tomd-cli 0.1.0__tar.gz

tomd_cli-0.1.0/.claude/settings.local.json

@@ -0,0 +1,30 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(pip3 show markitdown)",
+      "Bash(pip3 install markitdown)",
+      "Bash(pip3 install markitdown --break-system-packages)",
+      "Read(//usr/local/bin/**)",
+      "Bash(ln -sf /Users/nakamurakohki/workspace/private_dev/convert-md/convert_md.py /usr/local/bin/convert-md)",
+      "Bash(convert-md --help)",
+      "Bash(ln -sf /Users/nakamurakohki/workspace/private_dev/convert-md/convert_md.py /usr/local/bin/tomd)",
+      "Bash(tomd --help)",
+      "Bash(ln -sf /Users/nakamurakohki/workspace/private_dev/convert-md/tomd.py /usr/local/bin/tomd)",
+      "Bash(sudo ln -sf /Users/nakamurakohki/workspace/private_dev/tomd/tomd.py /usr/local/bin/tomd)",
+      "Bash(python3 /Users/nakamurakohki/workspace/private_dev/tomd/tomd.py \"バックオフィス業務システム化_提案資料.docx\" -o /tmp/test_output.md)",
+      "Read(//tmp/**)",
+      "Bash(python3 /Users/nakamurakohki/workspace/private_dev/tomd/tomd.py \"/Users/nakamurakohki/Downloads/バックオフィス業務システム化_提案資料.docx\" -o /tmp/test_output2.md)",
+      "Bash(pip3 index:*)",
+      "Bash(pip3 install:*)",
+      "Bash(for name:*)",
+      "Bash(do echo:*)",
+      "WebFetch(domain:pypi.org)",
+      "Bash(python3 -m pytest tests/ -v)",
+      "Read(//Users/nakamurakohki/**)",
+      "Bash(python3 -m build)"
+    ],
+    "additionalDirectories": [
+      "/Users/nakamurakohki/workspace/private_dev/tomd/src"
+    ]
+  }
+}

tomd_cli-0.1.0/.gitignore

@@ -0,0 +1,26 @@
+# Python
+__pycache__/
+*.py[cod]
+*.egg-info/
+*.egg
+dist/
+build/
+
+# Virtual environments
+.venv/
+venv/
+
+# Environment variables
+.env
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+
+# IDE
+.vscode/
+.idea/
+
+# OS
+.DS_Store

tomd_cli-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Kohki Nakamura
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

tomd_cli-0.1.0/PKG-INFO

@@ -0,0 +1,78 @@
+Metadata-Version: 2.4
+Name: tomd-cli
+Version: 0.1.0
+Summary: Convert Office files (.docx, .pptx, .xlsx, .pdf) to Markdown using MarkItDown
+Project-URL: Homepage, https://github.com/nakamurakohki/tomd-cli
+Project-URL: Repository, https://github.com/nakamurakohki/tomd-cli
+Project-URL: Issues, https://github.com/nakamurakohki/tomd-cli/issues
+Author: Kohki Nakamura
+License-Expression: MIT
+License-File: LICENSE
+Keywords: converter,docx,markdown,pdf,pptx,xlsx
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: MacOS
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Text Processing :: Markup :: Markdown
+Requires-Python: >=3.10
+Requires-Dist: markitdown>=0.0.2
+Description-Content-Type: text/markdown
+
+# tomd-cli
+
+Convert Office files to Markdown using [MarkItDown](https://github.com/microsoft/markitdown).
+
+## Supported formats
+
+- `.docx` (Word)
+- `.pptx` (PowerPoint)
+- `.xlsx` (Excel)
+- `.pdf`
+
+## Installation
+
+```bash
+pip install tomd-cli
+```
+
+## Usage
+
+### CLI
+
+```bash
+# Convert a single file
+tomd document.docx
+
+# Specify output path
+tomd document.docx -o output.md
+
+# Convert all files in a directory
+tomd --dir ./documents/
+
+# Convert directory with custom output
+tomd --dir ./documents/ -o ./markdown/
+```
+
+### Python API
+
+```python
+from tomd import convert_file, convert_dir
+
+# Single file
+output_path = convert_file("document.docx")
+output_path = convert_file("document.docx", "output.md")
+
+# Directory
+output_paths = convert_dir("./documents/")
+output_paths = convert_dir("./documents/", "./markdown/")
+```
+
+## License
+
+MIT

tomd_cli-0.1.0/README.md

@@ -0,0 +1,52 @@
+# tomd-cli
+
+Convert Office files to Markdown using [MarkItDown](https://github.com/microsoft/markitdown).
+
+## Supported formats
+
+- `.docx` (Word)
+- `.pptx` (PowerPoint)
+- `.xlsx` (Excel)
+- `.pdf`
+
+## Installation
+
+```bash
+pip install tomd-cli
+```
+
+## Usage
+
+### CLI
+
+```bash
+# Convert a single file
+tomd document.docx
+
+# Specify output path
+tomd document.docx -o output.md
+
+# Convert all files in a directory
+tomd --dir ./documents/
+
+# Convert directory with custom output
+tomd --dir ./documents/ -o ./markdown/
+```
+
+### Python API
+
+```python
+from tomd import convert_file, convert_dir
+
+# Single file
+output_path = convert_file("document.docx")
+output_path = convert_file("document.docx", "output.md")
+
+# Directory
+output_paths = convert_dir("./documents/")
+output_paths = convert_dir("./documents/", "./markdown/")
+```
+
+## License
+
+MIT

tomd_cli-0.1.0/draft.md

@@ -0,0 +1,135 @@
+はい、**MarkItDown**というMicrosoft製のPythonライブラリがまさにそれです。 [note](https://note.com/kiyo_ai_note/n/n351a9018e99b)
+
+完全にローカルPCで動作し、一括変換も可能です。以下に具体的なセットアップとコードを示します。
+
+## MarkItDown ライブラリのインストールと確認
+
+```bash
+pip install markitdown
+```
+
+これでPPTX、DOCX、XLSX、PDFなど多様な形式が一括でMarkdownに変換できます。 [okumuralab](https://okumuralab.org/~okumura/python/markitdown.html)
+
+## 単一ファイル変換（最もシンプル）
+
+```python
+from markitdown import MarkItDown
+
+# インスタンス作成
+md = MarkItDown()
+
+# PPTXをMarkdownに変換
+result = md.convert("presentation.pptx")
+
+# Markdownファイルとして保存
+with open("presentation.md", "w", encoding="utf-8") as f:
+    f.write(result.text_content)
+
+print("変換完了: presentation.md")
+```
+
+出力例（スライドが適切に`<!-- Slide number: 1 -->`形式で区切られる） [note](https://note.com/kiyo_ai_note/n/n351a9018e99b)
+```
+<!-- Slide number: 1 -->
+# オープンデータに取り組む地方公共団体数の推移
+- 2020年: 100団体
+- 2021年: 150団体
+```
+
+## フォルダ内全PPTX一括変換（実務向け）
+
+```python
+import glob
+import os
+from pathlib import Path
+from markitdown import MarkItDown
+
+def batch_convert_pptx(input_folder="input", output_folder="output"):
+    # 出力フォルダ作成
+    os.makedirs(output_folder, exist_ok=True)
+    
+    md = MarkItDown()
+    
+    # inputフォルダ内の全PPTXを処理
+    pptx_files = glob.glob(f"{input_folder}/*.pptx")
+    
+    for pptx_path in pptx_files:
+        print(f"変換中: {pptx_path}")
+        
+        result = md.convert(pptx_path)
+        
+        # ファイル名から拡張子を除いて.md生成
+        base_name = Path(pptx_path).stem
+        md_path = f"{output_folder}/{base_name}.md"
+        
+        with open(md_path, "w", encoding="utf-8") as f:
+            f.write(result.text_content)
+        
+        print(f"完了: {md_path}")
+
+# 実行
+batch_convert_pptx()
+```
+
+## ディレクトリ構造例
+```
+project/
+├── input/          # PPTXファイルをここに放り込む
+│   ├── slide1.pptx
+│   └── slide2.pptx
+├── output/         # 自動でMarkdown生成
+│   ├── slide1.md
+│   └── slide2.md
+└── convert.py
+```
+
+## VSCode + ターミナルでワンクリック運用
+
+1. 上記スクリプトを`convert.py`として保存
+2. VSCodeで作業フォルダを開く
+3. `Ctrl+`` `でターミナルを開く
+4. `python convert.py`で一括変換
+
+## 高度な使い方（Azure OpenAI連携）
+
+画像内の文字や複雑なレイアウトも読み取りたい場合：
+
+```python
+from openai import OpenAI
+from markitdown import MarkItDown
+
+# Azure OpenAIクライアント
+client = OpenAI(
+    api_key="your-azure-openai-key",
+    azure_endpoint="your-endpoint"
+)
+
+# LLM強化版MarkItDown
+md = MarkItDown(
+    llm_client=client, 
+    llm_model="gpt-4o"
+)
+
+result = md.convert("complex-slides.pptx")
+```
+
+## 注意点と精度向上のコツ
+
+1. **スライドデザインをシンプルに**  
+   - テキストはテキストボックス内に  
+   - 画像に文字を埋め込まない
+
+2. **出力確認と微調整**  
+   ```python
+   # 変換前にプレビュー
+   print(result.text_content[:1000])  # 最初の1000文字確認
+   ```
+
+3. **大容量ファイル対応**  
+   ```python
+   md = MarkItDown(max_memory_mb=2048)  # メモリ使用量指定
+   ```
+
+この方法なら、**ローカル完結・一括変換・高精度**の3点を満たします。 [zenn](https://zenn.dev/acntechjp/articles/e794ed9d524812)
+
+中村さんのAzure/Python環境なら、すぐに運用開始できそうですね。試してみたい具体的なユースケースがあれば、さらにカスタマイズしたスクリプトも作れます！

tomd_cli-0.1.0/pyproject.toml

@@ -0,0 +1,45 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "tomd-cli"
+version = "0.1.0"
+description = "Convert Office files (.docx, .pptx, .xlsx, .pdf) to Markdown using MarkItDown"
+readme = "README.md"
+license = "MIT"
+requires-python = ">=3.10"
+authors = [
+    { name = "Kohki Nakamura" },
+]
+keywords = ["markdown", "docx", "pptx", "xlsx", "pdf", "converter"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Environment :: Console",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: MacOS",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Text Processing :: Markup :: Markdown",
+]
+dependencies = [
+    "markitdown>=0.0.2",
+]
+
+[project.scripts]
+tomd = "tomd.cli:main"
+
+[project.urls]
+Homepage = "https://github.com/nakamurakohki/tomd-cli"
+Repository = "https://github.com/nakamurakohki/tomd-cli"
+Issues = "https://github.com/nakamurakohki/tomd-cli/issues"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/tomd"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

tomd_cli-0.1.0/src/tomd/__init__.py

@@ -0,0 +1,5 @@
+"""tomd-cli: Convert Office files to Markdown using MarkItDown."""
+
+from tomd.converter import convert_file, convert_dir, strip_base64_images
+
+__all__ = ["convert_file", "convert_dir", "strip_base64_images"]

tomd_cli-0.1.0/src/tomd/cli.py

@@ -0,0 +1,55 @@
+"""Command-line interface for tomd."""
+
+from __future__ import annotations
+
+import argparse
+import sys
+
+from tomd.converter import SUPPORTED_EXTENSIONS, convert_dir, convert_file
+
+
+def _build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        prog="tomd",
+        description="Convert Office files to Markdown using MarkItDown.",
+    )
+    parser.add_argument(
+        "input",
+        help="file or directory to convert",
+    )
+    parser.add_argument(
+        "-o", "--output",
+        help="output file or directory path",
+    )
+    parser.add_argument(
+        "--dir",
+        action="store_true",
+        dest="is_dir",
+        help="treat input as a directory and convert all supported files",
+    )
+    fmt = ", ".join(sorted(SUPPORTED_EXTENSIONS))
+    parser.epilog = f"Supported formats: {fmt}"
+    return parser
+
+
+def main(argv: list[str] | None = None) -> None:
+    parser = _build_parser()
+    args = parser.parse_args(argv)
+
+    try:
+        if args.is_dir:
+            results = convert_dir(args.input, args.output)
+            if not results:
+                print(f"No convertible files found in {args.input}")
+            else:
+                for dest in results:
+                    print(f"Converted: {dest}")
+        else:
+            dest = convert_file(args.input, args.output)
+            print(f"Converted: {dest}")
+    except (FileNotFoundError, NotADirectoryError) as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(1)
+    except Exception as e:
+        print(f"Conversion failed: {e}", file=sys.stderr)
+        sys.exit(1)

tomd_cli-0.1.0/src/tomd/converter.py

@@ -0,0 +1,76 @@
+"""Core conversion logic."""
+
+from __future__ import annotations
+
+import re
+from pathlib import Path
+
+from markitdown import MarkItDown
+
+SUPPORTED_EXTENSIONS = {".pptx", ".docx", ".xlsx", ".pdf"}
+
+
+def strip_base64_images(text: str) -> str:
+    """Replace embedded base64 image data with a placeholder."""
+    return re.sub(
+        r'!\[([^\]]*)\]\(data:image/[^)]+\)',
+        lambda m: f'![{m.group(1)}]()',
+        text,
+    )
+
+
+def convert_file(
+    input_path: str | Path,
+    output_path: str | Path | None = None,
+) -> Path:
+    """Convert a single file to Markdown.
+
+    Returns the path to the generated Markdown file.
+    Raises FileNotFoundError if input does not exist.
+    """
+    src = Path(input_path).resolve()
+    if not src.is_file():
+        raise FileNotFoundError(f"File not found: {input_path}")
+
+    dest = Path(output_path).resolve() if output_path else src.with_suffix(".md")
+
+    md = MarkItDown()
+    result = md.convert(str(src))
+    content = strip_base64_images(result.text_content)
+
+    dest.parent.mkdir(parents=True, exist_ok=True)
+    dest.write_text(content, encoding="utf-8")
+    return dest
+
+
+def convert_dir(
+    input_dir: str | Path,
+    output_dir: str | Path | None = None,
+) -> list[Path]:
+    """Convert all supported files in a directory to Markdown.
+
+    Returns a list of generated Markdown file paths.
+    Raises NotADirectoryError if input is not a directory.
+    """
+    src_dir = Path(input_dir).resolve()
+    if not src_dir.is_dir():
+        raise NotADirectoryError(f"Directory not found: {input_dir}")
+
+    dest_dir = Path(output_dir).resolve() if output_dir else src_dir / "output"
+    dest_dir.mkdir(parents=True, exist_ok=True)
+
+    files = sorted(
+        f for f in src_dir.iterdir() if f.suffix.lower() in SUPPORTED_EXTENSIONS
+    )
+    if not files:
+        return []
+
+    md = MarkItDown()
+    results: list[Path] = []
+    for f in files:
+        dest = dest_dir / f.with_suffix(".md").name
+        result = md.convert(str(f))
+        dest.write_text(strip_base64_images(result.text_content), encoding="utf-8")
+        results.append(dest)
+
+    return results

tomd_cli-0.1.0/tests/test_cli.py

@@ -0,0 +1,28 @@
+"""Tests for tomd.cli."""
+
+import pytest
+from tomd.cli import main
+
+
+def test_help_flag(capsys):
+    with pytest.raises(SystemExit) as exc_info:
+        main(["--help"])
+    assert exc_info.value.code == 0
+    captured = capsys.readouterr()
+    assert "Convert Office files" in captured.out
+
+
+def test_missing_file(capsys):
+    with pytest.raises(SystemExit) as exc_info:
+        main(["nonexistent.docx"])
+    assert exc_info.value.code == 1
+    captured = capsys.readouterr()
+    assert "Error" in captured.err
+
+
+def test_missing_dir(capsys):
+    with pytest.raises(SystemExit) as exc_info:
+        main(["--dir", "nonexistent_dir"])
+    assert exc_info.value.code == 1
+    captured = capsys.readouterr()
+    assert "Error" in captured.err

tomd_cli-0.1.0/tests/test_converter.py

@@ -0,0 +1,39 @@
+"""Tests for tomd.converter."""
+
+import pytest
+from tomd.converter import strip_base64_images
+
+
+class TestStripBase64Images:
+    def test_replaces_base64_png(self):
+        text = '![alt text](data:image/png;base64,iVBORw0KGgoAAAANSUhEUg==)'
+        result = strip_base64_images(text)
+        assert result == '![alt text]()'
+
+    def test_replaces_base64_jpeg(self):
+        text = '![photo](data:image/jpeg;base64,/9j/4AAQSkZJRg==)'
+        result = strip_base64_images(text)
+        assert result == '![photo]()'
+
+    def test_preserves_empty_alt(self):
+        text = '![](data:image/png;base64,abc123)'
+        result = strip_base64_images(text)
+        assert result == '![]()'
+
+    def test_preserves_normal_images(self):
+        text = '![alt](https://example.com/image.png)'
+        result = strip_base64_images(text)
+        assert result == '![alt](https://example.com/image.png)'
+
+    def test_preserves_plain_text(self):
+        text = 'Hello world'
+        result = strip_base64_images(text)
+        assert result == 'Hello world'
+
+    def test_multiple_images(self):
+        text = (
+            '![a](data:image/png;base64,AAA) middle '
+            '![b](data:image/gif;base64,BBB)'
+        )
+        result = strip_base64_images(text)
+        assert result == '![a]() middle ![b]()'