I want to process the data in segments that correspond to individual translations. These updates make it happen.

Author: johnml1135

.vscode/settings.json

@@ -13,6 +13,9 @@
       "source.organizeImports": "explicit"
     },
   },
+  "files.associations": {
+    "*.SFM": "usfm",
+  },
   "black-formatter.path": [
     "poetry",
     "run",

machine/corpora/usfm_parser_state.py

@@ -108,6 +108,10 @@ def is_verse_para(self) -> bool:
 
     @property
     def is_verse_text(self) -> bool:
+        # anything before verse 1 is not verse text
+        if self.verse_ref.verse_num == 0:
+            return False
+
         # Sidebars and notes are not verse text
         if any(e.type in {UsfmElementType.SIDEBAR, UsfmElementType.NOTE} for e in self._stack):
             return False

tests/corpora/test_update_usfm_parser_handler.py

@@ -202,6 +202,7 @@ def test_paragraph_in_verse():
     ]
     usfm = r"""\id MAT - Test
 \c 1
+\p paragraph not in a verse
 \v 1 verse 1 \p inner verse paragraph
 \s1 Section Header
 \v 2 Verse 2 \p inner verse paragraph
@@ -211,6 +212,7 @@ def test_paragraph_in_verse():
 
     result = r"""\id MAT - Test
 \c 1
+\p paragraph not in a verse
 \v 1 Update 1
 \s1 Section Header
 \v 2 Verse 2
@@ -228,6 +230,7 @@ def test_paragraph_in_verse():
 
     result_strip = r"""\id MAT
 \c 1
+\p 
 \v 1 Update 1
 \s1
 \v 2