diff options
| -rw-r--r-- | skills/docx/SKILL.md | 7 | ||||
| -rw-r--r-- | skills/docx/scripts/office/soffice.py | 84 | ||||
| -rwxr-xr-x | skills/docx/scripts/office/validate.py | 16 | ||||
| -rw-r--r-- | skills/pptx/SKILL.md | 4 | ||||
| -rw-r--r-- | skills/pptx/scripts/office/soffice.py | 84 | ||||
| -rwxr-xr-x | skills/pptx/scripts/office/validate.py | 16 | ||||
| -rw-r--r-- | skills/xlsx/scripts/office/soffice.py | 84 | ||||
| -rwxr-xr-x | skills/xlsx/scripts/office/validate.py | 16 |
8 files changed, 290 insertions, 21 deletions
diff --git a/skills/docx/SKILL.md b/skills/docx/SKILL.md index 8620c46..a95379e 100644 --- a/skills/docx/SKILL.md +++ b/skills/docx/SKILL.md @@ -11,7 +11,7 @@ A `.docx` is a ZIP archive of XML files. Choose your approach by task: | Task | Approach | |---|---| | **Create** a new document | Write a `docx` (npm) script — see gotchas below | -| **Edit** an existing document | `unzip` → edit `word/document.xml` → `zip` (docx-js cannot open existing files) | +| **Edit** an existing document | unpack → edit `word/document.xml` → `zip` (docx-js cannot open existing files) | | **Read** content | `pandoc -t markdown file.docx` | > Script paths below are relative to this skill's directory. @@ -51,11 +51,10 @@ ls page-*.jpg # then Read the images Legacy `.doc` files must be converted first: `python scripts/office/soffice.py --headless --convert-to docx file.doc`. ```bash -unzip -q doc.docx -d unpacked/ -find unpacked -type l -delete # strip symlink entries — docx from external parties is untrusted +python3 -c "import sys,zipfile; zipfile.ZipFile(sys.argv[1]).extractall('unpacked')" doc.docx # not unzip, which restores symlinks — docx from external parties is untrusted python scripts/merge_runs.py unpacked/ # coalesce fragmented runs so text is findable # edit unpacked/word/document.xml in place — do NOT reformat or pretty-print -(cd unpacked && rm -f ../out.docx && zip -XrD ../out.docx .) +(cd unpacked && rm -f ../out.docx && zip -XrDy ../out.docx .) python scripts/office/validate.py out.docx --original doc.docx # XSD checks; --auto-repair fixes common issues # redlining? add --author "<the name you redlined under>" to check every edit is tracked ``` diff --git a/skills/docx/scripts/office/soffice.py b/skills/docx/scripts/office/soffice.py index eec1687..59b18d9 100644 --- a/skills/docx/scripts/office/soffice.py +++ b/skills/docx/scripts/office/soffice.py @@ -15,11 +15,16 @@ not be completed" and converts nothing. get_soffice_env() stays public for the callers that build their own argv (they must pass -env:UserInstallation too). """ +from __future__ import annotations + import contextlib import os +import re +import shutil import socket import subprocess import tempfile +import zipfile from collections.abc import Iterable from pathlib import Path @@ -43,12 +48,91 @@ def run_soffice(args: Iterable[str], **kwargs) -> subprocess.CompletedProcess: tempfile.TemporaryDirectory(prefix="lo_profile_", ignore_cleanup_errors=True) ) args = [f"-env:UserInstallation={Path(profile).as_uri()}"] + args + if _draws_the_document(args): + copies = Path(stack.enter_context( + tempfile.TemporaryDirectory(prefix="lo_input_", ignore_cleanup_errors=True) + )) + args = [_without_outside_links(str(a), copies / str(i)) for i, a in enumerate(args)] return subprocess.run(["soffice"] + args, env=get_soffice_env(), **kwargs) _SHIM_SO = Path(tempfile.gettempdir()) / "lo_socket_shim.so" +_DRAWN_FORMATS = frozenset( + {"pdf", "png", "jpg", "jpeg", "gif", "bmp", "tif", "tiff", "webp", "svg", "eps", "emf", "wmf"} +) +_WEB_OR_MAIL = re.compile(r"^(?:https?|mailto):", re.I) +_RELS_NS = "http://schemas.openxmlformats.org/package/2006/relationships" +_NO_RELS = f'<Relationships xmlns="{_RELS_NS}"/>'.encode() +_MAX_RELS_BYTES = 32 * 1024 * 1024 + + +def _draws_the_document(args: list) -> bool: + for flag, value in zip(args, args[1:]): + if str(flag) in ("--convert-to", "-convert-to"): + return str(value).split(":")[0].lower() in _DRAWN_FORMATS + return False + + +def _cut_outside_links(rels: bytes) -> bytes | None: + from defusedxml import ElementTree + + try: + root = ElementTree.fromstring(rels) + except (ElementTree.ParseError, ValueError, LookupError): + return _NO_RELS + cut = False + for entry in root.iter(): + if entry.get("TargetMode", "Internal") == "Internal": + continue + if _WEB_OR_MAIL.match(entry.get("Target", "")): + continue + entry.set("TargetMode", "External") + entry.set("Target", "about:blank") + cut = True + if not cut: + return None + for element in root.iter(): + element.tag = element.tag.rsplit("}", 1)[-1] + root.set("xmlns", _RELS_NS) + return ElementTree.tostring(root) + + +def _without_outside_links(arg: str, folder: Path) -> str: + + if not os.path.isfile(arg) or not zipfile.is_zipfile(arg): + return arg + with open(arg, "rb") as file: + if file.read(4) != b"PK\x03\x04": + return arg + with zipfile.ZipFile(arg) as package: + cut = {} + for member in package.infolist(): + if member.filename.lower().endswith(".rels"): + try: + data = package.read(member) if member.file_size <= _MAX_RELS_BYTES else None + except Exception: + data = None + rels = _NO_RELS if data is None else _cut_outside_links(data) + if rels is not None: + cut[member.filename] = rels + if not cut: + return arg + folder.mkdir() + copy = folder / Path(arg).name + with zipfile.ZipFile(copy, "w") as out: + for member in package.infolist(): + entry = zipfile.ZipInfo(member.filename, member.date_time) + entry.compress_type = member.compress_type + if member.filename in cut: + entry.compress_type = zipfile.ZIP_DEFLATED + out.writestr(entry, cut[member.filename]) + else: + with package.open(member) as source, out.open(entry, "w", force_zip64=True) as target: + shutil.copyfileobj(source, target) + return str(copy) + def _needs_shim() -> bool: try: diff --git a/skills/docx/scripts/office/validate.py b/skills/docx/scripts/office/validate.py index ff3bde0..cdd6a91 100755 --- a/skills/docx/scripts/office/validate.py +++ b/skills/docx/scripts/office/validate.py @@ -43,6 +43,14 @@ def _fail(message: str): sys.exit(2) +def _unpack(package: Path, dest: Path): + try: + with zipfile.ZipFile(package, "r") as zf: + safe_extract(zf, dest) + except Exception as e: + _fail(f"cannot unpack {package}: {e}") + + def _has_tracked_changes(unpacked_dir: Path) -> bool: document = unpacked_dir / "word" / "document.xml" if not document.is_file(): @@ -105,6 +113,8 @@ def main(): _fail(f"{original_file} is not a file") if original_file.suffix.lower() not in OOXML_FAMILY: _fail(f"{original_file} must be one of: {', '.join(sorted(OOXML_FAMILY))}") + with tempfile.TemporaryDirectory() as scratch: + _unpack(original_file, Path(scratch)) family = OOXML_FAMILY.get((original_file or path).suffix.lower()) if family is None: @@ -121,11 +131,7 @@ def main(): packed_file = path temp_dir_ctx = tempfile.TemporaryDirectory() unpacked_dir = Path(temp_dir_ctx.name) - try: - with zipfile.ZipFile(path, "r") as zf: - safe_extract(zf, unpacked_dir) - except (zipfile.BadZipFile, ValueError, OSError) as e: - _fail(f"cannot unpack {path}: {e}") + _unpack(path, unpacked_dir) else: if not path.is_dir(): _fail(f"{path} is not a directory or Office file") diff --git a/skills/pptx/SKILL.md b/skills/pptx/SKILL.md index 785fea6..6857031 100644 --- a/skills/pptx/SKILL.md +++ b/skills/pptx/SKILL.md @@ -11,7 +11,7 @@ A `.pptx` is a ZIP archive of XML files. Choose your approach by task: | Task | Approach | |---|---| | **Create** a new deck | Write a `pptxgenjs` script — see gotchas below — and build it as a [structured deck](#structured-decks) unless the user asks for a quick throwaway | -| **Edit** an existing deck, or build from a template | unzip → edit `ppt/slides/slideN.xml` → zip | +| **Edit** an existing deck, or build from a template | unpack → edit `ppt/slides/slideN.xml` → zip | | **Read** content | `python scripts/slide_text.py deck.pptx` (one block per slide under `<!-- Slide number: N -->` markers); visual grid: `python scripts/thumbnail.py deck.pptx` | ## Scripts @@ -76,7 +76,7 @@ python scripts/add_slide.py unpacked/ slide2.xml --after slide2.xml # duplicat # reorder / delete slides = edit <p:sldIdLst> in ppt/presentation.xml python scripts/clean.py unpacked/ # after deletions: removes orphaned slides, media, rels # edit slide content in ppt/slides/slideN.xml -(cd unpacked && rm -f ../out.pptx && zip -XrD ../out.pptx .) # zip from INSIDE the dir; rm first or deleted parts survive +(cd unpacked && rm -f ../out.pptx && zip -XrDy ../out.pptx .) # zip from INSIDE the dir; rm first or deleted parts survive python scripts/office/validate.py out.pptx --original deck.pptx ``` diff --git a/skills/pptx/scripts/office/soffice.py b/skills/pptx/scripts/office/soffice.py index eec1687..59b18d9 100644 --- a/skills/pptx/scripts/office/soffice.py +++ b/skills/pptx/scripts/office/soffice.py @@ -15,11 +15,16 @@ not be completed" and converts nothing. get_soffice_env() stays public for the callers that build their own argv (they must pass -env:UserInstallation too). """ +from __future__ import annotations + import contextlib import os +import re +import shutil import socket import subprocess import tempfile +import zipfile from collections.abc import Iterable from pathlib import Path @@ -43,12 +48,91 @@ def run_soffice(args: Iterable[str], **kwargs) -> subprocess.CompletedProcess: tempfile.TemporaryDirectory(prefix="lo_profile_", ignore_cleanup_errors=True) ) args = [f"-env:UserInstallation={Path(profile).as_uri()}"] + args + if _draws_the_document(args): + copies = Path(stack.enter_context( + tempfile.TemporaryDirectory(prefix="lo_input_", ignore_cleanup_errors=True) + )) + args = [_without_outside_links(str(a), copies / str(i)) for i, a in enumerate(args)] return subprocess.run(["soffice"] + args, env=get_soffice_env(), **kwargs) _SHIM_SO = Path(tempfile.gettempdir()) / "lo_socket_shim.so" +_DRAWN_FORMATS = frozenset( + {"pdf", "png", "jpg", "jpeg", "gif", "bmp", "tif", "tiff", "webp", "svg", "eps", "emf", "wmf"} +) +_WEB_OR_MAIL = re.compile(r"^(?:https?|mailto):", re.I) +_RELS_NS = "http://schemas.openxmlformats.org/package/2006/relationships" +_NO_RELS = f'<Relationships xmlns="{_RELS_NS}"/>'.encode() +_MAX_RELS_BYTES = 32 * 1024 * 1024 + + +def _draws_the_document(args: list) -> bool: + for flag, value in zip(args, args[1:]): + if str(flag) in ("--convert-to", "-convert-to"): + return str(value).split(":")[0].lower() in _DRAWN_FORMATS + return False + + +def _cut_outside_links(rels: bytes) -> bytes | None: + from defusedxml import ElementTree + + try: + root = ElementTree.fromstring(rels) + except (ElementTree.ParseError, ValueError, LookupError): + return _NO_RELS + cut = False + for entry in root.iter(): + if entry.get("TargetMode", "Internal") == "Internal": + continue + if _WEB_OR_MAIL.match(entry.get("Target", "")): + continue + entry.set("TargetMode", "External") + entry.set("Target", "about:blank") + cut = True + if not cut: + return None + for element in root.iter(): + element.tag = element.tag.rsplit("}", 1)[-1] + root.set("xmlns", _RELS_NS) + return ElementTree.tostring(root) + + +def _without_outside_links(arg: str, folder: Path) -> str: + + if not os.path.isfile(arg) or not zipfile.is_zipfile(arg): + return arg + with open(arg, "rb") as file: + if file.read(4) != b"PK\x03\x04": + return arg + with zipfile.ZipFile(arg) as package: + cut = {} + for member in package.infolist(): + if member.filename.lower().endswith(".rels"): + try: + data = package.read(member) if member.file_size <= _MAX_RELS_BYTES else None + except Exception: + data = None + rels = _NO_RELS if data is None else _cut_outside_links(data) + if rels is not None: + cut[member.filename] = rels + if not cut: + return arg + folder.mkdir() + copy = folder / Path(arg).name + with zipfile.ZipFile(copy, "w") as out: + for member in package.infolist(): + entry = zipfile.ZipInfo(member.filename, member.date_time) + entry.compress_type = member.compress_type + if member.filename in cut: + entry.compress_type = zipfile.ZIP_DEFLATED + out.writestr(entry, cut[member.filename]) + else: + with package.open(member) as source, out.open(entry, "w", force_zip64=True) as target: + shutil.copyfileobj(source, target) + return str(copy) + def _needs_shim() -> bool: try: diff --git a/skills/pptx/scripts/office/validate.py b/skills/pptx/scripts/office/validate.py index ff3bde0..cdd6a91 100755 --- a/skills/pptx/scripts/office/validate.py +++ b/skills/pptx/scripts/office/validate.py @@ -43,6 +43,14 @@ def _fail(message: str): sys.exit(2) +def _unpack(package: Path, dest: Path): + try: + with zipfile.ZipFile(package, "r") as zf: + safe_extract(zf, dest) + except Exception as e: + _fail(f"cannot unpack {package}: {e}") + + def _has_tracked_changes(unpacked_dir: Path) -> bool: document = unpacked_dir / "word" / "document.xml" if not document.is_file(): @@ -105,6 +113,8 @@ def main(): _fail(f"{original_file} is not a file") if original_file.suffix.lower() not in OOXML_FAMILY: _fail(f"{original_file} must be one of: {', '.join(sorted(OOXML_FAMILY))}") + with tempfile.TemporaryDirectory() as scratch: + _unpack(original_file, Path(scratch)) family = OOXML_FAMILY.get((original_file or path).suffix.lower()) if family is None: @@ -121,11 +131,7 @@ def main(): packed_file = path temp_dir_ctx = tempfile.TemporaryDirectory() unpacked_dir = Path(temp_dir_ctx.name) - try: - with zipfile.ZipFile(path, "r") as zf: - safe_extract(zf, unpacked_dir) - except (zipfile.BadZipFile, ValueError, OSError) as e: - _fail(f"cannot unpack {path}: {e}") + _unpack(path, unpacked_dir) else: if not path.is_dir(): _fail(f"{path} is not a directory or Office file") diff --git a/skills/xlsx/scripts/office/soffice.py b/skills/xlsx/scripts/office/soffice.py index eec1687..59b18d9 100644 --- a/skills/xlsx/scripts/office/soffice.py +++ b/skills/xlsx/scripts/office/soffice.py @@ -15,11 +15,16 @@ not be completed" and converts nothing. get_soffice_env() stays public for the callers that build their own argv (they must pass -env:UserInstallation too). """ +from __future__ import annotations + import contextlib import os +import re +import shutil import socket import subprocess import tempfile +import zipfile from collections.abc import Iterable from pathlib import Path @@ -43,12 +48,91 @@ def run_soffice(args: Iterable[str], **kwargs) -> subprocess.CompletedProcess: tempfile.TemporaryDirectory(prefix="lo_profile_", ignore_cleanup_errors=True) ) args = [f"-env:UserInstallation={Path(profile).as_uri()}"] + args + if _draws_the_document(args): + copies = Path(stack.enter_context( + tempfile.TemporaryDirectory(prefix="lo_input_", ignore_cleanup_errors=True) + )) + args = [_without_outside_links(str(a), copies / str(i)) for i, a in enumerate(args)] return subprocess.run(["soffice"] + args, env=get_soffice_env(), **kwargs) _SHIM_SO = Path(tempfile.gettempdir()) / "lo_socket_shim.so" +_DRAWN_FORMATS = frozenset( + {"pdf", "png", "jpg", "jpeg", "gif", "bmp", "tif", "tiff", "webp", "svg", "eps", "emf", "wmf"} +) +_WEB_OR_MAIL = re.compile(r"^(?:https?|mailto):", re.I) +_RELS_NS = "http://schemas.openxmlformats.org/package/2006/relationships" +_NO_RELS = f'<Relationships xmlns="{_RELS_NS}"/>'.encode() +_MAX_RELS_BYTES = 32 * 1024 * 1024 + + +def _draws_the_document(args: list) -> bool: + for flag, value in zip(args, args[1:]): + if str(flag) in ("--convert-to", "-convert-to"): + return str(value).split(":")[0].lower() in _DRAWN_FORMATS + return False + + +def _cut_outside_links(rels: bytes) -> bytes | None: + from defusedxml import ElementTree + + try: + root = ElementTree.fromstring(rels) + except (ElementTree.ParseError, ValueError, LookupError): + return _NO_RELS + cut = False + for entry in root.iter(): + if entry.get("TargetMode", "Internal") == "Internal": + continue + if _WEB_OR_MAIL.match(entry.get("Target", "")): + continue + entry.set("TargetMode", "External") + entry.set("Target", "about:blank") + cut = True + if not cut: + return None + for element in root.iter(): + element.tag = element.tag.rsplit("}", 1)[-1] + root.set("xmlns", _RELS_NS) + return ElementTree.tostring(root) + + +def _without_outside_links(arg: str, folder: Path) -> str: + + if not os.path.isfile(arg) or not zipfile.is_zipfile(arg): + return arg + with open(arg, "rb") as file: + if file.read(4) != b"PK\x03\x04": + return arg + with zipfile.ZipFile(arg) as package: + cut = {} + for member in package.infolist(): + if member.filename.lower().endswith(".rels"): + try: + data = package.read(member) if member.file_size <= _MAX_RELS_BYTES else None + except Exception: + data = None + rels = _NO_RELS if data is None else _cut_outside_links(data) + if rels is not None: + cut[member.filename] = rels + if not cut: + return arg + folder.mkdir() + copy = folder / Path(arg).name + with zipfile.ZipFile(copy, "w") as out: + for member in package.infolist(): + entry = zipfile.ZipInfo(member.filename, member.date_time) + entry.compress_type = member.compress_type + if member.filename in cut: + entry.compress_type = zipfile.ZIP_DEFLATED + out.writestr(entry, cut[member.filename]) + else: + with package.open(member) as source, out.open(entry, "w", force_zip64=True) as target: + shutil.copyfileobj(source, target) + return str(copy) + def _needs_shim() -> bool: try: diff --git a/skills/xlsx/scripts/office/validate.py b/skills/xlsx/scripts/office/validate.py index ff3bde0..cdd6a91 100755 --- a/skills/xlsx/scripts/office/validate.py +++ b/skills/xlsx/scripts/office/validate.py @@ -43,6 +43,14 @@ def _fail(message: str): sys.exit(2) +def _unpack(package: Path, dest: Path): + try: + with zipfile.ZipFile(package, "r") as zf: + safe_extract(zf, dest) + except Exception as e: + _fail(f"cannot unpack {package}: {e}") + + def _has_tracked_changes(unpacked_dir: Path) -> bool: document = unpacked_dir / "word" / "document.xml" if not document.is_file(): @@ -105,6 +113,8 @@ def main(): _fail(f"{original_file} is not a file") if original_file.suffix.lower() not in OOXML_FAMILY: _fail(f"{original_file} must be one of: {', '.join(sorted(OOXML_FAMILY))}") + with tempfile.TemporaryDirectory() as scratch: + _unpack(original_file, Path(scratch)) family = OOXML_FAMILY.get((original_file or path).suffix.lower()) if family is None: @@ -121,11 +131,7 @@ def main(): packed_file = path temp_dir_ctx = tempfile.TemporaryDirectory() unpacked_dir = Path(temp_dir_ctx.name) - try: - with zipfile.ZipFile(path, "r") as zf: - safe_extract(zf, unpacked_dir) - except (zipfile.BadZipFile, ValueError, OSError) as e: - _fail(f"cannot unpack {path}: {e}") + _unpack(path, unpacked_dir) else: if not path.is_dir(): _fail(f"{path} is not a directory or Office file") |
