require_once(SM_PATH . 'functions/global.php');
/**
- * Decodes a string to the internal encoding from the given charset
+ * Converts string from given charset to charset, that can be displayed by user translation.
+ *
+ * Function by default returns html encoded strings, if translation uses different encoding.
+ * If Japanese translation is used - function returns string converted to euc-jp
+ * If iconv or recode functions are enabled and translation uses utf-8 - function returns utf-8 encoded string.
+ * If $charset is not supported - function returns unconverted string.
*
+ * sanitizing of html tags is also done by this function.
+ *
* @param string $charset
* @param string $string Text to be decoded
- * @return string Decoded text
+ * @return string decoded string
*/
function charset_decode ($charset, $string) {
global $languages, $squirrelmail_language, $default_charset;
if (! isset($agresive_decoding) || $agresive_decoding=="" ) {
$agresive_decoding=false; }
- if (ereg('iso-8859-([[:digit:]]+)', $charset, $res)) {
- if ($res[1] == '1') {
- include_once(SM_PATH . 'functions/decode/iso8859-1.php');
- $ret = charset_decode_iso8859_1 ($string);
- } else if ($res[1] == '2') {
- include_once(SM_PATH . 'functions/decode/iso8859-2.php');
- $ret = charset_decode_iso8859_2 ($string);
- } else if ($res[1] == '3') {
- include_once(SM_PATH . 'functions/decode/iso8859-3.php');
- $ret = charset_decode_iso8859_3 ($string);
- } else if ($res[1] == '4') {
- include_once(SM_PATH . 'functions/decode/iso8859-4.php');
- $ret = charset_decode_iso8859_4 ($string);
- } else if ($res[1] == '5') {
- include_once(SM_PATH . 'functions/decode/iso8859-5.php');
- $ret = charset_decode_iso8859_5 ($string);
- } else if ($res[1] == '6') {
- include_once(SM_PATH . 'functions/decode/iso8859-6.php');
- $ret = charset_decode_iso8859_6 ($string);
- } else if ($res[1] == '7') {
- include_once(SM_PATH . 'functions/decode/iso8859-7.php');
- $ret = charset_decode_iso8859_7 ($string);
- } else if ($res[1] == '8') {
- include_once(SM_PATH . 'functions/decode/iso8859-8.php');
- $ret = charset_decode_iso8859_8 ($string);
- } else if ($res[1] == '9') {
- include_once(SM_PATH . 'functions/decode/iso8859-9.php');
- $ret = charset_decode_iso8859_9 ($string);
- } else if ($res[1] == '10') {
- include_once(SM_PATH . 'functions/decode/iso8859-10.php');
- $ret = charset_decode_iso8859_10 ($string);
- } else if ($res[1] == '11') {
- include_once(SM_PATH . 'functions/decode/iso8859-11.php');
- $ret = charset_decode_iso8859_11 ($string);
- } else if ($res[1] == '13') {
- include_once(SM_PATH . 'functions/decode/iso8859-13.php');
- $ret = charset_decode_iso8859_13 ($string);
- } else if ($res[1] == '14') {
- include_once(SM_PATH . 'functions/decode/iso8859-14.php');
- $ret = charset_decode_iso8859_14 ($string);
- } else if ($res[1] == '15') {
- include_once(SM_PATH . 'functions/decode/iso8859-15.php');
- $ret = charset_decode_iso8859_15 ($string);
- } else if ($res[1] == '16') {
- include_once(SM_PATH . 'functions/decode/iso8859-16.php');
- $ret = charset_decode_iso8859_16 ($string);
- } else {
- $ret = charset_decode_iso_8859_default ($string);
- }
- } else if ($charset == 'ns_4551-1') {
- $ret = charset_decode_ns_4551_1 ($string);
- } else if ($charset == 'koi8-r') {
- include_once(SM_PATH . 'functions/decode/koi8-r.php');
- $ret = charset_decode_koi8r ($string);
- } else if ($charset == 'koi8-u') {
- include_once(SM_PATH . 'functions/decode/koi8-u.php');
- $ret = charset_decode_koi8u ($string);
- } else if ($charset == 'windows-1250') {
- include_once(SM_PATH . 'functions/decode/cp1250.php');
- $ret = charset_decode_cp1250 ($string);
- } else if ($charset == 'windows-1251') {
- include_once(SM_PATH . 'functions/decode/cp1251.php');
- $ret = charset_decode_cp1251 ($string);
- } else if ($charset == 'windows-1252') {
- include_once(SM_PATH . 'functions/decode/cp1252.php');
- $ret = charset_decode_cp1252 ($string);
- } else if ($charset == 'windows-1253') {
- include_once(SM_PATH . 'functions/decode/cp1253.php');
- $ret = charset_decode_cp1253 ($string);
- } else if ($charset == 'windows-1254') {
- include_once(SM_PATH . 'functions/decode/cp1254.php');
- $ret = charset_decode_cp1254 ($string);
- } else if ($charset == 'windows-1255') {
- include_once(SM_PATH . 'functions/decode/cp1255.php');
- $ret = charset_decode_cp1255 ($string);
- } else if ($charset == 'windows-1256') {
- include_once(SM_PATH . 'functions/decode/cp1256.php');
- $ret = charset_decode_cp1256 ($string);
- } else if ($charset == 'windows-1257') {
- include_once(SM_PATH . 'functions/decode/cp1257.php');
- $ret = charset_decode_cp1257 ($string);
- } else if ($charset == 'windows-1258') {
- include_once(SM_PATH . 'functions/decode/cp1258.php');
- $ret = charset_decode_cp1258 ($string);
- } else if ($charset == 'x-mac-roman') {
- include_once(SM_PATH . 'functions/decode/cp10000.php');
- $ret = charset_decode_cp10000 ($string);
- } else if ($charset == 'x-mac-greek') {
- include_once(SM_PATH . 'functions/decode/cp10006.php');
- $ret = charset_decode_cp10006 ($string);
- } else if ($charset == 'x-mac-cyrillic') {
- include_once(SM_PATH . 'functions/decode/cp10007.php');
- $ret = charset_decode_cp10007 ($string);
- } else if ($charset == 'x-mac-ukrainian') {
- include_once(SM_PATH . 'functions/decode/cp10017.php');
- $ret = charset_decode_cp10017 ($string);
- } else if ($charset == 'x-mac-centraleurroman') {
- include_once(SM_PATH . 'functions/decode/cp10029.php');
- $ret = charset_decode_cp10029 ($string);
- } else if ($charset == 'x-mac-icelandic') {
- include_once(SM_PATH . 'functions/decode/cp10079.php');
- $ret = charset_decode_cp10079 ($string);
- } else if ($charset == 'x-mac-turkish') {
- include_once(SM_PATH . 'functions/decode/cp10081.php');
- $ret = charset_decode_cp10081 ($string);
- } else if ($charset == 'ibm855') {
- include_once(SM_PATH . 'functions/decode/cp855.php');
- $ret = charset_decode_cp855 ($string);
- } else if ($charset == 'ibm866') {
- include_once(SM_PATH . 'functions/decode/cp866.php');
- $ret = charset_decode_cp866 ($string);
- } else if ($charset == 'iso-ir-111') {
- include_once(SM_PATH . 'functions/decode/iso-ir-111.php');
- $ret = charset_decode_iso_ir_111 ($string);
- } else if ($charset == 'tis-620') {
- include_once(SM_PATH . 'functions/decode/tis620.php');
- $ret = charset_decode_tis620 ($string);
- } else if ($charset == 'big5' and $agresive_decoding ) {
- include_once(SM_PATH . 'functions/decode/big5.php');
- $ret = charset_decode_big5 ($string);
- } else if ($charset == 'gb2312' and $agresive_decoding ) {
- include_once(SM_PATH . 'functions/decode/gb2312.php');
- $ret = charset_decode_gb2312 ($string);
- } else if ($charset == 'utf-8' && $squirrelmail_language != 'ja_JP') {
- include_once(SM_PATH . 'functions/decode/utf-8.php');
- $ret = charset_decode_utf8 ($string);
+ $decode=fixcharset($charset);
+ $decodefile=SM_PATH . 'functions/decode/' . $decode . '.php';
+ if (file_exists($decodefile)) {
+ include_once($decodefile);
+ $ret = call_user_func('charset_decode_'.$decode, $string);
} else {
- $ret = $string;
+ $ret = $string;
}
return( $ret );
}
+
+/**
+ * Makes charset name suitable for decoding cycles
+ *
+ * @param string $charset Name of charset
+ * @return string $charset Adjusted name of charset
+ */
+function fixcharset($charset) {
+ // minus removed from function names
+ $charset=str_replace('-','_',$charset);
+
+ // windows-125x and cp125x charsets
+ $charset=str_replace('windows_','cp',$charset);
+ // ibm > cp
+ $charset=str_replace('ibm','cp',$charset);
-/* Remove all 8 bit characters from all other ISO-8859 character sets */
+ // iso-8859-8-i -> iso-8859-8
+ // use same cycle until I'll find differences
+ $charset=str_replace('iso_8859_8_i','iso_8859_8',$charset);
+
+ return $charset;
+}
+
+/**
+ * 8bit cleanup functions.
+ *
+ * Replaces all 8 bit characters from ISO-8859 character sets with '?'
+ * Legacy function used for unsupported ISO-8859 charsets
+ *
+ * @param string $string string that has to be cleaned
+ * @return string cleaned string
+ */
function charset_decode_iso_8859_default ($string) {
return (strtr($string, "\240\241\242\243\244\245\246\247".
"\250\251\252\253\254\255\256\257".
}
-/*
+/**
+ * ns_4551_1 decoding function
+ *
* This is the same as ISO-646-NO and is used by some
* Microsoft programs when sending Norwegian characters
+ *
+ * @param string $string
+ * @return string
*/
function charset_decode_ns_4551_1 ($string) {
/*
}
-/*
+/**
* Set up the language to be output
* if $do_search is true, then scan the browser information
* for a possible language that we know
+ *
+ * Function sets system locale environment (LC_ALL, LANG, LANGUAGE),
+ * gettext translation bindings and html header information.
+ *
+ * Function returns error codes, if there is some fatal error.
+ * 0 = no error,
+ * 1 = mbstring support is not present,
+ * 2 = mbstring support is not present, user's translation reverted to en_US.
+ *
+ * @param string $sm_language translation used by user's interface
+ * @param bool $do_search use browser's preferred language detection functions. Defaults to false.
+ * @param bool $default set $sm_language to $squirrelmail_default_language if language detection fails or language is not set. Defaults to false.
+ * @return int function execution error codes.
*/
function set_up_language($sm_language, $do_search = false, $default = false) {
static $SetupAlready = 0;
global $use_gettext, $languages,
$squirrelmail_language, $squirrelmail_default_language,
- $sm_notAlias;
+ $sm_notAlias, $username, $data_dir;
if ($SetupAlready) {
return;
bindtextdomain( 'squirrelmail', SM_PATH . 'locale/' );
textdomain( 'squirrelmail' );
if (function_exists('bind_textdomain_codeset')) {
- bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] );
+ if ($sm_notAlias == 'ja_JP') {
+ bind_textdomain_codeset ("squirrelmail", 'EUC-JP');
+ } else {
+ bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] );
+ }
}
if (isset($languages[$sm_notAlias]['LOCALE'])){
$longlocale=$languages[$sm_notAlias]['LOCALE'];
putenv( "LANGUAGE=$longlocale" );
}
setlocale(LC_ALL, $longlocale);
+
+ // Set text direction/alignment variables
+ if (isset($languages[$sm_notAlias]['DIR']) &&
+ $languages[$sm_notAlias]['DIR'] == 'rtl') {
+ $text_direction='rtl';
+ $left_align='right';
+ $right_align='left';
+ } else {
+ $text_direction='ltr';
+ $left_align='left';
+ $right_align='right';
+ }
+
$squirrelmail_language = $sm_notAlias;
- if ($squirrelmail_language == 'ja_JP' && function_exists('mb_detect_encoding') ) {
+ if ($squirrelmail_language == 'ja_JP') {
header ('Content-Type: text/html; charset=EUC-JP');
if (!function_exists('mb_internal_encoding')) {
- echo _("You need to have php4 installed with the multibyte string function enabled (using configure option --enable-mbstring).");
+ // Error messages can't be displayed here
+ $error = 1;
+ // Revert to English if possible.
+ if (function_exists('setPref') && $username!='' && $data_dir!="") {
+ setPref($data_dir, $username, 'language', "en_US");
+ $error = 2;
+ }
+ // stop further execution in order not to get php errors on mb_internal_encoding().
+ return $error;
}
if (function_exists('mb_language')) {
mb_language('Japanese');
header( 'Content-Type: text/html; charset=' . $languages[$sm_notAlias]['CHARSET'] );
}
}
+ return 0;
}
+/**
+ * Sets default_charset variable according to the one that is used by user's translations.
+ *
+ * Function changes global $default_charset variable in order to be sure, that it
+ * contains charset used by user's translation. Sanity of $squirrelmail_default_language
+ * and $default_charset combination provided in SquirrelMail config is also tested.
+ *
+ * There can be a $default_charset setting in the
+ * config.php file, but the user may have a different language
+ * selected for a user interface. This function checks the
+ * language selected by the user and tags the outgoing messages
+ * with the appropriate charset corresponding to the language
+ * selection. This is "more right" (tm), than just stamping the
+ * message blindly with the system-wide $default_charset.
+ */
function set_my_charset(){
-
- /*
- * There can be a $default_charset setting in the
- * config.php file, but the user may have a different language
- * selected for a user interface. This function checks the
- * language selected by the user and tags the outgoing messages
- * with the appropriate charset corresponding to the language
- * selection. This is "more right" (tm), than just stamping the
- * message blindly with the system-wide $default_charset.
- */
global $data_dir, $username, $default_charset, $languages, $squirrelmail_default_language;
$my_language = getPref($data_dir, $username, 'language');
$squirrelmail_language = '';
}
-/* This array specifies the available languages. */
+/**
+ * Array specifies the available translations.
+ *
+ * Structure of array:
+ * $languages['language']['variable'] = 'value'
+ *
+ * Possible 'variable' names:
+ * NAME - Translation name in English
+ * CHARSET - Encoding used by translation
+ * ALIAS - used when 'language' is only short name and 'value' should provide long language name
+ * ALTNAME - Native translation name. Any 8bit symbols must be html encoded.
+ * LOCALE - Full locale name (in xx_XX.charset format)
+ * DIR - Text direction. Used to define Right-to-Left languages. Possible values 'rtl' or 'ltr'. If undefined - defaults to 'ltr'
+ * XTRA_CODE - translation uses special functions. 'value' provides name of that extra function
+ *
+ * Each 'language' definition requires NAME+CHARSET or ALIAS variables.
+ *
+ * @name $languages
+ * @global $languages
+ */
$languages['bg_BG']['NAME'] = 'Bulgarian';
$languages['bg_BG']['ALTNAME'] = 'Български';
$languages['bg_BG']['CHARSET'] = 'windows-1251';
$languages['ja_JP']['NAME'] = 'Japanese';
$languages['ja_JP']['ALTNAME'] = '日本語';
$languages['ja_JP']['CHARSET'] = 'iso-2022-jp';
+$languages['ja_JP']['LOCALE'] = 'ja_JP.EUC-JP';
$languages['ja_JP']['XTRA_CODE'] = 'japanese_charset_xtra';
$languages['ja']['ALIAS'] = 'ja_JP';
}
-/*
+/**
* Japanese charset extra function
*
+ * Action performed by function is defined by first argument.
+ * Default return value is defined by second argument.
+ * Use of third argument depends on action.
+ *
+ * @param string action performed by this function.
+ * possible values:
+ * decode - convert returned string to euc-jp. third argument unused
+ * encode - convert returned string to jis. third argument unused
+ * strimwidth - third argument=$width. trims string to $width symbols.
+ * encodeheader - create base64 encoded header in iso-2022-jp. third argument unused
+ * decodeheader - return human readable string from mime header. string is returned in euc-jp. third argument unused
+ * downloadfilename - third argument $useragent. Arguments provide browser info. Returns shift-jis or euc-jp encoded file name
+ * wordwrap - third argument=$wrap. wraps text at $wrap symbols
+ * utf7-imap_encode - returns string converted from euc-jp to utf7-imap. third argument unused
+ * utf7-imap_decode - returns string converted from utf7-imap to euc-jp. third argument unused
+ * @param string default return value
*/
function japanese_charset_xtra() {
$ret = func_get_arg(1); /* default return value */
}
-/*
- * Korean charset extra function
- * Hangul(Korean Character) Attached File Name Fix.
+/**
+ * Korean charset extra functions
+ *
+ * Action performed by function is defined by first argument.
+ * Default return value is defined by second argument.
+ *
+ * @param string action performed by this function.
+ * possible values:
+ * downloadfilename - Hangul(Korean Character) Attached File Name Fix.
+ * @param string default return value
*/
function korean_charset_xtra() {
}
}
-
return $ret;
}
-/*
+/**
+ * Replaces non-braking spaces inserted by some browsers with regular space
+ *
* This function can be used to replace non-braking space symbols
* that are inserted in forms by some browsers instead of normal
* space symbol.
+ *
+ * @param string $string Text that needs to be cleaned
+ * @param string $charset Charset used in text
+ * @return string Cleaned text
*/
function cleanup_nbsp($string,$charset) {
return str_replace($nbsp,' ',$string);
}
+/**
+ * Function informs if it is safe to convert given charset to the one that is used by user.
+ *
+ * It is safe to use conversion only if user uses utf-8 encoding and when
+ * converted charset is similar to the one that is used by user.
+ *
+ * @param string $input_charset Charset of text that needs to be converted
+ * @return bool is it possible to convert to user's charset
+ */
function is_conversion_safe($input_charset) {
global $languages, $sm_notAlias, $default_charset;
return false;
endswitch;
}
-?>
+?>
\ No newline at end of file