Improve javadoc parsing

standardize_test_format/__init__.py

@@ -5,27 +5,31 @@ Tool for standardizing Java tests.
 
 import re
 
+PATTERN_JAVADOC = r'/\*\*(?P<javadoc>.*(\n\s*\*.*)*?)\s*\*/'
+
 TEST_PATTERN: re.Pattern = re.compile(
-        r'(?:/\*\*(?P<comment>.*)\*/)?\s*'
+        r''
+        + r'(?:' + PATTERN_JAVADOC + r'\s*)?'
         + r'@(?P<annotation>Test|BeforeEach|ParameterizedTest)\s*'
-        + r'(?:@DisplayName\("(?P<display>.*)"\)\s*)?'
+        + r'(?:@DisplayName\("(?P<display>[^"]*?)"\)\s*)?'
         + r'(?P<visibility>public\s+|private\s+)?void\s+(?P<name>\w+)\(',
-        re.IGNORECASE | re.DOTALL)
+        re.IGNORECASE)
 
 END_SYMBOLS = '.?!'
 
 def format_test_prefix(name: str, description: str, annotation:
                        str,visibility:str, with_javadoc: bool,
                        with_display_name: bool) -> str:
+    indent = ''
     str_builder = []
     if with_javadoc:
         str_builder += ['/** ',description,' */','\n']
-    str_builder += ['@', annotation]
+    str_builder += [indent, '@', annotation]
     if with_display_name:
-        str_builder += ['\n', '@DisplayName("']
+        str_builder += ['\n', indent, '@DisplayName("']
         str_builder.append(description.rstrip(END_SYMBOLS))
         str_builder += ['")']
-    str_builder += ['\n']
+    str_builder += ['\n', indent]
     if visibility:
         str_builder += [visibility, ' ']
     str_builder += ['void ',name,'(']
@@ -44,14 +48,13 @@ def to_camel_case(description: str) -> str:
 def from_camel_case(name: str) -> str:
     return re.sub(r'(^|[A-Z])[a-z]*', lambda x: ' '+x.group(0).capitalize(), name).strip()
 
-def parse_comment_to_description(text: str| None):
+def parse_javadoc_to_description(text: str| None):
     if text is None:
         return ''
-    text = re.sub(r'^\s*\*', ' ', text.strip()).strip()
-    return text
+    return re.sub(r'^\s*\*', ' ', text.strip()).strip()
 
 def replace_test_pattern(match: re.Match, with_javadoc: bool, with_display_name: bool) -> str:
-    comment = parse_comment_to_description(match.group('comment'))
+    javadoc = parse_javadoc_to_description(match.group('javadoc'))
 
 
     annotation = match.group('annotation').strip()
@@ -60,7 +63,7 @@ def replace_test_pattern(match: re.Match, with_javadoc: bool, with_display_name:
     display = (match.group('display') or '').strip()
 
 
-    description = display or comment or from_camel_case(name)
+    description = display or javadoc or from_camel_case(name)
 
     return format_test_prefix(to_camel_case(description),
                                    description, annotation, visibility,

test/test_standardize.py

@@ -1,5 +1,6 @@
 
-from standardize_test_format import standardize_java_text
+from standardize_test_format import standardize_java_text, PATTERN_JAVADOC
+import re
 
 
 INPUT_1 = """
@@ -39,8 +40,8 @@ public void helloWorldTest(
 
 INPUT_4 = """
 /**
-* Concat two produces a new array with the two input arrays joined together, with no separators.
-*/
+ * Concat two produces a new array with the two input arrays joined together, with no separators.
+ */
 @Test
 public void concatTwo()
 """
@@ -52,6 +53,11 @@ public void concatTwoProducesANewArrayWithTheTwoInputArraysJoinedTogetherWithNoS
 """
 
 
+def test_javadoc_parsing():
+    assert re.match(PATTERN_JAVADOC, '/** Hello World */') is not None
+    assert re.match(PATTERN_JAVADOC, '/** Hello\n  * World */') is not None
+    assert re.match(PATTERN_JAVADOC, '/**\n  * Hello World\n */') is not None
+
 
 def test_1():
     assert standardize_java_text(INPUT_1.strip(),False,True) == OUTPUT_1.strip()