Update docx, pptx, and xlsx skills (#1447)

Add support for template formats (.dotx, .potx, .xltx) across validation and the helper scripts. Consolidate the shared office helpers into a single module, replacing the pack/unpack pipeline with explicit zip/unzip steps. Extraction now rejects symlink and path-traversal archive entries. Move run merging to a standalone docx script, since it only ever applied to Word documents. Fix the redlining validator so it compares against the original even when a document has no tracked changes, which is when an untracked edit would otherwise go unreported. Provision a LibreOffice user profile per invocation so conversions work in sandboxed environments. Trim the skill docs to the guidance that earns its place.
2026-08-02 13:05:28 +08:00 · 2026-07-16 19:47:37 -07:00
parent 9d2f1ae187
commit fa0fa64bdc
53 changed files with 4147 additions and 4442 deletions
@@ -0,0 +1,114 @@
+"""Find masters sharing a theme part in the way PowerPoint refuses to open.
+
+Reports only; the fix is to move <p:notesMasterIdLst> back to directly after
+<p:sldIdLst> in ppt/presentation.xml.
+"""
+
+
+from __future__ import annotations
+
+import posixpath
+import re
+from typing import Mapping
+
+from . import part_text
+
+THEME_REL_TYPE = "http://schemas.openxmlformats.org/officeDocument/2006/relationships/theme"
+
+_MASTER_RE = re.compile(
+    r"^ppt/(?P<group>slideMasters|notesMasters|handoutMasters)/"
+    r"(?:slide|notes|handout)Master(?P<num>\d+)\.xml$"
+)
+_GROUP_ORDER = {"slideMasters": 0, "notesMasters": 1, "handoutMasters": 2}
+
+_RELATIONSHIP_RE = re.compile(
+    r"<Relationship\b[^>]*?(?:/>|>.*?</Relationship\s*>)", re.DOTALL
+)
+
+
+def _sort_key(name: str) -> tuple[int, int]:
+    m = _MASTER_RE.match(name)
+    assert m is not None
+    return (_GROUP_ORDER[m.group("group")], int(m.group("num")))
+
+
+def _rels_path(part: str) -> str:
+    directory, base = posixpath.split(part)
+    return f"{directory}/_rels/{base}.rels"
+
+
+def _resolve(rels_path: str, target: str) -> str:
+    if target.startswith("/"):
+        return target.lstrip("/")
+    part_dir = posixpath.dirname(posixpath.dirname(rels_path))
+    return posixpath.normpath(posixpath.join(part_dir, target))
+
+
+def _theme_rel(files: Mapping[str, bytes], master: str):
+    rels_path = _rels_path(master)
+    rels = files.get(rels_path)
+    if rels is None:
+        return None
+    for element in _RELATIONSHIP_RE.findall(part_text(rels)):
+        if f'Type="{THEME_REL_TYPE}"' not in element:
+            continue
+        target = re.search(r'\bTarget="([^"]+)"', element)
+        if target is None:
+            continue
+        return rels_path, element, _resolve(rels_path, target.group(1))
+    return None
+
+
+def _masters(files: Mapping[str, bytes]) -> list[str]:
+    return sorted((n for n in files if _MASTER_RE.match(n)), key=_sort_key)
+
+
+_PRESENTATION = "ppt/presentation.xml"
+_NOTES_MASTERS = "ppt/notesMasters/"
+_IGNORABLE_RE = re.compile(r"<!--.*?-->|<\?.*?\?>", re.DOTALL)
+_AFTER_SLDIDLST_RE = re.compile(
+    r"<p:sldIdLst\b(?:[^>]*/>|[^>]*>.*?</p:sldIdLst\s*>)\s*(<[^>\s/]+)", re.DOTALL
+)
+
+
+def _notes_master_share_is_inert(files: Mapping[str, bytes]) -> bool:
+    data = files.get(_PRESENTATION)
+    if data is None:
+        return False
+    match = _AFTER_SLDIDLST_RE.search(_IGNORABLE_RE.sub("", part_text(data)))
+    return match is not None and match.group(1) == "<p:notesMasterIdLst"
+
+
+def _shares(files: Mapping[str, bytes]):
+    owner: dict[str, str] = {}
+    for master in _masters(files):
+        found = _theme_rel(files, master)
+        if found is None:
+            continue
+        rels_path, element, theme = found
+        if theme not in files:
+            continue  
+        if theme in owner:
+            yield master, rels_path, element, theme, owner[theme]
+        else:
+            owner[theme] = master
+
+
+def _is_inert(master: str, inert_notes: bool) -> bool:
+    return inert_notes and master.startswith(_NOTES_MASTERS)
+
+
+def find_shared_master_themes(files: Mapping[str, bytes]) -> list[str]:
+    return [
+        f"{master} shares {theme} with {first}"
+        for master, _, _, theme, first in _shares(files)
+    ]
+
+
+def live_shared_master_themes(files: Mapping[str, bytes]) -> list[str]:
+    inert_notes = _notes_master_share_is_inert(files)
+    return [
+        f"{master} shares {theme} with {first}"
+        for master, _, _, theme, first in _shares(files)
+        if not _is_inert(master, inert_notes)
+    ]