@firecrawl/pdf-inspector 1.19.0 → 1.20.0
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 +60 -2
- package/index.d.ts +54 -9
- package/index.js +52 -52
- package/package.json +7 -7
package/README.md
CHANGED
|
@@ -90,7 +90,7 @@ 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[]`
|
|
93
|
+
### `extractTextWithPositions(buffer: Buffer, pages?: number[], options?: FrameOptions): TextItem[]`
|
|
94
94
|
|
|
95
95
|
Every text item (plus image placeholders, links and form fields) with its font
|
|
96
96
|
and position. `x`/`y` are PDF points relative to the page's **visible page
|
|
@@ -104,6 +104,16 @@ above the baseline (descenders fall below it); for image, link and form-field
|
|
|
104
104
|
items `y` is the rect bottom and that box is exact. Pages whose CropBox equals
|
|
105
105
|
the MediaBox at `(0, 0)` are unaffected.
|
|
106
106
|
|
|
107
|
+
By default the page `/Rotate` is not applied and a page whose text is
|
|
108
|
+
predominantly rotated is turned so that text reads left-to-right (this is the
|
|
109
|
+
`"sheet"` frame; `extractTextWithPositionsAndRotations` reports which pages
|
|
110
|
+
were turned). Pass `{ frame: "display" }` to get every item in the rendered
|
|
111
|
+
page's frame instead — the visible page box turned clockwise by the page's
|
|
112
|
+
inheritable `/Rotate`, lower-left origin, `y` up, with the turn of a rotated
|
|
113
|
+
page undone — so `x`/`y`/`width`/`height` and `rotation` describe the item as
|
|
114
|
+
a renderer draws it. Pages with `/Rotate 0` whose text is not predominantly
|
|
115
|
+
rotated are identical in both frames.
|
|
116
|
+
|
|
107
117
|
`legacySymbolRewrite: true` marks items whose decoded text includes a character
|
|
108
118
|
changed by legacy symbol cleanup. Merged items retain this evidence from either
|
|
109
119
|
source, and split items conservatively inherit it. The field is omitted when
|
|
@@ -117,12 +127,38 @@ import { extractTextWithPositions } from '@firecrawl/pdf-inspector'
|
|
|
117
127
|
for (const item of extractTextWithPositions(pdf, [1])) { // pages are 1-indexed
|
|
118
128
|
console.log(item.page, item.text, item.x, item.y, item.fontSize)
|
|
119
129
|
}
|
|
130
|
+
|
|
131
|
+
// Boxes as a renderer draws the page (`/Rotate` applied)
|
|
132
|
+
const rendered = extractTextWithPositions(pdf, undefined, { frame: 'display' })
|
|
120
133
|
```
|
|
121
134
|
|
|
122
|
-
### `
|
|
135
|
+
### `extractTextWithPositionsAndRotations(buffer: Buffer, pages?: number[], options?: FrameOptions): PositionedText`
|
|
136
|
+
|
|
137
|
+
`extractTextWithPositions` plus `pageRotations`, one `{ page, rotation: 'ccw' | 'cw' }`
|
|
138
|
+
entry per page whose text was predominantly rotated and therefore turned in the
|
|
139
|
+
`"sheet"` frame. With `{ frame: "display" }` the items are in the rendered
|
|
140
|
+
page's frame and the entries only report which pages were turned.
|
|
141
|
+
|
|
142
|
+
### `extractTextInRegions(buffer: Buffer, pageRegions: PageRegions[], options?: FrameOptions): PageRegionTexts[]`
|
|
123
143
|
|
|
124
144
|
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.
|
|
125
145
|
|
|
146
|
+
Region bboxes are `[x1, y1, x2, y2]` in PDF points with a top-left origin,
|
|
147
|
+
relative to the visible page box. By default they are read in the `"sheet"`
|
|
148
|
+
frame: the box as laid out in the content stream, `/Rotate` not applied, the
|
|
149
|
+
frame `extractTextWithPositions` reports items in flipped to a top-left
|
|
150
|
+
origin. The sheet frame matches a rendered page image only when both hold:
|
|
151
|
+
the page has `/Rotate 0`, and its text is not predominantly rotated. A page
|
|
152
|
+
whose text is predominantly rotated is turned in the sheet frame so that text
|
|
153
|
+
reads left-to-right (`extractTextWithPositionsAndRotations` reports which
|
|
154
|
+
pages were turned), so its sheet-frame bboxes do not match the rendered image
|
|
155
|
+
even with `/Rotate 0`. Pass `{ frame: "display" }` to give bboxes on the
|
|
156
|
+
rendered page (the visible box turned clockwise by the page's inheritable
|
|
157
|
+
`/Rotate`; the page-level turn of a predominantly rotated page is undone
|
|
158
|
+
first, while individual runs keep their own `rotation`), as a layout model
|
|
159
|
+
working on page images reports them, whatever the page's `/Rotate` or text
|
|
160
|
+
direction. `extractTablesInRegions` takes the same option.
|
|
161
|
+
|
|
126
162
|
Each region result includes a `needsOcr` flag that signals unreliable extraction (empty text, GID-encoded fonts, garbage text, encoding issues). When the cause is a suspected garbled text layer, `ocrReason` is set to `"suspected_garbled_text"`.
|
|
127
163
|
|
|
128
164
|
```typescript
|
|
@@ -138,6 +174,13 @@ const result = extractTextInRegions(pdf, [
|
|
|
138
174
|
}
|
|
139
175
|
])
|
|
140
176
|
|
|
177
|
+
// The same call with bboxes taken from a rendered page image
|
|
178
|
+
const onRendered = extractTextInRegions(
|
|
179
|
+
pdf,
|
|
180
|
+
[{ page: 0, regions: [[0, 0, 300, 400]] }],
|
|
181
|
+
{ frame: 'display' },
|
|
182
|
+
)
|
|
183
|
+
|
|
141
184
|
for (const region of result[0].regions) {
|
|
142
185
|
if (region.needsOcr) {
|
|
143
186
|
// Unreliable text — send this region to OCR instead
|
|
@@ -176,6 +219,21 @@ interface PdfClassification {
|
|
|
176
219
|
interface PageRegions {
|
|
177
220
|
page: number // 0-indexed
|
|
178
221
|
regions: number[][] // [[x1, y1, x2, y2], ...] in PDF points, top-left origin of the visible page box
|
|
222
|
+
// (sheet frame by default; the rendered page with { frame: "display" })
|
|
223
|
+
}
|
|
224
|
+
|
|
225
|
+
interface FrameOptions {
|
|
226
|
+
frame?: "sheet" | "display" // coordinate frame of items and region bboxes; "sheet" by default
|
|
227
|
+
}
|
|
228
|
+
|
|
229
|
+
interface PositionedText {
|
|
230
|
+
items: TextItem[] // as returned by extractTextWithPositions
|
|
231
|
+
pageRotations: PageRotation[] // one entry per page whose text was predominantly rotated
|
|
232
|
+
}
|
|
233
|
+
|
|
234
|
+
interface PageRotation {
|
|
235
|
+
page: number // 1-indexed, matching TextItem.page
|
|
236
|
+
rotation: string // "ccw" | "cw": how the page was turned in the "sheet" frame
|
|
179
237
|
}
|
|
180
238
|
|
|
181
239
|
interface PageRegionTexts {
|
package/index.d.ts
CHANGED
|
@@ -82,9 +82,10 @@ export declare function extractStructureElements(buffer: Buffer, pages?: Array<n
|
|
|
82
82
|
* `needsOcr` is `true` so the caller can fall back to GPU OCR.
|
|
83
83
|
*
|
|
84
84
|
* Coordinates are PDF points with top-left origin, relative to the visible
|
|
85
|
-
* page box (see `extractTextInRegions`).
|
|
85
|
+
* page box (see `extractTextInRegions`); `options.frame` selects the frame
|
|
86
|
+
* the same way.
|
|
86
87
|
*/
|
|
87
|
-
export declare function extractTablesInRegions(buffer: Buffer, pageRegions: Array<PageRegions
|
|
88
|
+
export declare function extractTablesInRegions(buffer: Buffer, pageRegions: Array<PageRegions>, options?: FrameOptions | undefined | null): Array<PageRegionTexts>
|
|
88
89
|
|
|
89
90
|
/**
|
|
90
91
|
* Extract markdown tables using externally-supplied structure recovery.
|
|
@@ -144,9 +145,11 @@ export declare function extractText(buffer: Buffer): string
|
|
|
144
145
|
* origin: a positioned `y` becomes `boxHeight - y`. For text items `y` is
|
|
145
146
|
* the baseline, so `[x, boxHeight - y - height, x + width, boxHeight - y]`
|
|
146
147
|
* 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.
|
|
148
|
+
* items `y` is the rect bottom and that box is exact. `/Rotate` is not
|
|
149
|
+
* applied by default; pass `{ frame: "display" }` (see [`FrameOptions`]) to
|
|
150
|
+
* give bboxes on the rendered page instead.
|
|
148
151
|
*/
|
|
149
|
-
export declare function extractTextInRegions(buffer: Buffer, pageRegions: Array<PageRegions
|
|
152
|
+
export declare function extractTextInRegions(buffer: Buffer, pageRegions: Array<PageRegions>, options?: FrameOptions | undefined | null): Array<PageRegionTexts>
|
|
150
153
|
|
|
151
154
|
/**
|
|
152
155
|
* Extract text with position information from a PDF Buffer.
|
|
@@ -154,9 +157,11 @@ export declare function extractTextInRegions(buffer: Buffer, pageRegions: Array<
|
|
|
154
157
|
* Items are reported in PDF points relative to the page's visible page box
|
|
155
158
|
* (`CropBox ∩ MediaBox`, else the MediaBox) with the box's lower-left
|
|
156
159
|
* corner as origin — see [`TextItem`]. `pages` is 1-indexed (matching
|
|
157
|
-
* `TextItem.page`); omit it for the whole document.
|
|
160
|
+
* `TextItem.page`); omit it for the whole document. `options.frame`
|
|
161
|
+
* selects the coordinate frame (see [`FrameOptions`]): `"sheet"` by
|
|
162
|
+
* default, `"display"` for the rendered page's frame.
|
|
158
163
|
*/
|
|
159
|
-
export declare function extractTextWithPositions(buffer: Buffer, pages?: Array<number> | undefined | null): Array<TextItem>
|
|
164
|
+
export declare function extractTextWithPositions(buffer: Buffer, pages?: Array<number> | undefined | null, options?: FrameOptions | undefined | null): Array<TextItem>
|
|
160
165
|
|
|
161
166
|
/**
|
|
162
167
|
* Extract text with positions from a PDF Buffer, together with the
|
|
@@ -164,8 +169,34 @@ export declare function extractTextWithPositions(buffer: Buffer, pages?: Array<n
|
|
|
164
169
|
* Items on such a page are expressed in the turned frame (their dominant
|
|
165
170
|
* runs read left-to-right there); pages absent from `pageRotations` are
|
|
166
171
|
* upright.
|
|
172
|
+
*
|
|
173
|
+
* `pages` is 1-indexed (matching `TextItem.page`); omit it for the whole
|
|
174
|
+
* document. `options.frame` selects the coordinate frame (see
|
|
175
|
+
* [`FrameOptions`]); with `"display"` the turn of a rotated page is undone
|
|
176
|
+
* and every item is in the rendered page's frame, while `pageRotations`
|
|
177
|
+
* keeps reporting which pages were turned.
|
|
178
|
+
*/
|
|
179
|
+
export declare function extractTextWithPositionsAndRotations(buffer: Buffer, pages?: Array<number> | undefined | null, options?: FrameOptions | undefined | null): PositionedText
|
|
180
|
+
|
|
181
|
+
/**
|
|
182
|
+
* Coordinate frame selection shared by `extractTextWithPositions`,
|
|
183
|
+
* `extractTextWithPositionsAndRotations`, `extractTextInRegions` and
|
|
184
|
+
* `extractTablesInRegions`.
|
|
167
185
|
*/
|
|
168
|
-
export
|
|
186
|
+
export interface FrameOptions {
|
|
187
|
+
/**
|
|
188
|
+
* `"sheet"` (default): the visible page box as laid out in the content
|
|
189
|
+
* stream, `/Rotate` not applied; pages whose text is predominantly
|
|
190
|
+
* rotated are turned so that text reads left-to-right (see
|
|
191
|
+
* [`TextItem`]). `"display"`: the rendered page — the visible page box
|
|
192
|
+
* turned clockwise by the page's inheritable `/Rotate`, lower-left
|
|
193
|
+
* origin and `y` up for items, top-left origin and `y` down for region
|
|
194
|
+
* bboxes — with the turn of a rotated page undone, so items sit where a
|
|
195
|
+
* renderer draws them and region bboxes can be taken from a rendered
|
|
196
|
+
* page image.
|
|
197
|
+
*/
|
|
198
|
+
frame?: "sheet" | "display"
|
|
199
|
+
}
|
|
169
200
|
|
|
170
201
|
/** Type of a positioned text item. */
|
|
171
202
|
export declare const enum ItemType {
|
|
@@ -286,8 +317,16 @@ export interface PageRegions {
|
|
|
286
317
|
page: number
|
|
287
318
|
/**
|
|
288
319
|
* Each bbox is [x1, y1, x2, y2] in PDF points, top-left origin of the
|
|
289
|
-
* visible page box (`CropBox ∩ MediaBox`, else the MediaBox)
|
|
290
|
-
*
|
|
320
|
+
* visible page box (`CropBox ∩ MediaBox`, else the MediaBox). By
|
|
321
|
+
* default the box is read as laid out in the content stream with
|
|
322
|
+
* `/Rotate` not applied — the frame `extractTextWithPositions` reports
|
|
323
|
+
* items in, flipped to a top-left origin — which matches a rendered
|
|
324
|
+
* page image only for pages with `/Rotate 0` whose text is not
|
|
325
|
+
* predominantly rotated (such a page is turned so its text reads
|
|
326
|
+
* left-to-right, see [`TextItem`]). With
|
|
327
|
+
* `{ frame: "display" }` (see [`FrameOptions`]) the bbox is read on the
|
|
328
|
+
* rendered page: the visible box turned clockwise by the page's
|
|
329
|
+
* inheritable `/Rotate`, top-left origin, `y` down.
|
|
291
330
|
*/
|
|
292
331
|
regions: Array<Array<number>>
|
|
293
332
|
}
|
|
@@ -473,6 +512,12 @@ export interface TableExtractionResultJs {
|
|
|
473
512
|
* expressed in that turned frame. Use
|
|
474
513
|
* [`extract_text_with_positions_and_rotations`] (`extractTextWithPositionsAndRotations`
|
|
475
514
|
* in JavaScript) to learn which pages were turned and which way.
|
|
515
|
+
*
|
|
516
|
+
* Pass `{ frame: "display" }` (see [`FrameOptions`]) to get every item in
|
|
517
|
+
* the rendered page's frame instead: the visible page box turned clockwise
|
|
518
|
+
* by the page's inheritable `/Rotate`, with the turn of a rotated page
|
|
519
|
+
* undone, so `x`/`y`/`width`/`height` and `rotation` describe the item as
|
|
520
|
+
* a renderer draws it.
|
|
476
521
|
*/
|
|
477
522
|
export interface TextItem {
|
|
478
523
|
text: string
|
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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 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 !== '1.20.0' && 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 1.20.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
513
513
|
}
|
|
514
514
|
return binding
|
|
515
515
|
} catch (e) {
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@firecrawl/pdf-inspector",
|
|
3
|
-
"version": "1.
|
|
3
|
+
"version": "1.20.0",
|
|
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": "1.20.0",
|
|
56
|
+
"@firecrawl/pdf-inspector-linux-x64-musl": "1.20.0",
|
|
57
|
+
"@firecrawl/pdf-inspector-linux-arm64-gnu": "1.20.0",
|
|
58
|
+
"@firecrawl/pdf-inspector-linux-arm64-musl": "1.20.0",
|
|
59
|
+
"@firecrawl/pdf-inspector-darwin-arm64": "1.20.0",
|
|
60
|
+
"@firecrawl/pdf-inspector-win32-x64-msvc": "1.20.0"
|
|
61
61
|
}
|
|
62
62
|
}
|