ZenBrowserMirrors/pdf.js
1
0
Fork 0
mirror of https://github.com/zen-browser/pdf.js.git synced 2025-07-10 18:25:37 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Extract one page after the other and not all pages at once

Browse source
This commit is contained in:
Julian Viereck 2012-04-08 16:18:43 -07:00
parent 3c77291013
commit c9fb5637c3
3 changed files with 49 additions and 49 deletions
Download patch file Download diff file Expand all files Collapse all files

38
src/worker.js
View file

@ -94,7 +94,6 @@ var WorkerMessageHandler = {
handler.on('page_request', function wphSetupPageRequest(pageNum) {
pageNum = parseInt(pageNum);
// The following code does quite the same as
// Page.prototype.startRendering, but stops at one point and sends the
// result back to the main thread.
@ -156,37 +155,20 @@ var WorkerMessageHandler = {
});
}, this);
handler.on('extract_text', function wphExtractText() {
var numPages = pdfModel.numPages;
var index = [];
handler.on('extract_text', function wphExtractText(pageNum) {
var start = Date.now();
function indexPage(pageNum) {
if (pageNum > numPages) {
console.log('text indexing: time=%dms', Date.now() - start);
handler.send('text_extracted', [index]);
return;
}
var textContent = '';
// try {
var page = pdfModel.getPage(pageNum);
textContent = page.extractTextContent();
// } catch (e) {
// // Skip errored pages
// }
index.push(textContent);
// processing one page, interrupting thread to process
// other requests
setTimeout(function extractTextNextPage() {
indexPage(pageNum + 1);
}, 0);
var textContent = '';
try {
var page = pdfModel.getPage(pageNum);
textContent = page.extractTextContent();
} catch (e) {
// Skip errored pages
}
indexPage(1);
console.log('text indexing: page=%d - time=%dms',
pageNum, Date.now() - start);
handler.send('text_extracted', [pageNum, textContent]);
});
}
};