@uploadista/flow-documents-pdflib 0.0.16-beta.2
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/.turbo/turbo-build.log +16 -0
- package/LICENSE +21 -0
- package/README.md +43 -0
- package/dist/index.d.mts +27 -0
- package/dist/index.d.mts.map +1 -0
- package/dist/index.mjs +195 -0
- package/dist/index.mjs.map +1 -0
- package/package.json +32 -0
- package/src/document-plugin.ts +318 -0
- package/src/index.ts +2 -0
- package/src/utils/format-mappings.ts +23 -0
- package/tsconfig.json +14 -0
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
|
|
2
|
+
|
|
3
|
+
> @uploadista/flow-documents-pdflib@0.0.1 build /Users/denislaboureyras/Documents/uploadista/dev/uploadista-workspace/uploadista-sdk/packages/flow/documents/pdflib
|
|
4
|
+
> tsdown
|
|
5
|
+
|
|
6
|
+
[34mℹ[39m tsdown [2mv0.16.5[22m powered by rolldown [2mv1.0.0-beta.50[22m
|
|
7
|
+
[34mℹ[39m entry: [34msrc/index.ts[39m
|
|
8
|
+
[34mℹ[39m tsconfig: [34mtsconfig.json[39m
|
|
9
|
+
[34mℹ[39m Build start
|
|
10
|
+
[34mℹ[39m Cleaning 4 files
|
|
11
|
+
[34mℹ[39m [2mdist/[22m[1mindex.mjs[22m [2m 8.20 kB[22m [2m│ gzip: 1.87 kB[22m
|
|
12
|
+
[34mℹ[39m [2mdist/[22mindex.mjs.map [2m16.18 kB[22m [2m│ gzip: 3.54 kB[22m
|
|
13
|
+
[34mℹ[39m [2mdist/[22mindex.d.mts.map [2m 0.33 kB[22m [2m│ gzip: 0.23 kB[22m
|
|
14
|
+
[34mℹ[39m [2mdist/[22m[32m[1mindex.d.mts[22m[39m [2m 0.83 kB[22m [2m│ gzip: 0.37 kB[22m
|
|
15
|
+
[34mℹ[39m 4 files, total: 25.54 kB
|
|
16
|
+
[32m✔[39m Build complete in [32m7949ms[39m
|
package/LICENSE
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
1
|
+
MIT License
|
|
2
|
+
|
|
3
|
+
Copyright (c) 2025 uploadista
|
|
4
|
+
|
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
|
7
|
+
in the Software without restriction, including without limitation the rights
|
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
|
10
|
+
furnished to do so, subject to the following conditions:
|
|
11
|
+
|
|
12
|
+
The above copyright notice and this permission notice shall be included in all
|
|
13
|
+
copies or substantial portions of the Software.
|
|
14
|
+
|
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
21
|
+
SOFTWARE.
|
package/README.md
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
1
|
+
# @uploadista/flow-documents-pdflib
|
|
2
|
+
|
|
3
|
+
pdf-lib-based DocumentPlugin implementation for Uploadista Flow.
|
|
4
|
+
|
|
5
|
+
## Features
|
|
6
|
+
|
|
7
|
+
- Pure JavaScript implementation (no native dependencies)
|
|
8
|
+
- PDF splitting and merging
|
|
9
|
+
- Metadata extraction
|
|
10
|
+
- Works in both Node.js and browsers
|
|
11
|
+
|
|
12
|
+
## Installation
|
|
13
|
+
|
|
14
|
+
```bash
|
|
15
|
+
pnpm add @uploadista/flow-documents-pdflib
|
|
16
|
+
```
|
|
17
|
+
|
|
18
|
+
## Usage
|
|
19
|
+
|
|
20
|
+
```typescript
|
|
21
|
+
import { PdfLibDocumentPluginLive } from "@uploadista/flow-documents-pdflib";
|
|
22
|
+
import { Effect, Layer } from "effect";
|
|
23
|
+
|
|
24
|
+
// Provide the plugin to your flow execution
|
|
25
|
+
const program = Effect.gen(function* () {
|
|
26
|
+
// Your flow logic here
|
|
27
|
+
}).pipe(Effect.provide(PdfLibDocumentPluginLive));
|
|
28
|
+
```
|
|
29
|
+
|
|
30
|
+
## Why pdf-lib?
|
|
31
|
+
|
|
32
|
+
- **Pure JavaScript**: No native binaries or external dependencies
|
|
33
|
+
- **Cross-platform**: Works in Node.js, browsers, and edge runtimes
|
|
34
|
+
- **Actively maintained**: MIT licensed with regular updates
|
|
35
|
+
- **Comprehensive**: Supports PDF creation, modification, and reading
|
|
36
|
+
|
|
37
|
+
## Limitations
|
|
38
|
+
|
|
39
|
+
pdf-lib has limited text extraction capabilities. For text extraction from searchable PDFs, use the unpdf plugin instead.
|
|
40
|
+
|
|
41
|
+
## License
|
|
42
|
+
|
|
43
|
+
MIT
|
package/dist/index.d.mts
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
1
|
+
import { DocumentPlugin } from "@uploadista/core/flow";
|
|
2
|
+
import { Layer } from "effect";
|
|
3
|
+
|
|
4
|
+
//#region src/document-plugin.d.ts
|
|
5
|
+
declare const pdfLibDocumentPlugin: Layer.Layer<DocumentPlugin, never, never>;
|
|
6
|
+
declare const PdfLibDocumentPluginLive: Layer.Layer<DocumentPlugin, never, never>;
|
|
7
|
+
//#endregion
|
|
8
|
+
//#region src/utils/format-mappings.d.ts
|
|
9
|
+
/**
|
|
10
|
+
* PDF MIME type constant
|
|
11
|
+
*/
|
|
12
|
+
declare const PDF_MIME_TYPE = "application/pdf";
|
|
13
|
+
/**
|
|
14
|
+
* PDF file extension
|
|
15
|
+
*/
|
|
16
|
+
declare const PDF_EXTENSION = ".pdf";
|
|
17
|
+
/**
|
|
18
|
+
* Get MIME type for PDF format
|
|
19
|
+
*/
|
|
20
|
+
declare function getPdfMimeType(): string;
|
|
21
|
+
/**
|
|
22
|
+
* Get file extension for PDF format
|
|
23
|
+
*/
|
|
24
|
+
declare function getPdfExtension(): string;
|
|
25
|
+
//#endregion
|
|
26
|
+
export { PDF_EXTENSION, PDF_MIME_TYPE, PdfLibDocumentPluginLive, getPdfExtension, getPdfMimeType, pdfLibDocumentPlugin };
|
|
27
|
+
//# sourceMappingURL=index.d.mts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"index.d.mts","names":[],"sources":["../src/document-plugin.ts","../src/utils/format-mappings.ts"],"sourcesContent":[],"mappings":";;;;cAiCa,sBAAoB,KAAA,CAAA,MAAA;cA4RpB,0BAAwB,KAAA,CAAA,MAAA;;;;;;cC1TxB,aAAA;AD8Bb;AA4RA;;cCrTa,aAAA;;AALb;AAKA;AAKgB,iBAAA,cAAA,CAAA,CAAc,EAAA,MAAA;AAO9B;;;iBAAgB,eAAA,CAAA"}
|
package/dist/index.mjs
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
1
|
+
import { UploadistaError } from "@uploadista/core/errors";
|
|
2
|
+
import { DocumentPlugin } from "@uploadista/core/flow";
|
|
3
|
+
import { Effect, Layer } from "effect";
|
|
4
|
+
import { PDFDocument } from "pdf-lib";
|
|
5
|
+
|
|
6
|
+
//#region src/document-plugin.ts
|
|
7
|
+
/**
|
|
8
|
+
* Helper to parse date from PDF date string format
|
|
9
|
+
*/
|
|
10
|
+
function parsePdfDate(dateStr) {
|
|
11
|
+
if (!dateStr) return null;
|
|
12
|
+
try {
|
|
13
|
+
const match = dateStr.match(/D:(\d{4})(\d{2})(\d{2})(\d{2})?(\d{2})?(\d{2})?/);
|
|
14
|
+
if (!match) return null;
|
|
15
|
+
const [, year, month, day, hour = "00", minute = "00", second = "00"] = match;
|
|
16
|
+
return (/* @__PURE__ */ new Date(`${year}-${month}-${day}T${hour}:${minute}:${second}Z`)).toISOString();
|
|
17
|
+
} catch {
|
|
18
|
+
return null;
|
|
19
|
+
}
|
|
20
|
+
}
|
|
21
|
+
const pdfLibDocumentPlugin = Layer.succeed(DocumentPlugin, DocumentPlugin.of({
|
|
22
|
+
extractText: (_input) => {
|
|
23
|
+
return Effect.gen(function* () {
|
|
24
|
+
return yield* UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: "pdf-lib does not support text extraction. Use @uploadista/flow-documents-unpdf instead." }).toEffect();
|
|
25
|
+
});
|
|
26
|
+
},
|
|
27
|
+
getMetadata: (input) => {
|
|
28
|
+
return Effect.gen(function* () {
|
|
29
|
+
const pdfDoc = yield* Effect.tryPromise({
|
|
30
|
+
try: async () => await PDFDocument.load(input, { ignoreEncryption: false }),
|
|
31
|
+
catch: (error) => {
|
|
32
|
+
const errorMessage = error instanceof Error ? error.message : String(error);
|
|
33
|
+
if (errorMessage.toLowerCase().includes("encrypt")) return UploadistaError.fromCode("PDF_ENCRYPTED", { cause: errorMessage });
|
|
34
|
+
if (errorMessage.toLowerCase().includes("corrupt") || errorMessage.toLowerCase().includes("invalid")) return UploadistaError.fromCode("PDF_CORRUPTED", { cause: errorMessage });
|
|
35
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: errorMessage });
|
|
36
|
+
}
|
|
37
|
+
});
|
|
38
|
+
const pageCount = pdfDoc.getPageCount();
|
|
39
|
+
const author = pdfDoc.getAuthor() || null;
|
|
40
|
+
const title = pdfDoc.getTitle() || null;
|
|
41
|
+
const subject = pdfDoc.getSubject() || null;
|
|
42
|
+
const creator = pdfDoc.getCreator() || null;
|
|
43
|
+
const creationDateStr = pdfDoc.getCreationDate();
|
|
44
|
+
const modificationDateStr = pdfDoc.getModificationDate();
|
|
45
|
+
return {
|
|
46
|
+
pageCount,
|
|
47
|
+
format: "pdf",
|
|
48
|
+
author,
|
|
49
|
+
title,
|
|
50
|
+
subject,
|
|
51
|
+
creator,
|
|
52
|
+
creationDate: creationDateStr ? parsePdfDate(creationDateStr.toString()) : null,
|
|
53
|
+
modifiedDate: modificationDateStr ? parsePdfDate(modificationDateStr.toString()) : null,
|
|
54
|
+
fileSize: input.byteLength
|
|
55
|
+
};
|
|
56
|
+
});
|
|
57
|
+
},
|
|
58
|
+
splitPdf: (input, options) => {
|
|
59
|
+
return Effect.gen(function* () {
|
|
60
|
+
const pdfDoc = yield* Effect.tryPromise({
|
|
61
|
+
try: async () => await PDFDocument.load(input, { ignoreEncryption: false }),
|
|
62
|
+
catch: (error) => {
|
|
63
|
+
const errorMessage = error instanceof Error ? error.message : String(error);
|
|
64
|
+
if (errorMessage.toLowerCase().includes("encrypt")) return UploadistaError.fromCode("PDF_ENCRYPTED", { cause: errorMessage });
|
|
65
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: errorMessage });
|
|
66
|
+
}
|
|
67
|
+
});
|
|
68
|
+
const totalPages = pdfDoc.getPageCount();
|
|
69
|
+
if (options.mode === "individual") {
|
|
70
|
+
const pdfs = [];
|
|
71
|
+
for (let i = 0; i < totalPages; i++) {
|
|
72
|
+
const newPdf$1 = yield* Effect.tryPromise({
|
|
73
|
+
try: async () => await PDFDocument.create(),
|
|
74
|
+
catch: (error) => {
|
|
75
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: error instanceof Error ? error.message : String(error) });
|
|
76
|
+
}
|
|
77
|
+
});
|
|
78
|
+
const [copiedPage] = yield* Effect.tryPromise({
|
|
79
|
+
try: async () => await newPdf$1.copyPages(pdfDoc, [i]),
|
|
80
|
+
catch: (error) => {
|
|
81
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: error instanceof Error ? error.message : String(error) });
|
|
82
|
+
}
|
|
83
|
+
});
|
|
84
|
+
newPdf$1.addPage(copiedPage);
|
|
85
|
+
const pdfBytes$1 = yield* Effect.tryPromise({
|
|
86
|
+
try: async () => await newPdf$1.save(),
|
|
87
|
+
catch: (error) => {
|
|
88
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: error instanceof Error ? error.message : String(error) });
|
|
89
|
+
}
|
|
90
|
+
});
|
|
91
|
+
pdfs.push(new Uint8Array(pdfBytes$1));
|
|
92
|
+
}
|
|
93
|
+
return {
|
|
94
|
+
mode: "individual",
|
|
95
|
+
pdfs
|
|
96
|
+
};
|
|
97
|
+
}
|
|
98
|
+
if (!options.startPage || !options.endPage) return yield* UploadistaError.fromCode("PAGE_RANGE_INVALID", { cause: "startPage and endPage are required for range mode" }).toEffect();
|
|
99
|
+
if (options.startPage < 1 || options.endPage > totalPages || options.startPage > options.endPage) return yield* UploadistaError.fromCode("PAGE_RANGE_INVALID", { cause: `Invalid page range: ${options.startPage}-${options.endPage}. Document has ${totalPages} pages.` }).toEffect();
|
|
100
|
+
const newPdf = yield* Effect.tryPromise({
|
|
101
|
+
try: async () => await PDFDocument.create(),
|
|
102
|
+
catch: (error) => {
|
|
103
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: error instanceof Error ? error.message : String(error) });
|
|
104
|
+
}
|
|
105
|
+
});
|
|
106
|
+
const pageIndices = Array.from({ length: options.endPage - options.startPage + 1 }, (_, i) => (options.startPage ?? 1) - 1 + i);
|
|
107
|
+
const copiedPages = yield* Effect.tryPromise({
|
|
108
|
+
try: async () => await newPdf.copyPages(pdfDoc, pageIndices),
|
|
109
|
+
catch: (error) => {
|
|
110
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: error instanceof Error ? error.message : String(error) });
|
|
111
|
+
}
|
|
112
|
+
});
|
|
113
|
+
for (const page of copiedPages) newPdf.addPage(page);
|
|
114
|
+
const pdfBytes = yield* Effect.tryPromise({
|
|
115
|
+
try: async () => await newPdf.save(),
|
|
116
|
+
catch: (error) => {
|
|
117
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: error instanceof Error ? error.message : String(error) });
|
|
118
|
+
}
|
|
119
|
+
});
|
|
120
|
+
return {
|
|
121
|
+
mode: "range",
|
|
122
|
+
pdf: new Uint8Array(pdfBytes)
|
|
123
|
+
};
|
|
124
|
+
});
|
|
125
|
+
},
|
|
126
|
+
mergePdfs: (options) => {
|
|
127
|
+
return Effect.gen(function* () {
|
|
128
|
+
if (options.pdfs.length === 0) return yield* UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: "At least one PDF is required for merging" }).toEffect();
|
|
129
|
+
if (options.pdfs.length === 1) {
|
|
130
|
+
yield* Effect.logWarning("Only one PDF provided for merging, returning original");
|
|
131
|
+
return options.pdfs[0];
|
|
132
|
+
}
|
|
133
|
+
const mergedPdf = yield* Effect.tryPromise({
|
|
134
|
+
try: async () => await PDFDocument.create(),
|
|
135
|
+
catch: (error) => {
|
|
136
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: error instanceof Error ? error.message : String(error) });
|
|
137
|
+
}
|
|
138
|
+
});
|
|
139
|
+
for (const pdfBytes of options.pdfs) {
|
|
140
|
+
const pdf = yield* Effect.tryPromise({
|
|
141
|
+
try: async () => await PDFDocument.load(pdfBytes, { ignoreEncryption: false }),
|
|
142
|
+
catch: (error) => {
|
|
143
|
+
const errorMessage = error instanceof Error ? error.message : String(error);
|
|
144
|
+
if (errorMessage.toLowerCase().includes("encrypt")) return UploadistaError.fromCode("PDF_ENCRYPTED", { cause: errorMessage });
|
|
145
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: errorMessage });
|
|
146
|
+
}
|
|
147
|
+
});
|
|
148
|
+
const pageCount = pdf.getPageCount();
|
|
149
|
+
const pageIndices = Array.from({ length: pageCount }, (_, i) => i);
|
|
150
|
+
const copiedPages = yield* Effect.tryPromise({
|
|
151
|
+
try: async () => await mergedPdf.copyPages(pdf, pageIndices),
|
|
152
|
+
catch: (error) => {
|
|
153
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: error instanceof Error ? error.message : String(error) });
|
|
154
|
+
}
|
|
155
|
+
});
|
|
156
|
+
for (const page of copiedPages) mergedPdf.addPage(page);
|
|
157
|
+
}
|
|
158
|
+
const mergedBytes = yield* Effect.tryPromise({
|
|
159
|
+
try: async () => await mergedPdf.save(),
|
|
160
|
+
catch: (error) => {
|
|
161
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: error instanceof Error ? error.message : String(error) });
|
|
162
|
+
}
|
|
163
|
+
});
|
|
164
|
+
return new Uint8Array(mergedBytes);
|
|
165
|
+
});
|
|
166
|
+
}
|
|
167
|
+
}));
|
|
168
|
+
const PdfLibDocumentPluginLive = pdfLibDocumentPlugin;
|
|
169
|
+
|
|
170
|
+
//#endregion
|
|
171
|
+
//#region src/utils/format-mappings.ts
|
|
172
|
+
/**
|
|
173
|
+
* PDF MIME type constant
|
|
174
|
+
*/
|
|
175
|
+
const PDF_MIME_TYPE = "application/pdf";
|
|
176
|
+
/**
|
|
177
|
+
* PDF file extension
|
|
178
|
+
*/
|
|
179
|
+
const PDF_EXTENSION = ".pdf";
|
|
180
|
+
/**
|
|
181
|
+
* Get MIME type for PDF format
|
|
182
|
+
*/
|
|
183
|
+
function getPdfMimeType() {
|
|
184
|
+
return PDF_MIME_TYPE;
|
|
185
|
+
}
|
|
186
|
+
/**
|
|
187
|
+
* Get file extension for PDF format
|
|
188
|
+
*/
|
|
189
|
+
function getPdfExtension() {
|
|
190
|
+
return PDF_EXTENSION;
|
|
191
|
+
}
|
|
192
|
+
|
|
193
|
+
//#endregion
|
|
194
|
+
export { PDF_EXTENSION, PDF_MIME_TYPE, PdfLibDocumentPluginLive, getPdfExtension, getPdfMimeType, pdfLibDocumentPlugin };
|
|
195
|
+
//# sourceMappingURL=index.mjs.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"index.mjs","names":["pdfs: Uint8Array[]","newPdf","pdfBytes"],"sources":["../src/document-plugin.ts","../src/utils/format-mappings.ts"],"sourcesContent":["import { UploadistaError } from \"@uploadista/core/errors\";\nimport {\n type DocumentMetadata,\n DocumentPlugin,\n type SplitPdfResult,\n} from \"@uploadista/core/flow\";\nimport { Effect, Layer } from \"effect\";\nimport { PDFDocument } from \"pdf-lib\";\n\n/**\n * Helper to parse date from PDF date string format\n */\nfunction parsePdfDate(dateStr: string | undefined): string | null {\n if (!dateStr) return null;\n try {\n // PDF date format: D:YYYYMMDDHHmmSSOHH'mm'\n // Example: D:20230101120000Z\n const match = dateStr.match(\n /D:(\\d{4})(\\d{2})(\\d{2})(\\d{2})?(\\d{2})?(\\d{2})?/,\n );\n if (!match) return null;\n\n const [, year, month, day, hour = \"00\", minute = \"00\", second = \"00\"] =\n match;\n const date = new Date(\n `${year}-${month}-${day}T${hour}:${minute}:${second}Z`,\n );\n return date.toISOString();\n } catch {\n return null;\n }\n}\n\nexport const pdfLibDocumentPlugin = Layer.succeed(\n DocumentPlugin,\n DocumentPlugin.of({\n extractText: (_input) => {\n return Effect.gen(function* () {\n // pdf-lib has very limited text extraction capabilities\n // Return an error indicating that unpdf should be used instead\n return yield* UploadistaError.fromCode(\"DOCUMENT_PROCESSING_FAILED\", {\n cause:\n \"pdf-lib does not support text extraction. Use @uploadista/flow-documents-unpdf instead.\",\n }).toEffect();\n });\n },\n\n getMetadata: (input) => {\n return Effect.gen(function* () {\n const pdfDoc = yield* Effect.tryPromise({\n try: async () =>\n await PDFDocument.load(input, { ignoreEncryption: false }),\n catch: (error) => {\n const errorMessage =\n error instanceof Error ? error.message : String(error);\n\n if (errorMessage.toLowerCase().includes(\"encrypt\")) {\n return UploadistaError.fromCode(\"PDF_ENCRYPTED\", {\n cause: errorMessage,\n });\n }\n\n if (\n errorMessage.toLowerCase().includes(\"corrupt\") ||\n errorMessage.toLowerCase().includes(\"invalid\")\n ) {\n return UploadistaError.fromCode(\"PDF_CORRUPTED\", {\n cause: errorMessage,\n });\n }\n\n return UploadistaError.fromCode(\"DOCUMENT_PROCESSING_FAILED\", {\n cause: errorMessage,\n });\n },\n });\n\n const pageCount = pdfDoc.getPageCount();\n const author = pdfDoc.getAuthor() || null;\n const title = pdfDoc.getTitle() || null;\n const subject = pdfDoc.getSubject() || null;\n const creator = pdfDoc.getCreator() || null;\n const creationDateStr = pdfDoc.getCreationDate();\n const modificationDateStr = pdfDoc.getModificationDate();\n\n const creationDate = creationDateStr\n ? parsePdfDate(creationDateStr.toString())\n : null;\n const modifiedDate = modificationDateStr\n ? parsePdfDate(modificationDateStr.toString())\n : null;\n\n const metadata: DocumentMetadata = {\n pageCount,\n format: \"pdf\",\n author,\n title,\n subject,\n creator,\n creationDate,\n modifiedDate,\n fileSize: input.byteLength,\n };\n\n return metadata;\n });\n },\n\n splitPdf: (input, options) => {\n return Effect.gen(function* () {\n const pdfDoc = yield* Effect.tryPromise({\n try: async () =>\n await PDFDocument.load(input, { ignoreEncryption: false }),\n catch: (error) => {\n const errorMessage =\n error instanceof Error ? error.message : String(error);\n\n if (errorMessage.toLowerCase().includes(\"encrypt\")) {\n return UploadistaError.fromCode(\"PDF_ENCRYPTED\", {\n cause: errorMessage,\n });\n }\n\n return UploadistaError.fromCode(\"DOCUMENT_PROCESSING_FAILED\", {\n cause: errorMessage,\n });\n },\n });\n\n const totalPages = pdfDoc.getPageCount();\n\n if (options.mode === \"individual\") {\n // Split into individual pages\n const pdfs: Uint8Array[] = [];\n\n for (let i = 0; i < totalPages; i++) {\n const newPdf = yield* Effect.tryPromise({\n try: async () => await PDFDocument.create(),\n catch: (error) => {\n return UploadistaError.fromCode(\"DOCUMENT_PROCESSING_FAILED\", {\n cause: error instanceof Error ? error.message : String(error),\n });\n },\n });\n\n const [copiedPage] = yield* Effect.tryPromise({\n try: async () => await newPdf.copyPages(pdfDoc, [i]),\n catch: (error) => {\n return UploadistaError.fromCode(\"DOCUMENT_PROCESSING_FAILED\", {\n cause: error instanceof Error ? error.message : String(error),\n });\n },\n });\n\n newPdf.addPage(copiedPage);\n\n const pdfBytes = yield* Effect.tryPromise({\n try: async () => await newPdf.save(),\n catch: (error) => {\n return UploadistaError.fromCode(\"DOCUMENT_PROCESSING_FAILED\", {\n cause: error instanceof Error ? error.message : String(error),\n });\n },\n });\n\n pdfs.push(new Uint8Array(pdfBytes));\n }\n\n const result: SplitPdfResult = {\n mode: \"individual\",\n pdfs,\n };\n\n return result;\n }\n\n // Range mode\n if (!options.startPage || !options.endPage) {\n return yield* UploadistaError.fromCode(\"PAGE_RANGE_INVALID\", {\n cause: \"startPage and endPage are required for range mode\",\n }).toEffect();\n }\n\n // Validate page range (1-indexed)\n if (\n options.startPage < 1 ||\n options.endPage > totalPages ||\n options.startPage > options.endPage\n ) {\n return yield* UploadistaError.fromCode(\"PAGE_RANGE_INVALID\", {\n cause: `Invalid page range: ${options.startPage}-${options.endPage}. Document has ${totalPages} pages.`,\n }).toEffect();\n }\n\n const newPdf = yield* Effect.tryPromise({\n try: async () => await PDFDocument.create(),\n catch: (error) => {\n return UploadistaError.fromCode(\"DOCUMENT_PROCESSING_FAILED\", {\n cause: error instanceof Error ? error.message : String(error),\n });\n },\n });\n\n // Convert from 1-indexed to 0-indexed\n const pageIndices = Array.from(\n { length: options.endPage - options.startPage + 1 },\n (_, i) => (options.startPage ?? 1) - 1 + i,\n );\n\n const copiedPages = yield* Effect.tryPromise({\n try: async () => await newPdf.copyPages(pdfDoc, pageIndices),\n catch: (error) => {\n return UploadistaError.fromCode(\"DOCUMENT_PROCESSING_FAILED\", {\n cause: error instanceof Error ? error.message : String(error),\n });\n },\n });\n\n for (const page of copiedPages) {\n newPdf.addPage(page);\n }\n\n const pdfBytes = yield* Effect.tryPromise({\n try: async () => await newPdf.save(),\n catch: (error) => {\n return UploadistaError.fromCode(\"DOCUMENT_PROCESSING_FAILED\", {\n cause: error instanceof Error ? error.message : String(error),\n });\n },\n });\n\n const result: SplitPdfResult = {\n mode: \"range\",\n pdf: new Uint8Array(pdfBytes),\n };\n\n return result;\n });\n },\n\n mergePdfs: (options) => {\n return Effect.gen(function* () {\n if (options.pdfs.length === 0) {\n return yield* UploadistaError.fromCode(\"DOCUMENT_PROCESSING_FAILED\", {\n cause: \"At least one PDF is required for merging\",\n }).toEffect();\n }\n\n if (options.pdfs.length === 1) {\n // Single PDF, just return it\n yield* Effect.logWarning(\n \"Only one PDF provided for merging, returning original\",\n );\n return options.pdfs[0];\n }\n\n const mergedPdf = yield* Effect.tryPromise({\n try: async () => await PDFDocument.create(),\n catch: (error) => {\n return UploadistaError.fromCode(\"DOCUMENT_PROCESSING_FAILED\", {\n cause: error instanceof Error ? error.message : String(error),\n });\n },\n });\n\n for (const pdfBytes of options.pdfs) {\n const pdf = yield* Effect.tryPromise({\n try: async () =>\n await PDFDocument.load(pdfBytes, { ignoreEncryption: false }),\n catch: (error) => {\n const errorMessage =\n error instanceof Error ? error.message : String(error);\n\n if (errorMessage.toLowerCase().includes(\"encrypt\")) {\n return UploadistaError.fromCode(\"PDF_ENCRYPTED\", {\n cause: errorMessage,\n });\n }\n\n return UploadistaError.fromCode(\"DOCUMENT_PROCESSING_FAILED\", {\n cause: errorMessage,\n });\n },\n });\n\n const pageCount = pdf.getPageCount();\n const pageIndices = Array.from({ length: pageCount }, (_, i) => i);\n\n const copiedPages = yield* Effect.tryPromise({\n try: async () => await mergedPdf.copyPages(pdf, pageIndices),\n catch: (error) => {\n return UploadistaError.fromCode(\"DOCUMENT_PROCESSING_FAILED\", {\n cause: error instanceof Error ? error.message : String(error),\n });\n },\n });\n\n for (const page of copiedPages) {\n mergedPdf.addPage(page);\n }\n }\n\n const mergedBytes = yield* Effect.tryPromise({\n try: async () => await mergedPdf.save(),\n catch: (error) => {\n return UploadistaError.fromCode(\"DOCUMENT_PROCESSING_FAILED\", {\n cause: error instanceof Error ? error.message : String(error),\n });\n },\n });\n\n return new Uint8Array(mergedBytes);\n });\n },\n }),\n);\n\nexport const PdfLibDocumentPluginLive = pdfLibDocumentPlugin;\n","/**\n * PDF MIME type constant\n */\nexport const PDF_MIME_TYPE = \"application/pdf\";\n\n/**\n * PDF file extension\n */\nexport const PDF_EXTENSION = \".pdf\";\n\n/**\n * Get MIME type for PDF format\n */\nexport function getPdfMimeType(): string {\n return PDF_MIME_TYPE;\n}\n\n/**\n * Get file extension for PDF format\n */\nexport function getPdfExtension(): string {\n return PDF_EXTENSION;\n}\n"],"mappings":";;;;;;;;;AAYA,SAAS,aAAa,SAA4C;AAChE,KAAI,CAAC,QAAS,QAAO;AACrB,KAAI;EAGF,MAAM,QAAQ,QAAQ,MACpB,kDACD;AACD,MAAI,CAAC,MAAO,QAAO;EAEnB,MAAM,GAAG,MAAM,OAAO,KAAK,OAAO,MAAM,SAAS,MAAM,SAAS,QAC9D;AAIF,0BAHa,IAAI,KACf,GAAG,KAAK,GAAG,MAAM,GAAG,IAAI,GAAG,KAAK,GAAG,OAAO,GAAG,OAAO,GACrD,EACW,aAAa;SACnB;AACN,SAAO;;;AAIX,MAAa,uBAAuB,MAAM,QACxC,gBACA,eAAe,GAAG;CAChB,cAAc,WAAW;AACvB,SAAO,OAAO,IAAI,aAAa;AAG7B,UAAO,OAAO,gBAAgB,SAAS,8BAA8B,EACnE,OACE,2FACH,CAAC,CAAC,UAAU;IACb;;CAGJ,cAAc,UAAU;AACtB,SAAO,OAAO,IAAI,aAAa;GAC7B,MAAM,SAAS,OAAO,OAAO,WAAW;IACtC,KAAK,YACH,MAAM,YAAY,KAAK,OAAO,EAAE,kBAAkB,OAAO,CAAC;IAC5D,QAAQ,UAAU;KAChB,MAAM,eACJ,iBAAiB,QAAQ,MAAM,UAAU,OAAO,MAAM;AAExD,SAAI,aAAa,aAAa,CAAC,SAAS,UAAU,CAChD,QAAO,gBAAgB,SAAS,iBAAiB,EAC/C,OAAO,cACR,CAAC;AAGJ,SACE,aAAa,aAAa,CAAC,SAAS,UAAU,IAC9C,aAAa,aAAa,CAAC,SAAS,UAAU,CAE9C,QAAO,gBAAgB,SAAS,iBAAiB,EAC/C,OAAO,cACR,CAAC;AAGJ,YAAO,gBAAgB,SAAS,8BAA8B,EAC5D,OAAO,cACR,CAAC;;IAEL,CAAC;GAEF,MAAM,YAAY,OAAO,cAAc;GACvC,MAAM,SAAS,OAAO,WAAW,IAAI;GACrC,MAAM,QAAQ,OAAO,UAAU,IAAI;GACnC,MAAM,UAAU,OAAO,YAAY,IAAI;GACvC,MAAM,UAAU,OAAO,YAAY,IAAI;GACvC,MAAM,kBAAkB,OAAO,iBAAiB;GAChD,MAAM,sBAAsB,OAAO,qBAAqB;AAqBxD,UAZmC;IACjC;IACA,QAAQ;IACR;IACA;IACA;IACA;IACA,cAdmB,kBACjB,aAAa,gBAAgB,UAAU,CAAC,GACxC;IAaF,cAZmB,sBACjB,aAAa,oBAAoB,UAAU,CAAC,GAC5C;IAWF,UAAU,MAAM;IACjB;IAGD;;CAGJ,WAAW,OAAO,YAAY;AAC5B,SAAO,OAAO,IAAI,aAAa;GAC7B,MAAM,SAAS,OAAO,OAAO,WAAW;IACtC,KAAK,YACH,MAAM,YAAY,KAAK,OAAO,EAAE,kBAAkB,OAAO,CAAC;IAC5D,QAAQ,UAAU;KAChB,MAAM,eACJ,iBAAiB,QAAQ,MAAM,UAAU,OAAO,MAAM;AAExD,SAAI,aAAa,aAAa,CAAC,SAAS,UAAU,CAChD,QAAO,gBAAgB,SAAS,iBAAiB,EAC/C,OAAO,cACR,CAAC;AAGJ,YAAO,gBAAgB,SAAS,8BAA8B,EAC5D,OAAO,cACR,CAAC;;IAEL,CAAC;GAEF,MAAM,aAAa,OAAO,cAAc;AAExC,OAAI,QAAQ,SAAS,cAAc;IAEjC,MAAMA,OAAqB,EAAE;AAE7B,SAAK,IAAI,IAAI,GAAG,IAAI,YAAY,KAAK;KACnC,MAAMC,WAAS,OAAO,OAAO,WAAW;MACtC,KAAK,YAAY,MAAM,YAAY,QAAQ;MAC3C,QAAQ,UAAU;AAChB,cAAO,gBAAgB,SAAS,8BAA8B,EAC5D,OAAO,iBAAiB,QAAQ,MAAM,UAAU,OAAO,MAAM,EAC9D,CAAC;;MAEL,CAAC;KAEF,MAAM,CAAC,cAAc,OAAO,OAAO,WAAW;MAC5C,KAAK,YAAY,MAAMA,SAAO,UAAU,QAAQ,CAAC,EAAE,CAAC;MACpD,QAAQ,UAAU;AAChB,cAAO,gBAAgB,SAAS,8BAA8B,EAC5D,OAAO,iBAAiB,QAAQ,MAAM,UAAU,OAAO,MAAM,EAC9D,CAAC;;MAEL,CAAC;AAEF,cAAO,QAAQ,WAAW;KAE1B,MAAMC,aAAW,OAAO,OAAO,WAAW;MACxC,KAAK,YAAY,MAAMD,SAAO,MAAM;MACpC,QAAQ,UAAU;AAChB,cAAO,gBAAgB,SAAS,8BAA8B,EAC5D,OAAO,iBAAiB,QAAQ,MAAM,UAAU,OAAO,MAAM,EAC9D,CAAC;;MAEL,CAAC;AAEF,UAAK,KAAK,IAAI,WAAWC,WAAS,CAAC;;AAQrC,WAL+B;KAC7B,MAAM;KACN;KACD;;AAMH,OAAI,CAAC,QAAQ,aAAa,CAAC,QAAQ,QACjC,QAAO,OAAO,gBAAgB,SAAS,sBAAsB,EAC3D,OAAO,qDACR,CAAC,CAAC,UAAU;AAIf,OACE,QAAQ,YAAY,KACpB,QAAQ,UAAU,cAClB,QAAQ,YAAY,QAAQ,QAE5B,QAAO,OAAO,gBAAgB,SAAS,sBAAsB,EAC3D,OAAO,uBAAuB,QAAQ,UAAU,GAAG,QAAQ,QAAQ,iBAAiB,WAAW,UAChG,CAAC,CAAC,UAAU;GAGf,MAAM,SAAS,OAAO,OAAO,WAAW;IACtC,KAAK,YAAY,MAAM,YAAY,QAAQ;IAC3C,QAAQ,UAAU;AAChB,YAAO,gBAAgB,SAAS,8BAA8B,EAC5D,OAAO,iBAAiB,QAAQ,MAAM,UAAU,OAAO,MAAM,EAC9D,CAAC;;IAEL,CAAC;GAGF,MAAM,cAAc,MAAM,KACxB,EAAE,QAAQ,QAAQ,UAAU,QAAQ,YAAY,GAAG,GAClD,GAAG,OAAO,QAAQ,aAAa,KAAK,IAAI,EAC1C;GAED,MAAM,cAAc,OAAO,OAAO,WAAW;IAC3C,KAAK,YAAY,MAAM,OAAO,UAAU,QAAQ,YAAY;IAC5D,QAAQ,UAAU;AAChB,YAAO,gBAAgB,SAAS,8BAA8B,EAC5D,OAAO,iBAAiB,QAAQ,MAAM,UAAU,OAAO,MAAM,EAC9D,CAAC;;IAEL,CAAC;AAEF,QAAK,MAAM,QAAQ,YACjB,QAAO,QAAQ,KAAK;GAGtB,MAAM,WAAW,OAAO,OAAO,WAAW;IACxC,KAAK,YAAY,MAAM,OAAO,MAAM;IACpC,QAAQ,UAAU;AAChB,YAAO,gBAAgB,SAAS,8BAA8B,EAC5D,OAAO,iBAAiB,QAAQ,MAAM,UAAU,OAAO,MAAM,EAC9D,CAAC;;IAEL,CAAC;AAOF,UAL+B;IAC7B,MAAM;IACN,KAAK,IAAI,WAAW,SAAS;IAC9B;IAGD;;CAGJ,YAAY,YAAY;AACtB,SAAO,OAAO,IAAI,aAAa;AAC7B,OAAI,QAAQ,KAAK,WAAW,EAC1B,QAAO,OAAO,gBAAgB,SAAS,8BAA8B,EACnE,OAAO,4CACR,CAAC,CAAC,UAAU;AAGf,OAAI,QAAQ,KAAK,WAAW,GAAG;AAE7B,WAAO,OAAO,WACZ,wDACD;AACD,WAAO,QAAQ,KAAK;;GAGtB,MAAM,YAAY,OAAO,OAAO,WAAW;IACzC,KAAK,YAAY,MAAM,YAAY,QAAQ;IAC3C,QAAQ,UAAU;AAChB,YAAO,gBAAgB,SAAS,8BAA8B,EAC5D,OAAO,iBAAiB,QAAQ,MAAM,UAAU,OAAO,MAAM,EAC9D,CAAC;;IAEL,CAAC;AAEF,QAAK,MAAM,YAAY,QAAQ,MAAM;IACnC,MAAM,MAAM,OAAO,OAAO,WAAW;KACnC,KAAK,YACH,MAAM,YAAY,KAAK,UAAU,EAAE,kBAAkB,OAAO,CAAC;KAC/D,QAAQ,UAAU;MAChB,MAAM,eACJ,iBAAiB,QAAQ,MAAM,UAAU,OAAO,MAAM;AAExD,UAAI,aAAa,aAAa,CAAC,SAAS,UAAU,CAChD,QAAO,gBAAgB,SAAS,iBAAiB,EAC/C,OAAO,cACR,CAAC;AAGJ,aAAO,gBAAgB,SAAS,8BAA8B,EAC5D,OAAO,cACR,CAAC;;KAEL,CAAC;IAEF,MAAM,YAAY,IAAI,cAAc;IACpC,MAAM,cAAc,MAAM,KAAK,EAAE,QAAQ,WAAW,GAAG,GAAG,MAAM,EAAE;IAElE,MAAM,cAAc,OAAO,OAAO,WAAW;KAC3C,KAAK,YAAY,MAAM,UAAU,UAAU,KAAK,YAAY;KAC5D,QAAQ,UAAU;AAChB,aAAO,gBAAgB,SAAS,8BAA8B,EAC5D,OAAO,iBAAiB,QAAQ,MAAM,UAAU,OAAO,MAAM,EAC9D,CAAC;;KAEL,CAAC;AAEF,SAAK,MAAM,QAAQ,YACjB,WAAU,QAAQ,KAAK;;GAI3B,MAAM,cAAc,OAAO,OAAO,WAAW;IAC3C,KAAK,YAAY,MAAM,UAAU,MAAM;IACvC,QAAQ,UAAU;AAChB,YAAO,gBAAgB,SAAS,8BAA8B,EAC5D,OAAO,iBAAiB,QAAQ,MAAM,UAAU,OAAO,MAAM,EAC9D,CAAC;;IAEL,CAAC;AAEF,UAAO,IAAI,WAAW,YAAY;IAClC;;CAEL,CAAC,CACH;AAED,MAAa,2BAA2B;;;;;;;AC1TxC,MAAa,gBAAgB;;;;AAK7B,MAAa,gBAAgB;;;;AAK7B,SAAgB,iBAAyB;AACvC,QAAO;;;;;AAMT,SAAgB,kBAA0B;AACxC,QAAO"}
|
package/package.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
{
|
|
2
|
+
"name": "@uploadista/flow-documents-pdflib",
|
|
3
|
+
"type": "module",
|
|
4
|
+
"version": "0.0.16-beta.2",
|
|
5
|
+
"description": "pdf-lib plugin for Uploadista document processing",
|
|
6
|
+
"license": "MIT",
|
|
7
|
+
"author": "Uploadista",
|
|
8
|
+
"exports": {
|
|
9
|
+
".": {
|
|
10
|
+
"types": "./dist/index.d.mts",
|
|
11
|
+
"import": "./dist/index.mjs",
|
|
12
|
+
"require": "./dist/index.cjs",
|
|
13
|
+
"default": "./dist/index.mjs"
|
|
14
|
+
}
|
|
15
|
+
},
|
|
16
|
+
"dependencies": {
|
|
17
|
+
"effect": "3.19.4",
|
|
18
|
+
"pdf-lib": "^1.17.1",
|
|
19
|
+
"@uploadista/core": "0.0.16-beta.2"
|
|
20
|
+
},
|
|
21
|
+
"devDependencies": {
|
|
22
|
+
"@types/node": "24.10.1",
|
|
23
|
+
"tsdown": "0.16.5",
|
|
24
|
+
"@uploadista/typescript-config": "0.0.16-beta.2"
|
|
25
|
+
},
|
|
26
|
+
"scripts": {
|
|
27
|
+
"build": "tsdown",
|
|
28
|
+
"format": "biome format --write ./src",
|
|
29
|
+
"lint": "biome lint --write ./src",
|
|
30
|
+
"check": "biome check --write ./src"
|
|
31
|
+
}
|
|
32
|
+
}
|
|
@@ -0,0 +1,318 @@
|
|
|
1
|
+
import { UploadistaError } from "@uploadista/core/errors";
|
|
2
|
+
import {
|
|
3
|
+
type DocumentMetadata,
|
|
4
|
+
DocumentPlugin,
|
|
5
|
+
type SplitPdfResult,
|
|
6
|
+
} from "@uploadista/core/flow";
|
|
7
|
+
import { Effect, Layer } from "effect";
|
|
8
|
+
import { PDFDocument } from "pdf-lib";
|
|
9
|
+
|
|
10
|
+
/**
|
|
11
|
+
* Helper to parse date from PDF date string format
|
|
12
|
+
*/
|
|
13
|
+
function parsePdfDate(dateStr: string | undefined): string | null {
|
|
14
|
+
if (!dateStr) return null;
|
|
15
|
+
try {
|
|
16
|
+
// PDF date format: D:YYYYMMDDHHmmSSOHH'mm'
|
|
17
|
+
// Example: D:20230101120000Z
|
|
18
|
+
const match = dateStr.match(
|
|
19
|
+
/D:(\d{4})(\d{2})(\d{2})(\d{2})?(\d{2})?(\d{2})?/,
|
|
20
|
+
);
|
|
21
|
+
if (!match) return null;
|
|
22
|
+
|
|
23
|
+
const [, year, month, day, hour = "00", minute = "00", second = "00"] =
|
|
24
|
+
match;
|
|
25
|
+
const date = new Date(
|
|
26
|
+
`${year}-${month}-${day}T${hour}:${minute}:${second}Z`,
|
|
27
|
+
);
|
|
28
|
+
return date.toISOString();
|
|
29
|
+
} catch {
|
|
30
|
+
return null;
|
|
31
|
+
}
|
|
32
|
+
}
|
|
33
|
+
|
|
34
|
+
export const pdfLibDocumentPlugin = Layer.succeed(
|
|
35
|
+
DocumentPlugin,
|
|
36
|
+
DocumentPlugin.of({
|
|
37
|
+
extractText: (_input) => {
|
|
38
|
+
return Effect.gen(function* () {
|
|
39
|
+
// pdf-lib has very limited text extraction capabilities
|
|
40
|
+
// Return an error indicating that unpdf should be used instead
|
|
41
|
+
return yield* UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
|
|
42
|
+
cause:
|
|
43
|
+
"pdf-lib does not support text extraction. Use @uploadista/flow-documents-unpdf instead.",
|
|
44
|
+
}).toEffect();
|
|
45
|
+
});
|
|
46
|
+
},
|
|
47
|
+
|
|
48
|
+
getMetadata: (input) => {
|
|
49
|
+
return Effect.gen(function* () {
|
|
50
|
+
const pdfDoc = yield* Effect.tryPromise({
|
|
51
|
+
try: async () =>
|
|
52
|
+
await PDFDocument.load(input, { ignoreEncryption: false }),
|
|
53
|
+
catch: (error) => {
|
|
54
|
+
const errorMessage =
|
|
55
|
+
error instanceof Error ? error.message : String(error);
|
|
56
|
+
|
|
57
|
+
if (errorMessage.toLowerCase().includes("encrypt")) {
|
|
58
|
+
return UploadistaError.fromCode("PDF_ENCRYPTED", {
|
|
59
|
+
cause: errorMessage,
|
|
60
|
+
});
|
|
61
|
+
}
|
|
62
|
+
|
|
63
|
+
if (
|
|
64
|
+
errorMessage.toLowerCase().includes("corrupt") ||
|
|
65
|
+
errorMessage.toLowerCase().includes("invalid")
|
|
66
|
+
) {
|
|
67
|
+
return UploadistaError.fromCode("PDF_CORRUPTED", {
|
|
68
|
+
cause: errorMessage,
|
|
69
|
+
});
|
|
70
|
+
}
|
|
71
|
+
|
|
72
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
|
|
73
|
+
cause: errorMessage,
|
|
74
|
+
});
|
|
75
|
+
},
|
|
76
|
+
});
|
|
77
|
+
|
|
78
|
+
const pageCount = pdfDoc.getPageCount();
|
|
79
|
+
const author = pdfDoc.getAuthor() || null;
|
|
80
|
+
const title = pdfDoc.getTitle() || null;
|
|
81
|
+
const subject = pdfDoc.getSubject() || null;
|
|
82
|
+
const creator = pdfDoc.getCreator() || null;
|
|
83
|
+
const creationDateStr = pdfDoc.getCreationDate();
|
|
84
|
+
const modificationDateStr = pdfDoc.getModificationDate();
|
|
85
|
+
|
|
86
|
+
const creationDate = creationDateStr
|
|
87
|
+
? parsePdfDate(creationDateStr.toString())
|
|
88
|
+
: null;
|
|
89
|
+
const modifiedDate = modificationDateStr
|
|
90
|
+
? parsePdfDate(modificationDateStr.toString())
|
|
91
|
+
: null;
|
|
92
|
+
|
|
93
|
+
const metadata: DocumentMetadata = {
|
|
94
|
+
pageCount,
|
|
95
|
+
format: "pdf",
|
|
96
|
+
author,
|
|
97
|
+
title,
|
|
98
|
+
subject,
|
|
99
|
+
creator,
|
|
100
|
+
creationDate,
|
|
101
|
+
modifiedDate,
|
|
102
|
+
fileSize: input.byteLength,
|
|
103
|
+
};
|
|
104
|
+
|
|
105
|
+
return metadata;
|
|
106
|
+
});
|
|
107
|
+
},
|
|
108
|
+
|
|
109
|
+
splitPdf: (input, options) => {
|
|
110
|
+
return Effect.gen(function* () {
|
|
111
|
+
const pdfDoc = yield* Effect.tryPromise({
|
|
112
|
+
try: async () =>
|
|
113
|
+
await PDFDocument.load(input, { ignoreEncryption: false }),
|
|
114
|
+
catch: (error) => {
|
|
115
|
+
const errorMessage =
|
|
116
|
+
error instanceof Error ? error.message : String(error);
|
|
117
|
+
|
|
118
|
+
if (errorMessage.toLowerCase().includes("encrypt")) {
|
|
119
|
+
return UploadistaError.fromCode("PDF_ENCRYPTED", {
|
|
120
|
+
cause: errorMessage,
|
|
121
|
+
});
|
|
122
|
+
}
|
|
123
|
+
|
|
124
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
|
|
125
|
+
cause: errorMessage,
|
|
126
|
+
});
|
|
127
|
+
},
|
|
128
|
+
});
|
|
129
|
+
|
|
130
|
+
const totalPages = pdfDoc.getPageCount();
|
|
131
|
+
|
|
132
|
+
if (options.mode === "individual") {
|
|
133
|
+
// Split into individual pages
|
|
134
|
+
const pdfs: Uint8Array[] = [];
|
|
135
|
+
|
|
136
|
+
for (let i = 0; i < totalPages; i++) {
|
|
137
|
+
const newPdf = yield* Effect.tryPromise({
|
|
138
|
+
try: async () => await PDFDocument.create(),
|
|
139
|
+
catch: (error) => {
|
|
140
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
|
|
141
|
+
cause: error instanceof Error ? error.message : String(error),
|
|
142
|
+
});
|
|
143
|
+
},
|
|
144
|
+
});
|
|
145
|
+
|
|
146
|
+
const [copiedPage] = yield* Effect.tryPromise({
|
|
147
|
+
try: async () => await newPdf.copyPages(pdfDoc, [i]),
|
|
148
|
+
catch: (error) => {
|
|
149
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
|
|
150
|
+
cause: error instanceof Error ? error.message : String(error),
|
|
151
|
+
});
|
|
152
|
+
},
|
|
153
|
+
});
|
|
154
|
+
|
|
155
|
+
newPdf.addPage(copiedPage);
|
|
156
|
+
|
|
157
|
+
const pdfBytes = yield* Effect.tryPromise({
|
|
158
|
+
try: async () => await newPdf.save(),
|
|
159
|
+
catch: (error) => {
|
|
160
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
|
|
161
|
+
cause: error instanceof Error ? error.message : String(error),
|
|
162
|
+
});
|
|
163
|
+
},
|
|
164
|
+
});
|
|
165
|
+
|
|
166
|
+
pdfs.push(new Uint8Array(pdfBytes));
|
|
167
|
+
}
|
|
168
|
+
|
|
169
|
+
const result: SplitPdfResult = {
|
|
170
|
+
mode: "individual",
|
|
171
|
+
pdfs,
|
|
172
|
+
};
|
|
173
|
+
|
|
174
|
+
return result;
|
|
175
|
+
}
|
|
176
|
+
|
|
177
|
+
// Range mode
|
|
178
|
+
if (!options.startPage || !options.endPage) {
|
|
179
|
+
return yield* UploadistaError.fromCode("PAGE_RANGE_INVALID", {
|
|
180
|
+
cause: "startPage and endPage are required for range mode",
|
|
181
|
+
}).toEffect();
|
|
182
|
+
}
|
|
183
|
+
|
|
184
|
+
// Validate page range (1-indexed)
|
|
185
|
+
if (
|
|
186
|
+
options.startPage < 1 ||
|
|
187
|
+
options.endPage > totalPages ||
|
|
188
|
+
options.startPage > options.endPage
|
|
189
|
+
) {
|
|
190
|
+
return yield* UploadistaError.fromCode("PAGE_RANGE_INVALID", {
|
|
191
|
+
cause: `Invalid page range: ${options.startPage}-${options.endPage}. Document has ${totalPages} pages.`,
|
|
192
|
+
}).toEffect();
|
|
193
|
+
}
|
|
194
|
+
|
|
195
|
+
const newPdf = yield* Effect.tryPromise({
|
|
196
|
+
try: async () => await PDFDocument.create(),
|
|
197
|
+
catch: (error) => {
|
|
198
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
|
|
199
|
+
cause: error instanceof Error ? error.message : String(error),
|
|
200
|
+
});
|
|
201
|
+
},
|
|
202
|
+
});
|
|
203
|
+
|
|
204
|
+
// Convert from 1-indexed to 0-indexed
|
|
205
|
+
const pageIndices = Array.from(
|
|
206
|
+
{ length: options.endPage - options.startPage + 1 },
|
|
207
|
+
(_, i) => (options.startPage ?? 1) - 1 + i,
|
|
208
|
+
);
|
|
209
|
+
|
|
210
|
+
const copiedPages = yield* Effect.tryPromise({
|
|
211
|
+
try: async () => await newPdf.copyPages(pdfDoc, pageIndices),
|
|
212
|
+
catch: (error) => {
|
|
213
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
|
|
214
|
+
cause: error instanceof Error ? error.message : String(error),
|
|
215
|
+
});
|
|
216
|
+
},
|
|
217
|
+
});
|
|
218
|
+
|
|
219
|
+
for (const page of copiedPages) {
|
|
220
|
+
newPdf.addPage(page);
|
|
221
|
+
}
|
|
222
|
+
|
|
223
|
+
const pdfBytes = yield* Effect.tryPromise({
|
|
224
|
+
try: async () => await newPdf.save(),
|
|
225
|
+
catch: (error) => {
|
|
226
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
|
|
227
|
+
cause: error instanceof Error ? error.message : String(error),
|
|
228
|
+
});
|
|
229
|
+
},
|
|
230
|
+
});
|
|
231
|
+
|
|
232
|
+
const result: SplitPdfResult = {
|
|
233
|
+
mode: "range",
|
|
234
|
+
pdf: new Uint8Array(pdfBytes),
|
|
235
|
+
};
|
|
236
|
+
|
|
237
|
+
return result;
|
|
238
|
+
});
|
|
239
|
+
},
|
|
240
|
+
|
|
241
|
+
mergePdfs: (options) => {
|
|
242
|
+
return Effect.gen(function* () {
|
|
243
|
+
if (options.pdfs.length === 0) {
|
|
244
|
+
return yield* UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
|
|
245
|
+
cause: "At least one PDF is required for merging",
|
|
246
|
+
}).toEffect();
|
|
247
|
+
}
|
|
248
|
+
|
|
249
|
+
if (options.pdfs.length === 1) {
|
|
250
|
+
// Single PDF, just return it
|
|
251
|
+
yield* Effect.logWarning(
|
|
252
|
+
"Only one PDF provided for merging, returning original",
|
|
253
|
+
);
|
|
254
|
+
return options.pdfs[0];
|
|
255
|
+
}
|
|
256
|
+
|
|
257
|
+
const mergedPdf = yield* Effect.tryPromise({
|
|
258
|
+
try: async () => await PDFDocument.create(),
|
|
259
|
+
catch: (error) => {
|
|
260
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
|
|
261
|
+
cause: error instanceof Error ? error.message : String(error),
|
|
262
|
+
});
|
|
263
|
+
},
|
|
264
|
+
});
|
|
265
|
+
|
|
266
|
+
for (const pdfBytes of options.pdfs) {
|
|
267
|
+
const pdf = yield* Effect.tryPromise({
|
|
268
|
+
try: async () =>
|
|
269
|
+
await PDFDocument.load(pdfBytes, { ignoreEncryption: false }),
|
|
270
|
+
catch: (error) => {
|
|
271
|
+
const errorMessage =
|
|
272
|
+
error instanceof Error ? error.message : String(error);
|
|
273
|
+
|
|
274
|
+
if (errorMessage.toLowerCase().includes("encrypt")) {
|
|
275
|
+
return UploadistaError.fromCode("PDF_ENCRYPTED", {
|
|
276
|
+
cause: errorMessage,
|
|
277
|
+
});
|
|
278
|
+
}
|
|
279
|
+
|
|
280
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
|
|
281
|
+
cause: errorMessage,
|
|
282
|
+
});
|
|
283
|
+
},
|
|
284
|
+
});
|
|
285
|
+
|
|
286
|
+
const pageCount = pdf.getPageCount();
|
|
287
|
+
const pageIndices = Array.from({ length: pageCount }, (_, i) => i);
|
|
288
|
+
|
|
289
|
+
const copiedPages = yield* Effect.tryPromise({
|
|
290
|
+
try: async () => await mergedPdf.copyPages(pdf, pageIndices),
|
|
291
|
+
catch: (error) => {
|
|
292
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
|
|
293
|
+
cause: error instanceof Error ? error.message : String(error),
|
|
294
|
+
});
|
|
295
|
+
},
|
|
296
|
+
});
|
|
297
|
+
|
|
298
|
+
for (const page of copiedPages) {
|
|
299
|
+
mergedPdf.addPage(page);
|
|
300
|
+
}
|
|
301
|
+
}
|
|
302
|
+
|
|
303
|
+
const mergedBytes = yield* Effect.tryPromise({
|
|
304
|
+
try: async () => await mergedPdf.save(),
|
|
305
|
+
catch: (error) => {
|
|
306
|
+
return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
|
|
307
|
+
cause: error instanceof Error ? error.message : String(error),
|
|
308
|
+
});
|
|
309
|
+
},
|
|
310
|
+
});
|
|
311
|
+
|
|
312
|
+
return new Uint8Array(mergedBytes);
|
|
313
|
+
});
|
|
314
|
+
},
|
|
315
|
+
}),
|
|
316
|
+
);
|
|
317
|
+
|
|
318
|
+
export const PdfLibDocumentPluginLive = pdfLibDocumentPlugin;
|
package/src/index.ts
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* PDF MIME type constant
|
|
3
|
+
*/
|
|
4
|
+
export const PDF_MIME_TYPE = "application/pdf";
|
|
5
|
+
|
|
6
|
+
/**
|
|
7
|
+
* PDF file extension
|
|
8
|
+
*/
|
|
9
|
+
export const PDF_EXTENSION = ".pdf";
|
|
10
|
+
|
|
11
|
+
/**
|
|
12
|
+
* Get MIME type for PDF format
|
|
13
|
+
*/
|
|
14
|
+
export function getPdfMimeType(): string {
|
|
15
|
+
return PDF_MIME_TYPE;
|
|
16
|
+
}
|
|
17
|
+
|
|
18
|
+
/**
|
|
19
|
+
* Get file extension for PDF format
|
|
20
|
+
*/
|
|
21
|
+
export function getPdfExtension(): string {
|
|
22
|
+
return PDF_EXTENSION;
|
|
23
|
+
}
|
package/tsconfig.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
{
|
|
2
|
+
"extends": "@uploadista/typescript-config/server.json",
|
|
3
|
+
"compilerOptions": {
|
|
4
|
+
"baseUrl": "./",
|
|
5
|
+
"paths": {
|
|
6
|
+
"@/*": ["./src/*"]
|
|
7
|
+
},
|
|
8
|
+
"outDir": "./dist",
|
|
9
|
+
"rootDir": "./src",
|
|
10
|
+
"lib": ["ESNext", "DOM", "DOM.Iterable"],
|
|
11
|
+
"types": []
|
|
12
|
+
},
|
|
13
|
+
"include": ["src"]
|
|
14
|
+
}
|