small fix to resolve regex max error for ngram words

davidberenstein1957 · Sep 26, 2022 · 0326bec · 0326bec
1 parent ed6ad57
commit 0326bec
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 2 deletions.
diff --git a/concise_concepts/conceptualizer/Conceptualizer.py b/concise_concepts/conceptualizer/Conceptualizer.py
@@ -327,7 +327,8 @@ def add_patterns(input_dict):
                                 specific_copy[self.match_key] = "{op}".join(word_parts)
                             else:
                                 specific_copy[self.match_key] = {
-                                    "regex": r"(?i)" + "{op}".join(word_parts)
+                                    "regex": r"(?i)"
+                                    + re.escape(f"{op}".join(word_parts))
                                 }
 
                             patterns.append(

diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "concise-concepts"
-version = "0.6"
+version = "0.6.1"
 description = "This repository contains an easy and intuitive approach to few-shot NER using most similar expansion over spaCy embeddings. Now with entity confidence scores!"
 authors = ["David Berenstein <david.m.berenstein@gmail.com>"]
 license = "MIT"