@llamaindex/liteparse 1.5.2 → 2.0.0-beta.0

package/README.md

@@ -1,412 +1,89 @@
-# LiteParse
+# LiteParse Node.js
 
-[![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)
-|
-[Docs](https://developers.llamaindex.ai/liteparse/)
-
-<img src="https://github.com/user-attachments/assets/07ba6a82-6bb1-4dea-b0ef-cad7df7d1622" alt="out" width="600">
-
-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. 
-
-**Hitting the limits of local parsing?**
-For complex documents (dense tables, multi-column layouts, charts, handwritten text, or 
-scanned PDFs), you'll get significantly better results with [LlamaParse](https://developers.llamaindex.ai/python/cloud/llamaparse/?utm_source=github&utm_medium=liteparse), 
-our cloud-based document parser built for production document pipelines. LlamaParse handles the 
-hard stuff so your models see clean, structured data and markdown.
-
->  👉 [Sign up for LlamaParse free](https://cloud.llamaindex.ai?utm_source=github&utm_medium=liteparse)
-
-## Overview
-
-- **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
+Node.js/TypeScript bindings for [LiteParse](https://github.com/run-llama/liteparse) — fast, lightweight PDF and document parsing with spatial text extraction.
 
 ## 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
-```
-
-### Agent Skill
-
-You can use `liteparse` as an agent skill, downloading it with the `skills` CLI tool:
-
-```bash
-npx skills add run-llama/llamaparse-agent-skills --skill liteparse
-```
-
-Or copy-pasting the [`SKILL.md`](https://github.com/run-llama/llamaparse-agent-skills/blob/main/skills/liteparse/SKILL.md) file to your own skills setup.
-
-## 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
-
-# Parse a remote PDF
-curl -sL https://example.com/report.pdf | lit parse -
-```
-
-### Batch Parsing
-
-You can also parse an entire directory of documents:
-
 ```bash
-lit batch-parse ./input-directory ./output-directory
+npm i @llamaindex/liteparse
 ```
 
-### Generate Screenshots
+This also installs the `lit` CLI command (use `npm i -g` for global access).
 
-Screenshots are essential for LLM agents to extract visual information that text alone cannot capture.
+## Quick Start
 
-```bash
-# Screenshot all pages
-lit screenshot document.pdf -o ./screenshots
-
-# Screenshot specific pages
-lit screenshot document.pdf --target-pages "1,3,5" -o ./screenshots
+```typescript
+import { LiteParse } from '@llamaindex/liteparse';
 
-# Custom DPI
-lit screenshot document.pdf --dpi 300 -o ./screenshots
+const parser = new LiteParse();
+const result = await parser.parse('document.pdf');
+console.log(result.text);
 
-# Screenshot page range
-lit screenshot document.pdf --target-pages "1-10" -o ./screenshots
+// Access structured data
+for (const page of result.pages) {
+  console.log(`Page ${page.pageNum}: ${page.textItems.length} text items`);
+}
 ```
 
-### Library Usage
-
-Install as a dependency in your project:
+## Configuration
 
-```bash
-npm install @llamaindex/liteparse
-# or
-pnpm add @llamaindex/liteparse
-```
+All options are passed to the constructor:
 
 ```typescript
-import { LiteParse } from '@llamaindex/liteparse';
-
-const parser = new LiteParse({ ocrEnabled: true });
-const result = await parser.parse('document.pdf');
-console.log(result.text);
+const parser = new LiteParse({
+  ocrEnabled: true,              // Enable OCR (default: true)
+  ocrLanguage: 'eng',           // Tesseract language code
+  ocrServerUrl: undefined,       // HTTP OCR server URL (optional)
+  tessdataPath: undefined,       // Path to tessdata directory (optional)
+  maxPages: 1000,                // Max pages to parse
+  targetPages: '1-5,10',        // Specific pages (optional)
+  dpi: 150,                      // Rendering DPI
+  preserveVerySmallText: false,  // Keep tiny text
+  password: undefined,           // Password for protected documents
+  quiet: false,                  // Suppress progress output
+  numWorkers: 4,                 // Concurrent OCR workers
+});
 ```
 
-#### Buffer / Uint8Array Input
+## Parsing from Bytes
 
-You can pass raw bytes directly instead of a file path, which is useful for remote files:
+Pass a `Buffer` or `Uint8Array` directly — useful for HTTP responses or in-memory data:
 
 ```typescript
-import { LiteParse } from '@llamaindex/liteparse';
 import { readFile } from 'fs/promises';
 
-const parser = new LiteParse();
-
-// From a file read
 const pdfBytes = await readFile('document.pdf');
 const result = await parser.parse(pdfBytes);
-
-// From an HTTP response
-const response = await fetch('https://example.com/document.pdf');
-const buffer = Buffer.from(await response.arrayBuffer());
-const result2 = await parser.parse(buffer);
-```
-
-Non-PDF buffers (images, Office documents) are written to a temp directory for format conversion. Screenshots also work with buffer input:
-
-```typescript
-const screenshots = await parser.screenshot(pdfBytes, [1, 2, 3]);
-```
-
-### 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
-  --password <password>   Password for encrypted/protected documents
-  --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")
-  --password <password>   Password for encrypted/protected documents (applied to all files)
-  --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")
-  --password <password>   Password for encrypted/protected documents
-  --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
+console.log(result.text);
 ```
 
-By default, Tesseract.js downloads language data from the internet on first use. For offline or air-gapped environments, set the `TESSDATA_PREFIX` environment variable to a directory containing pre-downloaded `.traineddata` files:
-
-```bash
-export TESSDATA_PREFIX=/path/to/tessdata
-lit parse document.pdf --ocr-language eng
-```
+## Screenshots
 
-You can also pass `tessdataPath` in the library config:
+Generate PNG screenshots of document pages:
 
 ```typescript
-const parser = new LiteParse({ tessdataPath: '/path/to/tessdata' });
-```
-
-### 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
-```
-
-## Environment Variables
-
-| Variable | Description |
-|----------|-------------|
-| `TESSDATA_PREFIX` | Path to a directory containing Tesseract `.traineddata` files. Used for offline/air-gapped environments where Tesseract.js cannot download language data from the internet. |
-| `LITEPARSE_TMPDIR` | Override the temp directory used for format conversion and intermediate files. Defaults to the OS temp directory (`os.tmpdir()`). Useful in containerized or read-only filesystem environments. |
-
-## 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,
-  "password": "optional_password"
+const screenshots = parser.screenshot('document.pdf', [1, 2, 3]);
+for (const s of screenshots) {
+  console.log(`Page ${s.pageNum}: ${s.width}x${s.height}`);
+  // s.imageBuffer contains PNG bytes
 }
 ```
 
-For HTTP OCR servers, just add `ocrServerUrl`:
+## Supported Formats
 
-```json
-{
-  "ocrServerUrl": "http://localhost:8828/ocr",
-  "ocrLanguage": "en",
-  "outputFormat": "json"
-}
-```
+- PDF (`.pdf`)
+- Microsoft Office (`.docx`, `.xlsx`, `.pptx`, etc.) — requires LibreOffice
+- OpenDocument (`.odt`, `.ods`, `.odp`) — requires LibreOffice
+- Images (`.png`, `.jpg`, `.tiff`, etc.) — requires ImageMagick
+- And more!
 
-Use with:
+## CLI
 
-```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.
+The npm package includes the `lit` CLI:
 
 ```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
+lit parse document.pdf
+lit parse document.pdf --format json -o output.json
+lit screenshot document.pdf -o ./screenshots
+lit batch-parse ./input ./output
 ```
-
-## 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.d.ts

@@ -0,0 +1,3 @@
+#!/usr/bin/env node
+export {};
+//# sourceMappingURL=cli.d.ts.map

package/dist/cli.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"cli.d.ts","sourceRoot":"","sources":["../src/cli.ts"],"names":[],"mappings":""}

package/dist/cli.js

@@ -0,0 +1,87 @@
+#!/usr/bin/env node
+import { program } from "commander";
+import { LiteParse } from "./lib.js";
+import { readFileSync } from "node:fs";
+import { writeFileSync } from "node:fs";
+program
+    .name("liteparse")
+    .description("Fast, lightweight PDF and document parsing")
+    .version("2.0.0");
+program
+    .command("parse")
+    .description("Parse a document and extract text")
+    .argument("<file>", "Path to the document file")
+    .option("-o, --output <file>", "Output file path")
+    .option("--format <format>", 'Output format: json|text (default: "text")')
+    .option("--ocr-server-url <url>", "HTTP OCR server URL")
+    .option("--no-ocr", "Disable OCR")
+    .option("--ocr-language <lang>", "OCR language (default: eng)")
+    .option("--max-pages <n>", "Max pages to parse", parseInt)
+    .option("--target-pages <pages>", 'Pages to parse (e.g., "1-5,10,15-20")')
+    .option("--dpi <dpi>", "Rendering DPI", parseFloat)
+    .option("--preserve-small-text", "Keep very small text")
+    .option("--password <password>", "Password for encrypted documents")
+    .option("--config <file>", "JSON config file path")
+    .option("-q, --quiet", "Suppress progress output")
+    .option("--num-workers <n>", "Number of concurrent OCR workers", parseInt)
+    .action(async (file, opts) => {
+    try {
+        const config = {};
+        // Load config file if provided
+        if (opts.config) {
+            const fileConfig = JSON.parse(readFileSync(opts.config, "utf-8"));
+            Object.assign(config, fileConfig);
+        }
+        // CLI options override config file
+        if (opts.format)
+            config.outputFormat = opts.format;
+        if (opts.ocrServerUrl)
+            config.ocrServerUrl = opts.ocrServerUrl;
+        if (opts.ocr === false)
+            config.ocrEnabled = false;
+        if (opts.ocrLanguage)
+            config.ocrLanguage = opts.ocrLanguage;
+        if (opts.maxPages)
+            config.maxPages = opts.maxPages;
+        if (opts.targetPages)
+            config.targetPages = opts.targetPages;
+        if (opts.dpi)
+            config.dpi = opts.dpi;
+        if (opts.preserveSmallText)
+            config.preserveVerySmallText = true;
+        if (opts.password)
+            config.password = opts.password;
+        if (opts.quiet)
+            config.quiet = true;
+        if (opts.numWorkers)
+            config.numWorkers = opts.numWorkers;
+        // Default CLI output to text (library defaults to json)
+        if (!config.outputFormat)
+            config.outputFormat = "text";
+        const parser = new LiteParse(config);
+        const result = await parser.parse(file);
+        const output = config.outputFormat === "json"
+            ? JSON.stringify({
+                pages: result.pages.map((p) => ({
+                    page: p.pageNum,
+                    width: p.width,
+                    height: p.height,
+                    text: p.text,
+                    textItems: p.textItems,
+                })),
+            }, null, 2)
+            : result.text;
+        if (opts.output) {
+            writeFileSync(opts.output, output, "utf-8");
+        }
+        else {
+            process.stdout.write(output);
+        }
+    }
+    catch (err) {
+        console.error(`Error: ${err instanceof Error ? err.message : String(err)}`);
+        process.exit(1);
+    }
+});
+program.parse(process.argv);
+//# sourceMappingURL=cli.js.map

package/dist/cli.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"cli.js","sourceRoot":"","sources":["../src/cli.ts"],"names":[],"mappings":";AAEA,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AACpC,OAAO,EAAE,SAAS,EAAwB,MAAM,UAAU,CAAC;AAC3D,OAAO,EAAE,YAAY,EAAE,MAAM,SAAS,CAAC;AACvC,OAAO,EAAE,aAAa,EAAE,MAAM,SAAS,CAAC;AAExC,OAAO;KACJ,IAAI,CAAC,WAAW,CAAC;KACjB,WAAW,CAAC,4CAA4C,CAAC;KACzD,OAAO,CAAC,OAAO,CAAC,CAAC;AAEpB,OAAO;KACJ,OAAO,CAAC,OAAO,CAAC;KAChB,WAAW,CAAC,mCAAmC,CAAC;KAChD,QAAQ,CAAC,QAAQ,EAAE,2BAA2B,CAAC;KAC/C,MAAM,CAAC,qBAAqB,EAAE,kBAAkB,CAAC;KACjD,MAAM,CAAC,mBAAmB,EAAE,4CAA4C,CAAC;KACzE,MAAM,CAAC,wBAAwB,EAAE,qBAAqB,CAAC;KACvD,MAAM,CAAC,UAAU,EAAE,aAAa,CAAC;KACjC,MAAM,CAAC,uBAAuB,EAAE,6BAA6B,CAAC;KAC9D,MAAM,CAAC,iBAAiB,EAAE,oBAAoB,EAAE,QAAQ,CAAC;KACzD,MAAM,CACL,wBAAwB,EACxB,uCAAuC,CACxC;KACA,MAAM,CAAC,aAAa,EAAE,eAAe,EAAE,UAAU,CAAC;KAClD,MAAM,CAAC,uBAAuB,EAAE,sBAAsB,CAAC;KACvD,MAAM,CAAC,uBAAuB,EAAE,kCAAkC,CAAC;KACnE,MAAM,CAAC,iBAAiB,EAAE,uBAAuB,CAAC;KAClD,MAAM,CAAC,aAAa,EAAE,0BAA0B,CAAC;KACjD,MAAM,CAAC,mBAAmB,EAAE,kCAAkC,EAAE,QAAQ,CAAC;KACzE,MAAM,CAAC,KAAK,EAAE,IAAY,EAAE,IAA6B,EAAE,EAAE;IAC5D,IAAI,CAAC;QACH,MAAM,MAAM,GAA6B,EAAE,CAAC;QAE5C,+BAA+B;QAC/B,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC;YAChB,MAAM,UAAU,GAAG,IAAI,CAAC,KAAK,CAC3B,YAAY,CAAC,IAAI,CAAC,MAAgB,EAAE,OAAO,CAAC,CAC7C,CAAC;YACF,MAAM,CAAC,MAAM,CAAC,MAAM,EAAE,UAAU,CAAC,CAAC;QACpC,CAAC;QAED,mCAAmC;QACnC,IAAI,IAAI,CAAC,MAAM;YAAE,MAAM,CAAC,YAAY,GAAG,IAAI,CAAC,MAAyB,CAAC;QACtE,IAAI,IAAI,CAAC,YAAY;YACnB,MAAM,CAAC,YAAY,GAAG,IAAI,CAAC,YAAsB,CAAC;QACpD,IAAI,IAAI,CAAC,GAAG,KAAK,KAAK;YAAE,MAAM,CAAC,UAAU,GAAG,KAAK,CAAC;QAClD,IAAI,IAAI,CAAC,WAAW;YAAE,MAAM,CAAC,WAAW,GAAG,IAAI,CAAC,WAAqB,CAAC;QACtE,IAAI,IAAI,CAAC,QAAQ;YAAE,MAAM,CAAC,QAAQ,GAAG,IAAI,CAAC,QAAkB,CAAC;QAC7D,IAAI,IAAI,CAAC,WAAW;YAAE,MAAM,CAAC,WAAW,GAAG,IAAI,CAAC,WAAqB,CAAC;QACtE,IAAI,IAAI,CAAC,GAAG;YAAE,MAAM,CAAC,GAAG,GAAG,IAAI,CAAC,GAAa,CAAC;QAC9C,IAAI,IAAI,CAAC,iBAAiB;YAAE,MAAM,CAAC,qBAAqB,GAAG,IAAI,CAAC;QAChE,IAAI,IAAI,CAAC,QAAQ;YAAE,MAAM,CAAC,QAAQ,GAAG,IAAI,CAAC,QAAkB,CAAC;QAC7D,IAAI,IAAI,CAAC,KAAK;YAAE,MAAM,CAAC,KAAK,GAAG,IAAI,CAAC;QACpC,IAAI,IAAI,CAAC,UAAU;YAAE,MAAM,CAAC,UAAU,GAAG,IAAI,CAAC,UAAoB,CAAC;QAEnE,wDAAwD;QACxD,IAAI,CAAC,MAAM,CAAC,YAAY;YAAE,MAAM,CAAC,YAAY,GAAG,MAAM,CAAC;QAEvD,MAAM,MAAM,GAAG,IAAI,SAAS,CAAC,MAAM,CAAC,CAAC;QACrC,MAAM,MAAM,GAAG,MAAM,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QAExC,MAAM,MAAM,GACV,MAAM,CAAC,YAAY,KAAK,MAAM;YAC5B,CAAC,CAAC,IAAI,CAAC,SAAS,CACZ;gBACE,KAAK,EAAE,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC;oBAC9B,IAAI,EAAE,CAAC,CAAC,OAAO;oBACf,KAAK,EAAE,CAAC,CAAC,KAAK;oBACd,MAAM,EAAE,CAAC,CAAC,MAAM;oBAChB,IAAI,EAAE,CAAC,CAAC,IAAI;oBACZ,SAAS,EAAE,CAAC,CAAC,SAAS;iBACvB,CAAC,CAAC;aACJ,EACD,IAAI,EACJ,CAAC,CACF;YACH,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC;QAElB,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC;YAChB,aAAa,CAAC,IAAI,CAAC,MAAgB,EAAE,MAAM,EAAE,OAAO,CAAC,CAAC;QACxD,CAAC;aAAM,CAAC;YACN,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC;QAC/B,CAAC;IACH,CAAC;IAAC,OAAO,GAAG,EAAE,CAAC;QACb,OAAO,CAAC,KAAK,CACX,UAAU,GAAG,YAAY,KAAK,CAAC,CAAC,CAAC,GAAG,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,EAAE,CAC7D,CAAC;QACF,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IAClB,CAAC;AACH,CAAC,CAAC,CAAC;AAEL,OAAO,CAAC,KAAK,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC"}

package/dist/lib.d.ts

@@ -0,0 +1,58 @@
+export type LiteParseInput = string | Buffer | Uint8Array;
+export type OutputFormat = "json" | "text";
+export interface LiteParseConfig {
+    ocrLanguage: string;
+    ocrEnabled: boolean;
+    ocrServerUrl?: string;
+    tessdataPath?: string;
+    maxPages: number;
+    targetPages?: string;
+    dpi: number;
+    outputFormat: OutputFormat;
+    preserveVerySmallText: boolean;
+    password?: string;
+    quiet: boolean;
+    numWorkers: number;
+}
+export interface TextItem {
+    text: string;
+    x: number;
+    y: number;
+    width: number;
+    height: number;
+    fontName?: string;
+    fontSize?: number;
+    confidence?: number;
+}
+export interface ParsedPage {
+    pageNum: number;
+    width: number;
+    height: number;
+    text: string;
+    textItems: TextItem[];
+}
+export interface ParseResult {
+    pages: ParsedPage[];
+    text: string;
+}
+export interface ScreenshotResult {
+    pageNum: number;
+    width: number;
+    height: number;
+    imageBuffer: Buffer;
+}
+export declare class LiteParse {
+    private _native;
+    private _config;
+    constructor(userConfig?: Partial<LiteParseConfig>);
+    parse(input: LiteParseInput): Promise<ParseResult>;
+    screenshot(input: string, pageNumbers?: number[]): ScreenshotResult[];
+    getConfig(): LiteParseConfig;
+}
+export interface SearchItemsOptions {
+    phrase: string;
+    caseSensitive?: boolean;
+}
+export declare function searchItems(items: TextItem[], options: SearchItemsOptions): TextItem[];
+export default LiteParse;
+//# sourceMappingURL=lib.d.ts.map

package/dist/lib.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"lib.d.ts","sourceRoot":"","sources":["../src/lib.ts"],"names":[],"mappings":"AAaA,MAAM,MAAM,cAAc,GAAG,MAAM,GAAG,MAAM,GAAG,UAAU,CAAC;AAC1D,MAAM,MAAM,YAAY,GAAG,MAAM,GAAG,MAAM,CAAC;AAE3C,MAAM,WAAW,eAAe;IAC9B,WAAW,EAAE,MAAM,CAAC;IACpB,UAAU,EAAE,OAAO,CAAC;IACpB,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,QAAQ,EAAE,MAAM,CAAC;IACjB,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,GAAG,EAAE,MAAM,CAAC;IACZ,YAAY,EAAE,YAAY,CAAC;IAC3B,qBAAqB,EAAE,OAAO,CAAC;IAC/B,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,KAAK,EAAE,OAAO,CAAC;IACf,UAAU,EAAE,MAAM,CAAC;CACpB;AAED,MAAM,WAAW,QAAQ;IACvB,IAAI,EAAE,MAAM,CAAC;IACb,CAAC,EAAE,MAAM,CAAC;IACV,CAAC,EAAE,MAAM,CAAC;IACV,KAAK,EAAE,MAAM,CAAC;IACd,MAAM,EAAE,MAAM,CAAC;IACf,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,UAAU,CAAC,EAAE,MAAM,CAAC;CACrB;AAED,MAAM,WAAW,UAAU;IACzB,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,MAAM,EAAE,MAAM,CAAC;IACf,IAAI,EAAE,MAAM,CAAC;IACb,SAAS,EAAE,QAAQ,EAAE,CAAC;CACvB;AAED,MAAM,WAAW,WAAW;IAC1B,KAAK,EAAE,UAAU,EAAE,CAAC;IACpB,IAAI,EAAE,MAAM,CAAC;CACd;AAED,MAAM,WAAW,gBAAgB;IAC/B,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,MAAM,EAAE,MAAM,CAAC;IACf,WAAW,EAAE,MAAM,CAAC;CACrB;AAMD,qBAAa,SAAS;IACpB,OAAO,CAAC,OAAO,CAAkB;IACjC,OAAO,CAAC,OAAO,CAAkB;gBAErB,UAAU,GAAE,OAAO,CAAC,eAAe,CAAM;IAoC/C,KAAK,CAAC,KAAK,EAAE,cAAc,GAAG,OAAO,CAAC,WAAW,CAAC;IAWxD,UAAU,CACR,KAAK,EAAE,MAAM,EACb,WAAW,CAAC,EAAE,MAAM,EAAE,GACrB,gBAAgB,EAAE;IASrB,SAAS,IAAI,eAAe;CAG7B;AA6BD,MAAM,WAAW,kBAAkB;IACjC,MAAM,EAAE,MAAM,CAAC;IACf,aAAa,CAAC,EAAE,OAAO,CAAC;CACzB;AAED,wBAAgB,WAAW,CACzB,KAAK,EAAE,QAAQ,EAAE,EACjB,OAAO,EAAE,kBAAkB,GAC1B,QAAQ,EAAE,CAOZ;AAED,eAAe,SAAS,CAAC"}