Port 'Expose chapter numbers' sillsdev/machine#369

Author: Enkidu93

machine/punctuation_analysis/chapter.py

@@ -6,3 +6,4 @@
 @dataclass(frozen=True)
 class Chapter:
     verses: list[Verse]
+    chatper_num: int = 0

machine/punctuation_analysis/quotation_mark_update_first_pass.py

@@ -1,4 +1,4 @@
-from typing import Dict, List, Set
+from typing import Dict, List, Set, Tuple
 
 from .chapter import Chapter
 from .depth_based_quotation_mark_resolver import DepthBasedQuotationMarkResolver
@@ -54,11 +54,11 @@ def _check_whether_fallback_mode_will_work(
 
         return True
 
-    def find_best_chapter_strategies(self) -> List[QuotationMarkUpdateStrategy]:
-        best_actions_by_chapter: List[QuotationMarkUpdateStrategy] = []
+    def find_best_chapter_strategies(self) -> List[Tuple[int, QuotationMarkUpdateStrategy]]:
+        best_actions_by_chapter: List[Tuple[int, QuotationMarkUpdateStrategy]] = []
 
         for chapter in self.get_chapters():
-            best_actions_by_chapter.append(self._find_best_strategy_for_chapter(chapter))
+            best_actions_by_chapter.append((chapter.chatper_num, self._find_best_strategy_for_chapter(chapter)))
 
         return best_actions_by_chapter
 

machine/punctuation_analysis/usfm_structure_extractor.py

@@ -110,11 +110,11 @@ def get_chapters(self, include_chapters: Optional[Dict[int, List[int]]] = None)
                 current_verse_segments = []
             if text_segment.marker_is_in_preceding_context(UsfmMarkerType.CHAPTER):
                 if len(current_chapter_verses) > 0:
-                    chapters.append(Chapter(current_chapter_verses))
+                    chapters.append(Chapter(current_chapter_verses, current_chapter))
                 current_chapter_verses = []
             current_verse_segments.append(text_segment)
         if len(current_verse_segments) > 0:
             current_chapter_verses.append(Verse(current_verse_segments))
         if len(current_chapter_verses) > 0:
-            chapters.append(Chapter(current_chapter_verses))
+            chapters.append(Chapter(current_chapter_verses, current_chapter))
         return chapters

tests/punctuation_analysis/test_quotation_denormalization.py

@@ -38,9 +38,11 @@ def test_full_quotation_denormalization_pipeline() -> None:
     parse_usfm(normalized_usfm, quotation_mark_denormalization_first_pass)
     best_chapter_strategies = quotation_mark_denormalization_first_pass.find_best_chapter_strategies()
 
+    assert [chapter for chapter, _ in best_chapter_strategies] == [1]
+
     quotation_mark_denormalizer = QuotationMarkDenormalizationUsfmUpdateBlockHandler(
         standard_english_quote_convention,
-        QuotationMarkUpdateSettings(chapter_strategies=best_chapter_strategies),
+        QuotationMarkUpdateSettings(chapter_strategies=[strategy for _, strategy in best_chapter_strategies]),
     )
 
     updater = UpdateUsfmParserHandler(update_block_handlers=[quotation_mark_denormalizer])

tests/punctuation_analysis/test_quotation_mark_update_first_pass.py

@@ -678,7 +678,7 @@ def run_first_pass(
     first_pass_analyzer = QuotationMarkUpdateFirstPass(source_quote_convention, target_quote_convention)
     parse_usfm(normalized_usfm, first_pass_analyzer)
 
-    return first_pass_analyzer.find_best_chapter_strategies()
+    return [strategy for _, strategy in first_pass_analyzer.find_best_chapter_strategies()]
 
 
 def run_first_pass_on_chapter(