Merge pull request #1061 from iorisa/feature/repo_to_markdown

feat: repo to markdown

metagpt/utils/common.py

@@ -18,6 +18,7 @@ import csv
 import importlib
 import inspect
 import json
+import mimetypes
 import os
 import platform
 import re
@@ -819,3 +820,21 @@ See FAQ 5.8
 """
     )
     raise retry_state.outcome.exception()
+
+
+def get_markdown_codeblock_type(filename: str) -> str:
+    """Return the markdown code-block type corresponding to the file extension."""
+    mime_type, _ = mimetypes.guess_type(filename)
+    mappings = {
+        "text/x-shellscript": "bash",
+        "text/x-c++src": "cpp",
+        "text/css": "css",
+        "text/html": "html",
+        "text/x-java": "java",
+        "application/javascript": "javascript",
+        "application/json": "json",
+        "text/x-python": "python",
+        "text/x-ruby": "ruby",
+        "application/sql": "sql",
+    }
+    return mappings.get(mime_type, "text")

metagpt/utils/repo_to_markdown.py

@@ -0,0 +1,80 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+This file provides functionality to convert a local repository into a markdown representation.
+"""
+from __future__ import annotations
+
+import mimetypes
+from pathlib import Path
+
+from gitignore_parser import parse_gitignore
+
+from metagpt.logs import logger
+from metagpt.utils.common import aread, awrite, get_markdown_codeblock_type, list_files
+from metagpt.utils.tree import tree
+
+
+async def repo_to_markdown(repo_path: str | Path, output: str | Path = None, gitignore: str | Path = None) -> str:
+    """
+    Convert a local repository into a markdown representation.
+
+    This function takes a path to a local repository and generates a markdown representation of the repository structure,
+    including directory trees and file listings.
+
+    Args:
+        repo_path (str | Path): The path to the local repository.
+        output (str | Path, optional): The path to save the generated markdown file. Defaults to None.
+        gitignore (str | Path, optional): The path to the .gitignore file. Defaults to None.
+
+    Returns:
+        str: The markdown representation of the repository.
+    """
+    repo_path = Path(repo_path)
+    gitignore = Path(gitignore or Path(__file__).parent / "../../.gitignore").resolve()
+
+    markdown = await _write_dir_tree(repo_path=repo_path, gitignore=gitignore)
+
+    gitignore_rules = parse_gitignore(full_path=str(gitignore))
+    markdown += await _write_files(repo_path=repo_path, gitignore_rules=gitignore_rules)
+
+    if output:
+        await awrite(filename=str(output), data=markdown, encoding="utf-8")
+    return markdown
+
+
+async def _write_dir_tree(repo_path: Path, gitignore: Path) -> str:
+    try:
+        content = tree(repo_path, gitignore, run_command=True)
+    except Exception as e:
+        logger.info(f"{e}, using safe mode.")
+        content = tree(repo_path, gitignore, run_command=False)
+
+    doc = f"## Directory Tree\n```text\n{content}\n```\n---\n\n"
+    return doc
+
+
+async def _write_files(repo_path, gitignore_rules) -> str:
+    filenames = list_files(repo_path)
+    markdown = ""
+    for filename in filenames:
+        if gitignore_rules(str(filename)):
+            continue
+        markdown += await _write_file(filename=filename, repo_path=repo_path)
+    return markdown
+
+
+async def _write_file(filename: Path, repo_path: Path) -> str:
+    relative_path = filename.relative_to(repo_path)
+    markdown = f"## {relative_path}\n"
+
+    mime_type, _ = mimetypes.guess_type(filename.name)
+    if "text/" not in mime_type:
+        logger.info(f"Ignore content: {filename}")
+        markdown += "<binary file>\n---\n\n"
+        return markdown
+    content = await aread(filename, encoding="utf-8")
+    content = content.replace("```", "\\`\\`\\`").replace("---", "\\-\\-\\-")
+    code_block_type = get_markdown_codeblock_type(filename.name)
+    markdown += f"```{code_block_type}\n{content}\n```\n---\n\n"
+    return markdown