pdf-to-markdown-cli 0.2.0__py3-none-any.whl

docs_to_md/utils/logging.py

@@ -0,0 +1,134 @@
+import logging
+import sys
+from typing import Optional
+
+# Keep tqdm import at top level
+from tqdm import tqdm
+
+def setup_logging(level: int = logging.INFO, log_file: Optional[str] = None) -> logging.Logger:
+    """
+    Set up standardized logging configuration.
+    
+    Args:
+        level: Logging level (default: INFO)
+        log_file: Optional file path to write logs to
+        
+    Returns:
+        Logger instance for the application.
+    """
+    # Create formatter
+    formatter = logging.Formatter(
+        fmt="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
+        datefmt="%Y-%m-%d %H:%M:%S"
+    )
+    
+    # Create handlers
+    handlers = []
+    
+    # Console handler (using stderr for better tqdm compatibility)
+    console_handler = logging.StreamHandler(stream=sys.stderr) 
+    console_handler.setFormatter(formatter)
+    handlers.append(console_handler)
+    
+    # File handler if specified
+    if log_file:
+        file_handler = logging.FileHandler(log_file)
+        file_handler.setFormatter(formatter)
+        handlers.append(file_handler)
+    
+    # Configure root logger
+    root_logger = logging.getLogger()
+    root_logger.setLevel(level)
+    
+    # Remove existing handlers from root logger to avoid duplication
+    for handler in root_logger.handlers[:]:
+        root_logger.removeHandler(handler)
+        
+    # Add our handlers to root logger
+    for handler in handlers:
+        root_logger.addHandler(handler)
+    
+    # Silence noisy library loggers
+    logging.getLogger("urllib3").setLevel(logging.WARNING)
+    logging.getLogger("backoff").setLevel(logging.WARNING)
+
+    # Get and return the application-specific logger
+    logger = logging.getLogger("docs_to_md") # Updated name
+    # Ensure the app logger also has the correct level if root is different
+    logger.setLevel(level) 
+    return logger
+
+
+class ProgressTracker:
+    """
+    Manages progress tracking for long-running operations.
+    Uses tqdm for progress bars but abstracts its usage.
+    """
+    
+    def __init__(self, total: int, description: str, unit: str = "item"):
+        """
+        Initialize a progress tracker.
+        
+        Args:
+            total: Total number of items to process
+            description: Description of the progress (shown in the bar)
+            unit: Unit of items being processed
+        """
+        self.pbar: Optional[tqdm] = None
+        self._has_tqdm: bool = False
+        self.description = description # For fallback
+        self.total = total # For fallback
+        self.current = 0 # For fallback
+        self.logger = logging.getLogger("docs_to_md.progress") # Updated name
+        
+        try:
+            # Initialize tqdm here
+            self.pbar = tqdm(
+                total=total, 
+                desc=description, 
+                unit=unit, 
+                file=sys.stderr, # Explicitly use stderr
+                leave=False
+                )
+            self._has_tqdm = True
+        except Exception as e: # Catching generic Exception is broad, but okay for try/except on import/init
+            self.logger.warning(f"Could not initialize tqdm: {e}. Falling back to log messages.")
+            self._has_tqdm = False
+
+    def __enter__(self):
+        # The pbar is already created in __init__ if possible
+        return self
+    
+    def update(self, count: int = 1) -> None:
+        """
+        Update progress count.
+        
+        Args:
+            count: Number of items to add to progress (default: 1)
+        """
+        if self._has_tqdm and self.pbar:
+            self.pbar.update(count)
+        else:
+            self.current += count
+            # Log progress only periodically or based on some condition to avoid excessive logging
+            if self.current % 10 == 0 or self.current == self.total: # Example: log every 10 updates or on completion
+                 self.logger.info(f"{self.description}: {self.current}/{self.total}")
+    
+    def close(self) -> None:
+        """Close the progress tracker and free resources."""
+        if self._has_tqdm and self.pbar:
+            self.pbar.close()
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        self.close()
+
+# Example usage (for testing):
+# if __name__ == "__main__":
+#     setup_logging()
+#     log = logging.getLogger("docs_to_md")
+#     log.info("Starting test")
+#     with ProgressTracker(10, "Testing Progress") as pt:
+#         for i in range(10):
+#             time.sleep(0.2)
+#             pt.update()
+#     log.info("Finished test") 

pdf_to_markdown_cli-0.2.0.dist-info/METADATA

@@ -0,0 +1,179 @@
+Metadata-Version: 2.4
+Name: pdf-to-markdown-cli
+Version: 0.2.0
+Summary: CLI tool to convert PDF files (and other documents) to markdown using the Marker API.
+Home-page: https://github.com/SokolskyNikita/pdf-to-markdown-cli
+Author: Nikita Sokolsky
+Project-URL: Bug Tracker, https://github.com/SokolskyNikita/pdf-to-markdown-cli/issues
+Keywords: pdf,markdown,converter,cli,document,marker,md
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: End Users/Desktop
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Text Processing
+Classifier: Topic :: Utilities
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: backoff>=2.0
+Requires-Dist: diskcache>=5.0
+Requires-Dist: filetype>=1.0
+Requires-Dist: pikepdf>=8.0
+Requires-Dist: pydantic>=2.0
+Requires-Dist: ratelimit>=2.0
+Requires-Dist: requests>=2.0
+Requires-Dist: tqdm>=4.0
+Dynamic: author
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license-file
+Dynamic: project-url
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# PDF to Markdown CLI (using Marker API)
+
+Convert PDF files (and other documents) to markdown using the [Marker API](https://www.marker.io/) via a command-line tool.
+
+## Overview
+
+This package provides a convenient command-line interface (`pdf-to-md`) for converting PDF files (and other document formats like Word, EPUB, images, etc.) to markdown. It leverages the Marker API for high-quality PDF conversion and handles chunking, parallel processing, and result combination.
+
+## Features
+
+- Convert PDFs, Word documents, PowerPoint files, spreadsheets, epub, HTML, and images to markdown
+- Optionally use the Marker API for enhanced PDF conversion
+- Handle large documents by splitting them into chunks
+- Progress tracking for long-running operations
+- Customizable OCR options
+- Local caching of results
+- Output in markdown, JSON, or HTML format
+
+## Installation
+
+### From PyPI
+
+```bash
+pip install pdf-to-markdown-cli
+```
+
+### From source
+
+```bash
+git clone https://github.com/SokolskyNikita/pdf-to-markdown-cli.git 
+cd pdf-to-markdown-cli
+pip install -e .
+```
+
+## Usage
+
+### Command-line interface
+
+```bash
+# Set your Marker API key
+export MARKER_PDF_KEY=your_api_key_here
+
+# Basic usage
+pdf-to-md /path/to/file.pdf
+
+# Process all files in a directory
+pdf-to-md /path/to/directory
+
+# Output in JSON format
+pdf-to-md /path/to/file.pdf --json
+
+# Use additional languages for OCR
+pdf-to-md /path/to/file.pdf --langs "English,French,German"
+
+# Use all Marker OCR enhancements
+pdf-to-md /path/to/file.pdf --max
+```
+
+### API
+
+```python
+# Internal module paths remain the same
+from docs_to_md.config.settings import Config
+from docs_to_md.core.processor import MarkerProcessor
+
+# Create configuration
+config = Config(
+    api_key="your_api_key_here",
+    input_path="/path/to/file.pdf",
+    output_format="markdown",
+    use_llm=True
+)
+
+# Create processor and run
+processor = MarkerProcessor(config)
+processor.process()
+```
+
+## Command-line Options
+
+- `input`: Input file or directory path
+- `--json`: Output in JSON format (default is markdown)
+- `--langs`: Comma-separated OCR languages (default: "English")
+- `--llm`: Use LLM for enhanced processing
+- `--strip`: Redo OCR processing
+- `--noimg`: Disable image extraction
+- `--force`: Force OCR on all pages
+- `--pages`: Add page delimiters
+- `--max`: Enable all OCR enhancements (equivalent to --llm --strip --force)
+- `--max-pages`: Maximum number of pages to process from the start of the file
+- `--no-chunk`: Disable PDF chunking
+- `--chunk-size`: Set PDF chunk size in pages (default: 25)
+- `--output-dir`: Output directory (default: "converted")
+- `--cache-dir`: Cache directory (default: ".marker_cache")
+
+## Project Structure
+
+The package is organized as follows:
+
+```
+pdf-to-markdown-cli/ (Project Root)
+├── docs_to_md/      (Python Package Source)
+│   ├── api/
+│   ├── config/
+│   ├── core/
+│   ├── pdf/
+│   ├── storage/
+│   └── utils/
+├── setup.py
+├── README.md
+└── ... (other config files)
+```
+
+## Requirements
+
+- Python 3.10 or higher
+- Runtime dependencies are listed in `setup.py` and automatically installed via pip.
+- The `requirements.txt` file lists exact versions used for development and testing, and can be used to set up a development environment: `pip install -r requirements.txt`
+
+## Development
+
+To run the code directly from the source tree without installation:
+
+```bash
+# Using the installed entry point (requires editable install):
+# pip install -e .
+# pdf-to-md /path/to/file.pdf
+
+# Or running the module directly:
+python -m docs_to_md /path/to/file.pdf 
+```
+
+For regular use after installation, use the `pdf-to-md` command.
+
+## License
+
+This project is licensed under the MIT License - see the LICENSE file for details.

pdf_to_markdown_cli-0.2.0.dist-info/RECORD

@@ -0,0 +1,27 @@
+docs_to_md/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docs_to_md/__main__.py,sha256=ebTiYZ1owy2lbPJNsCEKfGGAvr91uFJeeoZt-7tI0-k,83
+docs_to_md/main.py,sha256=P8m9mYk4sHAimTZX2vhGKJORBMyDJQHqih0YAGyc-hg,1358
+docs_to_md/api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docs_to_md/api/client.py,sha256=YSHbkc6JKQG-RzR0R6mfuxpSlIh3JrTmVm-hhQHxCiM,7945
+docs_to_md/api/models.py,sha256=cblbgWP4PXS3rtGkY_2FKD2A__imdfDN5Hlx93euBOw,2258
+docs_to_md/config/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docs_to_md/config/cli.py,sha256=CQsyXrlwFzGdYvLUZJCTxHQOsCWEEAumWyZ1oVUsqGo,3267
+docs_to_md/config/settings.py,sha256=9MkZqE8AAeNulWj4Stx6EPZHbhGWE5sMuV0eg9djfzA,3967
+docs_to_md/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docs_to_md/core/processor.py,sha256=nHekhyquNfJ-2QLxQH5j5ybGOFVJDujkQvavPt9hkRc,8649
+docs_to_md/core/result_handler.py,sha256=a333CyvxSHbgZrJOPE4uxcIYswNZyr9rETMiCpjg_nA,18449
+docs_to_md/pdf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docs_to_md/pdf/splitter.py,sha256=ZSzyAcWx0hmyEbK1uCEzb5iTRqg8AB46NDPVe0PUhcA,5926
+docs_to_md/storage/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docs_to_md/storage/cache.py,sha256=ZRntNXieRrFKyD6YE_8iZuzI8WriHzJoV3cKDKKxLFU,3817
+docs_to_md/storage/models.py,sha256=KKKhJtkNvOlS-snksjL2KaggSqhrP67bXoPc1li8KXE,2841
+docs_to_md/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docs_to_md/utils/exceptions.py,sha256=ljStvAU6wY0G-lbJENgwp_JUq5wQqCOGOfQYrchqCAw,757
+docs_to_md/utils/file_utils.py,sha256=3oMDAol8LF5ExZtaa8BHNtDkNwKY_aqKbz4gx018ZLg,6699
+docs_to_md/utils/logging.py,sha256=KD3V-4XqQ18ZANEj8-DvAvY8kbgnjJPPwpQEWz1Ny7w,4496
+pdf_to_markdown_cli-0.2.0.dist-info/licenses/LICENSE,sha256=TvzNGSILmRdjt79Z-5m7QYS8dOY2hoszcVo_KxZRA5s,1071
+pdf_to_markdown_cli-0.2.0.dist-info/METADATA,sha256=NRTVoyaGT3voVDNG-UbjbCzhQOHy4pCnN34tXuUMhXQ,5220
+pdf_to_markdown_cli-0.2.0.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+pdf_to_markdown_cli-0.2.0.dist-info/entry_points.txt,sha256=gL4qvIudGRvzVrAZWqpyspqDVEtJbFpGuHiwj7_N_Ds,51
+pdf_to_markdown_cli-0.2.0.dist-info/top_level.txt,sha256=6P0VeRWDqZ8Ckk8xooPcwNAPPgep5yVEYmmcI3A9C2M,11
+pdf_to_markdown_cli-0.2.0.dist-info/RECORD,,

pdf_to_markdown_cli-0.2.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (78.1.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

pdf_to_markdown_cli-0.2.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+pdf-to-md = docs_to_md.main:main

pdf_to_markdown_cli-0.2.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 SokolskyNikita
+
+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.

pdf_to_markdown_cli-0.2.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+docs_to_md