Removed the _remove_lucene_chars function

Author: alexthomas93

src/neo4j_graphrag/indexes.py

@@ -471,35 +471,6 @@ async def async_upsert_vector_on_relationship(
         ) from e
 
 
-def _remove_lucene_chars(text: str) -> str:
-    """Remove Lucene special characters"""
-    special_chars = [
-        "+",
-        "-",
-        "&",
-        "|",
-        "!",
-        "(",
-        ")",
-        "{",
-        "}",
-        "[",
-        "]",
-        "^",
-        '"',
-        "~",
-        "*",
-        "?",
-        ":",
-        "\\",
-        "/",
-    ]
-    for char in special_chars:
-        if char in text:
-            text = text.replace(char, " ")
-    return text.strip()
-
-
 def _sort_by_index_name(
     records: List[neo4j.Record], index_name: str
 ) -> List[neo4j.Record]:

src/neo4j_graphrag/retrievers/hybrid.py

@@ -27,7 +27,6 @@
     RetrieverInitializationError,
     SearchValidationError,
 )
-from neo4j_graphrag.indexes import _remove_lucene_chars
 from neo4j_graphrag.neo4j_queries import get_search_query
 from neo4j_graphrag.retrievers.base import Retriever
 from neo4j_graphrag.types import (
@@ -184,7 +183,7 @@ def get_search_results(
         parameters = validated_data.model_dump(exclude_none=True)
         parameters["vector_index_name"] = self.vector_index_name
         parameters["fulltext_index_name"] = self.fulltext_index_name
-        parameters["query_text"] = _remove_lucene_chars(query_text)
+        parameters["query_text"] = query_text
 
         if query_text and not query_vector:
             if not self.embedder:
@@ -344,7 +343,7 @@ def get_search_results(
         parameters = validated_data.model_dump(exclude_none=True)
         parameters["vector_index_name"] = self.vector_index_name
         parameters["fulltext_index_name"] = self.fulltext_index_name
-        parameters["query_text"] = _remove_lucene_chars(query_text)
+        parameters["query_text"] = query_text
 
         if query_text and not query_vector:
             if not self.embedder:

tests/unit/retrievers/test_hybrid.py

@@ -21,7 +21,6 @@
     EmbeddingRequiredError,
     RetrieverInitializationError,
 )
-from neo4j_graphrag.indexes import _remove_lucene_chars
 from neo4j_graphrag.neo4j_queries import get_search_query
 from neo4j_graphrag.retrievers import HybridCypherRetriever, HybridRetriever
 from neo4j_graphrag.types import RetrieverResult, RetrieverResultItem, SearchType
@@ -269,7 +268,7 @@ def test_hybrid_search_sanitizes_text(
             "vector_index_name": vector_index_name,
             "top_k": top_k,
             "effective_search_ratio": effective_search_ratio,
-            "query_text": _remove_lucene_chars(query_text),
+            "query_text": query_text,
             "fulltext_index_name": fulltext_index_name,
             "query_vector": embed_query_vector,
         },
@@ -599,7 +598,7 @@ def test_hybrid_cypher_search_sanitizes_text(
             "vector_index_name": vector_index_name,
             "top_k": top_k,
             "effective_search_ratio": effective_search_ratio,
-            "query_text": _remove_lucene_chars(query_text),
+            "query_text": query_text,
             "fulltext_index_name": fulltext_index_name,
             "query_vector": embed_query_vector,
         },

tests/unit/test_indexes.py

@@ -23,7 +23,6 @@
     create_fulltext_index,
     create_vector_index,
     drop_index_if_exists,
-    _remove_lucene_chars,
     upsert_vector,
     upsert_vector_on_relationship,
 )
@@ -288,49 +287,3 @@ def test_upsert_vector_raises_neo4j_insertion_error(
         upsert_vector(driver, id, embedding_property, vector)
 
     assert "Upserting vector to Neo4j failed" in str(excinfo)
-
-
-def test_escaping_lucene() -> None:
-    """Test escaping lucene characters"""
-    assert _remove_lucene_chars("Hello+World") == "Hello World"
-    assert _remove_lucene_chars("Hello World\\") == "Hello World"
-    assert (
-        _remove_lucene_chars("It is the end of the world. Take shelter!")
-        == "It is the end of the world. Take shelter"
-    )
-    assert (
-        _remove_lucene_chars("It is the end of the world. Take shelter&&")
-        == "It is the end of the world. Take shelter"
-    )
-    assert (
-        _remove_lucene_chars("Bill&&Melinda Gates Foundation")
-        == "Bill  Melinda Gates Foundation"
-    )
-    assert (
-        _remove_lucene_chars("It is the end of the world. Take shelter(&&)")
-        == "It is the end of the world. Take shelter"
-    )
-    assert (
-        _remove_lucene_chars("It is the end of the world. Take shelter??")
-        == "It is the end of the world. Take shelter"
-    )
-    assert (
-        _remove_lucene_chars("It is the end of the world. Take shelter^")
-        == "It is the end of the world. Take shelter"
-    )
-    assert (
-        _remove_lucene_chars("It is the end of the world. Take shelter+")
-        == "It is the end of the world. Take shelter"
-    )
-    assert (
-        _remove_lucene_chars("It is the end of the world. Take shelter-")
-        == "It is the end of the world. Take shelter"
-    )
-    assert (
-        _remove_lucene_chars("It is the end of the world. Take shelter~")
-        == "It is the end of the world. Take shelter"
-    )
-    assert (
-        _remove_lucene_chars("It is the end of the world. Take shelter/")
-        == "It is the end of the world. Take shelter"
-    )