github2gerrit 0.1.10__py3-none-any.whl → 0.1.11__py3-none-any.whl

github2gerrit/pr_content_filter.py

@@ -3,9 +3,10 @@
 #
 # PR Content Filtering Module
 #
-# This module provides an extensible, rule-based system for filtering and cleaning
-# GitHub pull request content for Gerrit consumption. It supports multiple automation
-# tools (Dependabot, pre-commit.ci, etc.) with author-specific filtering rules.
+# This module provides an extensible, rule-based system for filtering and
+# cleaning GitHub pull request content for Gerrit consumption. It supports
+# multiple automation tools (Dependabot, pre-commit.ci, etc.) with
+# author-specific filtering rules.
 #
 # Key features:
 # - Author-specific filtering rules
@@ -29,7 +30,8 @@ log = logging.getLogger("github2gerrit.pr_content_filter")
 
 # Common patterns used across filters
 _HTML_DETAILS_PATTERN = re.compile(
-    r"<details[^>]*>\s*<summary[^>]*>(.*?)</summary>\s*(.*?)</details>", re.IGNORECASE | re.DOTALL
+    r"<details[^>]*>\s*<summary[^>]*>(.*?)</summary>\s*(.*?)</details>",
+    re.IGNORECASE | re.DOTALL,
 )
 _MARKDOWN_LINK_PATTERN = re.compile(r"\[([^\]]+)\]\([^)]+\)")
 _HTML_TAG_PATTERN = re.compile(r"<[^>]+>")
@@ -50,8 +52,12 @@ class FilterConfig:
     author_rules: dict[str, str] = field(default_factory=dict)
 
     # Rule-specific configurations
-    dependabot_config: DependabotConfig = field(default_factory=lambda: DependabotConfig())
-    precommit_config: PrecommitConfig = field(default_factory=lambda: PrecommitConfig())
+    dependabot_config: DependabotConfig = field(
+        default_factory=lambda: DependabotConfig()
+    )
+    precommit_config: PrecommitConfig = field(
+        default_factory=lambda: PrecommitConfig()
+    )
 
 
 @dataclass
@@ -149,12 +155,18 @@ class DependabotRule(FilterRule):
 
     def _remove_compatibility_images(self, content: str) -> str:
         """Remove Dependabot compatibility score images."""
-        pattern = re.compile(r"!\[.*?\]\(https://camo\.githubusercontent\.com/[^)]*\)", re.IGNORECASE | re.DOTALL)
+        pattern = re.compile(
+            r"!\[.*?\]\(https://camo\.githubusercontent\.com/[^)]*\)",
+            re.IGNORECASE | re.DOTALL,
+        )
         return pattern.sub("", content)
 
     def _truncate_at_dependabot_commands(self, content: str) -> str:
         """Truncate at Dependabot command instructions."""
-        pattern = re.compile(r"Dependabot will resolve any conflicts", re.IGNORECASE | re.MULTILINE)
+        pattern = re.compile(
+            r"Dependabot will resolve any conflicts",
+            re.IGNORECASE | re.MULTILINE,
+        )
         match = pattern.search(content)
         if match:
             return content[: match.start()].rstrip()
@@ -210,7 +222,10 @@ class PRContentFilter:
         # Check author-specific rules first
         if author in self.config.author_rules:
             rule_name = self.config.author_rules[author]
-            return any(rule.__class__.__name__.lower().startswith(rule_name.lower()) for rule in self.rules)
+            return any(
+                rule.__class__.__name__.lower().startswith(rule_name.lower())
+                for rule in self.rules
+            )
 
         # Check if any rule matches
         return any(rule.matches(title, body, author) for rule in self.rules)
@@ -232,7 +247,9 @@ class PRContentFilter:
                 config_key = rule.get_config_key()
                 rule_config = getattr(self.config, config_key, None)
                 if rule_config:
-                    filtered_body = rule.apply(title, filtered_body, rule_config)
+                    filtered_body = rule.apply(
+                        title, filtered_body, rule_config
+                    )
 
         # Apply global post-processing
         filtered_body = self._post_process(title, filtered_body)
@@ -263,6 +280,9 @@ class PRContentFilter:
         # Clean up whitespace
         processed = self._clean_whitespace(processed)
 
+        # Remove trailing ellipses
+        processed = self._remove_trailing_ellipses(processed)
+
         return processed
 
     def _remove_emoji_codes(self, content: str) -> str:
@@ -283,14 +303,18 @@ class PRContentFilter:
 
             # Fix lines that started with emoji codes and now have leading space
             if cleaned_line.startswith(" ") and not line.startswith(" "):
-                # This line originally started with an emoji, remove the leading space
+                # This line originally started with an emoji, remove the
+                # leading space
                 cleaned_line = cleaned_line.lstrip()
 
             # Fix markdown headers that lost their emoji but kept leading space
-            # e.g., "### :sparkles: New features" -> "### New features" not "###  New features"
+            # e.g., "### :sparkles: New features" -> "### New features"
+            # not "###  New features"
             if cleaned_line.startswith("### "):
                 # Ensure exactly one space after ###
-                header_text = cleaned_line[4:].lstrip()  # Remove ### and any spaces
+                header_text = cleaned_line[
+                    4:
+                ].lstrip()  # Remove ### and any spaces
                 cleaned_line = f"### {header_text}" if header_text else "###"
             elif cleaned_line.startswith("## "):
                 # Same for ## headers
@@ -309,7 +333,8 @@ class PRContentFilter:
         for i, line in enumerate(cleaned_lines):
             final_lines.append(line)
 
-            # If this line looks like a heading (not starting with #) and should have
+            # If this line looks like a heading (not starting with #) and should
+            # have
             # a blank line after it, add one
             if (
                 i < len(cleaned_lines) - 1
@@ -380,7 +405,8 @@ class PRContentFilter:
         )
 
         if is_duplicate:
-            # Remove the duplicate line and any immediately following empty lines
+            # Remove the duplicate line and any immediately following empty
+            # lines
             remaining_lines = lines[first_content_line_idx + 1 :]
             while remaining_lines and not remaining_lines[0].strip():
                 remaining_lines = remaining_lines[1:]
@@ -407,6 +433,24 @@ class PRContentFilter:
 
         return cleaned
 
+    def _remove_trailing_ellipses(self, content: str) -> str:
+        """Remove trailing ellipses that are often left by truncated content."""
+        lines = content.splitlines()
+        cleaned_lines = []
+
+        for line in lines:
+            # Remove lines that are just "..." or whitespace + "..."
+            stripped = line.strip()
+            if stripped == "..." or stripped == "…":
+                continue
+
+            # Remove trailing ellipses from lines
+            cleaned_line = re.sub(r"\s*\.{3,}\s*$", "", line)
+            cleaned_line = re.sub(r"\s*…\s*$", "", cleaned_line)
+            cleaned_lines.append(cleaned_line)
+
+        return "\n".join(cleaned_lines)
+
     def add_rule(self, rule: FilterRule) -> None:
         """Add a custom filtering rule."""
         self.rules.append(rule)
@@ -434,7 +478,9 @@ def create_default_filter() -> PRContentFilter:
     return PRContentFilter(config)
 
 
-def filter_pr_body(title: str, body: str | None, author: str | None = None) -> str:
+def filter_pr_body(
+    title: str, body: str | None, author: str | None = None
+) -> str:
     """
     Main entry point for PR body filtering with default configuration.
 
@@ -454,7 +500,9 @@ def filter_pr_body(title: str, body: str | None, author: str | None = None) -> s
 
 
 # Legacy compatibility functions
-def should_filter_pr_body(title: str, body: str | None, author: str | None = None) -> bool:
+def should_filter_pr_body(
+    title: str, body: str | None, author: str | None = None
+) -> bool:
     """Legacy function for checking if filtering should be applied."""
     if not body:
         return False