Use the (faster) native mb_string functions where available, and fallbacks where not.

3 files changed, 37 insertions, 31 deletions

diff --git a/includes/functions/functions_export.php b/includes/functions/functions_export.php
index 29fd732ae8..5cab08305f 100644
--- a/includes/functions/functions_export.php
+++ b/includes/functions/functions_export.php
@@ -38,10 +38,9 @@ function reformat_record_export($rec) {
 		// Split long lines
 		// The total length of a GEDCOM line, including level number, cross-reference number,
 		// tag, value, delimiters, and terminator, must not exceed 255 (wide) characters.
-		// Use quick strlen() check before using slower WT_I18N::strlen() check
-		if (strlen($line)>WT_GEDCOM_LINE_LENGTH && WT_I18N::strlen($line)>WT_GEDCOM_LINE_LENGTH) {
+		if (mb_strlen($line) > WT_GEDCOM_LINE_LENGTH) {
 			list($level, $tag)=explode(' ', $line, 3);
-			if ($tag!='CONT' && $tag!='CONC') {
+			if ($tag != 'CONT' && $tag != 'CONC') {
 				$level++;
 			}
 			do {
@@ -49,31 +48,31 @@ function reformat_record_export($rec) {
 				$pos=WT_GEDCOM_LINE_LENGTH;
 				if ($WORD_WRAPPED_NOTES) {
 					// Split on a space, and remove it (for compatibility with some desktop apps)
-					while ($pos && WT_I18N::substr($line, $pos-1, 1)!=' ') {
+					while ($pos && mb_substr($line, $pos-1, 1)!=' ') {
 						--$pos;
 					}
-					if ($pos==strpos($line, ' ', 3)+1) {
+					if ($pos == strpos($line, ' ', 3) + 1) {
 						// No spaces in the data! Can’t split it :-(
 						break;
 					} else {
-						$newrec.=WT_I18N::substr($line, 0, $pos-1).WT_EOL;
-						$line=$level.' CONC '.WT_I18N::substr($line, $pos);
+						$newrec .= mb_substr($line, 0, $pos - 1).WT_EOL;
+						$line=$level.' CONC ' . mb_substr($line, $pos);
 					}
 				} else {
 					// Split on a non-space (standard gedcom behaviour)
-					while ($pos && WT_I18N::substr($line, $pos-1, 1)==' ') {
+					while ($pos && mb_substr($line, $pos-1, 1) == ' ') {
 						--$pos;
 					}
-					if ($pos==strpos($line, ' ', 3)) {
+					if ($pos == strpos($line, ' ', 3)) {
 						// No non-spaces in the data! Can’t split it :-(
 						break;
 					}
-					$newrec.=WT_I18N::substr($line, 0, $pos).WT_EOL;
-					$line=$level.' CONC '.WT_I18N::substr($line, $pos);
+					$newrec .= mb_substr($line, 0, $pos) . WT_EOL;
+					$line = $level . ' CONC ' . mb_substr($line, $pos);
 				}
-			} while (WT_I18N::strlen($line)>WT_GEDCOM_LINE_LENGTH);
+			} while (mb_strlen($line) > WT_GEDCOM_LINE_LENGTH);
 		}
-		$newrec.=$line.WT_EOL;
+		$newrec .= $line . WT_EOL;
 	}
 	return $newrec;
 }
diff --git a/includes/functions/functions_rtl.php b/includes/functions/functions_rtl.php
index 0a7a249a96..019a0308b9 100644
--- a/includes/functions/functions_rtl.php
+++ b/includes/functions/functions_rtl.php
@@ -1038,29 +1038,29 @@ function finishCurrentSpan(&$result, $theEnd=false) {
 function utf8_wordwrap($string, $width=75, $sep="\n", $cut=false) {
 	$out='';
 	while ($string) {
-		if (WT_I18N::strlen($string) <= $width){ //Do not wrap any text that is less than the output area.
-			$out.=$string;
-			$string='';
+		if (mb_strlen($string) <= $width){ //Do not wrap any text that is less than the output area.
+			$out .= $string;
+			$string = '';
 		} else {
-			$sub1=WT_I18N::substr($string, 0, $width+1);
-			if (WT_I18N::substr($string,WT_I18N::strlen($sub1)-1,1)==' ') //include words that end by a space immediately after the area.
-				$sub=$sub1;
+			$sub1 = mb_substr($string, 0, $width+1);
+			if (mb_substr($string, mb_strlen($sub1)-1, 1) == ' ') //include words that end by a space immediately after the area.
+				$sub = $sub1;
 			else
-				$sub=WT_I18N::substr($string, 0, $width);
-			$spacepos=strrpos($sub, ' ');
-			if ($spacepos==false) {
+				$sub = mb_substr($string, 0, $width);
+			$spacepos = strrpos($sub, ' ');
+			if ($spacepos == false) {
 				// No space on line?
 				if ($cut) {
-					$out.=$sub.$sep;
-					$string=WT_I18N::substr($string, WT_I18N::strlen($sub));
+					$out .= $sub . $sep;
+					$string = mb_substr($string, mb_strlen($sub));
 				} else {
-					$spacepos=strpos($string, ' ');
-					if ($spacepos==false) {
-						$out.=$string;
-						$string='';
+					$spacepos = strpos($string, ' ');
+					if ($spacepos == false) {
+						$out .= $string;
+						$string = '';
 					} else {
-						$out.=substr($string, 0, $spacepos).$sep;
-						$string=substr($string, $spacepos+1);
+						$out .= substr($string, 0, $spacepos).$sep;
+						$string = substr($string, $spacepos + 1);
 					}
 				}
 			} else {
diff --git a/includes/session.php b/includes/session.php
index 0cf4fd2180..cf5242a6c9 100644
--- a/includes/session.php
+++ b/includes/session.php
@@ -185,6 +185,14 @@ if (!ini_get('date.timezone')) {
 	date_default_timezone_set(@date_default_timezone_get());
 }
 
+// Use the patchwork/utf8 library to:
+// set all PHP defaults to UTF-8
+// create shims for missing mb_string functions such as mb_strlen()
+// check that requests are valid UTF-8
+\Patchwork\Utf8\Bootup::initAll();             // Enables the portablity layer and configures PHP for UTF-8
+\Patchwork\Utf8\Bootup::filterRequestUri();    // Redirects to an UTF-8 encoded URL if it's not already the case
+\Patchwork\Utf8\Bootup::filterRequestInputs(); // Normalizes HTTP inputs to UTF-8 NFC
+
 // Split the request protocol://host:port/path/to/script.php?var=value into parts
 // WT_SERVER_NAME  = protocol://host:port
 // WT_SCRIPT_PATH  = /path/to/   (begins and ends with /)
@@ -227,7 +235,6 @@ if (!isset($_SERVER['HTTP_USER_AGENT'])) {
 // Common functions
 require WT_ROOT.'includes/functions/functions.php';
 require WT_ROOT.'includes/functions/functions_db.php';
-// TODO: Not all pages require all of these.  Only load them in scripts that need them?
 require WT_ROOT.'includes/functions/functions_print.php';
 require WT_ROOT.'includes/functions/functions_mediadb.php';
 require WT_ROOT.'includes/functions/functions_date.php';