feat: Integrate pdfjs-dist for improved PDF parsing fallback

Co-authored-by: Copilot <copilot@github.com>

backend/package-lock.json

@@ -16,6 +16,7 @@
         "multer": "^1.4.5-lts.1",
         "pdf-lib": "^1.17.1",
         "pdf-parse": "^1.1.1",
+        "pdfjs-dist": "^5.7.284",
         "reflect-metadata": "^0.2.2",
         "rxjs": "^7.8.1",
         "tesseract.js": "^5.1.1"
@@ -411,6 +412,271 @@
         "node": ">=8"
       }
     },
+    "node_modules/@napi-rs/canvas": {
+      "version": "0.1.100",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas/-/canvas-0.1.100.tgz",
+      "integrity": "sha512-xglYA6q3XO5P3BNJYxVZ1IV7DLVjp1Py6nwag88YntrS+3vKHyYcMqXVS4ZztJmwz2uGvz1FWhI/4LgbR5uQDA==",
+      "license": "MIT",
+      "optional": true,
+      "workspaces": [
+        "e2e/*"
+      ],
+      "engines": {
+        "node": ">= 10"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/Brooooooklyn"
+      },
+      "optionalDependencies": {
+        "@napi-rs/canvas-android-arm64": "0.1.100",
+        "@napi-rs/canvas-darwin-arm64": "0.1.100",
+        "@napi-rs/canvas-darwin-x64": "0.1.100",
+        "@napi-rs/canvas-linux-arm-gnueabihf": "0.1.100",
+        "@napi-rs/canvas-linux-arm64-gnu": "0.1.100",
+        "@napi-rs/canvas-linux-arm64-musl": "0.1.100",
+        "@napi-rs/canvas-linux-riscv64-gnu": "0.1.100",
+        "@napi-rs/canvas-linux-x64-gnu": "0.1.100",
+        "@napi-rs/canvas-linux-x64-musl": "0.1.100",
+        "@napi-rs/canvas-win32-arm64-msvc": "0.1.100",
+        "@napi-rs/canvas-win32-x64-msvc": "0.1.100"
+      }
+    },
+    "node_modules/@napi-rs/canvas-android-arm64": {
+      "version": "0.1.100",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-android-arm64/-/canvas-android-arm64-0.1.100.tgz",
+      "integrity": "sha512-hjhCKhntPv9+t4ckHymdx0phYNcVW+GKQR6Lzw2zE+pOVjOplSmtx9nNNknTjbEDLcuLZqA1y8ufKg1XfgftzQ==",
+      "cpu": [
+        "arm64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "android"
+      ],
+      "engines": {
+        "node": ">= 10"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/Brooooooklyn"
+      }
+    },
+    "node_modules/@napi-rs/canvas-darwin-arm64": {
+      "version": "0.1.100",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-darwin-arm64/-/canvas-darwin-arm64-0.1.100.tgz",
+      "integrity": "sha512-2PcswRaC7Ly645DGt88///zuFDhJxJYdKAs1uU3mfk1atYkXufgcgLfBpk6Tm12nCQBaNt1wpybuPZ4qOhTo8A==",
+      "cpu": [
+        "arm64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "darwin"
+      ],
+      "engines": {
+        "node": ">= 10"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/Brooooooklyn"
+      }
+    },
+    "node_modules/@napi-rs/canvas-darwin-x64": {
+      "version": "0.1.100",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-darwin-x64/-/canvas-darwin-x64-0.1.100.tgz",
+      "integrity": "sha512-ePNZtj7pNIva/siZMg+HmbeozkIjqUIYdoymH8HaA3qK7LfzFN4WMBM8G6HQ9ZC+H3+Dnn5pqtiXpgLykaPOhw==",
+      "cpu": [
+        "x64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "darwin"
+      ],
+      "engines": {
+        "node": ">= 10"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/Brooooooklyn"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-arm-gnueabihf": {
+      "version": "0.1.100",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-arm-gnueabihf/-/canvas-linux-arm-gnueabihf-0.1.100.tgz",
+      "integrity": "sha512-d5cDB48oWFGU8/XPhUOFAlySgb/VAu7D+s8fi55K1Pcfg8aPplHWqMgibhVLU8ky7Pyg/fuiVLz4Nf3JrSTuUA==",
+      "cpu": [
+        "arm"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/Brooooooklyn"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-arm64-gnu": {
+      "version": "0.1.100",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-arm64-gnu/-/canvas-linux-arm64-gnu-0.1.100.tgz",
+      "integrity": "sha512-rDxgxRu69RvDlX/bh9o22DxLsGr8EqsNgotL9+RwQE1S0b0cqeatqsw6aW45mukm0B42DIAaAacKaYQ8cqS1nw==",
+      "cpu": [
+        "arm64"
+      ],
+      "libc": [
+        "glibc"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/Brooooooklyn"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-arm64-musl": {
+      "version": "0.1.100",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-arm64-musl/-/canvas-linux-arm64-musl-0.1.100.tgz",
+      "integrity": "sha512-K3mDW66N+xT2/V439u1alFANiBUjdEx2gLiNYnCmUsva5jZMxWTjafBYwTzYK+EMFMHrUoabuU+T1BIP5CgbYQ==",
+      "cpu": [
+        "arm64"
+      ],
+      "libc": [
+        "musl"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/Brooooooklyn"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-riscv64-gnu": {
+      "version": "0.1.100",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-riscv64-gnu/-/canvas-linux-riscv64-gnu-0.1.100.tgz",
+      "integrity": "sha512-mooqUBTIsccZpnoQC4NgrC1v6C1vof39etLNMnBwCY+p0gajWJvAHLGQ6g/gGyS5YrpDW+GefSN4+Cvcr08UWw==",
+      "cpu": [
+        "riscv64"
+      ],
+      "libc": [
+        "glibc"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/Brooooooklyn"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-x64-gnu": {
+      "version": "0.1.100",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-x64-gnu/-/canvas-linux-x64-gnu-0.1.100.tgz",
+      "integrity": "sha512-1eCvkDCazm7FFhsT7DfGOdSaHgZVK3bt/dSBl5EWHOWmnz+I7j8tPseJqqD81NF+MH21jKUK4wQSDjN0mdhnTg==",
+      "cpu": [
+        "x64"
+      ],
+      "libc": [
+        "glibc"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/Brooooooklyn"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-x64-musl": {
+      "version": "0.1.100",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-x64-musl/-/canvas-linux-x64-musl-0.1.100.tgz",
+      "integrity": "sha512-20arT6lnI19S68qNlii73TSEDbECNgzMz2EpldC1V3mZFuRkeujXkcebRk0LRJe9SEUAooYiLokfMViY8IX7yA==",
+      "cpu": [
+        "x64"
+      ],
+      "libc": [
+        "musl"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/Brooooooklyn"
+      }
+    },
+    "node_modules/@napi-rs/canvas-win32-arm64-msvc": {
+      "version": "0.1.100",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-win32-arm64-msvc/-/canvas-win32-arm64-msvc-0.1.100.tgz",
+      "integrity": "sha512-DZFFT1wIAg37LJw37yhMRFfjATd3vTQzjZ1Yki8u2vhO6Hi5VE6BVaGQ1aaDu7xb4iMErz+9EOwjpS7xcxFeBw==",
+      "cpu": [
+        "arm64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "win32"
+      ],
+      "engines": {
+        "node": ">= 10"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/Brooooooklyn"
+      }
+    },
+    "node_modules/@napi-rs/canvas-win32-x64-msvc": {
+      "version": "0.1.100",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-win32-x64-msvc/-/canvas-win32-x64-msvc-0.1.100.tgz",
+      "integrity": "sha512-MyT1j3mHC2+Lu4pBi9mKyMJhtP6U7k7EldY7sj/uS5gJA65gTXt8MefJQXLJo5d/vZbuWmfxzkEUNc/urV3pHA==",
+      "cpu": [
+        "x64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "win32"
+      ],
+      "engines": {
+        "node": ">= 10"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/Brooooooklyn"
+      }
+    },
     "node_modules/@nestjs/cli": {
       "version": "10.4.9",
       "resolved": "https://registry.npmjs.org/@nestjs/cli/-/cli-10.4.9.tgz",
@@ -3494,6 +3760,18 @@
         "url": "https://github.com/sponsors/mehmet-kozan"
       }
     },
+    "node_modules/pdfjs-dist": {
+      "version": "5.7.284",
+      "resolved": "https://registry.npmjs.org/pdfjs-dist/-/pdfjs-dist-5.7.284.tgz",
+      "integrity": "sha512-h4EdYQczmGhbOlqc3PPZwxevn7ApdWPbovAuWXOB/DjIyigSnwfy2oze7c6mRcSr9XgLp3eN3EeL4DyySTPMFw==",
+      "license": "Apache-2.0",
+      "engines": {
+        "node": ">=22.13.0 || >=24"
+      },
+      "optionalDependencies": {
+        "@napi-rs/canvas": "^0.1.100"
+      }
+    },
     "node_modules/picocolors": {
       "version": "1.1.1",
       "resolved": "https://registry.npmjs.org/picocolors/-/picocolors-1.1.1.tgz",

backend/package.json

@@ -16,6 +16,7 @@
     "multer": "^1.4.5-lts.1",
     "pdf-lib": "^1.17.1",
     "pdf-parse": "^1.1.1",
+    "pdfjs-dist": "^5.7.284",
     "reflect-metadata": "^0.2.2",
     "rxjs": "^7.8.1",
     "tesseract.js": "^5.1.1"

backend/src/receipt-parsing/receipt-parsing.service.ts

@@ -288,13 +288,23 @@ export class ReceiptParsingService {
     } catch (err) {
       this.logger.warn(`pdf-parse misslyckades: ${err}`);
       
-      // Fallback to pdf-lib for more complex PDFs
+      // Fallback to pdfjs-dist for more complex PDFs
       try {
-        const { PDFDocument } = await import('pdf-lib');
+        const pdfjsLib = await import('pdfjs-dist');
-        const pdfDoc = await PDFDocument.load(buffer);
+        const loadingTask = pdfjsLib.getDocument({ data: buffer });
-        text = pdfDoc.getPages().map(page => page.getText()).join(' ');
+        const pdfDocument = await loadingTask.promise;
+        
+        let fullText = '';
+        for (let i = 1; i <= pdfDocument.numPages; i++) {
+          const page = await pdfDocument.getPage(i);
+          const textContent = await page.getTextContent();
+          const pageText = textContent.items.map(item => item.str).join(' ');
+          fullText += pageText + ' ';
+        }
+        
+        text = fullText;
       } catch (fallbackErr) {
-        this.logger.error(`Både pdf-parse och pdf-lib misslyckades: ${fallbackErr}`);
+        this.logger.error(`Både pdf-parse och pdfjs-dist misslyckades: ${fallbackErr}`);
         throw new BadRequestException('PDF-filen kunde inte läsas. Kontrollera att filen inte är skadad eller krypterad.');
       }
     }