Merge pull request #162 from Christoph-Koschel/patch-1

Escape special Markdown characters

action.yml

@@ -75,4 +75,8 @@ inputs:
   GITHUB_URL:
     description: 'Base url of GitHub API'
     required: false
-    default: ${{ github.api_url }}
+    default: ${{ github.api_url }}
+  ESCAPE:
+    description: 'Escape all special Markdown characters'
+    required: false
+    default: true

main.py

@@ -295,6 +295,9 @@ class TodoParser(object):
     ORG_PROJECTS_PATTERN = re.compile(r'(?<=org projects:\s).+')
 
     def __init__(self):
+        # Determine if the Issues should be escaped.
+        self.should_escape = os.getenv('INPUT_ESCAPE', 'true') == 'true'
+
         # Load any custom identifiers, otherwise use the default.
         custom_identifiers = os.getenv('INPUT_IDENTIFIERS')
         self.identifiers = ['TODO']
@@ -530,7 +533,10 @@ def _extract_issue_if_exists(self, comment, marker, code_block):
                     elif org_projects:
                         issue.org_projects.extend(org_projects)
                     elif len(cleaned_line):
-                        issue.body.append(cleaned_line)
+                        if self.should_escape:
+                            issue.body.append(self._escape_markdown(cleaned_line))
+                        else:
+                            issue.body.append(cleaned_line)
 
         if issue is not None and issue.identifier is not None and self.identifiers_dict is not None:
             for identifier_dict in self.identifiers_dict:
@@ -541,6 +547,23 @@ def _extract_issue_if_exists(self, comment, marker, code_block):
 
         return issue
 
+    @staticmethod
+    def _escape_markdown(comment):
+        # All basic characters according to: https://www.markdownguide.org/basic-syntax
+        must_escaped = ['\\', '<', '>', '#', '`', '*', '_', '[', ']', '(', ')', '!', '+', '-', '.', '|', '{', '}', '~', '=']
+
+        escaped = ''
+
+        # Linear Escape Algorithm, because the algorithm ends in an infinite loop when using the function 'replace',
+        # which tries to replace all backslashes with duplicate backslashes, i.e. also the already other escaped
+        # characters.
+        for c in comment:
+            if c in must_escaped:
+                escaped += '\\' + c
+            else:
+                escaped += c
+        return escaped
+
     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_escape.diff

@@ -0,0 +1,19 @@
+diff --git a/tests/ExampleFile.java b/tests/ExampleFile.java
+index d340f6a..29b54da 100644
+--- a/tests/ExampleFile.java
++++ b/tests/ExampleFile.java
+@@ -1,13 +1,5 @@
+ package com.mydomain.myapp;
+
+ public class JavaTests {
+-    // TODO: Some Java
+-    // # Some title
+-    // <SomeTag>
+
+-    /*
+-    TODO: Definitely some Java
+-    # Another title
+-    <AnotherTag>
+-    */
+ }
+\ No newline at end of file

tests/test_todo_parser.py

@@ -169,7 +169,7 @@ def test_clojure_issues(self):
 
     def test_nix_issues(self):
         self.assertEqual(count_issues_for_file_type(self.raw_issues, 'nix'), 2)
-        
+
     def test_xaml_issues(self):
         self.assertEqual(count_issues_for_file_type(self.raw_issues, 'xml'), 2)
 
@@ -204,3 +204,26 @@ def test_multiple_ignores(self):
         # Includes 2 tests for Crystal.
         self.assertEqual(count_issues_for_file_type(self.raw_issues, 'ruby'), 5)
         os.environ['INPUT_IGNORE'] = ''
+
+class EscapeMarkdownTest(unittest.TestCase):
+    def test_simple_escape(self):
+        os.environ['INPUT_ESCAPE'] = 'true'
+        parser = TodoParser()
+        with open('syntax.json', 'r') as syntax_json:
+            parser.syntax_dict = json.load(syntax_json)
+        diff_file = open('tests/test_escape.diff', 'r')
+
+        # I had no other idea to make these checks dynamic.
+        self.raw_issues = parser.parse(diff_file)
+        self.assertEqual(len(self.raw_issues), 2)
+
+        issue = self.raw_issues[0]
+        self.assertEqual(len(issue.body), 2)
+        self.assertEqual(issue.body[0], '\\# Some title')
+        self.assertEqual(issue.body[1], '\\<SomeTag\\>')
+
+        issue = self.raw_issues[1]
+        self.assertEqual(len(issue.body), 2)
+        self.assertEqual(issue.body[0], '\\# Another title')
+        self.assertEqual(issue.body[1], '\\<AnotherTag\\>')
+