@firecrawl/pdf-inspector 1.0.0

package/README.md

@@ -0,0 +1,99 @@
+# firecrawl-pdf-inspector
+
+Fast PDF classification and region-based text extraction for Node.js/Bun. Native Rust performance via [napi-rs](https://napi.rs).
+
+Built by [Firecrawl](https://firecrawl.dev) for hybrid OCR pipelines — extract text from PDF structure where possible, fall back to OCR only when needed.
+
+## Install
+
+```bash
+npm install firecrawl-pdf-inspector
+# or
+bun add firecrawl-pdf-inspector
+```
+
+Prebuilt binaries included for **linux-x64** and **macOS ARM64**. No Rust toolchain needed.
+
+## API
+
+### `classifyPdf(buffer: Buffer): PdfClassification`
+
+Classify a PDF as TextBased, Scanned, Mixed, or ImageBased (~10-50ms). Returns which pages need OCR.
+
+```typescript
+import { classifyPdf } from 'firecrawl-pdf-inspector'
+import { readFileSync } from 'fs'
+
+const pdf = readFileSync('document.pdf')
+const result = classifyPdf(pdf)
+
+console.log(result.pdfType)        // "TextBased" | "Scanned" | "Mixed" | "ImageBased"
+console.log(result.pageCount)      // 42
+console.log(result.pagesNeedingOcr) // [5, 12, 15] (0-indexed)
+console.log(result.confidence)     // 0.875
+```
+
+### `extractTextInRegions(buffer: Buffer, pageRegions: PageRegions[]): PageRegionTexts[]`
+
+Extract text within bounding-box regions from a PDF. Designed for hybrid OCR pipelines where a layout model detects regions in rendered page images, and this function extracts text from the PDF structure for text-based pages — skipping GPU OCR.
+
+Each region result includes a `needsOcr` flag that signals unreliable extraction (empty text, GID-encoded fonts, garbage text, encoding issues).
+
+```typescript
+import { extractTextInRegions } from 'firecrawl-pdf-inspector'
+
+const result = extractTextInRegions(pdf, [
+  {
+    page: 0, // 0-indexed
+    regions: [
+      [0, 0, 300, 400],    // [x1, y1, x2, y2] in PDF points, top-left origin
+      [300, 0, 612, 400],
+    ]
+  }
+])
+
+for (const region of result[0].regions) {
+  if (region.needsOcr) {
+    // Unreliable text — send this region to OCR instead
+  } else {
+    console.log(region.text) // Extracted text in reading order
+  }
+}
+```
+
+## Types
+
+```typescript
+interface PdfClassification {
+  pdfType: string          // "TextBased" | "Scanned" | "Mixed" | "ImageBased"
+  pageCount: number
+  pagesNeedingOcr: number[] // 0-indexed page numbers
+  confidence: number        // 0.0 - 1.0
+}
+
+interface PageRegions {
+  page: number              // 0-indexed
+  regions: number[][]       // [[x1, y1, x2, y2], ...] in PDF points, top-left origin
+}
+
+interface PageRegionTexts {
+  page: number
+  regions: RegionText[]
+}
+
+interface RegionText {
+  text: string
+  needsOcr: boolean         // true when text is unreliable
+}
+```
+
+## Platforms
+
+| Platform | Architecture | Supported |
+|----------|-------------|-----------|
+| Linux    | x64         | Yes       |
+| macOS    | ARM64       | Yes       |
+
+## License
+
+MIT

package/bin/pdf-inspector.mjs

@@ -0,0 +1,131 @@
+#!/usr/bin/env node
+
+import { readFileSync, writeFileSync } from "fs";
+import { createRequire } from "module";
+
+const require = createRequire(import.meta.url);
+const { version } = require("../package.json");
+
+const HELP = `pdf-inspector v${version} — Fast PDF text extraction to Markdown
+
+Usage:
+  pdf-inspector <file>                  Extract markdown (default)
+  pdf-inspector detect <file>           Classify PDF type
+
+Options:
+  --json                  Output as JSON
+  --pages <pages>         Comma-separated page numbers (e.g. 1,3,5)
+  -o, --output <file>     Write output to file instead of stdout
+  -h, --help              Show this help
+  -v, --version           Show version
+
+Examples:
+  pdf-inspector document.pdf
+  pdf-inspector document.pdf --json
+  pdf-inspector document.pdf --pages 1,2,3
+  pdf-inspector detect document.pdf --json
+  cat document.pdf | pdf-inspector -`;
+
+function die(msg) {
+  process.stderr.write(`error: ${msg}\n`);
+  process.exit(1);
+}
+
+function parseArgs(argv) {
+  const opts = { json: false, pages: null, output: null, file: null, command: "extract" };
+  let i = 0;
+
+  // Check for subcommand
+  if (argv[0] === "detect") {
+    opts.command = "detect";
+    i = 1;
+  }
+
+  while (i < argv.length) {
+    const arg = argv[i];
+    if (arg === "-h" || arg === "--help") {
+      process.stdout.write(HELP + "\n");
+      process.exit(0);
+    } else if (arg === "-v" || arg === "--version") {
+      process.stdout.write(`${version}\n`);
+      process.exit(0);
+    } else if (arg === "--json") {
+      opts.json = true;
+    } else if (arg === "--pages") {
+      i++;
+      if (!argv[i]) die("--pages requires a value (e.g. 1,3,5)");
+      opts.pages = argv[i].split(",").map((p) => {
+        const n = parseInt(p.trim(), 10);
+        if (Number.isNaN(n) || n < 1) die(`invalid page number: ${p}`);
+        return n;
+      });
+    } else if (arg === "-o" || arg === "--output") {
+      i++;
+      if (!argv[i]) die("-o requires a filename");
+      opts.output = argv[i];
+    } else if (arg === "-" || !arg.startsWith("-")) {
+      if (opts.file) die(`unexpected argument: ${arg}`);
+      opts.file = arg;
+    } else {
+      die(`unknown option: ${arg}`);
+    }
+    i++;
+  }
+
+  return opts;
+}
+
+function readInput(file) {
+  if (file === "-") {
+    return readFileSync(0); // stdin fd
+  }
+  try {
+    return readFileSync(file);
+  } catch (err) {
+    if (err.code === "ENOENT") die(`file not found: ${file}`);
+    die(err.message);
+  }
+}
+
+function output(text, outputPath) {
+  if (outputPath) {
+    writeFileSync(outputPath, text);
+  } else {
+    process.stdout.write(text);
+  }
+}
+
+// ---- main ----
+
+const opts = parseArgs(process.argv.slice(2));
+
+if (!opts.file) {
+  // Check if stdin is piped
+  if (process.stdin.isTTY !== false) {
+    process.stderr.write(HELP + "\n");
+    process.exit(1);
+  }
+  opts.file = "-";
+}
+
+const { processPdf, classifyPdf } = await import("../index.js");
+const buffer = readInput(opts.file);
+
+if (opts.command === "detect") {
+  const result = classifyPdf(buffer);
+  if (opts.json) {
+    output(JSON.stringify(result, null, 2) + "\n", opts.output);
+  } else {
+    const ocr = result.pagesNeedingOcr.length > 0
+      ? `, ${result.pagesNeedingOcr.length} pages need OCR`
+      : "";
+    output(`${result.pdfType} (${result.pageCount} pages, confidence: ${result.confidence.toFixed(2)}${ocr})\n`, opts.output);
+  }
+} else {
+  const result = processPdf(buffer, opts.pages ?? undefined);
+  if (opts.json) {
+    output(JSON.stringify(result, null, 2) + "\n", opts.output);
+  } else {
+    output((result.markdown ?? "") + "\n", opts.output);
+  }
+}

package/index.d.ts

@@ -0,0 +1,108 @@
+/* auto-generated by NAPI-RS */
+/* eslint-disable */
+/**
+ * Lightweight PDF classification — returns type, page count, and OCR pages.
+ * Faster than detectPdf as it skips building the full PdfResult.
+ * Pages in pagesNeedingOcr are 0-indexed.
+ */
+export declare function classifyPdf(buffer: Buffer): PdfClassification
+
+/** Fast detection only — no text extraction or markdown. */
+export declare function detectPdf(buffer: Buffer): PdfResult
+
+/**
+ * Extract markdown tables within bounding-box regions from a PDF.
+ *
+ * Like `extractTextInRegions` but runs table detection on items within each
+ * region and returns markdown pipe-tables instead of flat text.
+ *
+ * When table structure is detected, `text` contains a markdown pipe-table and
+ * `needsOcr` is `false`. When no table is found, `text` is empty and
+ * `needsOcr` is `true` so the caller can fall back to GPU OCR.
+ *
+ * Coordinates are PDF points with top-left origin.
+ */
+export declare function extractTablesInRegions(buffer: Buffer, pageRegions: Array<PageRegions>): Array<PageRegionTexts>
+
+/** Extract plain text from a PDF Buffer. */
+export declare function extractText(buffer: Buffer): string
+
+/**
+ * Extract text within bounding-box regions from a PDF.
+ *
+ * For hybrid OCR: layout model detects regions in rendered images,
+ * this extracts PDF text within those regions — skipping GPU OCR
+ * for text-based pages.
+ *
+ * Each region result includes `needsOcr` — set when the extracted text
+ * is unreliable (empty, GID-encoded fonts, garbage, encoding issues).
+ *
+ * Coordinates are PDF points with top-left origin.
+ */
+export declare function extractTextInRegions(buffer: Buffer, pageRegions: Array<PageRegions>): Array<PageRegionTexts>
+
+/** Extract text with position information from a PDF Buffer. */
+export declare function extractTextWithPositions(buffer: Buffer, pages?: Array<number> | undefined | null): Array<TextItem>
+
+/** A page's regions for text extraction: (page_index_0based, bboxes). */
+export interface PageRegions {
+  page: number
+  /** Each bbox is [x1, y1, x2, y2] in PDF points, top-left origin. */
+  regions: Array<Array<number>>
+}
+
+/** Extracted text for one page's regions. */
+export interface PageRegionTexts {
+  page: number
+  regions: Array<RegionText>
+}
+
+/** Lightweight PDF classification result. */
+export interface PdfClassification {
+  pdfType: string
+  pageCount: number
+  /** 0-indexed page numbers that need OCR. */
+  pagesNeedingOcr: Array<number>
+  confidence: number
+}
+
+/** Full PDF processing result with markdown and metadata. */
+export interface PdfResult {
+  pdfType: string
+  markdown?: string
+  pageCount: number
+  processingTimeMs: number
+  /** 1-indexed page numbers that need OCR. */
+  pagesNeedingOcr: Array<number>
+  title?: string
+  confidence: number
+  isComplexLayout: boolean
+  pagesWithTables: Array<number>
+  pagesWithColumns: Array<number>
+  hasEncodingIssues: boolean
+}
+
+/** Process a PDF from a Buffer: detect type, extract text, and convert to Markdown. */
+export declare function processPdf(buffer: Buffer, pages?: Array<number> | undefined | null): PdfResult
+
+/** Extracted text for a single region. */
+export interface RegionText {
+  text: string
+  /** `true` when the text should not be trusted (empty, GID fonts, garbage, encoding issues). */
+  needsOcr: boolean
+}
+
+/** A positioned text item extracted from a PDF. */
+export interface TextItem {
+  text: string
+  x: number
+  y: number
+  width: number
+  height: number
+  font: string
+  fontSize: number
+  page: number
+  isBold: boolean
+  isItalic: boolean
+  itemType: string
+}

package/index.js

@@ -0,0 +1,585 @@
+// prettier-ignore
+/* eslint-disable */
+// @ts-nocheck
+/* auto-generated by NAPI-RS */
+
+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('./pdf-inspector.android-arm64.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('firecrawl-pdf-inspector-android-arm64')
+        const bindingPackageVersion = require('firecrawl-pdf-inspector-android-arm64/package.json').version
+        if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.android-arm-eabi.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('firecrawl-pdf-inspector-android-arm-eabi')
+        const bindingPackageVersion = require('firecrawl-pdf-inspector-android-arm-eabi/package.json').version
+        if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.4.0 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') {
+      if (process.config?.variables?.shlib_suffix === 'dll.a' || process.config?.variables?.node_target_type === 'shared_library') {
+        try {
+        return require('./pdf-inspector.win32-x64-gnu.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('firecrawl-pdf-inspector-win32-x64-gnu')
+        const bindingPackageVersion = require('firecrawl-pdf-inspector-win32-x64-gnu/package.json').version
+        if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.4.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+        }
+        return binding
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      } else {
+        try {
+        return require('./pdf-inspector.win32-x64-msvc.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('firecrawl-pdf-inspector-win32-x64-msvc')
+        const bindingPackageVersion = require('firecrawl-pdf-inspector-win32-x64-msvc/package.json').version
+        if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.win32-ia32-msvc.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('firecrawl-pdf-inspector-win32-ia32-msvc')
+        const bindingPackageVersion = require('firecrawl-pdf-inspector-win32-ia32-msvc/package.json').version
+        if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.win32-arm64-msvc.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('firecrawl-pdf-inspector-win32-arm64-msvc')
+        const bindingPackageVersion = require('firecrawl-pdf-inspector-win32-arm64-msvc/package.json').version
+        if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.darwin-universal.node')
+    } catch (e) {
+      loadErrors.push(e)
+    }
+    try {
+      const binding = require('firecrawl-pdf-inspector-darwin-universal')
+      const bindingPackageVersion = require('firecrawl-pdf-inspector-darwin-universal/package.json').version
+      if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+        throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.darwin-x64.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('firecrawl-pdf-inspector-darwin-x64')
+        const bindingPackageVersion = require('firecrawl-pdf-inspector-darwin-x64/package.json').version
+        if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.darwin-arm64.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('firecrawl-pdf-inspector-darwin-arm64')
+        const bindingPackageVersion = require('firecrawl-pdf-inspector-darwin-arm64/package.json').version
+        if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.freebsd-x64.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('firecrawl-pdf-inspector-freebsd-x64')
+        const bindingPackageVersion = require('firecrawl-pdf-inspector-freebsd-x64/package.json').version
+        if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.freebsd-arm64.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('firecrawl-pdf-inspector-freebsd-arm64')
+        const bindingPackageVersion = require('firecrawl-pdf-inspector-freebsd-arm64/package.json').version
+        if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.linux-x64-musl.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('firecrawl-pdf-inspector-linux-x64-musl')
+          const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-x64-musl/package.json').version
+          if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.4.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+          }
+          return binding
+        } catch (e) {
+          loadErrors.push(e)
+        }
+      } else {
+        try {
+          return require('./pdf-inspector.linux-x64-gnu.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('firecrawl-pdf-inspector-linux-x64-gnu')
+          const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-x64-gnu/package.json').version
+          if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.linux-arm64-musl.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('firecrawl-pdf-inspector-linux-arm64-musl')
+          const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-arm64-musl/package.json').version
+          if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.4.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+          }
+          return binding
+        } catch (e) {
+          loadErrors.push(e)
+        }
+      } else {
+        try {
+          return require('./pdf-inspector.linux-arm64-gnu.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('firecrawl-pdf-inspector-linux-arm64-gnu')
+          const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-arm64-gnu/package.json').version
+          if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.linux-arm-musleabihf.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('firecrawl-pdf-inspector-linux-arm-musleabihf')
+          const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-arm-musleabihf/package.json').version
+          if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.4.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+          }
+          return binding
+        } catch (e) {
+          loadErrors.push(e)
+        }
+      } else {
+        try {
+          return require('./pdf-inspector.linux-arm-gnueabihf.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('firecrawl-pdf-inspector-linux-arm-gnueabihf')
+          const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-arm-gnueabihf/package.json').version
+          if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.linux-loong64-musl.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('firecrawl-pdf-inspector-linux-loong64-musl')
+          const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-loong64-musl/package.json').version
+          if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.4.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+          }
+          return binding
+        } catch (e) {
+          loadErrors.push(e)
+        }
+      } else {
+        try {
+          return require('./pdf-inspector.linux-loong64-gnu.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('firecrawl-pdf-inspector-linux-loong64-gnu')
+          const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-loong64-gnu/package.json').version
+          if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.linux-riscv64-musl.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('firecrawl-pdf-inspector-linux-riscv64-musl')
+          const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-riscv64-musl/package.json').version
+          if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.4.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
+          }
+          return binding
+        } catch (e) {
+          loadErrors.push(e)
+        }
+      } else {
+        try {
+          return require('./pdf-inspector.linux-riscv64-gnu.node')
+        } catch (e) {
+          loadErrors.push(e)
+        }
+        try {
+          const binding = require('firecrawl-pdf-inspector-linux-riscv64-gnu')
+          const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-riscv64-gnu/package.json').version
+          if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+            throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.linux-ppc64-gnu.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('firecrawl-pdf-inspector-linux-ppc64-gnu')
+        const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-ppc64-gnu/package.json').version
+        if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.linux-s390x-gnu.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('firecrawl-pdf-inspector-linux-s390x-gnu')
+        const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-s390x-gnu/package.json').version
+        if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.openharmony-arm64.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('firecrawl-pdf-inspector-openharmony-arm64')
+        const bindingPackageVersion = require('firecrawl-pdf-inspector-openharmony-arm64/package.json').version
+        if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.openharmony-x64.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('firecrawl-pdf-inspector-openharmony-x64')
+        const bindingPackageVersion = require('firecrawl-pdf-inspector-openharmony-x64/package.json').version
+        if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.openharmony-arm.node')
+      } catch (e) {
+        loadErrors.push(e)
+      }
+      try {
+        const binding = require('firecrawl-pdf-inspector-openharmony-arm')
+        const bindingPackageVersion = require('firecrawl-pdf-inspector-openharmony-arm/package.json').version
+        if (bindingPackageVersion !== '0.4.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
+          throw new Error(`Native binding package version mismatch, expected 0.4.0 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('./pdf-inspector.wasi.cjs')
+    nativeBinding = wasiBinding
+  } catch (err) {
+    if (process.env.NAPI_RS_FORCE_WASI) {
+      wasiBindingError = err
+    }
+  }
+  if (!nativeBinding || process.env.NAPI_RS_FORCE_WASI) {
+    try {
+      wasiBinding = require('firecrawl-pdf-inspector-wasm32-wasi')
+      nativeBinding = wasiBinding
+    } catch (err) {
+      if (process.env.NAPI_RS_FORCE_WASI) {
+        if (!wasiBindingError) {
+          wasiBindingError = err
+        } else {
+          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.classifyPdf = nativeBinding.classifyPdf
+module.exports.detectPdf = nativeBinding.detectPdf
+module.exports.extractTablesInRegions = nativeBinding.extractTablesInRegions
+module.exports.extractText = nativeBinding.extractText
+module.exports.extractTextInRegions = nativeBinding.extractTextInRegions
+module.exports.extractTextWithPositions = nativeBinding.extractTextWithPositions
+module.exports.processPdf = nativeBinding.processPdf

package/package.json

@@ -0,0 +1,54 @@
+{
+  "name": "@firecrawl/pdf-inspector",
+  "version": "1.0.0",
+  "description": "Fast PDF classification and text extraction. Detect text-based vs scanned PDFs, extract text by region with quality checks. Native Rust performance via napi-rs.",
+  "main": "index.js",
+  "types": "index.d.ts",
+  "bin": {
+    "pdf-inspector": "bin/pdf-inspector.mjs"
+  },
+  "license": "MIT",
+  "keywords": [
+    "pdf",
+    "pdf-extraction",
+    "pdf-parser",
+    "text-extraction",
+    "ocr",
+    "pdf-classification",
+    "napi",
+    "rust",
+    "firecrawl"
+  ],
+  "files": [
+    "index.js",
+    "index.d.ts",
+    "*.node",
+    "bin/",
+    "README.md"
+  ],
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/firecrawl/pdf-inspector"
+  },
+  "homepage": "https://github.com/firecrawl/pdf-inspector",
+  "publishConfig": {
+    "access": "public"
+  },
+  "napi": {
+    "binaryName": "pdf-inspector",
+    "targets": [
+      "x86_64-unknown-linux-gnu",
+      "aarch64-apple-darwin"
+    ],
+    "package": {
+      "name": "@firecrawl/pdf-inspector-js"
+    }
+  },
+  "scripts": {
+    "build": "napi build --platform --release",
+    "build:debug": "napi build --platform"
+  },
+  "devDependencies": {
+    "@napi-rs/cli": "^3.4.1"
+  }
+}