Merge remote-tracking branch 'origin/master' into atf-import-update

ElectronicBabylonianLiterature · Nov 7, 2024 · d3ab25b · d3ab25b
2 parents 1973bef + 60feb88
commit d3ab25b
Show file tree

Hide file tree

Showing 7 changed files with 206 additions and 260 deletions.
diff --git a/ebl/common/domain/provenance.py b/ebl/common/domain/provenance.py
@@ -45,6 +45,7 @@ class Provenance(ProvenanceEnum):
     KISURRA = ("Kisurra", "Ksr", "Babylonia", "KSR")
     KIS = ("Kiš", "Kiš", "Babylonia", "KSH")
     KUTALLA = ("Kutalla", "Kut", "Babylonia", "SFR")
+    LAGABA = ("Lagaba", "Lag", "Babylonia", "LGBunk")
     LAGAS = ("Lagaš", "Lag", "Babylonia", "LAG")
     LARAK = ("Larak", "Lrk", "Babylonia", "LRK")
     LARSA = ("Larsa", "Lar", "Babylonia", "LAR")
@@ -94,6 +95,7 @@ class Provenance(ProvenanceEnum):
     BAKR_AWA = ("Bakr Āwā", "Bakr", "Periphery", "BAW")
     BARAH = ("Bārah", "Bar", "Periphery", "PRA")
     BITWATA = ("Bitwātā", "Bitw", "Periphery", "SNJ")
+    CHUGHA_MISH = ("Chughā Mīsh", "Chughā", "Periphery", "CGM")
     DER = ("Dēr", "Der", "Periphery", "DER")
     DUGIRDKHAN = ("Dugirdkhan", "Dgr", "Periphery", "DGK")
     DUR_UNTAS = ("Dūr-Untaš", "Dun", "Periphery", "COZ")
@@ -103,6 +105,7 @@ class Provenance(ProvenanceEnum):
     GLAYA = ("Glay‘a", "Gla", "Periphery", "GLA")
     HAMATH = ("Hamath", "Ham", "Periphery", "HAM")
     HATTUSA = ("Ḫattuša", "Hat", "Periphery", "HAT")
+    KAYSERI = ("Kayseri", "Kay", "Periphery", "KRI")
     KANES = ("Kaneš", "Kan", "Periphery", "KNS")
     KARKEMIS = ("Karkemiš", "Kar", "Periphery", "KRK")
     KIMUNAH = ("Kimūnah", "Kmn", "Periphery", "KMN")
@@ -121,6 +124,7 @@ class Provenance(ProvenanceEnum):
     SUSARRA = ("Šušarra", "Šuš", "Periphery", "SZU")
     TALL_BAZ_MUSIYAN = ("Tall Bāz Musiyān", "Bazm", "Periphery", "BZM")
     TALL_AL_FAKHAR = ("Tall al-Fakhar", "Fakh", "Periphery", "FAK")
+    TALL_AL_FAKHIRIYA = ("Tall al-Fakhīriyah", "Fakhī", "Periphery", "FKR")
     TALL_GHADAIYRIFAH = ("Tall Ghaḍaiyrīfah", "Ghad", "Periphery", "GDR")
     TALL_AL_HAWA = ("Tall al-Hawa", "Haw", "Periphery", "THW")
     TALL_IBRAHIM_BAYIS = ("Tall Ibrāhīm Bayis", "Iba", "Periphery", "IBA")

diff --git a/ebl/common/query/query_collation.py b/ebl/common/query/query_collation.py
@@ -4,7 +4,7 @@
 from typing import Dict, Iterable, Literal, Sequence
 from urllib.parse import parse_qsl
 
-DataType = Literal["dictionary", "afo-register"]
+DataType = Literal["dictionary", "afo-register", "colophons"]
 
 
 class Fields(Enum):
@@ -18,13 +18,20 @@ class Fields(Enum):
         "WILDCARD_FIELDS": [],
         "MARKDOWN_FIELDS": ["text"],
     }
+    COLOPHONS = {
+        "COLLATED_FIELDS": ["names"],
+        "WILDCARD_FIELDS": [],
+        "MARKDOWN_FIELDS": [],
+    }
 
     @staticmethod
     def findByDataType(data_type: DataType) -> Dict[str, Sequence[str]]:
         if data_type == "dictionary":
             return Fields.DICTIONARY.value
         elif data_type == "afo-register":
             return Fields.AFO_REGISTER.value
+        elif data_type == "colophons":
+            return Fields.COLOPHONS.value
         else:
             raise ValueError("Invalid data type")
 

diff --git a/ebl/fragmentarium/domain/genres.py b/ebl/fragmentarium/domain/genres.py
@@ -17,6 +17,7 @@
     ("ARCHIVAL", "Legal"),
     ("ARCHIVAL", "Legal", "Debt Note, Loan"),
     ("ARCHIVAL", "Legal", "Decree"),
+    ("ARCHIVAL", "Legal", "Deposit"),
     ("ARCHIVAL", "Legal", "Guardianship"),
     ("ARCHIVAL", "Legal", "Herding"),
     ("ARCHIVAL", "Legal", "Hire"),
@@ -276,6 +277,7 @@
         "Ur-Nanše",
     ),
     ("CANONICAL", "Lexicography", "Thematic Word Lists", "Practical Vocabulary"),
+    ("CANONICAL", "Lexicography", "Thematic Word Lists", "Ugumu"),
     ("CANONICAL", "Lexicography", "Thematic Word Lists", "Ura"),
     ("CANONICAL", "Lexicography", "Vocabularies"),
     ("CANONICAL", "Lexicography", "Vocabularies", "Antagal"),
@@ -416,6 +418,8 @@
     ("CANONICAL", "Magic", "Varia", "Namerimburuda"),
     ("CANONICAL", "Magic", "Varia", "Zuburudabeda"),
     ("CANONICAL", "School Tablet"),
+    ("CANONICAL", "School Tablet", "Model contract"),
+    ("CANONICAL", "School Tablet", "Model letter"),
     ("CANONICAL", "Technical"),
     ("CANONICAL", "Technical", "Astronomy"),
     ("CANONICAL", "Technical", "Astronomy", "I.NAM.GIŠ.HUR.AN.KI.A"),

diff --git a/ebl/fragmentarium/infrastructure/mongo_fragment_repository_get_extended.py b/ebl/fragmentarium/infrastructure/mongo_fragment_repository_get_extended.py
@@ -22,12 +22,42 @@
     aggregate_random,
 )
 from ebl.transliteration.infrastructure.queries import query_number_is
+from ebl.common.query.query_collation import CollatedFieldQuery
 
 
 def has_none_values(dictionary: dict) -> bool:
     return not all(dictionary.values())
 
 
+def _get_colophon_names_query(name_regex: str) -> Sequence[dict]:
+    return [
+        {"$unwind": "$colophon.individuals"},
+        {
+            "$project": {
+                "names": [
+                    "$colophon.individuals.name.value",
+                    "$colophon.individuals.sonOf.value",
+                    "$colophon.individuals.grandsonOf.value",
+                    "$colophon.individuals.family.value",
+                ]
+            }
+        },
+        {"$unwind": "$names"},
+        {
+            "$match": {
+                "names": {
+                    "$regex": rf"{name_regex}",
+                    "$options": "i",
+                }
+            }
+        },
+        {"$group": {"_id": None, "unique_names": {"$addToSet": "$names"}}},
+        {"$unwind": "$unique_names"},
+        {"$sort": {"unique_names": 1}},
+        {"$project": {"_id": 0, "name": "$unique_names"}},
+    ]
+
+
 class MongoFragmentRepositoryGetExtended(MongoFragmentRepositoryBase):
     def __init__(self, database):
         super().__init__(database)
@@ -162,24 +192,9 @@ def fetch_scopes(self, number: MuseumNumber) -> List[Scope]:
         ]
 
     def fetch_names(self, name_query: str) -> List[str]:
-        pipeline = [
-            {"$unwind": "$colophon.individuals"},
-            {
-                "$project": {
-                    "names": [
-                        "$colophon.individuals.name.value",
-                        "$colophon.individuals.sonOf.value",
-                        "$colophon.individuals.grandsonOf.value",
-                        "$colophon.individuals.family.value",
-                    ]
-                }
-            },
-            {"$unwind": "$names"},
-            {"$match": {"names": {"$regex": name_query, "$options": "i"}}},
-            {"$group": {"_id": None, "unique_names": {"$addToSet": "$names"}}},
-            {"$unwind": "$unique_names"},
-            {"$sort": {"unique_names": 1}},
-            {"$project": {"_id": 0, "name": "$unique_names"}},
-        ]
+        if len(name_query) < 3:
+            return []
+        name_regex = CollatedFieldQuery(name_query, "names", "colophons").value
+        pipeline = _get_colophon_names_query(name_regex)
         cursor = self._fragments.aggregate(pipeline)
         return [data["name"] for data in cursor if data["name"]]
diff --git a/ebl/tests/fragmentarium/test_fragment_repository_colophon.py b/ebl/tests/fragmentarium/test_fragment_repository_colophon.py
@@ -8,7 +8,7 @@
 
 
 def test_fetch_names(fragment_repository):
-    names = ["barmarum", "garmarum", "harmarum", "zarmarum"]
+    names = ["barmarum", "garmarum", "harmarum", "zarmārum"]
     [name, second_name, third_name, fourth_name] = [
         NameAttestationFactory.build(value=name) for name in names
     ]
@@ -32,3 +32,4 @@ def test_fetch_names(fragment_repository):
     fragment_repository.create(fragment)
     assert names == fragment_repository.fetch_names("mar")
     assert ["pallaqum"] == fragment_repository.fetch_names("pal")
+    assert [] == fragment_repository.fetch_names("ma")
diff --git a/ebl/transliteration/domain/atf_parsers/lark_parser/ebl_atf_abbreviations.lark b/ebl/transliteration/domain/atf_parsers/lark_parser/ebl_atf_abbreviations.lark
@@ -1,123 +1,126 @@
 PROVENANCE: "Assa"
-         | "Baba"
+         | "Abs"
+         | "Adb"
+         | "Ajr"
+         | "Ala"
+         | "Ama"
+         | "Anh"
+         | "Anš"
          | "Ašš"
-         | "Huz"
-         | "Kal"
-         | "Kho"
-         | "Nin"
-         | "Tar"
+         | "Baba"
          | "Bab"
+         | "Bakr"
+         | "Baq"
+         | "Bar"
+         | "Bazm"
+         | "Bitw"
          | "Bor"
+         | "Btb"
+         | "Chughā"
          | "Cut"
+         | "Der"
+         | "Dgr"
          | "Dil"
-         | "Isn"
-         | "Kiš"
-         | "Lar"
-         | "MetS"
-         | "Met"
-         | "Nēr"
-         | "Nip"
-         | "Sipam"
-         | "Sip"
-         | "Šad"
-         | "Šah"
-         | "Urk"
-         | "Ala"
-         | "Ama"
-         | "Emr"
-         | "Hat"
-         | "Mard"
-         | "Mar"
-         | "Meg"
-         | "Sus"
-         | "Uga"
+         | "Diqd"
          | "Dka"
-         | "Har"
-         | "Img"
-         | "Ktn"
-         | "Šub"
-         | "Guz"
-         | "Adb"
-         | "Ešn"
-         | "Gir"
-         | "Lag"
-         | "Nig"
-         | "Šur"
-         | "Hur"
-         | "Ham"
-         | "Ttb"
-         | "Umm"
-         | "Zab"
-         | "Btb"
          | "Dku"
-         | "Eri"
-         | "Gar"
-         | "Irs"
-         | "Ksr"
-         | "Kut"
-         | "Mrd"
-         | "Maš"
-         | "Puz"
-         | "Lrk"
-         | "Pik"
-         | "Mal"
-         | "Paš"
-         | "Ttl"
-         | "Elam"
-         | "Anš"
-         | "Der"
          | "Dun"
          | "Ebl"
-         | "Kan"
-         | "Kar"
-         | "Per"
-         | "Ter"
-         | "Tgo"
-         | "Qaṭ"
-         | "Unc"
-         | "Ur"
-         | "Kmn"
-         | "Ylk"
-         | "Shn"
-         | "Zaw"
-         | "Anh"
+         | "Elam"
+         | "Emr"
+         | "Eri"
+         | "Ešn"
+         | "Fakhī"
+         | "Fakh"
+         | "Gar"
+         | "Ghad"
+         | "Gir"
          | "Gla"
-         | "Diqd"
-         | "Miz"
+         | "Guz"
          | "Hafr"
          | "Haf"
-         | "Nasr"
-         | "Sul"
-         | "Abs"
-         | "Ajr"
+         | "Ham"
+         | "Har"
+         | "Hat"
+         | "Haw"
+         | "Hur"
+         | "Huz"
+         | "Iba"
+         | "Img"
          | "Iml"
+         | "Irs"
+         | "Isn"
          | "Jid"
+         | "Kal"
+         | "Kan"
+         | "Kar"
+         | "Kay"
          | "Khat"
          | "Kha"
+         | "Kho"
+         | "Kiš"
+         | "Kmn"
+         | "Ksr"
+         | "Ktn"
+         | "Kut"
+         | "Lag"
          | "Lah"
-         | "Muh"
-         | "Ubd"
-         | "Uaaj"
-         | "Uqa"
-         | "Baq"
-         | "Tum"
-         | "Waw"
-         | "Zar"
-         | "Bakr"
-         | "Bar"
-         | "Bitw"
-         | "Dgr"
+         | "Lar"
+         | "Lrk"
+         | "Mal"
+         | "Mard"
+         | "Mar"
+         | "Maš"
+         | "Meg"
+         | "MetS"
+         | "Met"
          | "Milm"
+         | "Miz"
+         | "Mrd"
+         | "Muh"
+         | "Nasr"
+         | "Nēr"
+         | "Nig"
+         | "Nin"
+         | "Nip"
          | "Nuzi"
+         | "Paš"
+         | "Per"
+         | "Pik"
+         | "Puz"
          | "Qat"
+         | "Qaṭ"
+         | "Šad"
+         | "Šah"
+         | "Shn"
+         | "Sipam"
+         | "Sip"
+         | "Šub"
+         | "Sul"
+         | "Šur"
          | "Surj"
+         | "Sus"
          | "Šuš"
-         | "Bazm"
-         | "Fakh"
-         | "Ghad"
-         | "Haw"
-         | "Iba"
+         | "Tar"
+         | "Ter"
+         | "Tgo"
          | "Tikr"
+         | "Ttb"
+         | "Ttl"
+         | "Tum"
+         | "Uaaj"
+         | "Ubd"
+         | "Uga"
+         | "Umm"
+         | "Unc"
+         | "Uqa"
+         | "Urk"
+         | "Ur"
+         | "Waw"
+         | "Ylk"
+         | "Zab"
+         | "Zar"
+         | "Zaw"
 PERIOD: "ED1_2"
       | "Fara"
       | "Hel"