@farazirfan/costar-server-executor 1.7.37 → 1.7.39

package/skills/docx/scripts/helpers/simplify_redlines.py

@@ -0,0 +1,240 @@
+"""Simplify tracked changes by merging adjacent w:ins or w:del elements.
+
+Merges adjacent <w:ins> elements from the same author into a single element.
+Same for <w:del> elements. This makes heavily-redlined documents easier to
+work with by reducing the number of tracked change wrappers.
+
+Rules:
+- Only merges w:ins with w:ins, w:del with w:del (same element type)
+- Only merges if same author (ignores timestamp differences)
+- Only merges if truly adjacent (only whitespace between them)
+"""
+
+import xml.etree.ElementTree as ET
+import zipfile
+from pathlib import Path
+
+import defusedxml.minidom
+
+WORD_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
+
+
+def simplify_redlines(input_dir: str) -> tuple[int, str]:
+    """Merge adjacent tracked changes from the same author in document.xml.
+
+    Args:
+        input_dir: Path to unpacked DOCX directory
+
+    Returns:
+        (merge_count, message)
+    """
+    doc_xml = Path(input_dir) / "word" / "document.xml"
+
+    if not doc_xml.exists():
+        return 0, f"Error: {doc_xml} not found"
+
+    try:
+        dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8"))
+        root = dom.documentElement
+
+        merge_count = 0
+
+        # Find all paragraphs and table cells (containers for content)
+        containers = _find_elements(root, "p") + _find_elements(root, "tc")
+
+        for container in containers:
+            merge_count += _merge_tracked_changes_in(container, "ins")
+            merge_count += _merge_tracked_changes_in(container, "del")
+
+        doc_xml.write_bytes(dom.toxml(encoding="UTF-8"))
+        return merge_count, f"Simplified {merge_count} tracked changes"
+
+    except Exception as e:
+        return 0, f"Error: {e}"
+
+
+def _merge_tracked_changes_in(container, tag: str) -> int:
+    """Merge adjacent w:ins or w:del elements from the same author."""
+    merge_count = 0
+
+    # Get direct children that are tracked changes of this type
+    tracked = [
+        child
+        for child in container.childNodes
+        if child.nodeType == child.ELEMENT_NODE and _is_element(child, tag)
+    ]
+
+    if len(tracked) < 2:
+        return 0
+
+    # Process from front: merge next into current when possible
+    i = 0
+    while i < len(tracked) - 1:
+        curr = tracked[i]
+        next_elem = tracked[i + 1]
+
+        if _can_merge_tracked(curr, next_elem):
+            _merge_tracked_content(curr, next_elem)
+            container.removeChild(next_elem)
+            tracked.pop(i + 1)
+            merge_count += 1
+            # Don't increment i - try to merge more into curr
+        else:
+            i += 1
+
+    return merge_count
+
+
+def _is_element(node, tag: str) -> bool:
+    """Check if node matches the given tag name."""
+    name = node.localName or node.tagName
+    return name == tag or name.endswith(f":{tag}")
+
+
+def _get_author(elem) -> str:
+    """Get the author attribute from a tracked change element."""
+    author = elem.getAttribute("w:author")
+    if not author:
+        for attr in elem.attributes.values():
+            if attr.localName == "author" or attr.name.endswith(":author"):
+                return attr.value
+    return author
+
+
+def _can_merge_tracked(elem1, elem2) -> bool:
+    """Check if two tracked change elements can be merged."""
+    # Must be same author
+    if _get_author(elem1) != _get_author(elem2):
+        return False
+
+    # Must be truly adjacent (only whitespace between them)
+    node = elem1.nextSibling
+    while node and node != elem2:
+        if node.nodeType == node.ELEMENT_NODE:
+            return False
+        if node.nodeType == node.TEXT_NODE and node.data.strip():
+            return False
+        node = node.nextSibling
+
+    return True
+
+
+def _merge_tracked_content(target, source):
+    """Move all children from source tracked change to target."""
+    while source.firstChild:
+        child = source.firstChild
+        source.removeChild(child)
+        target.appendChild(child)
+
+
+def _find_elements(root, tag: str) -> list:
+    """Find all elements matching tag name (with or without namespace)."""
+    results = []
+
+    def traverse(node):
+        if node.nodeType == node.ELEMENT_NODE:
+            name = node.localName or node.tagName
+            if name == tag or name.endswith(f":{tag}"):
+                results.append(node)
+            for child in node.childNodes:
+                traverse(child)
+
+    traverse(root)
+    return results
+
+
+def get_tracked_change_authors(doc_xml_path: Path) -> dict[str, int]:
+    """Get authors and their tracked change counts from a document.xml file.
+
+    Returns:
+        Dict mapping author name to count of tracked changes (w:ins + w:del)
+    """
+    if not doc_xml_path.exists():
+        return {}
+
+    try:
+        tree = ET.parse(doc_xml_path)
+        root = tree.getroot()
+    except ET.ParseError:
+        return {}
+
+    namespaces = {"w": WORD_NS}
+    author_attr = f"{{{WORD_NS}}}author"
+
+    authors: dict[str, int] = {}
+    for tag in ["ins", "del"]:
+        for elem in root.findall(f".//w:{tag}", namespaces):
+            author = elem.get(author_attr)
+            if author:
+                authors[author] = authors.get(author, 0) + 1
+
+    return authors
+
+
+def _get_authors_from_docx(docx_path: Path) -> dict[str, int]:
+    """Get authors and counts from a packed DOCX file."""
+    try:
+        with zipfile.ZipFile(docx_path, "r") as zf:
+            if "word/document.xml" not in zf.namelist():
+                return {}
+            with zf.open("word/document.xml") as f:
+                tree = ET.parse(f)
+                root = tree.getroot()
+
+                namespaces = {"w": WORD_NS}
+                author_attr = f"{{{WORD_NS}}}author"
+
+                authors: dict[str, int] = {}
+                for tag in ["ins", "del"]:
+                    for elem in root.findall(f".//w:{tag}", namespaces):
+                        author = elem.get(author_attr)
+                        if author:
+                            authors[author] = authors.get(author, 0) + 1
+                return authors
+    except (zipfile.BadZipFile, ET.ParseError):
+        return {}
+
+
+def infer_author(modified_dir: Path, original_docx: Path, default: str = "Costar") -> str:
+    """Infer the author to validate by finding who added tracked changes.
+
+    Compares tracked change counts between modified and original documents.
+    Returns the author who added new tracked changes.
+
+    Args:
+        modified_dir: Path to unpacked DOCX directory
+        original_docx: Path to original DOCX file
+        default: Default author if no new changes found
+
+    Returns:
+        Author name to use for validation
+
+    Raises:
+        ValueError: If multiple authors added new changes (ambiguous)
+    """
+    modified_xml = modified_dir / "word" / "document.xml"
+    modified_authors = get_tracked_change_authors(modified_xml)
+
+    if not modified_authors:
+        return default
+
+    original_authors = _get_authors_from_docx(original_docx)
+
+    # Calculate new changes per author (modified count - original count)
+    new_changes: dict[str, int] = {}
+    for author, count in modified_authors.items():
+        original_count = original_authors.get(author, 0)
+        diff = count - original_count
+        if diff > 0:
+            new_changes[author] = diff
+
+    if not new_changes:
+        return default
+
+    if len(new_changes) == 1:
+        return next(iter(new_changes))
+
+    raise ValueError(
+        f"Multiple authors added new changes: {new_changes}. "
+        "Cannot infer which author to validate."
+    )