Merge "Generate Utf8Case.ser directly from UnicodeData.txt"
This commit is contained in:
jenkins-bot
Gerrit Code Review
commit
12238a3704
10 changed files with 251 additions and 2368 deletions
7
includes/normal/.gitignore
vendored
Normal file
7
includes/normal/.gitignore
vendored
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
/CompositionExclusions.txt
|
||||
/DerivedNormalizationProps.txt
|
||||
/NormalizationCorrections.txt
|
||||
/NormalizationTest.txt
|
||||
/UTF-8-test.txt
|
||||
/UnicodeData.txt
|
||||
/testdata
|
||||
|
|
@ -16,14 +16,11 @@ PHP=php
|
|||
FETCH=wget
|
||||
#FETCH=fetch
|
||||
|
||||
all : UtfNormalData.inc Utf8Case.php
|
||||
all : UtfNormalData.inc
|
||||
|
||||
UtfNormalData.inc : UtfNormalGenerate.php UtfNormalUtil.php UnicodeData.txt CompositionExclusions.txt NormalizationCorrections.txt DerivedNormalizationProps.txt
|
||||
$(PHP) UtfNormalGenerate.php
|
||||
|
||||
Utf8Case.php : Utf8CaseGenerate.php UtfNormalUtil.php UnicodeData.txt
|
||||
$(PHP) Utf8CaseGenerate.php
|
||||
|
||||
test : testutf8 UtfNormalTest.php UtfNormalData.inc NormalizationTest.txt
|
||||
$(PHP) UtfNormalTest.php
|
||||
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
|
|
@ -1,112 +0,0 @@
|
|||
<?php
|
||||
/**
|
||||
* This script generates Utf8Case.php from the Unicode Character Database
|
||||
* and supplementary files.
|
||||
*
|
||||
* Copyright © 2004,2008 Brion Vibber <brion@pobox.com>
|
||||
* http://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
|
||||
* the Free Software Foundation; either version 2 of the License, or
|
||||
* (at your option) any later version.
|
||||
*
|
||||
* This program is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
* GNU General Public License for more details.
|
||||
*
|
||||
* You should have received a copy of the GNU General Public License along
|
||||
* with this program; if not, write to the Free Software Foundation, Inc.,
|
||||
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
|
||||
* http://www.gnu.org/copyleft/gpl.html
|
||||
*
|
||||
* @file
|
||||
* @ingroup UtfNormal
|
||||
*/
|
||||
|
||||
if( PHP_SAPI != 'cli' ) {
|
||||
die( "Run me from the command line please.\n" );
|
||||
}
|
||||
|
||||
require_once 'UtfNormalDefines.php';
|
||||
require_once 'UtfNormalUtil.php';
|
||||
|
||||
$in = fopen("UnicodeData.txt", "rt" );
|
||||
if( !$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);
|
||||
}
|
||||
$wikiUpperChars = array();
|
||||
$wikiLowerChars = array();
|
||||
|
||||
print "Reading character definitions...\n";
|
||||
while( false !== ($line = fgets( $in ) ) ) {
|
||||
$columns = explode(';', $line);
|
||||
$codepoint = $columns[0];
|
||||
$name = $columns[1];
|
||||
$simpleUpper = $columns[12];
|
||||
$simpleLower = $columns[13];
|
||||
|
||||
$source = codepointToUtf8( hexdec( $codepoint ) );
|
||||
if( $simpleUpper ) {
|
||||
$wikiUpperChars[$source] = codepointToUtf8( hexdec( $simpleUpper ) );
|
||||
}
|
||||
if( $simpleLower ) {
|
||||
$wikiLowerChars[$source] = codepointToUtf8( hexdec( $simpleLower ) );
|
||||
}
|
||||
}
|
||||
fclose( $in );
|
||||
|
||||
$out = fopen( "Utf8Case.php", "wt" );
|
||||
if( $out ) {
|
||||
$outUpperChars = escapeArray( $wikiUpperChars );
|
||||
$outLowerChars = escapeArray( $wikiLowerChars );
|
||||
$outdata = "<" . "?php
|
||||
/**
|
||||
* Simple 1:1 upper/lowercase switching arrays for utf-8 text.
|
||||
* Won't get context-sensitive things yet.
|
||||
*
|
||||
* Hack for bugs in ucfirst() and company
|
||||
*
|
||||
* These are pulled from memcached if possible, as this is faster than filling
|
||||
* up a big array manually.
|
||||
*
|
||||
* @file
|
||||
* @ingroup Language
|
||||
*/
|
||||
|
||||
/**
|
||||
* Translation array to get upper case character
|
||||
*/
|
||||
\$wikiUpperChars = $outUpperChars;
|
||||
|
||||
/**
|
||||
* Translation array to get lower case character
|
||||
*/
|
||||
\$wikiLowerChars = $outLowerChars;\n";
|
||||
fputs( $out, $outdata );
|
||||
fclose( $out );
|
||||
print "Wrote out Utf8Case.php\n";
|
||||
} else {
|
||||
print "Can't create file Utf8Case.php\n";
|
||||
exit(-1);
|
||||
}
|
||||
|
||||
|
||||
function escapeArray( $arr ) {
|
||||
return "array(\n" .
|
||||
implode( ",\n",
|
||||
array_map( "escapeLine",
|
||||
array_keys( $arr ),
|
||||
array_values( $arr ) ) ) .
|
||||
"\n)";
|
||||
}
|
||||
|
||||
function escapeLine( $key, $val ) {
|
||||
$encKey = escapeSingleString( $key );
|
||||
$encVal = escapeSingleString( $val );
|
||||
return "\t'$encKey' => '$encVal'";
|
||||
}
|
||||
|
|
@ -1,6 +1,6 @@
|
|||
<?php
|
||||
/**
|
||||
* Generates normalizer data files for Arabic and Malayalam.
|
||||
* Generates the normalizer data file for Arabic.
|
||||
*
|
||||
* 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
|
||||
|
|
@ -21,47 +21,43 @@
|
|||
* @ingroup MaintenanceLanguage
|
||||
*/
|
||||
|
||||
require_once __DIR__ . '/../../includes/normal/UtfNormalUtil.php';
|
||||
|
||||
require_once __DIR__ . '/../Maintenance.php';
|
||||
|
||||
/**
|
||||
* Generates normalizer data files for Arabic and Malayalam.
|
||||
* Generates the normalizer data file for Arabic.
|
||||
* For NFC see includes/normal.
|
||||
*
|
||||
* @ingroup MaintenanceLanguage
|
||||
*/
|
||||
class GenerateNormalizerData extends Maintenance {
|
||||
public $dataFile;
|
||||
|
||||
class GenerateNormalizerDataAr extends Maintenance {
|
||||
public function __construct() {
|
||||
parent::__construct();
|
||||
$this->mDescription = 'Generate the normalizer data file for Arabic';
|
||||
$this->addOption( 'unicode-data-file', 'The local location of the data file ' .
|
||||
'from http://unicode.org/Public/UNIDATA/UnicodeData.txt', false, true );
|
||||
}
|
||||
|
||||
public function getDbType() {
|
||||
return Maintenance::DB_NONE;
|
||||
}
|
||||
|
||||
public function execute() {
|
||||
if ( !$this->hasOption( 'unicode-data-file' ) ) {
|
||||
$this->dataFile = 'UnicodeData.txt';
|
||||
if ( !file_exists( $this->dataFile ) ) {
|
||||
$dataFile = 'UnicodeData.txt';
|
||||
if ( !file_exists( $dataFile ) ) {
|
||||
$this->error( "Unable to find UnicodeData.txt. Please specify " .
|
||||
"its location with --unicode-data-file=<FILE>" );
|
||||
exit( 1 );
|
||||
}
|
||||
} else {
|
||||
$this->dataFile = $this->getOption( 'unicode-data-file' );
|
||||
if ( !file_exists( $this->dataFile ) ) {
|
||||
$dataFile = $this->getOption( 'unicode-data-file' );
|
||||
if ( !file_exists( $dataFile ) ) {
|
||||
$this->error( 'Unable to find the specified data file.' );
|
||||
exit( 1 );
|
||||
}
|
||||
}
|
||||
|
||||
$this->generateArabic();
|
||||
$this->generateMalayalam();
|
||||
}
|
||||
|
||||
function generateArabic() {
|
||||
$file = fopen( $this->dataFile, 'r' );
|
||||
$file = fopen( $dataFile, 'r' );
|
||||
if ( !$file ) {
|
||||
$this->error( 'Unable to open the data file.' );
|
||||
exit( 1 );
|
||||
|
|
@ -75,7 +71,9 @@ class GenerateNormalizerData extends Maintenance {
|
|||
'Canonical_Combining_Class',
|
||||
'Bidi_Class',
|
||||
'Decomposition_Type_Mapping',
|
||||
'Numeric_Type_Value',
|
||||
'Numeric_Type_Value_6',
|
||||
'Numeric_Type_Value_7',
|
||||
'Numeric_Type_Value_8',
|
||||
'Bidi_Mirrored',
|
||||
'Unicode_1_Name',
|
||||
'ISO_Comment',
|
||||
|
|
@ -129,32 +127,7 @@ class GenerateNormalizerData extends Maintenance {
|
|||
file_put_contents( "$IP/serialized/normalize-ar.ser", serialize( $pairs ) );
|
||||
echo "ar: " . count( $pairs ) . " pairs written.\n";
|
||||
}
|
||||
|
||||
function generateMalayalam() {
|
||||
$hexPairs = array(
|
||||
# From http://unicode.org/versions/Unicode5.1.0/#Malayalam_Chillu_Characters
|
||||
'0D23 0D4D 200D' => '0D7A',
|
||||
'0D28 0D4D 200D' => '0D7B',
|
||||
'0D30 0D4D 200D' => '0D7C',
|
||||
'0D32 0D4D 200D' => '0D7D',
|
||||
'0D33 0D4D 200D' => '0D7E',
|
||||
|
||||
# From http://permalink.gmane.org/gmane.science.linguistics.wikipedia.technical/46413
|
||||
'0D15 0D4D 200D' => '0D7F',
|
||||
);
|
||||
|
||||
$pairs = array();
|
||||
foreach ( $hexPairs as $hexSource => $hexDest ) {
|
||||
$source = hexSequenceToUtf8( $hexSource );
|
||||
$dest = hexSequenceToUtf8( $hexDest );
|
||||
$pairs[$source] = $dest;
|
||||
}
|
||||
|
||||
global $IP;
|
||||
file_put_contents( "$IP/serialized/normalize-ml.ser", serialize( $pairs ) );
|
||||
echo "ml: " . count( $pairs ) . " pairs written.\n";
|
||||
}
|
||||
}
|
||||
|
||||
$maintClass = 'GenerateNormalizerData';
|
||||
$maintClass = 'GenerateNormalizerDataAr';
|
||||
require_once RUN_MAINTENANCE_IF_MAIN;
|
||||
69
maintenance/language/generateNormalizerDataMl.php
Normal file
69
maintenance/language/generateNormalizerDataMl.php
Normal file
|
|
@ -0,0 +1,69 @@
|
|||
<?php
|
||||
/**
|
||||
* Generates the normalizer data file for Malayalam.
|
||||
*
|
||||
* 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
|
||||
* the Free Software Foundation; either version 2 of the License, or
|
||||
* (at your option) any later version.
|
||||
*
|
||||
* This program is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
* GNU General Public License for more details.
|
||||
*
|
||||
* You should have received a copy of the GNU General Public License along
|
||||
* with this program; if not, write to the Free Software Foundation, Inc.,
|
||||
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
|
||||
* http://www.gnu.org/copyleft/gpl.html
|
||||
*
|
||||
* @file
|
||||
* @ingroup MaintenanceLanguage
|
||||
*/
|
||||
|
||||
require_once __DIR__ . '/../Maintenance.php';
|
||||
|
||||
/**
|
||||
* Generates the normalizer data file for Malayalam.
|
||||
* For NFC see includes/normal.
|
||||
*
|
||||
* @ingroup MaintenanceLanguage
|
||||
*/
|
||||
class GenerateNormalizerDataMl extends Maintenance {
|
||||
public function __construct() {
|
||||
parent::__construct();
|
||||
$this->mDescription = 'Generate the normalizer data file for Malayalam';
|
||||
}
|
||||
|
||||
public function getDbType() {
|
||||
return Maintenance::DB_NONE;
|
||||
}
|
||||
|
||||
public function execute() {
|
||||
$hexPairs = array(
|
||||
# From http://unicode.org/versions/Unicode5.1.0/#Malayalam_Chillu_Characters
|
||||
'0D23 0D4D 200D' => '0D7A',
|
||||
'0D28 0D4D 200D' => '0D7B',
|
||||
'0D30 0D4D 200D' => '0D7C',
|
||||
'0D32 0D4D 200D' => '0D7D',
|
||||
'0D33 0D4D 200D' => '0D7E',
|
||||
|
||||
# From http://permalink.gmane.org/gmane.science.linguistics.wikipedia.technical/46413
|
||||
'0D15 0D4D 200D' => '0D7F',
|
||||
);
|
||||
|
||||
$pairs = array();
|
||||
foreach ( $hexPairs as $hexSource => $hexDest ) {
|
||||
$source = hexSequenceToUtf8( $hexSource );
|
||||
$dest = hexSequenceToUtf8( $hexDest );
|
||||
$pairs[$source] = $dest;
|
||||
}
|
||||
|
||||
global $IP;
|
||||
file_put_contents( "$IP/serialized/normalize-ml.ser", serialize( $pairs ) );
|
||||
echo "ml: " . count( $pairs ) . " pairs written.\n";
|
||||
}
|
||||
}
|
||||
|
||||
$maintClass = 'GenerateNormalizerDataMl';
|
||||
require_once RUN_MAINTENANCE_IF_MAIN;
|
||||
129
maintenance/language/generateUtf8Case.php
Normal file
129
maintenance/language/generateUtf8Case.php
Normal file
|
|
@ -0,0 +1,129 @@
|
|||
<?php
|
||||
/**
|
||||
* Generates Utf8Case.ser from the Unicode Character Database and
|
||||
* supplementary files.
|
||||
*
|
||||
* Copyright © 2004, 2008 Brion Vibber <brion@pobox.com>
|
||||
* http://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
|
||||
* the Free Software Foundation; either version 2 of the License, or
|
||||
* (at your option) any later version.
|
||||
*
|
||||
* This program is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
* GNU General Public License for more details.
|
||||
*
|
||||
* You should have received a copy of the GNU General Public License along
|
||||
* with this program; if not, write to the Free Software Foundation, Inc.,
|
||||
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
|
||||
* http://www.gnu.org/copyleft/gpl.html
|
||||
*
|
||||
* @file
|
||||
* @ingroup MaintenanceLanguage
|
||||
*/
|
||||
|
||||
require_once __DIR__ . '/../Maintenance.php';
|
||||
|
||||
/**
|
||||
* Generates Utf8Case.ser from the Unicode Character Database and
|
||||
* supplementary files.
|
||||
*
|
||||
* @ingroup MaintenanceLanguage
|
||||
*/
|
||||
class GenerateUtf8Case extends Maintenance {
|
||||
|
||||
public function __construct() {
|
||||
parent::__construct();
|
||||
$this->mDescription = 'Generate Utf8Case.ser from the Unicode Character Database ' .
|
||||
'and supplementary files';
|
||||
$this->addOption( 'unicode-data-file', 'The local location of the data file ' .
|
||||
'from http://unicode.org/Public/UNIDATA/UnicodeData.txt', false, true );
|
||||
}
|
||||
|
||||
public function getDbType() {
|
||||
return Maintenance::DB_NONE;
|
||||
}
|
||||
|
||||
public function execute() {
|
||||
if ( !$this->hasOption( 'unicode-data-file' ) ) {
|
||||
$dataFile = 'UnicodeData.txt';
|
||||
if ( !file_exists( $dataFile ) ) {
|
||||
$this->error( "Unable to find UnicodeData.txt. Please specify " .
|
||||
"its location with --unicode-data-file=<FILE>" );
|
||||
exit( 1 );
|
||||
}
|
||||
} else {
|
||||
$dataFile = $this->getOption( 'unicode-data-file' );
|
||||
if ( !file_exists( $dataFile ) ) {
|
||||
$this->error( 'Unable to find the specified data file.' );
|
||||
exit( 1 );
|
||||
}
|
||||
}
|
||||
|
||||
$file = fopen( $dataFile, 'r' );
|
||||
if ( !$file ) {
|
||||
$this->error( 'Unable to open the data file.' );
|
||||
exit( 1 );
|
||||
}
|
||||
|
||||
// For the file format, see http://www.unicode.org/reports/tr44/
|
||||
$fieldNames = array(
|
||||
'Code',
|
||||
'Name',
|
||||
'General_Category',
|
||||
'Canonical_Combining_Class',
|
||||
'Bidi_Class',
|
||||
'Decomposition_Type_Mapping',
|
||||
'Numeric_Type_Value_6',
|
||||
'Numeric_Type_Value_7',
|
||||
'Numeric_Type_Value_8',
|
||||
'Bidi_Mirrored',
|
||||
'Unicode_1_Name',
|
||||
'ISO_Comment',
|
||||
'Simple_Uppercase_Mapping',
|
||||
'Simple_Lowercase_Mapping',
|
||||
'Simple_Titlecase_Mapping'
|
||||
);
|
||||
|
||||
$upper = array();
|
||||
$lower = array();
|
||||
|
||||
$lineNum = 0;
|
||||
while ( false !== ( $line = fgets( $file ) ) ) {
|
||||
++$lineNum;
|
||||
|
||||
# Strip comments
|
||||
$line = trim( substr( $line, 0, strcspn( $line, '#' ) ) );
|
||||
if ( $line === '' ) {
|
||||
continue;
|
||||
}
|
||||
|
||||
# Split fields
|
||||
$numberedData = explode( ';', $line );
|
||||
$data = array();
|
||||
foreach ( $fieldNames as $number => $name ) {
|
||||
$data[$name] = $numberedData[$number];
|
||||
}
|
||||
|
||||
$source = hexSequenceToUtf8( $data['Code'] );
|
||||
if ( $data['Simple_Uppercase_Mapping'] ) {
|
||||
$upper[$source] = hexSequenceToUtf8( $data['Simple_Uppercase_Mapping'] );
|
||||
}
|
||||
if ( $data['Simple_Lowercase_Mapping'] ) {
|
||||
$lower[$source] = hexSequenceToUtf8( $data['Simple_Lowercase_Mapping'] );
|
||||
}
|
||||
}
|
||||
|
||||
global $IP;
|
||||
file_put_contents( "$IP/serialized/Utf8Case.ser", serialize( array(
|
||||
'wikiUpperChars' => $upper,
|
||||
'wikiLowerChars' => $lower,
|
||||
) ) );
|
||||
}
|
||||
}
|
||||
|
||||
$maintClass = 'GenerateUtf8Case';
|
||||
require_once RUN_MAINTENANCE_IF_MAIN;
|
||||
4
serialized/.gitignore
vendored
Normal file
4
serialized/.gitignore
vendored
Normal file
|
|
@ -0,0 +1,4 @@
|
|||
/UnicodeData.txt
|
||||
/allkeys.txt
|
||||
/ucd.all.grouped.xml
|
||||
/ucd.all.grouped.zip
|
||||
|
|
@ -1,7 +1,7 @@
|
|||
|
||||
SPECIAL_TARGETS=Utf8Case.ser
|
||||
SPECIAL_TARGETS=Utf8Case.ser normalize-ar.ser normalize-ml.ser first-letters-root.ser
|
||||
ALL_TARGETS=$(SPECIAL_TARGETS)
|
||||
DIST_TARGETS=$(SPECIAL_TARGETS)
|
||||
UNICODE_VERSION=6.0.0
|
||||
|
||||
.PHONY: all dist clean
|
||||
|
||||
|
|
@ -13,6 +13,26 @@ dist: $(DIST_TARGETS)
|
|||
clean:
|
||||
rm -f $(ALL_TARGETS)
|
||||
|
||||
Utf8Case.ser : ../includes/normal/Utf8Case.php
|
||||
php serialize.php -o $@ $<
|
||||
Utf8Case.ser: UnicodeData.txt
|
||||
php ../maintenance/language/generateUtf8Case.php
|
||||
|
||||
normalize-ar.ser: UnicodeData.txt
|
||||
php ../maintenance/language/generateNormalizerDataAr.php
|
||||
|
||||
normalize-ml.ser:
|
||||
php ../maintenance/language/generateNormalizerDataMl.php
|
||||
|
||||
first-letters-root.ser: allkeys.txt ucd.all.grouped.xml
|
||||
php ../maintenance/language/generateCollationData.php
|
||||
|
||||
UnicodeData.txt:
|
||||
wget http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/UnicodeData.txt
|
||||
|
||||
allkeys.txt:
|
||||
wget http://www.unicode.org/Public/UCA/$(UNICODE_VERSION)/allkeys.txt
|
||||
|
||||
ucd.all.grouped.xml: ucd.all.grouped.zip
|
||||
unzip ucd.all.grouped.zip ucd.all.grouped.xml
|
||||
|
||||
ucd.all.grouped.zip:
|
||||
wget http://www.unicode.org/Public/$(UNICODE_VERSION)/ucdxml/ucd.all.grouped.zip
|
||||
|
|
|
|||
|
|
@ -1,95 +0,0 @@
|
|||
<?php
|
||||
/**
|
||||
* Serialize variables found in input file and store the result in the
|
||||
* specified file.
|
||||
*
|
||||
* 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
|
||||
* the Free Software Foundation; either version 2 of the License, or
|
||||
* (at your option) any later version.
|
||||
*
|
||||
* This program is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
* GNU General Public License for more details.
|
||||
*
|
||||
* You should have received a copy of the GNU General Public License along
|
||||
* with this program; if not, write to the Free Software Foundation, Inc.,
|
||||
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
|
||||
* http://www.gnu.org/copyleft/gpl.html
|
||||
*
|
||||
* @file
|
||||
*/
|
||||
|
||||
if ( !defined( 'MEDIAWIKI' ) ) {
|
||||
$wgNoDBParam = true;
|
||||
$optionsWithArgs = array( 'o' );
|
||||
require_once __DIR__ .'/../maintenance/commandLine.inc';
|
||||
|
||||
$stderr = fopen( 'php://stderr', 'w' );
|
||||
if ( !isset( $args[0] ) ) {
|
||||
fwrite( $stderr, "No input file specified\n" );
|
||||
exit( 1 );
|
||||
}
|
||||
if ( wfIsWindows() ) {
|
||||
$files = array();
|
||||
foreach ( $args as $arg ) {
|
||||
$files = array_merge( $files, glob( $arg ) );
|
||||
}
|
||||
if ( !$files ) {
|
||||
fwrite( $stderr, "No files found\n" );
|
||||
}
|
||||
} else {
|
||||
$files = $args;
|
||||
}
|
||||
|
||||
if ( isset( $options['o'] ) ) {
|
||||
$out = fopen( $options['o'], 'wb' );
|
||||
if ( !$out ) {
|
||||
fwrite( $stderr, "Unable to open file \"{$options['o']}\" for output\n" );
|
||||
exit( 1 );
|
||||
}
|
||||
} else {
|
||||
$out = fopen( 'php://stdout', 'wb' );
|
||||
}
|
||||
|
||||
$vars = array();
|
||||
foreach ( $files as $inputFile ) {
|
||||
$vars = array_merge( $vars, getVars( $inputFile ) );
|
||||
}
|
||||
fwrite( $out, serialize( $vars ) );
|
||||
fclose( $out );
|
||||
exit( 0 );
|
||||
}
|
||||
|
||||
//----------------------------------------------------------------------------
|
||||
|
||||
function getVars( $_gv_filename ) {
|
||||
require $_gv_filename;
|
||||
$vars = get_defined_vars();
|
||||
unset( $vars['_gv_filename'] );
|
||||
|
||||
# Clean up line endings
|
||||
if ( wfIsWindows() ) {
|
||||
$vars = unixLineEndings( $vars );
|
||||
}
|
||||
return $vars;
|
||||
}
|
||||
|
||||
function unixLineEndings( $var ) {
|
||||
static $recursionLevel = 0;
|
||||
if ( $recursionLevel > 50 ) {
|
||||
global $stderr;
|
||||
fwrite( $stderr, "Error: Recursion limit exceeded. Possible circular reference in array variable.\n" );
|
||||
exit( 2 );
|
||||
}
|
||||
|
||||
if ( is_array( $var ) ) {
|
||||
++$recursionLevel;
|
||||
$var = array_map( 'unixLineEndings', $var );
|
||||
--$recursionLevel;
|
||||
} elseif ( is_string( $var ) ) {
|
||||
$var = str_replace( "\r\n", "\n", $var );
|
||||
}
|
||||
return $var;
|
||||
}
|
||||
Loading…
Reference in a new issue