@firecrawl/pdf-inspector 1.17.0 → 1.18.0
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 +24 -2
- package/index.d.ts +108 -8
- package/index.js +53 -52
- package/package.json +7 -7
package/README.md
CHANGED
|
@@ -90,6 +90,28 @@ console.log(result.pagesNeedingOcr) // [5, 12, 15] (0-indexed)
|
|
|
90
90
|
console.log(result.confidence) // 0.875
|
|
91
91
|
```
|
|
92
92
|
|
|
93
|
+
### `extractTextWithPositions(buffer: Buffer, pages?: number[]): TextItem[]`
|
|
94
|
+
|
|
95
|
+
Every text item (plus image placeholders, links and form fields) with its font
|
|
96
|
+
and position. `x`/`y` are PDF points relative to the page's **visible page
|
|
97
|
+
box** (`CropBox ∩ MediaBox`, else the MediaBox), origin at the box's lower-left
|
|
98
|
+
corner with `y` growing upward. `extractTextInRegions` reads its regions
|
|
99
|
+
relative to the same box but from its top-left corner with `y` growing
|
|
100
|
+
downward, so flip with the box height: `boxHeight - y`. For text items `y` is
|
|
101
|
+
the baseline and `height` the font size, so
|
|
102
|
+
`[x, boxHeight - y - height, x + width, boxHeight - y]` covers the glyph band
|
|
103
|
+
above the baseline (descenders fall below it); for image, link and form-field
|
|
104
|
+
items `y` is the rect bottom and that box is exact. Pages whose CropBox equals
|
|
105
|
+
the MediaBox at `(0, 0)` are unaffected.
|
|
106
|
+
|
|
107
|
+
```typescript
|
|
108
|
+
import { extractTextWithPositions } from '@firecrawl/pdf-inspector'
|
|
109
|
+
|
|
110
|
+
for (const item of extractTextWithPositions(pdf, [1])) { // pages are 1-indexed
|
|
111
|
+
console.log(item.page, item.text, item.x, item.y, item.fontSize)
|
|
112
|
+
}
|
|
113
|
+
```
|
|
114
|
+
|
|
93
115
|
### `extractTextInRegions(buffer: Buffer, pageRegions: PageRegions[]): PageRegionTexts[]`
|
|
94
116
|
|
|
95
117
|
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.
|
|
@@ -103,7 +125,7 @@ const result = extractTextInRegions(pdf, [
|
|
|
103
125
|
{
|
|
104
126
|
page: 0, // 0-indexed
|
|
105
127
|
regions: [
|
|
106
|
-
[0, 0, 300, 400], // [x1, y1, x2, y2] in PDF points, top-left origin
|
|
128
|
+
[0, 0, 300, 400], // [x1, y1, x2, y2] in PDF points, top-left origin of the visible page box (CropBox)
|
|
107
129
|
[300, 0, 612, 400],
|
|
108
130
|
]
|
|
109
131
|
}
|
|
@@ -146,7 +168,7 @@ interface PdfClassification {
|
|
|
146
168
|
|
|
147
169
|
interface PageRegions {
|
|
148
170
|
page: number // 0-indexed
|
|
149
|
-
regions: number[][] // [[x1, y1, x2, y2], ...] in PDF points, top-left origin
|
|
171
|
+
regions: number[][] // [[x1, y1, x2, y2], ...] in PDF points, top-left origin of the visible page box
|
|
150
172
|
}
|
|
151
173
|
|
|
152
174
|
interface PageRegionTexts {
|
package/index.d.ts
CHANGED
|
@@ -25,7 +25,8 @@ export declare function detectPdf(buffer: Buffer): PdfResult
|
|
|
25
25
|
* `null` when the region does not contain a valid vector grid.
|
|
26
26
|
*
|
|
27
27
|
* `pageIdx` is 0-indexed. `regionPdfPtBbox` is `[x1,y1,x2,y2]` in PDF
|
|
28
|
-
* points with top-left origin
|
|
28
|
+
* points with top-left origin, relative to the visible page box (see
|
|
29
|
+
* `extractTextInRegions`). `renderDpi` is the DPI of the crop image that
|
|
29
30
|
* will consume the returned cell bboxes.
|
|
30
31
|
*/
|
|
31
32
|
export declare function detectVectorGridInRegion(buffer: Buffer, pageIdx: number, regionPdfPtBbox: Array<number>, renderDpi: number): VectorGridDetectionJs | null
|
|
@@ -80,7 +81,8 @@ export declare function extractStructureElements(buffer: Buffer, pages?: Array<n
|
|
|
80
81
|
* `needsOcr` is `false`. When no table is found, `text` is empty and
|
|
81
82
|
* `needsOcr` is `true` so the caller can fall back to GPU OCR.
|
|
82
83
|
*
|
|
83
|
-
* Coordinates are PDF points with top-left origin
|
|
84
|
+
* Coordinates are PDF points with top-left origin, relative to the visible
|
|
85
|
+
* page box (see `extractTextInRegions`).
|
|
84
86
|
*/
|
|
85
87
|
export declare function extractTablesInRegions(buffer: Buffer, pageRegions: Array<PageRegions>): Array<PageRegionTexts>
|
|
86
88
|
|
|
@@ -136,13 +138,35 @@ export declare function extractText(buffer: Buffer): string
|
|
|
136
138
|
* Each region result includes `needsOcr` — set when the extracted text
|
|
137
139
|
* is unreliable (empty, GID-encoded fonts, garbage, encoding issues).
|
|
138
140
|
*
|
|
139
|
-
* Coordinates are PDF points with top-left origin
|
|
141
|
+
* Coordinates are PDF points with top-left origin, relative to the visible
|
|
142
|
+
* page box (`CropBox ∩ MediaBox`, else the MediaBox) — the same box
|
|
143
|
+
* [`extractTextWithPositions`] reports items in, flipped to a top-left
|
|
144
|
+
* origin: a positioned `y` becomes `boxHeight - y`. For text items `y` is
|
|
145
|
+
* the baseline, so `[x, boxHeight - y - height, x + width, boxHeight - y]`
|
|
146
|
+
* covers the glyph band above the baseline; for image, link and form-field
|
|
147
|
+
* items `y` is the rect bottom and that box is exact.
|
|
140
148
|
*/
|
|
141
149
|
export declare function extractTextInRegions(buffer: Buffer, pageRegions: Array<PageRegions>): Array<PageRegionTexts>
|
|
142
150
|
|
|
143
|
-
/**
|
|
151
|
+
/**
|
|
152
|
+
* Extract text with position information from a PDF Buffer.
|
|
153
|
+
*
|
|
154
|
+
* Items are reported in PDF points relative to the page's visible page box
|
|
155
|
+
* (`CropBox ∩ MediaBox`, else the MediaBox) with the box's lower-left
|
|
156
|
+
* corner as origin — see [`TextItem`]. `pages` is 1-indexed (matching
|
|
157
|
+
* `TextItem.page`); omit it for the whole document.
|
|
158
|
+
*/
|
|
144
159
|
export declare function extractTextWithPositions(buffer: Buffer, pages?: Array<number> | undefined | null): Array<TextItem>
|
|
145
160
|
|
|
161
|
+
/**
|
|
162
|
+
* Extract text with positions from a PDF Buffer, together with the
|
|
163
|
+
* coordinate frame of every page whose text was predominantly rotated.
|
|
164
|
+
* Items on such a page are expressed in the turned frame (their dominant
|
|
165
|
+
* runs read left-to-right there); pages absent from `pageRotations` are
|
|
166
|
+
* upright.
|
|
167
|
+
*/
|
|
168
|
+
export declare function extractTextWithPositionsAndRotations(buffer: Buffer): PositionedText
|
|
169
|
+
|
|
146
170
|
/** Type of a positioned text item. */
|
|
147
171
|
export declare const enum ItemType {
|
|
148
172
|
Text = 'Text',
|
|
@@ -260,7 +284,11 @@ export interface PageOcrReasons {
|
|
|
260
284
|
/** A page's regions for text extraction: (page_index_0based, bboxes). */
|
|
261
285
|
export interface PageRegions {
|
|
262
286
|
page: number
|
|
263
|
-
/**
|
|
287
|
+
/**
|
|
288
|
+
* Each bbox is [x1, y1, x2, y2] in PDF points, top-left origin of the
|
|
289
|
+
* visible page box (`CropBox ∩ MediaBox`, else the MediaBox) — the
|
|
290
|
+
* frame of a rendered page image.
|
|
291
|
+
*/
|
|
264
292
|
regions: Array<Array<number>>
|
|
265
293
|
}
|
|
266
294
|
|
|
@@ -270,6 +298,18 @@ export interface PageRegionTexts {
|
|
|
270
298
|
regions: Array<RegionText>
|
|
271
299
|
}
|
|
272
300
|
|
|
301
|
+
/** The coordinate frame of a page whose text was predominantly rotated. */
|
|
302
|
+
export interface PageRotation {
|
|
303
|
+
/** 1-indexed page number, matching `TextItem.page`. */
|
|
304
|
+
page: number
|
|
305
|
+
/**
|
|
306
|
+
* `"ccw"` when the page's runs read bottom-to-top and the frame was
|
|
307
|
+
* turned so they read left-to-right, `"cw"` for runs reading
|
|
308
|
+
* top-to-bottom.
|
|
309
|
+
*/
|
|
310
|
+
rotation: string
|
|
311
|
+
}
|
|
312
|
+
|
|
273
313
|
/** Combined per-page markdown extraction and layout classification result. */
|
|
274
314
|
export interface PagesExtractionResult {
|
|
275
315
|
/** Per-page markdown results. */
|
|
@@ -321,6 +361,16 @@ export declare const enum PdfType {
|
|
|
321
361
|
Mixed = 'Mixed'
|
|
322
362
|
}
|
|
323
363
|
|
|
364
|
+
/** Positioned text plus the frame of every page whose text was turned. */
|
|
365
|
+
export interface PositionedText {
|
|
366
|
+
items: Array<TextItem>
|
|
367
|
+
/**
|
|
368
|
+
* One entry per re-based page; pages absent here are upright and their
|
|
369
|
+
* items are in plain page coordinates.
|
|
370
|
+
*/
|
|
371
|
+
pageRotations: Array<PageRotation>
|
|
372
|
+
}
|
|
373
|
+
|
|
324
374
|
/** Process a PDF from a Buffer: detect type, extract text, and convert to Markdown. */
|
|
325
375
|
export declare function processPdf(buffer: Buffer, pages?: Array<number> | undefined | null): PdfResult
|
|
326
376
|
|
|
@@ -366,7 +416,8 @@ export interface StructuredCellJs {
|
|
|
366
416
|
text: string
|
|
367
417
|
/**
|
|
368
418
|
* Axis-aligned bbox `[x1, y1, x2, y2]` in page PDF-points, top-left
|
|
369
|
-
* origin
|
|
419
|
+
* origin, relative to the visible page box (the crop's own frame).
|
|
420
|
+
* Useful for debug overlays or per-cell post-processing.
|
|
370
421
|
*/
|
|
371
422
|
pagePtBbox: Array<number>
|
|
372
423
|
}
|
|
@@ -405,13 +456,52 @@ export interface TableExtractionResultJs {
|
|
|
405
456
|
fallbackReason?: string
|
|
406
457
|
}
|
|
407
458
|
|
|
408
|
-
/**
|
|
459
|
+
/**
|
|
460
|
+
* A positioned text item extracted from a PDF.
|
|
461
|
+
*
|
|
462
|
+
* `x`/`y` are PDF points relative to the page's **visible page box**
|
|
463
|
+
* (`CropBox ∩ MediaBox`, else the MediaBox; a CropBox that does not overlap
|
|
464
|
+
* the MediaBox is ignored, and a page without a MediaBox is measured against
|
|
465
|
+
* US Letter), origin at the box's lower-left corner with `y` growing upward.
|
|
466
|
+
* [`extractTextInRegions`] reads its regions relative to the same box but
|
|
467
|
+
* from its top-left corner with `y` growing downward; flip with the box
|
|
468
|
+
* height. `/Rotate` is not applied.
|
|
469
|
+
*
|
|
470
|
+
* On a page whose text is predominantly rotated the extractor turns the
|
|
471
|
+
* coordinate frame so that text reads left-to-right, and the shift into the
|
|
472
|
+
* visible page box is turned the same way; items on such a page are
|
|
473
|
+
* expressed in that turned frame. Use
|
|
474
|
+
* [`extract_text_with_positions_and_rotations`] (`extractTextWithPositionsAndRotations`
|
|
475
|
+
* in JavaScript) to learn which pages were turned and which way.
|
|
476
|
+
*/
|
|
409
477
|
export interface TextItem {
|
|
410
478
|
text: string
|
|
479
|
+
/** Left edge, in PDF points from the visible page box's left edge. */
|
|
411
480
|
x: number
|
|
481
|
+
/**
|
|
482
|
+
* Baseline for text (rect bottom edge for image, link and form-field
|
|
483
|
+
* items), in PDF points from the visible page box's bottom edge.
|
|
484
|
+
*/
|
|
412
485
|
y: number
|
|
413
486
|
width: number
|
|
414
487
|
height: number
|
|
488
|
+
/**
|
|
489
|
+
* Rotation of the run's baseline in degrees counter-clockwise from the
|
|
490
|
+
* page's x axis, in `[0, 360)`: `0` for ordinary horizontal text, `90`
|
|
491
|
+
* for text reading bottom-to-top (a rotated margin stamp), `270` for
|
|
492
|
+
* top-to-bottom, `180` for upside-down. `x`/`y`/`width`/`height` is the
|
|
493
|
+
* run's axis-aligned box, so a vertical run is tall and thin (height
|
|
494
|
+
* ≫ width) instead of zero-width.
|
|
495
|
+
*/
|
|
496
|
+
rotation: number
|
|
497
|
+
/**
|
|
498
|
+
* Whether the run's advance came from font metrics. `false` when the
|
|
499
|
+
* font carries no width information (or an ActualText span's advance
|
|
500
|
+
* could not be recovered): the box's extent along the baseline is then
|
|
501
|
+
* an estimate of half an em per painted glyph (an ActualText span counts
|
|
502
|
+
* the glyphs it covers, not its replacement text), not a measurement.
|
|
503
|
+
*/
|
|
504
|
+
advanceKnown: boolean
|
|
415
505
|
font: string
|
|
416
506
|
fontTag: string
|
|
417
507
|
fontSize: number
|
|
@@ -428,6 +518,15 @@ export interface TextItem {
|
|
|
428
518
|
* x-height).
|
|
429
519
|
*/
|
|
430
520
|
isStrikeout: boolean
|
|
521
|
+
/**
|
|
522
|
+
* Signed baseline offset (PDF points, y-up) of a super/subscript glyph
|
|
523
|
+
* run from the body baseline it is attached to; `0` for normal text.
|
|
524
|
+
* Positive = raised (superscript: footnote/affiliation markers,
|
|
525
|
+
* exponents), negative = lowered (subscript). Emit `<sup>`/`<sub>` from
|
|
526
|
+
* the sign. Digit-only markers beside a word are already fused into it
|
|
527
|
+
* as Unicode super/subscript characters ("word²") and carry `0`.
|
|
528
|
+
*/
|
|
529
|
+
baselineShift: number
|
|
431
530
|
itemType: ItemType
|
|
432
531
|
/** URL for link items, `None` for other types. */
|
|
433
532
|
linkUrl?: string
|
|
@@ -454,7 +553,8 @@ export interface TsrTableInputJs {
|
|
|
454
553
|
page: number
|
|
455
554
|
/**
|
|
456
555
|
* Crop bbox on the page, `[x1, y1, x2, y2]` in PDF points with
|
|
457
|
-
* top-left origin
|
|
556
|
+
* top-left origin, relative to the visible page box (see
|
|
557
|
+
* `extractTextInRegions`).
|
|
458
558
|
*/
|
|
459
559
|
cropPdfPtBbox: Array<number>
|
|
460
560
|
/** DPI the crop image was rendered at (e.g. `200.0`). */
|
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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 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 !== '1.18.0' && 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 1.18.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
513
513
|
}
|
|
514
514
|
return binding
|
|
515
515
|
} catch (e) {
|
|
@@ -590,6 +590,7 @@ module.exports.extractTablesWithStructureCells = nativeBinding.extractTablesWith
|
|
|
590
590
|
module.exports.extractText = nativeBinding.extractText
|
|
591
591
|
module.exports.extractTextInRegions = nativeBinding.extractTextInRegions
|
|
592
592
|
module.exports.extractTextWithPositions = nativeBinding.extractTextWithPositions
|
|
593
|
+
module.exports.extractTextWithPositionsAndRotations = nativeBinding.extractTextWithPositionsAndRotations
|
|
593
594
|
module.exports.ItemType = nativeBinding.ItemType
|
|
594
595
|
module.exports.OcrMode = nativeBinding.OcrMode
|
|
595
596
|
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": "1.18.0",
|
|
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": "1.18.0",
|
|
56
|
+
"@firecrawl/pdf-inspector-linux-x64-musl": "1.18.0",
|
|
57
|
+
"@firecrawl/pdf-inspector-linux-arm64-gnu": "1.18.0",
|
|
58
|
+
"@firecrawl/pdf-inspector-linux-arm64-musl": "1.18.0",
|
|
59
|
+
"@firecrawl/pdf-inspector-darwin-arm64": "1.18.0",
|
|
60
|
+
"@firecrawl/pdf-inspector-win32-x64-msvc": "1.18.0"
|
|
61
61
|
}
|
|
62
62
|
}
|