sophhub 0.2.1 → 0.2.2

package/skills/sophnet-xlsx/src/scripts/office/helpers/simplify_redlines.py

@@ -0,0 +1,197 @@
+"""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]:
+    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
+
+        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_count = 0
+
+    tracked = [
+        child
+        for child in container.childNodes
+        if child.nodeType == child.ELEMENT_NODE and _is_element(child, tag)
+    ]
+
+    if len(tracked) < 2:
+        return 0
+
+    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
+        else:
+            i += 1
+
+    return merge_count
+
+
+def _is_element(node, tag: str) -> bool:
+    name = node.localName or node.tagName
+    return name == tag or name.endswith(f":{tag}")
+
+
+def _get_author(elem) -> str:
+    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:
+    if _get_author(elem1) != _get_author(elem2):
+        return False
+
+    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):
+    while source.firstChild:
+        child = source.firstChild
+        source.removeChild(child)
+        target.appendChild(child)
+
+
+def _find_elements(root, tag: str) -> list:
+    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]:
+    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]:
+    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 = "Claude") -> str:
+    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)
+
+    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."
+    )

package/skills/sophnet-xlsx/src/scripts/office/pack.py

@@ -0,0 +1,159 @@
+"""Pack a directory into a DOCX, PPTX, or XLSX file.
+
+Validates with auto-repair, condenses XML formatting, and creates the Office file.
+
+Usage:
+    python pack.py <input_directory> <output_file> [--original <file>] [--validate true|false]
+
+Examples:
+    python pack.py unpacked/ output.docx --original input.docx
+    python pack.py unpacked/ output.pptx --validate false
+"""
+
+import argparse
+import sys
+import shutil
+import tempfile
+import zipfile
+from pathlib import Path
+
+import defusedxml.minidom
+
+from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator
+
+def pack(
+    input_directory: str,
+    output_file: str,
+    original_file: str | None = None,
+    validate: bool = True,
+    infer_author_func=None,
+) -> tuple[None, str]:
+    input_dir = Path(input_directory)
+    output_path = Path(output_file)
+    suffix = output_path.suffix.lower()
+
+    if not input_dir.is_dir():
+        return None, f"Error: {input_dir} is not a directory"
+
+    if suffix not in {".docx", ".pptx", ".xlsx"}:
+        return None, f"Error: {output_file} must be a .docx, .pptx, or .xlsx file"
+
+    if validate and original_file:
+        original_path = Path(original_file)
+        if original_path.exists():
+            success, output = _run_validation(
+                input_dir, original_path, suffix, infer_author_func
+            )
+            if output:
+                print(output)
+            if not success:
+                return None, f"Error: Validation failed for {input_dir}"
+
+    with tempfile.TemporaryDirectory() as temp_dir:
+        temp_content_dir = Path(temp_dir) / "content"
+        shutil.copytree(input_dir, temp_content_dir)
+
+        for pattern in ["*.xml", "*.rels"]:
+            for xml_file in temp_content_dir.rglob(pattern):
+                _condense_xml(xml_file)
+
+        output_path.parent.mkdir(parents=True, exist_ok=True)
+        with zipfile.ZipFile(output_path, "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))
+
+    return None, f"Successfully packed {input_dir} to {output_file}"
+
+
+def _run_validation(
+    unpacked_dir: Path,
+    original_file: Path,
+    suffix: str,
+    infer_author_func=None,
+) -> tuple[bool, str | None]:
+    output_lines = []
+    validators = []
+
+    if suffix == ".docx":
+        author = "Claude"
+        if infer_author_func:
+            try:
+                author = infer_author_func(unpacked_dir, original_file)
+            except ValueError as e:
+                print(f"Warning: {e} Using default author 'Claude'.", file=sys.stderr)
+
+        validators = [
+            DOCXSchemaValidator(unpacked_dir, original_file),
+            RedliningValidator(unpacked_dir, original_file, author=author),
+        ]
+    elif suffix == ".pptx":
+        validators = [PPTXSchemaValidator(unpacked_dir, original_file)]
+
+    if not validators:
+        return True, None
+
+    total_repairs = sum(v.repair() for v in validators)
+    if total_repairs:
+        output_lines.append(f"Auto-repaired {total_repairs} issue(s)")
+
+    success = all(v.validate() for v in validators)
+
+    if success:
+        output_lines.append("All validations PASSED!")
+
+    return success, "\n".join(output_lines) if output_lines else None
+
+
+def _condense_xml(xml_file: Path) -> None:
+    try:
+        with open(xml_file, encoding="utf-8") as f:
+            dom = defusedxml.minidom.parse(f)
+
+        for element in dom.getElementsByTagName("*"):
+            if element.tagName.endswith(":t"):
+                continue
+
+            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)
+
+        xml_file.write_bytes(dom.toxml(encoding="UTF-8"))
+    except Exception as e:
+        print(f"ERROR: Failed to parse {xml_file.name}: {e}", file=sys.stderr)
+        raise
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="Pack a directory into a DOCX, PPTX, or XLSX 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(
+        "--original",
+        help="Original file for validation comparison",
+    )
+    parser.add_argument(
+        "--validate",
+        type=lambda x: x.lower() == "true",
+        default=True,
+        metavar="true|false",
+        help="Run validation with auto-repair (default: true)",
+    )
+    args = parser.parse_args()
+
+    _, message = pack(
+        args.input_directory,
+        args.output_file,
+        original_file=args.original,
+        validate=args.validate,
+    )
+    print(message)
+
+    if "Error" in message:
+        sys.exit(1)