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

20
test/unit/api_spec.js
View file

@ -482,11 +482,21 @@ describe('api', function() {
});
});
it('gets text content', function () {
var promise = page.getTextContent();
waitsForPromiseResolved(promise, function (data) {
expect(!!data.items).toEqual(true);
expect(data.items.length).toEqual(7);
expect(!!data.styles).toEqual(true);
var defaultPromise = page.getTextContent();
var normalizeWhitespacePromise = page.getTextContent({
normalizeWhitespace: true });
var promises = [
defaultPromise,
normalizeWhitespacePromise
];
waitsForPromiseResolved(Promise.all(promises), function (data) {
expect(!!data[0].items).toEqual(true);
expect(data[0].items.length).toEqual(7);
expect(!!data[0].styles).toEqual(true);
// A simple check that ensures the two `textContent` object match.
expect(JSON.stringify(data[0])).toEqual(JSON.stringify(data[1]));
});
});
it('gets operator list', function() {