feat: improved parsing of commit message in backend

backend/app/git/status/incoming_changes.py

@@ -2,33 +2,50 @@
 
 import os
 import logging
-from .utils import extract_data_from_yaml, determine_type
+from .utils import extract_data_from_yaml, determine_type, parse_commit_message
 
 logger = logging.getLogger(__name__)
 
+
 def get_incoming_changes(repo, branch):
     incoming_changes = []
     diff = repo.git.diff(f'HEAD...origin/{branch}', name_only=True)
     changed_files = diff.split('\n') if diff else []
-    
+
     for file_path in changed_files:
         if file_path:
             full_path = os.path.join(repo.working_dir, file_path)
-            file_data = extract_data_from_yaml(full_path) if os.path.exists(full_path) else None
-            
+            file_data = extract_data_from_yaml(full_path) if os.path.exists(
+                full_path) else None
+
             # Correcting the git show command
-            commit_message = repo.git.show(f'HEAD...origin/{branch}', '--format=%B', '-s', file_path).strip()
-            
+            raw_commit_message = repo.git.show(f'HEAD...origin/{branch}',
+                                               '--format=%B', '-s',
+                                               file_path).strip()
+            parsed_commit_message = parse_commit_message(
+                raw_commit_message
+            )  # Parse commit message using the util function
+
             incoming_changes.append({
-                'name': file_data.get('name', os.path.basename(file_path)) if file_data else os.path.basename(file_path),
-                'id': file_data.get('id') if file_data else None,
-                'type': determine_type(file_path),
-                'status': 'Incoming',
-                'file_path': file_path,
-                'commit_message': commit_message,  # Include commit message here
-                'staged': False,
-                'modified': True,
-                'deleted': False
+                'name':
+                file_data.get('name', os.path.basename(file_path))
+                if file_data else os.path.basename(file_path),
+                'id':
+                file_data.get('id') if file_data else None,
+                'type':
+                determine_type(file_path),
+                'status':
+                'Incoming',
+                'file_path':
+                file_path,
+                'commit_message':
+                parsed_commit_message,  # Use parsed commit message
+                'staged':
+                False,
+                'modified':
+                True,
+                'deleted':
+                False
             })
-    
-    return incoming_changes
+
+    return incoming_changes

backend/app/git/status/utils.py

@@ -3,31 +3,34 @@
 import os
 import yaml
 import logging
+import re
 
 logger = logging.getLogger(__name__)
 
+
 def extract_data_from_yaml(file_path):
     logger.debug(f"Extracting data from file: {file_path}")
     try:
         with open(file_path, 'r') as f:
             content = yaml.safe_load(f)
-            logger.debug(f"File content: {content}")  # Log the full file content
+            logger.debug(
+                f"File content: {content}")  # Log the full file content
             if content is None:
-                logger.error(f"Failed to parse YAML file or file is empty: {file_path}")
+                logger.error(
+                    f"Failed to parse YAML file or file is empty: {file_path}")
                 return None
-            
+
             # Check if expected keys are in the content
             if 'name' not in content or 'id' not in content:
-                logger.warning(f"'name' or 'id' not found in file: {file_path}")
-            
-            return {
-                'name': content.get('name'),
-                'id': content.get('id')
-            }
+                logger.warning(
+                    f"'name' or 'id' not found in file: {file_path}")
+
+            return {'name': content.get('name'), 'id': content.get('id')}
     except Exception as e:
         logger.warning(f"Error reading file {file_path}: {str(e)}")
         return None
 
+
 def determine_type(file_path):
     if 'regex_patterns' in file_path:
         return 'Regex Pattern'
@@ -37,6 +40,7 @@ def determine_type(file_path):
         return 'Quality Profile'
     return 'Unknown'
 
+
 def interpret_git_status(x, y):
     if x == 'D' or y == 'D':
         return 'Deleted'
@@ -54,3 +58,89 @@ def interpret_git_status(x, y):
         return 'Untracked'
     else:
         return 'Unknown'
+
+
+def parse_commit_message(commit_message):
+    # Default placeholders for missing parts of the commit message
+    placeholders = {
+        'type': 'Unknown Type',
+        'scope': 'Unknown Scope',
+        'subject': 'No subject provided',
+        'body': 'No body provided',
+        'footer': 'No footer provided'
+    }
+
+    # Mapping of commit types and scopes to canonical forms
+    type_mapping = {
+        'feat': 'New Feature',
+        'feature': 'New Feature',
+        'new': 'New Feature',
+        'fix': 'BugFix',
+        'bugfix': 'BugFix',
+        'bug': 'BugFix',
+        'docs': 'Documentation',
+        'documentation': 'Documentation',
+        'doc': 'Documentation',
+        'style': 'Style Change',
+        'formatting': 'Style Change',
+        'format': 'Style Change',
+        'lint': 'Style Change',
+        'refactor': 'Refactor',
+        'refactoring': 'Refactor',
+        'restructure': 'Refactor',
+        'redesign': 'Refactor',
+        'perf': 'Performance Improvement',
+        'performance': 'Performance Improvement',
+        'optimize': 'Performance Improvement',
+        'optimisation': 'Performance Improvement',
+        'test': 'Test',
+        'testing': 'Test',
+        'chore': 'Maintenance',
+        'maintenance': 'Maintenance',
+        'maintain': 'Maintenance'
+    }
+
+    scope_mapping = {
+        'regex': 'Regex Pattern',
+        'regex pattern': 'Regex Pattern',
+        'format': 'Custom Format',
+        'custom format': 'Custom Format',
+        'profile': 'Quality Profile',
+        'quality profile': 'Quality Profile'
+    }
+
+    # Regex patterns for each part of the commit message
+    type_pattern = r'^(?P<type>feat|feature|new|fix|bugfix|bug|docs|documentation|doc|style|formatting|format|lint|refactor|refactoring|restructure|redesign|perf|performance|optimize|optimisation|test|testing|chore|maintenance|maintain)'
+    scope_pattern = r'\((?P<scope>regex|regex pattern|format|custom format|profile|quality profile)\)'
+    subject_pattern = r':\s(?P<subject>.+)'
+    body_pattern = r'(?P<body>(?:- .+\n?)+)'  # Handles multiple lines in the body
+    footer_pattern = r'(?P<footer>(Fixes|Resolves|See also|Relates to)\s.+)'
+
+    # Initialize result with placeholders
+    parsed_message = placeholders.copy()
+
+    # Parse the type and scope
+    type_scope_match = re.match(
+        f'{type_pattern}{scope_pattern}{subject_pattern}', commit_message,
+        re.IGNORECASE)
+    if type_scope_match:
+        matched_type = type_scope_match.group('type').lower()
+        matched_scope = type_scope_match.group('scope').lower()
+
+        # Map the matched values to their canonical forms
+        parsed_message['type'] = type_mapping.get(matched_type, 'Unknown Type')
+        parsed_message['scope'] = scope_mapping.get(matched_scope,
+                                                    'Unknown Scope')
+        parsed_message['subject'] = type_scope_match.group('subject').strip()
+
+    # Match and extract the body part
+    body_match = re.search(body_pattern, commit_message, re.MULTILINE)
+    if body_match:
+        parsed_message['body'] = body_match.group('body').strip()
+
+    # Match and extract the footer (if present)
+    footer_match = re.search(footer_pattern, commit_message)
+    if footer_match:
+        parsed_message['footer'] = footer_match.group('footer').strip()
+
+    return parsed_message

frontend/src/components/settings/git/ChangeRow.jsx

@@ -59,6 +59,7 @@ const ChangeRow = ({
 
     const handleViewDiff = e => {
         e.stopPropagation();
+        console.log('Change Object: ', JSON.stringify(change, null, 2));
         setShowDiff(true);
     };
 

frontend/src/components/settings/git/modal/DiffCommit.jsx

@@ -5,8 +5,7 @@ import {GitCommit} from 'lucide-react';
 const DiffCommit = ({commitMessage}) => {
     if (!commitMessage) return null;
 
-    const [firstLine, ...restLines] = commitMessage.split('\n');
-    const [commitType, commitSummary] = firstLine.split(': ');
+    const {type, scope, subject, body, footer} = commitMessage;
 
     return (
         <div className='bg-gray-100 dark:bg-gray-800 p-4 rounded-lg shadow-sm'>
@@ -21,15 +20,15 @@ const DiffCommit = ({commitMessage}) => {
                     </h4>
                     <div className='mb-2'>
                         <span className='inline-block px-2 py-1 rounded text-xs font-medium bg-blue-100 text-blue-800 dark:bg-blue-900 dark:text-blue-200 mr-2'>
-                            {commitType}
+                            {type}
                         </span>
                         <span className='text-sm font-semibold text-gray-700 dark:text-gray-300'>
-                            {commitSummary}
+                            {`${scope ? `(${scope})` : ''} ${subject}`}
                         </span>
                     </div>
-                    {restLines.length > 0 && (
+                    {body && (
                         <ul className='list-disc pl-5 space-y-1'>
-                            {restLines.map((line, index) => (
+                            {body.split('\n').map((line, index) => (
                                 <li
                                     key={index}
                                     className='text-sm text-gray-600 dark:text-gray-400'>
@@ -38,6 +37,11 @@ const DiffCommit = ({commitMessage}) => {
                             ))}
                         </ul>
                     )}
+                    {footer && (
+                        <div className='mt-2 text-sm text-gray-600 dark:text-gray-400'>
+                            {footer}
+                        </div>
+                    )}
                 </div>
             </div>
         </div>
@@ -45,7 +49,13 @@ const DiffCommit = ({commitMessage}) => {
 };
 
 DiffCommit.propTypes = {
-    commitMessage: PropTypes.string
+    commitMessage: PropTypes.shape({
+        type: PropTypes.string.isRequired,
+        scope: PropTypes.string,
+        subject: PropTypes.string.isRequired,
+        body: PropTypes.string,
+        footer: PropTypes.string
+    })
 };
 
 export default DiffCommit;

frontend/src/components/settings/git/modal/ViewDiff.jsx

@@ -77,7 +77,8 @@ const ViewDiff = ({
             title={titleContent}
             size='4xl'>
             <div className='space-y-4'>
-                <DiffCommit commitMessage={commitMessage} />
+                <DiffCommit commitMessage={commitMessage} />{' '}
+                {/* Passing the commitMessage object */}
                 <div className='border border-gray-300 dark:border-gray-600 rounded-lg overflow-hidden'>
                     <div className='bg-gray-50 dark:bg-gray-800 p-2 text-sm font-medium text-gray-600 dark:text-gray-300 border-b border-gray-300 dark:border-gray-600'>
                         Diff Content
@@ -103,7 +104,13 @@ ViewDiff.propTypes = {
     diffContent: PropTypes.string,
     type: PropTypes.string.isRequired,
     name: PropTypes.string.isRequired,
-    commitMessage: PropTypes.string,
+    commitMessage: PropTypes.shape({
+        type: PropTypes.string,
+        scope: PropTypes.string,
+        subject: PropTypes.string,
+        body: PropTypes.string,
+        footer: PropTypes.string
+    }),
     isIncoming: PropTypes.bool.isRequired
 };