zerofancy/git_line_analyzer.py

## git_line_analyzer.py
#!/usr/bin/env python3
"""
Git Line Analyzer

This script analyzes all git-tracked text files in the current repository,
counts lines in each file, performs git blame to attribute lines to users,
and generates an HTML report with aggregated statistics.
"""

import os
import sys
import subprocess
import re
from collections import defaultdict
from pathlib import Path
import webbrowser
from datetime import datetime


def get_tracked_text_files():
    """Get a list of all git-tracked text files in the repository."""
    try:
        # Get all tracked files
        result = subprocess.run(['git', 'ls-files'], capture_output=True, text=True, check=True)
        all_files = result.stdout.strip().split('\n')

        # Filter for text files (simple heuristic: check file extension or use file command)
        text_extensions = {'.txt', '.md', '.markdown', '.rst', '.py', '.js', '.ts', '.jsx', '.tsx',
                          '.java', '.cpp', '.c', '.h', '.hpp', '.cs', '.rb', '.go', '.rs', '.kt',
                          '.scala', '.php', '.html', '.htm', '.css', '.scss', '.sass', '.json',
                          '.yaml', '.yml', '.xml', '.sql', '.sh', '.bash', '.zsh', '.pl', '.pm',
                          '.lua', '.r', '.dart', '.swift', '.m', '.mm', '.groovy', '.gradle',
                          '.toml', '.ini', '.cfg', '.conf', '.properties', '.env', '.dockerfile',
                          '.gitignore', '.gitattributes', '.editorconfig', '.lock'}

        text_files = []
        for file_path in all_files:
            if not file_path:
                continue

            # Check if it's a text file by extension or by checking if it's not binary
            path_obj = Path(file_path)
            if path_obj.suffix.lower() in text_extensions:
                text_files.append(file_path)
            elif path_obj.is_file():
                # Additional check: try to determine if it's a text file
                try:
                    with open(path_obj, 'r', encoding='utf-8') as f:
                        f.read(1024)  # Try to read first 1KB as text
                    text_files.append(file_path)
                except UnicodeDecodeError:
                    # Likely a binary file, skip it
                    continue

        return text_files
    except subprocess.CalledProcessError:
        print("Error: Not in a git repository or git command failed.")
        sys.exit(1)


def count_lines_in_file(file_path):
    """Count the total number of lines in a file."""
    try:
        with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
            lines = f.readlines()
        return len(lines)
    except Exception:
        return 0


def get_git_blame_stats(file_path):
    """Perform git blame on a file and return user line counts."""
    try:
        result = subprocess.run(
            ['git', 'blame', '--line-porcelain', file_path],
            capture_output=True, text=True, check=True
        )

        # Parse the git blame output to count lines per author
        authors = defaultdict(int)
        current_author = None

        for line in result.stdout.splitlines():
            if line.startswith('author '):
                current_author = line[7:]  # Remove 'author ' prefix
            elif line.startswith('\t'):  # Actual code line
                if current_author:
                    authors[current_author] += 1
                current_author = None

        return dict(authors)
    except subprocess.CalledProcessError:
        # If git blame fails, return empty dict
        return {}


def generate_html_report(results, output_file):
    """Generate an HTML report with the analysis results."""
    html_template = """
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>Git Line Analysis Report</title>
    <style>
        body {{
            font-family: Arial, sans-serif;
            margin: 20px;
            background-color: #f5f5f5;
        }}
        .container {{
            max-width: 1200px;
            margin: 0 auto;
            background-color: white;
            padding: 20px;
            border-radius: 8px;
            box-shadow: 0 2px 10px rgba(0,0,0,0.1);
        }}
        h1 {{
            color: #333;
            text-align: center;
            border-bottom: 2px solid #4CAF50;
            padding-bottom: 10px;
        }}
        .summary {{
            background-color: #e9f7ef;
            padding: 15px;
            border-radius: 5px;
            margin-bottom: 20px;
        }}
        table {{
            width: 100%;
            border-collapse: collapse;
            margin-bottom: 20px;
        }}
        th, td {{
            border: 1px solid #ddd;
            padding: 12px;
            text-align: left;
        }}
        th {{
            background-color: #4CAF50;
            color: white;
        }}
        tr:nth-child(even) {{
            background-color: #f2f2f2;
        }}
        .file-details {{
            margin-top: 20px;
        }}
        .file-header {{
            background-color: #2196F3;
            color: white;
            padding: 10px;
            margin-top: 15px;
            border-radius: 5px;
        }}
        .author-stats {{
            margin-left: 20px;
        }}
        .total-lines {{
            font-weight: bold;
            color: #4CAF50;
        }}
        .timestamp {{
            color: #666;
            font-size: 0.9em;
        }}
    </style>
</head>
<body>
    <div class="container">
        <h1>Git Line Analysis Report</h1>
        <p class="timestamp">Generated on: {timestamp}</p>

        <div class="summary">
            <h2>Summary</h2>
            <p>Total files analyzed: <strong>{total_files}</strong></p>
            <p>Total lines across all files: <strong>{total_lines}</strong></p>
            <p>Total unique contributors: <strong>{unique_contributors}</strong></p>
        </div>

        <h2>Detailed Analysis</h2>
        <table>
            <thead>
                <tr>
                    <th>File Path</th>
                    <th>Total Lines</th>
                    <th>Contributors Count</th>
                </tr>
            </thead>
            <tbody>
                {file_rows}
            </tbody>
        </table>

        <h2>Contributor Statistics</h2>
        <table>
            <thead>
                <tr>
                    <th>Contributor</th>
                    <th>Total Lines Contributed</th>
                    <th>Percentage</th>
                </tr>
            </thead>
            <tbody>
                {contributor_rows}
            </tbody>
        </table>

        <div class="file-details">
            <h2>Per-File Contributor Details</h2>
            {detailed_sections}
        </div>
    </div>
</body>
</html>
    """

    # Calculate totals
    total_files = len(results)
    total_lines = sum(r['total_lines'] for r in results.values())

    # Aggregate contributor stats
    contributor_totals = defaultdict(int)
    for file_data in results.values():
        for author, line_count in file_data['authors'].items():
            contributor_totals[author] += line_count

    unique_contributors = len(contributor_totals)

    # Generate file rows for the summary table
    file_rows = ""
    for file_path, data in results.items():
        file_rows += f"""
                <tr>
                    <td><code>{file_path}</code></td>
                    <td class="total-lines">{data['total_lines']}</td>
                    <td>{len(data['authors'])}</td>
                </tr>
        """

    # Generate contributor rows for the contributor table
    contributor_rows = ""
    sorted_contributors = sorted(contributor_totals.items(), key=lambda x: x[1], reverse=True)
    for author, line_count in sorted_contributors:
        percentage = (line_count / total_lines * 100) if total_lines > 0 else 0
        contributor_rows += f"""
                <tr>
                    <td>{author}</td>
                    <td>{line_count}</td>
                    <td>{percentage:.2f}%</td>
                </tr>
        """

    # Generate detailed sections for each file
    detailed_sections = ""
    for file_path, data in results.items():
        detailed_sections += f"""
            <div class="file-header">
                <strong>File:</strong> {file_path} | <strong>Total Lines:</strong> {data['total_lines']}
            </div>
            <div class="author-stats">
                <table>
                    <thead>
                        <tr>
                            <th>Author</th>
                            <th>Lines</th>
                            <th>Percentage</th>
                        </tr>
                    </thead>
                    <tbody>
        """

        for author, line_count in sorted(data['authors'].items(), key=lambda x: x[1], reverse=True):
            percentage = (line_count / data['total_lines'] * 100) if data['total_lines'] > 0 else 0
            detailed_sections += f"""
                        <tr>
                            <td>{author}</td>
                            <td>{line_count}</td>
                            <td>{percentage:.2f}%</td>
                        </tr>
            """

        detailed_sections += """
                    </tbody>
                </table>
            </div>
        """

    # Format the HTML
    html_content = html_template.format(
        timestamp=datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
        total_files=total_files,
        total_lines=total_lines,
        unique_contributors=unique_contributors,
        file_rows=file_rows,
        contributor_rows=contributor_rows,
        detailed_sections=detailed_sections
    )

    # Write the HTML to file
    with open(output_file, 'w', encoding='utf-8') as f:
        f.write(html_content)


def main():
    """Main function to run the analysis."""
    print("Starting git line analysis...")

    # Get all tracked text files
    text_files = get_tracked_text_files()
    print(f"Found {len(text_files)} git-tracked text files to analyze.\n")

    # Initialize results dictionary
    results = {}

    # Process each file
    for i, file_path in enumerate(text_files, 1):
        print(f"[{i}/{len(text_files)}] Processing: {file_path}")

        # Count lines in file
        total_lines = count_lines_in_file(file_path)

        # Get git blame stats
        authors = get_git_blame_stats(file_path)

        # Store results
        results[file_path] = {
            'total_lines': total_lines,
            'authors': authors
        }

        print(f"  - Total lines: {total_lines}")
        print(f"  - Contributors: {len(authors)}")
        if authors:
            top_contributor = max(authors.items(), key=lambda x: x[1])
            print(f"  - Top contributor: {top_contributor[0]} ({top_contributor[1]} lines)")
        print()

    # Generate HTML report
    output_file = "git_line_analysis_report.html"
    generate_html_report(results, output_file)

    print(f"Analysis complete!")
    print(f"HTML report generated: {os.path.abspath(output_file)}")

    # Open the report in the default browser
    try:
        webbrowser.open(f'file://{os.path.abspath(output_file)}')
        print("Report opened in default browser.")
    except Exception as e:
        print(f"Could not open browser automatically: {e}")
        print("Please open the report manually.")


if __name__ == "__main__":
    main()

## prompt
帮我实现一段python脚本，对于当前仓库下所有文本文件，如果该文件被git跟踪：

统计该文件行数
对该文件执行git blame，统计当前版本每个用户的行数
对每一个文件实施上述操作，并在控制台持续更新结果
汇总统计结果，生成一个html格式的报表，把该文件的地址输出到控制台
自动打开生成的报表文件
	#!/usr/bin/env python3
	"""
	Git Line Analyzer

	This script analyzes all git-tracked text files in the current repository,
	counts lines in each file, performs git blame to attribute lines to users,
	and generates an HTML report with aggregated statistics.
	"""

	import os
	import sys
	import subprocess
	import re
	from collections import defaultdict
	from pathlib import Path
	import webbrowser
	from datetime import datetime


	def get_tracked_text_files():
	"""Get a list of all git-tracked text files in the repository."""
	try:
	# Get all tracked files
	result = subprocess.run(['git', 'ls-files'], capture_output=True, text=True, check=True)
	all_files = result.stdout.strip().split('\n')

	# Filter for text files (simple heuristic: check file extension or use file command)
	text_extensions = {'.txt', '.md', '.markdown', '.rst', '.py', '.js', '.ts', '.jsx', '.tsx',
	'.java', '.cpp', '.c', '.h', '.hpp', '.cs', '.rb', '.go', '.rs', '.kt',
	'.scala', '.php', '.html', '.htm', '.css', '.scss', '.sass', '.json',
	'.yaml', '.yml', '.xml', '.sql', '.sh', '.bash', '.zsh', '.pl', '.pm',
	'.lua', '.r', '.dart', '.swift', '.m', '.mm', '.groovy', '.gradle',
	'.toml', '.ini', '.cfg', '.conf', '.properties', '.env', '.dockerfile',
	'.gitignore', '.gitattributes', '.editorconfig', '.lock'}

	text_files = []
	for file_path in all_files:
	if not file_path:
	continue

	# Check if it's a text file by extension or by checking if it's not binary
	path_obj = Path(file_path)
	if path_obj.suffix.lower() in text_extensions:
	text_files.append(file_path)
	elif path_obj.is_file():
	# Additional check: try to determine if it's a text file
	try:
	with open(path_obj, 'r', encoding='utf-8') as f:
	f.read(1024) # Try to read first 1KB as text
	text_files.append(file_path)
	except UnicodeDecodeError:
	# Likely a binary file, skip it
	continue

	return text_files
	except subprocess.CalledProcessError:
	print("Error: Not in a git repository or git command failed.")
	sys.exit(1)


	def count_lines_in_file(file_path):
	"""Count the total number of lines in a file."""
	try:
	with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
	lines = f.readlines()
	return len(lines)
	except Exception:
	return 0


	def get_git_blame_stats(file_path):
	"""Perform git blame on a file and return user line counts."""
	try:
	result = subprocess.run(
	['git', 'blame', '--line-porcelain', file_path],
	capture_output=True, text=True, check=True
	)

	# Parse the git blame output to count lines per author
	authors = defaultdict(int)
	current_author = None

	for line in result.stdout.splitlines():
	if line.startswith('author '):
	current_author = line[7:] # Remove 'author ' prefix
	elif line.startswith('\t'): # Actual code line
	if current_author:
	authors[current_author] += 1
	current_author = None

	return dict(authors)
	except subprocess.CalledProcessError:
	# If git blame fails, return empty dict
	return {}


	def generate_html_report(results, output_file):
	"""Generate an HTML report with the analysis results."""
	html_template = """
	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="UTF-8">
	<meta name="viewport" content="width=device-width, initial-scale=1.0">
	<title>Git Line Analysis Report</title>
	<style>
	body {{
	font-family: Arial, sans-serif;
	margin: 20px;
	background-color: #f5f5f5;
	}}
	.container {{
	max-width: 1200px;
	margin: 0 auto;
	background-color: white;
	padding: 20px;
	border-radius: 8px;
	box-shadow: 0 2px 10px rgba(0,0,0,0.1);
	}}
	h1 {{
	color: #333;
	text-align: center;
	border-bottom: 2px solid #4CAF50;
	padding-bottom: 10px;
	}}
	.summary {{
	background-color: #e9f7ef;
	padding: 15px;
	border-radius: 5px;
	margin-bottom: 20px;
	}}
	table {{
	width: 100%;
	border-collapse: collapse;
	margin-bottom: 20px;
	}}
	th, td {{
	border: 1px solid #ddd;
	padding: 12px;
	text-align: left;
	}}
	th {{
	background-color: #4CAF50;
	color: white;
	}}
	tr:nth-child(even) {{
	background-color: #f2f2f2;
	}}
	.file-details {{
	margin-top: 20px;
	}}
	.file-header {{
	background-color: #2196F3;
	color: white;
	padding: 10px;
	margin-top: 15px;
	border-radius: 5px;
	}}
	.author-stats {{
	margin-left: 20px;
	}}
	.total-lines {{
	font-weight: bold;
	color: #4CAF50;
	}}
	.timestamp {{
	color: #666;
	font-size: 0.9em;
	}}
	</style>
	</head>
	<body>
	<div class="container">
	<h1>Git Line Analysis Report</h1>
	<p class="timestamp">Generated on: {timestamp}</p>

	<div class="summary">
	<h2>Summary</h2>
	<p>Total files analyzed: <strong>{total_files}</strong></p>
	<p>Total lines across all files: <strong>{total_lines}</strong></p>
	<p>Total unique contributors: <strong>{unique_contributors}</strong></p>
	</div>

	<h2>Detailed Analysis</h2>
	<table>
	<thead>
	<tr>
	<th>File Path</th>
	<th>Total Lines</th>
	<th>Contributors Count</th>
	</tr>
	</thead>
	<tbody>
	{file_rows}
	</tbody>
	</table>

	<h2>Contributor Statistics</h2>
	<table>
	<thead>
	<tr>
	<th>Contributor</th>
	<th>Total Lines Contributed</th>
	<th>Percentage</th>
	</tr>
	</thead>
	<tbody>
	{contributor_rows}
	</tbody>
	</table>

	<div class="file-details">
	<h2>Per-File Contributor Details</h2>
	{detailed_sections}
	</div>
	</div>
	</body>
	</html>
	"""

	# Calculate totals
	total_files = len(results)
	total_lines = sum(r['total_lines'] for r in results.values())

	# Aggregate contributor stats
	contributor_totals = defaultdict(int)
	for file_data in results.values():
	for author, line_count in file_data['authors'].items():
	contributor_totals[author] += line_count

	unique_contributors = len(contributor_totals)

	# Generate file rows for the summary table
	file_rows = ""
	for file_path, data in results.items():
	file_rows += f"""
	<tr>
	<td><code>{file_path}</code></td>
	<td class="total-lines">{data['total_lines']}</td>
	<td>{len(data['authors'])}</td>
	</tr>
	"""

	# Generate contributor rows for the contributor table
	contributor_rows = ""
	sorted_contributors = sorted(contributor_totals.items(), key=lambda x: x[1], reverse=True)
	for author, line_count in sorted_contributors:
	percentage = (line_count / total_lines * 100) if total_lines > 0 else 0
	contributor_rows += f"""
	<tr>
	<td>{author}</td>
	<td>{line_count}</td>
	<td>{percentage:.2f}%</td>
	</tr>
	"""

	# Generate detailed sections for each file
	detailed_sections = ""
	for file_path, data in results.items():
	detailed_sections += f"""
	<div class="file-header">
	<strong>File:</strong> {file_path} \| <strong>Total Lines:</strong> {data['total_lines']}
	</div>
	<div class="author-stats">
	<table>
	<thead>
	<tr>
	<th>Author</th>
	<th>Lines</th>
	<th>Percentage</th>
	</tr>
	</thead>
	<tbody>
	"""

	for author, line_count in sorted(data['authors'].items(), key=lambda x: x[1], reverse=True):
	percentage = (line_count / data['total_lines'] * 100) if data['total_lines'] > 0 else 0
	detailed_sections += f"""
	<tr>
	<td>{author}</td>
	<td>{line_count}</td>
	<td>{percentage:.2f}%</td>
	</tr>
	"""

	detailed_sections += """
	</tbody>
	</table>
	</div>
	"""

	# Format the HTML
	html_content = html_template.format(
	timestamp=datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
	total_files=total_files,
	total_lines=total_lines,
	unique_contributors=unique_contributors,
	file_rows=file_rows,
	contributor_rows=contributor_rows,
	detailed_sections=detailed_sections
	)

	# Write the HTML to file
	with open(output_file, 'w', encoding='utf-8') as f:
	f.write(html_content)


	def main():
	"""Main function to run the analysis."""
	print("Starting git line analysis...")

	# Get all tracked text files
	text_files = get_tracked_text_files()
	print(f"Found {len(text_files)} git-tracked text files to analyze.\n")

	# Initialize results dictionary
	results = {}

	# Process each file
	for i, file_path in enumerate(text_files, 1):
	print(f"[{i}/{len(text_files)}] Processing: {file_path}")

	# Count lines in file
	total_lines = count_lines_in_file(file_path)

	# Get git blame stats
	authors = get_git_blame_stats(file_path)

	# Store results
	results[file_path] = {
	'total_lines': total_lines,
	'authors': authors
	}

	print(f" - Total lines: {total_lines}")
	print(f" - Contributors: {len(authors)}")
	if authors:
	top_contributor = max(authors.items(), key=lambda x: x[1])
	print(f" - Top contributor: {top_contributor[0]} ({top_contributor[1]} lines)")
	print()

	# Generate HTML report
	output_file = "git_line_analysis_report.html"
	generate_html_report(results, output_file)

	print(f"Analysis complete!")
	print(f"HTML report generated: {os.path.abspath(output_file)}")

	# Open the report in the default browser
	try:
	webbrowser.open(f'file://{os.path.abspath(output_file)}')
	print("Report opened in default browser.")
	except Exception as e:
	print(f"Could not open browser automatically: {e}")
	print("Please open the report manually.")


	if __name__ == "__main__":
	main()
	帮我实现一段python脚本，对于当前仓库下所有文本文件，如果该文件被git跟踪：

	统计该文件行数
	对该文件执行git blame，统计当前版本每个用户的行数
	对每一个文件实施上述操作，并在控制台持续更新结果
	汇总统计结果，生成一个html格式的报表，把该文件的地址输出到控制台
	自动打开生成的报表文件