better title_hash

yindaheng98 · Sep 5, 2024 · b9ce6ec · b9ce6ec
1 parent 28acdef
commit b9ce6ec
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 2 deletions.
diff --git a/dblp_crawler/parser.py b/dblp_crawler/parser.py
@@ -9,6 +9,10 @@
 logger = logging.getLogger("parser")
 
 
+def title_hash(title):
+    return re.sub(r"[^0-9a-z]", "", title.lower()) or title.lower()
+
+
 class Person:
     def __init__(self, data: ElementTree.Element) -> None:
         assert data.tag == "person", "Should be xml of a person in dblpperson!"
@@ -74,7 +78,7 @@ def title(self) -> str:
                 return " ".join(t for t in child.itertext())
 
     def title_hash(self) -> str:
-        return re.sub(r"[^0-9a-z\u4e00-\u9fa5]", "", self.title().lower())
+        return title_hash(self.title())
 
     def journal(self) -> Optional[str]:
         tag = {

diff --git a/setup.py b/setup.py
@@ -17,7 +17,7 @@
 
 setup(
     name='dblp_crawler',
-    version='2.1.5',
+    version='2.1.6',
     author='yindaheng98',
     author_email='[email protected]',
     url='https://github.com/yindaheng98/dblp-crawler',