- DHParser/transform.py: has_content: rules for matching content changed:...

- DHParser/transform.py: has_content: rules for matching content changed: regexp must not match the complete content, nur just the beginning

DHParser/transform.py

@@ -411,7 +411,14 @@ def is_one_of(context: List[Node], tag_name_set: AbstractSet[str]) -> bool:
 
 @transformation_factory
 def has_content(context: List[Node], regexp: str) -> bool:
-    """Checks a node's content against a regular expression."""
+    """
+    Checks a node's content against a regular expression.
+
+    In contrast to ``re.match`` the regular expression must match the complete
+    string and not just the beginning of the string to succeed!
+    """
+    if not regexp.endswith('$'):
+        regexp += "$"
     return bool(re.match(regexp, context[-1].content))
 
 

test/test_transform.py

@@ -26,7 +26,7 @@ sys.path.extend(['../', './'])
 
 from DHParser.syntaxtree import mock_syntax_tree
 from DHParser.transform import traverse, reduce_single_child, remove_whitespace, \
-    traverse_locally, collapse, lstrip, rstrip
+    traverse_locally, collapse, lstrip, rstrip, remove_content
 
 
 class TestRemoval:
@@ -71,6 +71,14 @@ class TestRemoval:
         rstrip([cst])
         assert cst.as_sxpr().find(":Whitespace") < 0, cst.as_sxpr()
 
+    def test_remove_content(self):
+        cst = mock_syntax_tree('(BelegLemma (:Series (:RegExp "#") (LAT_WORT (:RegExp "facitergula"))))')
+        remove_content([cst], '#')
+        assert cst.content == "#facitergula", str(cst.content)
+        reduce_single_child([cst])
+        remove_content([cst], '#')
+        assert cst.content == "facitergula"
+
 
 class TestConditionalTransformations:
     """Tests conditional transformations."""