mirrors/pdf.js
1
0
Fork 0
mirror of https://github.com/mozilla/pdf.js.git synced 2025-04-20 15:18:08 +02:00
Code Activity

Merge pull request #16186 from Snuffleupagus/issue-16176

Browse source 
Support multi-byte ToUnicode entries, when using predefined CMaps (issue 16176)
This commit is contained in:
Jonas Jenwald 2023-03-21 22:17:18 +01:00 • committed by GitHub
commit 9321758d91
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 27 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

1
test/pdfs/.gitignore vendored
View file

@ -118,6 +118,7 @@
!issue6127.pdf
!issue7891_bc0.pdf
!issue11242_reduced.pdf
!issue16176.pdf
!issue11279.pdf
!issue11362.pdf
!issue13325_reduced.pdf

BIN
test/pdfs/issue16176.pdf Normal file
View file

Binary file not shown.

18
test/unit/api_spec.js
View file

@ -29,6 +29,7 @@ import {
} from "../../src/shared/util.js";
import {
buildGetDocumentParams,
CMAP_URL,
DefaultFileReaderFactory,
TEST_PDFS_PATH,
} from "./test_utils.js";
@ -2623,6 +2624,23 @@ Caron Broadcasting, Inc., an Ohio corporation (“Lessee”).`)
await loadingTask.destroy();
});
it("gets text content with multi-byte entries, using predefined CMaps (issue 16176)", async function () {
const loadingTask = getDocument(
buildGetDocumentParams("issue16176.pdf", {
cMapUrl: CMAP_URL,
useWorkerFetch: false,
})
);
const pdfDoc = await loadingTask.promise;
const pdfPage = await pdfDoc.getPage(1);
const { items } = await pdfPage.getTextContent();
const text = mergeText(items);
expect(text).toEqual("𠮷");
await loadingTask.destroy();
});
it("gets empty structure tree", async function () {
const tree = await page.getStructTree();