python-docx-oss 0.3.0__tar.gz → 0.3.1__tar.gz

{python_docx_oss-0.3.0 → python_docx_oss-0.3.1}/HISTORY.md

@@ -2,6 +2,11 @@
 
 **Unreleased**
 
+**0.3.1 (2026-09-08)**
+
+- Fixed an issue where calling `itertext()` on oxml elements produced duplicated
+  text due to overridden `.text` properties.
+
 **0.3.0 (2026-08-29)**
 
 - Added opt-in package-level document sanitization for personal metadata,

{python_docx_oss-0.3.0/src/python_docx_oss.egg-info → python_docx_oss-0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-docx-oss
-Version: 0.3.0
+Version: 0.3.1
 Summary: Create, read, and update Microsoft Word .docx files.
 Author: Ethan St Lee
 License-Expression: MIT

{python_docx_oss-0.3.0 → python_docx_oss-0.3.1}/docs/conf.py

@@ -13,7 +13,7 @@ import sys
 # add these directories to sys.path here. If the directory is relative to the
 # documentation root, use os.path.abspath to make it absolute, like shown here.
 #
-sys.path.insert(0, os.path.abspath(".."))
+sys.path.insert(0, os.path.abspath("../src"))
 
 from docx import __version__  # noqa
 

{python_docx_oss-0.3.0 → python_docx_oss-0.3.1}/src/docx/__init__.py

@@ -13,7 +13,7 @@ from docx.api import Document
 if TYPE_CHECKING:
     from docx.opc.part import Part
 
-__version__ = "0.3.0"
+__version__ = "0.3.1"
 
 
 __all__ = ["Document"]

{python_docx_oss-0.3.0 → python_docx_oss-0.3.1}/src/docx/oxml/xmlchemy.py

@@ -5,7 +5,7 @@
 from __future__ import annotations
 
 import re
-from typing import TYPE_CHECKING, Any, Callable, Sequence, Type, TypeVar
+from typing import TYPE_CHECKING, Any, Callable, Iterator, Sequence, Type, TypeVar
 
 from lxml import etree
 from lxml.etree import ElementBase, _Element  # pyright: ignore[reportPrivateUsage]
@@ -653,6 +653,11 @@ class ZeroOrOneChoice(_BaseChildElement):
         return "_remove_%s" % self._prop_name
 
 
+# -- raw lxml text/tail accessors, used to bypass `.text` property overrides --
+_raw_text = _Element.text.__get__
+_raw_tail = _Element.tail.__get__
+
+
 # -- lxml typing isn't quite right here, just ignore this error on _Element --
 class BaseOxmlElement(etree.ElementBase, metaclass=MetaOxmlElement):
     """Effective base class for all custom element classes.
@@ -683,6 +688,22 @@ class BaseOxmlElement(etree.ElementBase, metaclass=MetaOxmlElement):
             self.append(elm)
         return elm
 
+    def itertext(self, tag: Any | None = None, *tags: Any, with_tail: bool = True) -> Iterator[str]:
+        """Iterate over text content of this element and its descendants.
+
+        Bypasses the overridden `.text` properties on custom oxml element classes (such as
+        `CT_P`, `CT_R`, `CT_Hyperlink`), which would otherwise duplicate text, so standard
+        lxml `itertext()` semantics are preserved.
+        """
+        for node in self.iter(tag, *tags):
+            text = _raw_text(node)
+            if text:
+                yield text
+            if with_tail and node is not self:
+                tail = _raw_tail(node)
+                if tail:
+                    yield tail
+
     def remove_all(self, *tagnames: str) -> None:
         """Remove child elements with tagname (e.g. "a:p") in `tagnames`."""
         for tagname in tagnames:

{python_docx_oss-0.3.0 → python_docx_oss-0.3.1/src/python_docx_oss.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-docx-oss
-Version: 0.3.0
+Version: 0.3.1
 Summary: Create, read, and update Microsoft Word .docx files.
 Author: Ethan St Lee
 License-Expression: MIT

{python_docx_oss-0.3.0 → python_docx_oss-0.3.1}/src/python_docx_oss.egg-info/SOURCES.txt

@@ -175,6 +175,7 @@ features/txt-add-break.feature
 features/txt-font-color.feature
 features/txt-font-props.feature
 features/txt-parfmt-props.feature
+features/_scratch/test_out.docx
 features/steps/api.py
 features/steps/block.py
 features/steps/comments.py

{python_docx_oss-0.3.0 → python_docx_oss-0.3.1}/tests/integration/customxml/test_custom_xml_roundtrip.py

@@ -11,6 +11,7 @@ import pytest
 
 from docx import Document
 from docx.document import Document as DocumentType
+from docx.oxml.parser import parse_xml
 from docx.parts.customxml import CustomXmlPart
 
 FIXTURE = (
@@ -83,6 +84,28 @@ class DescribeMultipleCustomXmlParts:
         assert "customXml/_rels/item1.xml.rels" in names
         assert "customXml/_rels/item3.xml.rels" in names
 
+    def it_round_trips_replacing_a_custom_xml_part_element(self):
+        document = Document(io.BytesIO(FIXTURE.read_bytes()))
+        customers = _parts_by_name(document)["/customXml/item1.xml"]
+        wrapper = parse_xml('<wrapper xmlns="urn:python-docx-oss:wrapper" version="1"/>')
+        wrapper.append(customers.element)
+        customers.element = wrapper
+
+        output = io.BytesIO()
+        document.save(output)
+        reopened = Document(io.BytesIO(output.getvalue()))
+        replaced = _parts_by_name(reopened)["/customXml/item1.xml"]
+
+        assert replaced.tag == "{urn:python-docx-oss:wrapper}wrapper"
+        assert replaced.attrib["version"] == "1"
+        assert len(replaced.items) == 1
+        assert replaced.items[0].tag == f"{{{CUSTOMERS_NS}}}customers"
+        assert len(replaced.items[0]) == 2
+        with ZipFile(io.BytesIO(output.getvalue())) as package:
+            names = set(package.namelist())
+        assert "customXml/itemProps1.xml" in names
+        assert "customXml/_rels/item1.xml.rels" in names
+
     def it_rejects_an_explicit_partname_collision(self):
         document = Document(io.BytesIO(FIXTURE.read_bytes()))
 

{python_docx_oss-0.3.0 → python_docx_oss-0.3.1}/tests/integration/test_word_roundtrip.py

@@ -10,6 +10,10 @@ from zipfile import ZipFile
 from lxml import etree
 
 from docx import Document
+from docx.opc.constants import CONTENT_TYPE as CT
+from docx.opc.constants import RELATIONSHIP_TYPE as RT
+from docx.oxml import OxmlElement
+from docx.oxml.ns import qn
 
 FIXTURE_DIR = Path(__file__).parent.parent / "fixtures"
 TEST_FILE_DIR = Path(__file__).parent.parent / "test_files"
@@ -73,6 +77,60 @@ class DescribeWordDocumentRoundTrips:
         assert "word/styles.xml" in package
         assert not any(name.startswith("word/media/") for name in package)
 
+    def it_round_trips_a_default_numbering_part_when_the_source_has_none(self):
+        fixture = _fixture("documents", "word-blank.docx")
+        with ZipFile(fixture) as source_package:
+            assert "word/numbering.xml" not in source_package.namelist()
+
+        document = Document(io.BytesIO(fixture.read_bytes()))
+        numbering_part = document.part.numbering_part
+        output = document.to_bytes()
+        reopened = Document(output)
+
+        assert str(numbering_part.partname) == "/word/numbering.xml"
+        assert str(reopened.part.numbering_part.partname) == "/word/numbering.xml"
+        with ZipFile(io.BytesIO(output)) as package_file:
+            package = {name: package_file.read(name) for name in package_file.namelist()}
+        assert "word/numbering.xml" in package
+        assert _content_type(package, "/word/numbering.xml") == CT.WML_NUMBERING
+        relationships = _xml(package, "word/_rels/document.xml.rels")
+        numbering_relationship = relationships.find(
+            f"{{{PR_NS}}}Relationship[@Type='{RT.NUMBERING}']"
+        )
+        assert numbering_relationship is not None
+        assert numbering_relationship.get("Target") == "numbering.xml"
+
+    def it_round_trips_a_changed_external_hyperlink_target(self):
+        document = Document(_fixture("documents", "word-blank.docx").read_bytes())
+        paragraph = document.add_paragraph()
+        relationship_id = document.part.relate_to(
+            "https://example.invalid/objects/old-id",
+            RT.HYPERLINK,
+            is_external=True,
+        )
+        hyperlink = OxmlElement("w:hyperlink")
+        hyperlink.set(qn("r:id"), relationship_id)
+        run = OxmlElement("w:r")
+        text = OxmlElement("w:t")
+        text.text = "Business link"
+        run.append(text)
+        hyperlink.append(run)
+        paragraph._p.append(hyperlink)
+
+        new_target = "https://example.invalid/objects/new-id?position=begin"
+        document.part.rels[relationship_id].target_ref = new_target
+        output = document.to_bytes()
+        reopened = Document(output)
+
+        assert reopened.paragraphs[-1].hyperlinks[0].text == "Business link"
+        assert reopened.paragraphs[-1].hyperlinks[0].address == new_target
+        with ZipFile(io.BytesIO(output)) as package_file:
+            relationships = etree.fromstring(package_file.read("word/_rels/document.xml.rels"))
+        relationship = relationships.find(f"{{{PR_NS}}}Relationship[@Id='{relationship_id}']")
+        assert relationship is not None
+        assert relationship.get("Target") == new_target
+        assert relationship.get("TargetMode") == "External"
+
     def it_creates_independent_document_copies_from_one_snapshot(self):
         source = Document(_fixture("customxml", "multiple-custom-xml-parts.docx").read_bytes())
         source.add_paragraph("Shared snapshot")

{python_docx_oss-0.3.0 → python_docx_oss-0.3.1}/tests/oxml/test_xmlchemy.py

@@ -48,6 +48,16 @@ class DescribeBaseOxmlElement:
         element.remove_all(*tagnames)
         assert element.xml == expected_xml
 
+    def it_iterates_text_without_duplication_when_text_property_is_overridden(self):
+        elm = parse_xml(
+            '<w:p xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'
+            "<w:r><w:t>foo</w:t></w:r>"
+            "<w:hyperlink><w:r><w:t>bar</w:t></w:r></w:hyperlink>"
+            "</w:p>"
+        )
+        assert "".join(elm.itertext()) == "foobar"
+        assert list(elm.itertext(qn("w:t"))) == ["foo", "bar"]
+
     # fixtures ---------------------------------------------
 
     @pytest.fixture(

{python_docx_oss-0.3.0 → python_docx_oss-0.3.1}/tests/oxml/text/test_run.py

@@ -48,3 +48,8 @@ class DescribeCT_R:
         r.texts = "updated"
 
         assert r.text == "updated"
+
+    def it_iterates_text_without_duplication(self):
+        r = cast(CT_R, element('w:r/(w:br,w:t"foo",w:cr,w:t"bar")'))
+
+        assert "".join(r.itertext()) == "foobar"

{python_docx_oss-0.3.0 → python_docx_oss-0.3.1}/tests/test_sanitize.py

@@ -9,6 +9,7 @@ from zipfile import ZipFile
 from lxml import etree
 
 from docx import Document
+from docx.opc.constants import RELATIONSHIP_TYPE as RT
 from docx.opc.packuri import PackURI
 from docx.opc.part import Part
 from docx.oxml import OxmlElement
@@ -145,6 +146,56 @@ def it_removes_the_entire_web_extension_relationship_tree():
         assert not any(name.startswith("word/webextensions/") for name in archive.namelist())
 
 
+def it_round_trips_cleanup_without_removing_application_content():
+    document = Document(COMMENTS_FIXTURE)
+    custom_xml = document.part.add_custom_xml_part(
+        '<application xmlns="urn:python-docx-oss:application" version="1"/>'
+    )
+    business_relationship_id = document.part.relate_to(
+        "https://example.invalid/business/object-id",
+        RT.HYPERLINK,
+        is_external=True,
+    )
+    package = document.part.package
+    taskpanes = Part(
+        PackURI("/word/webextensions/taskpanes.xml"),
+        "application/vnd.ms-office.webextensiontaskpanes+xml",
+        b"<wetp:taskpanes xmlns:wetp='urn:test'/>",
+        package,
+    )
+    extension = Part(
+        PackURI("/word/webextensions/webextension1.xml"),
+        "application/vnd.ms-office.webextension+xml",
+        b"<we:webextension xmlns:we='urn:test'/>",
+        package,
+    )
+    package.relate_to(
+        taskpanes,
+        "http://schemas.microsoft.com/office/2011/relationships/webextensiontaskpanes",
+    )
+    taskpanes.relate_to(
+        extension,
+        "http://schemas.microsoft.com/office/2011/relationships/webextension",
+    )
+
+    report = document.sanitize(comments=True, web_extensions=True)
+    output = document.to_bytes()
+    reopened = Document(output)
+
+    assert report.removed_comment_markers > 0
+    assert str(custom_xml.partname) not in report.removed_parts
+    assert reopened.part.custom_xml_parts[0].tag == ("{urn:python-docx-oss:application}application")
+    assert reopened.part.rels[business_relationship_id].target_ref == (
+        "https://example.invalid/business/object-id"
+    )
+    assert reopened.sanitize(comments=True, web_extensions=True).changed is False
+    with ZipFile(io.BytesIO(output)) as archive:
+        names = archive.namelist()
+        assert "customXml/item1.xml" in names
+        assert "word/comments.xml" not in names
+        assert not any(name.startswith("word/webextensions/") for name in names)
+
+
 def it_removes_formatting_revisions_and_keeps_current_formatting():
     document = Document()
     paragraph = document.add_paragraph()