yetangitu/pdf.js
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[api-minor] Add a parameter to PDFPageProxy_getTextContent that controls whether PartialEvaluator_getTextContent will attempt to combine same line text items

Browse source 
From the discussion in issue 7445, it seems that there may be cases where an API consumer would want to get the text content as is, without combined text items.
This commit is contained in:
Jonas Jenwald 2016-07-03 18:29:47 +02:00
parent 9228a04061
commit f297e4d17c
8 changed files with 42 additions and 27 deletions
Download patch file Download diff file Expand all files Collapse all files

4
src/core/worker.js
View file

@ -891,12 +891,14 @@ var WorkerMessageHandler = {
handler.on('GetTextContent', function wphExtractText(data) {
var pageIndex = data.pageIndex;
var normalizeWhitespace = data.normalizeWhitespace;
var combineTextItems = data.combineTextItems;
return pdfManager.getPage(pageIndex).then(function(page) {
var task = new WorkerTask('GetTextContent: page ' + pageIndex);
startWorkerTask(task);
var pageNum = pageIndex + 1;
var start = Date.now();
return page.extractTextContent(task, normalizeWhitespace).then(
return page.extractTextContent(task, normalizeWhitespace,
combineTextItems).then(
function(textContent) {
finishWorkerTask(task);
info('text indexing: page=' + pageNum + ' - time=' +