Marmelator/pdf.js.mirror
1
0
Fork 0
mirror of https://github.com/mozilla/pdf.js.git synced 2026-06-04 01:01:00 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #21197 from Snuffleupagus/find-#extractText-more-await

Browse Source 
Improve error handling in the `PDFFindController.prototype.#extractText` method
This commit is contained in:
calixteman 2026-04-30 08:57:29 +02:00 committed by GitHub
commit ac63d851b8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 27 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
web/pdf_find_controller.js
View File

@ -906,40 +906,36 @@ class PDFFindController {
resolve();
return;
}
await pdfDoc
.getPage(i + 1)
.then(pdfPage => pdfPage.getTextContent(textOptions))
.then(
textContent => {
const strBuf = [];
try {
const pdfPage = await pdfDoc.getPage(i + 1);
const textContent = await pdfPage.getTextContent(textOptions);
for (const textItem of textContent.items) {
strBuf.push(textItem.str);
if (textItem.hasEOL) {
strBuf.push("\n");
}
}
if (pdfDoc !== this._pdfDocument) {
resolve();
return;
}
const strBuf = [];
// Store the normalized page content (text items) as one string.
[
this._pageContents[i],
this._pageDiffs[i],
this._hasDiacritics[i],
] = normalize(strBuf.join(""));
resolve();
},
reason => {
console.error(
`Unable to get text content for page ${i + 1}`,
reason
);
// Page error -- assuming no text content.
this._pageContents[i] = "";
this._pageDiffs[i] = null;
this._hasDiacritics[i] = false;
resolve();
for (const textItem of textContent.items) {
strBuf.push(textItem.str);
if (textItem.hasEOL) {
strBuf.push("\n");
}
);
}
// Store the normalized page content (text items) as one string.
[this._pageContents[i], this._pageDiffs[i], this._hasDiacritics[i]] =
normalize(strBuf.join(""));
} catch (ex) {
if (pdfDoc !== this._pdfDocument) {
resolve();
return;
}
console.error(`Unable to get text content for page ${i + 1}`, ex);
// Page error -- assuming no text content.
[this._pageContents[i], this._pageDiffs[i], this._hasDiacritics[i]] =
["", null, false];
}
resolve();
});
}
}