@uploadista/flow-documents-unpdf 0.0.16-beta.2

package/.turbo/turbo-build.log

@@ -0,0 +1,16 @@
+
+
+> @uploadista/flow-documents-unpdf@0.0.1 build /Users/denislaboureyras/Documents/uploadista/dev/uploadista-workspace/uploadista-sdk/packages/flow/documents/unpdf
+> tsdown
+
+ℹ tsdown v0.16.5 powered by rolldown v1.0.0-beta.50
+ℹ entry: src/index.ts
+ℹ tsconfig: tsconfig.json
+ℹ Build start
+ℹ Cleaning 4 files
+ℹ dist/index.mjs        2.25 kB │ gzip: 0.76 kB
+ℹ dist/index.mjs.map    4.30 kB │ gzip: 1.27 kB
+ℹ dist/index.d.mts.map  0.18 kB │ gzip: 0.15 kB
+ℹ dist/index.d.mts      0.39 kB │ gzip: 0.21 kB
+ℹ 4 files, total: 7.12 kB
+✔ Build complete in 1311ms

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 uploadista
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/README.md

@@ -0,0 +1,50 @@
+# @uploadista/flow-documents-unpdf
+
+unpdf-based text extraction plugin for Uploadista Flow.
+
+## Features
+
+- Fast text extraction from searchable PDFs
+- Modern TypeScript-first API
+- Async/await support
+- Multi-page text extraction with structure preservation
+
+## Installation
+
+```bash
+pnpm add @uploadista/flow-documents-unpdf
+```
+
+## Usage
+
+```typescript
+import { UnpdfDocumentPluginLive } from "@uploadista/flow-documents-unpdf";
+import { Effect } from "effect";
+
+// Provide the plugin for text extraction
+const program = Effect.gen(function* () {
+  // Your flow logic here
+}).pipe(Effect.provide(UnpdfDocumentPluginLive));
+```
+
+## Why unpdf?
+
+- **Modern**: TypeScript-first library maintained as an alternative to pdf-parse
+- **Reliable**: Uses pdfjs-dist under the hood (Mozilla's PDF.js)
+- **Fast**: Optimized for text extraction performance
+- **Universal**: Works across all JavaScript runtimes
+
+## Use Cases
+
+- Extract text from searchable PDFs for indexing
+- Parse PDF documents for content analysis
+- Extract structured text with paragraph/line preservation
+
+## When NOT to use
+
+- For scanned documents or image-based PDFs (use OCR instead)
+- For PDF manipulation (use pdf-lib instead)
+
+## License
+
+MIT

package/dist/index.d.mts

@@ -0,0 +1,9 @@
+import { DocumentPlugin } from "@uploadista/core/flow";
+import { Layer } from "effect";
+
+//#region src/document-plugin.d.ts
+declare const unpdfDocumentPlugin: Layer.Layer<DocumentPlugin, never, never>;
+declare const UnpdfDocumentPluginLive: Layer.Layer<DocumentPlugin, never, never>;
+//#endregion
+export { UnpdfDocumentPluginLive, unpdfDocumentPlugin };
+//# sourceMappingURL=index.d.mts.map

package/dist/index.d.mts.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.d.mts","names":[],"sources":["../src/document-plugin.ts"],"sourcesContent":[],"mappings":";;;;cAKa,qBAAmB,KAAA,CAAA,MAAA;cAqFnB,yBAAuB,KAAA,CAAA,MAAA"}

package/dist/index.mjs

@@ -0,0 +1,45 @@
+import { UploadistaError } from "@uploadista/core/errors";
+import { DocumentPlugin } from "@uploadista/core/flow";
+import { Effect, Layer } from "effect";
+import { extractText } from "unpdf";
+
+//#region src/document-plugin.ts
+const unpdfDocumentPlugin = Layer.succeed(DocumentPlugin, DocumentPlugin.of({
+	extractText: (input) => {
+		return Effect.gen(function* () {
+			const text = yield* Effect.tryPromise({
+				try: async () => {
+					return (await extractText(input, { mergePages: true })).text;
+				},
+				catch: (error) => {
+					const errorMessage = error instanceof Error ? error.message : String(error);
+					if (errorMessage.toLowerCase().includes("encrypt") || errorMessage.toLowerCase().includes("password")) return UploadistaError.fromCode("PDF_ENCRYPTED", { cause: errorMessage });
+					if (errorMessage.toLowerCase().includes("corrupt") || errorMessage.toLowerCase().includes("invalid") || errorMessage.toLowerCase().includes("malformed")) return UploadistaError.fromCode("PDF_CORRUPTED", { cause: errorMessage });
+					return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: errorMessage });
+				}
+			});
+			if (!text || text.trim().length === 0) yield* Effect.logWarning("No text extracted from PDF. This might be a scanned document or image-based PDF. Consider using OCR instead.");
+			return text;
+		});
+	},
+	getMetadata: () => {
+		return Effect.gen(function* () {
+			return yield* UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: "unpdf does not support metadata extraction. Use @uploadista/flow-documents-pdflib instead." }).toEffect();
+		});
+	},
+	splitPdf: () => {
+		return Effect.gen(function* () {
+			return yield* UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: "unpdf does not support PDF splitting. Use @uploadista/flow-documents-pdflib instead." }).toEffect();
+		});
+	},
+	mergePdfs: () => {
+		return Effect.gen(function* () {
+			return yield* UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", { cause: "unpdf does not support PDF merging. Use @uploadista/flow-documents-pdflib instead." }).toEffect();
+		});
+	}
+}));
+const UnpdfDocumentPluginLive = unpdfDocumentPlugin;
+
+//#endregion
+export { UnpdfDocumentPluginLive, unpdfDocumentPlugin };
+//# sourceMappingURL=index.mjs.map

package/dist/index.mjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.mjs","names":[],"sources":["../src/document-plugin.ts"],"sourcesContent":["import { UploadistaError } from \"@uploadista/core/errors\";\nimport { DocumentPlugin } from \"@uploadista/core/flow\";\nimport { Effect, Layer } from \"effect\";\nimport { extractText } from \"unpdf\";\n\nexport const unpdfDocumentPlugin = Layer.succeed(\n  DocumentPlugin,\n  DocumentPlugin.of({\n    extractText: (input) => {\n      return Effect.gen(function* () {\n        const text = yield* Effect.tryPromise({\n          try: async () => {\n            const result = await extractText(input, {\n              mergePages: true,\n            });\n            return result.text;\n          },\n          catch: (error) => {\n            const errorMessage =\n              error instanceof Error ? error.message : String(error);\n\n            if (\n              errorMessage.toLowerCase().includes(\"encrypt\") ||\n              errorMessage.toLowerCase().includes(\"password\")\n            ) {\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              errorMessage.toLowerCase().includes(\"malformed\")\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        // If no text was extracted, log a warning\n        if (!text || text.trim().length === 0) {\n          yield* Effect.logWarning(\n            \"No text extracted from PDF. This might be a scanned document or image-based PDF. Consider using OCR instead.\",\n          );\n        }\n\n        return text;\n      });\n    },\n\n    getMetadata: () => {\n      return Effect.gen(function* () {\n        // unpdf doesn't support metadata extraction\n        // Return an error indicating that pdf-lib should be used instead\n        return yield* UploadistaError.fromCode(\"DOCUMENT_PROCESSING_FAILED\", {\n          cause:\n            \"unpdf does not support metadata extraction. Use @uploadista/flow-documents-pdflib instead.\",\n        }).toEffect();\n      });\n    },\n\n    splitPdf: () => {\n      return Effect.gen(function* () {\n        // unpdf doesn't support PDF splitting\n        return yield* UploadistaError.fromCode(\"DOCUMENT_PROCESSING_FAILED\", {\n          cause:\n            \"unpdf does not support PDF splitting. Use @uploadista/flow-documents-pdflib instead.\",\n        }).toEffect();\n      });\n    },\n\n    mergePdfs: () => {\n      return Effect.gen(function* () {\n        // unpdf doesn't support PDF merging\n        return yield* UploadistaError.fromCode(\"DOCUMENT_PROCESSING_FAILED\", {\n          cause:\n            \"unpdf does not support PDF merging. Use @uploadista/flow-documents-pdflib instead.\",\n        }).toEffect();\n      });\n    },\n  }),\n);\n\nexport const UnpdfDocumentPluginLive = unpdfDocumentPlugin;\n"],"mappings":";;;;;;AAKA,MAAa,sBAAsB,MAAM,QACvC,gBACA,eAAe,GAAG;CAChB,cAAc,UAAU;AACtB,SAAO,OAAO,IAAI,aAAa;GAC7B,MAAM,OAAO,OAAO,OAAO,WAAW;IACpC,KAAK,YAAY;AAIf,aAHe,MAAM,YAAY,OAAO,EACtC,YAAY,MACb,CAAC,EACY;;IAEhB,QAAQ,UAAU;KAChB,MAAM,eACJ,iBAAiB,QAAQ,MAAM,UAAU,OAAO,MAAM;AAExD,SACE,aAAa,aAAa,CAAC,SAAS,UAAU,IAC9C,aAAa,aAAa,CAAC,SAAS,WAAW,CAE/C,QAAO,gBAAgB,SAAS,iBAAiB,EAC/C,OAAO,cACR,CAAC;AAGJ,SACE,aAAa,aAAa,CAAC,SAAS,UAAU,IAC9C,aAAa,aAAa,CAAC,SAAS,UAAU,IAC9C,aAAa,aAAa,CAAC,SAAS,YAAY,CAEhD,QAAO,gBAAgB,SAAS,iBAAiB,EAC/C,OAAO,cACR,CAAC;AAGJ,YAAO,gBAAgB,SAAS,8BAA8B,EAC5D,OAAO,cACR,CAAC;;IAEL,CAAC;AAGF,OAAI,CAAC,QAAQ,KAAK,MAAM,CAAC,WAAW,EAClC,QAAO,OAAO,WACZ,+GACD;AAGH,UAAO;IACP;;CAGJ,mBAAmB;AACjB,SAAO,OAAO,IAAI,aAAa;AAG7B,UAAO,OAAO,gBAAgB,SAAS,8BAA8B,EACnE,OACE,8FACH,CAAC,CAAC,UAAU;IACb;;CAGJ,gBAAgB;AACd,SAAO,OAAO,IAAI,aAAa;AAE7B,UAAO,OAAO,gBAAgB,SAAS,8BAA8B,EACnE,OACE,wFACH,CAAC,CAAC,UAAU;IACb;;CAGJ,iBAAiB;AACf,SAAO,OAAO,IAAI,aAAa;AAE7B,UAAO,OAAO,gBAAgB,SAAS,8BAA8B,EACnE,OACE,sFACH,CAAC,CAAC,UAAU;IACb;;CAEL,CAAC,CACH;AAED,MAAa,0BAA0B"}

package/package.json

@@ -0,0 +1,32 @@
+{
+  "name": "@uploadista/flow-documents-unpdf",
+  "type": "module",
+  "version": "0.0.16-beta.2",
+  "description": "unpdf plugin for Uploadista document text extraction",
+  "license": "MIT",
+  "author": "Uploadista",
+  "exports": {
+    ".": {
+      "types": "./dist/index.d.mts",
+      "import": "./dist/index.mjs",
+      "require": "./dist/index.cjs",
+      "default": "./dist/index.mjs"
+    }
+  },
+  "dependencies": {
+    "effect": "3.19.4",
+    "unpdf": "^1.4.0",
+    "@uploadista/core": "0.0.16-beta.2"
+  },
+  "devDependencies": {
+    "@types/node": "24.10.1",
+    "tsdown": "0.16.5",
+    "@uploadista/typescript-config": "0.0.16-beta.2"
+  },
+  "scripts": {
+    "build": "tsdown",
+    "format": "biome format --write ./src",
+    "lint": "biome lint --write ./src",
+    "check": "biome check --write ./src"
+  }
+}

package/src/document-plugin.ts

@@ -0,0 +1,91 @@
+import { UploadistaError } from "@uploadista/core/errors";
+import { DocumentPlugin } from "@uploadista/core/flow";
+import { Effect, Layer } from "effect";
+import { extractText } from "unpdf";
+
+export const unpdfDocumentPlugin = Layer.succeed(
+  DocumentPlugin,
+  DocumentPlugin.of({
+    extractText: (input) => {
+      return Effect.gen(function* () {
+        const text = yield* Effect.tryPromise({
+          try: async () => {
+            const result = await extractText(input, {
+              mergePages: true,
+            });
+            return result.text;
+          },
+          catch: (error) => {
+            const errorMessage =
+              error instanceof Error ? error.message : String(error);
+
+            if (
+              errorMessage.toLowerCase().includes("encrypt") ||
+              errorMessage.toLowerCase().includes("password")
+            ) {
+              return UploadistaError.fromCode("PDF_ENCRYPTED", {
+                cause: errorMessage,
+              });
+            }
+
+            if (
+              errorMessage.toLowerCase().includes("corrupt") ||
+              errorMessage.toLowerCase().includes("invalid") ||
+              errorMessage.toLowerCase().includes("malformed")
+            ) {
+              return UploadistaError.fromCode("PDF_CORRUPTED", {
+                cause: errorMessage,
+              });
+            }
+
+            return UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
+              cause: errorMessage,
+            });
+          },
+        });
+
+        // If no text was extracted, log a warning
+        if (!text || text.trim().length === 0) {
+          yield* Effect.logWarning(
+            "No text extracted from PDF. This might be a scanned document or image-based PDF. Consider using OCR instead.",
+          );
+        }
+
+        return text;
+      });
+    },
+
+    getMetadata: () => {
+      return Effect.gen(function* () {
+        // unpdf doesn't support metadata extraction
+        // Return an error indicating that pdf-lib should be used instead
+        return yield* UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
+          cause:
+            "unpdf does not support metadata extraction. Use @uploadista/flow-documents-pdflib instead.",
+        }).toEffect();
+      });
+    },
+
+    splitPdf: () => {
+      return Effect.gen(function* () {
+        // unpdf doesn't support PDF splitting
+        return yield* UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
+          cause:
+            "unpdf does not support PDF splitting. Use @uploadista/flow-documents-pdflib instead.",
+        }).toEffect();
+      });
+    },
+
+    mergePdfs: () => {
+      return Effect.gen(function* () {
+        // unpdf doesn't support PDF merging
+        return yield* UploadistaError.fromCode("DOCUMENT_PROCESSING_FAILED", {
+          cause:
+            "unpdf does not support PDF merging. Use @uploadista/flow-documents-pdflib instead.",
+        }).toEffect();
+      });
+    },
+  }),
+);
+
+export const UnpdfDocumentPluginLive = unpdfDocumentPlugin;

package/src/index.ts

@@ -0,0 +1 @@
+export { unpdfDocumentPlugin, UnpdfDocumentPluginLive } from "./document-plugin";

package/tsconfig.json

@@ -0,0 +1,14 @@
+{
+  "extends": "@uploadista/typescript-config/server.json",
+  "compilerOptions": {
+    "baseUrl": "./",
+    "paths": {
+      "@/*": ["./src/*"]
+    },
+    "outDir": "./dist",
+    "rootDir": "./src",
+    "lib": ["ESNext", "DOM", "DOM.Iterable"],
+    "types": []
+  },
+  "include": ["src"]
+}