@firecrawl/anydoc-wasm 0.2.3 → 0.2.5

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 CHANGED
@@ -36,7 +36,7 @@ Calls are synchronous: wasm runs single-threaded on the calling thread, so conve
36
36
 
37
37
  ## Errors
38
38
 
39
- A conversion throws only when no meaningful Markdown could come out of the bytes. The thrown value is an `Error` whose `code` names what went wrong:
39
+ A conversion throws only when no complete Markdown could come out of the bytes. The thrown value is an `Error` whose `code` names what went wrong:
40
40
 
41
41
  ```js
42
42
  try {
@@ -53,7 +53,8 @@ try {
53
53
 
54
54
  | `code` | Meaning |
55
55
  | --------------- | ------------------------------------------------------------------- |
56
- | `unsupported` | Unknown format, or one that cannot be converted (an image-only PDF) |
56
+ | `unsupported` | Unknown format, or one that cannot be converted |
57
+ | `needsOcr` | Pages of a PDF are scanned or image-only; `pages` names them |
57
58
  | `malformed` | Structurally unusable: no meaningful content could be extracted |
58
59
  | `encrypted` | Encrypted or password-protected |
59
60
  | `resourceLimit` | Crossed a fixed safety limit (decompression, nesting, node count) |
package/anydoc_wasm.d.ts CHANGED
@@ -10,13 +10,18 @@ export type Format = "doc" | "docx" | "odt" | "pdf" | "ppt" | "pptx" | "rtf" | "
10
10
 
11
11
  /**
12
12
  * `code` on the `Error` a failed conversion throws. Conversion fails only
13
- * when no meaningful Markdown could be produced; producer quirks are
13
+ * when no complete Markdown could be produced; producer quirks are
14
14
  * recovered or skipped instead. The crate's `io` code has no wasm
15
15
  * counterpart: there is no filesystem to read from.
16
16
  */
17
17
  export type ConvertErrorCode =
18
- /** Unknown format, or one that cannot be converted (an image-only PDF). */
18
+ /** Unknown format, or one that cannot be converted. */
19
19
  | 'unsupported'
20
+ /**
21
+ * Pages of a PDF are scanned or image-only and need OCR, which anydoc does
22
+ * not do. The error is a `NeedsOcrError` naming them.
23
+ */
24
+ | 'needsOcr'
20
25
  /** Structurally unusable: no meaningful content could be extracted. */
21
26
  | 'malformed'
22
27
  /** Encrypted or password-protected. */
@@ -26,6 +31,15 @@ export type ConvertErrorCode =
26
31
  /** A part required for any meaningful output is absent. */
27
32
  | 'missingPart'
28
33
 
34
+ /** The error thrown for a PDF with pages that need OCR. */
35
+ export interface NeedsOcrError extends Error {
36
+ code: 'needsOcr'
37
+ /** 1-indexed pages that need OCR. */
38
+ pages: number[]
39
+ /** Pages in the document. */
40
+ pageCount: number
41
+ }
42
+
29
43
  export interface Document {
30
44
  blocks: Array<Block>
31
45
  /**
package/anydoc_wasm.js CHANGED
@@ -141,6 +141,10 @@ function __wbg_get_imports() {
141
141
  const ret = new Object();
142
142
  return addHeapObject(ret);
143
143
  },
144
+ __wbg_push_d2ae3af0c1217ae6: function(arg0, arg1) {
145
+ const ret = getObject(arg0).push(getObject(arg1));
146
+ return ret;
147
+ },
144
148
  __wbg_set_6be42768c690e380: function(arg0, arg1, arg2) {
145
149
  getObject(arg0)[takeObject(arg1)] = takeObject(arg2);
146
150
  },
Binary file
package/package.json CHANGED
@@ -2,7 +2,7 @@
2
2
  "name": "@firecrawl/anydoc-wasm",
3
3
  "type": "module",
4
4
  "description": "WebAssembly bindings for anydoc: convert documents (doc, docx, odt, rtf, epub, pdf, presentations, spreadsheets, csv) to GitHub-Flavored Markdown in the browser",
5
- "version": "0.2.3",
5
+ "version": "0.2.5",
6
6
  "license": "MIT",
7
7
  "repository": {
8
8
  "type": "git",