fix #40 (PHP unicode)

rubychan · Feb 17, 2013 · d666db4 · d666db4
1 parent d0b9a7c
commit d666db4
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 3 deletions.
diff --git a/Changes.textile b/Changes.textile
@@ -8,6 +8,7 @@ h2. Changes in 1.0.9
 
 * Fix Ruby scanner: Ruby 1.9 hash syntax @{ key: value }@ is highlighted correctly. [GH #106, thanks to Seth Vargo]
 * Fix HTML scanner: Accept DTDs. [GH #83]
+* Fix PHP scanner: Accept Unicode. [GH #40]
 
 h2. Changes in 1.0.8
 

diff --git a/lib/coderay/scanners/php.rb b/lib/coderay/scanners/php.rb
@@ -1,4 +1,4 @@
-# encoding: ASCII-8BIT
+# encoding: utf-8
 module CodeRay
 module Scanners
 
@@ -11,7 +11,6 @@ class PHP < Scanner
 
     register_for :php
     file_extension 'php'
-    encoding 'BINARY'
 
     KINDS_NOT_LOC = HTML::KINDS_NOT_LOC
 
@@ -211,7 +210,7 @@ module RE  # :nodoc:
 
       HTML_INDICATOR = /<!DOCTYPE html|<(?:html|body|div|p)[> ]/i
 
-      IDENTIFIER = /[a-z_\x7f-\xFF][a-z0-9_\x7f-\xFF]*/i
+      IDENTIFIER = 'ä'[/[[:alpha:]]/] == 'ä' ? Regexp.new('[[:alpha:]_[^\0-\177]][[:alnum:]_[^\0-\177]]*') : Regexp.new('[a-z_\17f-\xFF][a-z0-9_\x7f-\xFF]*/', true)
       VARIABLE = /\$#{IDENTIFIER}/
 
       OPERATOR = /