mirror of
https://github.com/guillaumemeyer/watermarks-remover.git
synced 2026-08-22 13:11:57 +02:00
483c0479fc
* fix: decode XML entities before Layer A scrub in OOXML/ODF Watermark carriers encoded as XML character references (e.g. ​) reached Layer A as nine ASCII characters and survived cleaning untouched, because the XML parser in Word/Writer decodes the entity back into the invisible carrier after the cleaner ran (#129). A shared _decode_xml_entities resolves exactly what a conforming XML parser resolves (numeric references and the five predefined entities) and leaves everything else literal. The DOCX/XLSX/PPTX text-run scrubbers decode before clean_text and re-encode on the way out; the ODT scrubber splits paragraph content into markup and text segments and only round-trips the text segments, because a whole-paragraph decode/re-encode would entity-escape the nested text:span/text:tab markup. Untouched runs keep their original bytes. * fix: satisfy ruff lint and format checks --------- Co-authored-by: yzxcj797 <yzxcj797@users.noreply.github.com> Co-authored-by: Guillaume Meyer (The Opinionated Man) <1385518+guillaumemeyer@users.noreply.github.com>
118 lines
4.6 KiB
Python
118 lines
4.6 KiB
Python
"""Regression tests for entity-encoded watermark carriers (#129).
|
||
|
||
A zero-width space written as ``​`` reaches Layer A as nine ASCII
|
||
characters and survived cleaning untouched, because the XML parser in
|
||
Word/Writer decodes the entity back into the invisible carrier after the
|
||
cleaner has run. The scrub now decodes XML character references before
|
||
cleaning and re-encodes on the way out.
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import io
|
||
import sys
|
||
import zipfile
|
||
from pathlib import Path
|
||
|
||
ROOT = Path(__file__).resolve().parents[1]
|
||
SCRIPTS = ROOT / "service" / "scripts"
|
||
sys.path.insert(0, str(SCRIPTS))
|
||
|
||
from container_meta import _decode_xml_entities, _reencode_xml_text, clean_docx, clean_odt
|
||
|
||
|
||
def test_decode_resolves_numeric_and_predefined_entities_only():
|
||
assert _decode_xml_entities("​") == "\u200b"
|
||
assert _decode_xml_entities("​") == "\u200b"
|
||
assert _decode_xml_entities("&<>") == "&<>"
|
||
# HTML5-only named entities stay literal (an XML parser would not resolve them).
|
||
assert _decode_xml_entities(" ") == " "
|
||
# Invalid code points stay literal for the real parser to reject.
|
||
assert _decode_xml_entities("�") == "�"
|
||
assert _decode_xml_entities("�") == "�"
|
||
|
||
|
||
def test_reencode_round_trip_is_stable():
|
||
assert _reencode_xml_text("a&b<c>d") == "a&b<c>d"
|
||
decoded = _decode_xml_entities("Hello & welcome")
|
||
assert _reencode_xml_text(decoded) == "Hello & welcome"
|
||
|
||
|
||
def _make_docx(body_text: str) -> bytes:
|
||
buf = io.BytesIO()
|
||
with zipfile.ZipFile(buf, "w") as zf:
|
||
zf.writestr(
|
||
"[Content_Types].xml",
|
||
'<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">'
|
||
'<Default Extension="xml" ContentType="application/xml"/>'
|
||
'<Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/>'
|
||
"</Types>",
|
||
)
|
||
zf.writestr(
|
||
"word/document.xml",
|
||
'<?xml version="1.0"?><w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'
|
||
"<w:body><w:p><w:r><w:t>" + body_text + "</w:t></w:r></w:p></w:body></w:document>",
|
||
)
|
||
return buf.getvalue()
|
||
|
||
|
||
def test_entity_encoded_zero_width_space_is_scrubbed():
|
||
data = _make_docx("Hello​World")
|
||
cleaned, actions = clean_docx(data)
|
||
|
||
with zipfile.ZipFile(io.BytesIO(cleaned)) as zf:
|
||
document = zf.read("word/document.xml").decode()
|
||
|
||
# The entity must not survive in any form: neither the raw reference nor
|
||
# the decoded character (which a parser would resurrect).
|
||
assert "​" not in document
|
||
assert "\u200b" not in document
|
||
assert "HelloWorld" in document
|
||
assert any(a for a in actions), "cleaning must report an action"
|
||
|
||
|
||
def test_clean_text_without_carriers_is_byte_identical():
|
||
data = _make_docx("Hello World")
|
||
cleaned, _ = clean_docx(data)
|
||
with zipfile.ZipFile(io.BytesIO(cleaned)) as zf:
|
||
document = zf.read("word/document.xml").decode()
|
||
assert "Hello World" in document
|
||
|
||
|
||
def test_legitimate_ampersand_entity_round_trips():
|
||
data = _make_docx("Tom & Jerry")
|
||
cleaned, _ = clean_docx(data)
|
||
with zipfile.ZipFile(io.BytesIO(cleaned)) as zf:
|
||
document = zf.read("word/document.xml").decode()
|
||
# The ampersand survives as a well-formed reference, not a bare &.
|
||
assert "Tom & Jerry" in document
|
||
|
||
|
||
def _make_odt(body: str) -> bytes:
|
||
buf = io.BytesIO()
|
||
with zipfile.ZipFile(buf, "w") as zf:
|
||
zf.writestr("mimetype", "application/vnd.oasis.opendocument.text")
|
||
zf.writestr(
|
||
"content.xml",
|
||
'<?xml version="1.0"?><office:document-content '
|
||
'xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0" '
|
||
'xmlns:text="urn:oasis:names:tc:opendocument:xmlns:text:1.0">'
|
||
"<office:body><office:text>"
|
||
'<text:p text:style-name="Standard">' + body + "</text:p>"
|
||
"</office:text></office:body></office:document-content>",
|
||
)
|
||
return buf.getvalue()
|
||
|
||
|
||
def test_odt_entity_encoded_carrier_scrubbed_and_markup_preserved():
|
||
data = _make_odt("Hi​<text:span>world</text:span>!")
|
||
cleaned, _ = clean_odt(data)
|
||
with zipfile.ZipFile(io.BytesIO(cleaned)) as zf:
|
||
content = zf.read("content.xml").decode()
|
||
|
||
assert "​" not in content
|
||
assert "" not in content
|
||
# The nested span markup must stay intact (not entity-escaped).
|
||
assert "<text:span>world</text:span>" in content
|
||
assert "Hi" in content and "!</text:p>" in content
|