@thanhvn14/csvibe 0.1.3 → 0.1.5

package/.github/skills/document-skills/pptx/ooxml/schemas/microsoft/wml-cex-2018.xsd

@@ -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>

package/.github/skills/document-skills/pptx/ooxml/schemas/microsoft/wml-cid-2016.xsd

@@ -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>

package/.github/skills/document-skills/pptx/ooxml/schemas/microsoft/wml-sdtdatahash-2020.xsd

@@ -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>

package/.github/skills/document-skills/pptx/ooxml/schemas/microsoft/wml-symex-2015.xsd

@@ -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>

package/.github/skills/document-skills/pptx/ooxml/scripts/pack.py

@@ -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()

package/.github/skills/document-skills/pptx/ooxml/scripts/unpack.py

@@ -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}")

package/.github/skills/document-skills/pptx/ooxml/scripts/validate.py

@@ -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()

package/.github/skills/document-skills/pptx/ooxml/scripts/validation/__init__.py

@@ -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",
+]