Add optional batch_size to BatchAnalyzer.analyze_iterator

presidio-analyzer/presidio_analyzer/batch_analyzer_engine.py

@@ -44,10 +44,10 @@ def analyze_iterator(
         texts = self._validate_types(texts)
 
         # Process the texts as batch for improved performance
-        nlp_artifacts_batch: Iterator[Tuple[str, NlpArtifacts]] = (
-            self.analyzer_engine.nlp_engine.process_batch(
-                texts=texts, language=language, batch_size=batch_size
-            )
+        nlp_artifacts_batch: Iterator[
+            Tuple[str, NlpArtifacts]
+        ] = self.analyzer_engine.nlp_engine.process_batch(
+            texts=texts, language=language, batch_size=batch_size
         )
 
         list_results = []

presidio-analyzer/presidio_analyzer/nlp_engine/nlp_engine.py

@@ -1,4 +1,5 @@
 from abc import ABC, abstractmethod
+
 from typing import Iterable, Iterator, List, Optional, Tuple
 
 from presidio_analyzer.nlp_engine import NlpArtifacts

presidio-analyzer/presidio_analyzer/nlp_engine/spacy_nlp_engine.py

@@ -1,8 +1,10 @@
 import logging
+
 from pathlib import Path
 from typing import Dict, Iterator, List, Optional, Tuple, Union
 
 import spacy
+from presidio_analyzer.nlp_engine import NlpArtifacts, NlpEngine
 from spacy.language import Language
 from spacy.tokens import Doc, Span
 

presidio-analyzer/tests/test_batch_analyzer_engine.py

@@ -34,7 +34,7 @@ def test_analyze_iterator_returns_list_of_recognizer_results(
     texts, expected_output, batch_analyzer_engine_simple
 ):
 
-    results = batch_analyzer_engine_simple.analyze_iterator(texts=texts, language="en")
+    results = batch_analyzer_engine_simple.analyze_iterator(texts=texts, language="en", batch_size=2)
 
     assert len(results) == len(expected_output)
     for result, expected_result in zip(results, expected_output):

presidio-analyzer/tests/test_spacy_nlp_engine.py

@@ -21,6 +21,7 @@ def test_simple_process_text(spacy_nlp_engine):
     assert nlp_artifacts.lemmas[1] == "text"
 
 
+
 def test_process_batch_strings(spacy_nlp_engine):
     nlp_artifacts_batch = spacy_nlp_engine.process_batch(
         ["simple text", "simple text"], language="en"