2015-11-22 01:32:47 +09:00
|
|
|
/* Copyright 2012 Mozilla Foundation
|
|
|
|
*
|
|
|
|
* Licensed under the Apache License, Version 2.0 (the "License");
|
|
|
|
* you may not use this file except in compliance with the License.
|
|
|
|
* You may obtain a copy of the License at
|
|
|
|
*
|
|
|
|
* http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
*
|
|
|
|
* Unless required by applicable law or agreed to in writing, software
|
|
|
|
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
|
|
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
|
|
* See the License for the specific language governing permissions and
|
|
|
|
* limitations under the License.
|
|
|
|
*/
|
|
|
|
/* uses XRef */
|
|
|
|
|
Slightly simplify the lookup of data in `Dict.{get, getAsync, has}`
Note that `Dict.set` will only be called with values returned through `Parser.getObj`, and thus indirectly via `Lexer.getObj`. Since neither of those methods will ever return `undefined`, we can simply assert that that's the case when inserting data into the `Dict` and thus get rid of `in` checks when doing the data lookups.
In this case, since `Dict.set` is fairly hot, the patch utilizes an *inline check* and when necessary a direct call to `unreachable` to not affect performance of `gulp server/test` too much (rather than always just calling `assert`).
For very large and complex PDF files this will help performance *slightly*, since `Dict.{get, getAsync, has}` is called *a lot* during parsing in the worker.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, with the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
which gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2838 | 2820 | -18 | -0.65 | faster
Firefox | Page Request | 250 | 1 | 2 | 0 | 11.92 | slower
Firefox | Rendering | 250 | 2837 | 2818 | -19 | -0.65 | faster
```
2020-01-31 19:39:48 +09:00
|
|
|
import { assert, unreachable } from "../shared/util.js";
|
2019-05-26 00:40:14 +09:00
|
|
|
|
2017-01-27 21:34:37 +09:00
|
|
|
var EOF = {};
|
|
|
|
|
2015-11-22 01:32:47 +09:00
|
|
|
var Name = (function NameClosure() {
|
2019-05-26 21:20:31 +09:00
|
|
|
let nameCache = Object.create(null);
|
|
|
|
|
2020-03-25 18:15:50 +09:00
|
|
|
// eslint-disable-next-line no-shadow
|
2015-11-22 01:32:47 +09:00
|
|
|
function Name(name) {
|
|
|
|
this.name = name;
|
|
|
|
}
|
|
|
|
|
|
|
|
Name.prototype = {};
|
|
|
|
|
|
|
|
Name.get = function Name_get(name) {
|
|
|
|
var nameValue = nameCache[name];
|
2020-02-23 04:53:47 +09:00
|
|
|
// eslint-disable-next-line no-restricted-syntax
|
Enable auto-formatting of the entire code-base using Prettier (issue 11444)
Note that Prettier, purposely, has only limited [configuration options](https://prettier.io/docs/en/options.html). The configuration file is based on [the one in `mozilla central`](https://searchfox.org/mozilla-central/source/.prettierrc) with just a few additions (to avoid future breakage if the defaults ever changes).
Prettier is being used for a couple of reasons:
- To be consistent with `mozilla-central`, where Prettier is already in use across the tree.
- To ensure a *consistent* coding style everywhere, which is automatically enforced during linting (since Prettier is used as an ESLint plugin). This thus ends "all" formatting disussions once and for all, removing the need for review comments on most stylistic matters.
Many ESLint options are now redundant, and I've tried my best to remove all the now unnecessary options (but I may have missed some).
Note also that since Prettier considers the `printWidth` option as a guide, rather than a hard rule, this patch resorts to a small hack in the ESLint config to ensure that *comments* won't become too long.
*Please note:* This patch is generated automatically, by appending the `--fix` argument to the ESLint call used in the `gulp lint` task. It will thus require some additional clean-up, which will be done in a *separate* commit.
(On a more personal note, I'll readily admit that some of the changes Prettier makes are *extremely* ugly. However, in the name of consistency we'll probably have to live with that.)
2019-12-25 23:59:37 +09:00
|
|
|
return nameValue ? nameValue : (nameCache[name] = new Name(name));
|
2015-11-22 01:32:47 +09:00
|
|
|
};
|
|
|
|
|
2020-04-14 19:28:14 +09:00
|
|
|
Name._clearCache = function () {
|
2019-05-26 21:20:31 +09:00
|
|
|
nameCache = Object.create(null);
|
|
|
|
};
|
|
|
|
|
2015-11-22 01:32:47 +09:00
|
|
|
return Name;
|
|
|
|
})();
|
|
|
|
|
|
|
|
var Cmd = (function CmdClosure() {
|
2019-05-26 21:20:31 +09:00
|
|
|
let cmdCache = Object.create(null);
|
|
|
|
|
2020-03-25 18:15:50 +09:00
|
|
|
// eslint-disable-next-line no-shadow
|
2015-11-22 01:32:47 +09:00
|
|
|
function Cmd(cmd) {
|
|
|
|
this.cmd = cmd;
|
|
|
|
}
|
|
|
|
|
|
|
|
Cmd.prototype = {};
|
|
|
|
|
|
|
|
Cmd.get = function Cmd_get(cmd) {
|
|
|
|
var cmdValue = cmdCache[cmd];
|
2020-02-23 04:53:47 +09:00
|
|
|
// eslint-disable-next-line no-restricted-syntax
|
Enable auto-formatting of the entire code-base using Prettier (issue 11444)
Note that Prettier, purposely, has only limited [configuration options](https://prettier.io/docs/en/options.html). The configuration file is based on [the one in `mozilla central`](https://searchfox.org/mozilla-central/source/.prettierrc) with just a few additions (to avoid future breakage if the defaults ever changes).
Prettier is being used for a couple of reasons:
- To be consistent with `mozilla-central`, where Prettier is already in use across the tree.
- To ensure a *consistent* coding style everywhere, which is automatically enforced during linting (since Prettier is used as an ESLint plugin). This thus ends "all" formatting disussions once and for all, removing the need for review comments on most stylistic matters.
Many ESLint options are now redundant, and I've tried my best to remove all the now unnecessary options (but I may have missed some).
Note also that since Prettier considers the `printWidth` option as a guide, rather than a hard rule, this patch resorts to a small hack in the ESLint config to ensure that *comments* won't become too long.
*Please note:* This patch is generated automatically, by appending the `--fix` argument to the ESLint call used in the `gulp lint` task. It will thus require some additional clean-up, which will be done in a *separate* commit.
(On a more personal note, I'll readily admit that some of the changes Prettier makes are *extremely* ugly. However, in the name of consistency we'll probably have to live with that.)
2019-12-25 23:59:37 +09:00
|
|
|
return cmdValue ? cmdValue : (cmdCache[cmd] = new Cmd(cmd));
|
2015-11-22 01:32:47 +09:00
|
|
|
};
|
|
|
|
|
2020-04-14 19:28:14 +09:00
|
|
|
Cmd._clearCache = function () {
|
2019-05-26 21:20:31 +09:00
|
|
|
cmdCache = Object.create(null);
|
|
|
|
};
|
|
|
|
|
2015-11-22 01:32:47 +09:00
|
|
|
return Cmd;
|
|
|
|
})();
|
|
|
|
|
|
|
|
var Dict = (function DictClosure() {
|
|
|
|
var nonSerializable = function nonSerializableClosure() {
|
|
|
|
return nonSerializable; // creating closure on some variable
|
|
|
|
};
|
|
|
|
|
|
|
|
// xref is optional
|
2020-03-25 18:15:50 +09:00
|
|
|
// eslint-disable-next-line no-shadow
|
2015-11-22 01:32:47 +09:00
|
|
|
function Dict(xref) {
|
|
|
|
// Map should only be used internally, use functions below to access.
|
2017-06-13 17:25:33 +09:00
|
|
|
this._map = Object.create(null);
|
2015-11-22 01:32:47 +09:00
|
|
|
this.xref = xref;
|
|
|
|
this.objId = null;
|
2016-09-23 21:10:27 +09:00
|
|
|
this.suppressEncryption = false;
|
2015-11-22 01:32:47 +09:00
|
|
|
this.__nonSerializable__ = nonSerializable; // disable cloning of the Dict
|
|
|
|
}
|
|
|
|
|
|
|
|
Dict.prototype = {
|
|
|
|
assignXref: function Dict_assignXref(newXref) {
|
|
|
|
this.xref = newXref;
|
|
|
|
},
|
|
|
|
|
|
|
|
// automatically dereferences Ref objects
|
Reduce the number of function calls in the `Dict` class
The following changes were made:
- Remove unnecessary `typeof` checks in the `get`/`getAsync` methods.
- Reduce unnecessary code duplication in the `get`/`getAsync` methods.
- Inline the `Ref` checks in the `get`/`getAsync`/`getArray` methods, since it helps avoid many unnecessary functions calls. I.e. this way it's possible to directly call `XRef.{fetch, fetchAsync)` only when necessary, rather than always having to call `XRef.{fetchIfRef, fetchIfRefAsync)`.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, using the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
This gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2821 | 2790 | -32 | -1.12 | faster
Firefox | Page Request | 250 | 2 | 2 | 0 | 6.68 |
Firefox | Rendering | 250 | 2820 | 2788 | -32 | -1.13 | faster
```
2019-09-22 20:16:38 +09:00
|
|
|
get(key1, key2, key3) {
|
|
|
|
let value = this._map[key1];
|
Slightly simplify the lookup of data in `Dict.{get, getAsync, has}`
Note that `Dict.set` will only be called with values returned through `Parser.getObj`, and thus indirectly via `Lexer.getObj`. Since neither of those methods will ever return `undefined`, we can simply assert that that's the case when inserting data into the `Dict` and thus get rid of `in` checks when doing the data lookups.
In this case, since `Dict.set` is fairly hot, the patch utilizes an *inline check* and when necessary a direct call to `unreachable` to not affect performance of `gulp server/test` too much (rather than always just calling `assert`).
For very large and complex PDF files this will help performance *slightly*, since `Dict.{get, getAsync, has}` is called *a lot* during parsing in the worker.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, with the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
which gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2838 | 2820 | -18 | -0.65 | faster
Firefox | Page Request | 250 | 1 | 2 | 0 | 11.92 | slower
Firefox | Rendering | 250 | 2837 | 2818 | -19 | -0.65 | faster
```
2020-01-31 19:39:48 +09:00
|
|
|
if (value === undefined && key2 !== undefined) {
|
Reduce the number of function calls in the `Dict` class
The following changes were made:
- Remove unnecessary `typeof` checks in the `get`/`getAsync` methods.
- Reduce unnecessary code duplication in the `get`/`getAsync` methods.
- Inline the `Ref` checks in the `get`/`getAsync`/`getArray` methods, since it helps avoid many unnecessary functions calls. I.e. this way it's possible to directly call `XRef.{fetch, fetchAsync)` only when necessary, rather than always having to call `XRef.{fetchIfRef, fetchIfRefAsync)`.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, using the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
This gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2821 | 2790 | -32 | -1.12 | faster
Firefox | Page Request | 250 | 2 | 2 | 0 | 6.68 |
Firefox | Rendering | 250 | 2820 | 2788 | -32 | -1.13 | faster
```
2019-09-22 20:16:38 +09:00
|
|
|
value = this._map[key2];
|
Slightly simplify the lookup of data in `Dict.{get, getAsync, has}`
Note that `Dict.set` will only be called with values returned through `Parser.getObj`, and thus indirectly via `Lexer.getObj`. Since neither of those methods will ever return `undefined`, we can simply assert that that's the case when inserting data into the `Dict` and thus get rid of `in` checks when doing the data lookups.
In this case, since `Dict.set` is fairly hot, the patch utilizes an *inline check* and when necessary a direct call to `unreachable` to not affect performance of `gulp server/test` too much (rather than always just calling `assert`).
For very large and complex PDF files this will help performance *slightly*, since `Dict.{get, getAsync, has}` is called *a lot* during parsing in the worker.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, with the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
which gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2838 | 2820 | -18 | -0.65 | faster
Firefox | Page Request | 250 | 1 | 2 | 0 | 11.92 | slower
Firefox | Rendering | 250 | 2837 | 2818 | -19 | -0.65 | faster
```
2020-01-31 19:39:48 +09:00
|
|
|
if (value === undefined && key3 !== undefined) {
|
Reduce the number of function calls in the `Dict` class
The following changes were made:
- Remove unnecessary `typeof` checks in the `get`/`getAsync` methods.
- Reduce unnecessary code duplication in the `get`/`getAsync` methods.
- Inline the `Ref` checks in the `get`/`getAsync`/`getArray` methods, since it helps avoid many unnecessary functions calls. I.e. this way it's possible to directly call `XRef.{fetch, fetchAsync)` only when necessary, rather than always having to call `XRef.{fetchIfRef, fetchIfRefAsync)`.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, using the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
This gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2821 | 2790 | -32 | -1.12 | faster
Firefox | Page Request | 250 | 2 | 2 | 0 | 6.68 |
Firefox | Rendering | 250 | 2820 | 2788 | -32 | -1.13 | faster
```
2019-09-22 20:16:38 +09:00
|
|
|
value = this._map[key3];
|
|
|
|
}
|
2015-11-22 01:32:47 +09:00
|
|
|
}
|
Reduce the number of function calls in the `Dict` class
The following changes were made:
- Remove unnecessary `typeof` checks in the `get`/`getAsync` methods.
- Reduce unnecessary code duplication in the `get`/`getAsync` methods.
- Inline the `Ref` checks in the `get`/`getAsync`/`getArray` methods, since it helps avoid many unnecessary functions calls. I.e. this way it's possible to directly call `XRef.{fetch, fetchAsync)` only when necessary, rather than always having to call `XRef.{fetchIfRef, fetchIfRefAsync)`.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, using the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
This gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2821 | 2790 | -32 | -1.12 | faster
Firefox | Page Request | 250 | 2 | 2 | 0 | 6.68 |
Firefox | Rendering | 250 | 2820 | 2788 | -32 | -1.13 | faster
```
2019-09-22 20:16:38 +09:00
|
|
|
if (value instanceof Ref && this.xref) {
|
|
|
|
return this.xref.fetch(value, this.suppressEncryption);
|
2015-11-22 01:32:47 +09:00
|
|
|
}
|
Reduce the number of function calls in the `Dict` class
The following changes were made:
- Remove unnecessary `typeof` checks in the `get`/`getAsync` methods.
- Reduce unnecessary code duplication in the `get`/`getAsync` methods.
- Inline the `Ref` checks in the `get`/`getAsync`/`getArray` methods, since it helps avoid many unnecessary functions calls. I.e. this way it's possible to directly call `XRef.{fetch, fetchAsync)` only when necessary, rather than always having to call `XRef.{fetchIfRef, fetchIfRefAsync)`.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, using the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
This gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2821 | 2790 | -32 | -1.12 | faster
Firefox | Page Request | 250 | 2 | 2 | 0 | 6.68 |
Firefox | Rendering | 250 | 2820 | 2788 | -32 | -1.13 | faster
```
2019-09-22 20:16:38 +09:00
|
|
|
return value;
|
2015-11-22 01:32:47 +09:00
|
|
|
},
|
|
|
|
|
|
|
|
// Same as get(), but returns a promise and uses fetchIfRefAsync().
|
Reduce the number of function calls in the `Dict` class
The following changes were made:
- Remove unnecessary `typeof` checks in the `get`/`getAsync` methods.
- Reduce unnecessary code duplication in the `get`/`getAsync` methods.
- Inline the `Ref` checks in the `get`/`getAsync`/`getArray` methods, since it helps avoid many unnecessary functions calls. I.e. this way it's possible to directly call `XRef.{fetch, fetchAsync)` only when necessary, rather than always having to call `XRef.{fetchIfRef, fetchIfRefAsync)`.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, using the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
This gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2821 | 2790 | -32 | -1.12 | faster
Firefox | Page Request | 250 | 2 | 2 | 0 | 6.68 |
Firefox | Rendering | 250 | 2820 | 2788 | -32 | -1.13 | faster
```
2019-09-22 20:16:38 +09:00
|
|
|
async getAsync(key1, key2, key3) {
|
|
|
|
let value = this._map[key1];
|
Slightly simplify the lookup of data in `Dict.{get, getAsync, has}`
Note that `Dict.set` will only be called with values returned through `Parser.getObj`, and thus indirectly via `Lexer.getObj`. Since neither of those methods will ever return `undefined`, we can simply assert that that's the case when inserting data into the `Dict` and thus get rid of `in` checks when doing the data lookups.
In this case, since `Dict.set` is fairly hot, the patch utilizes an *inline check* and when necessary a direct call to `unreachable` to not affect performance of `gulp server/test` too much (rather than always just calling `assert`).
For very large and complex PDF files this will help performance *slightly*, since `Dict.{get, getAsync, has}` is called *a lot* during parsing in the worker.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, with the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
which gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2838 | 2820 | -18 | -0.65 | faster
Firefox | Page Request | 250 | 1 | 2 | 0 | 11.92 | slower
Firefox | Rendering | 250 | 2837 | 2818 | -19 | -0.65 | faster
```
2020-01-31 19:39:48 +09:00
|
|
|
if (value === undefined && key2 !== undefined) {
|
Reduce the number of function calls in the `Dict` class
The following changes were made:
- Remove unnecessary `typeof` checks in the `get`/`getAsync` methods.
- Reduce unnecessary code duplication in the `get`/`getAsync` methods.
- Inline the `Ref` checks in the `get`/`getAsync`/`getArray` methods, since it helps avoid many unnecessary functions calls. I.e. this way it's possible to directly call `XRef.{fetch, fetchAsync)` only when necessary, rather than always having to call `XRef.{fetchIfRef, fetchIfRefAsync)`.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, using the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
This gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2821 | 2790 | -32 | -1.12 | faster
Firefox | Page Request | 250 | 2 | 2 | 0 | 6.68 |
Firefox | Rendering | 250 | 2820 | 2788 | -32 | -1.13 | faster
```
2019-09-22 20:16:38 +09:00
|
|
|
value = this._map[key2];
|
Slightly simplify the lookup of data in `Dict.{get, getAsync, has}`
Note that `Dict.set` will only be called with values returned through `Parser.getObj`, and thus indirectly via `Lexer.getObj`. Since neither of those methods will ever return `undefined`, we can simply assert that that's the case when inserting data into the `Dict` and thus get rid of `in` checks when doing the data lookups.
In this case, since `Dict.set` is fairly hot, the patch utilizes an *inline check* and when necessary a direct call to `unreachable` to not affect performance of `gulp server/test` too much (rather than always just calling `assert`).
For very large and complex PDF files this will help performance *slightly*, since `Dict.{get, getAsync, has}` is called *a lot* during parsing in the worker.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, with the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
which gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2838 | 2820 | -18 | -0.65 | faster
Firefox | Page Request | 250 | 1 | 2 | 0 | 11.92 | slower
Firefox | Rendering | 250 | 2837 | 2818 | -19 | -0.65 | faster
```
2020-01-31 19:39:48 +09:00
|
|
|
if (value === undefined && key3 !== undefined) {
|
Reduce the number of function calls in the `Dict` class
The following changes were made:
- Remove unnecessary `typeof` checks in the `get`/`getAsync` methods.
- Reduce unnecessary code duplication in the `get`/`getAsync` methods.
- Inline the `Ref` checks in the `get`/`getAsync`/`getArray` methods, since it helps avoid many unnecessary functions calls. I.e. this way it's possible to directly call `XRef.{fetch, fetchAsync)` only when necessary, rather than always having to call `XRef.{fetchIfRef, fetchIfRefAsync)`.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, using the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
This gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2821 | 2790 | -32 | -1.12 | faster
Firefox | Page Request | 250 | 2 | 2 | 0 | 6.68 |
Firefox | Rendering | 250 | 2820 | 2788 | -32 | -1.13 | faster
```
2019-09-22 20:16:38 +09:00
|
|
|
value = this._map[key3];
|
2015-11-22 01:32:47 +09:00
|
|
|
}
|
|
|
|
}
|
Reduce the number of function calls in the `Dict` class
The following changes were made:
- Remove unnecessary `typeof` checks in the `get`/`getAsync` methods.
- Reduce unnecessary code duplication in the `get`/`getAsync` methods.
- Inline the `Ref` checks in the `get`/`getAsync`/`getArray` methods, since it helps avoid many unnecessary functions calls. I.e. this way it's possible to directly call `XRef.{fetch, fetchAsync)` only when necessary, rather than always having to call `XRef.{fetchIfRef, fetchIfRefAsync)`.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, using the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
This gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2821 | 2790 | -32 | -1.12 | faster
Firefox | Page Request | 250 | 2 | 2 | 0 | 6.68 |
Firefox | Rendering | 250 | 2820 | 2788 | -32 | -1.13 | faster
```
2019-09-22 20:16:38 +09:00
|
|
|
if (value instanceof Ref && this.xref) {
|
|
|
|
return this.xref.fetchAsync(value, this.suppressEncryption);
|
2015-11-22 01:32:47 +09:00
|
|
|
}
|
Reduce the number of function calls in the `Dict` class
The following changes were made:
- Remove unnecessary `typeof` checks in the `get`/`getAsync` methods.
- Reduce unnecessary code duplication in the `get`/`getAsync` methods.
- Inline the `Ref` checks in the `get`/`getAsync`/`getArray` methods, since it helps avoid many unnecessary functions calls. I.e. this way it's possible to directly call `XRef.{fetch, fetchAsync)` only when necessary, rather than always having to call `XRef.{fetchIfRef, fetchIfRefAsync)`.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, using the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
This gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2821 | 2790 | -32 | -1.12 | faster
Firefox | Page Request | 250 | 2 | 2 | 0 | 6.68 |
Firefox | Rendering | 250 | 2820 | 2788 | -32 | -1.13 | faster
```
2019-09-22 20:16:38 +09:00
|
|
|
return value;
|
2015-11-22 01:32:47 +09:00
|
|
|
},
|
|
|
|
|
|
|
|
// Same as get(), but dereferences all elements if the result is an Array.
|
Reduce the number of function calls in the `Dict` class
The following changes were made:
- Remove unnecessary `typeof` checks in the `get`/`getAsync` methods.
- Reduce unnecessary code duplication in the `get`/`getAsync` methods.
- Inline the `Ref` checks in the `get`/`getAsync`/`getArray` methods, since it helps avoid many unnecessary functions calls. I.e. this way it's possible to directly call `XRef.{fetch, fetchAsync)` only when necessary, rather than always having to call `XRef.{fetchIfRef, fetchIfRefAsync)`.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, using the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
This gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2821 | 2790 | -32 | -1.12 | faster
Firefox | Page Request | 250 | 2 | 2 | 0 | 6.68 |
Firefox | Rendering | 250 | 2820 | 2788 | -32 | -1.13 | faster
```
2019-09-22 20:16:38 +09:00
|
|
|
getArray(key1, key2, key3) {
|
|
|
|
let value = this.get(key1, key2, key3);
|
|
|
|
if (!Array.isArray(value) || !this.xref) {
|
2015-11-22 01:32:47 +09:00
|
|
|
return value;
|
|
|
|
}
|
|
|
|
value = value.slice(); // Ensure that we don't modify the Dict data.
|
Reduce the number of function calls in the `Dict` class
The following changes were made:
- Remove unnecessary `typeof` checks in the `get`/`getAsync` methods.
- Reduce unnecessary code duplication in the `get`/`getAsync` methods.
- Inline the `Ref` checks in the `get`/`getAsync`/`getArray` methods, since it helps avoid many unnecessary functions calls. I.e. this way it's possible to directly call `XRef.{fetch, fetchAsync)` only when necessary, rather than always having to call `XRef.{fetchIfRef, fetchIfRefAsync)`.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, using the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
This gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2821 | 2790 | -32 | -1.12 | faster
Firefox | Page Request | 250 | 2 | 2 | 0 | 6.68 |
Firefox | Rendering | 250 | 2820 | 2788 | -32 | -1.13 | faster
```
2019-09-22 20:16:38 +09:00
|
|
|
for (let i = 0, ii = value.length; i < ii; i++) {
|
|
|
|
if (!(value[i] instanceof Ref)) {
|
2015-11-22 01:32:47 +09:00
|
|
|
continue;
|
|
|
|
}
|
Reduce the number of function calls in the `Dict` class
The following changes were made:
- Remove unnecessary `typeof` checks in the `get`/`getAsync` methods.
- Reduce unnecessary code duplication in the `get`/`getAsync` methods.
- Inline the `Ref` checks in the `get`/`getAsync`/`getArray` methods, since it helps avoid many unnecessary functions calls. I.e. this way it's possible to directly call `XRef.{fetch, fetchAsync)` only when necessary, rather than always having to call `XRef.{fetchIfRef, fetchIfRefAsync)`.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, using the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
This gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2821 | 2790 | -32 | -1.12 | faster
Firefox | Page Request | 250 | 2 | 2 | 0 | 6.68 |
Firefox | Rendering | 250 | 2820 | 2788 | -32 | -1.13 | faster
```
2019-09-22 20:16:38 +09:00
|
|
|
value[i] = this.xref.fetch(value[i], this.suppressEncryption);
|
2015-11-22 01:32:47 +09:00
|
|
|
}
|
|
|
|
return value;
|
|
|
|
},
|
|
|
|
|
|
|
|
// no dereferencing
|
|
|
|
getRaw: function Dict_getRaw(key) {
|
2017-06-13 17:25:33 +09:00
|
|
|
return this._map[key];
|
2015-11-22 01:32:47 +09:00
|
|
|
},
|
|
|
|
|
|
|
|
getKeys: function Dict_getKeys() {
|
2017-06-13 17:25:33 +09:00
|
|
|
return Object.keys(this._map);
|
2015-11-22 01:32:47 +09:00
|
|
|
},
|
|
|
|
|
|
|
|
set: function Dict_set(key, value) {
|
Slightly simplify the lookup of data in `Dict.{get, getAsync, has}`
Note that `Dict.set` will only be called with values returned through `Parser.getObj`, and thus indirectly via `Lexer.getObj`. Since neither of those methods will ever return `undefined`, we can simply assert that that's the case when inserting data into the `Dict` and thus get rid of `in` checks when doing the data lookups.
In this case, since `Dict.set` is fairly hot, the patch utilizes an *inline check* and when necessary a direct call to `unreachable` to not affect performance of `gulp server/test` too much (rather than always just calling `assert`).
For very large and complex PDF files this will help performance *slightly*, since `Dict.{get, getAsync, has}` is called *a lot* during parsing in the worker.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, with the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
which gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2838 | 2820 | -18 | -0.65 | faster
Firefox | Page Request | 250 | 1 | 2 | 0 | 11.92 | slower
Firefox | Rendering | 250 | 2837 | 2818 | -19 | -0.65 | faster
```
2020-01-31 19:39:48 +09:00
|
|
|
if (
|
|
|
|
(typeof PDFJSDev === "undefined" ||
|
|
|
|
PDFJSDev.test("!PRODUCTION || TESTING")) &&
|
|
|
|
value === undefined
|
|
|
|
) {
|
|
|
|
unreachable('Dict.set: The "value" cannot be undefined.');
|
|
|
|
}
|
2017-06-13 17:25:33 +09:00
|
|
|
this._map[key] = value;
|
2015-11-22 01:32:47 +09:00
|
|
|
},
|
|
|
|
|
|
|
|
has: function Dict_has(key) {
|
Slightly simplify the lookup of data in `Dict.{get, getAsync, has}`
Note that `Dict.set` will only be called with values returned through `Parser.getObj`, and thus indirectly via `Lexer.getObj`. Since neither of those methods will ever return `undefined`, we can simply assert that that's the case when inserting data into the `Dict` and thus get rid of `in` checks when doing the data lookups.
In this case, since `Dict.set` is fairly hot, the patch utilizes an *inline check* and when necessary a direct call to `unreachable` to not affect performance of `gulp server/test` too much (rather than always just calling `assert`).
For very large and complex PDF files this will help performance *slightly*, since `Dict.{get, getAsync, has}` is called *a lot* during parsing in the worker.
This patch was tested using the PDF file from issue 2618, i.e. http://bugzilla-attachments.gnome.org/attachment.cgi?id=226471, with the following manifest file:
```
[
{ "id": "issue2618",
"file": "../web/pdfs/issue2618.pdf",
"md5": "",
"rounds": 250,
"type": "eq"
}
]
```
which gave the following results when comparing this patch against the `master` branch:
```
-- Grouped By browser, stat --
browser | stat | Count | Baseline(ms) | Current(ms) | +/- | % | Result(P<.05)
------- | ------------ | ----- | ------------ | ----------- | --- | ----- | -------------
Firefox | Overall | 250 | 2838 | 2820 | -18 | -0.65 | faster
Firefox | Page Request | 250 | 1 | 2 | 0 | 11.92 | slower
Firefox | Rendering | 250 | 2837 | 2818 | -19 | -0.65 | faster
```
2020-01-31 19:39:48 +09:00
|
|
|
return this._map[key] !== undefined;
|
2015-11-22 01:32:47 +09:00
|
|
|
},
|
|
|
|
|
|
|
|
forEach: function Dict_forEach(callback) {
|
2017-06-13 17:25:33 +09:00
|
|
|
for (var key in this._map) {
|
2015-11-22 01:32:47 +09:00
|
|
|
callback(key, this.get(key));
|
|
|
|
}
|
Fix inconsistent spacing and trailing commas in objects in `src/core/` files, so we can enable the `comma-dangle` and `object-curly-spacing` ESLint rules later on
*Unfortunately this patch is fairly big, even though it only covers the `src/core` folder, but splitting it even further seemed difficult.*
http://eslint.org/docs/rules/comma-dangle
http://eslint.org/docs/rules/object-curly-spacing
Given that we currently have quite inconsistent object formatting, fixing this in *one* big patch probably wouldn't be feasible (since I cannot imagine anyone wanting to review that); hence I've opted to try and do this piecewise instead.
Please note: This patch was created automatically, using the ESLint --fix command line option. In a couple of places this caused lines to become too long, and I've fixed those manually; please refer to the interdiff below for the only hand-edits in this patch.
```diff
diff --git a/src/core/evaluator.js b/src/core/evaluator.js
index abab9027..dcd3594b 100644
--- a/src/core/evaluator.js
+++ b/src/core/evaluator.js
@@ -2785,7 +2785,8 @@ var EvaluatorPreprocessor = (function EvaluatorPreprocessorClosure() {
t['Tz'] = { id: OPS.setHScale, numArgs: 1, variableArgs: false, };
t['TL'] = { id: OPS.setLeading, numArgs: 1, variableArgs: false, };
t['Tf'] = { id: OPS.setFont, numArgs: 2, variableArgs: false, };
- t['Tr'] = { id: OPS.setTextRenderingMode, numArgs: 1, variableArgs: false, };
+ t['Tr'] = { id: OPS.setTextRenderingMode, numArgs: 1,
+ variableArgs: false, };
t['Ts'] = { id: OPS.setTextRise, numArgs: 1, variableArgs: false, };
t['Td'] = { id: OPS.moveText, numArgs: 2, variableArgs: false, };
t['TD'] = { id: OPS.setLeadingMoveText, numArgs: 2, variableArgs: false, };
diff --git a/src/core/jbig2.js b/src/core/jbig2.js
index 5a17d482..71671541 100644
--- a/src/core/jbig2.js
+++ b/src/core/jbig2.js
@@ -123,19 +123,22 @@ var Jbig2Image = (function Jbig2ImageClosure() {
{ x: -1, y: -1, }, { x: 0, y: -1, }, { x: 1, y: -1, }, { x: -2, y: 0, },
{ x: -1, y: 0, }],
[{ x: -3, y: -1, }, { x: -2, y: -1, }, { x: -1, y: -1, }, { x: 0, y: -1, },
- { x: 1, y: -1, }, { x: -4, y: 0, }, { x: -3, y: 0, }, { x: -2, y: 0, }, { x: -1, y: 0, }]
+ { x: 1, y: -1, }, { x: -4, y: 0, }, { x: -3, y: 0, }, { x: -2, y: 0, },
+ { x: -1, y: 0, }]
];
var RefinementTemplates = [
{
coding: [{ x: 0, y: -1, }, { x: 1, y: -1, }, { x: -1, y: 0, }],
- reference: [{ x: 0, y: -1, }, { x: 1, y: -1, }, { x: -1, y: 0, }, { x: 0, y: 0, },
- { x: 1, y: 0, }, { x: -1, y: 1, }, { x: 0, y: 1, }, { x: 1, y: 1, }],
+ reference: [{ x: 0, y: -1, }, { x: 1, y: -1, }, { x: -1, y: 0, },
+ { x: 0, y: 0, }, { x: 1, y: 0, }, { x: -1, y: 1, },
+ { x: 0, y: 1, }, { x: 1, y: 1, }],
},
{
- coding: [{ x: -1, y: -1, }, { x: 0, y: -1, }, { x: 1, y: -1, }, { x: -1, y: 0, }],
- reference: [{ x: 0, y: -1, }, { x: -1, y: 0, }, { x: 0, y: 0, }, { x: 1, y: 0, },
- { x: 0, y: 1, }, { x: 1, y: 1, }],
+ coding: [{ x: -1, y: -1, }, { x: 0, y: -1, }, { x: 1, y: -1, },
+ { x: -1, y: 0, }],
+ reference: [{ x: 0, y: -1, }, { x: -1, y: 0, }, { x: 0, y: 0, },
+ { x: 1, y: 0, }, { x: 0, y: 1, }, { x: 1, y: 1, }],
}
];
```
2017-06-02 18:16:24 +09:00
|
|
|
},
|
2015-11-22 01:32:47 +09:00
|
|
|
};
|
|
|
|
|
|
|
|
Dict.empty = new Dict(null);
|
|
|
|
|
2020-04-14 19:28:14 +09:00
|
|
|
Dict.merge = function (xref, dictArray) {
|
2020-01-24 17:48:21 +09:00
|
|
|
const mergedDict = new Dict(xref);
|
2015-11-22 01:32:47 +09:00
|
|
|
|
2017-06-13 17:25:33 +09:00
|
|
|
for (let i = 0, ii = dictArray.length; i < ii; i++) {
|
2020-01-24 17:48:21 +09:00
|
|
|
const dict = dictArray[i];
|
2015-11-22 01:32:47 +09:00
|
|
|
if (!isDict(dict)) {
|
|
|
|
continue;
|
|
|
|
}
|
2020-01-24 17:48:21 +09:00
|
|
|
for (const keyName in dict._map) {
|
2017-06-13 17:25:33 +09:00
|
|
|
if (mergedDict._map[keyName] !== undefined) {
|
2015-11-22 01:32:47 +09:00
|
|
|
continue;
|
|
|
|
}
|
2017-06-13 17:25:33 +09:00
|
|
|
mergedDict._map[keyName] = dict._map[keyName];
|
2015-11-22 01:32:47 +09:00
|
|
|
}
|
|
|
|
}
|
|
|
|
return mergedDict;
|
|
|
|
};
|
|
|
|
|
|
|
|
return Dict;
|
|
|
|
})();
|
|
|
|
|
|
|
|
var Ref = (function RefClosure() {
|
2019-05-26 21:20:31 +09:00
|
|
|
let refCache = Object.create(null);
|
2019-05-26 00:40:14 +09:00
|
|
|
|
2020-03-25 18:15:50 +09:00
|
|
|
// eslint-disable-next-line no-shadow
|
2015-11-22 01:32:47 +09:00
|
|
|
function Ref(num, gen) {
|
|
|
|
this.num = num;
|
|
|
|
this.gen = gen;
|
|
|
|
}
|
|
|
|
|
|
|
|
Ref.prototype = {
|
|
|
|
toString: function Ref_toString() {
|
|
|
|
// This function is hot, so we make the string as compact as possible.
|
|
|
|
// |this.gen| is almost always zero, so we treat that case specially.
|
2019-05-26 00:40:14 +09:00
|
|
|
if (this.gen === 0) {
|
|
|
|
return `${this.num}R`;
|
2015-11-22 01:32:47 +09:00
|
|
|
}
|
2019-05-26 00:40:14 +09:00
|
|
|
return `${this.num}R${this.gen}`;
|
Fix inconsistent spacing and trailing commas in objects in `src/core/` files, so we can enable the `comma-dangle` and `object-curly-spacing` ESLint rules later on
*Unfortunately this patch is fairly big, even though it only covers the `src/core` folder, but splitting it even further seemed difficult.*
http://eslint.org/docs/rules/comma-dangle
http://eslint.org/docs/rules/object-curly-spacing
Given that we currently have quite inconsistent object formatting, fixing this in *one* big patch probably wouldn't be feasible (since I cannot imagine anyone wanting to review that); hence I've opted to try and do this piecewise instead.
Please note: This patch was created automatically, using the ESLint --fix command line option. In a couple of places this caused lines to become too long, and I've fixed those manually; please refer to the interdiff below for the only hand-edits in this patch.
```diff
diff --git a/src/core/evaluator.js b/src/core/evaluator.js
index abab9027..dcd3594b 100644
--- a/src/core/evaluator.js
+++ b/src/core/evaluator.js
@@ -2785,7 +2785,8 @@ var EvaluatorPreprocessor = (function EvaluatorPreprocessorClosure() {
t['Tz'] = { id: OPS.setHScale, numArgs: 1, variableArgs: false, };
t['TL'] = { id: OPS.setLeading, numArgs: 1, variableArgs: false, };
t['Tf'] = { id: OPS.setFont, numArgs: 2, variableArgs: false, };
- t['Tr'] = { id: OPS.setTextRenderingMode, numArgs: 1, variableArgs: false, };
+ t['Tr'] = { id: OPS.setTextRenderingMode, numArgs: 1,
+ variableArgs: false, };
t['Ts'] = { id: OPS.setTextRise, numArgs: 1, variableArgs: false, };
t['Td'] = { id: OPS.moveText, numArgs: 2, variableArgs: false, };
t['TD'] = { id: OPS.setLeadingMoveText, numArgs: 2, variableArgs: false, };
diff --git a/src/core/jbig2.js b/src/core/jbig2.js
index 5a17d482..71671541 100644
--- a/src/core/jbig2.js
+++ b/src/core/jbig2.js
@@ -123,19 +123,22 @@ var Jbig2Image = (function Jbig2ImageClosure() {
{ x: -1, y: -1, }, { x: 0, y: -1, }, { x: 1, y: -1, }, { x: -2, y: 0, },
{ x: -1, y: 0, }],
[{ x: -3, y: -1, }, { x: -2, y: -1, }, { x: -1, y: -1, }, { x: 0, y: -1, },
- { x: 1, y: -1, }, { x: -4, y: 0, }, { x: -3, y: 0, }, { x: -2, y: 0, }, { x: -1, y: 0, }]
+ { x: 1, y: -1, }, { x: -4, y: 0, }, { x: -3, y: 0, }, { x: -2, y: 0, },
+ { x: -1, y: 0, }]
];
var RefinementTemplates = [
{
coding: [{ x: 0, y: -1, }, { x: 1, y: -1, }, { x: -1, y: 0, }],
- reference: [{ x: 0, y: -1, }, { x: 1, y: -1, }, { x: -1, y: 0, }, { x: 0, y: 0, },
- { x: 1, y: 0, }, { x: -1, y: 1, }, { x: 0, y: 1, }, { x: 1, y: 1, }],
+ reference: [{ x: 0, y: -1, }, { x: 1, y: -1, }, { x: -1, y: 0, },
+ { x: 0, y: 0, }, { x: 1, y: 0, }, { x: -1, y: 1, },
+ { x: 0, y: 1, }, { x: 1, y: 1, }],
},
{
- coding: [{ x: -1, y: -1, }, { x: 0, y: -1, }, { x: 1, y: -1, }, { x: -1, y: 0, }],
- reference: [{ x: 0, y: -1, }, { x: -1, y: 0, }, { x: 0, y: 0, }, { x: 1, y: 0, },
- { x: 0, y: 1, }, { x: 1, y: 1, }],
+ coding: [{ x: -1, y: -1, }, { x: 0, y: -1, }, { x: 1, y: -1, },
+ { x: -1, y: 0, }],
+ reference: [{ x: 0, y: -1, }, { x: -1, y: 0, }, { x: 0, y: 0, },
+ { x: 1, y: 0, }, { x: 0, y: 1, }, { x: 1, y: 1, }],
}
];
```
2017-06-02 18:16:24 +09:00
|
|
|
},
|
2015-11-22 01:32:47 +09:00
|
|
|
};
|
|
|
|
|
2020-04-14 19:28:14 +09:00
|
|
|
Ref.get = function (num, gen) {
|
Enable auto-formatting of the entire code-base using Prettier (issue 11444)
Note that Prettier, purposely, has only limited [configuration options](https://prettier.io/docs/en/options.html). The configuration file is based on [the one in `mozilla central`](https://searchfox.org/mozilla-central/source/.prettierrc) with just a few additions (to avoid future breakage if the defaults ever changes).
Prettier is being used for a couple of reasons:
- To be consistent with `mozilla-central`, where Prettier is already in use across the tree.
- To ensure a *consistent* coding style everywhere, which is automatically enforced during linting (since Prettier is used as an ESLint plugin). This thus ends "all" formatting disussions once and for all, removing the need for review comments on most stylistic matters.
Many ESLint options are now redundant, and I've tried my best to remove all the now unnecessary options (but I may have missed some).
Note also that since Prettier considers the `printWidth` option as a guide, rather than a hard rule, this patch resorts to a small hack in the ESLint config to ensure that *comments* won't become too long.
*Please note:* This patch is generated automatically, by appending the `--fix` argument to the ESLint call used in the `gulp lint` task. It will thus require some additional clean-up, which will be done in a *separate* commit.
(On a more personal note, I'll readily admit that some of the changes Prettier makes are *extremely* ugly. However, in the name of consistency we'll probably have to live with that.)
2019-12-25 23:59:37 +09:00
|
|
|
const key = gen === 0 ? `${num}R` : `${num}R${gen}`;
|
2019-05-26 00:40:14 +09:00
|
|
|
const refValue = refCache[key];
|
2020-02-23 04:53:47 +09:00
|
|
|
// eslint-disable-next-line no-restricted-syntax
|
Enable auto-formatting of the entire code-base using Prettier (issue 11444)
Note that Prettier, purposely, has only limited [configuration options](https://prettier.io/docs/en/options.html). The configuration file is based on [the one in `mozilla central`](https://searchfox.org/mozilla-central/source/.prettierrc) with just a few additions (to avoid future breakage if the defaults ever changes).
Prettier is being used for a couple of reasons:
- To be consistent with `mozilla-central`, where Prettier is already in use across the tree.
- To ensure a *consistent* coding style everywhere, which is automatically enforced during linting (since Prettier is used as an ESLint plugin). This thus ends "all" formatting disussions once and for all, removing the need for review comments on most stylistic matters.
Many ESLint options are now redundant, and I've tried my best to remove all the now unnecessary options (but I may have missed some).
Note also that since Prettier considers the `printWidth` option as a guide, rather than a hard rule, this patch resorts to a small hack in the ESLint config to ensure that *comments* won't become too long.
*Please note:* This patch is generated automatically, by appending the `--fix` argument to the ESLint call used in the `gulp lint` task. It will thus require some additional clean-up, which will be done in a *separate* commit.
(On a more personal note, I'll readily admit that some of the changes Prettier makes are *extremely* ugly. However, in the name of consistency we'll probably have to live with that.)
2019-12-25 23:59:37 +09:00
|
|
|
return refValue ? refValue : (refCache[key] = new Ref(num, gen));
|
2019-05-26 00:40:14 +09:00
|
|
|
};
|
|
|
|
|
2020-04-14 19:28:14 +09:00
|
|
|
Ref._clearCache = function () {
|
2019-05-26 21:20:31 +09:00
|
|
|
refCache = Object.create(null);
|
|
|
|
};
|
|
|
|
|
2015-11-22 01:32:47 +09:00
|
|
|
return Ref;
|
|
|
|
})();
|
|
|
|
|
|
|
|
// The reference is identified by number and generation.
|
|
|
|
// This structure stores only one instance of the reference.
|
2020-06-08 01:51:05 +09:00
|
|
|
class RefSet {
|
|
|
|
constructor() {
|
|
|
|
this._set = new Set();
|
2015-11-22 01:32:47 +09:00
|
|
|
}
|
|
|
|
|
2020-06-08 01:51:05 +09:00
|
|
|
has(ref) {
|
|
|
|
return this._set.has(ref.toString());
|
|
|
|
}
|
2015-11-22 01:32:47 +09:00
|
|
|
|
2020-06-08 01:51:05 +09:00
|
|
|
put(ref) {
|
|
|
|
this._set.add(ref.toString());
|
|
|
|
}
|
2015-11-22 01:32:47 +09:00
|
|
|
|
2020-06-08 01:51:05 +09:00
|
|
|
remove(ref) {
|
|
|
|
this._set.delete(ref.toString());
|
|
|
|
}
|
|
|
|
}
|
2015-11-22 01:32:47 +09:00
|
|
|
|
|
|
|
var RefSetCache = (function RefSetCacheClosure() {
|
2020-03-25 18:15:50 +09:00
|
|
|
// eslint-disable-next-line no-shadow
|
2015-11-22 01:32:47 +09:00
|
|
|
function RefSetCache() {
|
|
|
|
this.dict = Object.create(null);
|
|
|
|
}
|
|
|
|
|
|
|
|
RefSetCache.prototype = {
|
Attempt to cache repeated images at the document, rather than the page, level (issue 11878)
Currently image resources, as opposed to e.g. font resources, are handled exclusively on a page-specific basis. Generally speaking this makes sense, since pages are separate from each other, however there's PDF documents where many (or even all) pages actually references exactly the same image resources (through the XRef table). Hence, in some cases, we're decoding the *same* images over and over for every page which is obviously slow and wasting both CPU and memory resources better used elsewhere.[1]
Obviously we cannot simply treat all image resources as-if they're used throughout the entire PDF document, since that would end up increasing memory usage too much.[2]
However, by introducing a `GlobalImageCache` in the worker we can track image resources that appear on more than one page. Hence we can switch image resources from being page-specific to being document-specific, once the image resource has been seen on more than a certain number of pages.
In many cases, such as e.g. the referenced issue, this patch will thus lead to reduced memory usage for image resources. Scrolling through all pages of the document, there's now only a few main-thread copies of the same image data, as opposed to one for each rendered page (i.e. there could theoretically be *twenty* copies of the image data).
While this obviously benefit both CPU and memory usage in this case, for *very* large image data this patch *may* possibly increase persistent main-thread memory usage a tiny bit. Thus to avoid negatively affecting memory usage too much in general, particularly on the main-thread, the `GlobalImageCache` will *only* cache a certain number of image resources at the document level and simply fallback to the default behaviour.
Unfortunately the asynchronous nature of the code, with ranged/streamed loading of data, actually makes all of this much more complicated than if all data could be assumed to be immediately available.[3]
*Please note:* The patch will lead to *small* movement in some existing test-cases, since we're now using the built-in PDF.js JPEG decoder more. This was done in order to simplify the overall implementation, especially on the main-thread, by limiting it to only the `OPS.paintImageXObject` operator.
---
[1] There's e.g. PDF documents that use the same image as background on all pages.
[2] Given that data stored in the `commonObjs`, on the main-thread, are only cleared manually through `PDFDocumentProxy.cleanup`. This as opposed to data stored in the `objs` of each page, which is automatically removed when the page is cleaned-up e.g. by being evicted from the cache in the default viewer.
[3] If the latter case were true, we could simply check for repeat images *before* parsing started and thus avoid handling *any* duplicate image resources.
2020-05-18 21:17:56 +09:00
|
|
|
get size() {
|
|
|
|
return Object.keys(this.dict).length;
|
|
|
|
},
|
|
|
|
|
2015-11-22 01:32:47 +09:00
|
|
|
get: function RefSetCache_get(ref) {
|
|
|
|
return this.dict[ref.toString()];
|
|
|
|
},
|
|
|
|
|
|
|
|
has: function RefSetCache_has(ref) {
|
|
|
|
return ref.toString() in this.dict;
|
|
|
|
},
|
|
|
|
|
|
|
|
put: function RefSetCache_put(ref, obj) {
|
|
|
|
this.dict[ref.toString()] = obj;
|
|
|
|
},
|
|
|
|
|
|
|
|
putAlias: function RefSetCache_putAlias(ref, aliasRef) {
|
|
|
|
this.dict[ref.toString()] = this.get(aliasRef);
|
|
|
|
},
|
|
|
|
|
2020-02-21 22:23:05 +09:00
|
|
|
forEach: function RefSetCache_forEach(callback) {
|
|
|
|
for (const i in this.dict) {
|
|
|
|
callback(this.dict[i]);
|
2015-11-22 01:32:47 +09:00
|
|
|
}
|
|
|
|
},
|
|
|
|
|
|
|
|
clear: function RefSetCache_clear() {
|
|
|
|
this.dict = Object.create(null);
|
Fix inconsistent spacing and trailing commas in objects in `src/core/` files, so we can enable the `comma-dangle` and `object-curly-spacing` ESLint rules later on
*Unfortunately this patch is fairly big, even though it only covers the `src/core` folder, but splitting it even further seemed difficult.*
http://eslint.org/docs/rules/comma-dangle
http://eslint.org/docs/rules/object-curly-spacing
Given that we currently have quite inconsistent object formatting, fixing this in *one* big patch probably wouldn't be feasible (since I cannot imagine anyone wanting to review that); hence I've opted to try and do this piecewise instead.
Please note: This patch was created automatically, using the ESLint --fix command line option. In a couple of places this caused lines to become too long, and I've fixed those manually; please refer to the interdiff below for the only hand-edits in this patch.
```diff
diff --git a/src/core/evaluator.js b/src/core/evaluator.js
index abab9027..dcd3594b 100644
--- a/src/core/evaluator.js
+++ b/src/core/evaluator.js
@@ -2785,7 +2785,8 @@ var EvaluatorPreprocessor = (function EvaluatorPreprocessorClosure() {
t['Tz'] = { id: OPS.setHScale, numArgs: 1, variableArgs: false, };
t['TL'] = { id: OPS.setLeading, numArgs: 1, variableArgs: false, };
t['Tf'] = { id: OPS.setFont, numArgs: 2, variableArgs: false, };
- t['Tr'] = { id: OPS.setTextRenderingMode, numArgs: 1, variableArgs: false, };
+ t['Tr'] = { id: OPS.setTextRenderingMode, numArgs: 1,
+ variableArgs: false, };
t['Ts'] = { id: OPS.setTextRise, numArgs: 1, variableArgs: false, };
t['Td'] = { id: OPS.moveText, numArgs: 2, variableArgs: false, };
t['TD'] = { id: OPS.setLeadingMoveText, numArgs: 2, variableArgs: false, };
diff --git a/src/core/jbig2.js b/src/core/jbig2.js
index 5a17d482..71671541 100644
--- a/src/core/jbig2.js
+++ b/src/core/jbig2.js
@@ -123,19 +123,22 @@ var Jbig2Image = (function Jbig2ImageClosure() {
{ x: -1, y: -1, }, { x: 0, y: -1, }, { x: 1, y: -1, }, { x: -2, y: 0, },
{ x: -1, y: 0, }],
[{ x: -3, y: -1, }, { x: -2, y: -1, }, { x: -1, y: -1, }, { x: 0, y: -1, },
- { x: 1, y: -1, }, { x: -4, y: 0, }, { x: -3, y: 0, }, { x: -2, y: 0, }, { x: -1, y: 0, }]
+ { x: 1, y: -1, }, { x: -4, y: 0, }, { x: -3, y: 0, }, { x: -2, y: 0, },
+ { x: -1, y: 0, }]
];
var RefinementTemplates = [
{
coding: [{ x: 0, y: -1, }, { x: 1, y: -1, }, { x: -1, y: 0, }],
- reference: [{ x: 0, y: -1, }, { x: 1, y: -1, }, { x: -1, y: 0, }, { x: 0, y: 0, },
- { x: 1, y: 0, }, { x: -1, y: 1, }, { x: 0, y: 1, }, { x: 1, y: 1, }],
+ reference: [{ x: 0, y: -1, }, { x: 1, y: -1, }, { x: -1, y: 0, },
+ { x: 0, y: 0, }, { x: 1, y: 0, }, { x: -1, y: 1, },
+ { x: 0, y: 1, }, { x: 1, y: 1, }],
},
{
- coding: [{ x: -1, y: -1, }, { x: 0, y: -1, }, { x: 1, y: -1, }, { x: -1, y: 0, }],
- reference: [{ x: 0, y: -1, }, { x: -1, y: 0, }, { x: 0, y: 0, }, { x: 1, y: 0, },
- { x: 0, y: 1, }, { x: 1, y: 1, }],
+ coding: [{ x: -1, y: -1, }, { x: 0, y: -1, }, { x: 1, y: -1, },
+ { x: -1, y: 0, }],
+ reference: [{ x: 0, y: -1, }, { x: -1, y: 0, }, { x: 0, y: 0, },
+ { x: 1, y: 0, }, { x: 0, y: 1, }, { x: 1, y: 1, }],
}
];
```
2017-06-02 18:16:24 +09:00
|
|
|
},
|
2015-11-22 01:32:47 +09:00
|
|
|
};
|
|
|
|
|
|
|
|
return RefSetCache;
|
|
|
|
})();
|
|
|
|
|
2017-01-27 21:34:37 +09:00
|
|
|
function isEOF(v) {
|
Enable auto-formatting of the entire code-base using Prettier (issue 11444)
Note that Prettier, purposely, has only limited [configuration options](https://prettier.io/docs/en/options.html). The configuration file is based on [the one in `mozilla central`](https://searchfox.org/mozilla-central/source/.prettierrc) with just a few additions (to avoid future breakage if the defaults ever changes).
Prettier is being used for a couple of reasons:
- To be consistent with `mozilla-central`, where Prettier is already in use across the tree.
- To ensure a *consistent* coding style everywhere, which is automatically enforced during linting (since Prettier is used as an ESLint plugin). This thus ends "all" formatting disussions once and for all, removing the need for review comments on most stylistic matters.
Many ESLint options are now redundant, and I've tried my best to remove all the now unnecessary options (but I may have missed some).
Note also that since Prettier considers the `printWidth` option as a guide, rather than a hard rule, this patch resorts to a small hack in the ESLint config to ensure that *comments* won't become too long.
*Please note:* This patch is generated automatically, by appending the `--fix` argument to the ESLint call used in the `gulp lint` task. It will thus require some additional clean-up, which will be done in a *separate* commit.
(On a more personal note, I'll readily admit that some of the changes Prettier makes are *extremely* ugly. However, in the name of consistency we'll probably have to live with that.)
2019-12-25 23:59:37 +09:00
|
|
|
return v === EOF;
|
2017-01-27 21:34:37 +09:00
|
|
|
}
|
|
|
|
|
2016-08-04 21:57:31 +09:00
|
|
|
function isName(v, name) {
|
|
|
|
return v instanceof Name && (name === undefined || v.name === name);
|
2015-11-22 01:32:47 +09:00
|
|
|
}
|
|
|
|
|
|
|
|
function isCmd(v, cmd) {
|
|
|
|
return v instanceof Cmd && (cmd === undefined || v.cmd === cmd);
|
|
|
|
}
|
|
|
|
|
|
|
|
function isDict(v, type) {
|
Enable auto-formatting of the entire code-base using Prettier (issue 11444)
Note that Prettier, purposely, has only limited [configuration options](https://prettier.io/docs/en/options.html). The configuration file is based on [the one in `mozilla central`](https://searchfox.org/mozilla-central/source/.prettierrc) with just a few additions (to avoid future breakage if the defaults ever changes).
Prettier is being used for a couple of reasons:
- To be consistent with `mozilla-central`, where Prettier is already in use across the tree.
- To ensure a *consistent* coding style everywhere, which is automatically enforced during linting (since Prettier is used as an ESLint plugin). This thus ends "all" formatting disussions once and for all, removing the need for review comments on most stylistic matters.
Many ESLint options are now redundant, and I've tried my best to remove all the now unnecessary options (but I may have missed some).
Note also that since Prettier considers the `printWidth` option as a guide, rather than a hard rule, this patch resorts to a small hack in the ESLint config to ensure that *comments* won't become too long.
*Please note:* This patch is generated automatically, by appending the `--fix` argument to the ESLint call used in the `gulp lint` task. It will thus require some additional clean-up, which will be done in a *separate* commit.
(On a more personal note, I'll readily admit that some of the changes Prettier makes are *extremely* ugly. However, in the name of consistency we'll probably have to live with that.)
2019-12-25 23:59:37 +09:00
|
|
|
return (
|
|
|
|
v instanceof Dict && (type === undefined || isName(v.get("Type"), type))
|
|
|
|
);
|
2015-11-22 01:32:47 +09:00
|
|
|
}
|
|
|
|
|
|
|
|
function isRef(v) {
|
|
|
|
return v instanceof Ref;
|
|
|
|
}
|
|
|
|
|
2016-05-16 23:28:25 +09:00
|
|
|
function isRefsEqual(v1, v2) {
|
Enable auto-formatting of the entire code-base using Prettier (issue 11444)
Note that Prettier, purposely, has only limited [configuration options](https://prettier.io/docs/en/options.html). The configuration file is based on [the one in `mozilla central`](https://searchfox.org/mozilla-central/source/.prettierrc) with just a few additions (to avoid future breakage if the defaults ever changes).
Prettier is being used for a couple of reasons:
- To be consistent with `mozilla-central`, where Prettier is already in use across the tree.
- To ensure a *consistent* coding style everywhere, which is automatically enforced during linting (since Prettier is used as an ESLint plugin). This thus ends "all" formatting disussions once and for all, removing the need for review comments on most stylistic matters.
Many ESLint options are now redundant, and I've tried my best to remove all the now unnecessary options (but I may have missed some).
Note also that since Prettier considers the `printWidth` option as a guide, rather than a hard rule, this patch resorts to a small hack in the ESLint config to ensure that *comments* won't become too long.
*Please note:* This patch is generated automatically, by appending the `--fix` argument to the ESLint call used in the `gulp lint` task. It will thus require some additional clean-up, which will be done in a *separate* commit.
(On a more personal note, I'll readily admit that some of the changes Prettier makes are *extremely* ugly. However, in the name of consistency we'll probably have to live with that.)
2019-12-25 23:59:37 +09:00
|
|
|
if (
|
|
|
|
typeof PDFJSDev === "undefined" ||
|
|
|
|
PDFJSDev.test("!PRODUCTION || TESTING")
|
|
|
|
) {
|
|
|
|
assert(
|
|
|
|
v1 instanceof Ref && v2 instanceof Ref,
|
|
|
|
"isRefsEqual: Both parameters should be `Ref`s."
|
|
|
|
);
|
2019-05-26 00:40:14 +09:00
|
|
|
}
|
2016-05-16 23:28:25 +09:00
|
|
|
return v1.num === v2.num && v1.gen === v2.gen;
|
|
|
|
}
|
|
|
|
|
2015-11-22 01:32:47 +09:00
|
|
|
function isStream(v) {
|
Enable auto-formatting of the entire code-base using Prettier (issue 11444)
Note that Prettier, purposely, has only limited [configuration options](https://prettier.io/docs/en/options.html). The configuration file is based on [the one in `mozilla central`](https://searchfox.org/mozilla-central/source/.prettierrc) with just a few additions (to avoid future breakage if the defaults ever changes).
Prettier is being used for a couple of reasons:
- To be consistent with `mozilla-central`, where Prettier is already in use across the tree.
- To ensure a *consistent* coding style everywhere, which is automatically enforced during linting (since Prettier is used as an ESLint plugin). This thus ends "all" formatting disussions once and for all, removing the need for review comments on most stylistic matters.
Many ESLint options are now redundant, and I've tried my best to remove all the now unnecessary options (but I may have missed some).
Note also that since Prettier considers the `printWidth` option as a guide, rather than a hard rule, this patch resorts to a small hack in the ESLint config to ensure that *comments* won't become too long.
*Please note:* This patch is generated automatically, by appending the `--fix` argument to the ESLint call used in the `gulp lint` task. It will thus require some additional clean-up, which will be done in a *separate* commit.
(On a more personal note, I'll readily admit that some of the changes Prettier makes are *extremely* ugly. However, in the name of consistency we'll probably have to live with that.)
2019-12-25 23:59:37 +09:00
|
|
|
return typeof v === "object" && v !== null && v.getBytes !== undefined;
|
2015-11-22 01:32:47 +09:00
|
|
|
}
|
|
|
|
|
2019-05-26 21:20:31 +09:00
|
|
|
function clearPrimitiveCaches() {
|
|
|
|
Cmd._clearCache();
|
|
|
|
Name._clearCache();
|
|
|
|
Ref._clearCache();
|
|
|
|
}
|
|
|
|
|
2017-04-02 23:14:30 +09:00
|
|
|
export {
|
|
|
|
EOF,
|
2019-05-26 21:20:31 +09:00
|
|
|
clearPrimitiveCaches,
|
2017-04-02 23:14:30 +09:00
|
|
|
Cmd,
|
|
|
|
Dict,
|
|
|
|
Name,
|
|
|
|
Ref,
|
|
|
|
RefSet,
|
|
|
|
RefSetCache,
|
|
|
|
isEOF,
|
|
|
|
isCmd,
|
|
|
|
isDict,
|
|
|
|
isName,
|
|
|
|
isRef,
|
|
|
|
isRefsEqual,
|
|
|
|
isStream,
|
|
|
|
};
|