Sakurai/pdf.js
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Simplify extractText in web/pdf_find_controller.js

Browse Source 
Currently this method first uses a loop to build a temporary array to hold Promises, which are then resolved from a recursive helper function once the textContent is fetched for each page.

To me, this is unncessarily complicated, since we can do everything within one loop by simply chaining the asynchronous calls to retrieve the textContent. (Note that this guarantees that the textContent of the pages is still fetched sequentially.)
This commit is contained in:
Jonas Jenwald 2017-05-10 13:33:08 +02:00
parent 9bfbf27f94
commit c750514903
1 changed files with 17 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
web/pdf_find_controller.js
View File

@ -13,6 +13,7 @@
* limitations under the License.
*/
import { createPromiseCapability } from './pdfjs';
import { scrollIntoView } from './ui_utils';
var FindStates = {
@ -231,43 +232,32 @@ var PDFFindController = (function PDFFindControllerClosure() {
}
},
extractText: function PDFFindController_extractText() {
extractText() {
if (this.startedTextExtraction) {
return;
}
this.startedTextExtraction = true;
this.pageContents.length = 0;
this.pageContents = [];
var extractTextPromisesResolves = [];
var numPages = this.pdfViewer.pagesCount;
for (var i = 0; i < numPages; i++) {
this.extractTextPromises.push(new Promise(function (resolve) {
extractTextPromisesResolves.push(resolve);
}));
}
let promise = Promise.resolve();
for (let i = 0, ii = this.pdfViewer.pagesCount; i < ii; i++) {
let extractTextCapability = createPromiseCapability();
this.extractTextPromises[i] = extractTextCapability.promise;
var self = this;
function extractPageText(pageIndex) {
self.pdfViewer.getPageTextContent(pageIndex).then(
function textContentResolved(textContent) {
var textItems = textContent.items;
var str = [];
promise = promise.then(() => {
return this.pdfViewer.getPageTextContent(i).then((textContent) => {
let textItems = textContent.items;
let strBuf = [];
for (var i = 0, len = textItems.length; i < len; i++) {
str.push(textItems[i].str);
for (let j = 0, jj = textItems.length; j < jj; j++) {
strBuf.push(textItems[j].str);
}
// Store the pageContent as a string.
self.pageContents.push(str.join(''));
extractTextPromisesResolves[pageIndex](pageIndex);
if ((pageIndex + 1) < self.pdfViewer.pagesCount) {
extractPageText(pageIndex + 1);
}
}
);
this.pageContents[i] = strBuf.join('');
extractTextCapability.resolve(i);
});
});
}
extractPageText(0);
},
executeCommand: function PDFFindController_executeCommand(cmd, state) {