firecrawl-pdf-inspector 0.2.2 → 0.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +99 -0
- package/index.d.ts +48 -3
- package/index.js +56 -52
- package/package.json +16 -2
- package/pdf-inspector.darwin-arm64.node +0 -0
- package/pdf-inspector.linux-x64-gnu.node +0 -0
package/README.md
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
1
|
+
# firecrawl-pdf-inspector
|
|
2
|
+
|
|
3
|
+
Fast PDF classification and region-based text extraction for Node.js/Bun. Native Rust performance via [napi-rs](https://napi.rs).
|
|
4
|
+
|
|
5
|
+
Built by [Firecrawl](https://firecrawl.dev) for hybrid OCR pipelines — extract text from PDF structure where possible, fall back to OCR only when needed.
|
|
6
|
+
|
|
7
|
+
## Install
|
|
8
|
+
|
|
9
|
+
```bash
|
|
10
|
+
npm install firecrawl-pdf-inspector
|
|
11
|
+
# or
|
|
12
|
+
bun add firecrawl-pdf-inspector
|
|
13
|
+
```
|
|
14
|
+
|
|
15
|
+
Prebuilt binaries included for **linux-x64** and **macOS ARM64**. No Rust toolchain needed.
|
|
16
|
+
|
|
17
|
+
## API
|
|
18
|
+
|
|
19
|
+
### `classifyPdf(buffer: Buffer): PdfClassification`
|
|
20
|
+
|
|
21
|
+
Classify a PDF as TextBased, Scanned, Mixed, or ImageBased (~10-50ms). Returns which pages need OCR.
|
|
22
|
+
|
|
23
|
+
```typescript
|
|
24
|
+
import { classifyPdf } from 'firecrawl-pdf-inspector'
|
|
25
|
+
import { readFileSync } from 'fs'
|
|
26
|
+
|
|
27
|
+
const pdf = readFileSync('document.pdf')
|
|
28
|
+
const result = classifyPdf(pdf)
|
|
29
|
+
|
|
30
|
+
console.log(result.pdfType) // "TextBased" | "Scanned" | "Mixed" | "ImageBased"
|
|
31
|
+
console.log(result.pageCount) // 42
|
|
32
|
+
console.log(result.pagesNeedingOcr) // [5, 12, 15] (0-indexed)
|
|
33
|
+
console.log(result.confidence) // 0.875
|
|
34
|
+
```
|
|
35
|
+
|
|
36
|
+
### `extractTextInRegions(buffer: Buffer, pageRegions: PageRegions[]): PageRegionTexts[]`
|
|
37
|
+
|
|
38
|
+
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.
|
|
39
|
+
|
|
40
|
+
Each region result includes a `needsOcr` flag that signals unreliable extraction (empty text, GID-encoded fonts, garbage text, encoding issues).
|
|
41
|
+
|
|
42
|
+
```typescript
|
|
43
|
+
import { extractTextInRegions } from 'firecrawl-pdf-inspector'
|
|
44
|
+
|
|
45
|
+
const result = extractTextInRegions(pdf, [
|
|
46
|
+
{
|
|
47
|
+
page: 0, // 0-indexed
|
|
48
|
+
regions: [
|
|
49
|
+
[0, 0, 300, 400], // [x1, y1, x2, y2] in PDF points, top-left origin
|
|
50
|
+
[300, 0, 612, 400],
|
|
51
|
+
]
|
|
52
|
+
}
|
|
53
|
+
])
|
|
54
|
+
|
|
55
|
+
for (const region of result[0].regions) {
|
|
56
|
+
if (region.needsOcr) {
|
|
57
|
+
// Unreliable text — send this region to OCR instead
|
|
58
|
+
} else {
|
|
59
|
+
console.log(region.text) // Extracted text in reading order
|
|
60
|
+
}
|
|
61
|
+
}
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
## Types
|
|
65
|
+
|
|
66
|
+
```typescript
|
|
67
|
+
interface PdfClassification {
|
|
68
|
+
pdfType: string // "TextBased" | "Scanned" | "Mixed" | "ImageBased"
|
|
69
|
+
pageCount: number
|
|
70
|
+
pagesNeedingOcr: number[] // 0-indexed page numbers
|
|
71
|
+
confidence: number // 0.0 - 1.0
|
|
72
|
+
}
|
|
73
|
+
|
|
74
|
+
interface PageRegions {
|
|
75
|
+
page: number // 0-indexed
|
|
76
|
+
regions: number[][] // [[x1, y1, x2, y2], ...] in PDF points, top-left origin
|
|
77
|
+
}
|
|
78
|
+
|
|
79
|
+
interface PageRegionTexts {
|
|
80
|
+
page: number
|
|
81
|
+
regions: RegionText[]
|
|
82
|
+
}
|
|
83
|
+
|
|
84
|
+
interface RegionText {
|
|
85
|
+
text: string
|
|
86
|
+
needsOcr: boolean // true when text is unreliable
|
|
87
|
+
}
|
|
88
|
+
```
|
|
89
|
+
|
|
90
|
+
## Platforms
|
|
91
|
+
|
|
92
|
+
| Platform | Architecture | Supported |
|
|
93
|
+
|----------|-------------|-----------|
|
|
94
|
+
| Linux | x64 | Yes |
|
|
95
|
+
| macOS | ARM64 | Yes |
|
|
96
|
+
|
|
97
|
+
## License
|
|
98
|
+
|
|
99
|
+
MIT
|
package/index.d.ts
CHANGED
|
@@ -1,11 +1,18 @@
|
|
|
1
1
|
/* auto-generated by NAPI-RS */
|
|
2
2
|
/* eslint-disable */
|
|
3
3
|
/**
|
|
4
|
-
*
|
|
5
|
-
*
|
|
4
|
+
* Lightweight PDF classification — returns type, page count, and OCR pages.
|
|
5
|
+
* Faster than detectPdf as it skips building the full PdfResult.
|
|
6
|
+
* Pages in pagesNeedingOcr are 0-indexed.
|
|
6
7
|
*/
|
|
7
8
|
export declare function classifyPdf(buffer: Buffer): PdfClassification
|
|
8
9
|
|
|
10
|
+
/** Fast detection only — no text extraction or markdown. */
|
|
11
|
+
export declare function detectPdf(buffer: Buffer): PdfResult
|
|
12
|
+
|
|
13
|
+
/** Extract plain text from a PDF Buffer. */
|
|
14
|
+
export declare function extractText(buffer: Buffer): string
|
|
15
|
+
|
|
9
16
|
/**
|
|
10
17
|
* Extract text within bounding-box regions from a PDF.
|
|
11
18
|
*
|
|
@@ -13,13 +20,16 @@ export declare function classifyPdf(buffer: Buffer): PdfClassification
|
|
|
13
20
|
* this extracts PDF text within those regions — skipping GPU OCR
|
|
14
21
|
* for text-based pages.
|
|
15
22
|
*
|
|
16
|
-
* Each region result includes `
|
|
23
|
+
* Each region result includes `needsOcr` — set when the extracted text
|
|
17
24
|
* is unreliable (empty, GID-encoded fonts, garbage, encoding issues).
|
|
18
25
|
*
|
|
19
26
|
* Coordinates are PDF points with top-left origin.
|
|
20
27
|
*/
|
|
21
28
|
export declare function extractTextInRegions(buffer: Buffer, pageRegions: Array<PageRegions>): Array<PageRegionTexts>
|
|
22
29
|
|
|
30
|
+
/** Extract text with position information from a PDF Buffer. */
|
|
31
|
+
export declare function extractTextWithPositions(buffer: Buffer, pages?: Array<number> | undefined | null): Array<TextItem>
|
|
32
|
+
|
|
23
33
|
/** A page's regions for text extraction: (page_index_0based, bboxes). */
|
|
24
34
|
export interface PageRegions {
|
|
25
35
|
page: number
|
|
@@ -37,13 +47,48 @@ export interface PageRegionTexts {
|
|
|
37
47
|
export interface PdfClassification {
|
|
38
48
|
pdfType: string
|
|
39
49
|
pageCount: number
|
|
50
|
+
/** 0-indexed page numbers that need OCR. */
|
|
51
|
+
pagesNeedingOcr: Array<number>
|
|
52
|
+
confidence: number
|
|
53
|
+
}
|
|
54
|
+
|
|
55
|
+
/** Full PDF processing result with markdown and metadata. */
|
|
56
|
+
export interface PdfResult {
|
|
57
|
+
pdfType: string
|
|
58
|
+
markdown?: string
|
|
59
|
+
pageCount: number
|
|
60
|
+
processingTimeMs: number
|
|
61
|
+
/** 1-indexed page numbers that need OCR. */
|
|
40
62
|
pagesNeedingOcr: Array<number>
|
|
63
|
+
title?: string
|
|
41
64
|
confidence: number
|
|
65
|
+
isComplexLayout: boolean
|
|
66
|
+
pagesWithTables: Array<number>
|
|
67
|
+
pagesWithColumns: Array<number>
|
|
68
|
+
hasEncodingIssues: boolean
|
|
42
69
|
}
|
|
43
70
|
|
|
71
|
+
/** Process a PDF from a Buffer: detect type, extract text, and convert to Markdown. */
|
|
72
|
+
export declare function processPdf(buffer: Buffer, pages?: Array<number> | undefined | null): PdfResult
|
|
73
|
+
|
|
44
74
|
/** Extracted text for a single region. */
|
|
45
75
|
export interface RegionText {
|
|
46
76
|
text: string
|
|
47
77
|
/** `true` when the text should not be trusted (empty, GID fonts, garbage, encoding issues). */
|
|
48
78
|
needsOcr: boolean
|
|
49
79
|
}
|
|
80
|
+
|
|
81
|
+
/** A positioned text item extracted from a PDF. */
|
|
82
|
+
export interface TextItem {
|
|
83
|
+
text: string
|
|
84
|
+
x: number
|
|
85
|
+
y: number
|
|
86
|
+
width: number
|
|
87
|
+
height: number
|
|
88
|
+
font: string
|
|
89
|
+
fontSize: number
|
|
90
|
+
page: number
|
|
91
|
+
isBold: boolean
|
|
92
|
+
isItalic: boolean
|
|
93
|
+
itemType: string
|
|
94
|
+
}
|
package/index.js
CHANGED
|
@@ -77,8 +77,8 @@ function requireNative() {
|
|
|
77
77
|
try {
|
|
78
78
|
const binding = require('firecrawl-pdf-inspector-android-arm64')
|
|
79
79
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-android-arm64/package.json').version
|
|
80
|
-
if (bindingPackageVersion !== '0.
|
|
81
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
80
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
81
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
82
82
|
}
|
|
83
83
|
return binding
|
|
84
84
|
} catch (e) {
|
|
@@ -93,8 +93,8 @@ function requireNative() {
|
|
|
93
93
|
try {
|
|
94
94
|
const binding = require('firecrawl-pdf-inspector-android-arm-eabi')
|
|
95
95
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-android-arm-eabi/package.json').version
|
|
96
|
-
if (bindingPackageVersion !== '0.
|
|
97
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
96
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
97
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
98
98
|
}
|
|
99
99
|
return binding
|
|
100
100
|
} catch (e) {
|
|
@@ -114,8 +114,8 @@ function requireNative() {
|
|
|
114
114
|
try {
|
|
115
115
|
const binding = require('firecrawl-pdf-inspector-win32-x64-gnu')
|
|
116
116
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-win32-x64-gnu/package.json').version
|
|
117
|
-
if (bindingPackageVersion !== '0.
|
|
118
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
117
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
118
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
119
119
|
}
|
|
120
120
|
return binding
|
|
121
121
|
} catch (e) {
|
|
@@ -130,8 +130,8 @@ function requireNative() {
|
|
|
130
130
|
try {
|
|
131
131
|
const binding = require('firecrawl-pdf-inspector-win32-x64-msvc')
|
|
132
132
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-win32-x64-msvc/package.json').version
|
|
133
|
-
if (bindingPackageVersion !== '0.
|
|
134
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
133
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
134
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
135
135
|
}
|
|
136
136
|
return binding
|
|
137
137
|
} catch (e) {
|
|
@@ -147,8 +147,8 @@ function requireNative() {
|
|
|
147
147
|
try {
|
|
148
148
|
const binding = require('firecrawl-pdf-inspector-win32-ia32-msvc')
|
|
149
149
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-win32-ia32-msvc/package.json').version
|
|
150
|
-
if (bindingPackageVersion !== '0.
|
|
151
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
150
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
151
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
152
152
|
}
|
|
153
153
|
return binding
|
|
154
154
|
} catch (e) {
|
|
@@ -163,8 +163,8 @@ function requireNative() {
|
|
|
163
163
|
try {
|
|
164
164
|
const binding = require('firecrawl-pdf-inspector-win32-arm64-msvc')
|
|
165
165
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-win32-arm64-msvc/package.json').version
|
|
166
|
-
if (bindingPackageVersion !== '0.
|
|
167
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
166
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
167
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
168
168
|
}
|
|
169
169
|
return binding
|
|
170
170
|
} catch (e) {
|
|
@@ -182,8 +182,8 @@ function requireNative() {
|
|
|
182
182
|
try {
|
|
183
183
|
const binding = require('firecrawl-pdf-inspector-darwin-universal')
|
|
184
184
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-darwin-universal/package.json').version
|
|
185
|
-
if (bindingPackageVersion !== '0.
|
|
186
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
185
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
186
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
187
187
|
}
|
|
188
188
|
return binding
|
|
189
189
|
} catch (e) {
|
|
@@ -198,8 +198,8 @@ function requireNative() {
|
|
|
198
198
|
try {
|
|
199
199
|
const binding = require('firecrawl-pdf-inspector-darwin-x64')
|
|
200
200
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-darwin-x64/package.json').version
|
|
201
|
-
if (bindingPackageVersion !== '0.
|
|
202
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
201
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
202
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
203
203
|
}
|
|
204
204
|
return binding
|
|
205
205
|
} catch (e) {
|
|
@@ -214,8 +214,8 @@ function requireNative() {
|
|
|
214
214
|
try {
|
|
215
215
|
const binding = require('firecrawl-pdf-inspector-darwin-arm64')
|
|
216
216
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-darwin-arm64/package.json').version
|
|
217
|
-
if (bindingPackageVersion !== '0.
|
|
218
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
217
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
218
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
219
219
|
}
|
|
220
220
|
return binding
|
|
221
221
|
} catch (e) {
|
|
@@ -234,8 +234,8 @@ function requireNative() {
|
|
|
234
234
|
try {
|
|
235
235
|
const binding = require('firecrawl-pdf-inspector-freebsd-x64')
|
|
236
236
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-freebsd-x64/package.json').version
|
|
237
|
-
if (bindingPackageVersion !== '0.
|
|
238
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
237
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
238
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
239
239
|
}
|
|
240
240
|
return binding
|
|
241
241
|
} catch (e) {
|
|
@@ -250,8 +250,8 @@ function requireNative() {
|
|
|
250
250
|
try {
|
|
251
251
|
const binding = require('firecrawl-pdf-inspector-freebsd-arm64')
|
|
252
252
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-freebsd-arm64/package.json').version
|
|
253
|
-
if (bindingPackageVersion !== '0.
|
|
254
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
253
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
254
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
255
255
|
}
|
|
256
256
|
return binding
|
|
257
257
|
} catch (e) {
|
|
@@ -271,8 +271,8 @@ function requireNative() {
|
|
|
271
271
|
try {
|
|
272
272
|
const binding = require('firecrawl-pdf-inspector-linux-x64-musl')
|
|
273
273
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-x64-musl/package.json').version
|
|
274
|
-
if (bindingPackageVersion !== '0.
|
|
275
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
274
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
275
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
276
276
|
}
|
|
277
277
|
return binding
|
|
278
278
|
} catch (e) {
|
|
@@ -287,8 +287,8 @@ function requireNative() {
|
|
|
287
287
|
try {
|
|
288
288
|
const binding = require('firecrawl-pdf-inspector-linux-x64-gnu')
|
|
289
289
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-x64-gnu/package.json').version
|
|
290
|
-
if (bindingPackageVersion !== '0.
|
|
291
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
290
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
291
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
292
292
|
}
|
|
293
293
|
return binding
|
|
294
294
|
} catch (e) {
|
|
@@ -305,8 +305,8 @@ function requireNative() {
|
|
|
305
305
|
try {
|
|
306
306
|
const binding = require('firecrawl-pdf-inspector-linux-arm64-musl')
|
|
307
307
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-arm64-musl/package.json').version
|
|
308
|
-
if (bindingPackageVersion !== '0.
|
|
309
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
308
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
309
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
310
310
|
}
|
|
311
311
|
return binding
|
|
312
312
|
} catch (e) {
|
|
@@ -321,8 +321,8 @@ function requireNative() {
|
|
|
321
321
|
try {
|
|
322
322
|
const binding = require('firecrawl-pdf-inspector-linux-arm64-gnu')
|
|
323
323
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-arm64-gnu/package.json').version
|
|
324
|
-
if (bindingPackageVersion !== '0.
|
|
325
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
324
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
325
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
326
326
|
}
|
|
327
327
|
return binding
|
|
328
328
|
} catch (e) {
|
|
@@ -339,8 +339,8 @@ function requireNative() {
|
|
|
339
339
|
try {
|
|
340
340
|
const binding = require('firecrawl-pdf-inspector-linux-arm-musleabihf')
|
|
341
341
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-arm-musleabihf/package.json').version
|
|
342
|
-
if (bindingPackageVersion !== '0.
|
|
343
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
342
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
343
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
344
344
|
}
|
|
345
345
|
return binding
|
|
346
346
|
} catch (e) {
|
|
@@ -355,8 +355,8 @@ function requireNative() {
|
|
|
355
355
|
try {
|
|
356
356
|
const binding = require('firecrawl-pdf-inspector-linux-arm-gnueabihf')
|
|
357
357
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-arm-gnueabihf/package.json').version
|
|
358
|
-
if (bindingPackageVersion !== '0.
|
|
359
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
358
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
359
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
360
360
|
}
|
|
361
361
|
return binding
|
|
362
362
|
} catch (e) {
|
|
@@ -373,8 +373,8 @@ function requireNative() {
|
|
|
373
373
|
try {
|
|
374
374
|
const binding = require('firecrawl-pdf-inspector-linux-loong64-musl')
|
|
375
375
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-loong64-musl/package.json').version
|
|
376
|
-
if (bindingPackageVersion !== '0.
|
|
377
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
376
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
377
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
378
378
|
}
|
|
379
379
|
return binding
|
|
380
380
|
} catch (e) {
|
|
@@ -389,8 +389,8 @@ function requireNative() {
|
|
|
389
389
|
try {
|
|
390
390
|
const binding = require('firecrawl-pdf-inspector-linux-loong64-gnu')
|
|
391
391
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-loong64-gnu/package.json').version
|
|
392
|
-
if (bindingPackageVersion !== '0.
|
|
393
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
392
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
393
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
394
394
|
}
|
|
395
395
|
return binding
|
|
396
396
|
} catch (e) {
|
|
@@ -407,8 +407,8 @@ function requireNative() {
|
|
|
407
407
|
try {
|
|
408
408
|
const binding = require('firecrawl-pdf-inspector-linux-riscv64-musl')
|
|
409
409
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-riscv64-musl/package.json').version
|
|
410
|
-
if (bindingPackageVersion !== '0.
|
|
411
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
410
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
411
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
412
412
|
}
|
|
413
413
|
return binding
|
|
414
414
|
} catch (e) {
|
|
@@ -423,8 +423,8 @@ function requireNative() {
|
|
|
423
423
|
try {
|
|
424
424
|
const binding = require('firecrawl-pdf-inspector-linux-riscv64-gnu')
|
|
425
425
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-riscv64-gnu/package.json').version
|
|
426
|
-
if (bindingPackageVersion !== '0.
|
|
427
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
426
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
427
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
428
428
|
}
|
|
429
429
|
return binding
|
|
430
430
|
} catch (e) {
|
|
@@ -440,8 +440,8 @@ function requireNative() {
|
|
|
440
440
|
try {
|
|
441
441
|
const binding = require('firecrawl-pdf-inspector-linux-ppc64-gnu')
|
|
442
442
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-ppc64-gnu/package.json').version
|
|
443
|
-
if (bindingPackageVersion !== '0.
|
|
444
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
443
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
444
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
445
445
|
}
|
|
446
446
|
return binding
|
|
447
447
|
} catch (e) {
|
|
@@ -456,8 +456,8 @@ function requireNative() {
|
|
|
456
456
|
try {
|
|
457
457
|
const binding = require('firecrawl-pdf-inspector-linux-s390x-gnu')
|
|
458
458
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-s390x-gnu/package.json').version
|
|
459
|
-
if (bindingPackageVersion !== '0.
|
|
460
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
459
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
460
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
461
461
|
}
|
|
462
462
|
return binding
|
|
463
463
|
} catch (e) {
|
|
@@ -476,8 +476,8 @@ function requireNative() {
|
|
|
476
476
|
try {
|
|
477
477
|
const binding = require('firecrawl-pdf-inspector-openharmony-arm64')
|
|
478
478
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-openharmony-arm64/package.json').version
|
|
479
|
-
if (bindingPackageVersion !== '0.
|
|
480
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
479
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
480
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
481
481
|
}
|
|
482
482
|
return binding
|
|
483
483
|
} catch (e) {
|
|
@@ -492,8 +492,8 @@ function requireNative() {
|
|
|
492
492
|
try {
|
|
493
493
|
const binding = require('firecrawl-pdf-inspector-openharmony-x64')
|
|
494
494
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-openharmony-x64/package.json').version
|
|
495
|
-
if (bindingPackageVersion !== '0.
|
|
496
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
495
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
496
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
497
497
|
}
|
|
498
498
|
return binding
|
|
499
499
|
} catch (e) {
|
|
@@ -508,8 +508,8 @@ function requireNative() {
|
|
|
508
508
|
try {
|
|
509
509
|
const binding = require('firecrawl-pdf-inspector-openharmony-arm')
|
|
510
510
|
const bindingPackageVersion = require('firecrawl-pdf-inspector-openharmony-arm/package.json').version
|
|
511
|
-
if (bindingPackageVersion !== '0.
|
|
512
|
-
throw new Error(`Native binding package version mismatch, expected 0.
|
|
511
|
+
if (bindingPackageVersion !== '0.3.0' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
|
|
512
|
+
throw new Error(`Native binding package version mismatch, expected 0.3.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
513
513
|
}
|
|
514
514
|
return binding
|
|
515
515
|
} catch (e) {
|
|
@@ -577,4 +577,8 @@ if (!nativeBinding) {
|
|
|
577
577
|
|
|
578
578
|
module.exports = nativeBinding
|
|
579
579
|
module.exports.classifyPdf = nativeBinding.classifyPdf
|
|
580
|
+
module.exports.detectPdf = nativeBinding.detectPdf
|
|
581
|
+
module.exports.extractText = nativeBinding.extractText
|
|
580
582
|
module.exports.extractTextInRegions = nativeBinding.extractTextInRegions
|
|
583
|
+
module.exports.extractTextWithPositions = nativeBinding.extractTextWithPositions
|
|
584
|
+
module.exports.processPdf = nativeBinding.processPdf
|
package/package.json
CHANGED
|
@@ -1,18 +1,32 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "firecrawl-pdf-inspector",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.3.0",
|
|
4
|
+
"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.",
|
|
4
5
|
"main": "index.js",
|
|
5
6
|
"types": "index.d.ts",
|
|
6
7
|
"license": "MIT",
|
|
8
|
+
"keywords": [
|
|
9
|
+
"pdf",
|
|
10
|
+
"pdf-extraction",
|
|
11
|
+
"pdf-parser",
|
|
12
|
+
"text-extraction",
|
|
13
|
+
"ocr",
|
|
14
|
+
"pdf-classification",
|
|
15
|
+
"napi",
|
|
16
|
+
"rust",
|
|
17
|
+
"firecrawl"
|
|
18
|
+
],
|
|
7
19
|
"files": [
|
|
8
20
|
"index.js",
|
|
9
21
|
"index.d.ts",
|
|
10
|
-
"*.node"
|
|
22
|
+
"*.node",
|
|
23
|
+
"README.md"
|
|
11
24
|
],
|
|
12
25
|
"repository": {
|
|
13
26
|
"type": "git",
|
|
14
27
|
"url": "https://github.com/firecrawl/pdf-inspector"
|
|
15
28
|
},
|
|
29
|
+
"homepage": "https://github.com/firecrawl/pdf-inspector",
|
|
16
30
|
"publishConfig": {
|
|
17
31
|
"access": "public"
|
|
18
32
|
},
|
|
Binary file
|
|
Binary file
|