Scan for more complex messages (constants and concatenations in arguments) #110
Description
This is not an issue, but your code could be enhanced based on the works i did.
The following code will scan ::t functions and for the first 2 arguments replace concats and constants by their correct value. All the scanning is done with Regex expressions.
It will correctly resolve:
Yii::t('appMenu', self::LBL_A);
Yii::t('appMenu', self::LBL_A, otherArg);
Yii::t('appMenu', OtherClass::LBL_A);
Yii::t('appMenu', OtherClassUsedAs::LBL_A);
Yii::t('appMenu', selfImplementingClass::LBL_A);
Yii::t('appMenu', self::LBL_A . 'xxxx' );
Yii::t( self::LBL_A . 'appMenu', OtherClass::LBL_B . 'xxxx' . OtherClassUsedAs::LBL_C);
The following items are taken into account to resolve constants:
- namespace ...;
- use ...;
- use ... as ...;
- class ... (implements ...);
- interface ...;
It works quite well and fast on a large project.
// which folder should be scanned
private $scanroot = '@_protected' . DIRECTORY_SEPARATOR;
// list of the php function for translating messages.
private $phpTranslators = ['::t'];
// list of file extensions that contain language elements.
private $phpPatterns = ['*.php'];
// these categories won't be included in the language database.
private $ignoredCategories = ['yii'];
// these files will not be processed.
private $ignoredItems = [
'.gitignore',
'/messages',
'/vendor',
'/frontend/assets',
'runtime',
'bower',
'nikic',
];
// Regular expression to match PHP namespace definitions.
public $patternNamespace = '/namespace\s*(.+?)\s*;/i';
// Regular expression to match PHP class definitions.
public $patternClass = '/(?<!(\/\/\s)|\*\s|\/\*\*\s)(?:class|interface)\s*(.+?)\s/i';
// Regular expression to match PHP Implements definitions.
public $patternImplements = '/class\s*.+?\simplements\s(.+?)\s/i';
// Regular expression to match PHP const assignments.
public $patternConst = '/const\s*(.+?)\s*=\s*(.+);/i';
// Regular expression to match PHP use and use as definitions.
public $patternUse = '/use\s*(.+?\\<Searchstring>)\s*;/i';
public $patternUseas = '/use\s*(.+?)\s*as\s*<Searchstring>\s*;/i';
// Regular expression to match PHP Yii::t functions.
public $patternPhp = '/::t\s*\(\s*(((["\'])(?:(?=(\\\\?))\4.)*?\3|[\w\d:$>-]*?|[\s\.]*?)+?)\s*\,\s*(((["\'])(?:(?=(\\\\?))\8.)*?\7|[\w\d:$>-]*?|[\s\.]*?)+?)\s*[,\)]/';
// Regular expression to split up PHP concat "./dot" into parts
public $patternConcatSplit = '/(["\'])(?:\\\\.|[^\1])*?\1|[^\s\.]+/';
// holds all the const elements
private $_constElements = [];
// holds all the language elements
private $_languageElements = [];
/**
* Scan source code for messages.
*
* @return \yii\web\Response
*/
public function actionScan()
{
// FILES LIST
$rootpath = Yii::getAlias($this->scanroot);
$files = FileHelper::findFiles($rootpath, [
'except' => $this->ignoredItems,
'only' => $this->phpPatterns,
]);
// first fetch constants
$implementstack = [];
foreach($files as $file) {
$text = file_get_contents($file);
$namespace = $this->regexFirstMatch($this->patternNamespace, $text);
if ($namespace) {
$class = $this->regexSecondMatch($this->patternClass, $text);
$implements = $this->regexFirstMatch($this->patternImplements, $text);
$namespaceclass = $namespace.'\\'.$class;
$namespaceimplements = $namespace.'\\'.$implements;
preg_match_all($this->patternConst, $text, $matches, PREG_SET_ORDER, 0);
foreach($matches as $match) {
$const = $match[1];
$msg = $match[2];
$this->_constElements[$namespaceclass.'\\'.$const] = $msg;
}
if ($implements) {
$implementstack[$namespaceclass] = $namespaceimplements;
}
}
}
// apply all the implements
foreach ($implementstack as $kis => $vis) {
foreach($this->_constElements as $constname => $msg) {
if (0 === strpos($constname.'\\', $vis.'\\')) {
$this->_constElements[str_replace($vis, $kis, $constname)] = $msg;
}
}
}
// dd($this->_constElements);
// parse all the files contains a namespace definition
foreach($files as $file) {
$text = file_get_contents($file);
$namespace = $this->regexFirstMatch($this->patternNamespace, $text);
// process files only if we have a namespace
if ($namespace) {
$class = $this->regexSecondMatch($this->patternClass, $text);
$implements = $this->regexFirstMatch($this->patternImplements, $text);
$namespaceclass = $namespace.'\\'.$class;
$namespaceimplements = $namespace.'\\'.$implements;
if ($this->containsTranslator($this->phpTranslators, $text)) {
preg_match_all($this->patternPhp, $text, $matches, PREG_SET_ORDER, 0);
foreach($matches as $match) {
$cat = $match[1];
$msg = $match[5];
$lines = file($file);
$line_number = false;
while (list($key, $line) = each($lines) and !$line_number) {
$line_number = (strpos($line, $match[0]) !== FALSE) ? $key + 1 : $line_number;
}
// split up the category by . and replace constants
$cat = $this->replaceConst($cat, $namespaceclass, $text);
$msg = $this->replaceConst($msg, $namespaceclass, $text);
if (!in_array($cat, $this->ignoredCategories)) {
$this->_languageElements[$cat][$msg][] = $namespaceclass.':'.$line_number;
}
}
}
}
}
dd($this->_languageElements);
return $this->redirect(Yii::$app->request->referrer);
}
protected function regexFirstMatch($pattern, &$subject) {
preg_match($pattern, $subject, $match);
if (count($match)>0) {
return $match[1];
}
}
protected function regexSecondMatch($pattern, &$subject) {
preg_match($pattern, $subject, $match);
if (count($match)>0) {
return $match[2];
}
}
protected function replaceConst(string &$argument, string $namespaceclass, string &$text) :string
{
preg_match_all($this->patternConcatSplit, $argument, $argumentdotparts, PREG_PATTERN_ORDER, 0);
$argumentdotparts = $argumentdotparts[0];
foreach ($argumentdotparts as $adkey => $adpart) {
$constparts = explode('::', $adpart);
if (count($constparts)>1) {
// we have a constant, replace it with value
if ($constparts[0] == 'self') {
// const within self::
$constparts[0] = $namespaceclass;
$constname = implode('\\', $constparts);
if (isset($this->_constElements[$constname])) {
// self refers to itself
$argumentdotparts[$adkey] = $this->_constElements[$constname];
}
} else {
// const within some other class
$otherclass = $constparts[0];
$useclass = $this->regexFirstMatch(str_replace('<Searchstring>', $otherclass, $this->patternUse), $text);
$constparts[0] = $useclass;
$constname = implode('\\', $constparts);
if (isset($this->_constElements[$constname])) {
// self refers to use class
$argumentdotparts[$adkey] = $this->_constElements[$constname];
} else {
// self refers to use as class
$useasclass = $this->regexFirstMatch(str_replace('<Searchstring>', $otherclass, $this->patternUseas), $text);
$constparts[0] = $useasclass;
$constname = implode('\\', $constparts);
if (isset($this->_constElements[$constname])) {
// self refers to useas class
$argumentdotparts[$adkey] = $this->_constElements[$constname];
}
}
}
$constname = implode('\\', $constparts);
if (isset($this->_constElements[$constname])) {
$argumentdotparts[$adkey] = $this->_constElements[$constname];
}
}
$argumentdotparts[$adkey] = trim($argumentdotparts[$adkey],'"');
$argumentdotparts[$adkey] = trim($argumentdotparts[$adkey],"'");
}
return implode('', $argumentdotparts);
}
/**
* Determines whether the file has any of the translators.
*
* @param string[] $translators Array of translator patterns to search (for example: `['::t']`).
* @param string $file Path of the file.
*
* @return bool
*/
protected function containsTranslator($translators, &$text)
{
return preg_match(
'#(' . implode('\s*\()|(', array_map('preg_quote', $translators)) . '\s*\()#i',
$text
) > 0;
}