Feat-fragment_field_ocr

ebl/fragmentarium/application/fragment_schema.py

@@ -204,6 +204,7 @@ class FragmentSchema(Schema):
         ScopeField(),
         data_key="authorizedScopes",
     )
+    ocr_signs = fields.String(load_default="", data_key="ocredSigns")
     introduction = fields.Nested(IntroductionSchema, default=Introduction())
     script = fields.Nested(ScriptSchema, load_default=Script())
     external_numbers = fields.Nested(

ebl/fragmentarium/domain/fragment.py

@@ -134,6 +134,7 @@ class Fragment:
     folios: Folios = Folios()
     text: Text = Text()
     signs: str = ""
+    ocr_signs: str = ""
     notes: Notes = Notes()
     references: Sequence[Reference] = ()
     uncurated_references: Optional[Sequence[UncuratedReference]] = None

ebl/fragmentarium/infrastructure/mongo_fragment_repository.py

@@ -92,6 +92,7 @@ def update_field(self, field, fragment):
             "authorized_scopes": [
                 "authorized_scopes",
             ],
+            "ocredSigns": ("ocredSigns"),
         }
 
         if field not in fields_to_update:

ebl/tests/alignment/test_named_sequence.py

@@ -4,6 +4,7 @@
 from ebl.tests.factories.fragment import FragmentFactory
 
 signs = "X X ABZ001\nABZ002\nX X X\n"
+ocr_signs = ""
 sequence = Sequence(["ABZ001", "#", "ABZ002", "#", "#"])
 
 
@@ -18,7 +19,7 @@ def test_of_signs() -> None:
 
 def test_of_fragment() -> None:
     vocabulary = Vocabulary()
-    fragment = FragmentFactory.build(signs=signs)
+    fragment = FragmentFactory.build(signs=signs, ocr_signs=ocr_signs)
     named = NamedSequence.of_fragment(fragment, vocabulary)
 
     assert named.name == str(fragment.number)

ebl/tests/factories/fragment.py

@@ -236,6 +236,7 @@ class Meta:
     projects = (ResearchProject.CAIC,)
     archaeology = factory.SubFactory(ArchaeologyFactory)
     colophon = factory.SubFactory(ColophonFactory)
+    ocr_signs = "ABZ10 X"
 
 
 class InterestingFragmentFactory(FragmentFactory):
@@ -454,6 +455,7 @@ class TransliteratedFragmentFactory(FragmentFactory):
         "X MU TA MA UD\n"
         "ŠU/|BI×IS|"
     )
+    ocr_signs = "ABZ10 X"
     folios = Folios((Folio("WGL", "3"), Folio("ARG", "3")))
     record = Record((RecordEntry("test", RecordType.TRANSLITERATION),))
     line_to_vec = (

ebl/tests/fragmentarium/test_dtos.py

@@ -117,6 +117,7 @@ def expected_dto(lemmatized_fragment, has_photo):
             "archaeology": ArchaeologySchema().dump(lemmatized_fragment.archaeology),
             "colophon": ColophonSchema().dump(lemmatized_fragment.colophon),
             "authorizedScopes": [],
+            "ocredSigns": "ABZ10 X",
         },
         pydash.is_none,
     )

ebl/tests/fragmentarium/test_fragment_repository.py

@@ -96,6 +96,7 @@
         )
     ),
     signs="MI DIŠ DIŠ UD ŠU",
+    ocr_signs="",
 )