@d0paminedriven/pdfdown-ocr 0.8.0 → 0.9.1

package/README.md

@@ -0,0 +1,268 @@
+# `@d0paminedriven/pdfdown-ocr`
+
+Rust-powered PDF extraction for Node.js with Tesseract OCR fallback for image-only pages. A superset of [`@d0paminedriven/pdfdown`](https://www.npmjs.com/package/@d0paminedriven/pdfdown) -- includes all base extraction APIs (text, images, annotations, structured text, metadata) plus OCR.
+
+**System requirement:** [Tesseract](https://github.com/tesseract-ocr/tesseract) 5.x must be installed on the host.
+
+## Install
+
+```bash
+npm install @d0paminedriven/pdfdown-ocr
+```
+
+### Tesseract setup
+
+```bash
+# Ubuntu/Debian (22.04 ships tesseract 3.x -- use the PPA for 5.x)
+sudo add-apt-repository ppa:alex-p/tesseract-ocr5
+sudo apt update
+sudo apt install tesseract-ocr tesseract-ocr-eng -y
+# Optional: all language packs
+# sudo apt install tesseract-ocr-all
+
+# macOS
+brew install tesseract
+
+# Arch
+sudo pacman -S tesseract tesseract-data-eng
+```
+
+Verify with `tesseract --version` -- you should see 5.x.
+
+### Tessdata auto-detection
+
+The package automatically detects the tessdata directory at runtime by parsing the output of `tesseract --list-langs`. The detected path is cached for the lifetime of the process using a `OnceLock<Option<String>>` -- no global environment mutation, fully thread-safe.
+
+**Resolution order:**
+
+1. `TESSDATA_PREFIX` environment variable (if set, used as-is -- no auto-detection runs)
+2. Auto-detection via `tesseract --list-langs` (parses the path from `List of available languages in "/path/to/tessdata/"`)
+3. Tesseract's compiled-in default (if neither of the above yields a path)
+
+Most users will not need to set `TESSDATA_PREFIX` at all. The auto-detection handles standard installations on Ubuntu (`/usr/share/tesseract-ocr/5/tessdata/`), macOS Homebrew (`/opt/homebrew/share/tessdata/`), Arch, and any other layout where `tesseract` is on `PATH`.
+
+Set `TESSDATA_PREFIX` explicitly only if:
+
+- Tesseract is not on `PATH` but the tessdata directory exists elsewhere
+- You want to override the detected path (e.g., pointing to a custom-trained data directory)
+
+```bash
+# Override example (not usually needed)
+export TESSDATA_PREFIX="/opt/custom/tessdata"
+```
+
+## API
+
+This package exports everything from `@d0paminedriven/pdfdown` (text, images, annotations, structured text, metadata -- both sync and async), plus the OCR-specific APIs below. See the [base package docs](https://www.npmjs.com/package/@d0paminedriven/pdfdown) for the full base API.
+
+### OCR standalone functions
+
+```typescript
+// Per-page OCR text extraction
+export declare function extractTextWithOcrPerPage(
+  buffer: Buffer,
+  opts?: OcrOptions,
+): Array<OcrPageText>
+
+export declare function extractTextWithOcrPerPageAsync(
+  buffer: Buffer,
+  opts?: OcrOptions,
+): Promise<Array<OcrPageText>>
+
+// Full document extraction with OCR text fallback
+export declare function pdfDocumentOcr(
+  buffer: Buffer,
+  opts?: OcrOptions,
+): PdfDocumentOcr
+
+export declare function pdfDocumentOcrAsync(
+  buffer: Buffer,
+  opts?: OcrOptions,
+): Promise<PdfDocumentOcr>
+```
+
+### `PdfDown` class (includes OCR methods)
+
+```typescript
+export declare class PdfDown {
+  constructor(buffer: Buffer)
+
+  // ── Base methods ──
+  textPerPage(): Array<PageText>
+  textPerPageAsync(): Promise<Array<PageText>>
+  imagesPerPage(): Array<PageImage>
+  imagesPerPageAsync(): Promise<Array<PageImage>>
+  annotationsPerPage(): Array<PageAnnotation>
+  annotationsPerPageAsync(): Promise<Array<PageAnnotation>>
+  structuredText(): Array<StructuredPageText>
+  structuredTextAsync(): Promise<Array<StructuredPageText>>
+  metadata(): PdfMeta
+  metadataAsync(): Promise<PdfMeta>
+  document(): PdfDocument
+  documentAsync(): Promise<PdfDocument>
+
+  // ── OCR methods ──
+  textWithOcrPerPage(opts?: OcrOptions): Array<OcrPageText>
+  textWithOcrPerPageAsync(opts?: OcrOptions): Promise<Array<OcrPageText>>
+  documentOcr(opts?: OcrOptions): PdfDocumentOcr
+  documentOcrAsync(opts?: OcrOptions): Promise<PdfDocumentOcr>
+}
+```
+
+### Types
+
+```typescript
+export const enum TextSource {
+  Native = 'Native',
+  Ocr = 'Ocr',
+}
+
+export interface OcrPageText {
+  page: number
+  text: string
+  source: TextSource
+}
+
+export interface OcrStructuredPageText {
+  page: number
+  header: string
+  body: string
+  footer: string
+  source: TextSource
+}
+
+export interface OcrOptions {
+  lang?: string        // Tesseract language code, default "eng"
+  minTextLength?: number // non-whitespace char threshold before OCR fallback, default 1
+  maxThreads?: number  // cap on Rayon threads for OCR parallelism, default 4, clamped to [1, available CPUs]
+}
+
+export interface PdfDocumentOcr {
+  version: string
+  isLinearized: boolean
+  pageCount: number
+  creator?: string
+  producer?: string
+  creationDate?: string
+  modificationDate?: string
+  totalImages: number
+  totalAnnotations: number
+  imagePages: Array<number>
+  annotationPages: Array<number>
+  text: Array<OcrPageText>
+  structuredText: Array<OcrStructuredPageText>
+  images: Array<PageImage>
+  annotations: Array<PageAnnotation>
+}
+```
+
+## Usage
+
+> **Use the async API for OCR.** The sync variants block the Node.js event loop for the duration of OCR processing, which can be significant for multi-page scanned documents.
+
+### Standalone
+
+```typescript
+import { readFile } from 'fs/promises'
+import { extractTextWithOcrPerPageAsync } from '@d0paminedriven/pdfdown-ocr'
+
+const pdf = await readFile('scanned-document.pdf')
+const pages = await extractTextWithOcrPerPageAsync(pdf, { lang: 'eng', minTextLength: 10 })
+
+for (const { page, text, source } of pages) {
+  console.log(`Page ${page} [${source}]: ${text.slice(0, 100)}...`)
+}
+```
+
+### Class-based (parse once, extract many)
+
+```typescript
+import { readFile } from 'fs/promises'
+import { PdfDown } from '@d0paminedriven/pdfdown-ocr'
+
+const pdf = new PdfDown(await readFile('scanned-document.pdf'))
+
+// OCR text extraction
+const pages = await pdf.textWithOcrPerPageAsync({ lang: 'eng', minTextLength: 10 })
+
+// All base methods work too
+const images = await pdf.imagesPerPageAsync()
+const meta = pdf.metadata()
+```
+
+### Extract everything with OCR in one call
+
+```typescript
+import { readFile } from 'fs/promises'
+import { PdfDown } from '@d0paminedriven/pdfdown-ocr'
+
+const pdf = new PdfDown(await readFile('scanned-document.pdf'))
+const result = await pdf.documentOcrAsync({ minTextLength: 10 })
+
+// result.text         — OcrPageText[] (page, text, source per page)
+// result.structuredText — OcrStructuredPageText[] (header/body/footer + source per page)
+// result.images       — PageImage[] (decoded PNGs with dimensions and color space)
+// result.annotations  — PageAnnotation[] (links, destinations, rects)
+// result.pageCount, result.version, result.creator, ...
+```
+
+### Combined: OCR text + images for multimodal pipelines
+
+```typescript
+import { readFile } from 'fs/promises'
+import { PdfDown } from '@d0paminedriven/pdfdown-ocr'
+
+const pdf = new PdfDown(await readFile('scanned-document.pdf'))
+
+const [ocrText, images] = await Promise.all([
+  pdf.textWithOcrPerPageAsync({ minTextLength: 10 }),
+  pdf.imagesPerPageAsync(),
+])
+
+const imagesByPage = Map.groupBy(images, (img) => img.page)
+
+for (const { page, text, source } of ocrText) {
+  const pageImages = (imagesByPage.get(page) ?? []).map((img) => ({
+    dataUrl: `data:image/png;base64,${img.data.toString('base64')}`,
+    width: img.width,
+    height: img.height,
+  }))
+  // Send { page, text, source, images: pageImages } to your embedding pipeline
+}
+```
+
+### `document()` vs `documentOcr()`
+
+Both methods extract everything from a PDF in a single call. The difference is how text is extracted:
+
+| Method | Text extraction | Return type | Use when |
+|--------|----------------|-------------|----------|
+| `document()` / `documentAsync()` | Native PDF text only | `PdfDocument` | PDF has selectable text |
+| `documentOcr()` / `documentOcrAsync()` | Native with OCR fallback | `PdfDocumentOcr` | PDF may contain scanned/image-only pages |
+
+`PdfDocumentOcr` uses `OcrPageText` (with `source: 'Native' | 'Ocr'`) and `OcrStructuredPageText` (with header/body/footer split plus source) instead of the base `PageText` and `StructuredPageText` types. Images, annotations, and metadata are identical in both.
+
+## How it works
+
+1. **Text extraction:** Each page is first attempted with native PDF text extraction. If a page yields fewer non-whitespace characters than `minTextLength`, its embedded images are decoded and fed to Tesseract for OCR. Each result is tagged with `source: 'Native'` or `source: 'Ocr'`.
+
+2. **Structured text:** After text extraction, repeated header/footer lines are detected across pages using frequency analysis (requires 3+ pages). Each page's text is split into `header`, `body`, and `footer` sections. For OCR results, the `source` tag is preserved so you know whether each page's content came from native extraction or OCR.
+
+3. **Parallelism:** OCR runs on a dedicated capped Rayon thread pool (default 4 threads, configurable via `maxThreads`) to prevent CPU oversubscription. Text extraction, image extraction, and annotation extraction run concurrently via `rayon::join` when using `documentOcr` / `documentOcrAsync`.
+
+4. **Tessdata discovery:** On first OCR invocation, the tessdata path is resolved once and cached in a `OnceLock`. The `TESSDATA_PREFIX` environment variable is checked first; if unset, `tesseract --list-langs` is executed and its output is parsed to extract the path. No environment variables are mutated -- the path is passed directly to Tesseract's init function.
+
+## Supported platforms
+
+Prebuilt binaries are provided for:
+
+- macOS (x64, ARM64)
+- Linux glibc (x64, ARM64)
+
+## Relationship to `@d0paminedriven/pdfdown`
+
+Same Rust codebase, compiled with the `ocr` Cargo feature flag enabled. This package is a strict superset -- you can use it as a drop-in replacement for the base package if you need OCR capabilities.
+
+## License
+
+MIT

package/index.d.ts

@@ -0,0 +1,174 @@
+/* auto-generated by NAPI-RS */
+/* eslint-disable */
+export declare class PdfDown {
+  constructor(buffer: Buffer)
+  /** Sync: extract text per page (reuses the already-parsed document) */
+  textPerPage(): Array<PageText>
+  /** Sync: extract images per page (reuses the already-parsed document) */
+  imagesPerPage(): Array<PageImage>
+  /** Sync: extract annotations per page (reuses the already-parsed document) */
+  annotationsPerPage(): Array<PageAnnotation>
+  /** Sync: get PDF metadata (reuses the already-parsed document) */
+  metadata(): PdfMeta
+  /** Async: extract text per page on the libuv thread pool (shares parsed document via Arc) */
+  textPerPageAsync(): Promise<Array<PageText>>
+  /** Async: extract images per page on the libuv thread pool (shares parsed document via Arc) */
+  imagesPerPageAsync(): Promise<Array<PageImage>>
+  /** Async: extract annotations per page on the libuv thread pool (shares parsed document via Arc) */
+  annotationsPerPageAsync(): Promise<Array<PageAnnotation>>
+  /** Async: get PDF metadata on the libuv thread pool (shares parsed document via Arc) */
+  metadataAsync(): Promise<PdfMeta>
+  /** Sync: extract everything from the PDF in one call (reuses the already-parsed document) */
+  document(): PdfDocument
+  /** Async: extract everything from the PDF on the libuv thread pool (shares parsed document via Arc) */
+  documentAsync(): Promise<PdfDocument>
+  /** Sync: extract structured text with header/footer detection */
+  structuredText(): Array<StructuredPageText>
+  /** Async: extract structured text with header/footer detection */
+  structuredTextAsync(): Promise<Array<StructuredPageText>>
+  /** Sync: extract text with OCR fallback for image-only pages */
+  textWithOcrPerPage(opts?: OcrOptions | undefined | null): Array<OcrPageText>
+  /** Async: extract text with OCR fallback for image-only pages */
+  textWithOcrPerPageAsync(opts?: OcrOptions | undefined | null): Promise<Array<OcrPageText>>
+  /** Sync: extract everything from the PDF with OCR text fallback */
+  documentOcr(opts?: OcrOptions | undefined | null): PdfDocumentOcr
+  /** Async: extract everything from the PDF with OCR text fallback */
+  documentOcrAsync(opts?: OcrOptions | undefined | null): Promise<PdfDocumentOcr>
+}
+
+export declare function extractAnnotationsPerPage(buffer: Buffer): Array<PageAnnotation>
+
+export declare function extractAnnotationsPerPageAsync(buffer: Buffer): Promise<Array<PageAnnotation>>
+
+export declare function extractImagesPerPage(buffer: Buffer): Array<PageImage>
+
+export declare function extractImagesPerPageAsync(buffer: Buffer): Promise<Array<PageImage>>
+
+export declare function extractStructuredTextPerPage(buffer: Buffer): Array<StructuredPageText>
+
+export declare function extractStructuredTextPerPageAsync(buffer: Buffer): Promise<Array<StructuredPageText>>
+
+export declare function extractTextPerPage(buffer: Buffer): Array<PageText>
+
+export declare function extractTextPerPageAsync(buffer: Buffer): Promise<Array<PageText>>
+
+export declare function extractTextWithOcrPerPage(buffer: Buffer, opts?: OcrOptions | undefined | null): Array<OcrPageText>
+
+export declare function extractTextWithOcrPerPageAsync(buffer: Buffer, opts?: OcrOptions | undefined | null): Promise<Array<OcrPageText>>
+
+export interface OcrOptions {
+  lang?: string
+  minTextLength?: number
+  maxThreads?: number
+}
+
+export interface OcrPageText {
+  page: number
+  text: string
+  source: TextSource
+}
+
+export interface OcrStructuredPageText {
+  page: number
+  header: string
+  body: string
+  footer: string
+  source: TextSource
+}
+
+export interface PageAnnotation {
+  page: number
+  subtype: string
+  rect: Array<number>
+  uri?: string
+  dest?: string
+  content?: string
+}
+
+export interface PageImage {
+  page: number
+  imageIndex: number
+  width: number
+  height: number
+  data: Buffer
+  colorSpace: string
+  bitsPerComponent: number
+  filter: string
+  xobjectName: string
+  objectId: string
+}
+
+export interface PageText {
+  page: number
+  text: string
+}
+
+export declare function pdfDocument(buffer: Buffer): PdfDocument
+
+export interface PdfDocument {
+  version: string
+  isLinearized: boolean
+  pageCount: number
+  creator?: string
+  producer?: string
+  creationDate?: string
+  modificationDate?: string
+  totalImages: number
+  totalAnnotations: number
+  imagePages: Array<number>
+  annotationPages: Array<number>
+  text: Array<PageText>
+  structuredText: Array<StructuredPageText>
+  images: Array<PageImage>
+  annotations: Array<PageAnnotation>
+}
+
+export declare function pdfDocumentAsync(buffer: Buffer): Promise<PdfDocument>
+
+export declare function pdfDocumentOcr(buffer: Buffer, opts?: OcrOptions | undefined | null): PdfDocumentOcr
+
+export interface PdfDocumentOcr {
+  version: string
+  isLinearized: boolean
+  pageCount: number
+  creator?: string
+  producer?: string
+  creationDate?: string
+  modificationDate?: string
+  totalImages: number
+  totalAnnotations: number
+  imagePages: Array<number>
+  annotationPages: Array<number>
+  text: Array<OcrPageText>
+  structuredText: Array<OcrStructuredPageText>
+  images: Array<PageImage>
+  annotations: Array<PageAnnotation>
+}
+
+export declare function pdfDocumentOcrAsync(buffer: Buffer, opts?: OcrOptions | undefined | null): Promise<PdfDocumentOcr>
+
+export interface PdfMeta {
+  pageCount: number
+  version: string
+  isLinearized: boolean
+  creator?: string
+  producer?: string
+  creationDate?: string
+  modificationDate?: string
+}
+
+export declare function pdfMetadata(buffer: Buffer): PdfMeta
+
+export declare function pdfMetadataAsync(buffer: Buffer): Promise<PdfMeta>
+
+export interface StructuredPageText {
+  page: number
+  header: string
+  body: string
+  footer: string
+}
+
+export declare const enum TextSource {
+  Native = 'Native',
+  Ocr = 'Ocr'
+}

package/index.js

@@ -0,0 +1,577 @@
+// prettier-ignore
+/* eslint-disable */
+// @ts-nocheck
+/* auto-generated by NAPI-RS */
+
+const { createRequire } = require('node:module')
+require = createRequire(__filename)
+
+const { readFileSync } = require('node:fs')
+let nativeBinding = null
+const loadErrors = []
+
+const isMusl = () => {
+  let musl = false
+  if (process.platform === 'linux') {
+    musl = isMuslFromFilesystem()
+    if (musl === null) {
+      musl = isMuslFromReport()
+    }
+    if (musl === null) {
+      musl = isMuslFromChildProcess()
+    }
+  }
+  return musl
+}
+
+const isFileMusl = (f) => f.includes('libc.musl-') || f.includes('ld-musl-')
+
+const isMuslFromFilesystem = () => {
+  try {
+    return readFileSync('/usr/bin/ldd', 'utf-8').includes('musl')
+  } catch {
+    return null
+  }
+}
+
+const isMuslFromReport = () => {
+  let report = null
+  if (typeof process.report?.getReport === 'function') {
+    process.report.excludeNetwork = true
+    report = process.report.getReport()
+  }
+  if (!report) {
+    return null
+  }
+  if (report.header && report.header.glibcVersionRuntime) {
+    return false
+  }
+  if (Array.isArray(report.sharedObjects)) {
+    if (report.sharedObjects.some(isFileMusl)) {
+      return true
+    }
+  }
+  return false
+}
+
+const isMuslFromChildProcess = () => {
+  try {
+    return require('child_process').execSync('ldd --version', { encoding: 'utf8' }).includes('musl')
+  } catch (e) {
+    // If we reach this case, we don't know if the system is musl or not, so is better to just fallback to false
+    return false
+  }
+}
+
+function requireNative() {
+  if (process.env.NAPI_RS_NATIVE_LIBRARY_PATH) {
+    try {
+      return require(process.env.NAPI_RS_NATIVE_LIBRARY_PATH);
+    } catch (err) {
+      loadErrors.push(err)
+    }
+  } else if (process.platform === 'android') {
+    if (process.arch === 'arm64') {
+      try {
+        return require('./pdfdown_ocr.android-arm64.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('@d0paminedriven/pdfdown-ocr-android-arm64')
+        const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-android-arm64/package.json').version
+        if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+        }
+        return binding
+      } catch (e) {
+        loadErrors.push(e)
+      }
+    } else if (process.arch === 'arm') {
+      try {
+        return require('./pdfdown_ocr.android-arm-eabi.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('@d0paminedriven/pdfdown-ocr-android-arm-eabi')
+        const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-android-arm-eabi/package.json').version
+        if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+        }
+        return binding
+      } catch (e) {
+        loadErrors.push(e)
+      }
+    } else {
+      loadErrors.push(new Error(`Unsupported architecture on Android ${process.arch}`))
+    }
+  } else if (process.platform === 'win32') {
+    if (process.arch === 'x64') {
+      try {
+        return require('./pdfdown_ocr.win32-x64-msvc.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('@d0paminedriven/pdfdown-ocr-win32-x64-msvc')
+        const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-win32-x64-msvc/package.json').version
+        if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+        }
+        return binding
+      } catch (e) {
+        loadErrors.push(e)
+      }
+    } else if (process.arch === 'ia32') {
+      try {
+        return require('./pdfdown_ocr.win32-ia32-msvc.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('@d0paminedriven/pdfdown-ocr-win32-ia32-msvc')
+        const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-win32-ia32-msvc/package.json').version
+        if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+        }
+        return binding
+      } catch (e) {
+        loadErrors.push(e)
+      }
+    } else if (process.arch === 'arm64') {
+      try {
+        return require('./pdfdown_ocr.win32-arm64-msvc.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('@d0paminedriven/pdfdown-ocr-win32-arm64-msvc')
+        const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-win32-arm64-msvc/package.json').version
+        if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+        }
+        return binding
+      } catch (e) {
+        loadErrors.push(e)
+      }
+    } else {
+      loadErrors.push(new Error(`Unsupported architecture on Windows: ${process.arch}`))
+    }
+  } else if (process.platform === 'darwin') {
+    try {
+      return require('./pdfdown_ocr.darwin-universal.node')
+    } catch (e) {
+      loadErrors.push(e)
+    }
+    try {
+      const binding = require('@d0paminedriven/pdfdown-ocr-darwin-universal')
+      const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-darwin-universal/package.json').version
+      if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+        throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+      }
+      return binding
+    } catch (e) {
+      loadErrors.push(e)
+    }
+    if (process.arch === 'x64') {
+      try {
+        return require('./pdfdown_ocr.darwin-x64.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('@d0paminedriven/pdfdown-ocr-darwin-x64')
+        const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-darwin-x64/package.json').version
+        if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+        }
+        return binding
+      } catch (e) {
+        loadErrors.push(e)
+      }
+    } else if (process.arch === 'arm64') {
+      try {
+        return require('./pdfdown_ocr.darwin-arm64.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('@d0paminedriven/pdfdown-ocr-darwin-arm64')
+        const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-darwin-arm64/package.json').version
+        if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+        }
+        return binding
+      } catch (e) {
+        loadErrors.push(e)
+      }
+    } else {
+      loadErrors.push(new Error(`Unsupported architecture on macOS: ${process.arch}`))
+    }
+  } else if (process.platform === 'freebsd') {
+    if (process.arch === 'x64') {
+      try {
+        return require('./pdfdown_ocr.freebsd-x64.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('@d0paminedriven/pdfdown-ocr-freebsd-x64')
+        const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-freebsd-x64/package.json').version
+        if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+        }
+        return binding
+      } catch (e) {
+        loadErrors.push(e)
+      }
+    } else if (process.arch === 'arm64') {
+      try {
+        return require('./pdfdown_ocr.freebsd-arm64.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('@d0paminedriven/pdfdown-ocr-freebsd-arm64')
+        const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-freebsd-arm64/package.json').version
+        if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+        }
+        return binding
+      } catch (e) {
+        loadErrors.push(e)
+      }
+    } else {
+      loadErrors.push(new Error(`Unsupported architecture on FreeBSD: ${process.arch}`))
+    }
+  } else if (process.platform === 'linux') {
+    if (process.arch === 'x64') {
+      if (isMusl()) {
+        try {
+          return require('./pdfdown_ocr.linux-x64-musl.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('@d0paminedriven/pdfdown-ocr-linux-x64-musl')
+          const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-linux-x64-musl/package.json').version
+          if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+          }
+          return binding
+        } catch (e) {
+          loadErrors.push(e)
+        }
+      } else {
+        try {
+          return require('./pdfdown_ocr.linux-x64-gnu.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('@d0paminedriven/pdfdown-ocr-linux-x64-gnu')
+          const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-linux-x64-gnu/package.json').version
+          if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+          }
+          return binding
+        } catch (e) {
+          loadErrors.push(e)
+        }
+      }
+    } else if (process.arch === 'arm64') {
+      if (isMusl()) {
+        try {
+          return require('./pdfdown_ocr.linux-arm64-musl.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('@d0paminedriven/pdfdown-ocr-linux-arm64-musl')
+          const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-linux-arm64-musl/package.json').version
+          if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+          }
+          return binding
+        } catch (e) {
+          loadErrors.push(e)
+        }
+      } else {
+        try {
+          return require('./pdfdown_ocr.linux-arm64-gnu.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('@d0paminedriven/pdfdown-ocr-linux-arm64-gnu')
+          const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-linux-arm64-gnu/package.json').version
+          if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+          }
+          return binding
+        } catch (e) {
+          loadErrors.push(e)
+        }
+      }
+    } else if (process.arch === 'arm') {
+      if (isMusl()) {
+        try {
+          return require('./pdfdown_ocr.linux-arm-musleabihf.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('@d0paminedriven/pdfdown-ocr-linux-arm-musleabihf')
+          const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-linux-arm-musleabihf/package.json').version
+          if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+          }
+          return binding
+        } catch (e) {
+          loadErrors.push(e)
+        }
+      } else {
+        try {
+          return require('./pdfdown_ocr.linux-arm-gnueabihf.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('@d0paminedriven/pdfdown-ocr-linux-arm-gnueabihf')
+          const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-linux-arm-gnueabihf/package.json').version
+          if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+          }
+          return binding
+        } catch (e) {
+          loadErrors.push(e)
+        }
+      }
+    } else if (process.arch === 'loong64') {
+      if (isMusl()) {
+        try {
+          return require('./pdfdown_ocr.linux-loong64-musl.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('@d0paminedriven/pdfdown-ocr-linux-loong64-musl')
+          const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-linux-loong64-musl/package.json').version
+          if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+          }
+          return binding
+        } catch (e) {
+          loadErrors.push(e)
+        }
+      } else {
+        try {
+          return require('./pdfdown_ocr.linux-loong64-gnu.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('@d0paminedriven/pdfdown-ocr-linux-loong64-gnu')
+          const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-linux-loong64-gnu/package.json').version
+          if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+          }
+          return binding
+        } catch (e) {
+          loadErrors.push(e)
+        }
+      }
+    } else if (process.arch === 'riscv64') {
+      if (isMusl()) {
+        try {
+          return require('./pdfdown_ocr.linux-riscv64-musl.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('@d0paminedriven/pdfdown-ocr-linux-riscv64-musl')
+          const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-linux-riscv64-musl/package.json').version
+          if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+          }
+          return binding
+        } catch (e) {
+          loadErrors.push(e)
+        }
+      } else {
+        try {
+          return require('./pdfdown_ocr.linux-riscv64-gnu.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('@d0paminedriven/pdfdown-ocr-linux-riscv64-gnu')
+          const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-linux-riscv64-gnu/package.json').version
+          if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+          }
+          return binding
+        } catch (e) {
+          loadErrors.push(e)
+        }
+      }
+    } else if (process.arch === 'ppc64') {
+      try {
+        return require('./pdfdown_ocr.linux-ppc64-gnu.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('@d0paminedriven/pdfdown-ocr-linux-ppc64-gnu')
+        const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-linux-ppc64-gnu/package.json').version
+        if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+        }
+        return binding
+      } catch (e) {
+        loadErrors.push(e)
+      }
+    } else if (process.arch === 's390x') {
+      try {
+        return require('./pdfdown_ocr.linux-s390x-gnu.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('@d0paminedriven/pdfdown-ocr-linux-s390x-gnu')
+        const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-linux-s390x-gnu/package.json').version
+        if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+        }
+        return binding
+      } catch (e) {
+        loadErrors.push(e)
+      }
+    } else {
+      loadErrors.push(new Error(`Unsupported architecture on Linux: ${process.arch}`))
+    }
+  } else if (process.platform === 'openharmony') {
+    if (process.arch === 'arm64') {
+      try {
+        return require('./pdfdown_ocr.openharmony-arm64.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('@d0paminedriven/pdfdown-ocr-openharmony-arm64')
+        const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-openharmony-arm64/package.json').version
+        if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+        }
+        return binding
+      } catch (e) {
+        loadErrors.push(e)
+      }
+    } else if (process.arch === 'x64') {
+      try {
+        return require('./pdfdown_ocr.openharmony-x64.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('@d0paminedriven/pdfdown-ocr-openharmony-x64')
+        const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-openharmony-x64/package.json').version
+        if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+        }
+        return binding
+      } catch (e) {
+        loadErrors.push(e)
+      }
+    } else if (process.arch === 'arm') {
+      try {
+        return require('./pdfdown_ocr.openharmony-arm.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('@d0paminedriven/pdfdown-ocr-openharmony-arm')
+        const bindingPackageVersion = require('@d0paminedriven/pdfdown-ocr-openharmony-arm/package.json').version
+        if (bindingPackageVersion !== '0.9.1' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.9.1 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+        }
+        return binding
+      } catch (e) {
+        loadErrors.push(e)
+      }
+    } else {
+      loadErrors.push(new Error(`Unsupported architecture on OpenHarmony: ${process.arch}`))
+    }
+  } else {
+    loadErrors.push(new Error(`Unsupported OS: ${process.platform}, architecture: ${process.arch}`))
+  }
+}
+
+nativeBinding = requireNative()
+
+if (!nativeBinding || process.env.NAPI_RS_FORCE_WASI) {
+  let wasiBinding = null
+  let wasiBindingError = null
+  try {
+    wasiBinding = require('./pdfdown_ocr.wasi.cjs')
+    nativeBinding = wasiBinding
+  } catch (err) {
+    if (process.env.NAPI_RS_FORCE_WASI) {
+      wasiBindingError = err
+    }
+  }
+  if (!nativeBinding) {
+    try {
+      wasiBinding = require('@d0paminedriven/pdfdown-ocr-wasm32-wasi')
+      nativeBinding = wasiBinding
+    } catch (err) {
+      if (process.env.NAPI_RS_FORCE_WASI) {
+        wasiBindingError.cause = err
+        loadErrors.push(err)
+      }
+    }
+  }
+  if (process.env.NAPI_RS_FORCE_WASI === 'error' && !wasiBinding) {
+    const error = new Error('WASI binding not found and NAPI_RS_FORCE_WASI is set to error')
+    error.cause = wasiBindingError
+    throw error
+  }
+}
+
+if (!nativeBinding) {
+  if (loadErrors.length > 0) {
+    throw new Error(
+      `Cannot find native binding. ` +
+        `npm has a bug related to optional dependencies (https://github.com/npm/cli/issues/4828). ` +
+        'Please try `npm i` again after removing both package-lock.json and node_modules directory.',
+      {
+        cause: loadErrors.reduce((err, cur) => {
+          cur.cause = err
+          return cur
+        }),
+      },
+    )
+  }
+  throw new Error(`Failed to load native binding`)
+}
+
+module.exports = nativeBinding
+module.exports.PdfDown = nativeBinding.PdfDown
+module.exports.extractAnnotationsPerPage = nativeBinding.extractAnnotationsPerPage
+module.exports.extractAnnotationsPerPageAsync = nativeBinding.extractAnnotationsPerPageAsync
+module.exports.extractImagesPerPage = nativeBinding.extractImagesPerPage
+module.exports.extractImagesPerPageAsync = nativeBinding.extractImagesPerPageAsync
+module.exports.extractStructuredTextPerPage = nativeBinding.extractStructuredTextPerPage
+module.exports.extractStructuredTextPerPageAsync = nativeBinding.extractStructuredTextPerPageAsync
+module.exports.extractTextPerPage = nativeBinding.extractTextPerPage
+module.exports.extractTextPerPageAsync = nativeBinding.extractTextPerPageAsync
+module.exports.extractTextWithOcrPerPage = nativeBinding.extractTextWithOcrPerPage
+module.exports.extractTextWithOcrPerPageAsync = nativeBinding.extractTextWithOcrPerPageAsync
+module.exports.pdfDocument = nativeBinding.pdfDocument
+module.exports.pdfDocumentAsync = nativeBinding.pdfDocumentAsync
+module.exports.pdfDocumentOcr = nativeBinding.pdfDocumentOcr
+module.exports.pdfDocumentOcrAsync = nativeBinding.pdfDocumentOcrAsync
+module.exports.pdfMetadata = nativeBinding.pdfMetadata
+module.exports.pdfMetadataAsync = nativeBinding.pdfMetadataAsync
+module.exports.TextSource = nativeBinding.TextSource

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@d0paminedriven/pdfdown-ocr",
-  "version": "0.8.0",
+  "version": "0.9.1",
   "description": "Rust powered PDF extraction for Node with OCR fallback (requires system tesseract).",
   "main": "index.js",
   "repository": {
@@ -10,7 +10,8 @@
   "license": "MIT",
   "files": [
     "index.d.ts",
-    "index.js"
+    "index.js",
+    "README.md"
   ],
   "os": [
     "darwin",