You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
248 lines
8.7 KiB
Python
248 lines
8.7 KiB
Python
"""
|
|
Validator for tracked changes in Word documents.
|
|
"""
|
|
|
|
import subprocess
|
|
import tempfile
|
|
import zipfile
|
|
from pathlib import Path
|
|
|
|
|
|
class RedliningValidator:
|
|
|
|
def __init__(self, unpacked_dir, original_docx, verbose=False, author="Claude"):
|
|
self.unpacked_dir = Path(unpacked_dir)
|
|
self.original_docx = Path(original_docx)
|
|
self.verbose = verbose
|
|
self.author = author
|
|
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
|
|
|
|
try:
|
|
import xml.etree.ElementTree as ET
|
|
|
|
tree = ET.parse(modified_file)
|
|
root = tree.getroot()
|
|
|
|
del_elements = root.findall(".//w:del", self.namespaces)
|
|
ins_elements = root.findall(".//w:ins", self.namespaces)
|
|
|
|
author_del_elements = [
|
|
elem
|
|
for elem in del_elements
|
|
if elem.get(f"{{{self.namespaces['w']}}}author") == self.author
|
|
]
|
|
author_ins_elements = [
|
|
elem
|
|
for elem in ins_elements
|
|
if elem.get(f"{{{self.namespaces['w']}}}author") == self.author
|
|
]
|
|
|
|
if not author_del_elements and not author_ins_elements:
|
|
if self.verbose:
|
|
print(f"PASSED - No tracked changes by {self.author} found.")
|
|
return True
|
|
|
|
except Exception:
|
|
pass
|
|
|
|
with tempfile.TemporaryDirectory() as temp_dir:
|
|
temp_path = Path(temp_dir)
|
|
|
|
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
|
|
|
|
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
|
|
|
|
self._remove_author_tracked_changes(original_root)
|
|
self._remove_author_tracked_changes(modified_root)
|
|
|
|
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 changes by {self.author} are properly tracked")
|
|
return True
|
|
|
|
def _generate_detailed_diff(self, original_text, modified_text):
|
|
error_parts = [
|
|
f"FAILED - Document text doesn't match after removing {self.author}'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>",
|
|
"",
|
|
]
|
|
|
|
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_author_tracked_changes(self, root):
|
|
ins_tag = f"{{{self.namespaces['w']}}}ins"
|
|
del_tag = f"{{{self.namespaces['w']}}}del"
|
|
author_attr = f"{{{self.namespaces['w']}}}author"
|
|
|
|
for parent in root.iter():
|
|
to_remove = []
|
|
for child in parent:
|
|
if child.tag == ins_tag and child.get(author_attr) == self.author:
|
|
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.get(author_attr) == self.author:
|
|
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}"):
|
|
if t_elem.text:
|
|
text_parts.append(t_elem.text)
|
|
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.")
|