python-docx-oss 0.2.0__py3-none-any.whl → 0.3.0__py3-none-any.whl

docx/__init__.py

@@ -13,7 +13,7 @@ from docx.api import Document
 if TYPE_CHECKING:
     from docx.opc.part import Part
 
-__version__ = "0.2.0"
+__version__ = "0.3.0"
 
 
 __all__ = ["Document"]

docx/document.py

@@ -12,6 +12,7 @@ from docx.api import Document as open_document
 from docx.blkcntnr import BlockItemContainer
 from docx.enum.section import WD_SECTION
 from docx.enum.text import WD_BREAK
+from docx.sanitize import SanitizationReport, sanitize_document
 from docx.section import Section, Sections
 from docx.shared import ElementProxy, Emu, Inches, Length
 from docx.text.run import Run
@@ -229,6 +230,27 @@ class Document(ElementProxy):
         """
         self._part.save(path_or_stream)
 
+    def sanitize(
+        self,
+        *,
+        personal_metadata: bool = False,
+        comments: bool = False,
+        web_extensions: bool = False,
+        formatting_revisions: bool = False,
+    ) -> SanitizationReport:
+        """Apply the explicitly selected package-level cleanup operations.
+
+        Every option defaults to |False| because sanitization is destructive. The
+        returned report describes all package and XML changes made to this document.
+        """
+        return sanitize_document(
+            self,
+            personal_metadata=personal_metadata,
+            comments=comments,
+            web_extensions=web_extensions,
+            formatting_revisions=formatting_revisions,
+        )
+
     @property
     def sections(self) -> Sections:
         """|Sections| object providing access to each section in this document."""

docx/opc/coreprops.py

@@ -9,6 +9,7 @@ import datetime as dt
 from typing import TYPE_CHECKING
 
 from docx.oxml.coreprops import CT_CoreProperties
+from docx.oxml.ns import qn
 
 if TYPE_CHECKING:
     from docx.oxml.coreprops import CT_CoreProperties
@@ -21,6 +22,40 @@ class CoreProperties:
     def __init__(self, element: CT_CoreProperties):
         self._element = element
 
+    def deduplicate(self, *property_names: str) -> set[str]:
+        """Remove duplicate XML elements for the named core properties.
+
+        The first occurrence is retained so callers can subsequently normalize its
+        value through the regular property setter.
+        """
+        element_tags = {
+            "author": qn("dc:creator"),
+            "category": qn("cp:category"),
+            "comments": qn("dc:description"),
+            "content_status": qn("cp:contentStatus"),
+            "created": qn("dcterms:created"),
+            "identifier": qn("dc:identifier"),
+            "keywords": qn("cp:keywords"),
+            "language": qn("dc:language"),
+            "last_modified_by": qn("cp:lastModifiedBy"),
+            "last_printed": qn("cp:lastPrinted"),
+            "modified": qn("dcterms:modified"),
+            "revision": qn("cp:revision"),
+            "subject": qn("dc:subject"),
+            "title": qn("dc:title"),
+            "version": qn("cp:version"),
+        }
+        changed: set[str] = set()
+        for property_name in property_names:
+            try:
+                tag = element_tags[property_name]
+            except KeyError as exc:
+                raise ValueError(f"Unsupported core property: {property_name}") from exc
+            for duplicate in self._element.findall(tag)[1:]:
+                self._element.remove(duplicate)
+                changed.add(property_name)
+        return changed
+
     @property
     def author(self):
         return self._element.author_text

docx/opc/part.py

@@ -144,6 +144,10 @@ class Part:
             rel = self.rels.get_or_add(reltype, cast(Part, target))
             return rel.rId
 
+    def replace_blob(self, blob: bytes) -> None:
+        """Replace the serialized payload of this non-XML part."""
+        self._blob = blob
+
     @property
     def related_parts(self):
         """Dictionary mapping related parts by rId, so child objects can resolve
@@ -235,6 +239,10 @@ class XmlPart(Part):
         """The root XML element of this XML part."""
         return self._element
 
+    def replace_blob(self, blob: bytes) -> None:
+        """Reject raw replacement because this part serializes from ``element``."""
+        raise TypeError("cannot replace the blob of an XmlPart; replace its element instead")
+
     @element.setter
     def element(self, e: BaseOxmlElement):
         self._element = e

docx/sanitize/__init__.py

@@ -0,0 +1,10 @@
+"""Package-level DOCX sanitization.
+
+Callers use :meth:`docx.document.Document.sanitize`; this package keeps OPC graph
+mutation and XML cleanup details behind that single method.
+"""
+
+from docx.sanitize.cleaner import sanitize_document
+from docx.sanitize.result import RemovedRelationship, SanitizationReport
+
+__all__ = ["RemovedRelationship", "SanitizationReport", "sanitize_document"]

docx/sanitize/cleaner.py

@@ -0,0 +1,221 @@
+"""Implementation of the package-level sanitization boundary."""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Iterator
+
+from lxml import etree
+
+from docx.opc.oxml import serialize_part_xml
+from docx.opc.part import Part, XmlPart
+from docx.oxml.ns import qn
+from docx.oxml.parser import parse_xml
+from docx.sanitize.result import RemovedRelationship, SanitizationReport
+
+if TYPE_CHECKING:
+    from lxml.etree import _Element as etree_Element  # pyright: ignore[reportPrivateUsage]
+
+    from docx.document import Document
+    from docx.opc.package import OpcPackage
+    from docx.oxml.xmlchemy import BaseOxmlElement
+
+
+_COMMENT_MARKER_TAGS = (
+    qn("w:commentRangeStart"),
+    qn("w:commentRangeEnd"),
+    qn("w:commentReference"),
+)
+_COMMENT_RELATIONSHIP_NAMES = frozenset(
+    {
+        "commentauthors",
+        "comments",
+        "commentsextended",
+        "commentsextensible",
+        "commentsids",
+        "people",
+    }
+)
+_FORMATTING_REVISION_TAGS = tuple(
+    qn(tag)
+    for tag in (
+        "w:rPrChange",
+        "w:pPrChange",
+        "w:tblPrChange",
+        "w:trPrChange",
+        "w:tcPrChange",
+        "w:sectPrChange",
+    )
+)
+_WEB_EXTENSION_RELATIONSHIP_NAMES = frozenset({"webextension", "webextensiontaskpanes"})
+
+
+def sanitize_document(
+    document: Document,
+    *,
+    personal_metadata: bool,
+    comments: bool,
+    web_extensions: bool,
+    formatting_revisions: bool,
+) -> SanitizationReport:
+    """Apply selected sanitizers while keeping all graph mechanics internal."""
+    package = document.part.package
+    assert package is not None
+
+    if not any((personal_metadata, comments, web_extensions, formatting_revisions)):
+        return SanitizationReport()
+
+    parts_before = _reachable_part_names(package)
+    scrubbed_properties: list[str] = []
+    removed_relationships: list[RemovedRelationship] = []
+    warnings: list[str] = []
+    removed_comment_markers = 0
+    removed_formatting_revisions = 0
+
+    if personal_metadata:
+        scrubbed_properties.extend(_scrub_personal_metadata(package))
+
+    if comments or formatting_revisions:
+        for part, root in _iter_word_xml(package, warnings):
+            part_changed = False
+            if comments:
+                count = _remove_elements(root, _COMMENT_MARKER_TAGS)
+                removed_comment_markers += count
+                part_changed = part_changed or count > 0
+            if formatting_revisions:
+                count = _remove_elements(root, _FORMATTING_REVISION_TAGS)
+                removed_formatting_revisions += count
+                part_changed = part_changed or count > 0
+            if part_changed and not isinstance(part, XmlPart):
+                part.replace_blob(serialize_part_xml(root))
+
+    if comments:
+        removed_relationships.extend(_drop_relationships(package, _COMMENT_RELATIONSHIP_NAMES))
+    if web_extensions:
+        removed_relationships.extend(
+            _drop_relationships(package, _WEB_EXTENSION_RELATIONSHIP_NAMES)
+        )
+
+    parts_after = _reachable_part_names(package)
+    return SanitizationReport(
+        scrubbed_properties=tuple(scrubbed_properties),
+        removed_comment_markers=removed_comment_markers,
+        removed_formatting_revisions=removed_formatting_revisions,
+        removed_parts=tuple(sorted(parts_before - parts_after)),
+        removed_relationships=tuple(removed_relationships),
+        warnings=tuple(warnings),
+    )
+
+
+def _drop_relationships(
+    package: OpcPackage, relationship_names: frozenset[str]
+) -> list[RemovedRelationship]:
+    removed: list[RemovedRelationship] = []
+    for source_name, source in _relationship_sources(package):
+        for rId, rel in list(source.rels.items()):
+            if _relationship_name(rel.reltype) not in relationship_names:
+                continue
+            target = rel.target_ref if rel.is_external else str(rel.target_part.partname)
+            removed.append(RemovedRelationship(source_name, rId, rel.reltype, target))
+            del source.rels[rId]
+    return removed
+
+
+def _iter_word_xml(
+    package: OpcPackage, warnings: list[str]
+) -> Iterator[tuple[Part, BaseOxmlElement]]:
+    for part in _reachable_parts(package):
+        if not str(part.partname).startswith("/word/"):
+            continue
+        if isinstance(part, XmlPart):
+            yield part, part.element
+            continue
+        if not part.content_type.endswith("+xml") and part.content_type != "application/xml":
+            continue
+        try:
+            yield part, parse_xml(part.blob)
+        except etree.XMLSyntaxError as exc:
+            warnings.append(f"Could not sanitize XML part {part.partname}: {exc}")
+
+
+def _reachable_parts(package: OpcPackage) -> list[Part]:
+    parts: list[Part] = []
+    visited: set[int] = set()
+
+    def walk(source: OpcPackage | Part) -> None:
+        for rel in source.rels.values():
+            if rel.is_external:
+                continue
+            part = rel.target_part
+            identity = id(part)
+            if identity in visited:
+                continue
+            visited.add(identity)
+            parts.append(part)
+            walk(part)
+
+    walk(package)
+    return parts
+
+
+def _reachable_part_names(package: OpcPackage) -> set[str]:
+    return {str(part.partname) for part in _reachable_parts(package)}
+
+
+def _relationship_name(relationship_type: str) -> str:
+    return relationship_type.rstrip("/").rsplit("/", 1)[-1].lower()
+
+
+def _relationship_sources(package: OpcPackage) -> list[tuple[str, OpcPackage | Part]]:
+    return [("/", package), *[(str(part.partname), part) for part in _reachable_parts(package)]]
+
+
+def _remove_elements(root: BaseOxmlElement, tags: tuple[str, ...]) -> int:
+    tag_set = set(tags)
+    elements = [
+        element
+        for tag in tags
+        for element in root.iter(tag)
+        if not any(ancestor.tag in tag_set for ancestor in element.iterancestors())
+    ]
+    for element in elements:
+        parent = element.getparent()
+        if parent is not None:
+            comment_run = _empty_comment_reference_run(element)
+            parent.remove(element)
+            if comment_run is not None:
+                comment_run_parent = comment_run.getparent()
+                if comment_run_parent is not None:
+                    comment_run_parent.remove(comment_run)
+    return len(elements)
+
+
+def _scrub_personal_metadata(package: OpcPackage) -> list[str]:
+    core_properties = package.core_properties
+    changed = core_properties.deduplicate("author", "last_modified_by", "revision")
+    if core_properties.author:
+        changed.add("author")
+    if core_properties.last_modified_by:
+        changed.add("last_modified_by")
+    if core_properties.revision != 1:
+        changed.add("revision")
+    core_properties.author = ""
+    core_properties.last_modified_by = ""
+    core_properties.revision = 1
+    return [name for name in ("author", "last_modified_by", "revision") if name in changed]
+
+
+def _empty_comment_reference_run(element: etree_Element) -> etree_Element | None:
+    if element.tag != qn("w:commentReference"):
+        return None
+    run = element.getparent()
+    if run is None or run.tag != qn("w:r"):
+        return None
+    remaining = [child for child in run if child is not element]
+    if not remaining:
+        return run
+    if len(remaining) != 1 or remaining[0].tag != qn("w:rPr"):
+        return None
+    run_properties = remaining[0]
+    if len(run_properties) != 1 or run_properties[0].tag != qn("w:rStyle"):
+        return None
+    return run if run_properties[0].get(qn("w:val")) == "CommentReference" else None

docx/sanitize/result.py

@@ -0,0 +1,38 @@
+"""Value objects returned by document sanitization."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+
+
+@dataclass(frozen=True)
+class RemovedRelationship:
+    """A package relationship removed during sanitization."""
+
+    source: str
+    relationship_id: str
+    relationship_type: str
+    target: str
+
+
+@dataclass(frozen=True)
+class SanitizationReport:
+    """Immutable summary of changes made by ``Document.sanitize()``."""
+
+    scrubbed_properties: tuple[str, ...] = ()
+    removed_comment_markers: int = 0
+    removed_formatting_revisions: int = 0
+    removed_parts: tuple[str, ...] = ()
+    removed_relationships: tuple[RemovedRelationship, ...] = ()
+    warnings: tuple[str, ...] = ()
+
+    @property
+    def changed(self) -> bool:
+        """Whether the document package was modified."""
+        return bool(
+            self.scrubbed_properties
+            or self.removed_comment_markers
+            or self.removed_formatting_revisions
+            or self.removed_parts
+            or self.removed_relationships
+        )

{python_docx_oss-0.2.0.dist-info → python_docx_oss-0.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-docx-oss
-Version: 0.2.0
+Version: 0.3.0
 Summary: Create, read, and update Microsoft Word .docx files.
 Author: Ethan St Lee
 License-Expression: MIT
@@ -23,7 +23,7 @@ Classifier: Topic :: Software Development :: Libraries
 Requires-Python: >=3.12
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: lxml>=3.1.0
+Requires-Dist: lxml>=6.1.0
 Requires-Dist: typing_extensions>=4.9.0
 Dynamic: license-file
 
@@ -65,7 +65,8 @@ or low-level package and relationship access.
 | Latin and East Asian font controls | Stable | `run.font.name`, `run.font.hAnsi`, `run.font.eastAsia` |
 | Low-level OPC parts and relationships | Stable | `document.part.package`, `part.rels` |
 | In-memory read, export, and independent copies | Stable | `Document()`, `to_bytes()`, `copy()` |
-| Package inspection, diff, and sanitization | Planned | — |
+| Document sanitization | Development | `document.sanitize()` |
+| Package inspection and diff | Planned | — |
 
 ## Installation
 

{python_docx_oss-0.2.0.dist-info → python_docx_oss-0.3.0.dist-info}/RECORD

@@ -1,8 +1,8 @@
-docx/__init__.py,sha256=aw9boQn8MrzqJFVCGmYy41YRdhhw3Ym0bIhqE643gCA,2102
+docx/__init__.py,sha256=sDaLx2PbYx5dXsjgnP0rhCKyeZZrysYhseDkNNC3Q2Y,2102
 docx/api.py,sha256=jIojXW4IRDEXQqaqvmOZbzBvNeyRXv9ntHByxd-Kb0M,1518
 docx/blkcntnr.py,sha256=_xe7Uz3RBCz4TPKXpIzRxtGg-1YPb3gAG9YvsSUyoLU,3525
 docx/comments.py,sha256=MmaP7U9mZOUFsRhaZNIbXatqOOA8-pOC6UlqWAuTHsc,6385
-docx/document.py,sha256=s9oolRg9W37W_8RG8v-rHVZtU9iBevV-NgnJ9JW2z00,12376
+docx/document.py,sha256=IYTU_lmh_f1SILGGc0XqrDMl814hZ937d8iubfsYFos,13163
 docx/exceptions.py,sha256=WWiMy3ZtsfKRS31Wv09egLZnpPkX0H66B8JkOPCC3FM,454
 docx/package.py,sha256=Eob2q7R6jXQ3iPD0cAGHzu2RVYgU2te4zfG3oVN_-lM,4288
 docx/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -37,13 +37,13 @@ docx/image/svg.py,sha256=qDtoQerJ7lJscevXM65BlWqmtUKVB05jTnQajjwLpFw,3576
 docx/image/tiff.py,sha256=LZx-P2uMSzgdzHfIWRqRqtnbhuIqWBY_cLkx9_HTrPs,10379
 docx/opc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docx/opc/constants.py,sha256=u7JE0q95EFiAp3jXOntjv1cV0GdGpKtLfx85D2mlch0,17124
-docx/opc/coreprops.py,sha256=IfQeqC5o4k9Obj_kQ4ZKfFl6IL7eIm7dcIC1AZkVvac,3468
+docx/opc/coreprops.py,sha256=DUE7xnk0syV2EtwHtJimX5V5efDccsqoB2KW_mmuHEA,4937
 docx/opc/customprops.py,sha256=oCHxWPNWSekBQrtO07WPSb0WKLQgTgfS3y8m8ZUXN-A,1986
 docx/opc/exceptions.py,sha256=pqa1GuFxMlGZDBgGBqntZ_8aDINLwo2gtPuNRwADzyM,264
 docx/opc/oxml.py,sha256=IE3H4F-DWr8QSZi0pxc767apU3Nk-BhFTs7HiTD5ck0,8325
 docx/opc/package.py,sha256=zWteqHOyPbR4mpcoOZy-sPVWvQR2e2fQVoYdjaHXXfI,10217
 docx/opc/packuri.py,sha256=1-uRAwjIftl475nozvssEoS-0EBz0w-oJvT-fNYcx9o,3729
-docx/opc/part.py,sha256=15TjdwOs137LDdr-EVNeLb4iQdRyIfDZg6Vjx6_8Zdc,9606
+docx/opc/part.py,sha256=WZsVGi25sZhRobXEFRBQCVX6EXan2pE1GPe_zH5nhxk,9977
 docx/opc/phys_pkg.py,sha256=-eNZDBbLShHo3W1iglf1CwN_nkK8qnmTWp6ABg77cjA,4005
 docx/opc/pkgreader.py,sha256=iUPZ7Ba4kNXjPB-q1mQEO44eVmbnP08po4WFH-HD2IE,9588
 docx/opc/pkgwriter.py,sha256=shDeuBtW2BbFOTHrXx8R97PWFaH_fE37JYBfbw6QWRs,4524
@@ -89,6 +89,9 @@ docx/parts/numbering.py,sha256=rrVIiRoBQIy6j8eWGhWyhcJvNx6RRaItWVDhorwrVyo,1715
 docx/parts/settings.py,sha256=lqcDzDNLEc8ElxmNMKwy6uNgOesfYcvBDhKz7uUMnb4,1717
 docx/parts/story.py,sha256=WgsvzLkfZ7DigCE9MVSGPfajzennxdPvOtIdoSxmeuk,4577
 docx/parts/styles.py,sha256=Ly7aJyPgtwQ2TRIwuUtHz_x1Z0FH9JTtsNohml1-ykM,1391
+docx/sanitize/__init__.py,sha256=woy_ORRETalWdjmOsDAV7F4ON0jmOWBWm5b8KHhp_yw,387
+docx/sanitize/cleaner.py,sha256=BwAKuJ_B36J6TLSnePMzzvgB129T3QitO6lHS5LXsB0,7602
+docx/sanitize/result.py,sha256=JL5IrKnFpG4WQrXcMqNNxFmBHib7J0IXp4D5p2_iI5c,1055
 docx/styles/__init__.py,sha256=aCJqhH4JhG_cIm3iwVJGtWpWW0AXJx3QMag7MORmrdI,1406
 docx/styles/latent.py,sha256=EDBcgd-1jKmW-wGz64GvcGSopnOuPQG1inU0pnHRsQA,7211
 docx/styles/style.py,sha256=BoGXQRSyODmPI38bAEWPgTXEPwhXyVYZZ9nSYxRSHPM,8051
@@ -125,8 +128,8 @@ docx/text/paragraph.py,sha256=N3F62_JRQZYaumuoaJXKCDnRSw2DIiOwzyMPV2Jd7GI,6828
 docx/text/parfmt.py,sha256=70M75HFo7ydpqmIdZjkV711muyrsBGdr4WZscF3YVJY,10339
 docx/text/run.py,sha256=tsW8dXOE4VnqEM7cJz_uU2Vq3qgdnrMGzyDq9x5jvE4,10800
 docx/text/tabstops.py,sha256=bJN98GWW22f4Sqg0dQbyUcnuOn65fHsNZuCGswI03_c,3896
-python_docx_oss-0.2.0.dist-info/licenses/LICENSE,sha256=lf2yZv-riPwFeah3IMDeG0zqI6fXcV9T9YOToeG54NM,1164
-python_docx_oss-0.2.0.dist-info/METADATA,sha256=xgmccioh4zptF-ExSr52_7IrSCIsMQXeiovBXzT7DRk,7851
-python_docx_oss-0.2.0.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
-python_docx_oss-0.2.0.dist-info/top_level.txt,sha256=zkbrD3gmyqHpD_XhHe7lCbr2M5vT229nJ4UFqF5VjIs,5
-python_docx_oss-0.2.0.dist-info/RECORD,,
+python_docx_oss-0.3.0.dist-info/licenses/LICENSE,sha256=lf2yZv-riPwFeah3IMDeG0zqI6fXcV9T9YOToeG54NM,1164
+python_docx_oss-0.3.0.dist-info/METADATA,sha256=hp-fShMO4V9dZLm86V-xoMsQgyphHVcgtLr8-tS7aa0,7900
+python_docx_oss-0.3.0.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
+python_docx_oss-0.3.0.dist-info/top_level.txt,sha256=zkbrD3gmyqHpD_XhHe7lCbr2M5vT229nJ4UFqF5VjIs,5
+python_docx_oss-0.3.0.dist-info/RECORD,,