PASSAGES: two languages possible, STET: fully specified passage bolding

Makefile

@@ -10,19 +10,25 @@ endif
 
 .PHONY: pipupgrade
 pipupgrade: checkvenv
-	pip install --upgrade pip
+	# pip-tools is not ready for pip 26
+	pip install pip==25.2
+	# pip install --upgrade pip
 
 .PHONY: pyupgrade
 pyupgrade: checkvenv pipupgrade
 # checks if pip-tools is installed
 ifeq ("$(wildcard .venv/bin/pip-compile)","")
 	@echo "Installing Pip-tools..."
-	@pip install --no-cache-dir pip-tools
+	# @pip install --no-cache-dir pip-tools
+	# pip-tools is not ready for pip 26
+	@pip install --no-cache-dir pip-tools==7.5.2
 endif
 
 ifeq ("$(wildcard .venv/bin/pip-sync)","")
 	@echo "Installing Pip-tools..."
-	@pip install --no-cache-dir pip-tools
+	# @pip install --no-cache-dir pip-tools
+	# pip-tools is not ready for pip 26
+	@pip install --no-cache-dir pip-tools==7.5.2
 endif
 
 .PHONY: install-cython

backend/doc/domain/resource_lookup.py

@@ -48,7 +48,6 @@
 from filelock import FileLock
 from pydantic import HttpUrl, ValidationError
 
-
 logger = settings.logger(__name__)
 
 fetch_source_data_cache: TTLCache[str, SourceData] = TTLCache(
@@ -821,24 +820,16 @@ def get_book_codes_for_lang_(
                 manifest_name = book_codes_and_names_localized_from_manifest.get(
                     code, ""
                 )
-                if not name and manifest_name:
-                    book_codes_and_names_localized.append(
-                        (
-                            code,
-                            maybe_correct_book_name(
-                                lang_code, normalize_localized_book_name(manifest_name)
-                            ),
-                        )
-                    )
-                else:
-                    book_codes_and_names_localized.append(
-                        (
-                            code,
-                            maybe_correct_book_name(
-                                lang_code, normalize_localized_book_name(name)
-                            ),
-                        )
+                chosen_name = name or manifest_name
+                book_codes_and_names_localized.append(
+                    (
+                        code,
+                        maybe_correct_book_name(
+                            lang_code,
+                            normalize_localized_book_name(chosen_name),
+                        ),
                     )
+                )
         elif (
             use_localized_book_name
             and len(repo_components) > 2
@@ -862,7 +853,8 @@ def get_book_codes_for_lang_(
                 (
                     repo_components[1],
                     maybe_correct_book_name(
-                        lang_code, normalize_localized_book_name(book_name_)
+                        lang_code,
+                        normalize_localized_book_name(book_name_),
                     ),
                 )
             )
@@ -882,14 +874,22 @@ def get_book_codes_for_lang_(
             )
     logger.debug("book_codes_and_names: %s", book_codes_and_names)
     logger.debug("book_codes_and_names_localized: %s", book_codes_and_names_localized)
-    if not book_codes_and_names_localized or any(
-        name == "" for _, name in book_codes_and_names_localized
-    ):
-        unique_values = unique_book_codes(book_codes_and_names)
-    else:
-        unique_values = unique_book_codes(book_codes_and_names_localized)
+    localized_map: dict[str, str] = {
+        code: name for code, name in book_codes_and_names_localized
+    }
+    non_localized_map: dict[str, str] = {
+        code: name for code, name in book_codes_and_names
+    }
+    merged: list[tuple[str, str]] = []
+    for code in set(localized_map) | set(non_localized_map):
+        name = localized_map.get(code, "")
+        if not name:
+            name = non_localized_map.get(code, "")
+        merged.append((code, name))
+    unique_values = unique_book_codes(merged)
     return sorted(
-        unique_values, key=lambda book_code_and_name: book_id_map[book_code_and_name[0]]
+        unique_values,
+        key=lambda book_code_and_name: book_id_map[book_code_and_name[0]],
     )
 
 
@@ -1212,11 +1212,14 @@ def nt_survey_rg_passages(
     resource_dir: str = settings.EN_RG_DIR,
 ) -> list[BibleReference]:
     """
-    >>> from doc.domain import resource_lookup
-    >>> ();rg_books = resource_lookup.nt_survey_rg_passages() ;() # doctest: +ELLIPSIS
-    (...)
-    >>> rg_books[0]
-    BibleReference(book_code='mat', book_name='Matthew', start_chapter=2, start_chapter_verse_ref='1-12', end_chapter=None, end_chapter_verse_ref=None)
+        Returns the list of all NT RG passages from the docx_file_path, but with
+    book names localized for language chosen.
+
+        >>> from doc.domain import resource_lookup
+        >>> ();rg_books = resource_lookup.nt_survey_rg_passages() ;() # doctest: +ELLIPSIS
+        (...)
+        >>> rg_books[0]
+        BibleReference(book_code='mat', book_name='Matthew', start_chapter=2, start_chapter_verse_ref='1-12', end_chapter=None, end_chapter_verse_ref=None)
     """
     path = join(resource_dir, docx_file_path)
     rg_books = get_rg_books(
@@ -1241,6 +1244,7 @@ def nt_survey_rg_passages(
         maybe_localized_book_name = book_name_map.get(
             bible_reference.book_code, bible_reference.book_name
         )
+        bible_reference.lang_code = lang_code
         bible_reference.book_name = maybe_localized_book_name
     return bible_references
 
@@ -1283,6 +1287,7 @@ def ot_survey_rg1_passages(
         maybe_localized_book_name = book_name_map.get(
             bible_reference.book_code, bible_reference.book_name
         )
+        bible_reference.lang_code = lang_code
         bible_reference.book_name = maybe_localized_book_name
     return bible_references
 
@@ -1325,6 +1330,7 @@ def ot_survey_rg2_passages(
         maybe_localized_book_name = book_name_map.get(
             bible_reference.book_code, bible_reference.book_name
         )
+        bible_reference.lang_code = lang_code
         bible_reference.book_name = maybe_localized_book_name
     return bible_references
 
@@ -1367,6 +1373,7 @@ def ot_survey_rg3_passages(
         maybe_localized_book_name = book_name_map.get(
             bible_reference.book_code, bible_reference.book_name
         )
+        bible_reference.lang_code = lang_code
         bible_reference.book_name = maybe_localized_book_name
     return bible_references
 
@@ -1409,6 +1416,7 @@ def ot_survey_rg4_passages(
         maybe_localized_book_name = book_name_map.get(
             bible_reference.book_code, bible_reference.book_name
         )
+        bible_reference.lang_code = lang_code
         bible_reference.book_name = maybe_localized_book_name
     return bible_references
 

backend/doc/entrypoints/routes.py

@@ -1,4 +1,4 @@
-from typing import Sequence
+from typing import Sequence, cast
 
 import celery.states
 from celery.result import AsyncResult
@@ -113,21 +113,28 @@ async def resource_types(
     Return the list of available resource types tuples for lang_code
     with book_codes.
     """
-    return resource_lookup.resource_types(lang_code, book_codes)
+    return cast(
+        Sequence[tuple[str, str]], resource_lookup.resource_types(lang_code, book_codes)
+    )
 
 
 @router.get("/book_codes_for_lang/{lang_code}")
 async def book_codes_for_lang(lang_code: str) -> Sequence[tuple[str, str]]:
     """Return list of all available resource codes."""
-    return resource_lookup.book_codes_for_lang(lang_code)
+    return cast(
+        Sequence[tuple[str, str]], resource_lookup.book_codes_for_lang(lang_code)
+    )
 
 
 @router.get("/book_codes_for_lang_from_usfm_only/{lang_code}")
 async def book_codes_for_lang_from_usfm_only(
     lang_code: str,
 ) -> Sequence[tuple[str, str]]:
     """Return list of all available resource codes."""
-    return resource_lookup.book_codes_for_lang_from_usfm_only(lang_code)
+    return cast(
+        Sequence[tuple[str, str]],
+        resource_lookup.book_codes_for_lang_from_usfm_only(lang_code),
+    )
 
 
 @router.get("/chapters_in_books")

backend/doc/reviewers_guide/model.py

@@ -22,6 +22,7 @@ class Part2Item(BaseModel):
 
 @final
 class BibleReference(BaseModel):
+    lang_code: Optional[str]
     book_code: str
     book_name: str
     start_chapter: ChapterNum
@@ -32,6 +33,7 @@ class BibleReference(BaseModel):
     def __hash__(self: "BibleReference") -> int:
         return hash(
             (
+                self.lang_code,
                 self.book_code,
                 self.book_name,
                 self.start_chapter,
@@ -45,13 +47,15 @@ def __eq__(self: "BibleReference", other: object) -> bool:
         if not isinstance(other, BibleReference):
             return NotImplemented
         return (
+            self.lang_code,
             self.book_code,
             self.book_name,
             self.start_chapter,
             self.start_chapter_verse_ref,
             self.end_chapter,
             self.end_chapter_verse_ref,
         ) == (
+            other.lang_code,
             other.book_code,
             other.book_name,
             other.start_chapter,

backend/doc/reviewers_guide/parser.py

@@ -147,6 +147,7 @@ def get_ordinal_bible_reference(
     start_chapter = chapter_verse_components[0]
     start_chapter_verse_ref = chapter_verse_components[1]
     bible_reference = BibleReference(
+        lang_code=None,
         book_code=book_code,
         book_name=book_name,
         start_chapter=int(start_chapter),
@@ -176,6 +177,7 @@ def get_bible_reference_spanning_chapter_boundary(
         chapter_verse_components[2] if len(chapter_verse_components) >= 3 else None
     )
     bible_reference = BibleReference(
+        lang_code=None,
         book_code=book_code,
         book_name=book_name,
         start_chapter=int(start_chapter),

backend/doc/utils/docx_util.py

@@ -3,6 +3,7 @@
 
 from docx import Document
 from docx.document import Document as DocxDocument
+from docx.enum.style import WD_STYLE_TYPE
 from docx.oxml import OxmlElement
 from docx.oxml.ns import qn
 from docx.shared import RGBColor
@@ -217,3 +218,57 @@ def style_superscripts(
                 position = OxmlElement("w:position")
                 position.set(qn("w:val"), str(lift_half_points))
                 rPr.append(position)
+
+
+def _ensure_character_style_based_on_default(
+    doc: DocxDocument,
+    name: str,
+    *,
+    color: RGBColor | None = None,
+    italic: bool | None = None,
+) -> None:
+    styles = doc.styles
+    if name in styles:
+        return
+    style = styles.add_style(name, WD_STYLE_TYPE.CHARACTER)
+    # ---- Base on Default Paragraph Font ----
+    style_elm = style._element
+    based_on = OxmlElement("w:basedOn")
+    based_on.set(qn("w:val"), "DefaultParagraphFont")
+    style_elm.insert(0, based_on)
+    # ---- Only override what is explicitly requested ----
+    font = style.font
+    if color is not None:
+        font.color.rgb = color
+    if italic is not None:
+        font.italic = italic
+
+
+def ensure_reference_styles(
+    doc: DocxDocument,
+    *,
+    available_color: RGBColor | None = None,
+    unavailable_color: RGBColor,
+) -> None:
+    """
+    Create semantic character styles for passage references.
+
+    AvailableReference:
+        - Based on Default Paragraph Font
+        - Usually no overrides (inherits document defaults)
+
+    UnavailableReference:
+        - Based on Default Paragraph Font
+        - Lighter color + italics to signal intentional absence
+    """
+    _ensure_character_style_based_on_default(
+        doc,
+        "AvailableReference",
+        color=available_color,  # usually None
+    )
+    _ensure_character_style_based_on_default(
+        doc,
+        "UnavailableReference",
+        color=unavailable_color,
+        italic=True,
+    )

backend/doc/utils/file_utils.py

@@ -154,7 +154,9 @@ def epub_filepath(
 
 
 def docx_filepath(
-    document_request_key: str, output_dir: str = settings.DOCUMENT_OUTPUT_DIR
+    document_request_key: str,
+    prefix: str = "",
+    output_dir: str = settings.DOCUMENT_OUTPUT_DIR,
 ) -> str:
     """Given document_request_key, return the docx output file path."""
-    return join(output_dir, "{}.docx".format(document_request_key))
+    return join(output_dir, "{}{}.docx".format(prefix, document_request_key))