SimpleMachines / SMF2.1

other/update_unicode_data.php

Braces +79 added lines, -37 removed lines

@@ -34,14 +34,16 @@ 
 $utf8_arrays['utf8_casefold_maps'] = array('file' => 'CaseFold.php', 'data' => array());
 $utf8_arrays['utf8_default_ignorables'] = array('file' => 'DefaultIgnorables.php', 'data' => array());
 
-foreach ($utf8_arrays as $func_name => $func_info) {
+foreach ($utf8_arrays as $func_name => $func_info)
+{
 	if (!is_file($unicodedir . '/' . $func_info['file']) || !is_writable($unicodedir . '/' . $func_info['file']))
 		die($unicodedir . '/' . $func_info['file'] . ' not found or not writable.');
 }
 
 // We need some of these for further analysis below.
 $derived_normalization_props = array();
-foreach (file($unicode_data_url . '/DerivedNormalizationProps.txt') as $line) {
+foreach (file($unicode_data_url . '/DerivedNormalizationProps.txt') as $line)
+{
 	$line = substr($line, 0, strcspn($line, '#'));
 
 	if (strpos($line, ';') === false)
@@ -49,17 +51,22 @@ 
 
 	$fields = explode(';', $line);
 
-	foreach ($fields as $key => $value) {
+	foreach ($fields as $key => $value)
+	{
 		$fields[$key] = trim($value);
 	}
 
-	if (!isset($derived_normalization_props[$fields[1]])) {
+	if (!isset($derived_normalization_props[$fields[1]]))
+	{
 		$derived_normalization_props[$fields[1]] = array();
 	}
 
-	if (strpos($fields[0], '..') === false) {
+	if (strpos($fields[0], '..') === false)
+	{
 		$entities = array('&#x' . $fields[0] . ';');
-	} else {
+	}
+	else
+	{
 		$entities = array();
 
 		list($start, $end) = explode('..', $fields[0]);
@@ -68,27 +75,35 @@ 
 		$ord_e = hexdec($end);
 
 		$ord = $ord_s;
-		while ($ord <= $ord_e) {
+		while ($ord <= $ord_e)
+		{
 			$entities[] = '&#x' . strtoupper(sprintf('%04s', dechex($ord++))) . ';';
 		}
 	}
 
 	$value = '';
-	if (!isset($fields[2])) {
+	if (!isset($fields[2]))
+	{
 		$value = 'SAME';
-	} elseif (in_array($fields[1], array('FC_NFKC', 'NFKC_CF'))) {
+	}
+	elseif (in_array($fields[1], array('FC_NFKC', 'NFKC_CF')))
+	{
 		$value = trim($fields[2]) !== '' ? '&#x' . str_replace(' ', '; &#x', trim($fields[2])) . ';' : '';
-	} else {
+	}
+	else
+	{
 		$value = $fields[2];
 	}
 
-	foreach ($entities as $entity) {
+	foreach ($entities as $entity)
+	{
 		$derived_normalization_props[$fields[1]][$entity] = $value === 'SAME' ? $entity : $value;
 	}
 }
 
 // Go through all the characters in the Unicode database.
-foreach (file($unicode_data_url . '/UnicodeData.txt') as $line) {
+foreach (file($unicode_data_url . '/UnicodeData.txt') as $line)
+{
 	$fields = explode(';', $line);
 
 	if (!empty($fields[3]))
@@ -109,12 +124,14 @@ 
 	$full_decomposition_maps['&#x' . $fields[0] . ';'] = '&#x' . str_replace(' ', '; &#x', trim(strip_tags($fields[5]))) . ';';
 
 	// Just the canonical decompositions.
-	if (strpos($fields[5], '<') === false) {
+	if (strpos($fields[5], '<') === false)
+	{
 		$utf8_arrays['utf8_normalize_d_maps']['data']['&#x' . $fields[0] . ';'] = '&#x' . str_replace(' ', '; &#x', trim($fields[5])) . ';';
 	}
 }
 
-foreach (file($unicode_data_url . '/CaseFolding.txt') as $line) {
+foreach (file($unicode_data_url . '/CaseFolding.txt') as $line)
+{
 	$line = substr($line, 0, strcspn($line, '#'));
 
 	if (strpos($line, ';') === false)
@@ -122,12 +139,14 @@ 
 
 	$fields = explode(';', $line);
 
-	foreach ($fields as $key => $value) {
+	foreach ($fields as $key => $value)
+	{
 		$fields[$key] = trim($value);
 	}
 
 	// Full casefolding.
-	if (in_array($fields[1], array('C', 'F'))) {
+	if (in_array($fields[1], array('C', 'F')))
+	{
 		$utf8_arrays['utf8_casefold_maps']['data']['&#x' . $fields[0] . ';'] = '&#x' . str_replace(' ', '; &#x', trim($fields[2])) . ';';
 	}
 
@@ -141,13 +160,17 @@ 
 // This is necessary because some characters decompose to other characters that
 // themselves decompose further.
 $changed = true;
-while ($changed) {
+while ($changed)
+{
 	$temp = array();
-	foreach ($full_decomposition_maps as $composed => $decomposed) {
+	foreach ($full_decomposition_maps as $composed => $decomposed)
+	{
 		$parts = strpos($decomposed, ' ') !== false ? explode(' ', $decomposed) : (array) $decomposed;
 
-		foreach ($parts as $partnum => $hex) {
-			if (isset($full_decomposition_maps[$hex])) {
+		foreach ($parts as $partnum => $hex)
+		{
+			if (isset($full_decomposition_maps[$hex]))
+			{
 				$parts[$partnum] = $full_decomposition_maps[$hex];
 			}
 		}
@@ -166,17 +189,22 @@ 
 // Same as above, but using only canonical decompositions.
 $changed = true;
 $iteration = 0;
-while ($changed) {
+while ($changed)
+{
 	$temp = array();
-	foreach ($utf8_arrays['utf8_normalize_d_maps']['data'] as $composed => $decomposed) {
-		if ($iteration === 0 && !in_array($composed, $derived_normalization_props['Full_Composition_Exclusion'])) {
+	foreach ($utf8_arrays['utf8_normalize_d_maps']['data'] as $composed => $decomposed)
+	{
+		if ($iteration === 0 && !in_array($composed, $derived_normalization_props['Full_Composition_Exclusion']))
+		{
 			$utf8_arrays['utf8_compose_maps']['data'][$decomposed] = $composed;
 		}
 
 		$parts = strpos($decomposed, ' ') !== false ? explode(' ', $decomposed) : (array) $decomposed;
 
-		foreach ($parts as $partnum => $hex) {
-			if (isset($utf8_arrays['utf8_normalize_d_maps']['data'][$hex])) {
+		foreach ($parts as $partnum => $hex)
+		{
+			if (isset($utf8_arrays['utf8_normalize_d_maps']['data'][$hex]))
+			{
 				$parts[$partnum] = $utf8_arrays['utf8_normalize_d_maps']['data'][$hex];
 			}
 		}
@@ -196,7 +224,8 @@ 
 $utf8_arrays['utf8_normalize_kd_maps']['data'] = array_diff_assoc($full_decomposition_maps, $utf8_arrays['utf8_normalize_d_maps']['data']);
 
 // Some characters have the 'Default_Ignorable_Code_Point' property.
-foreach (file($unicode_data_url . '/DerivedCoreProperties.txt') as $line) {
+foreach (file($unicode_data_url . '/DerivedCoreProperties.txt') as $line)
+{
 	if (strpos($line, 'Default_Ignorable_Code_Point') === false)
 		continue;
 
@@ -207,13 +236,17 @@ 
 
 	$fields = explode(';', $line);
 
-	foreach ($fields as $key => $value) {
+	foreach ($fields as $key => $value)
+	{
 		$fields[$key] = trim($value);
 	}
 
-	if (strpos($fields[0], '..') === false) {
+	if (strpos($fields[0], '..') === false)
+	{
 		$utf8_arrays['utf8_default_ignorables']['data'][] = '&#x' . $fields[0] . ';';
-	} else {
+	}
+	else
+	{
 		$entities = array();
 
 		list($start, $end) = explode('..', $fields[0]);
@@ -222,13 +255,15 @@ 
 		$ord_e = hexdec($end);
 
 		$ord = $ord_s;
-		while ($ord <= $ord_e) {
+		while ($ord <= $ord_e)
+		{
 			$utf8_arrays['utf8_default_ignorables']['data'][] = '&#x' . strtoupper(sprintf('%04s', dechex($ord++))) . ';';
 		}
 	}
 }
 
-foreach ($utf8_arrays as $func_name => $func_info) {
+foreach ($utf8_arrays as $func_name => $func_info)
+{
 	// Now update the file.
 	$file_contents = file_get_contents($unicodedir . '/' . $func_info['file']);
 
@@ -238,28 +273,35 @@ 
 
 	$func_text .= "\n\t" . 'return array(' . "\n";
 
-	foreach ($func_info['data'] as $key => $value) {
+	foreach ($func_info['data'] as $key => $value)
+	{
 		$func_text .= "\t\t";
 
-		if ($func_name !== 'utf8_default_ignorables') {
+		if ($func_name !== 'utf8_default_ignorables')
+		{
 			$func_text .= '"';
 
 			$key = mb_decode_numericentity(str_replace(' ', '', $key), array(0,0x10FFFF,0,0xFFFFFF), 'UTF-8');
 
-			foreach (unpack('C*', $key) as $byte_value) {
+			foreach (unpack('C*', $key) as $byte_value)
+			{
 				$func_text .= '\\x' . strtoupper(dechex($byte_value));
 			}
 
 			$func_text .= '" => ';
 		}
 
-		if ($func_name == 'utf8_combining_classes') {
+		if ($func_name == 'utf8_combining_classes')
+		{
 			$func_text .= $value;
-		} else {
+		}
+		else
+		{
 			$func_text .= '"';
 
 			$value = mb_decode_numericentity(str_replace(' ', '', $value), array(0,0x10FFFF,0,0xFFFFFF), 'UTF-8');
-			foreach (unpack('C*', $value) as $byte_value) {
+			foreach (unpack('C*', $value) as $byte_value)
+			{
 				$func_text .= '\\x' . strtoupper(dechex($byte_value));
 			}