mirror of
https://github.com/anthropics/skills.git
synced 2026-08-02 13:05:28 +08:00
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.
This commit is contained in:
@@ -0,0 +1,60 @@
|
||||
"""Pick the slide-XML schema errors PowerPoint refuses the file over.
|
||||
|
||||
A denylist over lxml's messages, so an unrecognised error class is a miss rather
|
||||
than a false alarm.
|
||||
"""
|
||||
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
|
||||
SLIDE_PART_RE = re.compile(
|
||||
r"ppt/(slides|slideLayouts|slideMasters|notesSlides|notesMasters|handoutMasters)"
|
||||
r"/[^/]+\.xml"
|
||||
)
|
||||
|
||||
FATAL_SLIDE_ERRORS: tuple[tuple[re.Pattern[str], str], ...] = (
|
||||
(
|
||||
re.compile(r"\}tableStyleId': This element is not expected"),
|
||||
"two <a:tableStyleId> in one <a:tblPr> (the schema allows one)",
|
||||
),
|
||||
(
|
||||
re.compile(r"\}srgbClr', attribute 'val'"),
|
||||
"a colour that is not six hex digits",
|
||||
),
|
||||
(
|
||||
re.compile(r"\}txBody': Missing child element"),
|
||||
"a <p:txBody> with no children",
|
||||
),
|
||||
(
|
||||
re.compile(r"\}miter', attribute 'lim'"),
|
||||
'a line join with lim="NaN"',
|
||||
),
|
||||
(
|
||||
re.compile(r"\}uLnTx': This element is not expected"),
|
||||
"<a:uLnTx> in a position the schema forbids",
|
||||
),
|
||||
(
|
||||
re.compile(r"\}overrideClrMapping': This element is not expected"),
|
||||
"<p:overrideClrMapping> in a position the schema forbids",
|
||||
),
|
||||
(
|
||||
re.compile(r"\}nvGrpSpPr': Missing child element"),
|
||||
"a <p:nvGrpSpPr> with no children",
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
def is_schema_verdict(error: str) -> bool:
|
||||
return error.startswith("Element ")
|
||||
|
||||
|
||||
def fatal_slide_errors(errors: set[str]) -> list[str]:
|
||||
out = []
|
||||
for error in sorted(errors):
|
||||
for pattern, meaning in FATAL_SLIDE_ERRORS:
|
||||
if pattern.search(error):
|
||||
out.append(f"{meaning}: {error}")
|
||||
break
|
||||
return out
|
||||
Reference in New Issue
Block a user