@vestfoldfylke/pdf-text-extract - npm Package Compare versions

Comparing version 1.0.0 to 2.0.0

index.js

		@@ -1,2 +0,6 @@
		const pdfjsLib = require('pdfjs-dist/legacy/build/pdf.js')
		const getPdfDocument = async (pdf) => {
		const { getDocument } = await import('pdfjs-dist/legacy/build/pdf.min.mjs')
		return await getDocument(pdf)
		}

		// Need the legacy build to work with Node - newer versions require Canvas to work, we don't want it
		@@ -50,3 +54,3 @@
		}
		const loadingTask = await pdfjsLib.getDocument(pdf)
		const loadingTask = await getPdfDocument(pdf)
		const doc = await loadingTask.promise
		@@ -53,0 +57,0 @@ pdfData.metadata = await doc.getMetadata()

package.json

		{
		"name": "@vestfoldfylke/pdf-text-extract",
		"description": "Node module that extracts metadata, text-content, and styling from readable pdf-files",
		"version": "1.0.0",
		"version": "2.0.0",
		"main": "index.js",
		@@ -28,3 +28,3 @@ "scripts": {
		"dependencies": {
		"pdfjs-dist": "2.16.105"
		"pdfjs-dist": "^4.2.67"
		},
		@@ -34,2 +34,2 @@ "devDependencies": {
		}
		}
		}

README.md

		@@ -17,3 +17,2 @@ # pdf-text-extract
		const pdf = 'https://<url-to-pdf>.pdf' // Network resource. Remember to handle CORS if using url
		const pdf = readFileSync('./<path-to-pdf>.pdf') // Buffer (doesnt have to come from readFile - just as an example)
		const pdf = new Uint8Array(readFileSync('./<path-to-pdf>.pdf')) // Uint8Array (doesnt have to come from readFile - just as an example)
		@@ -20,0 +19,0 @@ const pdf = { url: './<path-or url-to-pdf>.pdf', data: 'arrayBuffer or similar', verbosity: 0, ...options } // use either url or data - options are found in typedef, verboosity: 0 for suppressing logs

Improved metrics