@aslomon/effectum 0.3.2 → 0.3.4

package/system/skills/pptx/scripts/clean.py

@@ -0,0 +1,286 @@
+"""Remove unreferenced files from an unpacked PPTX directory.
+
+Usage: python clean.py <unpacked_dir>
+
+Example:
+    python clean.py unpacked/
+
+This script removes:
+- Orphaned slides (not in sldIdLst) and their relationships
+- [trash] directory (unreferenced files)
+- Orphaned .rels files for deleted resources
+- Unreferenced media, embeddings, charts, diagrams, drawings, ink files
+- Unreferenced theme files
+- Unreferenced notes slides
+- Content-Type overrides for deleted files
+"""
+
+import sys
+from pathlib import Path
+
+import defusedxml.minidom
+
+
+import re
+
+
+def get_slides_in_sldidlst(unpacked_dir: Path) -> set[str]:
+    pres_path = unpacked_dir / "ppt" / "presentation.xml"
+    pres_rels_path = unpacked_dir / "ppt" / "_rels" / "presentation.xml.rels"
+
+    if not pres_path.exists() or not pres_rels_path.exists():
+        return set()
+
+    rels_dom = defusedxml.minidom.parse(str(pres_rels_path))
+    rid_to_slide = {}
+    for rel in rels_dom.getElementsByTagName("Relationship"):
+        rid = rel.getAttribute("Id")
+        target = rel.getAttribute("Target")
+        rel_type = rel.getAttribute("Type")
+        if "slide" in rel_type and target.startswith("slides/"):
+            rid_to_slide[rid] = target.replace("slides/", "")
+
+    pres_content = pres_path.read_text(encoding="utf-8")
+    referenced_rids = set(re.findall(r'<p:sldId[^>]*r:id="([^"]+)"', pres_content))
+
+    return {rid_to_slide[rid] for rid in referenced_rids if rid in rid_to_slide}
+
+
+def remove_orphaned_slides(unpacked_dir: Path) -> list[str]:
+    slides_dir = unpacked_dir / "ppt" / "slides"
+    slides_rels_dir = slides_dir / "_rels"
+    pres_rels_path = unpacked_dir / "ppt" / "_rels" / "presentation.xml.rels"
+
+    if not slides_dir.exists():
+        return []
+
+    referenced_slides = get_slides_in_sldidlst(unpacked_dir)
+    removed = []
+
+    for slide_file in slides_dir.glob("slide*.xml"):
+        if slide_file.name not in referenced_slides:
+            rel_path = slide_file.relative_to(unpacked_dir)
+            slide_file.unlink()
+            removed.append(str(rel_path))
+
+            rels_file = slides_rels_dir / f"{slide_file.name}.rels"
+            if rels_file.exists():
+                rels_file.unlink()
+                removed.append(str(rels_file.relative_to(unpacked_dir)))
+
+    if removed and pres_rels_path.exists():
+        rels_dom = defusedxml.minidom.parse(str(pres_rels_path))
+        changed = False
+
+        for rel in list(rels_dom.getElementsByTagName("Relationship")):
+            target = rel.getAttribute("Target")
+            if target.startswith("slides/"):
+                slide_name = target.replace("slides/", "")
+                if slide_name not in referenced_slides:
+                    if rel.parentNode:
+                        rel.parentNode.removeChild(rel)
+                        changed = True
+
+        if changed:
+            with open(pres_rels_path, "wb") as f:
+                f.write(rels_dom.toxml(encoding="utf-8"))
+
+    return removed
+
+
+def remove_trash_directory(unpacked_dir: Path) -> list[str]:
+    trash_dir = unpacked_dir / "[trash]"
+    removed = []
+
+    if trash_dir.exists() and trash_dir.is_dir():
+        for file_path in trash_dir.iterdir():
+            if file_path.is_file():
+                rel_path = file_path.relative_to(unpacked_dir)
+                removed.append(str(rel_path))
+                file_path.unlink()
+        trash_dir.rmdir()
+
+    return removed
+
+
+def get_slide_referenced_files(unpacked_dir: Path) -> set:
+    referenced = set()
+    slides_rels_dir = unpacked_dir / "ppt" / "slides" / "_rels"
+
+    if not slides_rels_dir.exists():
+        return referenced
+
+    for rels_file in slides_rels_dir.glob("*.rels"):
+        dom = defusedxml.minidom.parse(str(rels_file))
+        for rel in dom.getElementsByTagName("Relationship"):
+            target = rel.getAttribute("Target")
+            if not target:
+                continue
+            target_path = (rels_file.parent.parent / target).resolve()
+            try:
+                referenced.add(target_path.relative_to(unpacked_dir.resolve()))
+            except ValueError:
+                pass
+
+    return referenced
+
+
+def remove_orphaned_rels_files(unpacked_dir: Path) -> list[str]:
+    resource_dirs = ["charts", "diagrams", "drawings"]
+    removed = []
+    slide_referenced = get_slide_referenced_files(unpacked_dir)
+
+    for dir_name in resource_dirs:
+        rels_dir = unpacked_dir / "ppt" / dir_name / "_rels"
+        if not rels_dir.exists():
+            continue
+
+        for rels_file in rels_dir.glob("*.rels"):
+            resource_file = rels_dir.parent / rels_file.name.replace(".rels", "")
+            try:
+                resource_rel_path = resource_file.resolve().relative_to(unpacked_dir.resolve())
+            except ValueError:
+                continue
+
+            if not resource_file.exists() or resource_rel_path not in slide_referenced:
+                rels_file.unlink()
+                rel_path = rels_file.relative_to(unpacked_dir)
+                removed.append(str(rel_path))
+
+    return removed
+
+
+def get_referenced_files(unpacked_dir: Path) -> set:
+    referenced = set()
+
+    for rels_file in unpacked_dir.rglob("*.rels"):
+        dom = defusedxml.minidom.parse(str(rels_file))
+        for rel in dom.getElementsByTagName("Relationship"):
+            target = rel.getAttribute("Target")
+            if not target:
+                continue
+            target_path = (rels_file.parent.parent / target).resolve()
+            try:
+                referenced.add(target_path.relative_to(unpacked_dir.resolve()))
+            except ValueError:
+                pass
+
+    return referenced
+
+
+def remove_orphaned_files(unpacked_dir: Path, referenced: set) -> list[str]:
+    resource_dirs = ["media", "embeddings", "charts", "diagrams", "tags", "drawings", "ink"]
+    removed = []
+
+    for dir_name in resource_dirs:
+        dir_path = unpacked_dir / "ppt" / dir_name
+        if not dir_path.exists():
+            continue
+
+        for file_path in dir_path.glob("*"):
+            if not file_path.is_file():
+                continue
+            rel_path = file_path.relative_to(unpacked_dir)
+            if rel_path not in referenced:
+                file_path.unlink()
+                removed.append(str(rel_path))
+
+    theme_dir = unpacked_dir / "ppt" / "theme"
+    if theme_dir.exists():
+        for file_path in theme_dir.glob("theme*.xml"):
+            rel_path = file_path.relative_to(unpacked_dir)
+            if rel_path not in referenced:
+                file_path.unlink()
+                removed.append(str(rel_path))
+                theme_rels = theme_dir / "_rels" / f"{file_path.name}.rels"
+                if theme_rels.exists():
+                    theme_rels.unlink()
+                    removed.append(str(theme_rels.relative_to(unpacked_dir)))
+
+    notes_dir = unpacked_dir / "ppt" / "notesSlides"
+    if notes_dir.exists():
+        for file_path in notes_dir.glob("*.xml"):
+            if not file_path.is_file():
+                continue
+            rel_path = file_path.relative_to(unpacked_dir)
+            if rel_path not in referenced:
+                file_path.unlink()
+                removed.append(str(rel_path))
+
+        notes_rels_dir = notes_dir / "_rels"
+        if notes_rels_dir.exists():
+            for file_path in notes_rels_dir.glob("*.rels"):
+                notes_file = notes_dir / file_path.name.replace(".rels", "")
+                if not notes_file.exists():
+                    file_path.unlink()
+                    removed.append(str(file_path.relative_to(unpacked_dir)))
+
+    return removed
+
+
+def update_content_types(unpacked_dir: Path, removed_files: list[str]) -> None:
+    ct_path = unpacked_dir / "[Content_Types].xml"
+    if not ct_path.exists():
+        return
+
+    dom = defusedxml.minidom.parse(str(ct_path))
+    changed = False
+
+    for override in list(dom.getElementsByTagName("Override")):
+        part_name = override.getAttribute("PartName").lstrip("/")
+        if part_name in removed_files:
+            if override.parentNode:
+                override.parentNode.removeChild(override)
+                changed = True
+
+    if changed:
+        with open(ct_path, "wb") as f:
+            f.write(dom.toxml(encoding="utf-8"))
+
+
+def clean_unused_files(unpacked_dir: Path) -> list[str]:
+    all_removed = []
+
+    slides_removed = remove_orphaned_slides(unpacked_dir)
+    all_removed.extend(slides_removed)
+
+    trash_removed = remove_trash_directory(unpacked_dir)
+    all_removed.extend(trash_removed)
+
+    while True:
+        removed_rels = remove_orphaned_rels_files(unpacked_dir)
+        referenced = get_referenced_files(unpacked_dir)
+        removed_files = remove_orphaned_files(unpacked_dir, referenced)
+
+        total_removed = removed_rels + removed_files
+        if not total_removed:
+            break
+
+        all_removed.extend(total_removed)
+
+    if all_removed:
+        update_content_types(unpacked_dir, all_removed)
+
+    return all_removed
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print("Usage: python clean.py <unpacked_dir>", file=sys.stderr)
+        print("Example: python clean.py unpacked/", file=sys.stderr)
+        sys.exit(1)
+
+    unpacked_dir = Path(sys.argv[1])
+
+    if not unpacked_dir.exists():
+        print(f"Error: {unpacked_dir} not found", file=sys.stderr)
+        sys.exit(1)
+
+    removed = clean_unused_files(unpacked_dir)
+
+    if removed:
+        print(f"Removed {len(removed)} unreferenced files:")
+        for f in removed:
+            print(f"  {f}")
+    else:
+        print("No unreferenced files found")

package/system/skills/pptx/scripts/office/helpers/merge_runs.py

@@ -0,0 +1,199 @@
+"""Merge adjacent runs with identical formatting in DOCX.
+
+Merges adjacent <w:r> elements that have identical <w:rPr> properties.
+Works on runs in paragraphs and inside tracked changes (<w:ins>, <w:del>).
+
+Also:
+- Removes rsid attributes from runs (revision metadata that doesn't affect rendering)
+- Removes proofErr elements (spell/grammar markers that block merging)
+"""
+
+from pathlib import Path
+
+import defusedxml.minidom
+
+
+def merge_runs(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
+
+        _remove_elements(root, "proofErr")
+        _strip_run_rsid_attrs(root)
+
+        containers = {run.parentNode for run in _find_elements(root, "r")}
+
+        merge_count = 0
+        for container in containers:
+            merge_count += _merge_runs_in(container)
+
+        doc_xml.write_bytes(dom.toxml(encoding="UTF-8"))
+        return merge_count, f"Merged {merge_count} runs"
+
+    except Exception as e:
+        return 0, f"Error: {e}"
+
+
+
+
+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_child(parent, tag: str):
+    for child in parent.childNodes:
+        if child.nodeType == child.ELEMENT_NODE:
+            name = child.localName or child.tagName
+            if name == tag or name.endswith(f":{tag}"):
+                return child
+    return None
+
+
+def _get_children(parent, tag: str) -> list:
+    results = []
+    for child in parent.childNodes:
+        if child.nodeType == child.ELEMENT_NODE:
+            name = child.localName or child.tagName
+            if name == tag or name.endswith(f":{tag}"):
+                results.append(child)
+    return results
+
+
+def _is_adjacent(elem1, elem2) -> bool:
+    node = elem1.nextSibling
+    while node:
+        if node == elem2:
+            return True
+        if node.nodeType == node.ELEMENT_NODE:
+            return False
+        if node.nodeType == node.TEXT_NODE and node.data.strip():
+            return False
+        node = node.nextSibling
+    return False
+
+
+
+
+def _remove_elements(root, tag: str):
+    for elem in _find_elements(root, tag):
+        if elem.parentNode:
+            elem.parentNode.removeChild(elem)
+
+
+def _strip_run_rsid_attrs(root):
+    for run in _find_elements(root, "r"):
+        for attr in list(run.attributes.values()):
+            if "rsid" in attr.name.lower():
+                run.removeAttribute(attr.name)
+
+
+
+
+def _merge_runs_in(container) -> int:
+    merge_count = 0
+    run = _first_child_run(container)
+
+    while run:
+        while True:
+            next_elem = _next_element_sibling(run)
+            if next_elem and _is_run(next_elem) and _can_merge(run, next_elem):
+                _merge_run_content(run, next_elem)
+                container.removeChild(next_elem)
+                merge_count += 1
+            else:
+                break
+
+        _consolidate_text(run)
+        run = _next_sibling_run(run)
+
+    return merge_count
+
+
+def _first_child_run(container):
+    for child in container.childNodes:
+        if child.nodeType == child.ELEMENT_NODE and _is_run(child):
+            return child
+    return None
+
+
+def _next_element_sibling(node):
+    sibling = node.nextSibling
+    while sibling:
+        if sibling.nodeType == sibling.ELEMENT_NODE:
+            return sibling
+        sibling = sibling.nextSibling
+    return None
+
+
+def _next_sibling_run(node):
+    sibling = node.nextSibling
+    while sibling:
+        if sibling.nodeType == sibling.ELEMENT_NODE:
+            if _is_run(sibling):
+                return sibling
+        sibling = sibling.nextSibling
+    return None
+
+
+def _is_run(node) -> bool:
+    name = node.localName or node.tagName
+    return name == "r" or name.endswith(":r")
+
+
+def _can_merge(run1, run2) -> bool:
+    rpr1 = _get_child(run1, "rPr")
+    rpr2 = _get_child(run2, "rPr")
+
+    if (rpr1 is None) != (rpr2 is None):
+        return False
+    if rpr1 is None:
+        return True
+    return rpr1.toxml() == rpr2.toxml()  
+
+
+def _merge_run_content(target, source):
+    for child in list(source.childNodes):
+        if child.nodeType == child.ELEMENT_NODE:
+            name = child.localName or child.tagName
+            if name != "rPr" and not name.endswith(":rPr"):
+                target.appendChild(child)
+
+
+def _consolidate_text(run):
+    t_elements = _get_children(run, "t")
+
+    for i in range(len(t_elements) - 1, 0, -1):
+        curr, prev = t_elements[i], t_elements[i - 1]
+
+        if _is_adjacent(prev, curr):
+            prev_text = prev.firstChild.data if prev.firstChild else ""
+            curr_text = curr.firstChild.data if curr.firstChild else ""
+            merged = prev_text + curr_text
+
+            if prev.firstChild:
+                prev.firstChild.data = merged
+            else:
+                prev.appendChild(run.ownerDocument.createTextNode(merged))
+
+            if merged.startswith(" ") or merged.endswith(" "):
+                prev.setAttribute("xml:space", "preserve")
+            elif prev.hasAttribute("xml:space"):
+                prev.removeAttribute("xml:space")
+
+            run.removeChild(curr)

package/system/skills/pptx/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."
+    )