Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
94.46% |
494 / 523 |
|
89.06% |
57 / 64 |
CRAP | |
0.00% |
0 / 1 |
| FilterEvaluator | |
94.46% |
494 / 523 |
|
89.06% |
57 / 64 |
186.59 | |
0.00% |
0 / 1 |
| __construct | |
90.91% |
10 / 11 |
|
0.00% |
0 / 1 |
2.00 | |||
| toggleConditionLimit | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| raiseCondCount | |
66.67% |
2 / 3 |
|
0.00% |
0 / 1 |
3.33 | |||
| setVariables | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| getCacheVersion | |
23.08% |
3 / 13 |
|
0.00% |
0 / 1 |
3.82 | |||
| resetState | |
100.00% |
5 / 5 |
|
100.00% |
1 / 1 |
1 | |||
| checkSyntaxThrow | |
100.00% |
7 / 7 |
|
100.00% |
1 / 1 |
1 | |||
| checkSyntax | |
87.50% |
7 / 8 |
|
0.00% |
0 / 1 |
2.01 | |||
| checkConditions | |
62.50% |
15 / 24 |
|
0.00% |
0 / 1 |
6.32 | |||
| parse | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
2 | |||
| evaluateExpression | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| getTree | |
100.00% |
25 / 25 |
|
100.00% |
1 / 1 |
1 | |||
| evalTree | |
100.00% |
7 / 7 |
|
100.00% |
1 / 1 |
2 | |||
| evalNode | |
99.36% |
155 / 156 |
|
0.00% |
0 / 1 |
58 | |||
| callFunc | |
100.00% |
19 / 19 |
|
100.00% |
1 / 1 |
8 | |||
| callKeyword | |
100.00% |
14 / 14 |
|
100.00% |
1 / 1 |
4 | |||
| varExists | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
2 | |||
| getVarValue | |
100.00% |
10 / 10 |
|
100.00% |
1 / 1 |
4 | |||
| setUserVariable | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| funcLc | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| funcUc | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| funcLen | |
100.00% |
4 / 4 |
|
100.00% |
1 / 1 |
2 | |||
| funcSpecialRatio | |
100.00% |
6 / 6 |
|
100.00% |
1 / 1 |
2 | |||
| funcCount | |
100.00% |
10 / 10 |
|
100.00% |
1 / 1 |
5 | |||
| funcRCount | |
100.00% |
14 / 14 |
|
100.00% |
1 / 1 |
3 | |||
| funcGetMatches | |
100.00% |
17 / 17 |
|
100.00% |
1 / 1 |
2 | |||
| funcIPInRange | |
100.00% |
10 / 10 |
|
100.00% |
1 / 1 |
3 | |||
| funcIPInRanges | |
100.00% |
12 / 12 |
|
100.00% |
1 / 1 |
4 | |||
| funcCCNorm | |
100.00% |
4 / 4 |
|
100.00% |
1 / 1 |
1 | |||
| funcSanitize | |
100.00% |
4 / 4 |
|
100.00% |
1 / 1 |
1 | |||
| funcContainsAny | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| funcContainsAll | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| funcCCNormContainsAny | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| funcCCNormContainsAll | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| contains | |
100.00% |
15 / 15 |
|
100.00% |
1 / 1 |
7 | |||
| funcEqualsToAny | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| equalsToAny | |
100.00% |
4 / 4 |
|
100.00% |
1 / 1 |
3 | |||
| ccnorm | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| rmspecials | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| rmdoubles | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| rmwhitespace | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| funcRMSpecials | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| funcRMWhitespace | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| funcRMDoubles | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| funcNorm | |
100.00% |
6 / 6 |
|
100.00% |
1 / 1 |
1 | |||
| funcSubstr | |
100.00% |
5 / 5 |
|
100.00% |
1 / 1 |
2 | |||
| funcStrPos | |
100.00% |
11 / 11 |
|
100.00% |
1 / 1 |
5 | |||
| funcStrReplace | |
100.00% |
4 / 4 |
|
100.00% |
1 / 1 |
1 | |||
| funcStrReplaceRegexp | |
100.00% |
16 / 16 |
|
100.00% |
1 / 1 |
2 | |||
| funcStrRegexEscape | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| funcSetVar | |
100.00% |
4 / 4 |
|
100.00% |
1 / 1 |
1 | |||
| containmentKeyword | |
100.00% |
5 / 5 |
|
100.00% |
1 / 1 |
3 | |||
| keywordIn | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| keywordContains | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| keywordLike | |
100.00% |
4 / 4 |
|
100.00% |
1 / 1 |
1 | |||
| keywordRegex | |
100.00% |
13 / 13 |
|
100.00% |
1 / 1 |
3 | |||
| keywordRegexInsensitive | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| castString | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| castInt | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| castFloat | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| castBool | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| maybeDiscardNode | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
2 | |||
| mungeRegexp | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| checkRegexMatchesEmpty | |
25.00% |
2 / 8 |
|
0.00% |
0 / 1 |
6.80 | |||
| 1 | <?php |
| 2 | |
| 3 | namespace MediaWiki\Extension\AbuseFilter\Parser; |
| 4 | |
| 5 | use BagOStuff; |
| 6 | use Exception; |
| 7 | use IBufferingStatsdDataFactory; |
| 8 | use InvalidArgumentException; |
| 9 | use Language; |
| 10 | use MediaWiki\Extension\AbuseFilter\KeywordsManager; |
| 11 | use MediaWiki\Extension\AbuseFilter\Parser\Exception\ConditionLimitException; |
| 12 | use MediaWiki\Extension\AbuseFilter\Parser\Exception\ExceptionBase; |
| 13 | use MediaWiki\Extension\AbuseFilter\Parser\Exception\InternalException; |
| 14 | use MediaWiki\Extension\AbuseFilter\Parser\Exception\UserVisibleException; |
| 15 | use MediaWiki\Extension\AbuseFilter\Parser\Exception\UserVisibleWarning; |
| 16 | use MediaWiki\Extension\AbuseFilter\Variables\VariableHolder; |
| 17 | use MediaWiki\Extension\AbuseFilter\Variables\VariablesManager; |
| 18 | use MediaWiki\Parser\Sanitizer; |
| 19 | use Psr\Log\LoggerInterface; |
| 20 | use Wikimedia\Equivset\Equivset; |
| 21 | use Wikimedia\IPUtils; |
| 22 | |
| 23 | /** |
| 24 | * This class evaluates an AST generated by the filter parser. |
| 25 | * |
| 26 | * @todo Override checkSyntax and make it only try to build the AST. That would mean faster results, |
| 27 | * and no need to mess with DUNDEFINED and the like. However, we must first try to reduce the |
| 28 | * amount of runtime-only exceptions, and try to detect them in the AFPTreeParser instead. |
| 29 | * Otherwise, people may be able to save a broken filter without the syntax check reporting that. |
| 30 | */ |
| 31 | class FilterEvaluator { |
| 32 | private const CACHE_VERSION = 1; |
| 33 | |
| 34 | public const FUNCTIONS = [ |
| 35 | 'lcase' => 'funcLc', |
| 36 | 'ucase' => 'funcUc', |
| 37 | 'length' => 'funcLen', |
| 38 | 'string' => 'castString', |
| 39 | 'int' => 'castInt', |
| 40 | 'float' => 'castFloat', |
| 41 | 'bool' => 'castBool', |
| 42 | 'norm' => 'funcNorm', |
| 43 | 'ccnorm' => 'funcCCNorm', |
| 44 | 'ccnorm_contains_any' => 'funcCCNormContainsAny', |
| 45 | 'ccnorm_contains_all' => 'funcCCNormContainsAll', |
| 46 | 'specialratio' => 'funcSpecialRatio', |
| 47 | 'rmspecials' => 'funcRMSpecials', |
| 48 | 'rmdoubles' => 'funcRMDoubles', |
| 49 | 'rmwhitespace' => 'funcRMWhitespace', |
| 50 | 'count' => 'funcCount', |
| 51 | 'rcount' => 'funcRCount', |
| 52 | 'get_matches' => 'funcGetMatches', |
| 53 | 'ip_in_range' => 'funcIPInRange', |
| 54 | 'ip_in_ranges' => 'funcIPInRanges', |
| 55 | 'contains_any' => 'funcContainsAny', |
| 56 | 'contains_all' => 'funcContainsAll', |
| 57 | 'equals_to_any' => 'funcEqualsToAny', |
| 58 | 'substr' => 'funcSubstr', |
| 59 | 'strlen' => 'funcLen', |
| 60 | 'strpos' => 'funcStrPos', |
| 61 | 'str_replace' => 'funcStrReplace', |
| 62 | 'str_replace_regexp' => 'funcStrReplaceRegexp', |
| 63 | 'rescape' => 'funcStrRegexEscape', |
| 64 | 'set' => 'funcSetVar', |
| 65 | 'set_var' => 'funcSetVar', |
| 66 | 'sanitize' => 'funcSanitize', |
| 67 | ]; |
| 68 | |
| 69 | /** |
| 70 | * The minimum and maximum amount of arguments required by each function. |
| 71 | * @var int[][] |
| 72 | */ |
| 73 | public const FUNC_ARG_COUNT = [ |
| 74 | 'lcase' => [ 1, 1 ], |
| 75 | 'ucase' => [ 1, 1 ], |
| 76 | 'length' => [ 1, 1 ], |
| 77 | 'string' => [ 1, 1 ], |
| 78 | 'int' => [ 1, 1 ], |
| 79 | 'float' => [ 1, 1 ], |
| 80 | 'bool' => [ 1, 1 ], |
| 81 | 'norm' => [ 1, 1 ], |
| 82 | 'ccnorm' => [ 1, 1 ], |
| 83 | 'ccnorm_contains_any' => [ 2, INF ], |
| 84 | 'ccnorm_contains_all' => [ 2, INF ], |
| 85 | 'specialratio' => [ 1, 1 ], |
| 86 | 'rmspecials' => [ 1, 1 ], |
| 87 | 'rmdoubles' => [ 1, 1 ], |
| 88 | 'rmwhitespace' => [ 1, 1 ], |
| 89 | 'count' => [ 1, 2 ], |
| 90 | 'rcount' => [ 1, 2 ], |
| 91 | 'get_matches' => [ 2, 2 ], |
| 92 | 'ip_in_range' => [ 2, 2 ], |
| 93 | 'ip_in_ranges' => [ 2, INF ], |
| 94 | 'contains_any' => [ 2, INF ], |
| 95 | 'contains_all' => [ 2, INF ], |
| 96 | 'equals_to_any' => [ 2, INF ], |
| 97 | 'substr' => [ 2, 3 ], |
| 98 | 'strlen' => [ 1, 1 ], |
| 99 | 'strpos' => [ 2, 3 ], |
| 100 | 'str_replace' => [ 3, 3 ], |
| 101 | 'str_replace_regexp' => [ 3, 3 ], |
| 102 | 'rescape' => [ 1, 1 ], |
| 103 | 'set' => [ 2, 2 ], |
| 104 | 'set_var' => [ 2, 2 ], |
| 105 | 'sanitize' => [ 1, 1 ], |
| 106 | ]; |
| 107 | |
| 108 | // Functions that affect parser state, and shouldn't be cached. |
| 109 | private const ACTIVE_FUNCTIONS = [ |
| 110 | 'funcSetVar', |
| 111 | ]; |
| 112 | |
| 113 | public const KEYWORDS = [ |
| 114 | 'in' => 'keywordIn', |
| 115 | 'like' => 'keywordLike', |
| 116 | 'matches' => 'keywordLike', |
| 117 | 'contains' => 'keywordContains', |
| 118 | 'rlike' => 'keywordRegex', |
| 119 | 'irlike' => 'keywordRegexInsensitive', |
| 120 | 'regex' => 'keywordRegex', |
| 121 | ]; |
| 122 | |
| 123 | /** |
| 124 | * @var bool Are we allowed to use short-circuit evaluation? |
| 125 | */ |
| 126 | private $mAllowShort; |
| 127 | |
| 128 | /** |
| 129 | * @var VariableHolder |
| 130 | */ |
| 131 | private $mVariables; |
| 132 | /** |
| 133 | * @var int The current amount of conditions being consumed |
| 134 | */ |
| 135 | private $mCondCount; |
| 136 | /** |
| 137 | * @var bool Whether the condition limit is enabled. |
| 138 | */ |
| 139 | private $condLimitEnabled = true; |
| 140 | /** |
| 141 | * @var string|null The ID of the filter being parsed, if available. Can also be "global-$ID" |
| 142 | */ |
| 143 | private $mFilter; |
| 144 | /** |
| 145 | * @var bool Whether we can allow retrieving _builtin_ variables not included in $this->mVariables |
| 146 | */ |
| 147 | private $allowMissingVariables = false; |
| 148 | |
| 149 | /** |
| 150 | * @var BagOStuff Used to cache the AST and the tokens |
| 151 | */ |
| 152 | private $cache; |
| 153 | /** |
| 154 | * @var bool Whether the AST was retrieved from cache |
| 155 | */ |
| 156 | private $fromCache = false; |
| 157 | /** |
| 158 | * @var LoggerInterface Used for debugging |
| 159 | */ |
| 160 | private $logger; |
| 161 | /** |
| 162 | * @var Language Content language, used for language-dependent functions |
| 163 | */ |
| 164 | private $contLang; |
| 165 | /** |
| 166 | * @var IBufferingStatsdDataFactory |
| 167 | */ |
| 168 | private $statsd; |
| 169 | |
| 170 | /** @var KeywordsManager */ |
| 171 | private $keywordsManager; |
| 172 | |
| 173 | /** @var VariablesManager */ |
| 174 | private $varManager; |
| 175 | |
| 176 | /** @var int */ |
| 177 | private $conditionsLimit; |
| 178 | |
| 179 | /** @var UserVisibleWarning[] */ |
| 180 | private $warnings = []; |
| 181 | |
| 182 | /** |
| 183 | * @var array Cached results of functions |
| 184 | */ |
| 185 | private $funcCache = []; |
| 186 | |
| 187 | /** |
| 188 | * @var Equivset |
| 189 | */ |
| 190 | private $equivset; |
| 191 | |
| 192 | /** |
| 193 | * Create a new instance |
| 194 | * |
| 195 | * @param Language $contLang Content language, used for language-dependent function |
| 196 | * @param BagOStuff $cache Used to cache the AST and the tokens |
| 197 | * @param LoggerInterface $logger Used for debugging |
| 198 | * @param KeywordsManager $keywordsManager |
| 199 | * @param VariablesManager $varManager |
| 200 | * @param IBufferingStatsdDataFactory $statsdDataFactory |
| 201 | * @param Equivset $equivset |
| 202 | * @param int $conditionsLimit |
| 203 | * @param VariableHolder|null $vars |
| 204 | */ |
| 205 | public function __construct( |
| 206 | Language $contLang, |
| 207 | BagOStuff $cache, |
| 208 | LoggerInterface $logger, |
| 209 | KeywordsManager $keywordsManager, |
| 210 | VariablesManager $varManager, |
| 211 | IBufferingStatsdDataFactory $statsdDataFactory, |
| 212 | Equivset $equivset, |
| 213 | int $conditionsLimit, |
| 214 | VariableHolder $vars = null |
| 215 | ) { |
| 216 | $this->contLang = $contLang; |
| 217 | $this->cache = $cache; |
| 218 | $this->logger = $logger; |
| 219 | $this->statsd = $statsdDataFactory; |
| 220 | $this->keywordsManager = $keywordsManager; |
| 221 | $this->varManager = $varManager; |
| 222 | $this->equivset = $equivset; |
| 223 | $this->conditionsLimit = $conditionsLimit; |
| 224 | $this->resetState(); |
| 225 | if ( $vars ) { |
| 226 | $this->mVariables = $vars; |
| 227 | } |
| 228 | } |
| 229 | |
| 230 | /** |
| 231 | * For use in batch scripts and the like |
| 232 | * |
| 233 | * @param bool $enable True to enable the limit, false to disable it |
| 234 | */ |
| 235 | public function toggleConditionLimit( $enable ) { |
| 236 | $this->condLimitEnabled = $enable; |
| 237 | } |
| 238 | |
| 239 | /** |
| 240 | * @throws ConditionLimitException |
| 241 | */ |
| 242 | private function raiseCondCount() { |
| 243 | $this->mCondCount++; |