2014-06-24 00:42:43 +02:00
|
|
|
/*******************************************************************************
|
|
|
|
|
2015-12-29 17:34:41 +01:00
|
|
|
uBlock Origin - a browser extension to block requests.
|
2018-12-14 17:01:21 +01:00
|
|
|
Copyright (C) 2014-present Raymond Hill
|
2014-06-24 00:42:43 +02:00
|
|
|
|
|
|
|
This program is free software: you can redistribute it and/or modify
|
|
|
|
it under the terms of the GNU General Public License as published by
|
|
|
|
the Free Software Foundation, either version 3 of the License, or
|
|
|
|
(at your option) any later version.
|
|
|
|
|
|
|
|
This program is distributed in the hope that it will be useful,
|
|
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
|
GNU General Public License for more details.
|
|
|
|
|
|
|
|
You should have received a copy of the GNU General Public License
|
|
|
|
along with this program. If not, see {http://www.gnu.org/licenses/}.
|
|
|
|
|
|
|
|
Home: https://github.com/gorhill/uBlock
|
|
|
|
*/
|
|
|
|
|
2014-10-19 13:11:27 +02:00
|
|
|
'use strict';
|
2014-06-24 00:42:43 +02:00
|
|
|
|
|
|
|
/******************************************************************************/
|
|
|
|
|
2015-12-29 17:34:41 +01:00
|
|
|
µBlock.formatCount = function(count) {
|
2014-08-20 02:41:52 +02:00
|
|
|
if ( typeof count !== 'number' ) {
|
|
|
|
return '';
|
|
|
|
}
|
2019-09-11 14:08:30 +02:00
|
|
|
let s = count.toFixed(0);
|
2014-08-20 02:41:52 +02:00
|
|
|
if ( count >= 1000 ) {
|
|
|
|
if ( count < 10000 ) {
|
2014-12-24 14:11:22 +01:00
|
|
|
s = '>' + s.slice(0,1) + 'k';
|
2014-08-20 02:41:52 +02:00
|
|
|
} else if ( count < 100000 ) {
|
2014-12-24 14:11:22 +01:00
|
|
|
s = s.slice(0,2) + 'k';
|
2014-08-20 02:41:52 +02:00
|
|
|
} else if ( count < 1000000 ) {
|
2014-12-24 14:11:22 +01:00
|
|
|
s = s.slice(0,3) + 'k';
|
2014-08-20 02:41:52 +02:00
|
|
|
} else if ( count < 10000000 ) {
|
|
|
|
s = s.slice(0,1) + 'M';
|
|
|
|
} else {
|
|
|
|
s = s.slice(0,-6) + 'M';
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return s;
|
2014-06-24 00:42:43 +02:00
|
|
|
};
|
|
|
|
|
2014-08-20 15:24:16 +02:00
|
|
|
// https://www.youtube.com/watch?v=DyvzfyqYm_s
|
2014-08-20 02:41:52 +02:00
|
|
|
|
|
|
|
/******************************************************************************/
|
2016-08-13 22:42:58 +02:00
|
|
|
|
2016-10-13 19:25:57 +02:00
|
|
|
µBlock.dateNowToSensibleString = function() {
|
2019-09-11 14:08:30 +02:00
|
|
|
const now = new Date(Date.now() - (new Date()).getTimezoneOffset() * 60000);
|
2016-10-13 19:25:57 +02:00
|
|
|
return now.toISOString().replace(/\.\d+Z$/, '')
|
|
|
|
.replace(/:/g, '.')
|
|
|
|
.replace('T', '_');
|
|
|
|
};
|
|
|
|
|
|
|
|
/******************************************************************************/
|
|
|
|
|
2019-09-11 14:08:30 +02:00
|
|
|
µBlock.LineIterator = class {
|
|
|
|
constructor(text, offset) {
|
|
|
|
this.text = text;
|
|
|
|
this.textLen = this.text.length;
|
|
|
|
this.offset = offset || 0;
|
2017-05-12 16:35:11 +02:00
|
|
|
}
|
2019-09-11 14:08:30 +02:00
|
|
|
next(offset) {
|
|
|
|
if ( offset !== undefined ) {
|
|
|
|
this.offset += offset;
|
|
|
|
}
|
|
|
|
let lineEnd = this.text.indexOf('\n', this.offset);
|
2016-08-13 22:42:58 +02:00
|
|
|
if ( lineEnd === -1 ) {
|
2019-09-11 14:08:30 +02:00
|
|
|
lineEnd = this.text.indexOf('\r', this.offset);
|
|
|
|
if ( lineEnd === -1 ) {
|
|
|
|
lineEnd = this.textLen;
|
|
|
|
}
|
2016-08-13 22:42:58 +02:00
|
|
|
}
|
2019-09-11 14:08:30 +02:00
|
|
|
const line = this.text.slice(this.offset, lineEnd);
|
|
|
|
this.offset = lineEnd + 1;
|
|
|
|
return line;
|
|
|
|
}
|
2020-03-15 13:15:17 +01:00
|
|
|
peek(n) {
|
|
|
|
const offset = this.offset;
|
|
|
|
return this.text.slice(offset, offset + n);
|
|
|
|
}
|
2019-09-11 14:08:30 +02:00
|
|
|
charCodeAt(offset) {
|
|
|
|
return this.text.charCodeAt(this.offset + offset);
|
|
|
|
}
|
|
|
|
eot() {
|
|
|
|
return this.offset >= this.textLen;
|
2016-08-13 22:42:58 +02:00
|
|
|
}
|
2016-09-12 16:22:25 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
/******************************************************************************/
|
|
|
|
|
|
|
|
// The field iterator is less CPU-intensive than when using native
|
|
|
|
// String.split().
|
|
|
|
|
2019-09-11 14:08:30 +02:00
|
|
|
µBlock.FieldIterator = class {
|
|
|
|
constructor(sep) {
|
|
|
|
this.text = '';
|
|
|
|
this.sep = sep;
|
|
|
|
this.sepLen = sep.length;
|
|
|
|
this.offset = 0;
|
|
|
|
}
|
|
|
|
first(text) {
|
|
|
|
this.text = text;
|
|
|
|
this.offset = 0;
|
|
|
|
return this.next();
|
|
|
|
}
|
|
|
|
next() {
|
|
|
|
let end = this.text.indexOf(this.sep, this.offset);
|
|
|
|
if ( end === -1 ) {
|
|
|
|
end = this.text.length;
|
|
|
|
}
|
|
|
|
const field = this.text.slice(this.offset, end);
|
|
|
|
this.offset = end + this.sepLen;
|
|
|
|
return field;
|
|
|
|
}
|
|
|
|
remainder() {
|
|
|
|
return this.text.slice(this.offset);
|
2016-09-12 16:22:25 +02:00
|
|
|
}
|
2017-05-12 16:35:11 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
/******************************************************************************/
|
|
|
|
|
2018-10-23 19:01:08 +02:00
|
|
|
µBlock.CompiledLineIO = {
|
|
|
|
serialize: JSON.stringify,
|
|
|
|
unserialize: JSON.parse,
|
|
|
|
blockStartPrefix: '#block-start-', // ensure no special regex characters
|
|
|
|
blockEndPrefix: '#block-end-', // ensure no special regex characters
|
|
|
|
|
2019-09-11 14:08:30 +02:00
|
|
|
Writer: class {
|
|
|
|
constructor() {
|
|
|
|
this.io = µBlock.CompiledLineIO;
|
|
|
|
this.blockId = undefined;
|
|
|
|
this.block = undefined;
|
|
|
|
this.stringifier = this.io.serialize;
|
|
|
|
this.blocks = new Map();
|
|
|
|
this.properties = new Map();
|
|
|
|
}
|
|
|
|
push(args) {
|
Expand bidi-trie usage in static network filtering engine
Related issues:
- https://github.com/uBlockOrigin/uBlock-issues/issues/761
- https://github.com/uBlockOrigin/uBlock-issues/issues/528
The previous bidi-trie code could only hold filters which
are plain pattern, i.e. no wildcard characters, and which
had no origin option (`domain=`), right and/or left anchor,
and no `csp=` option.
Example of filters that could be moved into a bidi-trie
data structure:
&ad_box_
/w/d/capu.php?z=$script,third-party
||liveonlinetv247.com/images/muvixx-150x50-watch-now-in-hd-play-btn.gif
Examples of filters that could NOT be moved to a bidi-trie:
-adap.$domain=~l-adap.org
/tsc.php?*&ses=
||ibsrv.net/*forumsponsor$domain=[...]
@@||imgspice.com/jquery.cookie.js|$script
||view.atdmt.com^*/iview/$third-party
||postimg.cc/image/$csp=[...]
Ideally the filters above should be able to be moved to a
bidi-trie since they are basically plain patterns, or at
least partially moved to a bidi-trie when there is only a
single wildcard (i.e. made of two plain patterns).
Also, there were two distinct bidi-tries in which
plain-pattern filters can be moved to: one for patterns
without hostname anchoring and another one for patterns
with hostname-anchoring. This was required because the
hostname-anchored patterns have an extra condition which
is outside the bidi-trie knowledge.
This commit expands the number of filters which can be
stored in the bidi-trie, and also remove the need to
use two distinct bidi-tries.
- Added ability to associate a pattern with an integer
in the bidi-trie [1].
- The bidi-trie match code passes this externally
provided integer when calling an externally
provided method used for testing extra conditions
that may be present for a plain pattern found to
be matching in the bidi-trie.
- Decomposed existing filters into smaller logical units:
- FilterPlainLeftAnchored =>
FilterPatternPlain +
FilterAnchorLeft
- FilterPlainRightAnchored =>
FilterPatternPlain +
FilterAnchorRight
- FilterExactMatch =>
FilterPatternPlain +
FilterAnchorLeft +
FilterAnchorRight
- FilterPlainHnAnchored =>
FilterPatternPlain +
FilterAnchorHn
- FilterWildcard1 =>
FilterPatternPlain + [
FilterPatternLeft or
FilterPatternRight
]
- FilterWildcard1HnAnchored =>
FilterPatternPlain + [
FilterPatternLeft or
FilterPatternRight
] +
FilterAnchorHn
- FilterGenericHnAnchored =>
FilterPatternGeneric +
FilterAnchorHn
- FilterGenericHnAndRightAnchored =>
FilterPatternGeneric +
FilterAnchorRight +
FilterAnchorHn
- FilterOriginMixedSet =>
FilterOriginMissSet +
FilterOriginHitSet
- Instances of FilterOrigin[...], FilterDataHolder
can also be added to a composite filter to
represent `domain=` and `csp=` options.
- Added a new filter class, FilterComposite, for
filters which are a combination of two or more
logical units. A FilterComposite instance is a
match when *all* filters composing it are a
match.
Since filters are now encoded into combination of
smaller units, it becomes possible to extract the
FilterPatternPlain component and store it in the
bidi-trie, and use the integer as a handle for the
remaining extra conditions, if any.
Since a single pattern in the bidi-trie may be a
component for different filters, the associated
integer points to a sequence of extra conditions,
and a match occurs as soon as one of the extra
conditions (which may itself be a sequence of
conditions) is fulfilled.
Decomposing filters which are currently single
instance into sequences of smaller logical filters
means increasing the storage and CPU overhead when
evaluating such filters. The CPU overhead is
compensated by the fact that more filters can now
moved into the bidi-trie, where the first match is
efficiently evaluated. The extra conditions have to
be evaluated if and only if there is a match in the
bidi-trie.
The storage overhead is compensated by the
bidi-trie's intrinsic nature of merging similar
patterns.
Furthermore, the storage overhead is reduced by no
longer using JavaScript array to store collection
of filters (which is what FilterComposite is):
the same technique used in [2] is imported to store
sequences of filters.
A sequence of filters is a sequence of integer pairs
where the first integer is an index to an actual
filter instance stored in a global array of filters
(`filterUnits`), while the second integer is an index
to the next pair in the sequence -- which means all
sequences of filters are encoded in one single array
of integers (`filterSequences` => Uint32Array). As
a result, a sequence of filters can be represented by
one single integer -- an index to the first pair --
regardless of the number of filters in the sequence.
This representation is further leveraged to replace
the use of JavaScript array in FilterBucket [3],
which used a JavaScript array to store collection
of filters. Doing so means there is no more need for
FilterPair [4], which purpose was to be a lightweight
representation when there was only two filters in a
collection.
As a result of the above changes, the map of `token`
(integer) => filter instance (object) used to
associate tokens to filters or collections of filters
is replaced with a more efficient map of `token`
(integer) to filter unit index (integer) to lookup a
filter object from the global `filterUnits` array.
Another consequence of using one single global
array to store all filter instances means we can reuse
existing instances when a logical filter instance is
parameter-less, which is the case for FilterAnchorLeft,
FilterAnchorRight, FilterAnchorHn, the index to these
single instances is reused where needed.
`urlTokenizer` now stores the character codes of the
scanned URL into a bidi-trie buffer, for reuse when
string matching methods are called.
New method: `tokenHistogram()`, used to generate
histograms of occurrences of token extracted from URLs
in built-in benchmark. The top results of the "miss"
histogram are used as "bad tokens", i.e. tokens to
avoid if possible when compiling filter lists.
All plain pattern strings are now stored in the
bidi-trie memory buffer, regardless of whether they
will be used in the trie proper or not.
Three methods have been added to the bidi-trie to test
stored string against the URL which is also stored in
then bidi-trie.
FilterParser is now instanciated on demand and
released when no longer used.
***
[1] https://github.com/gorhill/uBlock/blob/135a45a878f5b93bc538f822981e3a42b1e9073f/src/js/strie.js#L120
[2] https://github.com/gorhill/uBlock/commit/e94024d350b066e4e04a772b0a3dbc69daab3fb7
[3] https://github.com/gorhill/uBlock/blob/135a45a878f5b93bc538f822981e3a42b1e9073f/src/js/static-net-filtering.js#L1630
[4] https://github.com/gorhill/uBlock/blob/135a45a878f5b93bc538f822981e3a42b1e9073f/src/js/static-net-filtering.js#L1566
2019-10-21 14:15:58 +02:00
|
|
|
this.block.push(this.stringifier(args));
|
|
|
|
}
|
|
|
|
last() {
|
|
|
|
if ( Array.isArray(this.block) && this.block.length !== 0 ) {
|
|
|
|
return this.block[this.block.length - 1];
|
|
|
|
}
|
2019-09-11 14:08:30 +02:00
|
|
|
}
|
|
|
|
select(blockId) {
|
|
|
|
if ( blockId === this.blockId ) { return; }
|
|
|
|
this.blockId = blockId;
|
|
|
|
this.block = this.blocks.get(blockId);
|
|
|
|
if ( this.block === undefined ) {
|
|
|
|
this.blocks.set(blockId, (this.block = []));
|
|
|
|
}
|
2020-12-08 16:00:47 +01:00
|
|
|
return this;
|
2018-10-23 19:01:08 +02:00
|
|
|
}
|
2019-09-11 14:08:30 +02:00
|
|
|
toString() {
|
|
|
|
let result = [];
|
|
|
|
for ( let [ id, lines ] of this.blocks ) {
|
|
|
|
if ( lines.length === 0 ) { continue; }
|
|
|
|
result.push(
|
|
|
|
this.io.blockStartPrefix + id,
|
|
|
|
lines.join('\n'),
|
|
|
|
this.io.blockEndPrefix + id
|
|
|
|
);
|
|
|
|
}
|
|
|
|
return result.join('\n');
|
2017-12-28 19:49:02 +01:00
|
|
|
}
|
2017-05-25 23:46:59 +02:00
|
|
|
},
|
2017-05-12 16:35:11 +02:00
|
|
|
|
2019-09-11 14:08:30 +02:00
|
|
|
Reader: class {
|
|
|
|
constructor(raw, blockId) {
|
|
|
|
this.io = µBlock.CompiledLineIO;
|
|
|
|
this.block = '';
|
|
|
|
this.len = 0;
|
|
|
|
this.offset = 0;
|
2017-12-28 19:49:02 +01:00
|
|
|
this.line = '';
|
2019-09-11 14:08:30 +02:00
|
|
|
this.parser = this.io.unserialize;
|
|
|
|
this.blocks = new Map();
|
|
|
|
this.properties = new Map();
|
|
|
|
let reBlockStart = new RegExp(
|
2020-12-08 16:00:47 +01:00
|
|
|
`^${this.io.blockStartPrefix}(\\d+)\\n`,
|
2019-09-11 14:08:30 +02:00
|
|
|
'gm'
|
|
|
|
);
|
|
|
|
let match = reBlockStart.exec(raw);
|
|
|
|
while ( match !== null ) {
|
|
|
|
let beg = match.index + match[0].length;
|
|
|
|
let end = raw.indexOf(this.io.blockEndPrefix + match[1], beg);
|
|
|
|
this.blocks.set(parseInt(match[1], 10), raw.slice(beg, end));
|
|
|
|
reBlockStart.lastIndex = end;
|
|
|
|
match = reBlockStart.exec(raw);
|
|
|
|
}
|
|
|
|
if ( blockId !== undefined ) {
|
|
|
|
this.select(blockId);
|
|
|
|
}
|
2017-05-25 23:46:59 +02:00
|
|
|
}
|
2019-09-11 14:08:30 +02:00
|
|
|
next() {
|
|
|
|
if ( this.offset === this.len ) {
|
|
|
|
this.line = '';
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
let pos = this.block.indexOf('\n', this.offset);
|
|
|
|
if ( pos !== -1 ) {
|
|
|
|
this.line = this.block.slice(this.offset, pos);
|
|
|
|
this.offset = pos + 1;
|
|
|
|
} else {
|
|
|
|
this.line = this.block.slice(this.offset);
|
|
|
|
this.offset = this.len;
|
|
|
|
}
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
select(blockId) {
|
|
|
|
this.block = this.blocks.get(blockId) || '';
|
|
|
|
this.len = this.block.length;
|
|
|
|
this.offset = 0;
|
|
|
|
return this;
|
|
|
|
}
|
|
|
|
fingerprint() {
|
|
|
|
return this.line;
|
|
|
|
}
|
|
|
|
args() {
|
|
|
|
return this.parser(this.line);
|
2017-05-25 23:46:59 +02:00
|
|
|
}
|
|
|
|
}
|
2017-05-12 16:35:11 +02:00
|
|
|
};
|
|
|
|
|
2016-09-12 16:22:25 +02:00
|
|
|
/******************************************************************************/
|
|
|
|
|
2016-09-16 23:41:17 +02:00
|
|
|
µBlock.openNewTab = function(details) {
|
|
|
|
if ( details.url.startsWith('logger-ui.html') ) {
|
|
|
|
if ( details.shiftKey ) {
|
2016-09-17 01:12:16 +02:00
|
|
|
this.changeUserSettings(
|
|
|
|
'alwaysDetachLogger',
|
|
|
|
!this.userSettings.alwaysDetachLogger
|
|
|
|
);
|
2016-09-16 23:41:17 +02:00
|
|
|
}
|
2019-09-06 17:41:07 +02:00
|
|
|
if ( this.userSettings.alwaysDetachLogger ) {
|
|
|
|
details.popup = this.hiddenSettings.loggerPopupType;
|
2018-12-14 17:01:21 +01:00
|
|
|
const url = new URL(vAPI.getURL(details.url));
|
|
|
|
url.searchParams.set('popup', '1');
|
|
|
|
details.url = url.href;
|
|
|
|
let popupLoggerBox;
|
|
|
|
try {
|
|
|
|
popupLoggerBox = JSON.parse(
|
|
|
|
vAPI.localStorage.getItem('popupLoggerBox')
|
|
|
|
);
|
|
|
|
} catch(ex) {
|
|
|
|
}
|
|
|
|
if ( popupLoggerBox !== undefined ) {
|
|
|
|
details.box = popupLoggerBox;
|
|
|
|
}
|
|
|
|
}
|
2016-09-16 23:41:17 +02:00
|
|
|
}
|
|
|
|
vAPI.tabs.open(details);
|
|
|
|
};
|
|
|
|
|
|
|
|
/******************************************************************************/
|
2017-01-27 19:44:52 +01:00
|
|
|
|
2019-09-11 14:08:30 +02:00
|
|
|
µBlock.MRUCache = class {
|
|
|
|
constructor(size) {
|
|
|
|
this.size = size;
|
|
|
|
this.array = [];
|
|
|
|
this.map = new Map();
|
|
|
|
this.resetTime = Date.now();
|
|
|
|
}
|
|
|
|
add(key, value) {
|
|
|
|
const found = this.map.has(key);
|
2017-10-21 19:43:46 +02:00
|
|
|
this.map.set(key, value);
|
|
|
|
if ( !found ) {
|
|
|
|
if ( this.array.length === this.size ) {
|
|
|
|
this.map.delete(this.array.pop());
|
|
|
|
}
|
|
|
|
this.array.unshift(key);
|
|
|
|
}
|
2019-09-11 14:08:30 +02:00
|
|
|
}
|
|
|
|
remove(key) {
|
2017-10-21 19:43:46 +02:00
|
|
|
if ( this.map.has(key) ) {
|
|
|
|
this.array.splice(this.array.indexOf(key), 1);
|
|
|
|
}
|
2019-09-11 14:08:30 +02:00
|
|
|
}
|
|
|
|
lookup(key) {
|
|
|
|
const value = this.map.get(key);
|
2017-10-21 19:43:46 +02:00
|
|
|
if ( value !== undefined && this.array[0] !== key ) {
|
2019-09-11 14:08:30 +02:00
|
|
|
let i = this.array.indexOf(key);
|
2017-12-22 15:37:26 +01:00
|
|
|
do {
|
|
|
|
this.array[i] = this.array[i-1];
|
|
|
|
} while ( --i );
|
|
|
|
this.array[0] = key;
|
2017-10-21 19:43:46 +02:00
|
|
|
}
|
|
|
|
return value;
|
2019-09-11 14:08:30 +02:00
|
|
|
}
|
|
|
|
reset() {
|
2017-10-21 19:43:46 +02:00
|
|
|
this.array = [];
|
|
|
|
this.map.clear();
|
2017-12-21 23:05:25 +01:00
|
|
|
this.resetTime = Date.now();
|
2017-10-21 19:43:46 +02:00
|
|
|
}
|
|
|
|
};
|
|
|
|
|
|
|
|
/******************************************************************************/
|
2017-11-09 18:53:05 +01:00
|
|
|
|
|
|
|
// https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Regular_Expressions
|
|
|
|
|
|
|
|
µBlock.escapeRegex = function(s) {
|
|
|
|
return s.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
|
|
|
|
};
|
|
|
|
|
|
|
|
/******************************************************************************/
|
2018-06-03 19:27:42 +02:00
|
|
|
|
2019-09-11 14:08:30 +02:00
|
|
|
µBlock.decomposeHostname = (( ) => {
|
2018-06-03 19:27:42 +02:00
|
|
|
// For performance purpose, as simple tests as possible
|
2019-09-11 14:08:30 +02:00
|
|
|
const reHostnameVeryCoarse = /[g-z_-]/;
|
|
|
|
const reIPv4VeryCoarse = /\.\d+$/;
|
2018-06-03 19:27:42 +02:00
|
|
|
|
2019-09-11 14:08:30 +02:00
|
|
|
const toBroaderHostname = function(hostname) {
|
|
|
|
const pos = hostname.indexOf('.');
|
2018-06-03 19:27:42 +02:00
|
|
|
if ( pos !== -1 ) {
|
|
|
|
return hostname.slice(pos + 1);
|
|
|
|
}
|
|
|
|
return hostname !== '*' && hostname !== '' ? '*' : '';
|
|
|
|
};
|
|
|
|
|
2019-09-11 14:08:30 +02:00
|
|
|
const toBroaderIPv4Address = function(ipaddress) {
|
2018-08-09 17:31:25 +02:00
|
|
|
if ( ipaddress === '*' || ipaddress === '' ) { return ''; }
|
2019-09-11 14:08:30 +02:00
|
|
|
const pos = ipaddress.lastIndexOf('.');
|
2018-08-09 17:31:25 +02:00
|
|
|
if ( pos === -1 ) { return '*'; }
|
|
|
|
return ipaddress.slice(0, pos);
|
|
|
|
};
|
|
|
|
|
2019-09-11 14:08:30 +02:00
|
|
|
const toBroaderIPv6Address = function(ipaddress) {
|
2018-06-03 19:27:42 +02:00
|
|
|
return ipaddress !== '*' && ipaddress !== '' ? '*' : '';
|
|
|
|
};
|
|
|
|
|
|
|
|
return function decomposeHostname(hostname, decomposed) {
|
|
|
|
if ( decomposed.length === 0 || decomposed[0] !== hostname ) {
|
2018-08-09 17:31:25 +02:00
|
|
|
let broaden;
|
|
|
|
if ( reHostnameVeryCoarse.test(hostname) === false ) {
|
2018-09-03 22:15:51 +02:00
|
|
|
if ( reIPv4VeryCoarse.test(hostname) ) {
|
2018-08-09 17:31:25 +02:00
|
|
|
broaden = toBroaderIPv4Address;
|
|
|
|
} else if ( hostname.startsWith('[') ) {
|
|
|
|
broaden = toBroaderIPv6Address;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if ( broaden === undefined ) {
|
|
|
|
broaden = toBroaderHostname;
|
|
|
|
}
|
2018-06-03 19:27:42 +02:00
|
|
|
decomposed[0] = hostname;
|
|
|
|
let i = 1;
|
|
|
|
for (;;) {
|
|
|
|
hostname = broaden(hostname);
|
|
|
|
if ( hostname === '' ) { break; }
|
|
|
|
decomposed[i++] = hostname;
|
|
|
|
}
|
|
|
|
decomposed.length = i;
|
|
|
|
}
|
|
|
|
return decomposed;
|
|
|
|
};
|
|
|
|
})();
|
2018-10-23 19:01:08 +02:00
|
|
|
|
|
|
|
/******************************************************************************/
|
|
|
|
|
|
|
|
// TODO: evaluate using TextEncoder/TextDecoder
|
|
|
|
|
|
|
|
µBlock.orphanizeString = function(s) {
|
|
|
|
return JSON.parse(JSON.stringify(s));
|
2018-12-14 17:01:21 +01:00
|
|
|
};
|
2019-02-14 19:33:55 +01:00
|
|
|
|
|
|
|
/******************************************************************************/
|
|
|
|
|
2020-08-16 17:53:55 +02:00
|
|
|
// Custom base64 codecs. These codecs are meant to encode/decode typed arrays
|
|
|
|
// to/from strings.
|
|
|
|
|
2019-03-16 14:00:31 +01:00
|
|
|
// https://github.com/uBlockOrigin/uBlock-issues/issues/461
|
|
|
|
// Provide a fallback encoding for Chromium 59 and less by issuing a plain
|
|
|
|
// JSON string. The fallback can be removed once min supported version is
|
|
|
|
// above 59.
|
2019-02-14 19:33:55 +01:00
|
|
|
|
2020-08-16 17:53:55 +02:00
|
|
|
// TODO: rename µBlock.base64 to µBlock.SparseBase64, now that
|
|
|
|
// µBlock.DenseBase64 has been introduced.
|
|
|
|
// TODO: Should no longer need to test presence of TextEncoder/TextDecoder.
|
|
|
|
|
|
|
|
{
|
|
|
|
const valToDigit = new Uint8Array(64);
|
|
|
|
const digitToVal = new Uint8Array(128);
|
|
|
|
{
|
|
|
|
const chars = '0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz@%';
|
2019-04-20 15:06:54 +02:00
|
|
|
for ( let i = 0, n = chars.length; i < n; i++ ) {
|
|
|
|
const c = chars.charCodeAt(i);
|
2020-08-16 17:53:55 +02:00
|
|
|
valToDigit[i] = c;
|
|
|
|
digitToVal[c] = i;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// The sparse base64 codec is best for buffers which contains a lot of
|
|
|
|
// small u32 integer values. Those small u32 integer values are better
|
|
|
|
// represented with stringified integers, because small values can be
|
|
|
|
// represented with fewer bits than the usual base64 codec. For example,
|
|
|
|
// 0 become '0 ', i.e. 16 bits instead of 48 bits with official base64
|
|
|
|
// codec.
|
|
|
|
|
|
|
|
µBlock.base64 = {
|
|
|
|
magic: 'Base64_1',
|
|
|
|
|
|
|
|
encode: function(arrbuf, arrlen) {
|
|
|
|
const inputLength = (arrlen + 3) >>> 2;
|
|
|
|
const inbuf = new Uint32Array(arrbuf, 0, inputLength);
|
|
|
|
const outputLength = this.magic.length + 7 + inputLength * 7;
|
|
|
|
const outbuf = new Uint8Array(outputLength);
|
|
|
|
// magic bytes
|
|
|
|
let j = 0;
|
|
|
|
for ( let i = 0; i < this.magic.length; i++ ) {
|
|
|
|
outbuf[j++] = this.magic.charCodeAt(i);
|
|
|
|
}
|
|
|
|
// array size
|
|
|
|
let v = inputLength;
|
2019-04-20 15:06:54 +02:00
|
|
|
do {
|
2020-08-16 17:53:55 +02:00
|
|
|
outbuf[j++] = valToDigit[v & 0b111111];
|
2019-04-20 15:06:54 +02:00
|
|
|
v >>>= 6;
|
|
|
|
} while ( v !== 0 );
|
|
|
|
outbuf[j++] = 0x20 /* ' ' */;
|
2020-08-16 17:53:55 +02:00
|
|
|
// array content
|
|
|
|
for ( let i = 0; i < inputLength; i++ ) {
|
|
|
|
v = inbuf[i];
|
|
|
|
do {
|
|
|
|
outbuf[j++] = valToDigit[v & 0b111111];
|
|
|
|
v >>>= 6;
|
|
|
|
} while ( v !== 0 );
|
|
|
|
outbuf[j++] = 0x20 /* ' ' */;
|
|
|
|
}
|
|
|
|
if ( typeof TextDecoder === 'undefined' ) {
|
|
|
|
return JSON.stringify(
|
|
|
|
Array.from(new Uint32Array(outbuf.buffer, 0, j >>> 2))
|
|
|
|
);
|
|
|
|
}
|
|
|
|
const textDecoder = new TextDecoder();
|
|
|
|
return textDecoder.decode(new Uint8Array(outbuf.buffer, 0, j));
|
|
|
|
},
|
|
|
|
|
|
|
|
decode: function(instr, arrbuf) {
|
|
|
|
if ( instr.charCodeAt(0) === 0x5B /* '[' */ ) {
|
|
|
|
const inbuf = JSON.parse(instr);
|
|
|
|
if ( arrbuf instanceof ArrayBuffer === false ) {
|
|
|
|
return new Uint32Array(inbuf);
|
|
|
|
}
|
|
|
|
const outbuf = new Uint32Array(arrbuf);
|
|
|
|
outbuf.set(inbuf);
|
|
|
|
return outbuf;
|
|
|
|
}
|
|
|
|
if ( instr.startsWith(this.magic) === false ) {
|
|
|
|
throw new Error('Invalid µBlock.base64 encoding');
|
|
|
|
}
|
|
|
|
const inputLength = instr.length;
|
|
|
|
const outputLength = this.decodeSize(instr) >> 2;
|
|
|
|
const outbuf = arrbuf instanceof ArrayBuffer === false
|
|
|
|
? new Uint32Array(outputLength)
|
|
|
|
: new Uint32Array(arrbuf);
|
|
|
|
let i = instr.indexOf(' ', this.magic.length) + 1;
|
|
|
|
if ( i === -1 ) {
|
|
|
|
throw new Error('Invalid µBlock.base64 encoding');
|
|
|
|
}
|
|
|
|
// array content
|
|
|
|
let j = 0;
|
|
|
|
for (;;) {
|
|
|
|
if ( j === outputLength || i >= inputLength ) { break; }
|
|
|
|
let v = 0, l = 0;
|
|
|
|
for (;;) {
|
|
|
|
const c = instr.charCodeAt(i++);
|
|
|
|
if ( c === 0x20 /* ' ' */ ) { break; }
|
|
|
|
v += digitToVal[c] << l;
|
|
|
|
l += 6;
|
|
|
|
}
|
|
|
|
outbuf[j++] = v;
|
|
|
|
}
|
|
|
|
if ( i < inputLength || j < outputLength ) {
|
|
|
|
throw new Error('Invalid µBlock.base64 encoding');
|
2019-04-28 20:07:21 +02:00
|
|
|
}
|
|
|
|
return outbuf;
|
2020-08-16 17:53:55 +02:00
|
|
|
},
|
|
|
|
|
|
|
|
decodeSize: function(instr) {
|
|
|
|
if ( instr.startsWith(this.magic) === false ) { return 0; }
|
|
|
|
let v = 0, l = 0, i = this.magic.length;
|
2019-04-20 15:06:54 +02:00
|
|
|
for (;;) {
|
|
|
|
const c = instr.charCodeAt(i++);
|
|
|
|
if ( c === 0x20 /* ' ' */ ) { break; }
|
2020-08-16 17:53:55 +02:00
|
|
|
v += digitToVal[c] << l;
|
2019-04-20 15:06:54 +02:00
|
|
|
l += 6;
|
2019-03-16 14:00:31 +01:00
|
|
|
}
|
2020-08-16 17:53:55 +02:00
|
|
|
return v << 2;
|
|
|
|
},
|
|
|
|
};
|
2019-04-20 15:06:54 +02:00
|
|
|
|
2020-08-16 17:53:55 +02:00
|
|
|
// The dense base64 codec is best for typed buffers which values are
|
|
|
|
// more random. For example, buffer contents as a result of compression
|
|
|
|
// contain less repetitive values and thus the content is more
|
|
|
|
// random-looking.
|
|
|
|
|
|
|
|
// TODO: Investigate that in Firefox, creating a new Uint8Array from the
|
|
|
|
// ArrayBuffer fails, the content of the resulting Uint8Array is
|
|
|
|
// non-sensical. WASM-related?
|
|
|
|
|
|
|
|
µBlock.denseBase64 = {
|
|
|
|
magic: 'DenseBase64_1',
|
|
|
|
|
|
|
|
encode: function(input) {
|
|
|
|
const m = input.length % 3;
|
|
|
|
const n = input.length - m;
|
|
|
|
let outputLength = n / 3 * 4;
|
|
|
|
if ( m !== 0 ) {
|
|
|
|
outputLength += m + 1;
|
|
|
|
}
|
|
|
|
const output = new Uint8Array(outputLength);
|
|
|
|
let j = 0;
|
|
|
|
for ( let i = 0; i < n; i += 3) {
|
|
|
|
const i1 = input[i+0];
|
|
|
|
const i2 = input[i+1];
|
|
|
|
const i3 = input[i+2];
|
|
|
|
output[j+0] = valToDigit[ i1 >>> 2];
|
|
|
|
output[j+1] = valToDigit[i1 << 4 & 0b110000 | i2 >>> 4];
|
|
|
|
output[j+2] = valToDigit[i2 << 2 & 0b111100 | i3 >>> 6];
|
|
|
|
output[j+3] = valToDigit[i3 & 0b111111 ];
|
|
|
|
j += 4;
|
|
|
|
}
|
|
|
|
if ( m !== 0 ) {
|
|
|
|
const i1 = input[n];
|
|
|
|
output[j+0] = valToDigit[i1 >>> 2];
|
|
|
|
if ( m === 1 ) { // 1 value
|
|
|
|
output[j+1] = valToDigit[i1 << 4 & 0b110000];
|
|
|
|
} else { // 2 values
|
|
|
|
const i2 = input[n+1];
|
|
|
|
output[j+1] = valToDigit[i1 << 4 & 0b110000 | i2 >>> 4];
|
|
|
|
output[j+2] = valToDigit[i2 << 2 & 0b111100 ];
|
|
|
|
}
|
|
|
|
}
|
|
|
|
const textDecoder = new TextDecoder();
|
|
|
|
const b64str = textDecoder.decode(output);
|
|
|
|
return this.magic + b64str;
|
|
|
|
},
|
|
|
|
|
|
|
|
decode: function(instr, arrbuf) {
|
|
|
|
if ( instr.startsWith(this.magic) === false ) {
|
|
|
|
throw new Error('Invalid µBlock.denseBase64 encoding');
|
|
|
|
}
|
|
|
|
const outputLength = this.decodeSize(instr);
|
|
|
|
const outbuf = arrbuf instanceof ArrayBuffer === false
|
|
|
|
? new Uint8Array(outputLength)
|
|
|
|
: new Uint8Array(arrbuf);
|
|
|
|
const inputLength = instr.length - this.magic.length;
|
|
|
|
let i = this.magic.length;
|
|
|
|
let j = 0;
|
|
|
|
const m = inputLength & 3;
|
|
|
|
const n = i + inputLength - m;
|
|
|
|
while ( i < n ) {
|
|
|
|
const i1 = digitToVal[instr.charCodeAt(i+0)];
|
|
|
|
const i2 = digitToVal[instr.charCodeAt(i+1)];
|
|
|
|
const i3 = digitToVal[instr.charCodeAt(i+2)];
|
|
|
|
const i4 = digitToVal[instr.charCodeAt(i+3)];
|
|
|
|
i += 4;
|
|
|
|
outbuf[j+0] = i1 << 2 | i2 >>> 4;
|
|
|
|
outbuf[j+1] = i2 << 4 & 0b11110000 | i3 >>> 2;
|
|
|
|
outbuf[j+2] = i3 << 6 & 0b11000000 | i4;
|
|
|
|
j += 3;
|
|
|
|
}
|
|
|
|
if ( m !== 0 ) {
|
|
|
|
const i1 = digitToVal[instr.charCodeAt(i+0)];
|
|
|
|
const i2 = digitToVal[instr.charCodeAt(i+1)];
|
|
|
|
outbuf[j+0] = i1 << 2 | i2 >>> 4;
|
|
|
|
if ( m === 3 ) {
|
|
|
|
const i3 = digitToVal[instr.charCodeAt(i+2)];
|
|
|
|
outbuf[j+1] = i2 << 4 & 0b11110000 | i3 >>> 2;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return outbuf;
|
|
|
|
},
|
|
|
|
|
|
|
|
decodeSize: function(instr) {
|
|
|
|
if ( instr.startsWith(this.magic) === false ) { return 0; }
|
|
|
|
const inputLength = instr.length - this.magic.length;
|
|
|
|
const m = inputLength & 3;
|
|
|
|
const n = inputLength - m;
|
|
|
|
let outputLength = (n >>> 2) * 3;
|
|
|
|
if ( m !== 0 ) {
|
|
|
|
outputLength += m - 1;
|
|
|
|
}
|
|
|
|
return outputLength;
|
|
|
|
},
|
|
|
|
};
|
|
|
|
}
|
2019-02-19 16:46:33 +01:00
|
|
|
|
|
|
|
/******************************************************************************/
|
|
|
|
|
|
|
|
// The requests.json.gz file can be downloaded from:
|
|
|
|
// https://cdn.cliqz.com/adblocking/requests_top500.json.gz
|
|
|
|
//
|
|
|
|
// Which is linked from:
|
|
|
|
// https://whotracks.me/blog/adblockers_performance_study.html
|
|
|
|
//
|
|
|
|
// Copy the file into ./tmp/requests.json.gz
|
|
|
|
//
|
|
|
|
// If the file is present when you build uBO using `make-[target].sh` from
|
|
|
|
// the shell, the resulting package will have `./assets/requests.json`, which
|
|
|
|
// will be looked-up by the method below to launch a benchmark session.
|
|
|
|
//
|
|
|
|
// From uBO's dev console, launch the benchmark:
|
|
|
|
// µBlock.staticNetFilteringEngine.benchmark();
|
|
|
|
//
|
|
|
|
// The advanced setting `consoleLogLevel` must be set to `info` to see the
|
|
|
|
// results in uBO's dev console, see:
|
|
|
|
// https://github.com/gorhill/uBlock/wiki/Advanced-settings#consoleloglevel
|
|
|
|
//
|
|
|
|
// The usual browser dev tools can be used to obtain useful profiling
|
|
|
|
// data, i.e. start the profiler, call the benchmark method from the
|
|
|
|
// console, then stop the profiler when it completes.
|
|
|
|
//
|
|
|
|
// Keep in mind that the measurements at the blog post above where obtained
|
|
|
|
// with ONLY EasyList. The CPU reportedly used was:
|
|
|
|
// https://www.cpubenchmark.net/cpu.php?cpu=Intel+Core+i7-6600U+%40+2.60GHz&id=2608
|
|
|
|
//
|
|
|
|
// Rename ./tmp/requests.json.gz to something else if you no longer want
|
|
|
|
// ./assets/requests.json in the build.
|
|
|
|
|
2019-09-11 14:08:30 +02:00
|
|
|
µBlock.loadBenchmarkDataset = (( ) => {
|
2019-02-19 16:46:33 +01:00
|
|
|
let datasetPromise;
|
|
|
|
let ttlTimer;
|
|
|
|
|
|
|
|
return function() {
|
|
|
|
if ( ttlTimer !== undefined ) {
|
|
|
|
clearTimeout(ttlTimer);
|
|
|
|
ttlTimer = undefined;
|
|
|
|
}
|
|
|
|
|
|
|
|
vAPI.setTimeout(( ) => {
|
|
|
|
ttlTimer = undefined;
|
|
|
|
datasetPromise = undefined;
|
2020-02-21 14:06:52 +01:00
|
|
|
}, 5 * 60 * 1000);
|
2019-02-19 16:46:33 +01:00
|
|
|
|
|
|
|
if ( datasetPromise !== undefined ) {
|
|
|
|
return datasetPromise;
|
|
|
|
}
|
|
|
|
|
2020-02-21 14:06:52 +01:00
|
|
|
const datasetURL = µBlock.hiddenSettings.benchmarkDatasetURL;
|
|
|
|
if ( datasetURL === 'unset' ) {
|
2020-02-21 14:13:15 +01:00
|
|
|
console.info(`No benchmark dataset available.`);
|
|
|
|
return Promise.resolve();
|
2020-02-21 14:06:52 +01:00
|
|
|
}
|
2019-04-20 23:16:49 +02:00
|
|
|
console.info(`Loading benchmark dataset...`);
|
2020-02-21 14:06:52 +01:00
|
|
|
datasetPromise = µBlock.assets.fetchText(datasetURL).then(details => {
|
2019-04-20 23:16:49 +02:00
|
|
|
console.info(`Parsing benchmark dataset...`);
|
|
|
|
const requests = [];
|
|
|
|
const lineIter = new µBlock.LineIterator(details.content);
|
|
|
|
while ( lineIter.eot() === false ) {
|
|
|
|
let request;
|
|
|
|
try {
|
|
|
|
request = JSON.parse(lineIter.next());
|
|
|
|
} catch(ex) {
|
2019-02-19 16:46:33 +01:00
|
|
|
}
|
2019-04-20 23:16:49 +02:00
|
|
|
if ( request instanceof Object === false ) { continue; }
|
|
|
|
if ( !request.frameUrl || !request.url ) { continue; }
|
2020-10-27 17:59:31 +01:00
|
|
|
if ( request.cpt === 'document' ) {
|
|
|
|
request.cpt = 'main_frame';
|
|
|
|
} else if ( request.cpt === 'xhr' ) {
|
|
|
|
request.cpt = 'xmlhttprequest';
|
|
|
|
}
|
2019-04-20 23:16:49 +02:00
|
|
|
requests.push(request);
|
|
|
|
}
|
|
|
|
return requests;
|
|
|
|
}).catch(details => {
|
|
|
|
console.info(`Not found: ${details.url}`);
|
|
|
|
datasetPromise = undefined;
|
2019-02-19 16:46:33 +01:00
|
|
|
});
|
|
|
|
|
|
|
|
return datasetPromise;
|
|
|
|
};
|
|
|
|
})();
|
2019-08-10 16:57:24 +02:00
|
|
|
|
|
|
|
/******************************************************************************/
|
|
|
|
|
|
|
|
µBlock.fireDOMEvent = function(name) {
|
|
|
|
if (
|
|
|
|
window instanceof Object &&
|
|
|
|
window.dispatchEvent instanceof Function &&
|
|
|
|
window.CustomEvent instanceof Function
|
|
|
|
) {
|
|
|
|
window.dispatchEvent(new CustomEvent(name));
|
|
|
|
}
|
|
|
|
};
|
2021-01-16 16:35:56 +01:00
|
|
|
|
|
|
|
/******************************************************************************/
|
|
|
|
|
|
|
|
µBlock.getModifiedSettings = function(edit, orig = {}) {
|
|
|
|
const out = {};
|
|
|
|
for ( const prop in edit ) {
|
|
|
|
if ( orig.hasOwnProperty(prop) && edit[prop] !== orig[prop] ) {
|
|
|
|
out[prop] = edit[prop];
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return out;
|
|
|
|
};
|
|
|
|
|
|
|
|
µBlock.settingValueFromString = function(orig, name, s) {
|
|
|
|
if ( typeof name !== 'string' || typeof s !== 'string' ) { return; }
|
|
|
|
if ( orig.hasOwnProperty(name) === false ) { return; }
|
|
|
|
let r;
|
|
|
|
switch ( typeof orig[name] ) {
|
|
|
|
case 'boolean':
|
|
|
|
if ( s === 'true' ) {
|
|
|
|
r = true;
|
|
|
|
} else if ( s === 'false' ) {
|
|
|
|
r = false;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
case 'string':
|
|
|
|
r = s.trim();
|
|
|
|
break;
|
|
|
|
case 'number':
|
|
|
|
if ( s.startsWith('0b') ) {
|
|
|
|
r = parseInt(s.slice(2), 2);
|
|
|
|
} else if ( s.startsWith('0x') ) {
|
|
|
|
r = parseInt(s.slice(2), 16);
|
|
|
|
} else {
|
|
|
|
r = parseInt(s, 10);
|
|
|
|
}
|
|
|
|
if ( isNaN(r) ) { r = undefined; }
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
return r;
|
|
|
|
};
|