初始化项目版本
This commit is contained in:
Axhub Make
15
.agents/skills/docx/scripts/office/validators/__init__.py
Normal file
15
.agents/skills/docx/scripts/office/validators/__init__.py
Normal 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",
|
||||
]
|
||||
875
.agents/skills/docx/scripts/office/validators/base.py
Normal file
875
.agents/skills/docx/scripts/office/validators/base.py
Normal file
@@ -0,0 +1,875 @@
|
||||
"""
|
||||
Base validator with common validation logic for document files.
|
||||
"""
|
||||
|
||||
import re
|
||||
from pathlib import Path
|
||||
|
||||
import defusedxml.minidom
|
||||
from functools import lru_cache
|
||||
|
||||
import lxml.etree
|
||||
|
||||
from helpers import safe_extract
|
||||
|
||||
|
||||
@lru_cache(maxsize=None)
|
||||
def _load_schema(schema_path: str):
|
||||
with open(schema_path, "rb") as xsd_file:
|
||||
xsd_doc = lxml.etree.parse(
|
||||
xsd_file, parser=lxml.etree.XMLParser(), base_url=schema_path
|
||||
)
|
||||
return lxml.etree.XMLSchema(xsd_doc)
|
||||
|
||||
class BaseSchemaValidator:
|
||||
|
||||
IGNORED_VALIDATION_ERRORS = [
|
||||
"hyphenationZone",
|
||||
"purl.org/dc/terms",
|
||||
]
|
||||
|
||||
UNIQUE_ID_REQUIREMENTS = {
|
||||
"comment": ("id", "file"),
|
||||
"commentrangestart": ("id", "file"),
|
||||
"commentrangeend": ("id", "file"),
|
||||
"bookmarkstart": ("id", "file"),
|
||||
"bookmarkend": ("id", "file"),
|
||||
"sldid": ("id", "file"),
|
||||
"sldmasterid": ("id", "global"),
|
||||
"sldlayoutid": ("id", "global"),
|
||||
"cm": ("authorid", "file"),
|
||||
"sheet": ("sheetid", "file"),
|
||||
"definedname": ("id", "file"),
|
||||
"cxnsp": ("id", "file"),
|
||||
"sp": ("id", "file"),
|
||||
"pic": ("id", "file"),
|
||||
"grpsp": ("id", "file"),
|
||||
}
|
||||
|
||||
EXCLUDED_ID_CONTAINERS = {
|
||||
"sectionlst",
|
||||
}
|
||||
|
||||
ELEMENT_RELATIONSHIP_TYPES = {}
|
||||
|
||||
SCHEMA_MAPPINGS = {
|
||||
"word": "ISO-IEC29500-4_2016/wml.xsd",
|
||||
"ppt": "ISO-IEC29500-4_2016/pml.xsd",
|
||||
"xl": "ISO-IEC29500-4_2016/sml.xsd",
|
||||
"[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",
|
||||
"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": "ISO-IEC29500-4_2016/dml-chart.xsd",
|
||||
"theme": "ISO-IEC29500-4_2016/dml-main.xsd",
|
||||
"drawing": "ISO-IEC29500-4_2016/dml-main.xsd",
|
||||
}
|
||||
|
||||
MC_NAMESPACE = "http://schemas.openxmlformats.org/markup-compatibility/2006"
|
||||
XML_NAMESPACE = "http://www.w3.org/XML/1998/namespace"
|
||||
|
||||
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"
|
||||
)
|
||||
|
||||
MAIN_CONTENT_FOLDERS = {"word", "ppt", "xl"}
|
||||
|
||||
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=None, verbose=False):
|
||||
self.unpacked_dir = Path(unpacked_dir).resolve()
|
||||
self.original_file = Path(original_file) if original_file else None
|
||||
self.verbose = verbose
|
||||
|
||||
self.schemas_dir = Path(__file__).parent.parent / "schemas"
|
||||
|
||||
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):
|
||||
raise NotImplementedError("Subclasses must implement the validate method")
|
||||
|
||||
def repair(self) -> int:
|
||||
return self.repair_whitespace_preservation()
|
||||
|
||||
def repair_whitespace_preservation(self) -> int:
|
||||
repairs = 0
|
||||
|
||||
for xml_file in self.xml_files:
|
||||
try:
|
||||
content = xml_file.read_text(encoding="utf-8")
|
||||
dom = defusedxml.minidom.parseString(content)
|
||||
pending = []
|
||||
|
||||
for elem in dom.getElementsByTagName("*"):
|
||||
local_name = elem.tagName.rsplit(":", 1)[-1]
|
||||
if local_name in ("t", "delText", "instrText", "delInstrText"):
|
||||
text = "".join(
|
||||
child.data
|
||||
for child in elem.childNodes
|
||||
if child.nodeType in (child.TEXT_NODE, child.CDATA_SECTION_NODE)
|
||||
)
|
||||
ws = (" ", "\t", "\n", "\r")
|
||||
if text and (text.startswith(ws) or text.endswith(ws)):
|
||||
if elem.getAttribute("xml:space") != "preserve":
|
||||
elem.setAttribute("xml:space", "preserve")
|
||||
text_preview = repr(text[:30]) + "..." if len(text) > 30 else repr(text)
|
||||
pending.append(f" Repaired: {xml_file.name}: Added xml:space='preserve' to {elem.tagName}: {text_preview}")
|
||||
|
||||
if pending:
|
||||
xml_file.write_bytes(dom.toxml(encoding="UTF-8"))
|
||||
for message in pending:
|
||||
print(message)
|
||||
repairs += len(pending)
|
||||
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return repairs
|
||||
|
||||
def validate_xml(self):
|
||||
errors = []
|
||||
|
||||
for xml_file in self.xml_files:
|
||||
try:
|
||||
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):
|
||||
errors = []
|
||||
|
||||
for xml_file in self.xml_files:
|
||||
try:
|
||||
root = lxml.etree.parse(str(xml_file)).getroot()
|
||||
declared = set(root.nsmap.keys()) - {None}
|
||||
|
||||
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):
|
||||
errors = []
|
||||
global_ids = {}
|
||||
|
||||
for xml_file in self.xml_files:
|
||||
try:
|
||||
root = lxml.etree.parse(str(xml_file)).getroot()
|
||||
file_ids = {}
|
||||
|
||||
mc_elements = root.xpath(
|
||||
".//mc:AlternateContent", namespaces={"mc": self.MC_NAMESPACE}
|
||||
)
|
||||
for elem in mc_elements:
|
||||
elem.getparent().remove(elem)
|
||||
|
||||
for elem in root.iter():
|
||||
if not hasattr(elem, "tag") or callable(elem.tag):
|
||||
continue
|
||||
tag = (
|
||||
elem.tag.split("}")[-1].lower()
|
||||
if "}" in elem.tag
|
||||
else elem.tag.lower()
|
||||
)
|
||||
|
||||
if tag in self.UNIQUE_ID_REQUIREMENTS:
|
||||
in_excluded_container = any(
|
||||
ancestor.tag.split("}")[-1].lower() in self.EXCLUDED_ID_CONTAINERS
|
||||
for ancestor in elem.iterancestors()
|
||||
)
|
||||
if in_excluded_container:
|
||||
continue
|
||||
|
||||
attr_name, scope = self.UNIQUE_ID_REQUIREMENTS[tag]
|
||||
|
||||
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":
|
||||
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":
|
||||
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):
|
||||
errors = []
|
||||
|
||||
rels_files = list(self.unpacked_dir.rglob("*.rels"))
|
||||
|
||||
if not rels_files:
|
||||
if self.verbose:
|
||||
print("PASSED - No .rels files found")
|
||||
return True
|
||||
|
||||
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")
|
||||
):
|
||||
all_files.append(file_path.resolve())
|
||||
|
||||
all_referenced_files = set()
|
||||
|
||||
if self.verbose:
|
||||
print(
|
||||
f"Found {len(rels_files)} .rels files and {len(all_files)} target files"
|
||||
)
|
||||
|
||||
for rels_file in rels_files:
|
||||
try:
|
||||
rels_root = lxml.etree.parse(str(rels_file)).getroot()
|
||||
|
||||
rels_dir = rels_file.parent
|
||||
|
||||
referenced_files = set()
|
||||
broken_refs = []
|
||||
|
||||
for rel in rels_root.findall(
|
||||
".//ns:Relationship",
|
||||
namespaces={"ns": self.PACKAGE_RELATIONSHIPS_NAMESPACE},
|
||||
):
|
||||
target = rel.get("Target")
|
||||
if rel.get("TargetMode") == "External":
|
||||
continue
|
||||
if target and not target.startswith(
|
||||
("http", "mailto:")
|
||||
):
|
||||
if target.startswith("/"):
|
||||
target_path = self.unpacked_dir / target.lstrip("/")
|
||||
elif rels_file.name == ".rels":
|
||||
target_path = self.unpacked_dir / target
|
||||
else:
|
||||
base_dir = rels_dir.parent
|
||||
target_path = base_dir / target
|
||||
|
||||
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))
|
||||
|
||||
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}")
|
||||
|
||||
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):
|
||||
import lxml.etree
|
||||
|
||||
errors = []
|
||||
|
||||
for xml_file in self.xml_files:
|
||||
if xml_file.suffix == ".rels":
|
||||
continue
|
||||
|
||||
rels_dir = xml_file.parent / "_rels"
|
||||
rels_file = rels_dir / f"{xml_file.name}.rels"
|
||||
|
||||
if not rels_file.exists():
|
||||
continue
|
||||
|
||||
try:
|
||||
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:
|
||||
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)"
|
||||
)
|
||||
type_name = (
|
||||
rel_type.split("/")[-1] if "/" in rel_type else rel_type
|
||||
)
|
||||
rid_to_type[rid] = type_name
|
||||
|
||||
xml_root = lxml.etree.parse(str(xml_file)).getroot()
|
||||
|
||||
r_ns = self.OFFICE_RELATIONSHIPS_NAMESPACE
|
||||
rid_attrs_to_check = ["id", "embed", "link"]
|
||||
for elem in xml_root.iter():
|
||||
if not hasattr(elem, "tag") or callable(elem.tag):
|
||||
continue
|
||||
for attr_name in rid_attrs_to_check:
|
||||
rid_attr = elem.get(f"{{{r_ns}}}{attr_name}")
|
||||
if not rid_attr:
|
||||
continue
|
||||
xml_rel_path = xml_file.relative_to(self.unpacked_dir)
|
||||
elem_name = (
|
||||
elem.tag.split("}")[-1] if "}" in elem.tag else elem.tag
|
||||
)
|
||||
|
||||
if rid_attr not in rid_to_type:
|
||||
errors.append(
|
||||
f" {xml_rel_path}: Line {elem.sourceline}: "
|
||||
f"<{elem_name}> r:{attr_name} references non-existent relationship '{rid_attr}' "
|
||||
f"(valid IDs: {', '.join(sorted(rid_to_type.keys())[:5])}{'...' if len(rid_to_type) > 5 else ''})"
|
||||
)
|
||||
elif attr_name == "id" and self.ELEMENT_RELATIONSHIP_TYPES:
|
||||
expected_type = self._get_expected_relationship_type(
|
||||
elem_name
|
||||
)
|
||||
if expected_type:
|
||||
actual_type = rid_to_type[rid_attr]
|
||||
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):
|
||||
elem_lower = element_name.lower()
|
||||
|
||||
if elem_lower in self.ELEMENT_RELATIONSHIP_TYPES:
|
||||
return self.ELEMENT_RELATIONSHIP_TYPES[elem_lower]
|
||||
|
||||
if elem_lower.endswith("id") and len(elem_lower) > 2:
|
||||
prefix = elem_lower[:-2]
|
||||
if prefix.endswith("master"):
|
||||
return prefix.lower()
|
||||
elif prefix.endswith("layout"):
|
||||
return prefix.lower()
|
||||
else:
|
||||
if prefix == "sld":
|
||||
return "slide"
|
||||
return prefix.lower()
|
||||
|
||||
if elem_lower.endswith("reference") and len(elem_lower) > 9:
|
||||
prefix = elem_lower[:-9]
|
||||
return prefix.lower()
|
||||
|
||||
return None
|
||||
|
||||
def validate_content_types(self):
|
||||
errors = []
|
||||
|
||||
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:
|
||||
root = lxml.etree.parse(str(content_types_file)).getroot()
|
||||
declared_parts = set()
|
||||
declared_extensions = set()
|
||||
|
||||
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("/"))
|
||||
|
||||
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())
|
||||
|
||||
declarable_roots = {
|
||||
"sld",
|
||||
"sldLayout",
|
||||
"sldMaster",
|
||||
"presentation",
|
||||
"document",
|
||||
"workbook",
|
||||
"worksheet",
|
||||
"theme",
|
||||
}
|
||||
|
||||
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",
|
||||
}
|
||||
|
||||
all_files = list(self.unpacked_dir.rglob("*"))
|
||||
all_files = [f for f in all_files if f.is_file()]
|
||||
|
||||
for xml_file in self.xml_files:
|
||||
path_str = str(xml_file.relative_to(self.unpacked_dir)).replace(
|
||||
"\\", "/"
|
||||
)
|
||||
|
||||
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
|
||||
|
||||
for file_path in all_files:
|
||||
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:
|
||||
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):
|
||||
xml_file = Path(xml_file).resolve()
|
||||
unpacked_dir = self.unpacked_dir.resolve()
|
||||
|
||||
is_valid, current_errors = self._validate_single_file_xsd(
|
||||
xml_file, unpacked_dir
|
||||
)
|
||||
|
||||
if is_valid is None:
|
||||
return None, set()
|
||||
elif is_valid:
|
||||
return True, set()
|
||||
|
||||
original_errors = self._get_original_file_errors(xml_file)
|
||||
|
||||
assert current_errors is not None
|
||||
new_errors = current_errors - original_errors
|
||||
|
||||
new_errors = {
|
||||
e for e in new_errors
|
||||
if not any(pattern in e for pattern in self.IGNORED_VALIDATION_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:
|
||||
if verbose:
|
||||
print(
|
||||
f"PASSED - No new errors (original had {len(current_errors)} errors)"
|
||||
)
|
||||
return True, set()
|
||||
|
||||
def validate_against_xsd(self):
|
||||
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:
|
||||
original_error_count += 1
|
||||
valid_count += 1
|
||||
continue
|
||||
|
||||
new_errors.append(f" {relative_path}: {len(new_file_errors)} new error(s)")
|
||||
for error in list(new_file_errors)[:3]:
|
||||
new_errors.append(
|
||||
f" - {error[:250]}..." if len(error) > 250 else f" - {error}"
|
||||
)
|
||||
|
||||
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):
|
||||
if xml_file.name in self.SCHEMA_MAPPINGS:
|
||||
return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.name]
|
||||
|
||||
if xml_file.suffix == ".rels":
|
||||
return self.schemas_dir / self.SCHEMA_MAPPINGS[".rels"]
|
||||
|
||||
if "charts/" in str(xml_file) and xml_file.name.startswith("chart"):
|
||||
return self.schemas_dir / self.SCHEMA_MAPPINGS["chart"]
|
||||
|
||||
if "theme/" in str(xml_file) and xml_file.name.startswith("theme"):
|
||||
return self.schemas_dir / self.SCHEMA_MAPPINGS["theme"]
|
||||
|
||||
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):
|
||||
xml_string = lxml.etree.tostring(xml_doc, encoding="unicode")
|
||||
xml_copy = lxml.etree.fromstring(xml_string)
|
||||
|
||||
for elem in xml_copy.iter():
|
||||
attrs_to_remove = []
|
||||
|
||||
for attr in elem.attrib:
|
||||
if "{" in attr:
|
||||
ns = attr.split("}")[0][1:]
|
||||
if ns not in self.OOXML_NAMESPACES:
|
||||
attrs_to_remove.append(attr)
|
||||
|
||||
for attr in attrs_to_remove:
|
||||
del elem.attrib[attr]
|
||||
|
||||
self._remove_ignorable_elements(xml_copy)
|
||||
|
||||
return lxml.etree.ElementTree(xml_copy)
|
||||
|
||||
def _remove_ignorable_elements(self, root):
|
||||
elements_to_remove = []
|
||||
|
||||
for elem in list(root):
|
||||
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
|
||||
|
||||
self._remove_ignorable_elements(elem)
|
||||
|
||||
for elem in elements_to_remove:
|
||||
root.remove(elem)
|
||||
|
||||
def _preprocess_for_mc_ignorable(self, xml_doc):
|
||||
root = xml_doc.getroot()
|
||||
|
||||
if f"{{{self.MC_NAMESPACE}}}Ignorable" in root.attrib:
|
||||
del root.attrib[f"{{{self.MC_NAMESPACE}}}Ignorable"]
|
||||
|
||||
return xml_doc
|
||||
|
||||
def _preprocess_for_schema(self, xml_doc, relative_path):
|
||||
return xml_doc
|
||||
|
||||
def _validate_single_file_xsd(self, xml_file, base_path, schema_path=None):
|
||||
schema_path = schema_path or self._get_schema_path(xml_file)
|
||||
if not schema_path:
|
||||
return None, None
|
||||
|
||||
try:
|
||||
schema = _load_schema(str(schema_path))
|
||||
|
||||
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)
|
||||
|
||||
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)
|
||||
|
||||
xml_doc = self._preprocess_for_schema(xml_doc, relative_path)
|
||||
|
||||
if schema.validate(xml_doc):
|
||||
return True, set()
|
||||
else:
|
||||
errors = set()
|
||||
for error in schema.error_log:
|
||||
errors.add(error.message)
|
||||
return False, errors
|
||||
|
||||
except Exception as e:
|
||||
return False, {str(e)}
|
||||
|
||||
def _get_original_file_errors(self, xml_file, schema_path=None):
|
||||
if self.original_file is None:
|
||||
return set()
|
||||
|
||||
import tempfile
|
||||
import zipfile
|
||||
|
||||
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)
|
||||
|
||||
try:
|
||||
with zipfile.ZipFile(self.original_file, "r") as zip_ref:
|
||||
safe_extract(zip_ref, temp_path)
|
||||
except (zipfile.BadZipFile, ValueError, OSError):
|
||||
return set()
|
||||
|
||||
original_xml_file = temp_path / relative_path
|
||||
|
||||
if not original_xml_file.exists():
|
||||
return set()
|
||||
|
||||
is_valid, errors = self._validate_single_file_xsd(
|
||||
original_xml_file, temp_path, schema_path=schema_path
|
||||
)
|
||||
return errors if errors else set()
|
||||
|
||||
def _remove_template_tags_from_text_nodes(self, xml_doc):
|
||||
warnings = []
|
||||
template_pattern = re.compile(r"\{\{[^}]*\}\}")
|
||||
|
||||
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
|
||||
|
||||
for elem in xml_copy.iter():
|
||||
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.")
|
||||
466
.agents/skills/docx/scripts/office/validators/docx.py
Normal file
466
.agents/skills/docx/scripts/office/validators/docx.py
Normal file
@@ -0,0 +1,466 @@
|
||||
"""
|
||||
Validator for Word document XML files against XSD schemas.
|
||||
"""
|
||||
|
||||
import random
|
||||
import re
|
||||
import tempfile
|
||||
import zipfile
|
||||
from pathlib import Path
|
||||
|
||||
import defusedxml.minidom
|
||||
import lxml.etree
|
||||
|
||||
from helpers import safe_extract
|
||||
|
||||
from .base import BaseSchemaValidator
|
||||
|
||||
|
||||
class DOCXSchemaValidator(BaseSchemaValidator):
|
||||
|
||||
WORD_2006_NAMESPACE = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
|
||||
W14_NAMESPACE = "http://schemas.microsoft.com/office/word/2010/wordml"
|
||||
W16CID_NAMESPACE = "http://schemas.microsoft.com/office/word/2016/wordml/cid"
|
||||
|
||||
ELEMENT_RELATIONSHIP_TYPES = {}
|
||||
|
||||
def validate(self):
|
||||
if not self.validate_xml():
|
||||
return False
|
||||
|
||||
all_valid = True
|
||||
if not self.validate_namespaces():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_unique_ids():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_file_references():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_content_types():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_against_xsd():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_whitespace_preservation():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_deletions():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_insertions():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_all_relationship_ids():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_id_constraints():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_comment_markers():
|
||||
all_valid = False
|
||||
|
||||
self.compare_paragraph_counts()
|
||||
|
||||
return all_valid
|
||||
|
||||
def validate_whitespace_preservation(self):
|
||||
errors = []
|
||||
|
||||
for xml_file in self.xml_files:
|
||||
if xml_file.name != "document.xml":
|
||||
continue
|
||||
|
||||
try:
|
||||
root = lxml.etree.parse(str(xml_file)).getroot()
|
||||
|
||||
for elem in root.iter(f"{{{self.WORD_2006_NAMESPACE}}}t"):
|
||||
if elem.text:
|
||||
text = elem.text
|
||||
if re.search(r"^[ \t\n\r]", text) or re.search(
|
||||
r"[ \t\n\r]$", text
|
||||
):
|
||||
xml_space_attr = f"{{{self.XML_NAMESPACE}}}space"
|
||||
if (
|
||||
xml_space_attr not in elem.attrib
|
||||
or elem.attrib[xml_space_attr] != "preserve"
|
||||
):
|
||||
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):
|
||||
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}
|
||||
|
||||
for t_elem in root.xpath(".//w:del//w:t", namespaces=namespaces):
|
||||
if t_elem.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}"
|
||||
)
|
||||
|
||||
for instr_elem in root.xpath(
|
||||
".//w:del//w:instrText", namespaces=namespaces
|
||||
):
|
||||
text_preview = (
|
||||
repr(instr_elem.text or "")[:50] + "..."
|
||||
if len(repr(instr_elem.text or "")) > 50
|
||||
else repr(instr_elem.text or "")
|
||||
)
|
||||
errors.append(
|
||||
f" {xml_file.relative_to(self.unpacked_dir)}: "
|
||||
f"Line {instr_elem.sourceline}: <w:instrText> found within <w:del> (use <w:delInstrText>): {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 = 0
|
||||
|
||||
for xml_file in self.xml_files:
|
||||
if xml_file.name != "document.xml":
|
||||
continue
|
||||
|
||||
try:
|
||||
root = lxml.etree.parse(str(xml_file)).getroot()
|
||||
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):
|
||||
original = self.original_file
|
||||
if original is None:
|
||||
return 0
|
||||
|
||||
count = 0
|
||||
|
||||
try:
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
with zipfile.ZipFile(original, "r") as zip_ref:
|
||||
safe_extract(zip_ref, Path(temp_dir))
|
||||
|
||||
doc_xml_path = temp_dir + "/word/document.xml"
|
||||
root = lxml.etree.parse(doc_xml_path).getroot()
|
||||
|
||||
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):
|
||||
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}
|
||||
|
||||
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):
|
||||
new_count = self.count_paragraphs_in_unpacked()
|
||||
if self.original_file is None:
|
||||
print(f"\nParagraphs: {new_count}")
|
||||
return
|
||||
|
||||
original_count = self.count_paragraphs_in_original()
|
||||
diff = new_count - original_count
|
||||
diff_str = f"+{diff}" if diff > 0 else str(diff)
|
||||
print(f"\nParagraphs: {original_count} → {new_count} ({diff_str})")
|
||||
|
||||
def _parse_id_value(self, val: str, base: int = 16) -> int:
|
||||
return int(val, base)
|
||||
|
||||
def validate_id_constraints(self):
|
||||
errors = []
|
||||
para_id_attr = f"{{{self.W14_NAMESPACE}}}paraId"
|
||||
durable_id_attr = f"{{{self.W16CID_NAMESPACE}}}durableId"
|
||||
|
||||
for xml_file in self.xml_files:
|
||||
try:
|
||||
for elem in lxml.etree.parse(str(xml_file)).iter():
|
||||
if val := elem.get(para_id_attr):
|
||||
try:
|
||||
if self._parse_id_value(val, base=16) >= 0x80000000:
|
||||
errors.append(
|
||||
f" {xml_file.name}:{elem.sourceline}: paraId={val} >= 0x80000000"
|
||||
)
|
||||
except ValueError:
|
||||
errors.append(
|
||||
f" {xml_file.name}:{elem.sourceline}: "
|
||||
f"paraId={val} is not valid hex"
|
||||
)
|
||||
|
||||
if val := elem.get(durable_id_attr):
|
||||
if xml_file.name == "numbering.xml":
|
||||
try:
|
||||
if self._parse_id_value(val, base=10) >= 0x7FFFFFFF:
|
||||
errors.append(
|
||||
f" {xml_file.name}:{elem.sourceline}: "
|
||||
f"durableId={val} >= 0x7FFFFFFF"
|
||||
)
|
||||
except ValueError:
|
||||
errors.append(
|
||||
f" {xml_file.name}:{elem.sourceline}: "
|
||||
f"durableId={val} must be decimal in numbering.xml"
|
||||
)
|
||||
else:
|
||||
try:
|
||||
if self._parse_id_value(val, base=16) >= 0x7FFFFFFF:
|
||||
errors.append(
|
||||
f" {xml_file.name}:{elem.sourceline}: "
|
||||
f"durableId={val} >= 0x7FFFFFFF"
|
||||
)
|
||||
except ValueError:
|
||||
errors.append(
|
||||
f" {xml_file.name}:{elem.sourceline}: "
|
||||
f"durableId={val} is not valid hex"
|
||||
)
|
||||
except lxml.etree.XMLSyntaxError:
|
||||
continue
|
||||
|
||||
if errors:
|
||||
print(f"FAILED - {len(errors)} ID constraint violations:")
|
||||
for e in errors:
|
||||
print(e)
|
||||
elif self.verbose:
|
||||
print("PASSED - All paraId/durableId values within constraints")
|
||||
return not errors
|
||||
|
||||
def validate_comment_markers(self):
|
||||
errors = []
|
||||
|
||||
document_xml = None
|
||||
comments_xml = None
|
||||
for xml_file in self.xml_files:
|
||||
if xml_file.name == "document.xml" and "word" in str(xml_file):
|
||||
document_xml = xml_file
|
||||
elif xml_file.name == "comments.xml":
|
||||
comments_xml = xml_file
|
||||
|
||||
if not document_xml:
|
||||
if self.verbose:
|
||||
print("PASSED - No document.xml found (skipping comment validation)")
|
||||
return True
|
||||
|
||||
try:
|
||||
doc_root = lxml.etree.parse(str(document_xml)).getroot()
|
||||
namespaces = {"w": self.WORD_2006_NAMESPACE}
|
||||
|
||||
range_starts = {
|
||||
elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id")
|
||||
for elem in doc_root.xpath(
|
||||
".//w:commentRangeStart", namespaces=namespaces
|
||||
)
|
||||
}
|
||||
range_ends = {
|
||||
elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id")
|
||||
for elem in doc_root.xpath(
|
||||
".//w:commentRangeEnd", namespaces=namespaces
|
||||
)
|
||||
}
|
||||
references = {
|
||||
elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id")
|
||||
for elem in doc_root.xpath(
|
||||
".//w:commentReference", namespaces=namespaces
|
||||
)
|
||||
}
|
||||
|
||||
orphaned_ends = range_ends - range_starts
|
||||
for comment_id in sorted(
|
||||
orphaned_ends, key=lambda x: int(x) if x and x.isdigit() else 0
|
||||
):
|
||||
errors.append(
|
||||
f' document.xml: commentRangeEnd id="{comment_id}" has no matching commentRangeStart'
|
||||
)
|
||||
|
||||
orphaned_starts = range_starts - range_ends
|
||||
for comment_id in sorted(
|
||||
orphaned_starts, key=lambda x: int(x) if x and x.isdigit() else 0
|
||||
):
|
||||
errors.append(
|
||||
f' document.xml: commentRangeStart id="{comment_id}" has no matching commentRangeEnd'
|
||||
)
|
||||
|
||||
comment_ids = set()
|
||||
if comments_xml and comments_xml.exists():
|
||||
comments_root = lxml.etree.parse(str(comments_xml)).getroot()
|
||||
comment_ids = {
|
||||
elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id")
|
||||
for elem in comments_root.xpath(
|
||||
".//w:comment", namespaces=namespaces
|
||||
)
|
||||
}
|
||||
|
||||
marker_ids = range_starts | range_ends | references
|
||||
invalid_refs = marker_ids - comment_ids
|
||||
for comment_id in sorted(
|
||||
invalid_refs, key=lambda x: int(x) if x and x.isdigit() else 0
|
||||
):
|
||||
if comment_id:
|
||||
errors.append(
|
||||
f' document.xml: marker id="{comment_id}" references non-existent comment'
|
||||
)
|
||||
|
||||
except (lxml.etree.XMLSyntaxError, Exception) as e:
|
||||
errors.append(f" Error parsing XML: {e}")
|
||||
|
||||
if errors:
|
||||
print(f"FAILED - {len(errors)} comment marker violations:")
|
||||
for error in errors:
|
||||
print(error)
|
||||
return False
|
||||
else:
|
||||
if self.verbose:
|
||||
print("PASSED - All comment markers properly paired")
|
||||
return True
|
||||
|
||||
def repair(self) -> int:
|
||||
repairs = super().repair()
|
||||
repairs += self.repair_durableId()
|
||||
return repairs
|
||||
|
||||
def repair_durableId(self) -> int:
|
||||
DURABLE_ID_ATTRS = ("w16cid:durableId", "w16cex:durableId")
|
||||
repairs = 0
|
||||
renames: dict = {}
|
||||
|
||||
for xml_file in self.xml_files:
|
||||
try:
|
||||
content = xml_file.read_text(encoding="utf-8")
|
||||
dom = defusedxml.minidom.parseString(content)
|
||||
is_numbering = xml_file.name == "numbering.xml"
|
||||
base = 10 if is_numbering else 16
|
||||
pending = []
|
||||
seen_in_file = set()
|
||||
modified = False
|
||||
|
||||
for elem in dom.getElementsByTagName("*"):
|
||||
for attr_name in DURABLE_ID_ATTRS:
|
||||
if not elem.hasAttribute(attr_name):
|
||||
continue
|
||||
|
||||
durable_id = elem.getAttribute(attr_name)
|
||||
try:
|
||||
key = self._parse_id_value(durable_id, base=base)
|
||||
needs_repair = key >= 0x7FFFFFFF
|
||||
except ValueError:
|
||||
key = durable_id
|
||||
needs_repair = True
|
||||
|
||||
if needs_repair:
|
||||
if key in seen_in_file:
|
||||
value = random.randint(1, 0x7FFFFFFE)
|
||||
else:
|
||||
seen_in_file.add(key)
|
||||
if key not in renames:
|
||||
renames[key] = random.randint(1, 0x7FFFFFFE)
|
||||
value = renames[key]
|
||||
new_id = str(value) if is_numbering else f"{value:08X}"
|
||||
|
||||
elem.setAttribute(attr_name, new_id)
|
||||
pending.append(
|
||||
f" Repaired: {xml_file.name}: durableId {durable_id} → {new_id}"
|
||||
)
|
||||
modified = True
|
||||
|
||||
if modified:
|
||||
xml_file.write_bytes(dom.toxml(encoding="UTF-8"))
|
||||
for message in pending:
|
||||
print(message)
|
||||
repairs += len(pending)
|
||||
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return repairs
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise RuntimeError("This module should not be run directly.")
|
||||
441
.agents/skills/docx/scripts/office/validators/pptx.py
Normal file
441
.agents/skills/docx/scripts/office/validators/pptx.py
Normal file
@@ -0,0 +1,441 @@
|
||||
"""
|
||||
Validator for PowerPoint presentation XML files against XSD schemas.
|
||||
"""
|
||||
|
||||
import re
|
||||
from pathlib import Path
|
||||
|
||||
from helpers import opc_target, rels_source_part, safe_extract
|
||||
|
||||
from .base import BaseSchemaValidator
|
||||
|
||||
|
||||
class PPTXSchemaValidator(BaseSchemaValidator):
|
||||
|
||||
PRESENTATIONML_NAMESPACE = (
|
||||
"http://schemas.openxmlformats.org/presentationml/2006/main"
|
||||
)
|
||||
|
||||
ELEMENT_RELATIONSHIP_TYPES = {
|
||||
"sldid": "slide",
|
||||
"sldmasterid": "slidemaster",
|
||||
"notesmasterid": "notesmaster",
|
||||
"sldlayoutid": "slidelayout",
|
||||
"themeid": "theme",
|
||||
"tablestyleid": "tablestyles",
|
||||
}
|
||||
|
||||
def validate(self):
|
||||
if not self.validate_xml():
|
||||
return False
|
||||
|
||||
all_valid = True
|
||||
if not self.validate_namespaces():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_unique_ids():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_uuid_ids():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_file_references():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_slide_layout_ids():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_content_types():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_against_xsd():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_notes_slide_references():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_all_relationship_ids():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_no_duplicate_slide_layouts():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_master_theme_uniqueness():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_charts():
|
||||
all_valid = False
|
||||
|
||||
if not self.validate_slides():
|
||||
all_valid = False
|
||||
|
||||
return all_valid
|
||||
|
||||
def _package_map(self) -> dict:
|
||||
wanted = []
|
||||
wanted += list(self.unpacked_dir.glob("[[]Content_Types[]].xml"))
|
||||
wanted += list(self.unpacked_dir.glob("ppt/presentation.xml"))
|
||||
wanted += list(self.unpacked_dir.glob("ppt/theme/*.xml"))
|
||||
wanted += list(self.unpacked_dir.glob("ppt/theme/_rels/*.rels"))
|
||||
wanted += list(self.unpacked_dir.glob("ppt/charts/chart*.xml"))
|
||||
for group in ("slideMasters", "notesMasters", "handoutMasters"):
|
||||
wanted += list(self.unpacked_dir.glob(f"ppt/{group}/*.xml"))
|
||||
wanted += list(self.unpacked_dir.glob(f"ppt/{group}/_rels/*.rels"))
|
||||
return {
|
||||
p.relative_to(self.unpacked_dir).as_posix(): p.read_bytes()
|
||||
for p in wanted
|
||||
if p.is_file()
|
||||
}
|
||||
|
||||
def validate_master_theme_uniqueness(self):
|
||||
from helpers.pptx_theme import _NOTES_MASTERS, live_shared_master_themes
|
||||
|
||||
shared = live_shared_master_themes(self._package_map())
|
||||
if shared:
|
||||
print(f"FAILED - Found {len(shared)} master(s) sharing a theme part:")
|
||||
for message in shared:
|
||||
print(f" {message}")
|
||||
if any(m.startswith(_NOTES_MASTERS) for m in shared):
|
||||
print(" Fix: in ppt/presentation.xml, move <p:notesMasterIdLst> back to "
|
||||
"directly after <p:sldIdLst>. PowerPoint reads that happily.")
|
||||
else:
|
||||
print(" Fix: give each master its own theme part.")
|
||||
return False
|
||||
|
||||
if self.verbose:
|
||||
print("PASSED - No master shares a theme part in a way PowerPoint refuses")
|
||||
return True
|
||||
|
||||
def validate_charts(self):
|
||||
from helpers.pptx_chart import find_chart_problems
|
||||
|
||||
problems = find_chart_problems(self._package_map())
|
||||
if problems:
|
||||
print(f"FAILED - Found {len(problems)} chart problem(s) PowerPoint rejects:")
|
||||
for message in problems:
|
||||
print(f" {message}")
|
||||
return False
|
||||
|
||||
if self.verbose:
|
||||
print("PASSED - Charts satisfy the constraints PowerPoint enforces")
|
||||
return True
|
||||
|
||||
def _original_slide_defects(self, schema) -> set[str]:
|
||||
import tempfile
|
||||
import zipfile
|
||||
|
||||
from helpers.pptx_slide import SLIDE_PART_RE, fatal_slide_errors
|
||||
|
||||
if self.original_file is None:
|
||||
return set()
|
||||
|
||||
found: set[str] = set()
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
temp_path = Path(temp_dir)
|
||||
try:
|
||||
with zipfile.ZipFile(self.original_file, "r") as zf:
|
||||
safe_extract(zf, temp_path)
|
||||
except (zipfile.BadZipFile, ValueError, OSError):
|
||||
return set()
|
||||
|
||||
for part in sorted(temp_path.rglob("*.xml")):
|
||||
relative = part.relative_to(temp_path).as_posix()
|
||||
if not SLIDE_PART_RE.fullmatch(relative):
|
||||
continue
|
||||
ok, errors = self._validate_single_file_xsd(
|
||||
part.resolve(), temp_path.resolve(), schema_path=schema
|
||||
)
|
||||
if ok is None or ok or not errors:
|
||||
continue
|
||||
found |= set(fatal_slide_errors(set(errors)))
|
||||
return found
|
||||
|
||||
def validate_slides(self):
|
||||
from helpers.pptx_slide import (
|
||||
SLIDE_PART_RE,
|
||||
fatal_slide_errors,
|
||||
is_schema_verdict,
|
||||
)
|
||||
|
||||
schema = self.schemas_dir / self.SCHEMA_MAPPINGS["ppt"]
|
||||
inherited = self._original_slide_defects(schema)
|
||||
problems: list[str] = []
|
||||
broken: list[str] = []
|
||||
|
||||
for xml_file in self.xml_files:
|
||||
relative = xml_file.relative_to(self.unpacked_dir).as_posix()
|
||||
if not SLIDE_PART_RE.fullmatch(relative):
|
||||
continue
|
||||
ok, errors = self._validate_single_file_xsd(
|
||||
xml_file.resolve(), self.unpacked_dir.resolve(), schema_path=schema
|
||||
)
|
||||
if ok is None or not errors:
|
||||
continue
|
||||
|
||||
unreadable = [f"{relative}: {e}" for e in errors if not is_schema_verdict(e)]
|
||||
if unreadable:
|
||||
broken.extend(unreadable)
|
||||
continue
|
||||
if ok:
|
||||
continue
|
||||
|
||||
for message in fatal_slide_errors(set(errors)):
|
||||
if message in inherited:
|
||||
continue
|
||||
problems.append(f"{relative}: {message}")
|
||||
|
||||
if broken:
|
||||
print(f"FAILED - Could not check {len(broken)} slide part(s):")
|
||||
for message in sorted(broken):
|
||||
print(f" {message[:240]}")
|
||||
|
||||
if problems:
|
||||
print(f"FAILED - Found {len(problems)} slide problem(s) PowerPoint rejects:")
|
||||
for message in sorted(problems):
|
||||
print(f" {message[:240]}")
|
||||
|
||||
if broken or problems:
|
||||
return False
|
||||
|
||||
if self.verbose:
|
||||
print("PASSED - Slide XML has none of the defects PowerPoint refuses")
|
||||
return True
|
||||
|
||||
def _get_schema_path(self, xml_file):
|
||||
if xml_file.parent.name == "charts" and xml_file.name.startswith("chart"):
|
||||
return None
|
||||
return super()._get_schema_path(xml_file)
|
||||
|
||||
def _preprocess_for_schema(self, xml_doc, relative_path):
|
||||
if relative_path.as_posix() != "ppt/presentation.xml":
|
||||
return xml_doc
|
||||
|
||||
root = xml_doc.getroot()
|
||||
ns = f"{{{self.PRESENTATIONML_NAMESPACE}}}"
|
||||
notes = root.find(f"{ns}notesMasterIdLst")
|
||||
slides = root.find(f"{ns}sldIdLst")
|
||||
if notes is None or slides is None:
|
||||
return xml_doc
|
||||
|
||||
children = list(root)
|
||||
if children.index(notes) < children.index(slides):
|
||||
return xml_doc
|
||||
|
||||
root.remove(notes)
|
||||
root.insert(list(root).index(slides), notes)
|
||||
return xml_doc
|
||||
|
||||
def validate_uuid_ids(self):
|
||||
import lxml.etree
|
||||
|
||||
errors = []
|
||||
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()
|
||||
|
||||
for elem in root.iter():
|
||||
for attr, value in elem.attrib.items():
|
||||
attr_name = attr.split("}")[-1].lower()
|
||||
if attr_name == "id" or attr_name.endswith("id"):
|
||||
if self._looks_like_uuid(value):
|
||||
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):
|
||||
clean_value = value.strip("{}()").replace("-", "")
|
||||
return len(clean_value) == 32 and all(c.isalnum() for c in clean_value)
|
||||
|
||||
def validate_slide_layout_ids(self):
|
||||
import lxml.etree
|
||||
|
||||
errors = []
|
||||
|
||||
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:
|
||||
root = lxml.etree.parse(str(slide_master)).getroot()
|
||||
|
||||
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
|
||||
|
||||
rels_root = lxml.etree.parse(str(rels_file)).getroot()
|
||||
|
||||
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"))
|
||||
|
||||
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):
|
||||
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()
|
||||
|
||||
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):
|
||||
import lxml.etree
|
||||
|
||||
errors = []
|
||||
notes_slide_references = {}
|
||||
|
||||
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:
|
||||
root = lxml.etree.parse(str(rels_file)).getroot()
|
||||
|
||||
for rel in root.findall(
|
||||
f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship"
|
||||
):
|
||||
rel_type = rel.get("Type", "")
|
||||
if "notesSlide" in rel_type:
|
||||
part = opc_target(
|
||||
rel.get("Target", ""),
|
||||
rels_source_part(rels_file, self.unpacked_dir),
|
||||
rel.get("TargetMode", ""),
|
||||
)
|
||||
if part:
|
||||
slide_name = rels_file.stem.replace(
|
||||
".xml", ""
|
||||
)
|
||||
|
||||
notes_slide_references.setdefault(part, []).append(
|
||||
(slide_name, rels_file)
|
||||
)
|
||||
|
||||
except (lxml.etree.XMLSyntaxError, Exception) as e:
|
||||
errors.append(
|
||||
f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}"
|
||||
)
|
||||
|
||||
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.")
|
||||
299
.agents/skills/docx/scripts/office/validators/redlining.py
Normal file
299
.agents/skills/docx/scripts/office/validators/redlining.py
Normal file
@@ -0,0 +1,299 @@
|
||||
"""
|
||||
Validator for tracked changes in Word documents.
|
||||
|
||||
Detects untracked edits in word/document.xml: text that differs from the
|
||||
original without a <w:ins>/<w:del> wrapper recording it. The tracked changes
|
||||
that are new relative to the original are undone, and the result is compared
|
||||
against the original; whatever text still differs was edited without being
|
||||
tracked.
|
||||
|
||||
Only the document body is compared. Headers, footers, footnotes and endnotes
|
||||
are separate parts and are not checked.
|
||||
"""
|
||||
|
||||
import subprocess
|
||||
import tempfile
|
||||
import zipfile
|
||||
from pathlib import Path
|
||||
|
||||
import defusedxml.ElementTree as ET
|
||||
from defusedxml.common import DefusedXmlException
|
||||
|
||||
from helpers import rendered_text, safe_extract
|
||||
|
||||
|
||||
class RedliningValidator:
|
||||
|
||||
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 repair(self) -> int:
|
||||
return 0
|
||||
|
||||
def validate(self):
|
||||
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
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
temp_path = Path(temp_dir)
|
||||
|
||||
try:
|
||||
with zipfile.ZipFile(self.original_docx, "r") as zip_ref:
|
||||
safe_extract(zip_ref, 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
|
||||
|
||||
try:
|
||||
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, DefusedXmlException) as e:
|
||||
print(f"FAILED - Error parsing XML files: {e}")
|
||||
return False
|
||||
|
||||
new_changes = self._new_tracked_changes(original_root, modified_root)
|
||||
self._remove_tracked_changes(modified_root, new_changes)
|
||||
|
||||
modified_text = self._extract_text_content(modified_root)
|
||||
original_text = self._extract_text_content(original_root)
|
||||
|
||||
if modified_text != original_text:
|
||||
error_message = self._generate_detailed_diff(
|
||||
original_text, modified_text
|
||||
)
|
||||
print(error_message)
|
||||
return False
|
||||
|
||||
if self.verbose:
|
||||
print(
|
||||
f"PASSED - All {len(new_changes)} change(s) against the original "
|
||||
"are properly tracked"
|
||||
)
|
||||
return True
|
||||
|
||||
def _tracked_change_elements(self, root):
|
||||
ins_tag = f"{{{self.namespaces['w']}}}ins"
|
||||
del_tag = f"{{{self.namespaces['w']}}}del"
|
||||
return [elem for elem in root.iter() if elem.tag in (ins_tag, del_tag)]
|
||||
|
||||
def _rendered_text(self, elem):
|
||||
preserve = elem.get("{http://www.w3.org/XML/1998/namespace}space") == "preserve"
|
||||
return rendered_text(elem.text or "", preserve)
|
||||
|
||||
def _text_elements(self, elem):
|
||||
w = self.namespaces["w"]
|
||||
return [
|
||||
node
|
||||
for node in elem.iter()
|
||||
if node.tag in (f"{{{w}}}t", f"{{{w}}}delText")
|
||||
]
|
||||
|
||||
def _tracked_change_key(self, elem):
|
||||
w = self.namespaces["w"]
|
||||
text = "".join(self._rendered_text(node) for node in self._text_elements(elem))
|
||||
return (elem.tag, elem.get(f"{{{w}}}author"), elem.get(f"{{{w}}}date"), text)
|
||||
|
||||
def _new_tracked_changes(self, original_root, modified_root):
|
||||
original = self._tracked_change_elements(original_root)
|
||||
modified = self._tracked_change_elements(modified_root)
|
||||
|
||||
pool = {}
|
||||
for elem in original:
|
||||
pool.setdefault(self._tracked_change_key(elem), []).append(elem)
|
||||
|
||||
matched, leftover = set(), []
|
||||
for elem in modified:
|
||||
bucket = pool.get(self._tracked_change_key(elem))
|
||||
if bucket:
|
||||
matched.add(bucket.pop())
|
||||
else:
|
||||
leftover.append(elem)
|
||||
|
||||
def group(elem):
|
||||
return self._tracked_change_key(elem)[:3]
|
||||
|
||||
def text_of(elems):
|
||||
return "".join(self._tracked_change_key(e)[3] for e in elems)
|
||||
|
||||
unmatched_original = {}
|
||||
for elem in original:
|
||||
if elem not in matched:
|
||||
unmatched_original.setdefault(group(elem), []).append(elem)
|
||||
|
||||
by_group = {}
|
||||
for elem in leftover:
|
||||
by_group.setdefault(group(elem), []).append(elem)
|
||||
|
||||
new = set()
|
||||
for key, elems in by_group.items():
|
||||
rebuilt = text_of(elems)
|
||||
if rebuilt and rebuilt == text_of(unmatched_original.get(key, [])):
|
||||
continue
|
||||
new.update(elems)
|
||||
return new
|
||||
|
||||
def _generate_detailed_diff(self, original_text, modified_text):
|
||||
error_parts = [
|
||||
"FAILED - Document text doesn't match after removing the 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",
|
||||
" 4. Rewrote another author's <w:ins>/<w:del> and changed its text on",
|
||||
" the way. A tracked change from the original is recognised by its",
|
||||
" author, date and text; anything that doesn't reproduce one exactly",
|
||||
" reads as new, and the text it carried is reported missing.",
|
||||
"",
|
||||
"For pre-redlined documents, use correct patterns:",
|
||||
" - To reject another's INSERTION: Nest <w:del> inside their <w:ins>",
|
||||
" - To reject PART of one: nest <w:del> around only the runs you reject.",
|
||||
" Their <w:ins> may be split around it, so long as the pieces keep",
|
||||
" their author and date and still spell out the same text.",
|
||||
" - To restore another's DELETION: Add new <w:ins> AFTER their <w:del>",
|
||||
"",
|
||||
]
|
||||
|
||||
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):
|
||||
try:
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
temp_path = Path(temp_dir)
|
||||
|
||||
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")
|
||||
|
||||
result = subprocess.run(
|
||||
[
|
||||
"git",
|
||||
"diff",
|
||||
"--word-diff=plain",
|
||||
"--word-diff-regex=.",
|
||||
"-U0",
|
||||
"--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)
|
||||
|
||||
if content_lines:
|
||||
return "\n".join(content_lines)
|
||||
|
||||
result = subprocess.run(
|
||||
[
|
||||
"git",
|
||||
"diff",
|
||||
"--word-diff=plain",
|
||||
"-U0",
|
||||
"--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):
|
||||
pass
|
||||
|
||||
return None
|
||||
|
||||
def _remove_tracked_changes(self, root, targets):
|
||||
ins_tag = f"{{{self.namespaces['w']}}}ins"
|
||||
del_tag = f"{{{self.namespaces['w']}}}del"
|
||||
|
||||
for parent in root.iter():
|
||||
to_remove = []
|
||||
for child in parent:
|
||||
if child.tag == ins_tag and child in targets:
|
||||
to_remove.append(child)
|
||||
for elem in to_remove:
|
||||
parent.remove(elem)
|
||||
|
||||
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 in targets:
|
||||
to_process.append((child, list(parent).index(child)))
|
||||
|
||||
for del_elem, del_index in reversed(to_process):
|
||||
for elem in del_elem.iter():
|
||||
if elem.tag == deltext_tag:
|
||||
elem.tag = t_tag
|
||||
|
||||
for child in reversed(list(del_elem)):
|
||||
parent.insert(del_index, child)
|
||||
parent.remove(del_elem)
|
||||
|
||||
def _extract_text_content(self, root):
|
||||
p_tag = f"{{{self.namespaces['w']}}}p"
|
||||
t_tag = f"{{{self.namespaces['w']}}}t"
|
||||
|
||||
paragraphs = []
|
||||
for p_elem in root.findall(f".//{p_tag}"):
|
||||
text_parts = []
|
||||
for t_elem in p_elem.findall(f".//{t_tag}"):
|
||||
text_parts.append(self._rendered_text(t_elem))
|
||||
paragraph_text = "".join(text_parts)
|
||||
if paragraph_text:
|
||||
paragraphs.append(paragraph_text)
|
||||
|
||||
return "\n".join(paragraphs)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise RuntimeError("This module should not be run directly.")
|
||||
Reference in New Issue
Block a user