deblan/php-censor
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Fixed build log for invalid encoded utf8 characters. Issue #145.

Browse source
This commit is contained in:
SimonHeimberg 2018-02-03 13:35:58 +01:00
parent 45f8102ea5
commit 48e81efb86
1 changed files with 24 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

36
src/PHPCensor/Helper/CommandExecutor.php
View file

@ -98,26 +98,22 @@ class CommandExecutor implements CommandExecutorInterface
$pipes = [];
$process = proc_open($command, $descriptorSpec, $pipes, $this->buildPath, null);
$this->lastOutput = '';
$this->lastError = '';
$lastOutput = '';
$lastError = '';
if (is_resource($process)) {
fclose($pipes[0]);
list($this->lastOutput, $this->lastError) = $this->readAlternating([$pipes[1], $pipes[2]]);
list($lastOutput, $lastError) = $this->readAlternating([$pipes[1], $pipes[2]]);
$status = proc_close($process);
$lastOutput = $this->replaceIllegalCharacters($lastOutput);
$lastError = $this->replaceIllegalCharacters($lastError);
}
$regexp = '/[\x00-\x08\x10\x0B\x0C\x0E-\x19\x7F]' .
'|[\x00-\x7F][\x80-\xBF]+' .
'|([\xC0\xC1]|[\xF0-\xFF])[\x80-\xBF]*' .
'|[\xC2-\xDF]((?![\x80-\xBF])|[\x80-\xBF]{2,})' .
'|[\xE0-\xEF](([\x80-\xBF](?![\x80-\xBF]))|(?![\x80-\xBF]{2})|[\x80-\xBF]{3,})/S';
$this->lastOutput = preg_replace($regexp, '<27>', $this->lastOutput);
$this->lastError = preg_replace($regexp, '<27>', $this->lastError);
$this->lastOutput = array_filter(explode(PHP_EOL, $this->lastOutput));
$this->lastOutput = array_filter(explode(PHP_EOL, $lastOutput));
$this->lastError = $lastError;
$shouldOutput = ($this->logExecOutput && ($this->verbose || $status != 0));
@ -171,6 +167,22 @@ class CommandExecutor implements CommandExecutorInterface
return $outputs;
}
private static function replaceIllegalCharacters($utf8String)
{
$substCharCode = 65533;
mb_substitute_character($substCharCode);
$legalUtf8String = mb_convert_encoding($utf8String, 'utf8', 'utf8');
$regexp = '/[\x00-\x08\x10\x0B\x0C\x0E-\x19\x7F]' .
'|[\x00-\x7F][\x80-\xBF]+' .
'|([\xC0\xC1]|[\xF0-\xFF])[\x80-\xBF]*' .
'|[\xC2-\xDF]((?![\x80-\xBF])|[\x80-\xBF]{2,})' .
'|[\xE0-\xEF](([\x80-\xBF](?![\x80-\xBF]))|(?![\x80-\xBF]{2})|[\x80-\xBF]{3,})/S';
$cleanUtf8String = preg_replace($regexp, chr($substCharCode), $legalUtf8String);
return $cleanUtf8String;
}
/**
* Returns the output from the last command run.
*