ZenBrowserMirrors/pdf.js
1
0
Fork 0
mirror of https://github.com/zen-browser/pdf.js.git synced 2025-07-10 02:05:37 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add even more non-standard ligatures (PR 15517 follow-up)

Browse source 
Given that we already create multi-byte ToUnicode entries in other cases, see e.g. the `getNormalizedUnicodes` table, this is hopefully fine.
This commit is contained in:
Jonas Jenwald 2023-03-22 10:40:12 +01:00
parent f39ff20485
commit 137a2d6e30
3 changed files with 18 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

17
test/unit/api_spec.js
View file

@ -2607,23 +2607,6 @@ Caron Broadcasting, Inc., an Ohio corporation (“Lessee”).`)
await loadingTask.destroy();
});
// TODO: Change this to a `text` reference test instead.
// Currently that doesn't work, since the `XMLSerializer` fails on
// the ASCII "control characters" found in the text-content.
it("gets text content with non-standard ligatures (issue issue15516)", async function () {
const loadingTask = getDocument(
buildGetDocumentParams("issue15516_reduced.pdf")
);
const pdfDoc = await loadingTask.promise;
const pdfPage = await pdfDoc.getPage(1);
const { items } = await pdfPage.getTextContent();
const text = mergeText(items);
expect(text).toEqual("ffi fi ffl ff fl \x07 \x08 Ý");
await loadingTask.destroy();
});
it("gets text content with multi-byte entries, using predefined CMaps (issue 16176)", async function () {
const loadingTask = getDocument(
buildGetDocumentParams("issue16176.pdf", {