pdfstructx 0.2.0__tar.gz

pdfstructx-0.2.0/LICENSE

@@ -0,0 +1,38 @@
+pdfstruct - Personal Use License
+
+Copyright (c) 2026 Kyros Groupe. All rights reserved.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to use,
+copy, modify, and distribute the Software for PERSONAL, EDUCATIONAL, and
+NON-COMMERCIAL purposes only, subject to the following conditions:
+
+1. PERSONAL USE: You may use the Software for personal projects, learning,
+   research, and non-commercial open-source projects.
+
+2. COMMERCIAL USE PROHIBITED: You may NOT use the Software, in whole or in
+   part, for any commercial purpose without obtaining a separate commercial
+   license from Kyros Groupe. Commercial use includes, but is not limited to:
+   - Incorporating the Software into a product or service sold for profit
+   - Using the Software to provide paid services or SaaS offerings
+   - Using the Software within a for-profit business for internal operations
+   - Distributing the Software as part of a commercial product
+
+3. ATTRIBUTION: All copies or substantial portions of the Software must
+   include this license notice and the above copyright notice.
+
+4. NO SUBLICENSING: You may not sublicense the Software under different terms.
+
+5. MODIFICATIONS: You may modify the Software for personal use. Modified
+   versions must retain this license and cannot be distributed under
+   different terms.
+
+For commercial licensing inquiries, contact: licensing@kyros-groupe.com
+
+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.

pdfstructx-0.2.0/MANIFEST.in

@@ -0,0 +1,4 @@
+include LICENSE
+include README.md
+include pyproject.toml
+recursive-include src/pdfstruct *.py

pdfstructx-0.2.0/PKG-INFO

@@ -0,0 +1,217 @@
+Metadata-Version: 2.2
+Name: pdfstructx
+Version: 0.2.0
+Summary: Intelligent PDF parser with font-aware structure detection, table extraction, and multi-column support
+Author: Kyros Groupe
+License: pdfstruct - Personal Use License
+        
+        Copyright (c) 2026 Kyros Groupe. All rights reserved.
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to use,
+        copy, modify, and distribute the Software for PERSONAL, EDUCATIONAL, and
+        NON-COMMERCIAL purposes only, subject to the following conditions:
+        
+        1. PERSONAL USE: You may use the Software for personal projects, learning,
+           research, and non-commercial open-source projects.
+        
+        2. COMMERCIAL USE PROHIBITED: You may NOT use the Software, in whole or in
+           part, for any commercial purpose without obtaining a separate commercial
+           license from Kyros Groupe. Commercial use includes, but is not limited to:
+           - Incorporating the Software into a product or service sold for profit
+           - Using the Software to provide paid services or SaaS offerings
+           - Using the Software within a for-profit business for internal operations
+           - Distributing the Software as part of a commercial product
+        
+        3. ATTRIBUTION: All copies or substantial portions of the Software must
+           include this license notice and the above copyright notice.
+        
+        4. NO SUBLICENSING: You may not sublicense the Software under different terms.
+        
+        5. MODIFICATIONS: You may modify the Software for personal use. Modified
+           versions must retain this license and cannot be distributed under
+           different terms.
+        
+        For commercial licensing inquiries, contact: licensing@kyros-groupe.com
+        
+        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.
+        
+Project-URL: Homepage, https://github.com/kyros-groupe/pdfstruct
+Project-URL: Documentation, https://github.com/kyros-groupe/pdfstruct#readme
+Project-URL: Issues, https://github.com/kyros-groupe/pdfstruct/issues
+Keywords: pdf,parser,document,extraction,tables,structure
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+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 :: General
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pdfminer.six>=20231228
+Requires-Dist: Pillow>=10.0.0
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0; extra == "dev"
+Requires-Dist: ruff>=0.4.0; extra == "dev"
+
+# pdfstruct
+
+Intelligent PDF parser with font-aware structure detection, table extraction, and multi-column support.
+
+[![Python](https://img.shields.io/badge/python-≥3.10-blue.svg)](https://www.python.org/)
+
+## Overview
+
+**pdfstruct** is a Python library that extracts structured content from PDF documents. Unlike basic text extraction tools, pdfstruct understands document layout — detecting headings, sections, tables, lists, headers/footers, and multi-column layouts using font analysis and geometric reasoning.
+
+## Features
+
+- **Font-aware heading detection**: Uses font size, weight, and frequency analysis to classify headings (H1–H6)
+- **Table extraction**: Detects tables from grid lines and whitespace-aligned columns
+- **Section hierarchy**: Builds a document tree from headings and content
+- **Multi-column support**: Handles two-column and multi-column layouts
+- **Header/footer removal**: Identifies and filters repeating page content
+- **List detection**: Recognizes bulleted, numbered, lettered, and Roman numeral lists
+- **Multiple output formats**: JSON, Markdown, and plain text
+- **Rich metadata**: Word count, language detection, reading time, font statistics
+
+## Installation
+
+```bash
+pip install pdfstruct
+```
+
+Or install from source:
+
+```bash
+git clone https://github.com/kyros-groupe/pdfstruct.git
+cd pdfstruct
+pip install -e .
+```
+
+## Quickstart
+
+```python
+import pdfstruct
+
+# Parse a PDF
+doc = pdfstruct.parse("contract.pdf")
+
+# Access structured content
+print(doc.title)
+print(f"{doc.page_count} pages, {doc.metadata.word_count} words")
+
+# Browse sections
+for section in doc.sections:
+    print(f"{section.heading} ({len(section.content)} chars)")
+    for sub in section.subsections:
+        print(f"  {sub.heading}")
+
+# Get tables
+for table in doc.tables:
+    print(table.to_dicts())  # List of row dicts
+
+# Export to different formats
+print(pdfstruct.to_markdown(doc))
+print(pdfstruct.to_text(doc))
+print(pdfstruct.to_json(doc))
+
+# Full dict for programmatic use
+data = pdfstruct.to_dict(doc)
+```
+
+## API Reference
+
+### `pdfstruct.parse(source, **options) -> Document`
+
+Parse a PDF file, bytes, or file-like object.
+
+**Options:**
+- `detect_tables` (bool, default True) — Enable table detection
+- `detect_headers_footers` (bool, default True) — Remove repeating headers/footers
+- `detect_lists` (bool, default True) — Detect list structures
+- `detect_columns` (bool, default True) — Handle multi-column layouts
+
+### Document
+
+- `doc.title` — Detected document title
+- `doc.pages` — List of Page objects
+- `doc.sections` — Hierarchical section tree
+- `doc.tables` — All detected tables
+- `doc.metadata` — DocumentMetadata with statistics
+- `doc.text` — Full document text (concatenated from pages)
+- `doc.to_dict()` — JSON-serializable dictionary
+
+### Section
+
+- `section.heading` — Section heading text
+- `section.heading_level` — HeadingLevel enum (H1–H6)
+- `section.content` — Section body text
+- `section.paragraphs` — List of Paragraph objects
+- `section.subsections` — Nested subsections
+
+### Table
+
+- `table.rows` — List of TableRow objects
+- `table.to_list()` — 2D list of cell text
+- `table.to_dicts()` — List of dicts (header row as keys)
+- `table.num_rows`, `table.num_cols` — Dimensions
+
+### Metadata
+
+- `metadata.word_count`, `metadata.char_count` — Text statistics
+- `metadata.language` — Detected language code
+- `metadata.page_count` — Number of pages
+- `metadata.is_scanned` — Whether PDF appears to be scanned
+- `metadata.has_tables`, `metadata.has_images` — Content flags
+- `metadata.primary_font`, `metadata.primary_font_size` — Font info
+
+## Architecture
+
+```
+pdfstruct/
+├── parser.py           # Main PDFParser class and parse() entry point
+├── models/
+│   ├── document.py     # Core models: Document, Page, Section, TextLine, Table, etc.
+│   └── metadata.py     # DocumentMetadata with computed statistics
+├── extractors/
+│   └── text.py         # PDF text extraction via pdfminer.six
+├── layout/
+│   └── analyzer.py     # Paragraph grouping, reading order, margins
+├── structure/
+│   ├── headings.py     # Font-aware heading detection
+│   ├── headers_footers.py  # Repeating content detection
+│   ├── lists.py        # List structure detection
+│   └── sections.py     # Section hierarchy builder
+├── tables/
+│   └── detector.py     # Grid and whitespace table detection
+├── output/
+│   ├── json_output.py  # JSON/dict export
+│   ├── markdown.py     # Markdown export
+│   └── text_output.py  # Plain text export
+└── utils/
+    ├── fonts.py        # Font analysis and heading classification
+    ├── geometry.py     # Bounding box utilities, column detection
+    └── language.py     # Language detection heuristics
+```
+
+## Requirements
+
+- Python >= 3.10
+- pdfminer.six >= 20231228
+- Pillow >= 10.0.0
+
+## License
+
+Personal Use License by Kyros Groupe. See [LICENSE](LICENSE) for details.

pdfstructx-0.2.0/README.md

@@ -0,0 +1,150 @@
+# pdfstruct
+
+Intelligent PDF parser with font-aware structure detection, table extraction, and multi-column support.
+
+[![Python](https://img.shields.io/badge/python-≥3.10-blue.svg)](https://www.python.org/)
+
+## Overview
+
+**pdfstruct** is a Python library that extracts structured content from PDF documents. Unlike basic text extraction tools, pdfstruct understands document layout — detecting headings, sections, tables, lists, headers/footers, and multi-column layouts using font analysis and geometric reasoning.
+
+## Features
+
+- **Font-aware heading detection**: Uses font size, weight, and frequency analysis to classify headings (H1–H6)
+- **Table extraction**: Detects tables from grid lines and whitespace-aligned columns
+- **Section hierarchy**: Builds a document tree from headings and content
+- **Multi-column support**: Handles two-column and multi-column layouts
+- **Header/footer removal**: Identifies and filters repeating page content
+- **List detection**: Recognizes bulleted, numbered, lettered, and Roman numeral lists
+- **Multiple output formats**: JSON, Markdown, and plain text
+- **Rich metadata**: Word count, language detection, reading time, font statistics
+
+## Installation
+
+```bash
+pip install pdfstruct
+```
+
+Or install from source:
+
+```bash
+git clone https://github.com/kyros-groupe/pdfstruct.git
+cd pdfstruct
+pip install -e .
+```
+
+## Quickstart
+
+```python
+import pdfstruct
+
+# Parse a PDF
+doc = pdfstruct.parse("contract.pdf")
+
+# Access structured content
+print(doc.title)
+print(f"{doc.page_count} pages, {doc.metadata.word_count} words")
+
+# Browse sections
+for section in doc.sections:
+    print(f"{section.heading} ({len(section.content)} chars)")
+    for sub in section.subsections:
+        print(f"  {sub.heading}")
+
+# Get tables
+for table in doc.tables:
+    print(table.to_dicts())  # List of row dicts
+
+# Export to different formats
+print(pdfstruct.to_markdown(doc))
+print(pdfstruct.to_text(doc))
+print(pdfstruct.to_json(doc))
+
+# Full dict for programmatic use
+data = pdfstruct.to_dict(doc)
+```
+
+## API Reference
+
+### `pdfstruct.parse(source, **options) -> Document`
+
+Parse a PDF file, bytes, or file-like object.
+
+**Options:**
+- `detect_tables` (bool, default True) — Enable table detection
+- `detect_headers_footers` (bool, default True) — Remove repeating headers/footers
+- `detect_lists` (bool, default True) — Detect list structures
+- `detect_columns` (bool, default True) — Handle multi-column layouts
+
+### Document
+
+- `doc.title` — Detected document title
+- `doc.pages` — List of Page objects
+- `doc.sections` — Hierarchical section tree
+- `doc.tables` — All detected tables
+- `doc.metadata` — DocumentMetadata with statistics
+- `doc.text` — Full document text (concatenated from pages)
+- `doc.to_dict()` — JSON-serializable dictionary
+
+### Section
+
+- `section.heading` — Section heading text
+- `section.heading_level` — HeadingLevel enum (H1–H6)
+- `section.content` — Section body text
+- `section.paragraphs` — List of Paragraph objects
+- `section.subsections` — Nested subsections
+
+### Table
+
+- `table.rows` — List of TableRow objects
+- `table.to_list()` — 2D list of cell text
+- `table.to_dicts()` — List of dicts (header row as keys)
+- `table.num_rows`, `table.num_cols` — Dimensions
+
+### Metadata
+
+- `metadata.word_count`, `metadata.char_count` — Text statistics
+- `metadata.language` — Detected language code
+- `metadata.page_count` — Number of pages
+- `metadata.is_scanned` — Whether PDF appears to be scanned
+- `metadata.has_tables`, `metadata.has_images` — Content flags
+- `metadata.primary_font`, `metadata.primary_font_size` — Font info
+
+## Architecture
+
+```
+pdfstruct/
+├── parser.py           # Main PDFParser class and parse() entry point
+├── models/
+│   ├── document.py     # Core models: Document, Page, Section, TextLine, Table, etc.
+│   └── metadata.py     # DocumentMetadata with computed statistics
+├── extractors/
+│   └── text.py         # PDF text extraction via pdfminer.six
+├── layout/
+│   └── analyzer.py     # Paragraph grouping, reading order, margins
+├── structure/
+│   ├── headings.py     # Font-aware heading detection
+│   ├── headers_footers.py  # Repeating content detection
+│   ├── lists.py        # List structure detection
+│   └── sections.py     # Section hierarchy builder
+├── tables/
+│   └── detector.py     # Grid and whitespace table detection
+├── output/
+│   ├── json_output.py  # JSON/dict export
+│   ├── markdown.py     # Markdown export
+│   └── text_output.py  # Plain text export
+└── utils/
+    ├── fonts.py        # Font analysis and heading classification
+    ├── geometry.py     # Bounding box utilities, column detection
+    └── language.py     # Language detection heuristics
+```
+
+## Requirements
+
+- Python >= 3.10
+- pdfminer.six >= 20231228
+- Pillow >= 10.0.0
+
+## License
+
+Personal Use License by Kyros Groupe. See [LICENSE](LICENSE) for details.

pdfstructx-0.2.0/pyproject.toml

@@ -0,0 +1,52 @@
+[build-system]
+requires = ["setuptools>=68.0,<77", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "pdfstructx"
+version = "0.2.0"
+description = "Intelligent PDF parser with font-aware structure detection, table extraction, and multi-column support"
+readme = "README.md"
+license = {file = "LICENSE"}
+requires-python = ">=3.10"
+authors = [
+    {name = "Kyros Groupe"},
+]
+keywords = ["pdf", "parser", "document", "extraction", "tables", "structure"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "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 :: General",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+]
+dependencies = [
+    "pdfminer.six>=20231228",
+    "Pillow>=10.0.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=8.0",
+    "pytest-cov>=4.0",
+    "ruff>=0.4.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/kyros-groupe/pdfstruct"
+Documentation = "https://github.com/kyros-groupe/pdfstruct#readme"
+Issues = "https://github.com/kyros-groupe/pdfstruct/issues"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"

pdfstructx-0.2.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

pdfstructx-0.2.0/src/pdfstruct/__init__.py

@@ -0,0 +1,76 @@
+"""pdfstruct — Intelligent PDF parser with structure detection.
+
+Parse PDFs into structured documents with headings, sections, tables,
+lists, and metadata. Font-aware heading detection. Multi-column support.
+Grid and whitespace table extraction.
+
+Basic usage:
+    >>> import pdfstruct
+    >>> doc = pdfstruct.parse("document.pdf")
+    >>> print(doc.title)
+    >>> print(doc.sections)
+    >>> print(doc.tables)
+
+Export formats:
+    >>> pdfstruct.to_json(doc)
+    >>> pdfstruct.to_markdown(doc)
+    >>> pdfstruct.to_text(doc)
+    >>> pdfstruct.to_dict(doc)
+
+License: Personal Use Only — see LICENSE file.
+Copyright (c) 2026 Kyros Groupe.
+"""
+
+__version__ = "0.2.0"
+
+from pdfstruct.parser import parse, PDFParser
+from pdfstruct.models.document import (
+    Document,
+    Page,
+    Section,
+    Paragraph,
+    TextLine,
+    Table,
+    TableRow,
+    TableCell,
+    BBox,
+    FontInfo,
+    HeadingLevel,
+    ListType,
+    ListItem,
+    ImageInfo,
+)
+from pdfstruct.models.metadata import DocumentMetadata
+from pdfstruct.output.json_output import to_json, to_dict
+from pdfstruct.output.markdown import to_markdown
+from pdfstruct.output.text_output import to_text
+from pdfstruct.extractors.images import generate_thumbnail
+
+__all__ = [
+    # Core API
+    "parse",
+    "PDFParser",
+    # Models
+    "Document",
+    "Page",
+    "Section",
+    "Paragraph",
+    "TextLine",
+    "Table",
+    "TableRow",
+    "TableCell",
+    "BBox",
+    "FontInfo",
+    "HeadingLevel",
+    "ListType",
+    "ListItem",
+    "ImageInfo",
+    "DocumentMetadata",
+    # Output
+    "to_json",
+    "to_dict",
+    "to_markdown",
+    "to_text",
+    # Utilities
+    "generate_thumbnail",
+]