From d8c28fbfad2f35bda52080993f2c40c5efc0e6f3 Mon Sep 17 00:00:00 2001 From: George Date: Fri, 10 May 2024 20:55:01 +0100 Subject: [PATCH 1/3] pdf2json -> v3.1.2 --- package.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/package.json b/package.json index fff3afc..3eb131c 100644 --- a/package.json +++ b/package.json @@ -21,6 +21,6 @@ } ], "dependencies": { - "pdf2json": "^0.7.1" + "pdf2json": "3.1.2" } } From 51d8e3a0c86af0c1b1cbde9bcd4b0d0456dd178c Mon Sep 17 00:00:00 2001 From: George Date: Fri, 10 May 2024 21:02:35 +0100 Subject: [PATCH 2/3] Update pdf2json import --- lib/pdf2table.js | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/lib/pdf2table.js b/lib/pdf2table.js index 91afc28..73181ac 100644 --- a/lib/pdf2table.js +++ b/lib/pdf2table.js @@ -23,8 +23,7 @@ SOFTWARE. */ var path = require('path'); -var PDFParser = require("pdf2json/pdfparser"); - +var PDFParser = require("pdf2json"); function parse (pdfBuffer, callback) { var pdfParser = new PDFParser(); From 5526c055053e950546abd9dc606a4012f9014a30 Mon Sep 17 00:00:00 2001 From: George Date: Fri, 10 May 2024 21:16:21 +0100 Subject: [PATCH 3/3] Tweak page data returned by pdf2json --- lib/pdf2table.js | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/lib/pdf2table.js b/lib/pdf2table.js index 73181ac..a9c0e7e 100644 --- a/lib/pdf2table.js +++ b/lib/pdf2table.js @@ -67,8 +67,8 @@ function parse (pdfBuffer, callback) { var smallestYValueForPage = []; - for (var p = 0; p < data.data.Pages.length; p++) { - var page = data.data.Pages[p]; + for (var p = 0; p < data.Pages.length; p++) { + var page = data.Pages[p]; var smallestYValue = null; // per page @@ -110,8 +110,8 @@ function parse (pdfBuffer, callback) { // now lets find Texts with 'the same' y-values, Actually y-values in the range of y-smallestYValue and y+smallestYValue: var myPages = []; - for (var p = 0; p < data.data.Pages.length; p++) { - var page = data.data.Pages[p]; + for (var p = 0; p < data.Pages.length; p++) { + var page = data.Pages[p]; var rows = []; // store Texts and their x positions in rows