add NgramMatchResource

ebl/common/application/ngram_matcher.py

@@ -0,0 +1,46 @@
+from typing import Set, Tuple, Optional, Sequence, List
+
+
+def aggregate_ngram_overlaps(
+    ngrams: Set[Tuple[str]], limit: Optional[int] = None
+) -> Sequence[dict]:
+    ngram_list = list(ngrams)
+    pipeline: List[dict] = [
+        {"$match": {"textId.category": {"$ne": 99}}},
+        {
+            "$project": {
+                "_id": 0,
+                "textId": 1,
+                "name": 1,
+                "stage": 1,
+                "overlap": {
+                    "$let": {
+                        "vars": {
+                            "intersection": {
+                                "$size": {"$setIntersection": ["$ngrams", ngram_list]}
+                            },
+                            "minLength": {
+                                "$min": [
+                                    {"$size": "$ngrams"},
+                                    {"$size": [ngram_list]},
+                                ]
+                            },
+                        },
+                        "in": {
+                            "$cond": [
+                                {"$eq": ["$$minLength", 0]},
+                                0.0,
+                                {"$divide": ["$$intersection", "$$minLength"]},
+                            ]
+                        },
+                    }
+                },
+            }
+        },
+        {"$sort": {"overlap": -1}},
+    ]
+
+    if limit:
+        pipeline.append({"$limit": limit})
+
+    return pipeline

ebl/fragmentarium/web/bootstrap.py

@@ -10,6 +10,7 @@
 from ebl.fragmentarium.web.folio_pager import FolioPagerResource
 from ebl.fragmentarium.web.folios import FoliosResource
 from ebl.fragmentarium.web.fragment_genre import FragmentGenreResource
+from ebl.fragmentarium.web.fragment_ngram_matcher import NgramMatchResource
 from ebl.fragmentarium.web.fragment_script import FragmentScriptResource
 from ebl.fragmentarium.web.fragment_date import (
     FragmentDateResource,
@@ -85,6 +86,7 @@ def create_fragmentarium_routes(api: falcon.App, context: Context):
     fragment_query = FragmentsQueryResource(
         context.fragment_repository, context.get_transliteration_query_factory()
     )
+    ngram_matcher = NgramMatchResource(context.fragment_repository)
     genres = GenresResource()
     periods = PeriodsResource()
     lemmatization = LemmatizationResource(updater)
@@ -124,6 +126,7 @@ def create_fragmentarium_routes(api: falcon.App, context: Context):
         ("/fragments/{number}/annotations", annotations),
         ("/fragments/{number}/photo", photo),
         ("/fragments/{number}/corpus", chapters),
+        ("/fragments/{number}/ngrams", ngram_matcher),
         ("/genres", genres),
         ("/periods", periods),
         ("/statistics", statistics),

ebl/fragmentarium/web/fragment_ngram_matcher.py

@@ -0,0 +1,22 @@
+from ebl.common.application.ngram_matcher import aggregate_ngram_overlaps
+from ebl.corpus.application.text_repository import TextRepository
+from ebl.fragmentarium.application.fragment_repository import FragmentRepository
+from falcon import Request, Response
+
+from ebl.transliteration.domain.museum_number import MuseumNumber
+
+
+class NgramMatchResource:
+    def __init__(
+        self,
+        fragment_repository: FragmentRepository,
+        text_repository: TextRepository,
+    ):
+        self._fragment_repository = fragment_repository
+        self._text_repository = text_repository
+
+    def on_get(self, _req: Request, resp: Response, number: str) -> None:
+        ngrams = self._fragment_repository.get_ngrams(MuseumNumber.of(number))
+        resp.media = self._text_repository._chapters.aggregate(
+            aggregate_ngram_overlaps(ngrams)
+        )