Skip to content

Convert Catalog.getPageDict to an async method #11312

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Nov 8, 2019
Merged

Convert Catalog.getPageDict to an async method #11312

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0d89006
Convert `Catalog.getPageDict` to an `async` method
Snuffleupagus Nov 4, 2019
79d7c00
Inline a couple of `isRef`/`isDict` checks in the `getPageDict` method
Snuffleupagus Nov 8, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
146 changes: 66 additions & 80 deletions src/core/obj.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,10 +14,9 @@
*/

import {
assert, bytesToString, createPromiseCapability, createValidAbsoluteUrl,
FormatError, info, InvalidPDFException, isBool, isNum, isString,
PermissionFlag, shadow, stringToPDFString, stringToUTF8String, unreachable,
warn
assert, bytesToString, createValidAbsoluteUrl, FormatError, info,
InvalidPDFException, isBool, isNum, isString, PermissionFlag, shadow,
stringToPDFString, stringToUTF8String, unreachable, warn
} from '../shared/util';
import {
clearPrimitiveCaches, Cmd, Dict, isCmd, isDict, isName, isRef, isRefsEqual,
Expand Down Expand Up @@ -680,99 +679,86 @@ class Catalog {
});
}

getPageDict(pageIndex) {
const capability = createPromiseCapability();
async getPageDict(pageIndex) {
const nodesToVisit = [this.catDict.getRaw('Pages')];
const xref = this.xref, pageKidsCountCache = this.pageKidsCountCache;
let count, currentPageIndex = 0;

function next() {
while (nodesToVisit.length) {
const currentNode = nodesToVisit.pop();
while (nodesToVisit.length) {
const currentNode = nodesToVisit.pop();

if (isRef(currentNode)) {
count = pageKidsCountCache.get(currentNode);
// Skip nodes where the page can't be.
if (count > 0 && currentPageIndex + count < pageIndex) {
currentPageIndex += count;
continue;
}
if (currentNode instanceof Ref) {
count = pageKidsCountCache.get(currentNode);
// Skip nodes where the page can't be.
if (count > 0 && currentPageIndex + count < pageIndex) {
currentPageIndex += count;
continue;
}
const obj = await xref.fetchAsync(currentNode);

xref.fetchAsync(currentNode).then(function(obj) {
if (isDict(obj, 'Page') || (isDict(obj) && !obj.has('Kids'))) {
if (pageIndex === currentPageIndex) {
// Cache the Page reference, since it can *greatly* improve
// performance by reducing redundant lookups in long documents
// where all nodes are found at *one* level of the tree.
if (currentNode && !pageKidsCountCache.has(currentNode)) {
pageKidsCountCache.put(currentNode, 1);
}
capability.resolve([obj, currentNode]);
} else {
currentPageIndex++;
next();
}
return;
if ((obj instanceof Dict) && (isName(obj.get('Type'), 'Page') ||
(!obj.has('Type') && !obj.has('Kids')))) {
if (pageIndex === currentPageIndex) {
// Cache the Page reference, since it can *greatly* improve
// performance by reducing redundant lookups in long documents
// where all nodes are found at *one* level of the tree.
if (currentNode && !pageKidsCountCache.has(currentNode)) {
pageKidsCountCache.put(currentNode, 1);
}
nodesToVisit.push(obj);
next();
}, capability.reject);
return;
return [obj, currentNode];
}
currentPageIndex++;
continue;
}
nodesToVisit.push(obj);
continue;
}

// Must be a child page dictionary.
if (!isDict(currentNode)) {
capability.reject(new FormatError(
'Page dictionary kid reference points to wrong type of object.'));
return;
}
// Must be a child page dictionary.
if (!(currentNode instanceof Dict)) {
throw new FormatError(
'Page dictionary kid reference points to wrong type of object.');
}

count = currentNode.get('Count');
if (Number.isInteger(count) && count >= 0) {
// Cache the Kids count, since it can reduce redundant lookups in
// documents where all nodes are found at *one* level of the tree.
const objId = currentNode.objId;
if (objId && !pageKidsCountCache.has(objId)) {
pageKidsCountCache.put(objId, count);
}
// Skip nodes where the page can't be.
if (currentPageIndex + count <= pageIndex) {
currentPageIndex += count;
continue;
}
count = currentNode.get('Count');
if (Number.isInteger(count) && count >= 0) {
// Cache the Kids count, since it can reduce redundant lookups in
// documents where all nodes are found at *one* level of the tree.
const objId = currentNode.objId;
if (objId && !pageKidsCountCache.has(objId)) {
pageKidsCountCache.put(objId, count);
}
// Skip nodes where the page can't be.
if (currentPageIndex + count <= pageIndex) {
currentPageIndex += count;
continue;
}
}

const kids = currentNode.get('Kids');
if (!Array.isArray(kids)) {
// Prevent errors in corrupt PDF documents that violate the
// specification by *inlining* Page dicts directly in the Kids
// array, rather than using indirect objects (fixes issue9540.pdf).
if (isName(currentNode.get('Type'), 'Page') ||
(!currentNode.has('Type') && currentNode.has('Contents'))) {
if (currentPageIndex === pageIndex) {
capability.resolve([currentNode, null]);
return;
}
currentPageIndex++;
continue;
const kids = currentNode.get('Kids');
if (!Array.isArray(kids)) {
// Prevent errors in corrupt PDF documents that violate the
// specification by *inlining* Page dicts directly in the Kids
// array, rather than using indirect objects (fixes issue9540.pdf).
if (isName(currentNode.get('Type'), 'Page') ||
(!currentNode.has('Type') && currentNode.has('Contents'))) {
if (currentPageIndex === pageIndex) {
return [currentNode, null];
}

capability.reject(new FormatError(
'Page dictionary kids object is not an array.'));
return;
currentPageIndex++;
continue;
}
throw new FormatError('Page dictionary kids object is not an array.');
}

// Always check all `Kids` nodes, to avoid getting stuck in an empty
// node further down in the tree (see issue5644.pdf, issue8088.pdf),
// and to ensure that we actually find the correct `Page` dict.
for (let last = kids.length - 1; last >= 0; last--) {
nodesToVisit.push(kids[last]);
}
// Always check all `Kids` nodes, to avoid getting stuck in an empty
// node further down in the tree (see issue5644.pdf, issue8088.pdf),
// and to ensure that we actually find the correct `Page` dict.
for (let last = kids.length - 1; last >= 0; last--) {
nodesToVisit.push(kids[last]);
}
capability.reject(new Error(`Page index ${pageIndex} not found.`));
}
next();
return capability.promise;
throw new Error(`Page index ${pageIndex} not found.`);
}

getPageIndex(pageRef) {
Expand Down