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

Correctly compute the mapping between text and normalized text when it contains a compound word on two lines

It fixes #19120.

The original text doesn't contain the cr so we must take that into account.
This commit is contained in:
Calixte Denizet 2024-11-28 15:56:00 +01:00
parent 22babd722f
commit aa9503e51f
4 changed files with 27 additions and 5 deletions

View file

@ -682,3 +682,4 @@
!bug1922766.pdf
!issue18956.pdf
!issue19083.pdf
!issue19120.pdf

BIN
test/pdfs/issue19120.pdf Executable file

Binary file not shown.

View file

@ -1062,15 +1062,16 @@ describe("pdf_find_controller", function () {
await testOnFind({ eventBus });
});
it("performs a search in a text with compound word on two lines", async function () {
it("performs a search in a text with a compound word on two lines", async function () {
const { eventBus, pdfFindController } =
await initPdfFindController("issue18693.pdf");
const query = "hel-Lo";
await testSearch({
eventBus,
pdfFindController,
state: {
query: "hel-Lo",
query,
},
matchesPerPage: [1],
selectedMatch: {
@ -1078,7 +1079,28 @@ describe("pdf_find_controller", function () {
matchIndex: 0,
},
pageMatches: [[6]],
pageMatchesLength: [[7]],
pageMatchesLength: [[query.length]],
});
});
it("performs a search after a compound word on two lines", async function () {
const { eventBus, pdfFindController } =
await initPdfFindController("issue19120.pdf");
const query = "a";
await testSearch({
eventBus,
pdfFindController,
state: {
query,
},
matchesPerPage: [3],
selectedMatch: {
pageIndex: 0,
matchIndex: 0,
},
pageMatches: [[0, 4, 15]],
pageMatchesLength: [[query.length, query.length, query.length]],
});
});