diff --git a/backend/doc/domain/assembly_strategies/assemble_by_chapter.py b/backend/doc/domain/assembly_strategies/assemble_by_chapter.py index 3a15bba6..e141fb4d 100644 --- a/backend/doc/domain/assembly_strategies/assemble_by_chapter.py +++ b/backend/doc/domain/assembly_strategies/assemble_by_chapter.py @@ -7,8 +7,6 @@ chapter_commentary_parts, collect_unique_book_codes, collect_unique_lang_codes, - demote_headings_by_one, - demote_headings_by_two, filter_books_by_book_code, filter_books_by_lang_code, get_book_intros, @@ -26,6 +24,7 @@ tq_verses_parts, rg_verses_parts, ) +from doc.utils.text_utils import demote_headings_by_one from doc.domain.bible_books import BOOK_CHAPTERS, BOOK_ID_MAP, BOOK_NAMES from doc.domain.model import ( AssemblyLayoutEnum, diff --git a/backend/doc/domain/assembly_strategies/assembly_strategy_utils.py b/backend/doc/domain/assembly_strategies/assembly_strategy_utils.py index 53704d2f..3751ff45 100644 --- a/backend/doc/domain/assembly_strategies/assembly_strategy_utils.py +++ b/backend/doc/domain/assembly_strategies/assembly_strategy_utils.py @@ -2,8 +2,8 @@ Utility functions used by assembly_strategies. """ -from re import compile, IGNORECASE, Match, search -from typing import Optional, Sequence, TypeVar +from re import search +from typing import Optional, Sequence from doc.config import settings from doc.domain.bible_books import BOOK_ID_MAP @@ -19,6 +19,7 @@ from doc.reviewers_guide.model import RGBook from doc.reviewers_guide.render_to_html import render_chapter from doc.utils.tw_utils import translation_words_content +from doc.utils.text_utils import demote_headings_by_one from docx.document import Document as DocxDocument from docx.enum.section import WD_SECTION from docx.enum.text import WD_BREAK @@ -29,11 +30,6 @@ logger = settings.logger(__name__) -HEADING_RE = compile(r" str: """ Return the HTML for verses that are in the chapter with @@ -970,27 +965,6 @@ def get_non_usfm_resources_verse( return document_parts -def _demote_heading(match: Match[str], levels: int) -> str: - tag = match.group(0) - level = int(match.group(1)) - new_level = min(level + levels, 6) - return tag.replace(f"h{level}", f"h{new_level}", 1) - - -def demote_headings_by_one(content: str) -> str: - return HEADING_RE.sub( - lambda m: _demote_heading(m, levels=1), - content, - ) - - -def demote_headings_by_two(content: str) -> str: - return HEADING_RE.sub( - lambda m: _demote_heading(m, levels=2), - content, - ) - - def tnc_chapter_intro( tnc_book: Optional[TNCBook], chapter_num: int, diff --git a/backend/doc/domain/document_generator.py b/backend/doc/domain/document_generator.py index 7bff28d1..4429b0bf 100755 --- a/backend/doc/domain/document_generator.py +++ b/backend/doc/domain/document_generator.py @@ -775,7 +775,7 @@ def compose_docx_document( add_full_width_hr(doc) if part.add_page_break: add_page_break(doc) - style_superscripts(doc, lift_half_points=4, color=RGBColor(0x99, 0x99, 0x99)) + style_superscripts(doc, lift_half_points=6, color=RGBColor(0x99, 0x99, 0x99)) t1 = time.time() logger.info("Time for converting HTML to Docx: %.2f seconds", t1 - t0) return doc diff --git a/backend/doc/domain/parsing.py b/backend/doc/domain/parsing.py index af30d26b..eb5cf122 100644 --- a/backend/doc/domain/parsing.py +++ b/backend/doc/domain/parsing.py @@ -14,10 +14,7 @@ import requests from bs4 import BeautifulSoup from doc.config import settings -from doc.domain.assembly_strategies.assembly_strategy_utils import ( - demote_headings_by_one, - demote_headings_by_two, -) +from doc.utils.text_utils import demote_headings_by_one from doc.domain.bible_books import BOOK_ID_MAP, BOOK_NAMES from doc.domain.model import ( BC_RESOURCE_TYPE, @@ -80,6 +77,11 @@ H1, H2, H3, H4, H5 = "h1", "h2", "h3", "h4", "h5" +_SECTIONHEAD5_RE = re.compile( + r'\s*', + re.MULTILINE, +) + BC_ARTICLE_URL_FMT_STR: str = ( "https://content.bibletranslationtools.org/WycliffeAssociates/en_bc/src/branch/master/{}" @@ -447,6 +449,10 @@ def ensure_chapter_marker( return f"\\c {chapter_num}\n" + chapter_usfm_text +def remove_sectionhead5_elements(content: str) -> str: + return _SECTIONHEAD5_RE.sub(" ", content) + + def usfm_book_content( resource_lookup_dto: ResourceLookupDto, resource_dir: str, @@ -511,9 +517,12 @@ def usfm_book_content( cleaned_chapter_html_content = remove_null_bytes_and_control_characters( chapter_html_content ) + chapter_html_content_sans_s5 = remove_sectionhead5_elements( + cleaned_chapter_html_content + ) usfm_chapters[chapter_num] = USFMChapter( content=( - cleaned_chapter_html_content if cleaned_chapter_html_content else "" + chapter_html_content_sans_s5 if chapter_html_content_sans_s5 else "" ), verses=None, ) @@ -1278,7 +1287,7 @@ def assemble_chapter_usfm( verse_content = read_verse_file(usfm_file) cleaned_verse_content = clean_verse_content(verse_content) verse_content = ensure_paragraph_before_verses(usfm_file, cleaned_verse_content) - chapter_usfm_content.append(cleaned_verse_content) + chapter_usfm_content.append(verse_content) chapter_usfm_content.append( " \n" ) # Make sure a space before next chunk, e.g., auh, mat, ch 9, v 14 @@ -1456,6 +1465,8 @@ def handle_split_chapter_into_verses( def split_chapter_into_verses_with_formatting( chapter: USFMChapter, + empty_paragraph: str = "

", + sectionhead5_element: str = '
', ) -> dict[VerseRef, str]: """ Given a USFMChapter instance, return the same instance with its @@ -1465,29 +1476,27 @@ def split_chapter_into_verses_with_formatting( Sample HTML content with multiple verse elements: >>> html_content = ''' - >>> - >>> 19 - >>> For through the law I died to the law, so that I might live for God. I have been crucified with Christ. - >>> 1 - >>>
- >>> - >>> - >>> 20 - >>> I have been crucified with Christ and I no longer live, but Christ lives in me. The life I now live in the body, I live by faith in the Son of God, who loved me and gave himself for me. - >>> 2 - >>>
- >>> - >>> ''' + ... + ... 19 + ... For through the law I died to the law, so that I might live for God. I have been crucified with Christ. + ... 1 + ...
+ ... + ... + ... 20 + ... I have been crucified with Christ and I no longer live, but Christ lives in me. The life I now live in the body, I live by faith in the Son of God, who loved me and gave himself for me. + ... 2 + ...
+ ... + ... ''' >>> from doc.domain.parsing import split_chapter_into_verses_with_formatting - >>> chapter = USFMChapter(content=html_content) + >>> chapter = USFMChapter(content=html_content, verses=None) >>> chapter.verses = split_chapter_into_verses_with_formatting(chapter) - >>> chapter.verses["19"] - + >>> print(chapter.verses["19"]) 19 For through the law I died to the law, so that I might live for God. I have been crucified with Christ. 1 -
- + """ # TODO What to do about footnote targets? Perhaps have the value be a # tuple with first element of the verse HTML (which includes the @@ -1505,14 +1514,16 @@ def split_chapter_into_verses_with_formatting( # Add to the dictionary with verse number as the key and verse text as the value verse_dict[verse_number_] = ( verse_span.strip() - .replace("

", "") - .replace('
', "") + .replace(empty_paragraph, "") + .replace(sectionhead5_element, "") ) return verse_dict def split_chapter_into_verses_with_formatting_for_f10( chapter: USFMChapter, + empty_paragraph: str = "

", + sectionhead5_element: str = '
', ) -> dict[str, str]: """ Parse chapter.content as HTML, extract each , @@ -1555,8 +1566,8 @@ def split_chapter_into_verses_with_formatting_for_f10( # store cleaned HTML fragment (still contains etc.) verse_dict[verse_number] = ( cleaned_html.strip() - .replace("

", "") - .replace('
', "") + .replace(empty_paragraph, "") + .replace(sectionhead5_element, "") ) return verse_dict diff --git a/backend/doc/domain/resource_lookup.py b/backend/doc/domain/resource_lookup.py index 60503393..20878848 100644 --- a/backend/doc/domain/resource_lookup.py +++ b/backend/doc/domain/resource_lookup.py @@ -16,7 +16,7 @@ import requests from cachetools import TTLCache, cached from doc.config import settings -from doc.domain import worker, parsing +from doc.domain import worker from doc.domain.bible_books import BOOK_CHAPTERS, BOOK_ID_MAP, BOOK_NAMES from doc.domain.model import ( NON_USFM_RESOURCE_TYPES, @@ -36,7 +36,6 @@ from doc.utils.file_utils import ( delete_tree, file_needs_update, - read_file, ) from doc.utils.list_utils import unique_tuples, unique_book_codes from doc.utils.text_utils import maybe_correct_book_name, normalize_localized_book_name @@ -79,7 +78,7 @@ def fetch_source_data( >>> ();result = resource_lookup.fetch_source_data();() # doctest: +ELLIPSIS (...) >>> result.git_repo[0] - RepoEntry(repo_url=HttpUrl('https://content.bibletranslationtools.org/klero/ach-SS-acholi_rev_text_reg'), content=Content(resource_type='reg', language=Language(english_name='Acholi', ietf_code='ach-SS-acholi', national_name='Acholi', direction=))) + RepoEntry(repo_url=HttpUrl('https://content.bibletranslationtools.org/0success/cli_1jn_text_reg'), content=Content(resource_type='reg', language=Language(english_name='Chakali', ietf_code='cli', national_name='Chakali', direction=))) """ graphql_query = """ query MyQuery { @@ -111,6 +110,8 @@ def fetch_source_data( for repo in data_payload["git_repo"] if repo.get("content", {}).get("resource_type") is not None ] + # Sort for test stability - ensures consistent ordering + valid_repos.sort(key=lambda repo: repo["repo_url"]) return SourceData.model_validate({"git_repo": valid_repos}) else: logger.info("Invalid payload structure, no data.") @@ -263,6 +264,8 @@ def get_resource_types( str, str ] = settings.RESOURCE_TYPE_CODES_AND_NAMES, ) -> list[tuple[str, str]]: + from doc.domain.parsing import find_usfm_files + resource_types = [] for url, resource_filepath, resource_type in repo_clone_list: if resource_type: @@ -285,7 +288,7 @@ def get_resource_types( and file.name.split("-")[1].lower() in book_codes ] elif resource_type in usfm_resource_types: - book_assets = parsing.find_usfm_files(resource_filepath) + book_assets = find_usfm_files(resource_filepath) elif resource_type == "rg": between_texts, bible_reference_strs = find_bible_references( join(en_rg, docx_file_path) @@ -574,6 +577,8 @@ def usfm_resource_types_and_book_tuples( >>> sorted(tuples, key=lambda value: value[1]) [('reg', '1co'), ('reg', '1jn'), ('reg', '1pe'), ('reg', '1th'), ('reg', '1ti'), ('reg', '2co'), ('reg', '2jn'), ('reg', '2pe'), ('reg', '2th'), ('reg', '2ti'), ('reg', '3jn'), ('reg', 'act'), ('reg', 'col'), ('reg', 'eph'), ('reg', 'gal'), ('reg', 'heb'), ('reg', 'jas'), ('reg', 'jhn'), ('reg', 'jud'), ('reg', 'luk'), ('reg', 'mat'), ('reg', 'mrk'), ('reg', 'phm'), ('reg', 'php'), ('reg', 'rev'), ('reg', 'rom'), ('reg', 'tit')] """ + from doc.domain.parsing import usfm_asset_file + book_codes = book_codes_str.split(",") data: SourceData | None = fetch_source_data() resource_type_and_book_tuples = set() @@ -602,9 +607,7 @@ def usfm_resource_types_and_book_tuples( resource_filepath = prepare_resource_filepath(dto) if file_needs_update(resource_filepath): provision_asset_files(dto.url, resource_filepath) - content_file = parsing.usfm_asset_file( - dto, resource_filepath, False - ) + content_file = usfm_asset_file(dto, resource_filepath, False) if content_file: resource_type_and_book_tuples.add((resource_type, book_code)) return sorted(resource_type_and_book_tuples, key=lambda value: value[0]) @@ -942,18 +945,24 @@ def get_book_names_from_usfm_metadata( be localized, it depends on the translation work done for language lang_code. """ + from doc.domain.parsing import ( + find_usfm_files, + split_usfm_by_chapters, + maybe_localized_book_name, + ) + book_codes_and_names_localized: dict[str, str] = {} - usfm_files = parsing.find_usfm_files(resource_filepath) + usfm_files = find_usfm_files(resource_filepath) for usfm_file in usfm_files: usfm = "" usfm_file_components = Path(usfm_file).stem.lower().split("-") book_code = usfm_file_components[1] with open(usfm_file, "r") as f: usfm = f.read() - frontmatter, _, _ = parsing.split_usfm_by_chapters( + frontmatter, _, _ = split_usfm_by_chapters( lang_code, resource_type, book_code, usfm ) - localized_book_name = parsing.maybe_localized_book_name(frontmatter) + localized_book_name = maybe_localized_book_name(frontmatter) # localized_book_name = maybe_correct_book_name(lang_code, localized_book_name) book_codes_and_names_localized[book_code] = localized_book_name logger.debug("book_codes_and_names_localized: %s", book_codes_and_names_localized) @@ -1204,7 +1213,8 @@ def nt_survey_rg_passages( ) -> list[BibleReference]: """ >>> from doc.domain import resource_lookup - >>> rg_books = resource_lookup.nt_survey_rg_passages() + >>> ();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) """ @@ -1245,9 +1255,10 @@ def ot_survey_rg1_passages( ) -> list[BibleReference]: """ >>> from doc.domain import resource_lookup - >>> rg_books = resource_lookup.ot_survey_rg1_passages() + >>> ();rg_books = resource_lookup.ot_survey_rg1_passages();() # doctest: +ELLIPSIS + (...) >>> rg_books[0] - BibleReference(book_code='gen', book_name='Genesis', start_chapter=2, start_chapter_verse_ref='1-12', end_chapter=None, end_chapter_verse_ref=None) + BibleReference(book_code='gen', book_name='Genesis', start_chapter=1, start_chapter_verse_ref='1', end_chapter=2, end_chapter_verse_ref='3') """ path = join(resource_dir, docx_file_path) rg_books = get_rg_books( @@ -1286,9 +1297,10 @@ def ot_survey_rg2_passages( ) -> list[BibleReference]: """ >>> from doc.domain import resource_lookup - >>> rg_books = resource_lookup.ot_survey_rg2_passages() + >>> ();rg_books = resource_lookup.ot_survey_rg2_passages();() # doctest: +ELLIPSIS + (...) >>> rg_books[0] - BibleReference(book_code='jos', book_name='Joshua', start_chapter=2, start_chapter_verse_ref='1-12', end_chapter=None, end_chapter_verse_ref=None) + BibleReference(book_code='jos', book_name='Joshua', start_chapter=1, start_chapter_verse_ref='1-9', end_chapter=None, end_chapter_verse_ref=None) """ path = join(resource_dir, docx_file_path) rg_books = get_rg_books( @@ -1327,9 +1339,10 @@ def ot_survey_rg3_passages( ) -> list[BibleReference]: """ >>> from doc.domain import resource_lookup - >>> rg_books = resource_lookup.ot_survey_rg3_passages() + >>> ();rg_books = resource_lookup.ot_survey_rg3_passages();() # doctest: +ELLIPSIS + (...) >>> rg_books[0] - BibleReference(book_code='job', book_name='Job', start_chapter=2, start_chapter_verse_ref='1-12', end_chapter=None, end_chapter_verse_ref=None) + BibleReference(book_code='job', book_name='Job', start_chapter=1, start_chapter_verse_ref='6-22', end_chapter=None, end_chapter_verse_ref=None) """ path = join(resource_dir, docx_file_path) rg_books = get_rg_books( @@ -1368,9 +1381,10 @@ def ot_survey_rg4_passages( ) -> list[BibleReference]: """ >>> from doc.domain import resource_lookup - >>> rg_books = resource_lookup.ot_survey_rg4_passages() + >>> ();rg_books = resource_lookup.ot_survey_rg4_passages();() # doctest: +ELLIPSIS + (...) >>> rg_books[0] - BibleReference(book_code='isa', book_name='Isaiah', start_chapter=2, start_chapter_verse_ref='1-12', end_chapter=None, end_chapter_verse_ref=None) + BibleReference(book_code='isa', book_name='Isaiah', start_chapter=1, start_chapter_verse_ref='1-9', end_chapter=None, end_chapter_verse_ref=None) """ path = join(resource_dir, docx_file_path) rg_books = get_rg_books( diff --git a/backend/doc/domain/usfm_error_detection_and_fixes.py b/backend/doc/domain/usfm_error_detection_and_fixes.py index 2c02fb61..28f14f94 100644 --- a/backend/doc/domain/usfm_error_detection_and_fixes.py +++ b/backend/doc/domain/usfm_error_detection_and_fixes.py @@ -37,7 +37,7 @@ ("bem-x-kabenmushi", "reg", "sng"), ("bem-x-kabenmushi", "reg", "deu"), ("bem-x-kabenmushi", "reg", "1ki"), - ("bem-x-kabenmushi", "reg", "1ch"), + # ("bem-x-kabenmushi", "reg", "1ch"), # unavailable from data API ("bem-x-kabenmushi", "reg", "ecc"), ("bem-x-kabenmushi", "reg", "2ki"), ("bi", "reg", "act"), @@ -129,7 +129,7 @@ ("kod", "reg", "phm"), # ("kqi", "reg", "2th"), # unavailable from data API # ("kqi", "reg", "2ti"), # unavailable from data API - # ("kqi", "reg", "mrk"), # book no longer available from data api + # ("kqi", "reg", "mrk"), # unavailable from data API ("kqi", "reg", "heb"), # ("kqi", "reg", "1pe"), # unavailable from data API # ("kqi", "reg", "tit"), # unavailable from data API @@ -160,7 +160,7 @@ ("mhi-x-burolo", "reg", "2th"), ("mhy-x-benualima", "reg", "mrk"), # ("mwe", "reg", "tit"), # book is available as choice, but resource not cloned? - # ("mxo", "reg", "mrk"), # not currently unavailable from data API + # ("mxo", "reg", "mrk"), # unavailable from data API ("nak-x-bileki", "reg", "mat"), ("nak-x-bileki", "reg", "1ti"), ("nak-x-bileki", "reg", "eph"), @@ -174,7 +174,7 @@ ("nfd", "reg", "2th"), ("nfd", "reg", "2ti"), ("nfd", "reg", "heb"), - # ("nhx", "reg", "jos"), # not currently available from data API + # ("nhx", "reg", "jos"), # unavailable from data API ("nnb-x-kishula", "reg", "mrk"), ("not", "reg", "jos"), ("now", "reg", "mic"), @@ -246,10 +246,10 @@ ("txy", "reg", "2jn"), ("tyn", "reg", "jud"), ("tyn", "reg", "mrk"), - # ("vin", "reg", "2co"), # not currently available from data API - # ("vin", "reg", "1th"), - # ("vin", "reg", "1ti"), - # ("vin", "reg", "gal"), + # ("vin", "reg", "2co"), # unavailable from data API + # ("vin", "reg", "1th"), # unavailable from data API + # ("vin", "reg", "1ti"), # unavailable from data API + # ("vin", "reg", "gal"), # unavailable from data API ("wbj", "reg", "luk"), ("wbj", "reg", "tit"), ("wbj", "reg", "2jn"), diff --git a/backend/doc/utils/docx_util.py b/backend/doc/utils/docx_util.py index ee4da674..fa3e3078 100644 --- a/backend/doc/utils/docx_util.py +++ b/backend/doc/utils/docx_util.py @@ -192,10 +192,6 @@ def add_internal_docx_links(doc: DocxDocument) -> None: _replace_runs(para, new_elements) -# from docx.oxml import OxmlElement -# from docx.oxml.ns import qn - - def style_superscripts( doc: DocxDocument, *, diff --git a/backend/doc/utils/text_utils.py b/backend/doc/utils/text_utils.py index 97be6488..05d6486f 100644 --- a/backend/doc/utils/text_utils.py +++ b/backend/doc/utils/text_utils.py @@ -1,13 +1,15 @@ -import re +from re import compile, match, sub, IGNORECASE, Match from doc.config import settings logger = settings.logger(__name__) +HEADING_RE = compile(r" str: - return re.sub(r"\s+", " ", text).strip() + return sub(r"\s+", " ", text).strip() _ROMAN_TO_INT = { @@ -50,9 +52,9 @@ def normalize_localized_book_name(localized_book_name: str) -> str: 'Isaías' """ name = localized_book_name.strip() - match = re.match(r"^(1|2|3|i{1,3})", name, re.IGNORECASE) - if match: - numeral_raw = match.group(1) + match_ = match(r"^(1|2|3|i{1,3})", name, IGNORECASE) + if match_: + numeral_raw = match_.group(1) numeral_upper = numeral_raw.upper() next_char = name[len(numeral_raw) : len(numeral_raw) + 1] # Special case: single "I" must be followed by space or uppercase to count as numeral @@ -114,6 +116,27 @@ def maybe_correct_book_name( return book_name_ +def _demote_heading(match: Match[str], levels: int) -> str: + tag = match.group(0) + level = int(match.group(1)) + new_level = min(level + levels, 6) + return tag.replace(f"h{level}", f"h{new_level}", 1) + + +def demote_headings_by_one(content: str) -> str: + return HEADING_RE.sub( + lambda m: _demote_heading(m, levels=1), + content, + ) + + +def demote_headings_by_two(content: str) -> str: + return HEADING_RE.sub( + lambda m: _demote_heading(m, levels=2), + content, + ) + + if __name__ == "__main__": # To run the doctests in this module, in the root of the project do: diff --git a/backend/doc/utils/tw_utils.py b/backend/doc/utils/tw_utils.py index a5da944b..23c36471 100644 --- a/backend/doc/utils/tw_utils.py +++ b/backend/doc/utils/tw_utils.py @@ -11,7 +11,7 @@ from typing import Mapping, Optional, Sequence from doc.config import settings -from doc.domain import parsing, resource_lookup, bible_books +from doc.domain import resource_lookup, bible_books from doc.domain.model import ( DocumentPart, LangDirEnum, @@ -363,6 +363,8 @@ def fetch_usfm_books( resource_requests: Sequence[ResourceRequest], usfm_resource_types: Sequence[str] = settings.USFM_RESOURCE_TYPES, ) -> list[USFMBook]: + from doc.domain.parsing import usfm_book_content + usfm_resource_lookup_dtos = [] for resource_request in resource_requests: for usfm_type in usfm_resource_types: @@ -393,7 +395,7 @@ def fetch_usfm_books( ) # Initialize found resources from their provisioned assets. usfm_book_content_units = [ - parsing.usfm_book_content(resource_lookup_dto, resource_dir, False) # , False + usfm_book_content(resource_lookup_dto, resource_dir, False) for resource_lookup_dto, resource_dir in zip( found_usfm_resource_lookup_dtos, resource_dirs ) @@ -406,6 +408,8 @@ def fetch_usfm_book( book_code: str, resource_type: str, ) -> Optional[USFMBook]: + from doc.domain.parsing import usfm_book_content + usfm_book = None resource_lookup_dto = resource_lookup.resource_lookup_dto( lang_code, @@ -421,7 +425,7 @@ def fetch_usfm_book( "Time to provision USFM asset files (acquire and write to disk) for TW resource: %s", t1 - t0, ) - usfm_book = parsing.usfm_book_content(resource_lookup_dto, resource_dir, False) + usfm_book = usfm_book_content(resource_lookup_dto, resource_dir, False) return usfm_book diff --git a/backend/passages/domain/document_generator.py b/backend/passages/domain/document_generator.py index c9065e68..6981955f 100644 --- a/backend/passages/domain/document_generator.py +++ b/backend/passages/domain/document_generator.py @@ -142,8 +142,7 @@ def generate_docx_document( else: non_book_name_portion_of_reference = f"{passage_ref_dto.start_chapter}:{passage_ref_dto.start_chapter_verse_ref}" # NOTE We want the document to show references even if there is no - # content for it. Will these continue to be the desired behavior, we - # will see. + # content for it. # localized_reference = ( # f"{selected_usfm_book.national_book_name} {non_book_name_portion_of_reference}" # if selected_usfm_book and non_book_name_portion_of_reference @@ -286,6 +285,7 @@ def generate_passages_docx_document( lang_name: str, passage_reference_dtos_json: str, email_address: str, + docx_filepath_prefix: str = "passages_", book_names: dict[str, str] = BOOK_NAMES, ) -> Json[str]: passage_reference_dtos_list = json.loads(passage_reference_dtos_json) @@ -299,7 +299,7 @@ def generate_passages_docx_document( email_address, ) document_request_key_ = document_request_key(lang_code, passage_reference_dtos) - docx_filepath_ = docx_filepath(document_request_key_) + docx_filepath_ = f"{docx_filepath_prefix}{docx_filepath(document_request_key_)}" if file_needs_update(docx_filepath_): generate_docx_document( lang_code,