@llamaindex/liteparse 1.0.0

package/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

package/README.md

@@ -0,0 +1,339 @@
+# LiteParse
+
+[![CI](https://github.com/run-llama/liteparse/actions/workflows/ci.yml/badge.svg)](https://github.com/run-llama/liteparse/actions/workflows/ci.yml)
+[![npm version](https://img.shields.io/npm/v/@llamaindex/liteparse.svg)](https://www.npmjs.com/package/@llamaindex/liteparse)
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+
+Open-source PDF parsing with spatial text parsing, no LLMs and cloud dependencies.
+
+## Overview
+
+LiteParse is a standalone OSS PDF parsing tool focused exclusively on **fast and light** parsing. It provides high-quality spatial text parsing with bounding boxes, without proprietary LLM features or cloud dependencies. Everything runs locally on your machine. 
+
+### Features
+
+- **Fast Text Parsing**: Spatial text parsing using PDF.js
+- **Flexible OCR System**:
+  - **Built-in**: Tesseract.js (zero setup, works out of the box!)
+  - **HTTP Servers**: Plug in any OCR server (EasyOCR, PaddleOCR, custom)
+  - **Standard API**: Simple, well-defined OCR API specification
+- **Screenshot Generation**: Generate high-quality page screenshots for LLM agents
+- **Multiple Output Formats**: JSON and Text
+- **Bounding Boxes**: Precise text positioning information
+- **Standalone Binary**: No cloud dependencies, runs entirely locally
+- **Multi-platform**: Linux, macOS (Intel/ARM), Windows
+
+## Installation
+
+### CLI Tool
+
+#### Option 1: Global Install (Recommended)
+
+Install globally via npm to use the `lit` command anywhere:
+
+```bash
+npm i -g @llamaindex/liteparse
+```
+
+Then use it:
+
+```bash
+lit parse document.pdf
+lit screenshot document.pdf
+```
+
+For macOS and Linux users, `liteparse` can be also installed via `brew`:
+
+```bash
+brew tap run-llama/liteparse
+brew install llamaindex-liteparse
+```
+
+#### Option 2: Install from Source
+
+You can clone the repo and install the CLI globally from source:
+
+```
+git clone https://github.com/run-llama/liteparse.git
+cd liteparse
+npm run build
+npm pack
+npm install -g ./liteparse-*.tgz
+```
+
+## Usage
+
+### Parse Files
+
+```bash
+# Basic parsing
+lit parse document.pdf
+
+# Parse with specific format
+lit parse document.pdf --format json -o output.md
+
+# Parse specific pages
+lit parse document.pdf --target-pages "1-5,10,15-20"
+
+# Parse without OCR
+lit parse document.pdf --no-ocr
+```
+
+### Batch Parsing
+
+You can also parse an entire directory of documents:
+
+```bash
+lit batch-parse ./input-directory ./output-directory
+```
+
+### Generate Screenshots
+
+Screenshots are essential for LLM agents to extract visual information that text alone cannot capture.
+
+```bash
+# Screenshot all pages
+lit screenshot document.pdf -o ./screenshots
+
+# Screenshot specific pages
+lit screenshot document.pdf --target-pages "1,3,5" -o ./screenshots
+
+# Custom DPI
+lit screenshot document.pdf --dpi 300 -o ./screenshots
+
+# Screenshot page range
+lit screenshot document.pdf --target-pages "1-10" -o ./screenshots
+```
+
+### Library Usage
+
+Install as a dependency in your project:
+
+```bash
+npm install @llamaindex/liteparse
+# or
+pnpm add @llamaindex/liteparse
+```
+
+```typescript
+import { LiteParse } from '@llamaindex/liteparse';
+
+const parser = new LiteParse({ ocrEnabled: true });
+const result = await parser.parse('document.pdf');
+console.log(result.text);
+```
+
+### CLI Options
+
+#### Parse Command
+
+```
+$ lit parse --help
+Usage: lit parse [options] <file>
+
+Parse a document file (PDF, DOCX, XLSX, PPTX, images, etc.)
+
+Options:
+  -o, --output <file>     Output file path
+  --format <format>       Output format: json|text (default: "text")
+  --ocr-server-url <url>  HTTP OCR server URL (uses Tesseract if not provided)
+  --no-ocr                Disable OCR
+  --ocr-language <lang>   OCR language(s) (default: "en")
+  --num-workers <n>       Number of pages to OCR in parallel (default: CPU cores - 1)
+  --max-pages <n>         Max pages to parse (default: "10000")
+  --target-pages <pages>  Target pages (e.g., "1-5,10,15-20")
+  --dpi <dpi>             DPI for rendering (default: "150")
+  --no-precise-bbox       Disable precise bounding boxes
+  --preserve-small-text   Preserve very small text
+  --config <file>         Config file (JSON)
+  -q, --quiet             Suppress progress output
+  -h, --help              display help for command
+```
+
+#### Batch Parse Command
+
+```
+$ lit batch-parse --help
+Usage: lit batch-parse [options] <input-dir> <output-dir>
+
+Parse multiple documents in batch mode (reuses PDF engine for efficiency)
+
+Options:
+  --format <format>       Output format: json|text (default: "text")
+  --ocr-server-url <url>  HTTP OCR server URL (uses Tesseract if not provided)
+  --no-ocr                Disable OCR
+  --ocr-language <lang>   OCR language(s) (default: "en")
+  --num-workers <n>       Number of pages to OCR in parallel (default: CPU cores - 1)
+  --max-pages <n>         Max pages to parse per file (default: "10000")
+  --dpi <dpi>             DPI for rendering (default: "150")
+  --no-precise-bbox       Disable precise bounding boxes
+  --recursive             Recursively search input directory
+  --extension <ext>       Only process files with this extension (e.g., ".pdf")
+  --config <file>         Config file (JSON)
+  -q, --quiet             Suppress progress output
+  -h, --help              display help for command
+```
+
+#### Screenshot Command
+
+```
+$ lit screenshot --help
+Usage: lit screenshot [options] <file>
+
+Generate screenshots of PDF pages
+
+Options:
+  -o, --output-dir <dir>  Output directory for screenshots (default: "./screenshots")
+  --target-pages <pages>  Page numbers to screenshot (e.g., "1,3,5" or "1-5")
+  --dpi <dpi>             DPI for rendering (default: "150")
+  --format <format>       Image format: png|jpg (default: "png")
+  --config <file>         Config file (JSON)
+  -q, --quiet             Suppress progress output
+  -h, --help              display help for command
+```
+
+## OCR Setup
+
+### Default: Tesseract.js
+
+```bash
+# Tesseract is enabled by default
+lit parse document.pdf
+
+# Specify language
+lit parse document.pdf --ocr-language fra
+
+# Disable OCR
+lit parse document.pdf --no-ocr
+```
+
+### Optional: HTTP OCR Servers
+
+For higher accuracy or better performance, you can use an HTTP OCR server. We provide ready-to-use example wrappers for popular OCR engines:
+
+- [EasyOCR](ocr/easyocr/README.md)
+- [PaddleOCR](ocr/paddleocr/README.md)
+
+You can integrate any OCR service by implementing the simple LiteParse OCR API specification (see [`OCR_API_SPEC.md`](OCR_API_SPEC.md)).
+
+The API requires:
+- POST `/ocr` endpoint
+- Accepts `file` and `language` parameters
+- Returns JSON: `{ results: [{ text, bbox: [x1,y1,x2,y2], confidence }] }`
+
+See the example servers in `ocr/easyocr/` and `ocr/paddleocr/` as templates.
+
+For the complete OCR API specification, see [`OCR_API_SPEC.md`](OCR_API_SPEC.md).
+
+## Multi-Format Input Support
+
+LiteParse supports **automatic conversion** of various document formats to PDF before parsing. This makes it unique compared to other PDF-only parsing tools!
+
+### Supported Input Formats
+
+#### Office Documents (via LibreOffice)
+- **Word**: `.doc`, `.docx`, `.docm`, `.odt`, `.rtf`
+- **PowerPoint**: `.ppt`, `.pptx`, `.pptm`, `.odp`
+- **Spreadsheets**: `.xls`, `.xlsx`, `.xlsm`, `.ods`, `.csv`, `.tsv`
+
+Just install the dependency and LiteParse will automatically convert these formats to PDF for parsing:
+
+```bash
+# macOS
+brew install --cask libreoffice
+
+# Ubuntu/Debian
+apt-get install libreoffice
+
+# Windows
+choco install libreoffice-fresh # might require admin permissions
+```
+
+> _For Windows, you might need to add the path to the directory containing LibreOffice CLI executable (generally `C:\Program Files\LibreOffice\program`) to the environment variables and re-start the machine._
+
+#### Images (via ImageMagick)
+- **Formats**: `.jpg`, `.jpeg`, `.png`, `.gif`, `.bmp`, `.tiff`, `.webp`, `.svg`
+
+Just install ImageMagick and LiteParse will convert images to PDF for parsing (with OCR):
+
+```bash
+# macOS
+brew install imagemagick
+
+# Ubuntu/Debian
+apt-get install imagemagick
+
+# Windows
+choco install imagemagick.app # might require admin permissions
+```
+
+## Configuration
+
+You can configure parsing options via CLI flags or a JSON config file. The config file allows you to set sensible defaults and override as needed.
+
+### Config File Example
+
+Create a `liteparse.config.json` file:
+
+```json
+{
+  "ocrLanguage": "en",
+  "ocrEnabled": true,
+  "maxPages": 1000,
+  "dpi": 150,
+  "outputFormat": "json",
+  "preciseBoundingBox": true,
+  "preserveVerySmallText": false
+}
+```
+
+For HTTP OCR servers, just add `ocrServerUrl`:
+
+```json
+{
+  "ocrServerUrl": "http://localhost:8828/ocr",
+  "ocrLanguage": "en",
+  "outputFormat": "json"
+}
+```
+
+Use with:
+
+```bash
+lit parse document.pdf --config liteparse.config.json
+```
+
+## Development
+
+We provide a fairly rich `AGENTS.md`/`CLAUDE.md` that we recommend using to help with development + coding agents.
+
+```bash
+# Install dependencies
+npm install
+
+# Build TypeScript (Linux/macOs)
+npm run build
+
+# Build Typescript (Windows)
+npm run build:windows
+
+# Watch mode
+npm run dev
+
+# Test parsing
+npm test
+```
+
+## License
+
+Apache 2.0
+
+## Credits
+
+Built on top of:
+
+- [PDF.js](https://github.com/mozilla/pdf.js) - PDF parsing engine
+- [Tesseract.js](https://github.com/naptha/tesseract.js) - In-process OCR engine
+- [EasyOCR](https://github.com/JaidedAI/EasyOCR) - HTTP OCR server (optional)
+- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR) - HTTP OCR server (optional)
+- [Sharp](https://github.com/lovell/sharp) - Image processing

package/dist/cli/parse.d.ts

@@ -0,0 +1,4 @@
+import { Command } from "commander";
+declare const program: Command;
+export { program };
+//# sourceMappingURL=parse.d.ts.map

package/dist/cli/parse.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"parse.d.ts","sourceRoot":"","sources":["../../cli/parse.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AAwDpC,QAAA,MAAM,OAAO,SAAgB,CAAC;AA2b9B,OAAO,EAAE,OAAO,EAAE,CAAC"}