Merge pull request #285 from hakonhagland/upd_addkeyword2

Use more accurate regex in add-keyword script
OPM · Jun 6, 2024 · 3d40a6f · 3d40a6f
2 parents 9c8ff37 + f9569ae
commit 3d40a6f
Showing 1 changed file with 3 additions and 1 deletion.
diff --git a/scripts/python/src/fodt/add_keyword.py b/scripts/python/src/fodt/add_keyword.py
@@ -116,7 +116,9 @@ def endElement(self, name: str):
 
     def extract_keyword_name(self, href: str) -> str:
         # Assume href starts with "#xxx.yyy.zzz.KEYWORD_NAME<space>"
-        if m:= re.match(r"#\d+\.\d+\.\d+\.(\w+)(?:\s+|$)", href):
+        # or "#xxx.yyy.zzz.KEYWORD_NAME|outline"
+        # KEYWORD_NAME can contain letters, numbers, and optionally a trailing hyphen or en-dash
+        if m:= re.match(r"#\d+\.\d+\.\d+\.(\w+[\-–]?)(?:\s+|$|\|outline$)", href):
             return m.group(1)
         else:
             return '<NOT FOUND>'