fix(direction): le sens du document traduit suit la langue cible, dans les deux sens

Persan -> francais : le document traduit restait en lecture de droite a
gauche, heritee de la source. Trois causes :

- PDF : regression du renommage precedent — le choix d'alignement
  testait la fonction is_rtl (toujours vraie) au lieu du parametre :
  tout texte traduit s'alignait a droite, quelle que soit la cible.
  Corrige + test epinglant l'alignement gauche pour une cible latine.
- Word : les marques RTL heritees (bidi, rtl, bidiVisual, notes et
  commentaires compris) sont desormais retirees quand la cible est
  latine ; retrait fait sur une liste figee (l'iterateur lxml sautait
  des elements pendant la suppression).
- Excel : les feuilles heritees d'un affichage droite-a-gauche sont
  remises en lecture gauche-a-droite pour une cible latine.
- PowerPoint : les attributs rtl herites sont retires pour une cible
  latine (alignements visuels conserves).

3 tests de bout en bout nouveaux : document RTL traduit vers le
francais ressort en lecture gauche-a-droite dans les trois formats.

tests/test_translators/test_rtl_layout.py

@@ -855,6 +855,21 @@ class TestPdfLayoutModeRtl:
         assert ok is True
         assert page.calls[0]["text"] == "Bonjour le monde"
 
+    def test_ltr_target_is_left_aligned(self):
+        """Regression guard: a Latin target (e.g. Persian → French) must be
+        left-aligned. A previous rename once made the alignment test the
+        truthiness of the imported is_rtl *function* — always true — and
+        every translated PDF came out right-aligned."""
+        import fitz
+
+        translator = PDFTranslator()
+        page = _FakePage()
+        ok = translator._write_translated_block(
+            page, self._block("Bonjour le monde"), font_path=None, rtl_target=False
+        )
+        assert ok is True
+        assert page.calls[0]["align"] == fitz.TEXT_ALIGN_LEFT
+
 
 class TestPdfFontSelection:
     def test_arabic_script_target_prefers_arabic_font(self, tmp_path, monkeypatch):
@@ -1054,3 +1069,85 @@ class TestPdfCleanModeRtl:
         # Presentation forms in the output prove both the shaping and the
         # Arabic-capable font reached the PDF (Helvetica cannot encode them).
         assert any(0xFB50 <= ord(c) <= 0xFEFF for c in extracted)
+
+
+# ---------------------------------------------------------------------------
+# Normalisation LTR — un document source RTL traduit vers une cible latine
+# (ex. persan → français) doit ressortir en lecture gauche-à-droite
+# ---------------------------------------------------------------------------
+
+
+class TestLtrNormalization:
+    def test_word_rtl_source_latin_target_strips_rtl(self, tmp_path):
+        """Persan → français : bidi/rtl/bidiVisual hérités de la source
+        sont retirés (corps, section, note de bas de page, tableau)."""
+        # 1) Fabrication d'un document RTL complet (cible fa)
+        t_fa = WordTranslator(
+            provider=MockTranslationProvider({"Hello": "FA1", "Extra": "FA2"})
+        )
+        doc = Document()
+        doc.add_paragraph("Hello")
+        table = doc.add_table(rows=1, cols=2)
+        table.cell(0, 0).text = "Extra"
+        fa_in = tmp_path / "in.docx"
+        doc.save(fa_in)
+        _inject_footnotes_part(fa_in)
+        fa_out = tmp_path / "fa.docx"
+        t_fa.translate_file(fa_in, fa_out, "fa")
+
+        # Sanity : la sortie fa porte bien les marques RTL
+        fa_doc = etree.fromstring(_read_zip_entry(fa_out, "word/document.xml"))
+        assert fa_doc.find(f".//{{{W_NS}}}bidi") is not None
+        fa_notes = etree.fromstring(_read_zip_entry(fa_out, "word/footnotes.xml"))
+        assert fa_notes.find(f".//{{{W_NS}}}bidi") is not None
+
+        # 2) Traduction de ce document RTL vers le français
+        t_fr = WordTranslator(
+            provider=MockTranslationProvider({"FA1": "Bonjour", "FA2": "ExtraFR"})
+        )
+        fr_out = tmp_path / "fr.docx"
+        t_fr.translate_file(fa_out, fr_out, "fr")
+
+        fr_doc = etree.fromstring(_read_zip_entry(fr_out, "word/document.xml"))
+        assert fr_doc.find(f".//{{{W_NS}}}bidi") is None
+        assert fr_doc.find(f".//{{{W_NS}}}rtl") is None
+        assert fr_doc.find(f".//{{{W_NS}}}bidiVisual") is None
+        fr_notes = etree.fromstring(_read_zip_entry(fr_out, "word/footnotes.xml"))
+        assert fr_notes.find(f".//{{{W_NS}}}bidi") is None
+        # La traduction française est bien là
+        assert "Bonjour" in "".join(t.text or "" for t in fr_doc.iter(f"{{{W_NS}}}t"))
+
+    def test_excel_rtl_source_latin_target_restores_ltr(self, tmp_path):
+        wb = Workbook()
+        wb.active["A1"] = "سلام"
+        wb.active.sheet_view.rightToLeft = True  # feuille d'origine persane
+        input_file = tmp_path / "in.xlsx"
+        wb.save(input_file)
+
+        out = tmp_path / "out.xlsx"
+        ExcelTranslator(provider=MockTranslationProvider({"سلام": "Bonjour"})).translate_file(
+            input_file, out, "fr"
+        )
+        assert not load_workbook(out).active.sheet_view.rightToLeft
+
+    def test_pptx_rtl_source_latin_target_strips_rtl(self, tmp_path):
+        prs = Presentation()
+        slide = prs.slides.add_slide(prs.slide_layouts[6])
+        box = slide.shapes.add_textbox(Inches(1), Inches(1), Inches(4), Inches(1))
+        para = box.text_frame.paragraphs[0]
+        para.text = "سلام"
+        # Simule un paragraphe d'origine persane
+        pPr = para._p.get_or_add_pPr()
+        pPr.set("rtl", "1")
+        input_file = tmp_path / "in.pptx"
+        prs.save(input_file)
+
+        out = tmp_path / "out.pptx"
+        PowerPointTranslator(
+            provider=MockTranslationProvider({"سلام": "Bonjour"})
+        ).translate_file(input_file, out, "fr")
+
+        out_para = _find_pptx_paragraph(Presentation(str(out)), "Bonjour")
+        assert out_para is not None
+        out_pPr = out_para._p.find(f"{{{A_NS}}}pPr")
+        assert out_pPr is None or out_pPr.get("rtl") != "1"

translators/excel_translator.py

@@ -355,25 +355,35 @@ class ExcelTranslator:
                     except Exception as e:
                         _log_error("excel_sheet_images_failed", sheet_name=sheet_name, error=str(e))
 
-            # RTL targets: flip the sheet view so every sheet reads
+            # Normalize the sheet reading direction to the TARGET language.
-            # right-to-left (column A renders rightmost). Content and
+            # RTL targets: flip every sheet so column A renders rightmost.
-            # formatting are untouched — only the reading direction.
+            # Latin targets: restore left-to-right on sheets inherited from
+            # an RTL source (Persian → French must not keep the RTL view).
+            # Content and formatting are untouched — only the direction.
             # Chartsheets have no `sheet_view` and must never break the
             # save: each sheet is guarded individually.
-            if is_rtl(target_language):
+            rtl_target = is_rtl(target_language)
-                flipped = 0
+            flipped = 0
-                for sheet_name in workbook.sheetnames:
+            for sheet_name in workbook.sheetnames:
-                    ws = workbook[sheet_name]
+                ws = workbook[sheet_name]
-                    try:
+                try:
-                        if getattr(ws, "sheet_view", None) is not None:
+                    if getattr(ws, "sheet_view", None) is None:
-                            ws.sheet_view.rightToLeft = True
+                        continue
-                            flipped += 1
+                    if rtl_target:
-                    except Exception as e:
+                        ws.sheet_view.rightToLeft = True
-                        _log_error(
+                        flipped += 1
-                            "excel_rtl_view_failed", sheet=sheet_name, error=str(e)
+                    elif getattr(ws.sheet_view, "rightToLeft", False):
-                        )
+                        ws.sheet_view.rightToLeft = False
-                if flipped:
+                        flipped += 1
-                    _log_info("excel_rtl_view_applied", sheets=flipped)
+                except Exception as e:
+                    _log_error(
+                        "excel_direction_view_failed", sheet=sheet_name, error=str(e)
+                    )
+            if flipped:
+                _log_info(
+                    "excel_rtl_view_applied" if rtl_target else "excel_ltr_view_restored",
+                    sheets=flipped,
+                )
 
             try:
                 workbook.save(output_path)

translators/pdf_translator.py

@@ -1063,7 +1063,7 @@ class PDFTranslator:
         target_size = block["font_size"]
 
         color = self._int_to_rgb(block["color"])
-        align = fitz.TEXT_ALIGN_RIGHT if is_rtl else fitz.TEXT_ALIGN_LEFT
+        align = fitz.TEXT_ALIGN_RIGHT if rtl_target else fitz.TEXT_ALIGN_LEFT
 
         # PyMuPDF bug: fontname=None raises AttributeError. Default to 'helv'.
         # If a custom font file is available, use it via fontfile (fontname ignored).

translators/pptx_translator.py

@@ -121,6 +121,46 @@ def _apply_rtl_to_presentation(presentation: Presentation) -> None:
                 _set_pptx_paragraph_rtl(paragraph)
 
 
+def _unset_pptx_paragraph_rtl(paragraph) -> None:
+    """Drop a paragraph's inherited RTL direction (Latin targets).
+
+    Translating a Persian/Arabic source into a Latin target must not keep
+    the source's rtl="1" marks: with rtl gone the paragraph falls back to
+    the natural left-to-right direction. Alignment attributes are left
+    untouched (algn is visual in DrawingML — centered stays centered).
+    """
+    pPr = paragraph._p.find(f"{{{_NS_A}}}pPr")
+    if pPr is not None and pPr.get("rtl") == "1":
+        pPr.attrib.pop("rtl", None)
+
+
+def _apply_ltr_to_presentation(presentation: Presentation) -> None:
+    """Strip inherited RTL direction from all slides and notes (Latin targets)."""
+    for slide in presentation.slides:
+        for shape in slide.shapes:
+            _apply_ltr_to_shape(shape)
+        if slide.has_notes_slide and slide.notes_slide.notes_text_frame is not None:
+            for paragraph in slide.notes_slide.notes_text_frame.paragraphs:
+                _unset_pptx_paragraph_rtl(paragraph)
+
+
+def _apply_ltr_to_shape(shape) -> None:
+    """Recursively strip RTL from a shape (handles groups and tables)."""
+    if shape.has_text_frame:
+        for paragraph in shape.text_frame.paragraphs:
+            _unset_pptx_paragraph_rtl(paragraph)
+
+    if shape.shape_type == MSO_SHAPE_TYPE.TABLE:
+        for row in shape.table.rows:
+            for cell in row.cells:
+                for paragraph in cell.text_frame.paragraphs:
+                    _unset_pptx_paragraph_rtl(paragraph)
+
+    if shape.shape_type == MSO_SHAPE_TYPE.GROUP:
+        for sub_shape in shape.shapes:
+            _apply_ltr_to_shape(sub_shape)
+
+
 def _apply_rtl_to_shape(shape) -> None:
     """Recursively apply RTL to a shape (handles groups and tables)."""
     if shape.has_text_frame:
@@ -468,9 +508,14 @@ class PowerPointTranslator:
                                 index=i,
                             )
 
-            # Apply RTL layout when the target language is written right-to-left.
+            # Normalize the direction to the TARGET language: RTL targets
+            # switch to right-to-left, Latin targets strip the rtl marks
+            # inherited from an RTL source (Persian → French must read
+            # left-to-right, not keep the source's layout).
             if is_rtl(target_language):
                 _apply_rtl_to_presentation(presentation)
+            else:
+                _apply_ltr_to_presentation(presentation)
 
             # CJK font hint so the target script renders with a proper
             # typeface instead of shape-dependent fallbacks.

translators/word_translator.py

@@ -282,6 +282,94 @@ def _apply_bidi_to_part_tree(root) -> int:
     return switched
 
 
+def _normalize_part_direction(root, rtl: bool) -> int:
+    """
+    Normalize the direction of a footnotes/endnotes/comments tree.
+
+    RTL target: every paragraph/run/table switches to RTL (same marks as
+    the document body). Latin target: inherited RTL marks from an RTL
+    source are stripped so the translated notes read left-to-right.
+    Returns the number of paragraphs switched (RTL) or marks removed (LTR).
+    """
+    if rtl:
+        return _apply_bidi_to_part_tree(root)
+    return _strip_rtl_marks(root)
+
+
+def _strip_rtl_marks(root) -> int:
+    """
+    Remove every RTL direction mark under an element tree (LTR targets).
+
+    Translating a Persian/Arabic source into a Latin target must not keep
+    the source's right-to-left layout: w:bidi (paragraph/section
+    direction), w:rtl (run-level marks, including paragraph marks inside
+    w:pPr/w:rPr) and w:bidiVisual (mirrored tables) are stripped so the
+    translated document reads left-to-right, exactly like a document
+    written in the target language.
+
+    Works on python-docx trees and plain lxml trees (notes/comments
+    parts) alike. Returns the number of marks removed.
+    """
+    removed = 0
+    # Materialize the iteration first: removing children while a live
+    # lxml iterator walks the tree makes it skip elements (seen in
+    # practice: some w:bidi survived the strip).
+    for el in list(root.iter()):
+        if el.tag == qn("w:pPr") or el.tag == qn("w:sectPr"):
+            bidi = el.find(qn("w:bidi"))
+            if bidi is not None:
+                el.remove(bidi)
+                removed += 1
+        elif el.tag == qn("w:rPr"):
+            rtl = el.find(qn("w:rtl"))
+            if rtl is not None:
+                el.remove(rtl)
+                removed += 1
+        elif el.tag == qn("w:tblPr"):
+            bidi_visual = el.find(qn("w:bidiVisual"))
+            if bidi_visual is not None:
+                el.remove(bidi_visual)
+                removed += 1
+    return removed
+
+
+def _apply_ltr_to_document(document: Document) -> None:
+    """
+    Force left-to-right direction on the whole document (Latin targets).
+
+    Mirror of _apply_rtl_to_document: an RTL source translated to a Latin
+    target must end up reading left-to-right, not keep the source's RTL
+    layout. Stripping alone is enough — with w:bidi gone, paragraphs fall
+    back to the natural LTR start edge, and explicit alignments (center,
+    justify) keep their meaning.
+    """
+    stripped = _strip_rtl_marks(document.element)
+
+    for section in document.sections:
+        headers_footers = (
+            section.header,
+            section.footer,
+            getattr(section, "first_page_header", None),
+            getattr(section, "first_page_footer", None),
+            getattr(section, "even_page_header", None),
+            getattr(section, "even_page_footer", None),
+        )
+        for hf in headers_footers:
+            if hf is None:
+                continue
+            root = getattr(hf, "_element", None)
+            if root is None:
+                paras = hf.paragraphs
+                if paras:
+                    root = paras[0]._p.getroottree().getroot()
+            if root is not None:
+                stripped += _strip_rtl_marks(root)
+
+    if stripped:
+        from core.logging import get_logger as _gl
+        _gl(__name__).info("word_ltr_normalized", marks_removed=stripped)
+
+
 def _apply_rtl_to_document(document: Document) -> None:
     """Apply RTL direction to every paragraph and section in the document."""
     body = document.element.body
@@ -577,9 +665,14 @@ class WordTranslator:
                                 index=i,
                             )
 
-            # Apply RTL layout when the target language is written right-to-left.
+            # Normalize the document direction to the TARGET language:
+            # RTL targets switch to right-to-left, Latin targets strip the
+            # RTL marks inherited from an RTL source (Persian → French
+            # must read left-to-right, not keep the source's layout).
             if is_rtl(target_language):
                 _apply_rtl_to_document(document)
+            else:
+                _apply_ltr_to_document(document)
 
             # CJK / Arabic-script font hints so Word renders the target
             # script with a proper typeface instead of per-run fallbacks.
@@ -1046,8 +1139,7 @@ class WordTranslator:
             # setters hold references to t_elems inside this tree.
             def write_footnotes_back(output_path: Path) -> None:
                 try:
-                    if rtl:
+                    _normalize_part_direction(footnotes_xml, rtl)
-                        _apply_bidi_to_part_tree(footnotes_xml)
                     new_blob = etree.tostring(
                         footnotes_xml,
                         xml_declaration=True,
@@ -1114,8 +1206,7 @@ class WordTranslator:
         if text_elements and post_save_callbacks is not None:
             def write_endnotes_back(output_path: Path) -> None:
                 try:
-                    if rtl:
+                    _normalize_part_direction(endnotes_xml, rtl)
-                        _apply_bidi_to_part_tree(endnotes_xml)
                     new_blob = etree.tostring(
                         endnotes_xml,
                         xml_declaration=True,
@@ -1170,8 +1261,7 @@ class WordTranslator:
         if collected and post_save_callbacks is not None:
             def write_comments_back(output_path: Path) -> None:
                 try:
-                    if rtl:
+                    _normalize_part_direction(comments_xml, rtl)
-                        _apply_bidi_to_part_tree(comments_xml)
                     new_blob = etree.tostring(
                         comments_xml,
                         xml_declaration=True,