Add MemoryParatextProjectTextUpdater and move MemoryParatextProjectFileHandler to production code

- Create MemoryParatextProjectFileHandler in machine/corpora/ (promoted from testutils)
- Create MemoryParatextProjectTextUpdater in machine/corpora/
- Rename testutils file to default_paratext_project_settings.py
- Update all imports to use new locations
- Refactor test_update_usfm_parser_handler to use MemoryParatextProjectTextUpdater

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: mshannon-sil

machine/corpora/__init__.py

@@ -14,6 +14,8 @@
 from .file_paratext_project_versification_error_detector import FileParatextProjectVersificationErrorDetector
 from .flatten import flatten
 from .memory_alignment_collection import MemoryAlignmentCollection
+from .memory_paratext_project_file_handler import MemoryParatextProjectFileHandler
+from .memory_paratext_project_text_updater import MemoryParatextProjectTextUpdater
 from .memory_stream_container import MemoryStreamContainer
 from .memory_text import MemoryText
 from .multi_key_ref import MultiKeyRef
@@ -121,6 +123,8 @@
     "KeyTerm",
     "lowercase",
     "MemoryAlignmentCollection",
+    "MemoryParatextProjectFileHandler",
+    "MemoryParatextProjectTextUpdater",
     "MemoryStreamContainer",
     "MemoryText",
     "MultiKeyRef",

machine/corpora/memory_paratext_project_file_handler.py

@@ -0,0 +1,25 @@
+from io import BytesIO
+from typing import BinaryIO, Dict, Optional
+
+from .paratext_project_file_handler import ParatextProjectFileHandler
+from .usfm_stylesheet import UsfmStylesheet
+
+
+class MemoryParatextProjectFileHandler(ParatextProjectFileHandler):
+    def __init__(self, files: Dict[str, str]) -> None:
+        self.files = files
+
+    def exists(self, file_name: str) -> bool:
+        return file_name in self.files
+
+    def open(self, file_name: str) -> BinaryIO:
+        return BytesIO(self.files[file_name].encode("utf-8"))
+
+    def find(self, extension: str) -> Optional[str]:
+        for name in self.files:
+            if name.endswith(extension):
+                return name
+        return None
+
+    def create_stylesheet(self, file_name: str) -> UsfmStylesheet:
+        return UsfmStylesheet(file_name)

machine/corpora/memory_paratext_project_text_updater.py

@@ -0,0 +1,10 @@
+from typing import Dict
+
+from .memory_paratext_project_file_handler import MemoryParatextProjectFileHandler
+from .paratext_project_settings import ParatextProjectSettings
+from .paratext_project_text_updater_base import ParatextProjectTextUpdaterBase
+
+
+class MemoryParatextProjectTextUpdater(ParatextProjectTextUpdaterBase):
+    def __init__(self, files: Dict[str, str], settings: ParatextProjectSettings) -> None:
+        super().__init__(MemoryParatextProjectFileHandler(files), settings)

tests/corpora/test_paratext_project_terms_parser.py

@@ -1,6 +1,6 @@
 from typing import Dict, List, Optional
 
-from testutils.memory_paratext_project_file_handler import DefaultParatextProjectSettings
+from testutils.default_paratext_project_settings import DefaultParatextProjectSettings
 from testutils.memory_paratext_project_terms_parser import MemoryParatextProjectTermsParser
 
 from machine.corpora import KeyTerm, ParatextProjectSettings, ParatextProjectTermsParserBase

tests/corpora/test_update_usfm_parser_handler.py

@@ -1,20 +1,18 @@
 from typing import Iterable, List, Optional, Sequence, Tuple, Union
 
 from testutils.corpora_test_helpers import USFM_TEST_PROJECT_PATH, ignore_line_endings
+from testutils.default_paratext_project_settings import DefaultParatextProjectSettings
 
 from machine.corpora import (
     FileParatextProjectTextUpdater,
+    MemoryParatextProjectTextUpdater,
     ScriptureRef,
     UpdateUsfmMarkerBehavior,
-    UpdateUsfmParserHandler,
     UpdateUsfmRow,
     UpdateUsfmTextBehavior,
-    UsfmTokenizer,
     UsfmUpdateBlock,
     UsfmUpdateBlockElementType,
     UsfmUpdateBlockHandler,
-    filter_tokens_by_chapter,
-    parse_usfm,
 )
 
 
@@ -1685,8 +1683,12 @@ def update_usfm(
         )
     else:
         source = source.strip().replace("\r\n", "\n") + "\r\n"
-        updater = UpdateUsfmParserHandler(
+        settings = DefaultParatextProjectSettings(file_name_form="MAT", file_name_suffix="")
+        updater = MemoryParatextProjectTextUpdater({"MAT": source}, settings)
+        return updater.update_usfm(
+            "MAT",
             rows,
+            chapters,
             id_text,
             text_behavior,
             paragraph_behavior,
@@ -1698,11 +1700,6 @@ def update_usfm(
             lambda _: False,
             compare_segments,
         )
-        tokenizer = UsfmTokenizer()
-        tokens = tokenizer.tokenize(source)
-        tokens = filter_tokens_by_chapter(tokens, chapters)
-        parse_usfm(tokens, updater)
-        return updater.get_usfm()
 
 
 def assert_usfm_equals(target: Optional[str], truth: str) -> None:

tests/corpora/test_usfm_versification_error_detector.py

@@ -1,7 +1,7 @@
 from io import StringIO
 from typing import Dict, List, Optional
 
-from testutils.memory_paratext_project_file_handler import DefaultParatextProjectSettings
+from testutils.default_paratext_project_settings import DefaultParatextProjectSettings
 from testutils.memory_paratext_project_versification_error_detector import (
     MemoryParatextProjectVersificationErrorDetector,
 )

tests/punctuation_analysis/test_paratext_project_quote_convention_detector.py

@@ -1,6 +1,6 @@
 from typing import Dict, List, Optional
 
-from testutils.memory_paratext_project_file_handler import DefaultParatextProjectSettings
+from testutils.default_paratext_project_settings import DefaultParatextProjectSettings
 from testutils.memory_paratext_project_quote_convention_detector import MemoryParatextProjectQuoteConventionDetector
 
 from machine.corpora import ParatextProjectSettings

…/memory_paratext_project_file_handler.py …ils/default_paratext_project_settings.pytests/testutils/memory_paratext_project_file_handler.py renamed to tests/testutils/default_paratext_project_settings.py tests/testutils/memory_paratext_project_file_handler.py renamed to tests/testutils/default_paratext_project_settings.py

@@ -1,28 +1,9 @@
-from io import BytesIO
-from typing import BinaryIO, Dict, Optional
+from typing import Optional
 
-from machine.corpora import ParatextProjectFileHandler, ParatextProjectSettings, UsfmStylesheet
+from machine.corpora import ParatextProjectSettings, UsfmStylesheet
 from machine.scripture import ORIGINAL_VERSIFICATION, Versification
 
 
-class MemoryParatextProjectFileHandler(ParatextProjectFileHandler):
-    def __init__(self, files: Dict[str, str]) -> None:
-
-        self.files = files
-
-    def exists(self, file_name: str) -> bool:
-        return file_name in self.files
-
-    def open(self, file_name: str) -> BinaryIO:
-        return BytesIO(self.files[file_name].encode("utf-8"))
-
-    def find(self, extension):
-        raise NotImplementedError
-
-    def create_stylesheet(self, file_name):
-        raise NotImplementedError
-
-
 class DefaultParatextProjectSettings(ParatextProjectSettings):
     def __init__(
         self,

tests/testutils/memory_paratext_project_quote_convention_detector.py

@@ -1,9 +1,9 @@
 from typing import Dict
 
-from machine.corpora import ParatextProjectSettings
+from machine.corpora import MemoryParatextProjectFileHandler, ParatextProjectSettings
 from machine.punctuation_analysis import ParatextProjectQuoteConventionDetector
 
-from .memory_paratext_project_file_handler import DefaultParatextProjectSettings, MemoryParatextProjectFileHandler
+from .default_paratext_project_settings import DefaultParatextProjectSettings
 
 
 class MemoryParatextProjectQuoteConventionDetector(ParatextProjectQuoteConventionDetector):

tests/testutils/memory_paratext_project_terms_parser.py

@@ -1,8 +1,8 @@
 from typing import Dict, Optional
 
-from machine.corpora import ParatextProjectSettings, ParatextProjectTermsParserBase
+from machine.corpora import MemoryParatextProjectFileHandler, ParatextProjectSettings, ParatextProjectTermsParserBase
 
-from .memory_paratext_project_file_handler import DefaultParatextProjectSettings, MemoryParatextProjectFileHandler
+from .default_paratext_project_settings import DefaultParatextProjectSettings
 
 
 class MemoryParatextProjectTermsParser(ParatextProjectTermsParserBase):