requirements for Hardcodes
- Comment or in cells beside (if end of table). Format: "Source: [System/Document], [Date], [Specific Reference], [URL if applicable]"
- Examples:
- "Source: Company 10-K, FY2024, Page 45, Revenue Note, [SEC EDGAR URL]"
- "Source: Company 10-Q, Q2 2025, Exhibit 99.1, [SEC EDGAR URL]"
- "Source: Bloomberg Terminal, 8/15/2025, AAPL US Equity"
- "Source: FactSet, 8/20/2025, Consensus Estimates Screen"
# XLSX creation, editing, and analysis
## Overview
A user may ask you to create, edit, or analyze the contents of an .xlsx file. You have different tools and workflows available for different tasks.
## Important Requirements
**LibreOffice Required for Formula Recalculation**: You can assume LibreOffice is installed for recalculating formula values using the `recalc.py` script. The script automatically configures LibreOffice on first run
## Reading and analyzing data
### Data analysis with pandas
For data analysis, visualization, and basic operations, use **pandas** which provides powerful data manipulation capabilities:
```python
import pandas as pd
# Read Excel
df = pd.read_excel('file.xlsx') # Default: first sheet
all_sheets = pd.read_excel('file.xlsx', sheet_name=None) # All sheets as dict
# Analyze
df.head() # Preview data
df.info() # Column info
df.describe() # Statistics
# Write Excel
df.to_excel('output.xlsx', index=False)
```
## Excel File Workflows
## CRITICAL: Use Formulas, Not Hardcoded Values
**Always use Excel formulas instead of calculating values in Python and hardcoding them.** This ensures the spreadsheet remains dynamic and updateable.
### ❌ WRONG - Hardcoding Calculated Values
```python
# Bad: Calculating in Python and hardcoding result
total = df['Sales'].sum()
sheet['B10'] = total # Hardcodes 5000
# Bad: Computing growth rate in Python
growth = (df.iloc[-1]['Revenue'] - df.iloc[0]['Revenue']) / df.iloc[0]['Revenue']
sheet['C5'] = growth # Hardcodes 0.15
# Bad: Python calculation for average
avg = sum(values) / len(values)
sheet['D20'] = avg # Hardcodes 42.5
```
### ✅ CORRECT - Using Excel Formulas
```python
# Good: Let Excel calculate the sum
sheet['B10'] = '=SUM(B2:B9)'
# Good: Growth rate as Excel formula
sheet['C5'] = '=(C4-C2)/C2'
# Good: Average using Excel function
sheet['D20'] = '=AVERAGE(D2:D19)'
```
This applies to ALL calculations - totals, percentages, ratios, differences, etc. The spreadsheet should be able to recalculate when source data changes.
## Common Workflow
1. **Choose tool**: pandas for data, openpyxl for formulas/formatting
2. **Create/Load**: Create new workbook or load existing file
3. **Modify**: Add/edit data, formulas, and formatting
4. **Save**: Write to file
5. **Recalculate formulas (MANDATORY IF USING FORMULAS)**: Use the recalc.py script
```bash
python recalc.py output.xlsx
```
6. **Verify and fix any errors**:
- The script returns JSON with error details
- If `status` is `errors_found`, check `error_summary` for specific error types and locations
- Fix the identified errors and recalculate again
- Common errors to fix:
- `#REF!`: Invalid cell references
- `#DIV/0!`: Division by zero
- `#VALUE!`: Wrong data type in formula
- `#NAME?`: Unrecognized formula name
### Creating new Excel files
```python
# Using openpyxl for formulas and formatting
from openpyxl import Workbook
from openpyxl.styles import Font, PatternFill, Alignment
wb = Workbook()
sheet = wb.active
# Add data
sheet['A1'] = 'Hello'
sheet['B1'] = 'World'
sheet.append(['Row', 'of', 'data'])
# Add formula
sheet['B2'] = '=SUM(A1:A10)'
# Formatting
sheet['A1'].font = Font(bold=True, color='FF0000')
sheet['A1'].fill = PatternFill('solid', start_color='FFFF00')
sheet['A1'].alignment = Alignment(horizontal='center')
# Column width
sheet.column_dimensions['A'].width = 20
wb.save('output.xlsx')
```
### Editing existing Excel files
```python
# Using openpyxl to preserve formulas and formatting
from openpyxl import load_workbook
# Load existing file
wb = load_workbook('existing.xlsx')
sheet = wb.active # or wb['SheetName'] for specific sheet
# Working with multiple sheets
for sheet_name in wb.sheetnames:
sheet = wb[sheet_name]
print(f"Sheet: {sheet_name}")
# Modify cells
sheet['A1'] = 'New Value'
sheet.insert_rows(2) # Insert row at position 2
sheet.delete_cols(3) # Delete column 3
# Add new sheet
new_sheet = wb.create_sheet('NewSheet')
new_sheet['A1'] = 'Data'
wb.save('modified.xlsx')
```
## Recalculating formulas
Excel files created or modified by openpyxl contain formulas as strings but not calculated values. Use the provided `recalc.py` script to recalculate formulas:
```bash
python recalc.py <excel_file> [timeout_seconds]
```
Example:
```bash
python recalc.py output.xlsx 30
```
The script:
- Automatically sets up LibreOffice macro on first run
- Recalculates all formulas in all sheets
- Scans ALL cells for Excel errors (#REF!, #DIV/0!, etc.)
- Returns JSON with detailed error locations and counts
- Works on both Linux and macOS
## Formula Verification Checklist
Quick checks to ensure formulas work correctly:
### Essential Verification
- [ ] **Test 2-3 sample references**: Verify they pull correct values before building full model
- [ ] **Column mapping**: Confirm Excel columns match (e.g., column 64 = BL, not BK)
- [ ] **Row offset**: Remember Excel rows are 1-indexed (DataFrame row 5 = Excel row 6)
### Common Pitfalls
- [ ] **NaN handling**: Check for null values with `pd.notna()`
- [ ] **Far-right columns**: FY data often in columns 50+
- [ ] **Multiple matches**: Search all occurrences, not just first
- [ ] **Division by zero**: Check denominators before using `/` in formulas (#DIV/0!)
- [ ] **Wrong references**: Verify all cell references point to intended cells (#REF!)
- [ ] **Cross-sheet references**: Use correct format (Sheet1!A1) for linking sheets
### Formula Testing Strategy
- [ ] **Start small**: Test formulas on 2-3 cells before applying broadly
- [ ] **Verify dependencies**: Check all cells referenced in formulas exist
- [ ] **Test edge cases**: Include zero, negative, and very large values
### Interpreting recalc.py Output
The script returns JSON with error details:
```json
{
"status": "success", // or "errors_found"
"total_errors": 0, // Total error count
"total_formulas": 42, // Number of formulas in file
"error_summary": { // Only present if errors found
"#REF!": {
"count": 2,
"locations": ["Sheet1!B5", "Sheet1!C10"]
}
}
}
```
## Best Practices
### Library Selection
- **pandas**: Best for data analysis, bulk operations, and simple data export
- **openpyxl**: Best for complex formatting, formulas, and Excel-specific features
### Working with openpyxl
- Cell indices are 1-based (row=1, column=1 refers to cell A1)
- Use `data_only=True` to read calculated values: `load_workbook('file.xlsx', data_only=True)`
- **Warning**: If opened with `data_only=True` and saved, formulas are replaced with values and permanently lost
- For large files: Use `read_only=True` for reading or `write_only=True` for writing
- Formulas are preserved but not evaluated - use recalc.py to update values
### Working with pandas
- Specify data types to avoid inference issues: `pd.read_excel('file.xlsx', dtype={'id': str})`
- For large files, read specific columns: `pd.read_excel('file.xlsx', usecols=['A', 'C', 'E'])`
- Handle dates properly: `pd.read_excel('file.xlsx', parse_dates=['date_column'])`
## Code Style Guidelines
**IMPORTANT**: When generating Python code for Excel operations:
- Write minimal, concise Python code without unnecessary comments
- Avoid verbose variable names and redundant operations
- Avoid unnecessary print statements
**For Excel files themselves**:
- Add comments to cells with complex formulas or important assumptions
- Document data sources for hardcoded values
- Include notes for key calculations and model sections

178
skills/xlsx/recalc.py Normal file
View File

@@ -0,0 +1,178 @@
#!/usr/bin/env python3
"""
Excel Formula Recalculation Script
Recalculates all formulas in an Excel file using LibreOffice
"""
import json
import sys
import subprocess
import os
import platform
from pathlib import Path
from openpyxl import load_workbook
def setup_libreoffice_macro():
"""Setup LibreOffice macro for recalculation if not already configured"""
if platform.system() == 'Darwin':
macro_dir = os.path.expanduser('~/Library/Application Support/LibreOffice/4/user/basic/Standard')
else:
macro_dir = os.path.expanduser('~/.config/libreoffice/4/user/basic/Standard')
macro_file = os.path.join(macro_dir, 'Module1.xba')
if os.path.exists(macro_file):
with open(macro_file, 'r') as f:
if 'RecalculateAndSave' in f.read():
return True
if not os.path.exists(macro_dir):
subprocess.run(['soffice', '--headless', '--terminate_after_init'],
capture_output=True, timeout=10)
os.makedirs(macro_dir, exist_ok=True)
macro_content = '''<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE script:module PUBLIC "-//OpenOffice.org//DTD OfficeDocument 1.0//EN" "module.dtd">
<script:module xmlns:script="http://openoffice.org/2000/script" script:name="Module1" script:language="StarBasic">
Sub RecalculateAndSave()
ThisComponent.calculateAll()
ThisComponent.store()
ThisComponent.close(True)
End Sub
</script:module>'''
try:
with open(macro_file, 'w') as f:
f.write(macro_content)
return True
except Exception:
return False
def recalc(filename, timeout=30):
"""
Recalculate formulas in Excel file and report any errors
Args:
filename: Path to Excel file
timeout: Maximum time to wait for recalculation (seconds)
Returns:
dict with error locations and counts
"""
if not Path(filename).exists():
return {'error': f'File {filename} does not exist'}
abs_path = str(Path(filename).absolute())
if not setup_libreoffice_macro():
return {'error': 'Failed to setup LibreOffice macro'}
cmd = [
'soffice', '--headless', '--norestore',
'vnd.sun.star.script:Standard.Module1.RecalculateAndSave?language=Basic&location=application',
abs_path
]
# Handle timeout command differences between Linux and macOS
if platform.system() != 'Windows':
timeout_cmd = 'timeout' if platform.system() == 'Linux' else None
if platform.system() == 'Darwin':
# Check if gtimeout is available on macOS
try:
subprocess.run(['gtimeout', '--version'], capture_output=True, timeout=1, check=False)
timeout_cmd = 'gtimeout'
except (FileNotFoundError, subprocess.TimeoutExpired):
pass
if timeout_cmd:
cmd = [timeout_cmd, str(timeout)] + cmd
result = subprocess.run(cmd, capture_output=True, text=True)
if result.returncode != 0 and result.returncode != 124: # 124 is timeout exit code
error_msg = result.stderr or 'Unknown error during recalculation'
if 'Module1' in error_msg or 'RecalculateAndSave' not in error_msg:
return {'error': 'LibreOffice macro not configured properly'}
else:
return {'error': error_msg}
# Check for Excel errors in the recalculated file - scan ALL cells
try:
wb = load_workbook(filename, data_only=True)
excel_errors = ['#VALUE!', '#DIV/0!', '#REF!', '#NAME?', '#NULL!', '#NUM!', '#N/A']
error_details = {err: [] for err in excel_errors}
total_errors = 0
for sheet_name in wb.sheetnames:
ws = wb[sheet_name]
# Check ALL rows and columns - no limits
for row in ws.iter_rows():
for cell in row:
if cell.value is not None and isinstance(cell.value, str):
for err in excel_errors:
if err in cell.value:
location = f"{sheet_name}!{cell.coordinate}"
error_details[err].append(location)
total_errors += 1
break
wb.close()
# Build result summary
result = {
'status': 'success' if total_errors == 0 else 'errors_found',
'total_errors': total_errors,
'error_summary': {}
}
# Add non-empty error categories
for err_type, locations in error_details.items():
if locations:
result['error_summary'][err_type] = {
'count': len(locations),
'locations': locations[:20] # Show up to 20 locations
}
# Add formula count for context - also check ALL cells
wb_formulas = load_workbook(filename, data_only=False)
formula_count = 0
for sheet_name in wb_formulas.sheetnames:
ws = wb_formulas[sheet_name]
for row in ws.iter_rows():
for cell in row:
if cell.value and isinstance(cell.value, str) and cell.value.startswith('='):
formula_count += 1
wb_formulas.close()
result['total_formulas'] = formula_count
return result
except Exception as e:
return {'error': str(e)}
def main():
if len(sys.argv) < 2:
print("Usage: python recalc.py <excel_file> [timeout_seconds]")
print("\nRecalculates all formulas in an Excel file using LibreOffice")
print("\nReturns JSON with error details:")
print(" - status: 'success' or 'errors_found'")
print(" - total_errors: Total number of Excel errors found")
print(" - total_formulas: Number of formulas in the file")
print(" - error_summary: Breakdown by error type with locations")
print(" - #VALUE!, #DIV/0!, #REF!, #NAME?, #NULL!, #NUM!, #N/A")
sys.exit(1)
filename = sys.argv[1]
timeout = int(sys.argv[2]) if len(sys.argv) > 2 else 30
result = recalc(filename, timeout)
print(json.dumps(result, indent=2))
if __name__ == '__main__':
main()