@firecrawl/pdf-inspector 1.14.1 → 1.15.0
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 +52 -1
- package/index.d.ts +97 -0
- package/index.js +55 -52
- package/package.json +7 -7
package/README.md
CHANGED
|
@@ -10,7 +10,8 @@ Built by [Firecrawl](https://firecrawl.dev) for hybrid OCR pipelines — extract
|
|
|
10
10
|
- **Region-based extraction** — pull text from bounding boxes with per-region quality checks (`needsOcr`).
|
|
11
11
|
- **Layout-aware** — multi-column reading order, position and font info per text item, RTL support.
|
|
12
12
|
- **Robust text decoding** — CID/Type0 fonts via ToUnicode CMaps, plus automatic flagging of broken encodings so callers can fall back to OCR.
|
|
13
|
-
- **
|
|
13
|
+
- **Selective OCR** — `Auto` routes only pages rejected by native extraction and returns source/model provenance plus hosted-fallback recommendations.
|
|
14
|
+
- **External artifacts** — the native package embeds no OCR models, PDFium, or ONNX Runtime; clean `Auto` requests never load or download them.
|
|
14
15
|
|
|
15
16
|
## Benchmark
|
|
16
17
|
|
|
@@ -36,8 +37,42 @@ bun add @firecrawl/pdf-inspector
|
|
|
36
37
|
|
|
37
38
|
Prebuilt binaries for **Linux x64/ARM64** (glibc and musl/Alpine), **macOS ARM64**, and **Windows x64** — npm installs only the one matching your platform. No Rust toolchain needed.
|
|
38
39
|
|
|
40
|
+
OCR calls that route work require compatible PDFium and ONNX Runtime shared
|
|
41
|
+
libraries. Set `PDFIUM_LIB_PATH` and `ORT_DYLIB_PATH` when they are not on the
|
|
42
|
+
platform library search path. The pinned OCR model set is downloaded and
|
|
43
|
+
checksum-verified on the first routed page; use `offline: true` with a warm
|
|
44
|
+
cache or `modelDirectory` to prohibit network access. See the
|
|
45
|
+
[OCR runtime setup guide](https://github.com/firecrawl/pdf-inspector/blob/main/docs/ocr-runtime.md)
|
|
46
|
+
for pinned downloads, supported platforms, and hosted-fallback behavior.
|
|
47
|
+
|
|
39
48
|
## API
|
|
40
49
|
|
|
50
|
+
### `processPdfWithOcr(buffer: Buffer, options?: OcrOptions): Promise<OcrPdfResult>`
|
|
51
|
+
|
|
52
|
+
Run native extraction first and OCR only the pages selected by its quality
|
|
53
|
+
signals. The default mode is `Auto`; `Off` returns the same detailed result
|
|
54
|
+
shape without external runtime work, and `Force` OCRs every selected page.
|
|
55
|
+
The work runs on the libuv thread pool and never blocks Node's event loop.
|
|
56
|
+
|
|
57
|
+
```typescript
|
|
58
|
+
import { OcrMode, processPdfWithOcr } from '@firecrawl/pdf-inspector'
|
|
59
|
+
|
|
60
|
+
const result = await processPdfWithOcr(pdf, {
|
|
61
|
+
mode: OcrMode.Auto,
|
|
62
|
+
pageNumbers: [1, 3], // 1-indexed
|
|
63
|
+
})
|
|
64
|
+
|
|
65
|
+
for (const page of result.pages) {
|
|
66
|
+
console.log(page.pageNumber, page.provenance.source)
|
|
67
|
+
}
|
|
68
|
+
console.log(result.pagesRoutedToOcr)
|
|
69
|
+
console.log(result.pagesRecommendingHosted)
|
|
70
|
+
```
|
|
71
|
+
|
|
72
|
+
For offline deployments, pass `modelDirectory` and `offline: true`. Other
|
|
73
|
+
controls include `dpi`, `minimumConfidence`,
|
|
74
|
+
`hostedRecommendationConfidence`, and `password`.
|
|
75
|
+
|
|
41
76
|
### `classifyPdf(buffer: Buffer): PdfClassification`
|
|
42
77
|
|
|
43
78
|
Classify a PDF as TextBased, Scanned, Mixed, or ImageBased (~10-50ms). Returns which pages need OCR.
|
|
@@ -124,6 +159,22 @@ interface RegionText {
|
|
|
124
159
|
needsOcr: boolean // true when text is unreliable
|
|
125
160
|
ocrReason?: string // "suspected_garbled_text" when known
|
|
126
161
|
}
|
|
162
|
+
|
|
163
|
+
interface OcrPdfResult {
|
|
164
|
+
markdown: string
|
|
165
|
+
pages: OcrPageResult[] // 1-indexed pages + provenance
|
|
166
|
+
pageCount: number
|
|
167
|
+
pagesRecommendedForOcr: number[]
|
|
168
|
+
pagesRoutedToOcr: number[]
|
|
169
|
+
pagesRecommendingHosted: number[]
|
|
170
|
+
ocrReasonsByPage: PageOcrReasons[]
|
|
171
|
+
pagesWithTables: number[]
|
|
172
|
+
pagesWithColumns: number[]
|
|
173
|
+
isComplex: boolean
|
|
174
|
+
processingTimeMs: number
|
|
175
|
+
renderTimeMs: number
|
|
176
|
+
ocrTimeMs: number
|
|
177
|
+
}
|
|
127
178
|
```
|
|
128
179
|
|
|
129
180
|
## Platforms
|
package/index.d.ts
CHANGED
|
@@ -151,6 +151,94 @@ export declare const enum ItemType {
|
|
|
151
151
|
FormField = 'FormField'
|
|
152
152
|
}
|
|
153
153
|
|
|
154
|
+
/** Selects when OCR runs. */
|
|
155
|
+
export declare const enum OcrMode {
|
|
156
|
+
/** Never run OCR; return the native extraction in the OCR result shape. */
|
|
157
|
+
Off = 'Off',
|
|
158
|
+
/** Run OCR only on pages selected by the native quality signals. */
|
|
159
|
+
Auto = 'Auto',
|
|
160
|
+
/** Run OCR on every selected page. */
|
|
161
|
+
Force = 'Force'
|
|
162
|
+
}
|
|
163
|
+
|
|
164
|
+
/** Exact OCR model identity retained in page provenance. */
|
|
165
|
+
export interface OcrModelIdentity {
|
|
166
|
+
name: string
|
|
167
|
+
revision: string
|
|
168
|
+
}
|
|
169
|
+
|
|
170
|
+
/** Options for one-call native extraction with selective OCR. */
|
|
171
|
+
export interface OcrOptions {
|
|
172
|
+
/** OCR routing behavior. Defaults to Auto. */
|
|
173
|
+
mode?: OcrMode
|
|
174
|
+
/** Optional 1-indexed page selection. */
|
|
175
|
+
pageNumbers?: Array<number>
|
|
176
|
+
/** Password for an encrypted PDF. */
|
|
177
|
+
password?: string
|
|
178
|
+
/** Page rasterization resolution. Defaults to 150 DPI. */
|
|
179
|
+
dpi?: number
|
|
180
|
+
/** Drop OCR spans below this inclusive 0-1 threshold. */
|
|
181
|
+
minimumConfidence?: number
|
|
182
|
+
/** Recommend hosted parsing below this inclusive 0-1 page confidence. */
|
|
183
|
+
hostedRecommendationConfidence?: number
|
|
184
|
+
/** Directory containing an offline OCR model set. */
|
|
185
|
+
modelDirectory?: string
|
|
186
|
+
/** Disable model downloads and require a model directory or warm cache. */
|
|
187
|
+
offline?: boolean
|
|
188
|
+
}
|
|
189
|
+
|
|
190
|
+
/** Source, model, confidence, and fallback metadata for one page. */
|
|
191
|
+
export interface OcrPageProvenance {
|
|
192
|
+
/** 1-indexed page number. */
|
|
193
|
+
pageNumber: number
|
|
194
|
+
source: PageContentSource
|
|
195
|
+
ocrModel?: OcrModelIdentity
|
|
196
|
+
renderDpi?: number
|
|
197
|
+
ocrConfidence?: number
|
|
198
|
+
timings: OcrTimings
|
|
199
|
+
warnings: Array<string>
|
|
200
|
+
hostedRecommended: boolean
|
|
201
|
+
}
|
|
202
|
+
|
|
203
|
+
/** Final Markdown and provenance for one page. */
|
|
204
|
+
export interface OcrPageResult {
|
|
205
|
+
/** 1-indexed page number. */
|
|
206
|
+
pageNumber: number
|
|
207
|
+
markdown: string
|
|
208
|
+
provenance: OcrPageProvenance
|
|
209
|
+
}
|
|
210
|
+
|
|
211
|
+
/** Complete native/OCR Markdown output. */
|
|
212
|
+
export interface OcrPdfResult {
|
|
213
|
+
markdown: string
|
|
214
|
+
pages: Array<OcrPageResult>
|
|
215
|
+
pageCount: number
|
|
216
|
+
pagesRecommendedForOcr: Array<number>
|
|
217
|
+
pagesRoutedToOcr: Array<number>
|
|
218
|
+
pagesRecommendingHosted: Array<number>
|
|
219
|
+
ocrReasonsByPage: Array<PageOcrReasons>
|
|
220
|
+
pagesWithTables: Array<number>
|
|
221
|
+
pagesWithColumns: Array<number>
|
|
222
|
+
isComplex: boolean
|
|
223
|
+
processingTimeMs: number
|
|
224
|
+
renderTimeMs: number
|
|
225
|
+
ocrTimeMs: number
|
|
226
|
+
}
|
|
227
|
+
|
|
228
|
+
/** Per-page OCR processing timings. */
|
|
229
|
+
export interface OcrTimings {
|
|
230
|
+
renderMs: number
|
|
231
|
+
ocrMs: number
|
|
232
|
+
assemblyMs: number
|
|
233
|
+
}
|
|
234
|
+
|
|
235
|
+
/** How final page content was sourced. */
|
|
236
|
+
export declare const enum PageContentSource {
|
|
237
|
+
Native = 'Native',
|
|
238
|
+
Ocr = 'Ocr',
|
|
239
|
+
Fused = 'Fused'
|
|
240
|
+
}
|
|
241
|
+
|
|
154
242
|
/** Per-page markdown extraction result. */
|
|
155
243
|
export interface PageMarkdownResult {
|
|
156
244
|
/** 0-indexed page number. */
|
|
@@ -244,6 +332,15 @@ export declare function processPdf(buffer: Buffer, pages?: Array<number> | undef
|
|
|
244
332
|
*/
|
|
245
333
|
export declare function processPdfAsync(buffer: Buffer, pages?: Array<number> | undefined | null): Promise<PdfResult>
|
|
246
334
|
|
|
335
|
+
/**
|
|
336
|
+
* Process a PDF with selective OCR on the libuv thread pool.
|
|
337
|
+
*
|
|
338
|
+
* OCR defaults to Auto, which only loads PDFium, ONNX Runtime, and the OCR
|
|
339
|
+
* model if native extraction routes at least one page. The input buffer is
|
|
340
|
+
* copied before the promise is returned and is safe to reuse immediately.
|
|
341
|
+
*/
|
|
342
|
+
export declare function processPdfWithOcr(buffer: Buffer, options?: OcrOptions | undefined | null): Promise<OcrPdfResult>
|
|
343
|
+
|
|
247
344
|
/** Extracted text for a single region. */
|
|
248
345
|
export interface RegionText {
|
|
249
346
|
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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 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 !== '1.15.0' && 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 1.15.0 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
|
|
513
513
|
}
|
|
514
514
|
return binding
|
|
515
515
|
} catch (e) {
|
|
@@ -591,6 +591,9 @@ module.exports.extractText = nativeBinding.extractText
|
|
|
591
591
|
module.exports.extractTextInRegions = nativeBinding.extractTextInRegions
|
|
592
592
|
module.exports.extractTextWithPositions = nativeBinding.extractTextWithPositions
|
|
593
593
|
module.exports.ItemType = nativeBinding.ItemType
|
|
594
|
+
module.exports.OcrMode = nativeBinding.OcrMode
|
|
595
|
+
module.exports.PageContentSource = nativeBinding.PageContentSource
|
|
594
596
|
module.exports.PdfType = nativeBinding.PdfType
|
|
595
597
|
module.exports.processPdf = nativeBinding.processPdf
|
|
596
598
|
module.exports.processPdfAsync = nativeBinding.processPdfAsync
|
|
599
|
+
module.exports.processPdfWithOcr = nativeBinding.processPdfWithOcr
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@firecrawl/pdf-inspector",
|
|
3
|
-
"version": "1.
|
|
3
|
+
"version": "1.15.0",
|
|
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": "1.15.0",
|
|
56
|
+
"@firecrawl/pdf-inspector-linux-x64-musl": "1.15.0",
|
|
57
|
+
"@firecrawl/pdf-inspector-linux-arm64-gnu": "1.15.0",
|
|
58
|
+
"@firecrawl/pdf-inspector-linux-arm64-musl": "1.15.0",
|
|
59
|
+
"@firecrawl/pdf-inspector-darwin-arm64": "1.15.0",
|
|
60
|
+
"@firecrawl/pdf-inspector-win32-x64-msvc": "1.15.0"
|
|
61
61
|
}
|
|
62
62
|
}
|