@firecrawl/pdf-inspector 1.23.0 → 1.25.0
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 +42 -3
- package/index.d.ts +65 -0
- package/index.js +53 -52
- package/package.json +7 -7
package/README.md
CHANGED
|
@@ -92,6 +92,9 @@ console.log(result.confidence) // 0.875
|
|
|
92
92
|
|
|
93
93
|
### `extractTextWithPositions(buffer: Buffer, pages?: number[], options?: FrameOptions): TextItem[]`
|
|
94
94
|
|
|
95
|
+
An async variant, `extractTextWithPositionsAsync`, takes the same arguments and
|
|
96
|
+
resolves to the same items (see [Async variants](#async-variants)).
|
|
97
|
+
|
|
95
98
|
Every text item (plus image placeholders, links and form fields) with its font
|
|
96
99
|
and position. `x`/`y` are PDF points relative to the page's **visible page
|
|
97
100
|
box** (`CropBox ∩ MediaBox`, else the MediaBox), origin at the box's lower-left
|
|
@@ -143,6 +146,22 @@ nothing and no two advances differ but fewer than a dozen share one. Many
|
|
|
143
146
|
producers write `/Flags 4`
|
|
144
147
|
whatever the face, so the flag is only ever read as a yes.
|
|
145
148
|
|
|
149
|
+
`fillColor` and `strokeColor` are the colours a run was shown with, as sRGB
|
|
150
|
+
`[red, green, blue]` arrays of 0..255: its glyphs are filled with the first in
|
|
151
|
+
render modes 0, 2, 4 and 6 and outlined with the second in modes 1, 2, 5 and
|
|
152
|
+
6. DeviceRGB is read as sRGB, DeviceGray as three equal components and
|
|
153
|
+
DeviceCMYK converted the way the PDF specification converts it to DeviceRGB;
|
|
154
|
+
ICCBased spaces are read by their component count and Indexed spaces through
|
|
155
|
+
their palette. A colour is omitted for any other colour space (Separation,
|
|
156
|
+
DeviceN, Pattern, CalRGB, Lab, ...). `renderMode` is the text render mode
|
|
157
|
+
(`Tr`) the run was shown with, 0..7: runs in mode 3 (invisible, the mode of OCR
|
|
158
|
+
text layers) and mode 7 (clipping only) put no glyphs on the page, so a caller
|
|
159
|
+
can tell visible text from invisible text. The colours and the mode are
|
|
160
|
+
graphics state — they hold across text objects, `q`/`Q` save and restore them,
|
|
161
|
+
and a Form XObject starts with the paint it was invoked under — and reporting
|
|
162
|
+
them changes nothing about which runs are extracted. All three are omitted for
|
|
163
|
+
image, link and form-field items, and a merged item keeps its first run's.
|
|
164
|
+
|
|
146
165
|
`legacySymbolRewrite: true` marks items whose decoded text includes a character
|
|
147
166
|
changed by legacy symbol cleanup. Merged items retain this evidence from either
|
|
148
167
|
source, and split items conservatively inherit it. The field is omitted when
|
|
@@ -228,18 +247,20 @@ for (const region of result[0].regions) {
|
|
|
228
247
|
|
|
229
248
|
### Async variants
|
|
230
249
|
|
|
231
|
-
`processPdf`, `classifyPdf`, and `
|
|
250
|
+
`processPdf`, `classifyPdf`, `extractPagesMarkdown`, and `extractTextWithPositions` are synchronous and parse on the calling thread — in Node, that's the event loop. For a one-off call in a script that's fine, but in a server a large document can hold the loop for tens to hundreds of milliseconds, and an unusual one for much longer.
|
|
232
251
|
|
|
233
|
-
`processPdfAsync`, `classifyPdfAsync`, and `
|
|
252
|
+
`processPdfAsync`, `classifyPdfAsync`, `extractPagesMarkdownAsync`, and `extractTextWithPositionsAsync` take the same arguments and produce the same results, but run the parse on the libuv thread pool and return a promise, keeping the event loop free. Invalid options still throw when the call is made. The input buffer is copied before the call returns, so it's safe to reuse or mutate immediately:
|
|
234
253
|
|
|
235
254
|
```typescript
|
|
236
|
-
import { classifyPdfAsync, extractPagesMarkdownAsync } from '@firecrawl/pdf-inspector'
|
|
255
|
+
import { classifyPdfAsync, extractPagesMarkdownAsync, extractTextWithPositionsAsync } from '@firecrawl/pdf-inspector'
|
|
237
256
|
|
|
238
257
|
const classification = await classifyPdfAsync(pdf)
|
|
239
258
|
if (classification.pdfType === 'TextBased') {
|
|
240
259
|
const { pages } = await extractPagesMarkdownAsync(pdf)
|
|
241
260
|
// ...
|
|
242
261
|
}
|
|
262
|
+
|
|
263
|
+
const items = await extractTextWithPositionsAsync(pdf, [1, 2], { frame: 'display' })
|
|
243
264
|
```
|
|
244
265
|
|
|
245
266
|
## Types
|
|
@@ -252,6 +273,24 @@ interface PdfClassification {
|
|
|
252
273
|
confidence: number // 0.0 - 1.0
|
|
253
274
|
}
|
|
254
275
|
|
|
276
|
+
interface PdfResult { // processPdf / detectPdf (excerpt)
|
|
277
|
+
pdfType: string
|
|
278
|
+
markdown?: string // omitted by detectPdf
|
|
279
|
+
pageCount: number
|
|
280
|
+
// The document information dictionary's entries, decoded as PDF text
|
|
281
|
+
// strings (UTF-16 or UTF-8 after a byte order mark, PDFDocEncoding
|
|
282
|
+
// otherwise); each omitted when missing or not a string.
|
|
283
|
+
title?: string
|
|
284
|
+
author?: string
|
|
285
|
+
subject?: string
|
|
286
|
+
keywords?: string
|
|
287
|
+
creator?: string // the application the document was authored in
|
|
288
|
+
producer?: string // the application that wrote the PDF
|
|
289
|
+
creationDate?: string // as written, e.g. "D:20240115103000+01'00'"
|
|
290
|
+
modDate?: string
|
|
291
|
+
// ...
|
|
292
|
+
}
|
|
293
|
+
|
|
255
294
|
interface PageRegions {
|
|
256
295
|
page: number // 0-indexed
|
|
257
296
|
regions: number[][] // [[x1, y1, x2, y2], ...] in PDF points, top-left origin of the visible page box
|
package/index.d.ts
CHANGED
|
@@ -205,6 +205,15 @@ export declare function extractTextWithPositions(buffer: Buffer, pages?: Array<n
|
|
|
205
205
|
*/
|
|
206
206
|
export declare function extractTextWithPositionsAndRotations(buffer: Buffer, pages?: Array<number> | undefined | null, options?: FrameOptions | undefined | null): PositionedText
|
|
207
207
|
|
|
208
|
+
/**
|
|
209
|
+
* Async variant of [`extractTextWithPositions`]: same result, but the
|
|
210
|
+
* extraction runs on the libuv thread pool instead of the event loop and
|
|
211
|
+
* the call returns a promise. Options are validated before the call
|
|
212
|
+
* returns (an unknown frame throws synchronously, as in the sync call), and
|
|
213
|
+
* the buffer is copied then, so it may be reused or mutated immediately.
|
|
214
|
+
*/
|
|
215
|
+
export declare function extractTextWithPositionsAsync(buffer: Buffer, pages?: Array<number> | undefined | null, options?: FrameOptions | undefined | null): Promise<Array<TextItem>>
|
|
216
|
+
|
|
208
217
|
/**
|
|
209
218
|
* A font whose ToUnicode CMap — or, for a font without one, the embedded
|
|
210
219
|
* program's cmap table — had no entry for some of the codes the document
|
|
@@ -451,7 +460,36 @@ export interface PdfResult {
|
|
|
451
460
|
pagesNeedingOcr: Array<number>
|
|
452
461
|
/** Machine-readable OCR reasons by 1-indexed page. */
|
|
453
462
|
ocrReasonsByPage: Array<PageOcrReasons>
|
|
463
|
+
/**
|
|
464
|
+
* The `/Title` of the document information dictionary, decoded as a PDF
|
|
465
|
+
* text string (UTF-16 or UTF-8 after a byte order mark, PDFDocEncoding
|
|
466
|
+
* otherwise). Omitted when the entry is missing or not a string. The
|
|
467
|
+
* entries below follow the same decoding and missing-value rule.
|
|
468
|
+
*/
|
|
454
469
|
title?: string
|
|
470
|
+
/** The document information dictionary's `/Author`. */
|
|
471
|
+
author?: string
|
|
472
|
+
/** The document information dictionary's `/Subject`. */
|
|
473
|
+
subject?: string
|
|
474
|
+
/** The document information dictionary's `/Keywords`. */
|
|
475
|
+
keywords?: string
|
|
476
|
+
/**
|
|
477
|
+
* The document information dictionary's `/Creator`: the application the
|
|
478
|
+
* document was authored in.
|
|
479
|
+
*/
|
|
480
|
+
creator?: string
|
|
481
|
+
/**
|
|
482
|
+
* The document information dictionary's `/Producer`: the application
|
|
483
|
+
* that wrote the PDF.
|
|
484
|
+
*/
|
|
485
|
+
producer?: string
|
|
486
|
+
/**
|
|
487
|
+
* The document information dictionary's `/CreationDate` as written, a
|
|
488
|
+
* PDF date string such as `D:20240115103000+01'00'`.
|
|
489
|
+
*/
|
|
490
|
+
creationDate?: string
|
|
491
|
+
/** The document information dictionary's `/ModDate` as written. */
|
|
492
|
+
modDate?: string
|
|
455
493
|
confidence: number
|
|
456
494
|
isComplexLayout: boolean
|
|
457
495
|
pagesWithTables: Array<number>
|
|
@@ -673,6 +711,33 @@ export interface TextItem {
|
|
|
673
711
|
* only ever read as a yes.
|
|
674
712
|
*/
|
|
675
713
|
fixedPitch?: boolean
|
|
714
|
+
/**
|
|
715
|
+
* The fill colour the run was shown with, as sRGB `[red, green, blue]`
|
|
716
|
+
* of 0..255: what its glyphs are filled with in the render modes that
|
|
717
|
+
* fill (0, 2, 4, 6). DeviceRGB is read as sRGB, DeviceGray as three
|
|
718
|
+
* equal components and DeviceCMYK converted as the PDF specification
|
|
719
|
+
* converts it to DeviceRGB; ICCBased spaces are read by their component
|
|
720
|
+
* count and Indexed spaces through their palette. Omitted for any other
|
|
721
|
+
* colour space (Separation, DeviceN, Pattern, CalRGB, Lab, ...), and for
|
|
722
|
+
* image, link and form-field items. A merged item keeps its first run's.
|
|
723
|
+
*/
|
|
724
|
+
fillColor?: [number, number, number]
|
|
725
|
+
/**
|
|
726
|
+
* The stroke colour the run was shown with, read like `fillColor`: what
|
|
727
|
+
* its glyph outlines are stroked with in the render modes that stroke
|
|
728
|
+
* (1, 2, 5, 6).
|
|
729
|
+
*/
|
|
730
|
+
strokeColor?: [number, number, number]
|
|
731
|
+
/**
|
|
732
|
+
* The text render mode (`Tr`) the run was shown with, 0..7: 0 fill, 1
|
|
733
|
+
* stroke, 2 fill and stroke, 3 invisible (the mode of OCR text layers),
|
|
734
|
+
* 4..6 as 0..2 and clip, 7 clip only. Runs in modes 3 and 7 put no
|
|
735
|
+
* glyphs on the page. The mode holds across text objects, is saved and
|
|
736
|
+
* restored by `q`/`Q` and is inherited by Form XObjects. Which runs are
|
|
737
|
+
* extracted is unchanged by it. Omitted for image, link and form-field
|
|
738
|
+
* items.
|
|
739
|
+
*/
|
|
740
|
+
renderMode?: number
|
|
676
741
|
/**
|
|
677
742
|
* Underline detected geometrically (drawn rule/thin rect under the
|
|
678
743
|
* baseline) — PDFs carry no underline font flag.
|
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 !== '1.
|
|
81
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
80
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
97
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
96
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
118
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
117
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
134
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
133
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
151
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
150
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
167
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
166
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
186
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
185
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
202
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
201
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
218
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
217
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
238
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
237
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
254
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
253
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
275
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
274
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
291
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
290
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
309
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
308
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
325
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
324
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
343
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
342
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
359
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
358
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
377
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
376
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
393
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
392
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
411
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
410
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
427
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
426
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
444
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
443
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
460
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
459
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
480
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
479
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
496
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
495
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 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 !== '1.
|
|
512
|
-
throw new Error(`Native binding package version mismatch, expected 1.
|
|
511
|
+
if (bindingPackageVersion !== '1.25.0' && 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 1.25.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
513
513
|
}
|
|
514
514
|
return binding
|
|
515
515
|
} catch (e) {
|
|
@@ -592,6 +592,7 @@ module.exports.extractText = nativeBinding.extractText
|
|
|
592
592
|
module.exports.extractTextInRegions = nativeBinding.extractTextInRegions
|
|
593
593
|
module.exports.extractTextWithPositions = nativeBinding.extractTextWithPositions
|
|
594
594
|
module.exports.extractTextWithPositionsAndRotations = nativeBinding.extractTextWithPositionsAndRotations
|
|
595
|
+
module.exports.extractTextWithPositionsAsync = nativeBinding.extractTextWithPositionsAsync
|
|
595
596
|
module.exports.ItemType = nativeBinding.ItemType
|
|
596
597
|
module.exports.OcrMode = nativeBinding.OcrMode
|
|
597
598
|
module.exports.PageContentSource = nativeBinding.PageContentSource
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@firecrawl/pdf-inspector",
|
|
3
|
-
"version": "1.
|
|
3
|
+
"version": "1.25.0",
|
|
4
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.",
|
|
5
5
|
"main": "index.js",
|
|
6
6
|
"types": "index.d.ts",
|
|
@@ -52,11 +52,11 @@
|
|
|
52
52
|
"@napi-rs/cli": "^3.4.1"
|
|
53
53
|
},
|
|
54
54
|
"optionalDependencies": {
|
|
55
|
-
"@firecrawl/pdf-inspector-linux-x64-gnu": "1.
|
|
56
|
-
"@firecrawl/pdf-inspector-linux-x64-musl": "1.
|
|
57
|
-
"@firecrawl/pdf-inspector-linux-arm64-gnu": "1.
|
|
58
|
-
"@firecrawl/pdf-inspector-linux-arm64-musl": "1.
|
|
59
|
-
"@firecrawl/pdf-inspector-darwin-arm64": "1.
|
|
60
|
-
"@firecrawl/pdf-inspector-win32-x64-msvc": "1.
|
|
55
|
+
"@firecrawl/pdf-inspector-linux-x64-gnu": "1.25.0",
|
|
56
|
+
"@firecrawl/pdf-inspector-linux-x64-musl": "1.25.0",
|
|
57
|
+
"@firecrawl/pdf-inspector-linux-arm64-gnu": "1.25.0",
|
|
58
|
+
"@firecrawl/pdf-inspector-linux-arm64-musl": "1.25.0",
|
|
59
|
+
"@firecrawl/pdf-inspector-darwin-arm64": "1.25.0",
|
|
60
|
+
"@firecrawl/pdf-inspector-win32-x64-msvc": "1.25.0"
|
|
61
61
|
}
|
|
62
62
|
}
|