including metadata

app.py

@@ -3,7 +3,8 @@ import streamlit as st
 import re 
 import logging
 from presidio_anonymizer import AnonymizerEngine
-from presidio_analyzer import AnalyzerEngine, RecognizerRegistry
+from presidio_analyzer import AnalyzerEngine, PatternRecognizer
+
 from annotated_text import annotated_text
 from flair_recognizer import FlairRecognizer
 
@@ -36,9 +37,17 @@ def analyzer_engine():
 
 def analyze(**kwargs):
     """Analyze input using Analyzer engine and input arguments (kwargs)."""
+    analyzer_engine = analyzer_engine()
+
     if "entities" not in kwargs or "All" in kwargs["entities"]:
         kwargs["entities"] = None
-    return analyzer_engine().analyze(**kwargs)
+
+    if st.session_state.excluded_words:
+        excluded_words_recognizer = PatternRecognizer(supported_entity="MANUAL ADD",
+                                      deny_list=st.session_state.excluded_words)
+        analyzer_engine.registry.add_recognizer(excluded_words_recognizer)
+
+    return analyzer_engine.analyze(**kwargs)
 
 def annotate():
     text = st.session_state.text 
@@ -88,8 +97,8 @@ def analyze_text():
                 return_decision_process=False,
             )
 
-            if st.session_state.excluded_words:
-                analyze_results = include_manual_input(analyze_results)
+            # if st.session_state.excluded_words:
+            #     analyze_results = include_manual_input(analyze_results)
 
             if st.session_state.allowed_words:
                 analyze_results = exclude_manual_input(analyze_results)
@@ -99,29 +108,29 @@ def analyze_text():
             logging.info(
                 f"analyse results: {st.session_state.analyze_results}\n"
             )
-            
 
-def include_manual_input(analyze_results):
-    analyze_results_extended=analyze_results
-    logging.info(
-                f"analyse results before adding extra words: {analyze_results}\n"
-            )
-    for word in st.session_state.excluded_words:
-        if word in st.session_state.text:
-            r = re.compile(word)
-            index_entries = [[m.start(),m.end()] for m in r.finditer(st.session_state.text)]
-            for entry in index_entries:
-                start=entry[0]
-                end=entry[1]
+
+# def include_manual_input(analyze_results):
+#     analyze_results_extended=analyze_results
+#     logging.info(
+#                 f"analyse results before adding extra words: {analyze_results}\n"
+#             )
+#     for word in st.session_state.excluded_words:
+#         if word in st.session_state.text:
+#             r = re.compile(word)
+#             index_entries = [[m.start(),m.end()] for m in r.finditer(st.session_state.text)]
+#             for entry in index_entries:
+#                 start=entry[0]
+#                 end=entry[1]
                 
-                analyze_results_extended.append({"type": "MANUAL ADD", "start": start, "end": end, "score": 1.0})
-    logging.info(
-                f"analyse results after adding allowed words: {analyze_results_extended}\n"
-            )
-    logging.info(
-                f"type of entries in results: {type(analyze_results[0])}\n"
-            )
-    return analyze_results_extended
+#                 analyze_results_extended.append("type": "MANUAL ADD", "start": start, "end": end, "score": 1.0})
+#     logging.info(
+#                 f"analyse results after adding allowed words: {analyze_results_extended}\n"
+#             )
+#     logging.info(
+#                 f"type of entries in results: {type(analyze_results[0])}\n"
+#             )
+#     return analyze_results_extended
 
 def exclude_manual_input(analyze_results):
     analyze_results_fltered=[]