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

[api-minor] Add a parameter to PDFPageProxy_getTextContent that enables replacing of all whitespace with standard spaces in the textLayer (issue 6612)

Browse source 
This patch goes a bit further than issue 6612 requires, and replaces all kinds of whitespace with standard spaces.

When testing this locally, it actually seemed to slightly improve two existing test-cases (`tracemonkey-text` and `taro-text`).

Fixes 6612.
This commit is contained in:
Jonas Jenwald 2015-11-23 16:57:43 +01:00
parent c2dfe9e9a9
commit 6dfe53b976
12 changed files with 75 additions and 24 deletions
Download patch file Download diff file Expand all files Collapse all files

4
web/pdf_viewer.js
View file

@ -471,7 +471,7 @@ var PDFViewer = (function pdfViewer() {
if (!this.pdfDocument) {
return;
}
var pageView = this._pages[pageNumber - 1];
if (this.isInPresentationMode) {
@ -729,7 +729,7 @@ var PDFViewer = (function pdfViewer() {
getPageTextContent: function (pageIndex) {
return this.pdfDocument.getPage(pageIndex + 1).then(function (page) {
return page.getTextContent();
return page.getTextContent({ normalizeWhitespace: true });
});
},