LanguageNameIndexer: Generate PHP file instead of serialized file.

Serialized format is no longer in style for data. PHP files can
take advantage of AutoLoader and caching so they can even be faster
than serialized files. As side bonus we can have readable diffs
for updates.

Only downside is that the file generation takes about ten lines of
ugly string manipulation.

Change-Id: If09704d1172daa13c72a308814534cac1fe9899f

data/LanguageNameIndexer.php

@@ -44,7 +44,34 @@ class LanguageNameIndexer extends Maintenance {
 		}
 
 		$this->output( 'Total buckets: ' . count( $buckets ) . "\n" );
-		file_put_contents( 'langnames.ser', serialize( $buckets ) );
+		$this->generateFile( $buckets );
+	}
+
+	private function generateFile( array $buckets ) {
+		$template = <<<PHP
+<?php
+// This file is generated by script!
+class LanguageNameSearchData {
+	public static \$buckets = ___;
+}
+
+PHP;
+
+		// Format for short array format
+		$data = var_export( $buckets, true );
+		$data = str_replace( "array (", '[', $data );
+		$data = str_replace( "),", '],', $data );
+		// Closing of the array, add correct indendation
+		$data = preg_replace( "/\)$/", "\t]", $data );
+		// Remove newlines after =>s
+		$data = preg_replace( '/(=>)\s+(\[)/m', '\1 \2', $data );
+		// Convert spaces to tabs. Since we are not top-level need more tabs.
+		$data = preg_replace( '/^    /m', "\t\t\t", $data );
+		$data = preg_replace( '/^  /m', "\t\t", $data );
+
+		$template = str_replace( '___', $data, $template );
+
+		file_put_contents( __DIR__ . '/LanguageNameSearchData.php', $template );
 	}
 }