any-extractor 2.0.2 → 2.0.4

package/README.md

@@ -4,31 +4,10 @@
 [![License](https://img.shields.io/npm/l/any-extractor)](https://www.npmjs.com/package/any-extractor)
 [![Downloads](https://img.shields.io/npm/dm/any-extractor)](https://www.npmjs.com/package/any-extractor)
 
-A Node.js package to extract text from any file.
-
-> This package is designed for **Node.js only** and does not work in browser environments.
-
-## Table of Contents
-
-- [Features](#features)
-- [Supported Files](#supported-files)
-- [Installation](#installation)
-- [Getting Started](#getting-started)
-- [Advanced Usage](#advanced-usage)
-- [Custom Parsers](#custom-parsers)
-- [Confluence Crawling](#confluence-crawling)
-- [Needs Work](#needs-work)
-- [Contributing](#contributing)
-- [Credits](#credits)
-- [License](#license)
-- [Support](#support)
+A Node.js package to extract text from files.
 
 ## Features
 
-- **Multi-format file support:** Extracts text from a wide range of file types. (See below for list of supported files)
-- **OCR for images:** Uses Optical Character Recognition to extract text from images within documents and standalone image files.
-- **LLM for image description:** Leverages AI to extract images description, providing richer information.
-- **ES6 and CommonJS support:** Supports both modern ES6 and traditional CommonJS JavaScript environments.
 - **Flexible input options:** Supports local file path, buffers, and file URLs.
 - **Auto type detection:** Automatically detects file type and extracts text using MIME type.
 - **Customizable parsers:** Allows creating new or modifying existing document parsers for any MIME types.
@@ -38,43 +17,29 @@ A Node.js package to extract text from any file.
 
 Here's a breakdown of the text extraction capabilities for each file type:
 
-| File Type                                        | Text Extraction | Image Extraction |
-| ------------------------------------------------ | --------------- | ---------------- |
-| `.docx`                                          | ✅              | ✅               |
-| `.pptx`                                          | ✅              | ✅               |
-| `.xlsx`                                          | ✅              | ✅               |
-| `.pdf`                                           | ✅              | ❌               |
-| `.png`                                           | N/A             | ✅               |
-| `.jpg`, `.jpeg`                                  | N/A             | ✅               |
-| `.webp`                                          | N/A             | ✅               |
-| `.odt`                                           | ✅              | ❌               |
-| `.odp`                                           | ✅              | ❌               |
-| `.ods`                                           | ✅              | ❌               |
-| `.csv`                                           | ✅              | N/A              |
-| `.txt`                                           | ✅              | N/A              |
-| `.json`                                          | ✅              | N/A              |
-| Plain text (e.g., `.py`,<br> `.ts`, `.md`, etc.) | ✅              | N/A              |
-| `confluence`                                     | ✅              | ✅               |
+| File Type                                        | Text Extraction |
+| ------------------------------------------------ | --------------- |
+| `.docx`                                          | ✅              |
+| `.pptx`                                          | ✅              |
+| `.xlsx`                                          | ✅              |
+| `.pdf`                                           | ✅              |
+| `.odt`                                           | ✅              |
+| `.odp`                                           | ✅              |
+| `.ods`                                           | ✅              |
+| `.csv`                                           | ✅              |
+| `.txt`                                           | ✅              |
+| `.json`                                          | ✅              |
+| Plain text (e.g., `.py`,<br> `.ts`, `.md`, etc.) | ✅              |
+| `confluence`                                     | ✅              |
 
 ## Installation
 
-This is a Node.js module available through the npm registry.<br>
-To work with this package, Node.js 20 or higher is required.
-
-#### Package Manager
-
-Using npm:
-
 ```bash
 npm install any-extractor
 ```
 
 ## Getting Started
 
-Here's a basic example of how to use AnyExtractor in both ES6 and CommonJS environments:
-
-#### ES6 (using `import`):
-
 ```ts
 import { getAnyExtractor } from 'any-extractor';
 
@@ -87,64 +52,8 @@ async function extractFromFile() {
 extractFromFile();
 ```
 
-#### CommonJS (using `require`):
-
-```ts
-const { getAnyExtractor } = require('any-extractor');
-
-async function extractFromFile() {
-  const textExt = getAnyExtractor();
-  const result = await textExt.parseFile('./filename.docx');
-  console.log(result);
-}
-
-extractFromFile();
-```
-
 ## Advanced Usage
 
-#### Parsing Images:
-
-AnyExtractor provides two primary methods for extracting text from images.
-
-1. Optical Character Recognition (OCR):<br>
-
-   ```ts
-   const anyExt = getAnyExtractor();
-
-   const text = await anyExt.parseFile('./imgfile.png', null, {
-     extractImages: true,
-     imageExtractionMethod: 'ocr',
-     language: 'eng',
-   });
-
-   console.log('Extracted Text:', text);
-   ```
-
-2. Using LLM:<br>
-
-   ```ts
-   const anyExt = getAnyExtractor({
-     llmProvider: 'google',
-     visionModel: 'gemini-2.0-flash',
-     apikey: '<your-api-key>',
-   });
-
-   const text = await anyExt.parseFile('./imgfile.png', null, {
-     extractImages: true,
-     imageExtractionMethod: 'llm',
-     language: 'eng',
-   });
-
-   console.log('Extracted Text:', text);
-   ```
-
-> Llm parsing supports `openai`, `google` and `anthropic` llmProvider for now. But you can always overwrite the image parser implementation with your code.
-
-> Optional argument of methods `getAnyExtractor` and `parseFile` are required for the extractor to parse images. Otherwise it will return empty string.
-
-> Image parsing also works other files, e.g., .docx, .pptx etc (see the table above).
-
 #### Authorization Parameter
 
 The second argument in `parseFile`, shown as `null`, is for Basic Authentication when accessing file URLs. Format: `Basic <base64-encoded-credentials>`
@@ -177,12 +86,7 @@ import { AnyParserMethod } from 'any-extractor';
 export class CustomParser implements AnyParserMethod {
   public mimes = ['application/hdb', 'application/sql'];
 
-  public apply = async (
-    file: Buffer,
-    mimeType: string,
-    extractingOptions: ExtractingOptions,
-    extractorConfig: ExtractorConfig,
-  ): Promise<string> => {
+  public apply = async (file: Buffer, extractorConfig: ExtractorConfig): Promise<string> => {
     // your text extraction logic
   };
 }
@@ -208,11 +112,6 @@ const { getAnyExtractor } = require('any-extractor');
 
 async function crawlConfluence() {
   const textExt = getAnyExtractor({
-    llm: {
-      llmProvider: 'google',
-      visionModel: 'gemini-2.0-flash',
-      apikey: '<your-api-key>',
-    },
     confluence: {
       baseUrl: '<baseurl>',
       email: '<username>',
@@ -220,39 +119,12 @@ async function crawlConfluence() {
     },
   });
 
-  const result = await textExt.parseConfluenceDoc('<pageId>', {
-    extractAttachments: true,
-    extractImages: false,
-    imageExtractionMethod: 'ocr',
-    language: 'eng',
-  });
+  const result = await textExt.parseConfluenceDoc('<pageId>');
 }
 
 crawlConfluence();
 ```
 
-## Needs Work
-
-1. `.pdf` and `OpenOffice` files doesn't support image extraction.
-2. `.xlsx` parsing isn't well structured and ordered.
-3. Doesn't support text extraction from web and compressed files.
-
-## Changelog
-
-This project uses [semantic-release](https://github.com/semantic-release/semantic-release) for automated versioning and changelog generation. See the [Releases](https://github.com/pranit-sh/any-extractor/releases) section for details.
-
-## Contributing
-
-Contributions are welcome! Please follow the [Conventional Commits](https://www.conventionalcommits.org/) style when committing changes.
-
-1. Fork the repository
-2. Create your feature branch (`git checkout -b feat/my-feature`)
-3. Commit your changes
-4. Push to the branch
-5. Open a Pull Request
-
-> Pre-commit hooks will run linting and formatting checks automatically.
-
 ## Credits
 
 **any-extractor** is inspired from [officeparser](https://www.npmjs.com/package/officeparser) and it uses [tesseract.js](https://www.npmjs.com/package/tesseract.js)<br>

package/dist/index.d.mts

@@ -1,35 +1,18 @@
 type AnyParserMethod = {
     mimes: string[];
-    apply: (_: Buffer, ___: ExtractingOptions, ____: ExtractorConfig) => Promise<string>;
+    apply: (_: Buffer, ____: ExtractorConfig) => Promise<string>;
 };
 type ExtractedFile = {
     path: string;
     content: Buffer;
 };
 type ExtractorConfig = {
-    llm?: {
-        llmProvider: 'openai' | 'google' | 'anthropic';
-        visionModel: string;
-        apikey: string;
-    };
     confluence?: {
         baseUrl: string;
         email: string;
         apiKey: string;
     };
 };
-type ExtractingOptions = {
-    extractImages: boolean;
-    imageExtractionMethod: 'llm' | 'ocr';
-    language: SupportedOCRLanguage;
-};
-type ConfluenceOptions = {
-    extractAttachments: boolean;
-    extractImages: boolean;
-    imageExtractionMethod: 'llm' | 'ocr';
-    language: SupportedOCRLanguage;
-};
-type SupportedOCRLanguage = 'afr' | 'amh' | 'ara' | 'asm' | 'aze' | 'aze_cyrl' | 'bel' | 'ben' | 'bod' | 'bos' | 'bul' | 'cat' | 'ceb' | 'ces' | 'chi_sim' | 'chi_tra' | 'chr' | 'cym' | 'dan' | 'deu' | 'dzo' | 'ell' | 'eng' | 'enm' | 'epo' | 'est' | 'eus' | 'fas' | 'fin' | 'fra' | 'frk' | 'frm' | 'gle' | 'glg' | 'grc' | 'guj' | 'hat' | 'heb' | 'hin' | 'hrv' | 'hun' | 'iku' | 'ind' | 'isl' | 'ita' | 'ita_old' | 'jav' | 'jpn' | 'kan' | 'kat' | 'kat_old' | 'kaz' | 'khm' | 'kir' | 'kor' | 'kur' | 'lao' | 'lat' | 'lav' | 'lit' | 'mal' | 'mar' | 'mkd' | 'mlt' | 'msa' | 'mya' | 'nep' | 'nld' | 'nor' | 'ori' | 'pan' | 'pol' | 'por' | 'pus' | 'ron' | 'rus' | 'san' | 'sin' | 'slk' | 'slv' | 'spa' | 'spa_old' | 'sqi' | 'srp' | 'srp_latn' | 'swa' | 'swe' | 'syr' | 'tam' | 'tel' | 'tgk' | 'tgl' | 'tha' | 'tir' | 'tur' | 'uig' | 'ukr' | 'urd' | 'uzb' | 'uzb_cyrl' | 'vie' | 'yid';
 type ExtractedXmlItem = {
     type: string;
     content: string;
@@ -40,8 +23,8 @@ declare class AnyExtractor {
     constructor(extractorConfig?: ExtractorConfig);
     private mimeParserMap;
     addParser: (method: AnyParserMethod) => this;
-    parseFile: (input: string | Buffer, basicAuth?: string | null, extractingOptions?: ExtractingOptions) => Promise<string>;
-    parseConfluenceDoc: (pageId: string, extractingOptions?: ConfluenceOptions) => Promise<string>;
+    parseFile: (input: string | Buffer, basicAuth?: string | null) => Promise<string>;
+    parseConfluenceDoc: (pageId: string) => Promise<string>;
 }
 
 /**
@@ -52,4 +35,4 @@ declare class AnyExtractor {
  */
 declare const getAnyExtractor: (config?: ExtractorConfig) => AnyExtractor;
 
-export { type AnyParserMethod, type ConfluenceOptions, type ExtractedFile, type ExtractedXmlItem, type ExtractingOptions, type ExtractorConfig, type SupportedOCRLanguage, getAnyExtractor };
+export { type AnyParserMethod, type ExtractedFile, type ExtractedXmlItem, type ExtractorConfig, getAnyExtractor };

package/dist/index.d.ts

@@ -1,35 +1,18 @@
 type AnyParserMethod = {
     mimes: string[];
-    apply: (_: Buffer, ___: ExtractingOptions, ____: ExtractorConfig) => Promise<string>;
+    apply: (_: Buffer, ____: ExtractorConfig) => Promise<string>;
 };
 type ExtractedFile = {
     path: string;
     content: Buffer;
 };
 type ExtractorConfig = {
-    llm?: {
-        llmProvider: 'openai' | 'google' | 'anthropic';
-        visionModel: string;
-        apikey: string;
-    };
     confluence?: {
         baseUrl: string;
         email: string;
         apiKey: string;
     };
 };
-type ExtractingOptions = {
-    extractImages: boolean;
-    imageExtractionMethod: 'llm' | 'ocr';
-    language: SupportedOCRLanguage;
-};
-type ConfluenceOptions = {
-    extractAttachments: boolean;
-    extractImages: boolean;
-    imageExtractionMethod: 'llm' | 'ocr';
-    language: SupportedOCRLanguage;
-};
-type SupportedOCRLanguage = 'afr' | 'amh' | 'ara' | 'asm' | 'aze' | 'aze_cyrl' | 'bel' | 'ben' | 'bod' | 'bos' | 'bul' | 'cat' | 'ceb' | 'ces' | 'chi_sim' | 'chi_tra' | 'chr' | 'cym' | 'dan' | 'deu' | 'dzo' | 'ell' | 'eng' | 'enm' | 'epo' | 'est' | 'eus' | 'fas' | 'fin' | 'fra' | 'frk' | 'frm' | 'gle' | 'glg' | 'grc' | 'guj' | 'hat' | 'heb' | 'hin' | 'hrv' | 'hun' | 'iku' | 'ind' | 'isl' | 'ita' | 'ita_old' | 'jav' | 'jpn' | 'kan' | 'kat' | 'kat_old' | 'kaz' | 'khm' | 'kir' | 'kor' | 'kur' | 'lao' | 'lat' | 'lav' | 'lit' | 'mal' | 'mar' | 'mkd' | 'mlt' | 'msa' | 'mya' | 'nep' | 'nld' | 'nor' | 'ori' | 'pan' | 'pol' | 'por' | 'pus' | 'ron' | 'rus' | 'san' | 'sin' | 'slk' | 'slv' | 'spa' | 'spa_old' | 'sqi' | 'srp' | 'srp_latn' | 'swa' | 'swe' | 'syr' | 'tam' | 'tel' | 'tgk' | 'tgl' | 'tha' | 'tir' | 'tur' | 'uig' | 'ukr' | 'urd' | 'uzb' | 'uzb_cyrl' | 'vie' | 'yid';
 type ExtractedXmlItem = {
     type: string;
     content: string;
@@ -40,8 +23,8 @@ declare class AnyExtractor {
     constructor(extractorConfig?: ExtractorConfig);
     private mimeParserMap;
     addParser: (method: AnyParserMethod) => this;
-    parseFile: (input: string | Buffer, basicAuth?: string | null, extractingOptions?: ExtractingOptions) => Promise<string>;
-    parseConfluenceDoc: (pageId: string, extractingOptions?: ConfluenceOptions) => Promise<string>;
+    parseFile: (input: string | Buffer, basicAuth?: string | null) => Promise<string>;
+    parseConfluenceDoc: (pageId: string) => Promise<string>;
 }
 
 /**
@@ -52,4 +35,4 @@ declare class AnyExtractor {
  */
 declare const getAnyExtractor: (config?: ExtractorConfig) => AnyExtractor;
 
-export { type AnyParserMethod, type ConfluenceOptions, type ExtractedFile, type ExtractedXmlItem, type ExtractingOptions, type ExtractorConfig, type SupportedOCRLanguage, getAnyExtractor };
+export { type AnyParserMethod, type ExtractedFile, type ExtractedXmlItem, type ExtractorConfig, getAnyExtractor };