Merge pull request #164 from Christoph-Koschel/patch-2

Allows to have no spaces between a comment pattern and a TODO identifier

.gitignore

@@ -139,4 +139,5 @@ dmypy.json
 # Cython debug symbols
 cython_debug/
 
-
+# JetBrains
+.idea

main.py

@@ -413,7 +413,32 @@ def parse(self, diff_file):
             for marker in block['markers']:
                 # Check if there are line or block comments.
                 if marker['type'] == 'line':
-                    comment_pattern = r'(^[+\-\s].*' + marker['pattern'] + r'\s.+$)'
+                    # Add a negative lookup include the second character from alternative comment patterns
+                    # This step is essential to handle cases like in Julia, where '#' and '#=' are comment patterns.
+                    # It ensures that when a space after the comment is optional ('\s' => '\s*'),
+                    # the second character would be matched because of the any character expression ('.+').
+                    suff_escape_list = []
+                    pref_escape_list = []
+                    for to_escape in block['markers']:
+                        if to_escape['type'] == 'line':
+                            if to_escape['pattern'] == marker['pattern']:
+                                continue
+                            if marker['pattern'][0] == to_escape['pattern'][0]:
+                                suff_escape_list.append(self._extract_character(to_escape['pattern'], 1))
+                        else:
+                            # Block comments and line comments cannot have the same comment pattern,
+                            # so a check if the string is the same is unnecessary
+                            if to_escape['pattern']['start'][0] == marker['pattern'][0]:
+                                suff_escape_list.append(self._extract_character(to_escape['pattern']['start'], 1))
+                            search = to_escape['pattern']['end'].find(marker['pattern'])
+                            if search != -1:
+                                pref_escape_list.append(self._extract_character(to_escape['pattern']['end'], search - 1))
+
+                    comment_pattern = (r'(^[+\-\s].*' +
+                                       (r'(?<!(' + '|'.join(pref_escape_list) + r'))' if len(pref_escape_list) > 0 else '') +
+                                       marker['pattern'] +
+                                       (r'(?!(' + '|'.join(suff_escape_list) + r'))' if len(suff_escape_list) > 0 else '') +
+                                       r'\s*.+$)')
                     comments = re.finditer(comment_pattern, block['hunk'], re.MULTILINE)
                     extracted_comments = []
                     prev_comment = None
@@ -564,6 +589,26 @@ def _escape_markdown(comment):
                 escaped += c
         return escaped
 
+    @staticmethod
+    def _extract_character(input_str, pos):
+        # Extracts a character from the input string at the specified position,
+        # considering escape sequences when applicable.
+        # Test cases
+        # print(_extract_character("/\\*", 1))   # Output: "\*"
+        # print(_extract_character("\\*", 0))    # Output: "\*"
+        # print(_extract_character("\\", 0))     # Output: "\\"
+        # print(_extract_character("w", 0))      # Output: "w"
+        # print(_extract_character("wa", 1))     # Output: "a"
+        # print(_extract_character("\\\\w", 1))  # Output: "\\"
+        if input_str[pos] == '\\':
+            if pos >= 1 and not input_str[pos - 1] == '\\' and len(input_str) > pos + 1:
+                return '\\' + input_str[pos + 1]
+            return '\\\\'
+        if pos >= 1:
+            if input_str[pos - 1] == '\\':
+                return '\\' + input_str[pos]
+        return input_str[pos]
+
     def _get_line_status(self, comment):
         """Return a Tuple indicating whether this is an addition/deletion/unchanged, plus the cleaned comment."""
         addition_search = self.ADDITION_PATTERN.search(comment)

tests/test_closed.diff

@@ -153,12 +153,17 @@ index 0000000..7cccc5b
 --- /dev/null
 +++ b/src/tests/example_file.jl
 @@ -0,0 +1,2 @@
-- # TODO: Hopefully this comment turns into an issue
+- #TODO: Hopefully this comment turns into an issue
+- # TODO: Hopefully this comment also turns into an issue
 - print("Hello World")
 - #= TODO: Multiline comments
 -   also need to be turned into task, and hopefully
 -   kept together as one.
 - =#
+- #=TODO: Another copied multiline comment
+-   also need to be turned into task, and hopefully
+-   kept together as one.
+- =#
 diff --git a/tests/defs.bzl b/tests/defs.bzl
 index 525e25d..ba4e68d 100644
 --- a/tests/defs.bzl

tests/test_todo_parser.py

@@ -129,7 +129,7 @@ def test_tex_issues(self):
         self.assertEqual(count_issues_for_file_type(self.raw_issues, 'tex'), 2)
 
     def test_julia_issues(self):
-        self.assertEqual(count_issues_for_file_type(self.raw_issues, 'julia'), 2)
+        self.assertEqual(count_issues_for_file_type(self.raw_issues, 'julia'), 4)
 
     def test_starlark_issues(self):
         self.assertEqual(count_issues_for_file_type(self.raw_issues, 'python'), 5)