dforge-cli 1.0.1__tar.gz

dforge_cli-1.0.1/PKG-INFO

@@ -0,0 +1,244 @@
+Metadata-Version: 2.4
+Name: dforge-cli
+Version: 1.0.1
+Summary: DForge — Unified Document Processing CLI. Forge your documents from your terminal.
+Author: Punith Naidu
+License: MIT
+Keywords: pdf,ocr,document,cli,conversion,tesseract,batch
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+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 :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Office/Business
+Classifier: Topic :: Utilities
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: typer[all]>=0.9.0
+Requires-Dist: pypdf>=3.0.0
+Requires-Dist: pikepdf>=8.0.0
+Requires-Dist: Pillow>=10.0.0
+Requires-Dist: opencv-python-headless>=4.8.0
+Requires-Dist: img2pdf>=0.4.4
+Requires-Dist: watchdog>=3.0.0
+Requires-Dist: tqdm>=4.66.0
+Requires-Dist: rich>=13.0.0
+Requires-Dist: questionary>=2.0.0
+Requires-Dist: prompt_toolkit>=3.0.0
+Requires-Dist: pyfiglet>=1.0.2
+Provides-Extra: ocr
+Requires-Dist: pytesseract>=0.3.10; extra == "ocr"
+Requires-Dist: pdf2image>=1.16.3; extra == "ocr"
+Provides-Extra: tables
+Requires-Dist: pdfplumber>=0.10.0; extra == "tables"
+Requires-Dist: pandas>=2.0.0; extra == "tables"
+Requires-Dist: openpyxl>=3.1.0; extra == "tables"
+Provides-Extra: full
+Requires-Dist: pytesseract>=0.3.10; extra == "full"
+Requires-Dist: pdf2image>=1.16.3; extra == "full"
+Requires-Dist: pdfplumber>=0.10.0; extra == "full"
+Requires-Dist: pandas>=2.0.0; extra == "full"
+Requires-Dist: openpyxl>=3.1.0; extra == "full"
+
+# DForge — Forge your documents from your terminal.
+
+A unified, offline-first Python CLI for all your document processing needs.
+
+---
+
+## Installation
+
+```bash
+pip install dforge
+```
+
+### External Dependencies
+
+| Tool | Purpose | Install |
+|------|---------|---------|
+| Tesseract OCR | OCR engine | [Install guide](https://tesseract-ocr.github.io/tessdoc/Installation.html) |
+| Ghostscript | PDF compression | [ghostscript.com](https://ghostscript.com/releases/gsdnld.html) |
+| Pandoc | Document conversion | [pandoc.org](https://pandoc.org/installing.html) |
+| Poppler | PDF → image (pdf2image) | `apt install poppler-utils` / `brew install poppler` |
+
+---
+
+## Quick Reference
+
+### PDF Operations
+
+```bash
+# Merge PDFs
+dforge merge a.pdf b.pdf c.pdf -o merged.pdf
+
+# Split into pages
+dforge split report.pdf
+
+# Compress (uses Ghostscript)
+dforge compress large.pdf --preset ebook
+
+# Rotate pages
+dforge rotate file.pdf 90
+
+# Extract page range
+dforge pages file.pdf 1-5
+
+# Watermark
+dforge watermark file.pdf logo.png
+
+# Encrypt / Decrypt
+dforge encrypt file.pdf
+dforge decrypt protected.pdf
+```
+
+### OCR
+
+```bash
+# OCR an image
+dforge ocr scan.png
+
+# OCR a PDF
+dforge ocr scan.pdf
+
+# Output as JSON or Markdown
+dforge ocr scan.pdf --fmt json
+dforge ocr scan.pdf --fmt md
+
+# Multi-language OCR
+dforge ocr scan.png --lang eng+hin
+
+# Make a scanned PDF searchable
+dforge searchable scan.pdf
+
+# Batch OCR an entire folder
+dforge batch-ocr invoices/
+```
+
+### Document Conversion
+
+```bash
+# Convert DOCX → PDF
+dforge convert report.docx pdf
+
+# Convert Markdown → HTML
+dforge convert notes.md html
+
+# Combine images into a PDF
+dforge img2pdf scans/
+
+# Export PDF pages as images
+dforge pdf2img report.pdf --dpi 300 --fmt png
+```
+
+### Content Extraction
+
+```bash
+# Extract text
+dforge text report.pdf
+
+# Extract embedded images
+dforge images report.pdf
+
+# Show / save metadata
+dforge metadata report.pdf
+dforge metadata report.pdf -o meta.json
+
+# Extract tables
+dforge tables invoice.pdf --fmt xlsx
+dforge tables invoice.pdf --fmt csv
+dforge tables invoice.pdf --fmt json
+```
+
+### Image Processing
+
+```bash
+# Enhance (contrast + sharpness)
+dforge enhance scan.png
+
+# Fix skewed scans
+dforge deskew scan.png
+
+# Remove noise
+dforge denoise scan.png
+
+# Resize
+dforge resize photo.png --width 800
+dforge resize photo.png --scale 0.5
+
+# Full OCR preprocessing pipeline
+dforge preprocess scan.png
+```
+
+### Batch Processing
+
+```bash
+# Batch OCR with 8 workers
+dforge batch ./documents --ocr --workers 8
+
+# Batch compress
+dforge batch ./pdfs --compress
+
+# Batch convert to markdown
+dforge batch ./docs --convert md
+```
+
+### Watch Mode
+
+```bash
+# Auto-OCR new files dropped into a folder
+dforge watch ./incoming --ocr
+
+# Auto-make-searchable
+dforge watch ./scans --searchable
+
+# Auto-compress
+dforge watch ./uploads --compress
+```
+
+---
+
+## Project Structure
+
+```
+dforge/
+├── cli.py           ← Typer CLI entry point
+├── config.py        ← Global configuration
+├── utils.py         ← Shared utilities
+├── pdf/
+│   └── operations.py  ← merge, split, compress, rotate, pages, watermark, encrypt, decrypt
+├── ocr/
+│   └── engine.py      ← ocr_image, ocr_pdf, make_searchable_pdf, batch_ocr
+├── convert/
+│   └── converter.py   ← convert, images_to_pdf, pdf_to_images
+├── extract/
+│   └── extractor.py   ← extract_text, extract_images, extract_metadata, extract_tables
+├── image/
+│   └── processor.py   ← enhance, deskew, denoise, resize, preprocess_for_ocr
+├── batch/
+│   └── processor.py   ← parallel batch processing
+└── watch/
+    └── watcher.py     ← watchdog-based directory monitor
+```
+
+---
+
+## Supported Formats
+
+| Category | Formats |
+|----------|---------|
+| Input documents | PDF, DOCX, ODT, MD, HTML, TXT, RST, EPUB |
+| Input images | PNG, JPG/JPEG, TIFF/TIF, BMP, WebP |
+| OCR output | TXT, JSON, Markdown |
+| Table export | CSV, XLSX, JSON |
+| Image export | PNG, JPEG, TIFF |
+
+---
+
+## License
+
+MIT License — DForge Contributors

dforge_cli-1.0.1/README.md

@@ -0,0 +1,197 @@
+# DForge — Forge your documents from your terminal.
+
+A unified, offline-first Python CLI for all your document processing needs.
+
+---
+
+## Installation
+
+```bash
+pip install dforge
+```
+
+### External Dependencies
+
+| Tool | Purpose | Install |
+|------|---------|---------|
+| Tesseract OCR | OCR engine | [Install guide](https://tesseract-ocr.github.io/tessdoc/Installation.html) |
+| Ghostscript | PDF compression | [ghostscript.com](https://ghostscript.com/releases/gsdnld.html) |
+| Pandoc | Document conversion | [pandoc.org](https://pandoc.org/installing.html) |
+| Poppler | PDF → image (pdf2image) | `apt install poppler-utils` / `brew install poppler` |
+
+---
+
+## Quick Reference
+
+### PDF Operations
+
+```bash
+# Merge PDFs
+dforge merge a.pdf b.pdf c.pdf -o merged.pdf
+
+# Split into pages
+dforge split report.pdf
+
+# Compress (uses Ghostscript)
+dforge compress large.pdf --preset ebook
+
+# Rotate pages
+dforge rotate file.pdf 90
+
+# Extract page range
+dforge pages file.pdf 1-5
+
+# Watermark
+dforge watermark file.pdf logo.png
+
+# Encrypt / Decrypt
+dforge encrypt file.pdf
+dforge decrypt protected.pdf
+```
+
+### OCR
+
+```bash
+# OCR an image
+dforge ocr scan.png
+
+# OCR a PDF
+dforge ocr scan.pdf
+
+# Output as JSON or Markdown
+dforge ocr scan.pdf --fmt json
+dforge ocr scan.pdf --fmt md
+
+# Multi-language OCR
+dforge ocr scan.png --lang eng+hin
+
+# Make a scanned PDF searchable
+dforge searchable scan.pdf
+
+# Batch OCR an entire folder
+dforge batch-ocr invoices/
+```
+
+### Document Conversion
+
+```bash
+# Convert DOCX → PDF
+dforge convert report.docx pdf
+
+# Convert Markdown → HTML
+dforge convert notes.md html
+
+# Combine images into a PDF
+dforge img2pdf scans/
+
+# Export PDF pages as images
+dforge pdf2img report.pdf --dpi 300 --fmt png
+```
+
+### Content Extraction
+
+```bash
+# Extract text
+dforge text report.pdf
+
+# Extract embedded images
+dforge images report.pdf
+
+# Show / save metadata
+dforge metadata report.pdf
+dforge metadata report.pdf -o meta.json
+
+# Extract tables
+dforge tables invoice.pdf --fmt xlsx
+dforge tables invoice.pdf --fmt csv
+dforge tables invoice.pdf --fmt json
+```
+
+### Image Processing
+
+```bash
+# Enhance (contrast + sharpness)
+dforge enhance scan.png
+
+# Fix skewed scans
+dforge deskew scan.png
+
+# Remove noise
+dforge denoise scan.png
+
+# Resize
+dforge resize photo.png --width 800
+dforge resize photo.png --scale 0.5
+
+# Full OCR preprocessing pipeline
+dforge preprocess scan.png
+```
+
+### Batch Processing
+
+```bash
+# Batch OCR with 8 workers
+dforge batch ./documents --ocr --workers 8
+
+# Batch compress
+dforge batch ./pdfs --compress
+
+# Batch convert to markdown
+dforge batch ./docs --convert md
+```
+
+### Watch Mode
+
+```bash
+# Auto-OCR new files dropped into a folder
+dforge watch ./incoming --ocr
+
+# Auto-make-searchable
+dforge watch ./scans --searchable
+
+# Auto-compress
+dforge watch ./uploads --compress
+```
+
+---
+
+## Project Structure
+
+```
+dforge/
+├── cli.py           ← Typer CLI entry point
+├── config.py        ← Global configuration
+├── utils.py         ← Shared utilities
+├── pdf/
+│   └── operations.py  ← merge, split, compress, rotate, pages, watermark, encrypt, decrypt
+├── ocr/
+│   └── engine.py      ← ocr_image, ocr_pdf, make_searchable_pdf, batch_ocr
+├── convert/
+│   └── converter.py   ← convert, images_to_pdf, pdf_to_images
+├── extract/
+│   └── extractor.py   ← extract_text, extract_images, extract_metadata, extract_tables
+├── image/
+│   └── processor.py   ← enhance, deskew, denoise, resize, preprocess_for_ocr
+├── batch/
+│   └── processor.py   ← parallel batch processing
+└── watch/
+    └── watcher.py     ← watchdog-based directory monitor
+```
+
+---
+
+## Supported Formats
+
+| Category | Formats |
+|----------|---------|
+| Input documents | PDF, DOCX, ODT, MD, HTML, TXT, RST, EPUB |
+| Input images | PNG, JPG/JPEG, TIFF/TIF, BMP, WebP |
+| OCR output | TXT, JSON, Markdown |
+| Table export | CSV, XLSX, JSON |
+| Image export | PNG, JPEG, TIFF |
+
+---
+
+## License
+
+MIT License — DForge Contributors

dforge_cli-1.0.1/dforge/__init__.py

@@ -0,0 +1 @@
+__version__ = "1.0.0"

dforge_cli-1.0.1/dforge/banner.py

@@ -0,0 +1,31 @@
+from rich.console import Console
+from rich.panel import Panel
+from rich.align import Align
+
+console = Console()
+
+
+def show_banner():
+    title = """
+⚡ DFORGE
+
+Fast Local Document Automation
+"""
+
+    console.print()
+
+    console.print(
+        Panel(
+            Align.center(f"[bold cyan]{title}[/bold cyan]"),
+            border_style="cyan",
+            padding=(1, 4),
+        )
+    )
+
+    console.print(
+        Align.center(
+            "[dim]Forge your documents from your terminal[/dim]"
+        )
+    )
+
+    console.print()

dforge_cli-1.0.1/dforge/batch.py

@@ -0,0 +1,156 @@
+"""
+DForge Batch Processing
+Handles: batch OCR, batch PDF compression, batch document conversion
+"""
+
+from __future__ import annotations
+
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from pathlib import Path
+from typing import Callable, Iterable
+
+from rich.progress import Progress, TextColumn
+
+from dforge.config import SUPPORTED_DOC_EXTS, SUPPORTED_IMAGE_EXTS, SUPPORTED_PDF_EXTS
+from dforge.utils import (
+    abort,
+    collect_files,
+    console,
+    info,
+    success,
+    warn,
+    require_ghostscript,
+    require_pandoc,
+    require_tesseract,
+)
+
+
+def _run_parallel(
+    label: str,
+    files: list[Path],
+    workers: int,
+    handler: Callable[[Path], None],
+) -> list[tuple[Path, str]]:
+    errors: list[tuple[Path, str]] = []
+    worker_count = max(1, workers or 1)
+
+    with Progress(
+        TextColumn("{task.description}"),
+        TextColumn("{task.completed}/{task.total}"),
+        console=console,
+    ) as progress:
+        task = progress.add_task(label, total=len(files))
+
+        if worker_count == 1:
+            for path in files:
+                try:
+                    handler(path)
+                except Exception as exc:
+                    errors.append((path, str(exc)))
+                progress.advance(task)
+            return errors
+
+        with ThreadPoolExecutor(max_workers=worker_count) as executor:
+            futures = {executor.submit(handler, path): path for path in files}
+            for future in as_completed(futures):
+                path = futures[future]
+                try:
+                    future.result()
+                except Exception as exc:
+                    errors.append((path, str(exc)))
+                progress.advance(task)
+
+    return errors
+
+
+def _report_errors(errors: list[tuple[Path, str]]) -> None:
+    if not errors:
+        return
+    warn(f"{len(errors)} file(s) failed:")
+    for path, err in errors:
+        console.print(f"  [red]{path.name}[/red]: {err}")
+
+
+def batch_with_ocr(
+    directory: Path,
+    lang: str,
+    fmt: str,
+    recursive: bool = True,
+    workers: int = 4,
+) -> None:
+    if not directory.exists():
+        abort(f"Directory not found: {directory}")
+
+    require_tesseract()
+
+    files = collect_files(directory, SUPPORTED_IMAGE_EXTS | SUPPORTED_PDF_EXTS, recursive=recursive)
+    if not files:
+        warn(f"No supported files found in {directory}")
+        return
+
+    info(f"Found {len(files)} file(s) to OCR...")
+
+    def handler(path: Path) -> None:
+        if path.suffix.lower() == ".pdf":
+            from dforge.engine import ocr_pdf
+            ocr_pdf(path, lang=lang, fmt=fmt)
+        else:
+            from dforge.engine import ocr_image
+            ocr_image(path, lang=lang, fmt=fmt)
+
+    errors = _run_parallel("Batch OCR", files, workers, handler)
+    _report_errors(errors)
+    success(f"Batch OCR complete. Processed {len(files) - len(errors)}/{len(files)} file(s).")
+
+
+def batch_compress(
+    directory: Path,
+    recursive: bool = True,
+    workers: int = 4,
+) -> None:
+    if not directory.exists():
+        abort(f"Directory not found: {directory}")
+
+    require_ghostscript()
+
+    files = collect_files(directory, SUPPORTED_PDF_EXTS, recursive=recursive)
+    if not files:
+        warn(f"No PDF files found in {directory}")
+        return
+
+    info(f"Found {len(files)} PDF(s) to compress...")
+
+    def handler(path: Path) -> None:
+        from dforge.operations import compress
+        compress(path)
+
+    errors = _run_parallel("Batch compress", files, workers, handler)
+    _report_errors(errors)
+    success(f"Batch compress complete. Processed {len(files) - len(errors)}/{len(files)} file(s).")
+
+
+def batch_convert(
+    directory: Path,
+    target_format: str,
+    recursive: bool = True,
+    workers: int = 4,
+) -> None:
+    if not directory.exists():
+        abort(f"Directory not found: {directory}")
+
+    require_pandoc()
+
+    files = collect_files(directory, SUPPORTED_DOC_EXTS, recursive=recursive)
+    if not files:
+        warn(f"No convertible documents found in {directory}")
+        return
+
+    info(f"Found {len(files)} document(s) to convert...")
+
+    def handler(path: Path) -> None:
+        from dforge.converter import convert
+        convert(path, target_format)
+
+    errors = _run_parallel("Batch convert", files, workers, handler)
+    _report_errors(errors)
+    success(f"Batch convert complete. Processed {len(files) - len(errors)}/{len(files)} file(s).")