summaryrefslogtreecommitdiff
path: root/includes/normal/UtfNormalGenerate.php
diff options
context:
space:
mode:
Diffstat (limited to 'includes/normal/UtfNormalGenerate.php')
-rw-r--r--includes/normal/UtfNormalGenerate.php103
1 files changed, 60 insertions, 43 deletions
diff --git a/includes/normal/UtfNormalGenerate.php b/includes/normal/UtfNormalGenerate.php
index f392df52..f57aa6cc 100644
--- a/includes/normal/UtfNormalGenerate.php
+++ b/includes/normal/UtfNormalGenerate.php
@@ -4,7 +4,7 @@
* and supplementary files.
*
* Copyright (C) 2004 Brion Vibber <brion@pobox.com>
- * http://www.mediawiki.org/
+ * https://www.mediawiki.org/
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -25,29 +25,37 @@
* @ingroup UtfNormal
*/
-if( PHP_SAPI != 'cli' ) {
+if ( PHP_SAPI != 'cli' ) {
die( "Run me from the command line please.\n" );
}
require_once 'UtfNormalDefines.php';
require_once 'UtfNormalUtil.php';
-$in = fopen("DerivedNormalizationProps.txt", "rt" );
-if( !$in ) {
+$in = fopen( "DerivedNormalizationProps.txt", "rt" );
+if ( !$in ) {
print "Can't open DerivedNormalizationProps.txt for reading.\n";
print "If necessary, fetch this file from the internet:\n";
print "http://www.unicode.org/Public/UNIDATA/DerivedNormalizationProps.txt\n";
- exit(-1);
+ exit( -1 );
}
print "Initializing normalization quick check tables...\n";
$checkNFC = array();
-while( false !== ($line = fgets( $in ) ) ) {
+while ( false !== ( $line = fgets( $in ) ) ) {
$matches = array();
- if( preg_match( '/^([0-9A-F]+)(?:..([0-9A-F]+))?\s*;\s*(NFC_QC)\s*;\s*([MN])/', $line, $matches ) ) {
+ if ( preg_match(
+ '/^([0-9A-F]+)(?:..([0-9A-F]+))?\s*;\s*(NFC_QC)\s*;\s*([MN])/',
+ $line,
+ $matches )
+ ) {
list( $junk, $first, $last, $prop, $value ) = $matches;
#print "$first $last $prop $value\n";
- if( !$last ) $last = $first;
- for( $i = hexdec( $first ); $i <= hexdec( $last ); $i++) {
+ if ( !$last ) {
+ $last = $first;
+ }
+
+ $lastInDecimal = hexdec( $last );
+ for ( $i = hexdec( $first ); $i <= $lastInDecimal; $i++ ) {
$char = codepointToUtf8( $i );
$checkNFC[$char] = $value;
}
@@ -55,29 +63,29 @@ while( false !== ($line = fgets( $in ) ) ) {
}
fclose( $in );
-$in = fopen("CompositionExclusions.txt", "rt" );
-if( !$in ) {
+$in = fopen( "CompositionExclusions.txt", "rt" );
+if ( !$in ) {
print "Can't open CompositionExclusions.txt for reading.\n";
print "If necessary, fetch this file from the internet:\n";
print "http://www.unicode.org/Public/UNIDATA/CompositionExclusions.txt\n";
- exit(-1);
+ exit( -1 );
}
$exclude = array();
-while( false !== ($line = fgets( $in ) ) ) {
- if( preg_match( '/^([0-9A-F]+)/i', $line, $matches ) ) {
+while ( false !== ( $line = fgets( $in ) ) ) {
+ if ( preg_match( '/^([0-9A-F]+)/i', $line, $matches ) ) {
$codepoint = $matches[1];
$source = codepointToUtf8( hexdec( $codepoint ) );
$exclude[$source] = true;
}
}
-fclose($in);
+fclose( $in );
-$in = fopen("UnicodeData.txt", "rt" );
-if( !$in ) {
+$in = fopen( "UnicodeData.txt", "rt" );
+if ( !$in ) {
print "Can't open UnicodeData.txt for reading.\n";
print "If necessary, fetch this file from the internet:\n";
print "http://www.unicode.org/Public/UNIDATA/UnicodeData.txt\n";
- exit(-1);
+ exit( -1 );
}
$compatibilityDecomp = array();
@@ -89,8 +97,8 @@ $compat = 0;
$canon = 0;
print "Reading character definitions...\n";
-while( false !== ($line = fgets( $in ) ) ) {
- $columns = explode(';', $line);
+while ( false !== ( $line = fgets( $in ) ) ) {
+ $columns = explode( ';', $line );
$codepoint = $columns[0];
$name = $columns[1];
$canonicalCombiningClass = $columns[3];
@@ -98,12 +106,12 @@ while( false !== ($line = fgets( $in ) ) ) {
$source = codepointToUtf8( hexdec( $codepoint ) );
- if( $canonicalCombiningClass != 0 ) {
+ if ( $canonicalCombiningClass != 0 ) {
$combiningClass[$source] = intval( $canonicalCombiningClass );
}
- if( $decompositionMapping === '' ) continue;
- if( preg_match( '/^<(.+)> (.*)$/', $decompositionMapping, $matches ) ) {
+ if ( $decompositionMapping === '' ) continue;
+ if ( preg_match( '/^<(.+)> (.*)$/', $decompositionMapping, $matches ) ) {
# Compatibility decomposition
$canonical = false;
$decompositionMapping = $matches[2];
@@ -116,9 +124,9 @@ while( false !== ($line = fgets( $in ) ) ) {
$dest = hexSequenceToUtf8( $decompositionMapping );
$compatibilityDecomp[$source] = $dest;
- if( $canonical ) {
+ if ( $canonical ) {
$canonicalDecomp[$source] = $dest;
- if( empty( $exclude[$source] ) ) {
+ if ( empty( $exclude[$source] ) ) {
$canonicalComp[$dest] = $source;
}
}
@@ -129,15 +137,15 @@ fclose( $in );
print "Recursively expanding canonical mappings...\n";
$changed = 42;
$pass = 1;
-while( $changed > 0 ) {
+while ( $changed > 0 ) {
print "pass $pass\n";
$changed = 0;
- foreach( $canonicalDecomp as $source => $dest ) {
+ foreach ( $canonicalDecomp as $source => $dest ) {
$newDest = preg_replace_callback(
'/([\xc0-\xff][\x80-\xbf]+)/',
'callbackCanonical',
- $dest);
- if( $newDest === $dest ) continue;
+ $dest );
+ if ( $newDest === $dest ) continue;
$changed++;
$canonicalDecomp[$source] = $newDest;
}
@@ -147,15 +155,15 @@ while( $changed > 0 ) {
print "Recursively expanding compatibility mappings...\n";
$changed = 42;
$pass = 1;
-while( $changed > 0 ) {
+while ( $changed > 0 ) {
print "pass $pass\n";
$changed = 0;
- foreach( $compatibilityDecomp as $source => $dest ) {
+ foreach ( $compatibilityDecomp as $source => $dest ) {
$newDest = preg_replace_callback(
'/([\xc0-\xff][\x80-\xbf]+)/',
'callbackCompat',
- $dest);
- if( $newDest === $dest ) continue;
+ $dest );
+ if ( $newDest === $dest ) continue;
$changed++;
$compatibilityDecomp[$source] = $newDest;
}
@@ -164,8 +172,8 @@ while( $changed > 0 ) {
print "$total decomposition mappings ($canon canonical, $compat compatibility)\n";
-$out = fopen("UtfNormalData.inc", "wt");
-if( $out ) {
+$out = fopen( "UtfNormalData.inc", "wt" );
+if ( $out ) {
$serCombining = escapeSingleString( serialize( $combiningClass ) );
$serComp = escapeSingleString( serialize( $canonicalComp ) );
$serCanon = escapeSingleString( serialize( $canonicalDecomp ) );
@@ -177,6 +185,7 @@ if( $out ) {
*
* @file
*/
+// @codingStandardsIgnoreFile
UtfNormal::\$utfCombiningClass = unserialize( '$serCombining' );
UtfNormal::\$utfCanonicalComp = unserialize( '$serComp' );
@@ -188,12 +197,11 @@ UtfNormal::\$utfCheckNFC = unserialize( '$serCheckNFC' );
print "Wrote out UtfNormalData.inc\n";
} else {
print "Can't create file UtfNormalData.inc\n";
- exit(-1);
+ exit( -1 );
}
-
-$out = fopen("UtfNormalDataK.inc", "wt");
-if( $out ) {
+$out = fopen( "UtfNormalDataK.inc", "wt" );
+if ( $out ) {
$serCompat = escapeSingleString( serialize( $compatibilityDecomp ) );
$outdata = "<" . "?php
/**
@@ -202,32 +210,41 @@ if( $out ) {
*
* @file
*/
+// @codingStandardsIgnoreFile
UtfNormal::\$utfCompatibilityDecomp = unserialize( '$serCompat' );
\n";
fputs( $out, $outdata );
fclose( $out );
print "Wrote out UtfNormalDataK.inc\n";
- exit(0);
+ exit( 0 );
} else {
print "Can't create file UtfNormalDataK.inc\n";
- exit(-1);
+ exit( -1 );
}
# ---------------
function callbackCanonical( $matches ) {
+ // @codingStandardsIgnoreStart MediaWiki.NamingConventions.ValidGlobalName.wgPrefix
global $canonicalDecomp;
- if( isset( $canonicalDecomp[$matches[1]] ) ) {
+ // @codingStandardsIgnoreEnd
+
+ if ( isset( $canonicalDecomp[$matches[1]] ) ) {
return $canonicalDecomp[$matches[1]];
}
+
return $matches[1];
}
function callbackCompat( $matches ) {
+ // @codingStandardsIgnoreStart MediaWiki.NamingConventions.ValidGlobalName.wgPrefix
global $compatibilityDecomp;
- if( isset( $compatibilityDecomp[$matches[1]] ) ) {
+ // @codingStandardsIgnoreEnd
+
+ if ( isset( $compatibilityDecomp[$matches[1]] ) ) {
return $compatibilityDecomp[$matches[1]];
}
+
return $matches[1];
}
generated by cgit v1.2.2 (git 2.25.0) at 2024-04-26 08:02:09 +0000