fix(rtl): les textes centrs en persan s'affichaient du mauvais cote

- Word: sous w:bidi, w:jc est logique (left=dbut=droite visuelle,
  right=fin=gauche visuelle) ; forcer jc=right alignait donc les
  paragraphes a gauche et crasait le centrage hrit du style.
  Dsormais le RTL pose w:bidi et w:rtl sans jamais toucher w:jc,
  comme le fait Word lui-mme pour un document RTL.
- PowerPoint: algn n'est plus crit quand le paragraphe n'en dfinit
  pas, afin de respecter l'alignement hrit du masque (titres centrs) ;
  algn=l explicite reste converti en r (algn est visuel en DrawingML).
- tests: centrage par style Word prserv, aucun w:jic crit, algn
  absent non cras côté PowerPoint
This commit is contained in:
2026-09-01 20:45:05 +02:00
parent f22f645fab
commit ffbd85a7b6
3 changed files with 70 additions and 19 deletions

View File

@@ -22,6 +22,7 @@ from pathlib import Path
import pytest
from docx import Document
from docx.enum.style import WD_STYLE_TYPE
from docx.enum.text import WD_ALIGN_PARAGRAPH
from lxml import etree
from openpyxl import Workbook, load_workbook
@@ -447,6 +448,46 @@ class TestWordRtlLayout:
)
assert marker in part_text, part_name
def test_fa_target_never_writes_alignment(self, tmp_path):
"""Reported bug: centered Persian text rendered on the wrong side.
Under w:bidi, Word interprets w:jc logically: "right" means the
END of the line — the visual LEFT for RTL. Writing jc="right"
pushes unaligned paragraphs to the left and overrides style-level
centering. RTL must add w:bidi (+ run w:rtl) and never touch
w:jc: unaligned paragraphs start at the right edge, explicit
"left" resolves to the right edge, and centering stays centering.
"""
provider = MockTranslationProvider(
{"Plain body": "FA1", "Styled centered title": "FA2"}
)
translator = WordTranslator(provider=provider)
doc = Document()
doc.add_paragraph("Plain body") # no alignment anywhere
style = doc.styles.add_style("CenteredCustom", WD_STYLE_TYPE.PARAGRAPH)
style.paragraph_format.alignment = WD_ALIGN_PARAGRAPH.CENTER
doc.add_paragraph("Styled centered title", style=style) # centered via style
input_file = tmp_path / "input.docx"
doc.save(input_file)
output_file = tmp_path / "output.docx"
translator.translate_file(input_file, output_file, "fa")
doc_out = Document(output_file)
for para in doc_out.paragraphs:
pPr = para._p.find(f"{{{W_NS}}}pPr")
assert pPr is not None
assert pPr.find(f"{{{W_NS}}}bidi") is not None
assert pPr.find(f"{{{W_NS}}}jc") is None, "RTL must never write w:jc"
# The style-level centering still resolves to centered
assert (
doc_out.paragraphs[1].style.paragraph_format.alignment
== WD_ALIGN_PARAGRAPH.CENTER
)
assert "FA2" in doc_out.paragraphs[1].text
def test_fr_target_no_rtl_attributes(self, tmp_path):
"""A non-RTL target produces no bidi/bidiVisual/rtl markup."""
provider = MockTranslationProvider({"Body text": "FR_Body"})
@@ -552,7 +593,14 @@ class TestPptxRtlLayout:
assert pPr.get("rtl") == "1"
assert pPr.get("algn") == "just", "justified alignment must be preserved"
def test_alignment_absent_becomes_right(self, tmp_path):
def test_alignment_absent_inherits_from_layout(self, tmp_path):
"""Reported bug: centered Persian text rendered on the wrong side.
When algn is absent the paragraph inherits its alignment from
the layout/master (often centered titles); writing algn="r"
overrides that inheritance. rtl="1" alone already renders the
paragraph from its start edge (right), so algn stays untouched.
"""
provider = MockTranslationProvider({"Plain text": "AR_Plain"})
translator = PowerPointTranslator(provider=provider)
input_file = self._build_single_text_pptx(tmp_path, "Plain text")
@@ -564,7 +612,7 @@ class TestPptxRtlLayout:
pPr = para._p.find(f"{{{A_NS}}}pPr")
assert pPr is not None
assert pPr.get("rtl") == "1"
assert pPr.get("algn") == "r"
assert pPr.get("algn") is None, "inherited alignment must not be overridden"
def test_alignment_left_becomes_right(self, tmp_path):
provider = MockTranslationProvider({"Left text": "AR_Left"})

View File

@@ -73,9 +73,15 @@ def _set_pptx_paragraph_rtl(paragraph) -> None:
Enable RTL mode on a PowerPoint paragraph.
Sets rtl="1" on the <a:pPr> element, which controls the paragraph
text direction. The horizontal alignment (algn) is only forced to
"r" when the paragraph has no explicit alignment or is aligned
"l" (left) — a centered or justified title keeps its alignment.
text direction; with rtl="1" and no explicit algn, PowerPoint
renders the paragraph from its start edge — the right edge.
algn is only rewritten when the paragraph explicitly says "l": in
DrawingML algn is visual (not logical like Word's w:jc), so an
explicit left would keep RTL text on the left edge. When algn is
absent, the inherited layout/master alignment (often centered
titles) must keep playing — writing "r" here would override it,
which is the centered-text mis-rendering reported for Persian.
"""
p_elem = paragraph._p
tag_pPr = f"{{{_NS_A}}}pPr"
@@ -84,7 +90,7 @@ def _set_pptx_paragraph_rtl(paragraph) -> None:
pPr = etree.Element(tag_pPr)
p_elem.insert(0, pPr)
pPr.set("rtl", "1")
if pPr.get("algn") in (None, "", "l"):
if pPr.get("algn") == "l":
pPr.set("algn", "r")

View File

@@ -153,8 +153,6 @@ _PPR_BIDI_SUCCESSORS = (
qn("w:sectPr"),
qn("w:pPrChange"),
)
# Elements that must come AFTER w:jc inside w:pPr (w:jc itself excluded).
_PPR_JC_SUCCESSORS = _PPR_BIDI_SUCCESSORS[_PPR_BIDI_SUCCESSORS.index(qn("w:jc")) + 1 :]
# Elements that must come AFTER w:rtl inside w:rPr.
_RPR_RTL_SUCCESSORS = (
qn("w:cs"),
@@ -205,11 +203,18 @@ def _set_paragraph_rtl(paragraph: Paragraph) -> None:
Sets:
- w:pPr/w:bidi → paragraph text direction = RTL
- w:pPr/w:jc → mirrored alignment (left→right), ONLY when the
paragraph has no explicit alignment — centered/justified titles
must not be forced right-aligned.
- w:rPr/w:rtl → run-level RTL marker for each run
w:jc is deliberately left untouched. Under w:bidi, Word interprets
w:jc LOGICALLY (start/end), not visually: "left" means the start —
the RIGHT edge for an RTL paragraph — and "right" means the end, the
LEFT edge. Forcing jc="right" therefore aligns paragraphs to the
visual left and overrides style-level centering, which is exactly
the mis-rendering reported for centered Persian text. With bidi
alone: unaligned paragraphs start at the right edge, "left" resolves
to the right edge, and center/justify stay centered/justified — the
same markup Word itself writes for RTL documents.
Every element is inserted at its schema position inside w:pPr/w:rPr
(OOXML requires a fixed child order; appended-at-the-end elements
make Word flag the file for repair).
@@ -219,14 +224,6 @@ def _set_paragraph_rtl(paragraph: Paragraph) -> None:
if pPr.find(qn("w:bidi")) is None:
_insert_ordered(pPr, OxmlElement("w:bidi"), _PPR_BIDI_SUCCESSORS)
jc = pPr.find(qn("w:jc"))
explicit_alignment = jc is not None and jc.get(qn("w:val")) not in (None, "", "left")
if not explicit_alignment:
if jc is None:
jc = OxmlElement("w:jc")
_insert_ordered(pPr, jc, _PPR_JC_SUCCESSORS)
jc.set(qn("w:val"), "right")
for run in paragraph.runs:
rPr = run._r.get_or_add_rPr()
if rPr.find(qn("w:rtl")) is None: