pyannotators-patterns 0.5.86__tar.gz → 0.5.88__tar.gz

{pyannotators_patterns-0.5.86 → pyannotators_patterns-0.5.88}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyannotators-patterns
-Version: 0.5.86
+Version: 0.5.88
 Summary: Annotator based on Presidio pattern recognizer
 Home-page: https://github.com/oterrier/pyannotators_patterns/
 Keywords: 

{pyannotators_patterns-0.5.86 → pyannotators_patterns-0.5.88}/setup.py

@@ -41,7 +41,7 @@ entry_points = \
                           'pyannotators_patterns.patterns:PatternsAnnotator']}
 
 setup(name='pyannotators-patterns',
-      version='0.5.86',
+      version='0.5.88',
       description='Annotator based on Presidio pattern recognizer',
       author='Olivier Terrier',
       author_email='olivier.terrier@kairntech.com',

{pyannotators_patterns-0.5.86 → pyannotators_patterns-0.5.88}/src/pyannotators_patterns/__init__.py

@@ -1,2 +1,2 @@
 """Annotator based on Presidio pattern recognizer"""
-__version__ = "0.5.86"
+__version__ = "0.5.88"

{pyannotators_patterns-0.5.86 → pyannotators_patterns-0.5.88}/src/pyannotators_patterns/patterns.py

@@ -52,7 +52,7 @@ class PatternsParameters(AnnotatorParameters):
     ```""" + PATTERNS_EXAMPLE_STR + "```", extra="key:label,val:json")
 
     score_threshold: float = Field(0.0, description="Minimum confidence value for detected entities to be returned")
-    context_similarity_factor: float = Field(0.0,
+    context_similarity_factor: float = Field(0.35,
                                              description="How much to enhance confidence of match entity, as explained [here](https://microsoft.github.io/presidio/tutorial/06_context/)",
                                              extra="advanced")
     min_score_with_context_similarity: float = Field(0.4,

pyannotators_patterns-0.5.88/tests/data/coords-document.json

@@ -0,0 +1,8 @@
+{
+  "text": "    Coordonnées degrés décimaux, référence devant :\n    Exemple : N85,8598654 W150,589654\n\n\n    Coordonnées degrés décimaux, référence derrière  : \n    Exemple 85,8598654N 150,589654W",
+  "metadata": {
+    "language": "fr"
+  },
+  "identifier": "c8ecc5153c542c4f6a07fbe813384842",
+  "title": "unknown test document"
+}

pyannotators_patterns-0.5.88/tests/data/tel-document.json

@@ -0,0 +1,8 @@
+{
+  "text": "Si vous êtes intéressé, veuillez nous appeler au +33.089-658-6494.",
+  "metadata": {
+    "language": "fr"
+  },
+  "identifier": "c9321541549ae539665b8bbf440cb1a0",
+  "title": "unknown test document"
+}

pyannotators_patterns-0.5.88/tests/data/tel.json

@@ -0,0 +1,21 @@
+{
+  "patterns": [
+    {
+      "name": "avec préfixe",
+      "regex": "(00|\\+)( |\\-|\\.)?(?P<prefix>9[976]\\d|8[987530]\\d|6[987]\\d|5[90]\\d|42\\d|3[875]\\d|2[98654321]\\d|9[8543210]|8[6421]|6[6543210]|5[87654321]|4[987654310]|3[9643210]|2[70]|7|1)( |\\-|\\.)?(?P<number>(?:\\d{1,3}( |\\-|\\.)?){5,14})\\b",
+      "score": 0.5
+    },
+    {
+      "name": "sans préfixe",
+      "regex": "\\b(?P<number>(?:\\d{1,3}( |\\-|\\.)?){5,14})\\b",
+      "score": 0.5
+    }
+  ],
+  "context": [
+    "appeler",
+    "appel",
+    "numéro",
+    "téléphone",
+    "téléphoner"
+  ]
+}

pyannotators_patterns-0.5.88/tests/test_tel.py

@@ -0,0 +1,32 @@
+import json
+from pathlib import Path
+from typing import List
+
+from dirty_equals import IsPartialDict
+from pymultirole_plugins.v1.schema import Document
+from pytest_check import check
+
+from pyannotators_patterns.patterns import PatternsAnnotator, PatternsParameters
+
+
+def test_tel(
+):
+    testdir = Path(__file__).parent
+    source = Path(testdir, "data/tel.json")
+    with source.open("r") as fin:
+        pat = json.load(fin)
+        parameters = PatternsParameters(mapping={
+            "telephone": json.dumps(pat, indent=2)
+        })
+    source = Path(testdir, "data/tel-document.json")
+    with source.open("r") as fin:
+        jdoc = json.load(fin)
+        doc = Document(**jdoc)
+    annotator = PatternsAnnotator()
+    docs: List[Document] = annotator.annotate([doc], parameters)
+    doc0 = docs[0]
+    tel = next(a.dict(exclude_none=True, exclude_unset=True) for a in doc0.annotations if
+               a.text == '+33.089-658-6494')
+    with check:
+        assert tel == IsPartialDict(labelName='telephone', text='+33.089-658-6494', score=0.85,
+                                    properties=IsPartialDict(prefix='33', number='089-658-6494'))

pyannotators_patterns-0.5.86/tests/data/coords-document.json

@@ -1,86 +0,0 @@
-{
-  "text": "    Coordonnées degrés décimaux, référence devant :\n    Exemple : N85,8598654 W150,589654\n\n\n    Coordonnées degrés décimaux, référence derrière  : \n    Exemple 85,8598654N 150,589654W",
-  "metadata": {
-    "language": "fr"
-  },
-  "annotations": [
-    {
-      "start": 66,
-      "end": 77,
-      "labelName": "coordonnees_geographiques",
-      "text": "N85,8598654",
-      "score": 0.9,
-      "properties": {
-        "analysis_explanation": {
-          "recognizer": "PatternRecognizer",
-          "pattern_name": "ref_lat",
-          "pattern": "\\b(?P<ref_lat>N|S|n|s)[0-9,]+\\b",
-          "original_score": 0.9,
-          "score": 0.9,
-          "score_context_improvement": 0,
-          "supportive_context_word": "",
-          "regex_flags": 26
-        }
-      }
-    },
-    {
-      "start": 78,
-      "end": 89,
-      "labelName": "coordonnees_geographiques",
-      "text": "W150,589654",
-      "score": 0.9,
-      "properties": {
-        "analysis_explanation": {
-          "recognizer": "PatternRecognizer",
-          "pattern_name": "ref_long",
-          "pattern": "\\b(?P<ref_long>E|O|w|e|o)[0-9,]+\\b",
-          "original_score": 0.9,
-          "score": 0.9,
-          "score_context_improvement": 0,
-          "supportive_context_word": "",
-          "regex_flags": 26
-        }
-      }
-    },
-    {
-      "start": 160,
-      "end": 171,
-      "labelName": "coordonnees_geographiques",
-      "text": "85,8598654N",
-      "score": 0.9,
-      "properties": {
-        "analysis_explanation": {
-          "recognizer": "PatternRecognizer",
-          "pattern_name": "ref_lat_DEVANT",
-          "pattern": "\\b[0-9,]+(?P<ref_lat>N|S|n|s)\\b",
-          "original_score": 0.9,
-          "score": 0.9,
-          "score_context_improvement": 0,
-          "supportive_context_word": "",
-          "regex_flags": 26
-        }
-      }
-    },
-    {
-      "start": 172,
-      "end": 183,
-      "labelName": "coordonnees_geographiques",
-      "text": "150,589654W",
-      "score": 0.9,
-      "properties": {
-        "analysis_explanation": {
-          "recognizer": "PatternRecognizer",
-          "pattern_name": "ref_long_DEVANT",
-          "pattern": "\\b[0-9,]+(?P<ref_long>E|O|w|e|o)\\b",
-          "original_score": 0.9,
-          "score": 0.9,
-          "score_context_improvement": 0,
-          "supportive_context_word": "",
-          "regex_flags": 26
-        }
-      }
-    }
-  ],
-  "identifier": "c8ecc5153c542c4f6a07fbe813384842",
-  "title": "unknown test document"
-}