Commit 7889068e authored by Bertrand Gauthier's avatar Bertrand Gauthier
Browse files

Module STepStar : tentative de suppression des caractères unicode qui font... 

Module STepStar : tentative de suppression des caractères unicode qui font planter le parser XML dans les résumés
parent beff3409

module/StepStar/src/StepStar/Command/TransformShellCommand.php

+1 −1
Original line number Diff line number Diff line
@@ -52,7 +52,7 @@ class TransformShellCommand extends ShellCommand 
        $parts = [

            $this->executable,

            $this->verbose ? '-t' : null,

            sprintf("-s:'%s' -xsl:'%s' -o:'%s'", $this->inputFilePath, $this->xslFilePath, $this->outputFilePath),

            sprintf("-s:'%s' -xsl:'%s' -o:'%s' 2>&1", $this->inputFilePath, $this->xslFilePath, $this->outputFilePath),

        ];



        $this->commandLine = implode(' ', array_filter($parts));

module/StepStar/src/StepStar/Service/Xml/XmlService.php

+52 −2
Original line number Diff line number Diff line
@@ -455,8 +455,8 @@ class XmlService 
            self::TITRE_LANGUE => $langue = $metadonnees['langue'] ?? 'fr',

            self::TITRE_TRADUIT => $metadonnees['titreAutreLangue'],

            self::TITRE_TRADUIT_LANGUE => $langue === 'fr' ? 'en' : 'fr',

            self::RESUME_FRANCAIS => $metadonnees['resume'] ?? null,

            self::RESUME_ANGLAIS => $metadonnees['resumeAnglais'] ?? null,

            self::RESUME_FRANCAIS => $this->sanitizeXML($metadonnees['resume'] ?? ''),

            self::RESUME_ANGLAIS => $this->sanitizeXML($metadonnees['resumeAnglais'] ?? ''),



            // contrat doctoral

            self::CONTRAT_DOCTORAL => $contratDoctoral,
@@ -675,4 +675,54 @@ class XmlService 
    {

        return $date ? $date->format('Y-m-d') : null;

    }



    /**

     * Removes invalid characters from a UTF-8 XML string

     *

     * @param string a XML string potentially containing invalid characters

     * @return string

     */

    private function sanitizeXML(string $string): string

    {

        if (!empty($string))

        {

            // remove EOT+NOREP+EOX|EOT+<char> sequence (FatturaPA)

            $string = preg_replace('/(\x{0004}(?:\x{201A}|\x{FFFD})(?:\x{0003}|\x{0004}).)/u', '', $string);



            $regex = '/(

            [\xC0-\xC1] # Invalid UTF-8 Bytes

            | [\xF5-\xFF] # Invalid UTF-8 Bytes

            | \xE0[\x80-\x9F] # Overlong encoding of prior code point

            | \xF0[\x80-\x8F] # Overlong encoding of prior code point

            | [\xC2-\xDF](?![\x80-\xBF]) # Invalid UTF-8 Sequence Start

            | [\xE0-\xEF](?![\x80-\xBF]{2}) # Invalid UTF-8 Sequence Start

            | [\xF0-\xF4](?![\x80-\xBF]{3}) # Invalid UTF-8 Sequence Start

            | (?<=[\x0-\x7F\xF5-\xFF])[\x80-\xBF] # Invalid UTF-8 Sequence Middle

            | (?<![\xC2-\xDF]|[\xE0-\xEF]|[\xE0-\xEF][\x80-\xBF]|[\xF0-\xF4]|[\xF0-\xF4][\x80-\xBF]|[\xF0-\xF4][\x80-\xBF]{2})[\x80-\xBF] # Overlong Sequence

            | (?<=[\xE0-\xEF])[\x80-\xBF](?![\x80-\xBF]) # Short 3 byte sequence

            | (?<=[\xF0-\xF4])[\x80-\xBF](?![\x80-\xBF]{2}) # Short 4 byte sequence

            | (?<=[\xF0-\xF4][\x80-\xBF])[\x80-\xBF](?![\x80-\xBF]) # Short 4 byte sequence (2)

        )/x';

            $string = preg_replace($regex, '', $string);



            $result = "";

            $length = strlen($string);

            for ($i=0; $i < $length; $i++)

            {

                $current = ord($string[$i]);

                if (($current == 0x9) ||

                    ($current == 0xA) ||

                    ($current == 0xD) ||

                    (($current >= 0x20) && ($current <= 0xD7FF)) ||

                    (($current >= 0xE000) && ($current <= 0xFFFD)) ||

                    (($current >= 0x10000) && ($current <= 0x10FFFF)))

                {

                    $result .= chr($current);

                }

            }

            $string = $result;

        }



        return $string;

    }

}
 
 No newline at end of file