Upgrade CodeRay to 0.9.2 (#3359).

git-svn-id: svn+ssh://rubyforge.org/var/svn/redmine/trunk@3592 e93f8b46-1217-0410-a6f0-8f06a7374b81
This commit is contained in:
Jean-Philippe Lang 2010-03-16 20:29:12 +00:00
parent e6c8760ad7
commit 0097770626
71 changed files with 4286 additions and 1053 deletions

View File

@ -1,53 +0,0 @@
= CodeRay - Trunk folder structure
== bench - Benchmarking system
All benchmarking stuff goes here.
Test inputs are stored in files named <code>example.<lang></code>.
Test outputs go to <code>bench/test.<encoder-default-file-extension></code>.
Run <code>bench/bench.rb</code> to get a usage description.
Run <code>rake bench</code> to perform an example benchmark.
== bin - Scripts
Executional files for CodeRay.
== demo - Demos and functional tests
Demonstrational scripts to show of CodeRay's features.
Run them as functional tests with <code>rake test:demos</code>.
== etc - Lots of stuff
Some addidtional files for CodeRay, mainly graphics and Vim scripts.
== gem_server - Gem output folder
For <code>rake gem</code>.
== lib - CodeRay library code
This is the base directory for the CodeRay library.
== rake_helpers - Rake helper libraries
Some files to enhance Rake, including the Autumnal Rdoc template and some scripts.
== test - Tests
Tests for the scanners.
Each language has its own subfolder and sub-suite.
Run with <code>rake test</code>.

View File

@ -1,82 +0,0 @@
#!/usr/bin/env ruby
# CodeRay Executable
#
# Version: 0.1
# Author: murphy
def err msg
$stderr.puts msg
end
begin
require 'coderay'
if ARGV.empty?
puts <<-USAGE
CodeRay #{CodeRay::VERSION} (http://rd.cYcnus.de/coderay)
Usage:
coderay -<lang> [-<format>] < file > output
coderay file [-<format>]
Example:
coderay -ruby -statistic < foo.rb
coderay codegen.c # generates codegen.c.html
USAGE
end
first, second = ARGV
if first
if first[/-(\w+)/] == first
lang = $1.to_sym
input = $stdin.read
tokens = :scan
elsif first == '-'
lang = $1.to_sym
input = $stdin.read
tokens = :scan
else
file = first
tokens = CodeRay.scan_file file
output_filename, output_ext = file, /#{Regexp.escape(File.extname(file))}$/
end
else
puts 'No lang/file given.'
exit 1
end
if second
if second[/-(\w+)/] == second
format = $1.to_sym
else
raise 'Invalid format (must be -xxx).'
end
else
$stderr.puts 'No format given; setting to default (HTML Page)'
format = :page
end
# TODO: allow streaming
if tokens == :scan
output = CodeRay::Duo[lang => format].highlight input #, :stream => true
else
output = tokens.encode format
end
out = $stdout
if output_filename
output_filename += '.' + CodeRay::Encoders[format]::FILE_EXTENSION
if File.exist? output_filename
err 'File %s already exists.' % output_filename
exit
else
out = File.open output_filename, 'w'
end
end
out.print output
rescue => boom
err "Error: #{boom.message}\n"
err boom.backtrace
err '-' * 50
err ARGV
exit 1
end

View File

@ -1,4 +0,0 @@
#!/usr/bin/env ruby
require 'coderay'
puts CodeRay::Encoders[:html]::CSS.new.stylesheet

View File

@ -1,9 +0,0 @@
module CodeRay
module Encoders
map :stats => :statistic,
:plain => :text,
:tex => :latex
end
end

View File

@ -1,44 +0,0 @@
module CodeRay
module Encoders
# The Tokens encoder converts the tokens to a simple
# readable format. It doesn't use colors and is mainly
# intended for console output.
#
# The tokens are converted with Tokens.write_token.
#
# The format is:
#
# <token-kind> \t <escaped token-text> \n
#
# Example:
#
# require 'coderay'
# puts CodeRay.scan("puts 3 + 4", :ruby).tokens
#
# prints:
#
# ident puts
# space
# integer 3
# space
# operator +
# space
# integer 4
#
class Tokens < Encoder
include Streamable
register_for :tokens
FILE_EXTENSION = 'tok'
protected
def token text, kind
@out << CodeRay::Tokens.write_token(text, kind)
end
end
end
end

View File

@ -1,15 +0,0 @@
module CodeRay
module Scanners
map :cpp => :c,
:plain => :plaintext,
:pascal => :delphi,
:irb => :ruby,
:xml => :html,
:xhtml => :nitro_xhtml,
:nitro => :nitro_xhtml
default :plain
end
end

View File

@ -1,130 +0,0 @@
module CodeRay
module Scanners
class Java < Scanner
register_for :java
RESERVED_WORDS = %w(abstract assert break case catch class
const continue default do else enum extends final finally for
goto if implements import instanceof interface native new
package private protected public return static strictfp super switch
synchronized this throw throws transient try void volatile while)
PREDEFINED_TYPES = %w(boolean byte char double float int long short)
PREDEFINED_CONSTANTS = %w(true false null)
IDENT_KIND = WordList.new(:ident).
add(RESERVED_WORDS, :reserved).
add(PREDEFINED_TYPES, :pre_type).
add(PREDEFINED_CONSTANTS, :pre_constant)
ESCAPE = / [rbfnrtv\n\\'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} /x
UNICODE_ESCAPE = / u[a-fA-F0-9]{4} | U[a-fA-F0-9]{8} /x
def scan_tokens tokens, options
state = :initial
until eos?
kind = nil
match = nil
case state
when :initial
if scan(/ \s+ | \\\n /x)
kind = :space
elsif scan(%r! // [^\n\\]* (?: \\. [^\n\\]* )* | /\* (?: .*? \*/ | .* ) !mx)
kind = :comment
elsif match = scan(/ \# \s* if \s* 0 /x)
match << scan_until(/ ^\# (?:elif|else|endif) .*? $ | \z /xm) unless eos?
kind = :comment
elsif scan(/ [-+*\/=<>?:;,!&^|()\[\]{}~%]+ | \.(?!\d) /x)
kind = :operator
elsif match = scan(/ [A-Za-z_][A-Za-z_0-9]* /x)
kind = IDENT_KIND[match]
if kind == :ident and check(/:(?!:)/)
match << scan(/:/)
kind = :label
end
elsif match = scan(/L?"/)
tokens << [:open, :string]
if match[0] == ?L
tokens << ['L', :modifier]
match = '"'
end
state = :string
kind = :delimiter
elsif scan(%r! \@ .* !x)
kind = :preprocessor
elsif scan(/ L?' (?: [^\'\n\\] | \\ #{ESCAPE} )? '? /ox)
kind = :char
elsif scan(/0[xX][0-9A-Fa-f]+/)
kind = :hex
elsif scan(/(?:0[0-7]+)(?![89.eEfF])/)
kind = :oct
elsif scan(/(?:\d+)(?![.eEfF])/)
kind = :integer
elsif scan(/\d[fF]?|\d*\.\d+(?:[eE][+-]?\d+)?[fF]?|\d+[eE][+-]?\d+[fF]?/)
kind = :float
else
getch
kind = :error
end
when :string
if scan(/[^\\\n"]+/)
kind = :content
elsif scan(/"/)
tokens << ['"', :delimiter]
tokens << [:close, :string]
state = :initial
next
elsif scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox)
kind = :char
elsif scan(/ \\ | $ /x)
tokens << [:close, :string]
kind = :error
state = :initial
else
raise_inspect "else case \" reached; %p not handled." % peek(1), tokens
end
else
raise_inspect 'Unknown state', tokens
end
match ||= matched
if $DEBUG and not kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens
end
raise_inspect 'Empty token', tokens unless match
tokens << [match, kind]
end
if state == :string
tokens << [:close, :string]
end
tokens
end
end
end
end

View File

@ -1,176 +0,0 @@
# http://pastie.textmate.org/50774/
module CodeRay module Scanners
class JavaScript < Scanner
register_for :javascript
RESERVED_WORDS = [
'asm', 'break', 'case', 'continue', 'default', 'do', 'else',
'for', 'goto', 'if', 'return', 'switch', 'while',
# 'struct', 'union', 'enum', 'typedef',
# 'static', 'register', 'auto', 'extern',
# 'sizeof',
'typeof',
# 'volatile', 'const', # C89
# 'inline', 'restrict', # C99
'var', 'function','try','new','in',
'instanceof','throw','catch'
]
PREDEFINED_CONSTANTS = [
'void', 'null', 'this',
'true', 'false','undefined',
]
IDENT_KIND = WordList.new(:ident).
add(RESERVED_WORDS, :reserved).
add(PREDEFINED_CONSTANTS, :pre_constant)
ESCAPE = / [rbfnrtv\n\\\/'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} /x
UNICODE_ESCAPE = / u[a-fA-F0-9]{4} | U[a-fA-F0-9]{8} /x
def scan_tokens tokens, options
state = :initial
string_type = nil
regexp_allowed = true
until eos?
kind = :error
match = nil
if state == :initial
if scan(/ \s+ | \\\n /x)
kind = :space
elsif scan(%r! // [^\n\\]* (?: \\. [^\n\\]* )* | /\* (?: .*? \*/ | .* ) !mx)
kind = :comment
regexp_allowed = false
elsif match = scan(/ \# \s* if \s* 0 /x)
match << scan_until(/ ^\# (?:elif|else|endif) .*? $ | \z /xm) unless eos?
kind = :comment
regexp_allowed = false
elsif regexp_allowed and scan(/\//)
tokens << [:open, :regexp]
state = :regex
kind = :delimiter
elsif scan(/ [-+*\/=<>?:;,!&^|()\[\]{}~%] | \.(?!\d) /x)
kind = :operator
regexp_allowed=true
elsif match = scan(/ [$A-Za-z_][A-Za-z_0-9]* /x)
kind = IDENT_KIND[match]
# if kind == :ident and check(/:(?!:)/)
# match << scan(/:/)
# kind = :label
# end
regexp_allowed=false
elsif match = scan(/["']/)
tokens << [:open, :string]
string_type = matched
state = :string
kind = :delimiter
# elsif scan(/#\s*(\w*)/)
# kind = :preprocessor # FIXME multiline preprocs
# state = :include_expected if self[1] == 'include'
#
# elsif scan(/ L?' (?: [^\'\n\\] | \\ #{ESCAPE} )? '? /ox)
# kind = :char
elsif scan(/0[xX][0-9A-Fa-f]+/)
kind = :hex
regexp_allowed=false
elsif scan(/(?:0[0-7]+)(?![89.eEfF])/)
kind = :oct
regexp_allowed=false
elsif scan(/(?:\d+)(?![.eEfF])/)
kind = :integer
regexp_allowed=false
elsif scan(/\d[fF]?|\d*\.\d+(?:[eE][+-]?\d+)?[fF]?|\d+[eE][+-]?\d+[fF]?/)
kind = :float
regexp_allowed=false
else
getch
end
elsif state == :regex
if scan(/[^\\\/]+/)
kind = :content
elsif scan(/\\\/|\\\\/)
kind = :content
elsif scan(/\//)
tokens << [matched, :delimiter]
tokens << [:close, :regexp]
state = :initial
next
else
getch
kind = :content
end
elsif state == :string
if scan(/[^\\"']+/)
kind = :content
elsif scan(/["']/)
if string_type==matched
tokens << [matched, :delimiter]
tokens << [:close, :string]
state = :initial
string_type=nil
next
else
kind = :content
end
elsif scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox)
kind = :char
elsif scan(/ \\ | $ /x)
kind = :error
state = :initial
else
raise "else case \" reached; %p not handled." % peek(1), tokens
end
# elsif state == :include_expected
# if scan(/<[^>\n]+>?|"[^"\n\\]*(?:\\.[^"\n\\]*)*"?/)
# kind = :include
# state = :initial
#
# elsif match = scan(/\s+/)
# kind = :space
# state = :initial if match.index ?\n
#
# else
# getch
#
# end
#
else
raise 'else-case reached', tokens
end
match ||= matched
# raise [match, kind], tokens if kind == :error
tokens << [match, kind]
end
tokens
end
end
end end

View File

@ -1,165 +0,0 @@
module CodeRay module Scanners
class PHP < Scanner
register_for :php
RESERVED_WORDS = [
'and', 'or', 'xor', '__FILE__', 'exception', '__LINE__', 'array', 'as', 'break', 'case',
'class', 'const', 'continue', 'declare', 'default',
'die', 'do', 'echo', 'else', 'elseif',
'empty', 'enddeclare', 'endfor', 'endforeach', 'endif',
'endswitch', 'endwhile', 'eval', 'exit', 'extends',
'for', 'foreach', 'function', 'global', 'if',
'include', 'include_once', 'isset', 'list', 'new',
'print', 'require', 'require_once', 'return', 'static',
'switch', 'unset', 'use', 'var', 'while',
'__FUNCTION__', '__CLASS__', '__METHOD__', 'final', 'php_user_filter',
'interface', 'implements', 'extends', 'public', 'private',
'protected', 'abstract', 'clone', 'try', 'catch',
'throw', 'cfunction', 'old_function'
]
PREDEFINED_CONSTANTS = [
'null', '$this', 'true', 'false'
]
IDENT_KIND = WordList.new(:ident).
add(RESERVED_WORDS, :reserved).
add(PREDEFINED_CONSTANTS, :pre_constant)
ESCAPE = / [\$\wrbfnrtv\n\\\/'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} /x
UNICODE_ESCAPE = / u[a-fA-F0-9]{4} | U[a-fA-F0-9]{8} /x
def scan_tokens tokens, options
state = :waiting_php
string_type = nil
regexp_allowed = true
until eos?
kind = :error
match = nil
if state == :initial
if scan(/ \s+ | \\\n /x)
kind = :space
elsif scan(/\?>/)
kind = :char
state = :waiting_php
elsif scan(%r{ (//|\#) [^\n\\]* (?: \\. [^\n\\]* )* | /\* (?: .*? \*/ | .* ) }mx)
kind = :comment
regexp_allowed = false
elsif match = scan(/ \# \s* if \s* 0 /x)
match << scan_until(/ ^\# (?:elif|else|endif) .*? $ | \z /xm) unless eos?
kind = :comment
regexp_allowed = false
elsif regexp_allowed and scan(/\//)
tokens << [:open, :regexp]
state = :regex
kind = :delimiter
elsif scan(/ [-+*\/=<>?:;,!&^|()\[\]{}~%] | \.(?!\d) /x)
kind = :operator
regexp_allowed=true
elsif match = scan(/ [$@A-Za-z_][A-Za-z_0-9]* /x)
kind = IDENT_KIND[match]
regexp_allowed=false
elsif match = scan(/["']/)
tokens << [:open, :string]
string_type = matched
state = :string
kind = :delimiter
elsif scan(/0[xX][0-9A-Fa-f]+/)
kind = :hex
regexp_allowed=false
elsif scan(/(?:0[0-7]+)(?![89.eEfF])/)
kind = :oct
regexp_allowed=false
elsif scan(/(?:\d+)(?![.eEfF])/)
kind = :integer
regexp_allowed=false
elsif scan(/\d[fF]?|\d*\.\d+(?:[eE][+-]?\d+)?[fF]?|\d+[eE][+-]?\d+[fF]?/)
kind = :float
regexp_allowed=false
else
getch
end
elsif state == :regex
if scan(/[^\\\/]+/)
kind = :content
elsif scan(/\\\/|\\/)
kind = :content
elsif scan(/\//)
tokens << [matched, :delimiter]
tokens << [:close, :regexp]
state = :initial
next
else
getch
kind = :content
end
elsif state == :string
if scan(/[^\\"']+/)
kind = :content
elsif scan(/["']/)
if string_type==matched
tokens << [matched, :delimiter]
tokens << [:close, :string]
state = :initial
string_type=nil
next
else
kind = :content
end
elsif scan(/ \\ (?: \S ) /mox)
kind = :char
elsif scan(/ \\ | $ /x)
kind = :error
state = :initial
else
raise "else case \" reached; %p not handled." % peek(1), tokens
end
elsif state == :waiting_php
if scan(/<\?php/m)
kind = :char
state = :initial
elsif scan(/[^<]+/)
kind = :comment
else
kind = :comment
getch
end
else
raise 'else-case reached', tokens
end
match ||= matched
tokens << [match, kind]
end
tokens
end
end
end end

View File

@ -1,7 +1,7 @@
= CodeRay
[- Tired of blue'n'gray? Try the original version of this documentation on
http://rd.cYcnus.de/coderay/doc (use Ctrl+Click to open it in its own frame.) -]
coderay.rubychan.de[http://coderay.rubychan.de/doc/] (use Ctrl+Click to open it in its own frame.) -]
== About
CodeRay is a Ruby library for syntax highlighting.
@ -18,14 +18,11 @@ And with line numbers.
* is what everybody should have on their website
* solves all your problems and makes the girls run after you
Version: 0.7.4 (2006.october.20)
Version: 0.9.2
Author:: murphy (Kornelius Kalnbach)
Contact:: murphy rubychan de
Website:: coderay.rubychan.de[http://coderay.rubychan.de]
License:: GNU LGPL; see LICENSE file in the main directory.
Subversion:: $Id: README 219 2006-10-20 15:52:25Z murphy $
-----
== Installation
@ -33,17 +30,10 @@ You need RubyGems[http://rubyforge.org/frs/?group_id=126].
% gem install coderay
Since CodeRay is still in beta stage, nightly buildy may be useful:
% gem install coderay -rs rd.cYcnus.de/coderay
=== Dependencies
CodeRay needs Ruby 1.8 and the
strscan[http://www.ruby-doc.org/stdlib/libdoc/strscan/rdoc/index.htm]
library (part of the standard library.) It should also run with Ruby 1.9 and
yarv.
CodeRay needs Ruby 1.8.6 or later. It also runs with Ruby 1.9.1+ and JRuby 1.1+.
== Example Usage
@ -60,11 +50,9 @@ yarv.
See CodeRay.
Please report errors in this documentation to <coderay cycnus de>.
Please report errors in this documentation to <murphy rubychan de>.
-----
== Credits
=== Special Thanks to
@ -72,30 +60,43 @@ Please report errors in this documentation to <coderay cycnus de>.
* licenser (Heinz N. Gies) for ending my QBasic career, inventing the Coder
project and the input/output plugin system.
CodeRay would not exist without him.
* bovi (Daniel Bovensiepen) for helping me out on various occasions.
=== Thanks to
* Caleb Clausen for writing RubyLexer (see
http://rubyforge.org/projects/rubylexer) and lots of very interesting mail
traffic
* birkenfeld (Georg Brandl) and mitsuhiku (Arnim Ronacher) for PyKleur. You
guys rock!
* birkenfeld (Georg Brandl) and mitsuhiku (Arnim Ronacher) for PyKleur, now pygments.
You guys rock!
* Jamis Buck for writing Syntax (see http://rubyforge.org/projects/syntax)
I got some useful ideas from it.
* Doug Kearns and everyone else who worked on ruby.vim - it not only helped me
coding CodeRay, but also gave me a wonderful target to reach for the Ruby
scanner.
* everyone who used CodeBB on http://www.rubyforen.de and
http://www.infhu.de/mx
* iGEL, magichisoka, manveru, WoNáDo and everyone I forgot from rubyforen.de
* Daniel and Dethix from ruby-mine.de
* Dookie (who is no longer with us...) and Leonidas from
http://www.python-forum.de
* everyone who uses CodeBB on http://www.rubyforen.de and http://www.python-forum.de
* iGEL, magichisoka, manveru, WoNáDo and everyone I forgot from rubyforen.de
* Dethix from ruby-mine.de
* zickzackw
* Dookie (who is no longer with us...) and Leonidas from http://www.python-forum.de
* Andreas Schwarz for finding out that CaseIgnoringWordList was not case
ignoring! Such things really make you write tests.
* closure for the first version of the Scheme scanner.
* Stefan Walk for the first version of the JavaScript and PHP scanners.
* Josh Goebel for another version of the JavaScript scanner, a SQL and a Diff scanner.
* Jonathan Younger for pointing out the licence confusion caused by wrong LICENSE file.
* Jeremy Hinegardner for finding the shebang-on-empty-file bug in FileType.
* Charles Oliver Nutter and Yehuda Katz for helping me benchmark CodeRay on JRuby.
* Andreas Neuhaus for pointing out a markup bug in coderay/for_redcloth.
* 0xf30fc7 for the FileType patch concerning Delphi file extensions.
* The folks at redmine.org - thank you for using and fixing CodeRay!
* Keith Pitt for his SQL scanners
* Rob Aldred for the terminal encoder
* Trans for pointing out $DEBUG dependencies
* Flameeyes for finding that Term::ANSIColor was obsolete
* matz and all Ruby gods and gurus
* The inventors of: the computer, the internet, the true color display, HTML &
CSS, VIM, RUBY, pizza, microwaves, guitars, scouting, programming, anime,
CSS, VIM, Ruby, pizza, microwaves, guitars, scouting, programming, anime,
manga, coke and green ice tea.
Where would we be without all those people?
@ -103,23 +104,27 @@ Where would we be without all those people?
=== Created using
* Ruby[http://ruby-lang.org/]
* Chihiro (my Sony VAIO laptop), Henrietta (my new MacBook) and
Seras (my Athlon 2200+ tower)
* VIM[http://vim.org] and TextMate[http://macromates.com]
* RDE[http://homepage2.nifty.com/sakazuki/rde_e.html]
* Microsoft Windows (yes, I confess!) and MacOS X
* Firefox[http://www.mozilla.org/products/firefox/] and
* Chihiro (my Sony VAIO laptop); Henrietta (my old MacBook);
Triella, born Rico (my new MacBook); as well as
Seras and Hikari (my PCs)
* RDE[http://homepage2.nifty.com/sakazuki/rde_e.html],
VIM[http://vim.org] and TextMate[http://macromates.com]
* Subversion[http://subversion.tigris.org/]
* Redmine[http://redmine.org/]
* Firefox[http://www.mozilla.org/products/firefox/],
Firebug[http://getfirebug.com/], Safari[http://www.apple.com/safari/], and
Thunderbird[http://www.mozilla.org/products/thunderbird/]
* Rake[http://rake.rubyforge.org/]
* RubyGems[http://docs.rubygems.org/]
* {Subversion/TortoiseSVN}[http://tortoisesvn.tigris.org/] using Apache via
* RubyGems[http://docs.rubygems.org/] and Rake[http://rake.rubyforge.org/]
* TortoiseSVN[http://tortoisesvn.tigris.org/] using Apache via
XAMPP[http://www.apachefriends.org/en/xampp.html]
* RDoc (though I'm quite unsatisfied with it)
* Microsoft Windows (yes, I confess!) and MacOS X
* GNUWin32, MinGW and some other tools to make the shell under windows a bit
more useful
less useless
* Term::ANSIColor[http://term-ansicolor.rubyforge.org/]
* PLEAC[http://pleac.sourceforge.net/] code examples
---
=== Free
* As you can see, CodeRay was created under heavy use of *free* software.
* So CodeRay is also *free*.

View File

@ -1,7 +1,5 @@
# = CodeRay Library
#
# $Id: coderay.rb 227 2007-04-24 12:26:18Z murphy $
#
# CodeRay is a Ruby library for syntax highlighting.
#
# I try to make CodeRay easy to use and intuitive, but at the same time fully featured, complete,
@ -16,7 +14,7 @@
#
# Here's a fancy graphic to light up this gray docu:
#
# http://rd.cYcnus.de/coderay/scheme.png
# http://cycnus.de/raindark/coderay/scheme.png
#
# == Documentation
#
@ -107,7 +105,7 @@
#
# CodeRay.scan_stream:: Scan in stream mode.
#
# == All-in-One Encoding
# == All-in-One Encoding
#
# CodeRay.encode:: Highlight a string with a given input and output format.
#
@ -128,15 +126,18 @@
# If you want to re-use scanners and encoders (because that is faster), see
# CodeRay::Duo for the most convenient (and recommended) interface.
module CodeRay
$CODERAY_DEBUG ||= false
# Version: Major.Minor.Teeny[.Revision]
# Major: 0 for pre-release
# Minor: odd for beta, even for stable
# Teeny: development state
# Revision: Subversion Revision number (generated on rake)
VERSION = '0.7.6'
# Major: 0 for pre-stable, 1 for stable
# Minor: feature milestone
# Teeny: development state, 0 for pre-release
# Revision: Subversion Revision number (generated on rake gem:make)
VERSION = '0.9.2'
require 'coderay/tokens'
require 'coderay/token_classes'
require 'coderay/scanner'
require 'coderay/encoder'
require 'coderay/duo'
@ -315,6 +316,7 @@ end
# Run a test script.
if $0 == __FILE__
$stderr.print 'Press key to print demo.'; gets
# Just use this file as an example of Ruby code.
code = File.read(__FILE__)[/module CodeRay.*/m]
print CodeRay.scan(code, :ruby).html
end

View File

@ -2,8 +2,6 @@ module CodeRay
# = Duo
#
# $Id: scanner.rb 123 2006-03-21 14:46:34Z murphy $
#
# A Duo is a convenient way to use CodeRay. You just create a Duo,
# giving it a lang (language of the input code) and a format (desired
# output format), and call Duo#highlight with the code.

View File

@ -1,5 +1,3 @@
require "stringio"
module CodeRay
# This module holds the Encoder class and its subclasses.
@ -126,36 +124,66 @@ module CodeRay
@out = ''
end
# Called with +text+ and +kind+ of the currently scanned token.
# Called with +content+ and +kind+ of the currently scanned token.
# For simple scanners, it's enougth to implement this method.
#
# By default, it calls text_token or block_token, depending on
# whether +text+ is a String.
def token text, kind
out =
if text.is_a? ::String # Ruby 1.9: :open.is_a? String
text_token text, kind
elsif text.is_a? ::Symbol
block_token text, kind
# whether +content+ is a String.
def token content, kind
encoded_token =
if content.is_a? ::String
text_token content, kind
elsif content.is_a? ::Symbol
block_token content, kind
else
raise 'Unknown token text type: %p' % text
raise 'Unknown token content type: %p' % [content]
end
@out << out if @out
append_encoded_token_to_output encoded_token
end
def append_encoded_token_to_output encoded_token
@out << encoded_token if encoded_token && defined?(@out) && @out
end
# Called for each text token ([text, kind]), where text is a String.
def text_token text, kind
end
# Called for each block (non-text) token ([action, kind]),
# where +action+ is a Symbol.
#
# Calls open_token, close_token, begin_line, and end_line according to
# the value of +action+.
def block_token action, kind
case action
when :open
open_token kind
when :close
close_token kind
when :begin_line
begin_line kind
when :end_line
end_line kind
else
raise 'unknown block action: %p' % action
end
end
# Called for each block token at the start of the block ([:open, kind]).
def open_token kind
end
# Called for each block token end of the block ([:close, kind]).
def close_token kind
end
# Called for each line token block at the start of the line ([:begin_line, kind]).
def begin_line kind
end
# Called for each line token block at the end of the line ([:end_line, kind]).
def end_line kind
end
# Called with merged options after encoding starts.
# The return value is the result of encoding, typically @out.
@ -167,8 +195,16 @@ module CodeRay
#
# The already created +tokens+ object must be used; it can be a
# TokenStream or a Tokens object.
def compile tokens, options
tokens.each(&self)
if RUBY_VERSION >= '1.9'
def compile tokens, options
for text, kind in tokens
token text, kind
end
end
else
def compile tokens, options
tokens.each(&self)
end
end
end

View File

@ -0,0 +1,12 @@
module CodeRay
module Encoders
map \
:loc => :lines_of_code,
:plain => :text,
:stats => :statistic,
:terminal => :term,
:tex => :latex
end
end

View File

@ -0,0 +1,43 @@
($:.unshift '../..'; require 'coderay') unless defined? CodeRay
module CodeRay
module Encoders
load :token_class_filter
class CommentFilter < TokenClassFilter
register_for :comment_filter
DEFAULT_OPTIONS = superclass::DEFAULT_OPTIONS.merge \
:exclude => [:comment]
end
end
end
if $0 == __FILE__
$VERBOSE = true
$: << File.join(File.dirname(__FILE__), '..')
eval DATA.read, nil, $0, __LINE__ + 4
end
__END__
require 'test/unit'
class CommentFilterTest < Test::Unit::TestCase
def test_filtering_comments
tokens = CodeRay.scan <<-RUBY, :ruby
#!/usr/bin/env ruby
# a minimal Ruby program
puts "Hello world!"
RUBY
assert_equal <<-RUBY_FILTERED, tokens.comment_filter.text
#!/usr/bin/env ruby
puts "Hello world!"
RUBY_FILTERED
end
end

View File

@ -35,6 +35,14 @@ module Encoders
">"
end
def begin_line kind
"#{kind}["
end
def end_line kind
"]"
end
end
end

View File

@ -9,10 +9,9 @@ module Encoders
register_for :div
DEFAULT_OPTIONS = HTML::DEFAULT_OPTIONS.merge({
DEFAULT_OPTIONS = HTML::DEFAULT_OPTIONS.merge \
:css => :style,
:wrap => :div,
})
:wrap => :div
end

View File

@ -0,0 +1,75 @@
($:.unshift '../..'; require 'coderay') unless defined? CodeRay
module CodeRay
module Encoders
class Filter < Encoder
register_for :filter
protected
def setup options
@out = Tokens.new
end
def text_token text, kind
[text, kind] if include_text_token? text, kind
end
def include_text_token? text, kind
true
end
def block_token action, kind
[action, kind] if include_block_token? action, kind
end
def include_block_token? action, kind
true
end
end
end
end
if $0 == __FILE__
$VERBOSE = true
$: << File.join(File.dirname(__FILE__), '..')
eval DATA.read, nil, $0, __LINE__ + 4
end
__END__
require 'test/unit'
class FilterTest < Test::Unit::TestCase
def test_creation
assert CodeRay::Encoders::Filter < CodeRay::Encoders::Encoder
filter = nil
assert_nothing_raised do
filter = CodeRay.encoder :filter
end
assert_kind_of CodeRay::Encoders::Encoder, filter
end
def test_filtering_text_tokens
tokens = CodeRay::Tokens.new
10.times do |i|
tokens << [i.to_s, :index]
end
assert_equal tokens, CodeRay::Encoders::Filter.new.encode_tokens(tokens)
assert_equal tokens, tokens.filter
end
def test_filtering_block_tokens
tokens = CodeRay::Tokens.new
10.times do |i|
tokens << [:open, :index]
tokens << [i.to_s, :content]
tokens << [:close, :index]
end
assert_equal tokens, CodeRay::Encoders::Filter.new.encode_tokens(tokens)
assert_equal tokens, tokens.filter
end
end

View File

@ -1,4 +1,4 @@
require "set"
require 'set'
module CodeRay
module Encoders
@ -25,10 +25,6 @@ module Encoders
#
# == Options
#
# === :escape
# Escape html entities
# Default: true
#
# === :tab_width
# Convert \t characters to +n+ spaces (a number.)
# Default: 8
@ -45,6 +41,12 @@ module Encoders
#
# Default: nil
#
# === :title
#
# The title of the HTML page (works only when :wrap is set to :page.)
#
# Default: 'CodeRay output'
#
# === :line_numbers
# Include line numbers in :table, :inline, :list or nil (no line numbers)
#
@ -60,6 +62,16 @@ module Encoders
#
# Default: 10
#
# === :highlight_lines
#
# Highlights certain line numbers.
# Can be any Enumerable, typically just an Array or Range, of numbers.
#
# Bolding is deactivated when :highlight_lines is set. It only makes sense
# in combination with :line_numbers.
#
# Default: nil
#
# === :hint
# Include some information into the output using the title attribute.
# Can be :info (show token type on mouse-over), :info_long (with full path)
@ -74,19 +86,18 @@ module Encoders
FILE_EXTENSION = 'html'
DEFAULT_OPTIONS = {
:escape => true,
:tab_width => 8,
:level => :xhtml,
:css => :class,
:style => :cycnus,
:wrap => nil,
:title => 'CodeRay output',
:line_numbers => nil,
:line_number_start => 1,
:bold_every => 10,
:highlight_lines => nil,
:hint => false,
}
@ -141,7 +152,7 @@ module Encoders
when :debug
classes.inspect
end
" title=\"#{title}\""
title ? " title=\"#{title}\"" : ''
end
def setup options
@ -150,7 +161,6 @@ module Encoders
@HTML_ESCAPE = HTML_ESCAPE.dup
@HTML_ESCAPE["\t"] = ' ' * options[:tab_width]
@escape = options[:escape]
@opened = [nil]
@css = CSS.new options[:style]
@ -164,7 +174,7 @@ module Encoders
when :class
@css_style = Hash.new do |h, k|
c = Tokens::ClassOfKind[k.first]
c = CodeRay::Tokens::ClassOfKind[k.first]
if c == :NO_HIGHLIGHT and not hint
h[k.dup] = false
else
@ -222,43 +232,70 @@ module Encoders
@out.css = @css
@out.numerize! options[:line_numbers], options
@out.wrap! options[:wrap]
@out.apply_title! options[:title]
super
end
def token text, type
if text.is_a? ::String
if @escape && (text =~ /#{HTML_ESCAPE_PATTERN}/o)
def token text, type = :plain
case text
when nil
# raise 'Token with nil as text was given: %p' % [[text, type]]
when String
if text =~ /#{HTML_ESCAPE_PATTERN}/o
text = text.gsub(/#{HTML_ESCAPE_PATTERN}/o) { |m| @HTML_ESCAPE[m] }
end
@opened[0] = type
if style = @css_style[@opened]
if text != "\n" && style = @css_style[@opened]
@out << style << text << '</span>'
else
@out << text
end
else
case text
when :open
@opened[0] = type
@out << (@css_style[@opened] || '<span>')
@opened << type
when :close
if @opened.empty?
# nothing to close
else
if $DEBUG and (@opened.size == 1 or @opened.last != type)
raise 'Malformed token stream: Trying to close a token (%p) \
that is not open. Open are: %p.' % [type, @opened[1..-1]]
end
@out << '</span>'
@opened.pop
end
when nil
raise 'Token with nil as text was given: %p' % [[text, type]]
# token groups, eg. strings
when :open
@opened[0] = type
@out << (@css_style[@opened] || '<span>')
@opened << type
when :close
if @opened.empty?
# nothing to close
else
raise 'unknown token kind: %p' % text
if $CODERAY_DEBUG and (@opened.size == 1 or @opened.last != type)
raise 'Malformed token stream: Trying to close a token (%p) \
that is not open. Open are: %p.' % [type, @opened[1..-1]]
end
@out << '</span>'
@opened.pop
end
# whole lines to be highlighted, eg. a deleted line in a diff
when :begin_line
@opened[0] = type
if style = @css_style[@opened]
@out << style.sub('<span', '<div')
else
@out << '<div>'
end
@opened << type
when :end_line
if @opened.empty?
# nothing to close
else
if $CODERAY_DEBUG and (@opened.size == 1 or @opened.last != type)
raise 'Malformed token stream: Trying to close a line (%p) \
that is not open. Open are: %p.' % [type, @opened[1..-1]]
end
@out << '</div>'
@opened.pop
end
else
raise 'unknown token kind: %p' % [text]
end
end

View File

@ -27,16 +27,19 @@ module Encoders
1.upto(styles.size) do |offset|
break if style = cl[styles[offset .. -1]]
end
raise 'Style not found: %p' % [styles] if $DEBUG and style.empty?
# warn 'Style not found: %p' % [styles] if style.empty?
return style
end
private
CSS_CLASS_PATTERN = /
( (?: # $1 = classes
\s* \. [-\w]+
)+ )
( # $1 = selectors
(?:
(?: \s* \. [-\w]+ )+
\s* ,?
)+
)
\s* \{ \s*
( [^\}]+ )? # $2 = style
\s* \} \s*
@ -44,12 +47,14 @@ module Encoders
( . ) # $3 = error
/mx
def parse stylesheet
stylesheet.scan CSS_CLASS_PATTERN do |classes, style, error|
stylesheet.scan CSS_CLASS_PATTERN do |selectors, style, error|
raise "CSS parse error: '#{error.inspect}' not recognized" if error
styles = classes.scan(/[-\w]+/)
cl = styles.pop
@classes[cl] ||= Hash.new
@classes[cl][styles] = style.to_s.strip
for selector in selectors.split(',')
classes = selector.scan(/[-\w]+/)
cl = classes.pop
@classes[cl] ||= Hash.new
@classes[cl][classes] = style.to_s.strip.delete(' ').chomp(';')
end
end
end

View File

@ -32,9 +32,19 @@ module Encoders
#end
bold_every = options[:bold_every]
highlight_lines = options[:highlight_lines]
bolding =
if bold_every == false
if bold_every == false && highlight_lines == nil
proc { |line| line.to_s }
elsif highlight_lines.is_a? Enumerable
highlight_lines = highlight_lines.to_set
proc do |line|
if highlight_lines.include? line
"<strong class=\"highlighted\">#{line}</strong>" # highlighted line numbers in bold
else
line.to_s
end
end
elsif bold_every.is_a? Integer
raise ArgumentError, ":bolding can't be 0." if bold_every == 0
proc do |line|
@ -51,12 +61,12 @@ module Encoders
case mode
when :inline
max_width = (start + line_count).to_s.size
line = start
line_number = start
gsub!(/^/) do
line_number = bolding.call line
indent = ' ' * (max_width - line.to_s.size)
res = "<span class=\"no\">#{indent}#{line_number}</span> "
line += 1
line_number_text = bolding.call line_number
indent = ' ' * (max_width - line_number.to_s.size) # TODO: Optimize (10^x)
res = "<span class=\"no\">#{indent}#{line_number_text}</span> "
line_number += 1
res
end
@ -65,12 +75,12 @@ module Encoders
# Because even monospace fonts seem to have different heights when bold,
# I make the newline bold, both in the code and the line numbers.
# FIXME Still not working perfect for Mr. Internet Exploder
# FIXME Firefox struggles with very long codes (> 200 lines)
line_numbers = (start ... start + line_count).to_a.map(&bolding).join("\n")
line_numbers << "\n" # also for Mr. MS Internet Exploder :-/
line_numbers.gsub!(/\n/) { "<tt>\n</tt>" }
line_numbers_table_tpl = TABLE.apply('LINE_NUMBERS', line_numbers)
gsub!(/<\/div>\n/) { '</div>' }
gsub!(/\n/) { "<tt>\n</tt>" }
wrap_in! line_numbers_table_tpl
@wrapped_in = :div
@ -90,8 +100,9 @@ module Encoders
end
close = '</span>' * opened_tags.size
"<li>#{open}#{line}#{close}</li>"
"<li>#{open}#{line}#{close}</li>\n"
end
chomp!("\n")
wrap_in! LIST
@wrapped_in = :div

View File

@ -86,6 +86,11 @@ module Encoders
Template.wrap! self, template, 'CONTENT'
self
end
def apply_title! title
self.sub!(/(<title>)(<\/title>)/) { $1 + title + $2 }
self
end
def wrap! element, *args
return self if not element or element == wrapped_in
@ -100,6 +105,10 @@ module Encoders
wrap! :div if wrapped_in? nil
raise "Can't wrap %p in %p" % [wrapped_in, element] unless wrapped_in? :div
wrap_in! Output.page_template_for_css(@css)
if args.first.is_a?(Hash) && title = args.first[:title]
apply_title! title
end
self
when nil
return self
else
@ -166,7 +175,9 @@ module Encoders
# title="double click to expand"
LIST = <<-`LIST`
<ol class="CodeRay"><%CONTENT%></ol>
<ol class="CodeRay">
<%CONTENT%>
</ol>
LIST
PAGE = <<-`PAGE`
@ -175,7 +186,7 @@ module Encoders
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="de">
<head>
<meta http-equiv="content-type" content="text/html; charset=utf-8" />
<title>CodeRay HTML Encoder Example</title>
<title></title>
<style type="text/css">
<%CSS%>
</style>

View File

@ -0,0 +1,69 @@
($:.unshift '../..'; require 'coderay') unless defined? CodeRay
module CodeRay
module Encoders
# = JSON Encoder
class JSON < Encoder
register_for :json
FILE_EXTENSION = 'json'
protected
def setup options
begin
require 'json'
rescue LoadError
require 'rubygems'
require 'json'
end
@out = []
end
def text_token text, kind
{ :type => 'text', :text => text, :kind => kind }
end
def block_token action, kind
{ :type => 'block', :action => action, :kind => kind }
end
def finish options
@out.to_json
end
end
end
end
if $0 == __FILE__
$VERBOSE = true
$: << File.join(File.dirname(__FILE__), '..')
eval DATA.read, nil, $0, __LINE__ + 4
end
__END__
require 'test/unit'
$:.delete '.'
require 'rubygems' if RUBY_VERSION < '1.9'
class JSONEncoderTest < Test::Unit::TestCase
def test_json_output
tokens = CodeRay.scan <<-RUBY, :ruby
puts "Hello world!"
RUBY
require 'json'
assert_equal [
{"type"=>"text", "text"=>"puts", "kind"=>"ident"},
{"type"=>"text", "text"=>" ", "kind"=>"space"},
{"type"=>"block", "action"=>"open", "kind"=>"string"},
{"type"=>"text", "text"=>"\"", "kind"=>"delimiter"},
{"type"=>"text", "text"=>"Hello world!", "kind"=>"content"},
{"type"=>"text", "text"=>"\"", "kind"=>"delimiter"},
{"type"=>"block", "action"=>"close", "kind"=>"string"},
{"type"=>"text", "text"=>"\n", "kind"=>"space"}
], JSON.load(tokens.json)
end
end

View File

@ -0,0 +1,90 @@
($:.unshift '../..'; require 'coderay') unless defined? CodeRay
module CodeRay
module Encoders
# Counts the LoC (Lines of Code). Returns an Integer >= 0.
#
# Alias: :loc
#
# Everything that is not comment, markup, doctype/shebang, or an empty line,
# is considered to be code.
#
# For example,
# * HTML files not containing JavaScript have 0 LoC
# * in a Java class without comments, LoC is the number of non-empty lines
#
# A Scanner class should define the token kinds that are not code in the
# KINDS_NOT_LOC constant, which defaults to [:comment, :doctype].
class LinesOfCode < Encoder
register_for :lines_of_code
NON_EMPTY_LINE = /^\s*\S.*$/
def compile tokens, options
if scanner = tokens.scanner
kinds_not_loc = scanner.class::KINDS_NOT_LOC
else
warn ArgumentError, 'Tokens have no scanner.' if $VERBOSE
kinds_not_loc = CodeRay::Scanners::Scanner::KINDS_NOT_LOC
end
code = tokens.token_class_filter :exclude => kinds_not_loc
@loc = code.text.scan(NON_EMPTY_LINE).size
end
def finish options
@loc
end
end
end
end
if $0 == __FILE__
$VERBOSE = true
$: << File.join(File.dirname(__FILE__), '..')
eval DATA.read, nil, $0, __LINE__ + 4
end
__END__
require 'test/unit'
class LinesOfCodeTest < Test::Unit::TestCase
def test_creation
assert CodeRay::Encoders::LinesOfCode < CodeRay::Encoders::Encoder
filter = nil
assert_nothing_raised do
filter = CodeRay.encoder :loc
end
assert_kind_of CodeRay::Encoders::LinesOfCode, filter
assert_nothing_raised do
filter = CodeRay.encoder :lines_of_code
end
assert_kind_of CodeRay::Encoders::LinesOfCode, filter
end
def test_lines_of_code
tokens = CodeRay.scan <<-RUBY, :ruby
#!/usr/bin/env ruby
# a minimal Ruby program
puts "Hello world!"
RUBY
assert_equal 1, CodeRay::Encoders::LinesOfCode.new.encode_tokens(tokens)
assert_equal 1, tokens.lines_of_code
assert_equal 1, tokens.loc
end
def test_filtering_block_tokens
tokens = CodeRay::Tokens.new
tokens << ["Hello\n", :world]
tokens << ["Hello\n", :space]
tokens << ["Hello\n", :comment]
assert_equal 2, CodeRay::Encoders::LinesOfCode.new.encode_tokens(tokens)
assert_equal 2, tokens.lines_of_code
assert_equal 2, tokens.loc
end
end

View File

@ -9,11 +9,10 @@ module Encoders
register_for :page
DEFAULT_OPTIONS = HTML::DEFAULT_OPTIONS.merge({
DEFAULT_OPTIONS = HTML::DEFAULT_OPTIONS.merge \
:css => :class,
:wrap => :page,
:line_numbers => :table
})
end

View File

@ -9,10 +9,9 @@ module Encoders
register_for :span
DEFAULT_OPTIONS = HTML::DEFAULT_OPTIONS.merge({
DEFAULT_OPTIONS = HTML::DEFAULT_OPTIONS.merge \
:css => :style,
:wrap => :span,
})
:wrap => :span
end

View File

@ -0,0 +1,158 @@
# encoders/term.rb
# By Rob Aldred (http://robaldred.co.uk)
# Based on idea by Nathan Weizenbaum (http://nex-3.com)
# MIT License (http://www.opensource.org/licenses/mit-license.php)
#
# A CodeRay encoder that outputs code highlighted for a color terminal.
# Check out http://robaldred.co.uk
module CodeRay
module Encoders
class Term < Encoder
register_for :term
TOKEN_COLORS = {
:annotation => '35',
:attribute_name => '33',
:attribute_name_fat => '33',
:attribute_value => '31',
:attribute_value_fat => '31',
:bin => '1;35',
:char => {:self => '36', :delimiter => '34'},
:class => '1;35',
:class_variable => '36',
:color => '32',
:comment => '37',
:complex => '34',
:constant => ['34', '4'],
:decoration => '35',
:definition => '1;32',
:directive => ['32', '4'],
:doc => '46',
:doctype => '1;30',
:doc_string => ['31', '4'],
:entity => '33',
:error => ['1;33', '41'],
:exception => '1;31',
:float => '1;35',
:function => '1;34',
:global_variable => '42',
:hex => '1;36',
:important => '1;31',
:include => '33',
:integer => '1;34',
:interpreted => '1;35',
:key => '35',
:label => '1;4',
:local_variable => '33',
:oct => '1;35',
:operator_name => '1;29',
:pre_constant => '1;36',
:pre_type => '1;30',
:predefined => ['4', '1;34'],
:preprocessor => '36',
:pseudo_class => '34',
:regexp => {
:content => '31',
:delimiter => '1;29',
:modifier => '35',
:function => '1;29'
},
:reserved => '1;31',
:shell => {
:self => '42',
:content => '1;29',
:delimiter => '37',
},
:string => {
:self => '32',
:modifier => '1;32',
:escape => '1;36',
:delimiter => '1;32',
},
:symbol => '1;32',
:tag => '34',
:tag_fat => '1;34',
:tag_special => ['34', '4'],
:type => '1;34',
:value => '36',
:variable => '34',
:insert => '42',
:delete => '41',
:change => '44',
:head => '45',
}
TOKEN_COLORS[:keyword] = TOKEN_COLORS[:reserved]
TOKEN_COLORS[:method] = TOKEN_COLORS[:function]
TOKEN_COLORS[:imaginary] = TOKEN_COLORS[:complex]
TOKEN_COLORS[:open] = TOKEN_COLORS[:close] = TOKEN_COLORS[:nesting_delimiter] = TOKEN_COLORS[:escape] = TOKEN_COLORS[:delimiter]
protected
def setup(options)
@out = ''
@opened = [nil]
@subcolors = nil
end
def finish(options)
super
end
def token text, type = :plain
case text
when nil
# raise 'Token with nil as text was given: %p' % [[text, type]]
when String
if color = (@subcolors || TOKEN_COLORS)[type]
color = color[:self] || return if Hash === color
@out << col(color) + text.gsub("\n", col(0) + "\n" + col(color)) + col(0)
@out << col(@subcolors[:self]) if @subcolors && @subcolors[:self]
else
@out << text
end
# token groups, eg. strings
when :open
@opened[0] = type
if color = TOKEN_COLORS[type]
if Hash === color
@subcolors = color
@out << col(color[:self]) if color[:self]
else
@subcolors = {}
@out << col(color)
end
end
@opened << type
when :close
if @opened.empty?
# nothing to close
else
@out << col(0) if (@subcolors || {})[:self]
@subcolors = nil
@opened.pop
end
# whole lines to be highlighted, eg. a added/modified/deleted lines in a diff
when :begin_line
when :end_line
else
raise 'unknown token kind: %p' % [text]
end
end
private
def col(color)
Array(color).map { |c| "\e[#{c}m" }.join
end
end
end
end

View File

@ -14,16 +14,16 @@ module Encoders
protected
def setup options
@out = ''
super
@sep = options[:separator]
end
def token text, kind
@out << text + @sep if text.is_a? ::String
def text_token text, kind
text + @sep
end
def finish options
@out.chomp @sep
super.chomp @sep
end
end

View File

@ -0,0 +1,84 @@
($:.unshift '../..'; require 'coderay') unless defined? CodeRay
module CodeRay
module Encoders
load :filter
class TokenClassFilter < Filter
include Streamable
register_for :token_class_filter
DEFAULT_OPTIONS = {
:exclude => [],
:include => :all
}
protected
def setup options
super
@exclude = options[:exclude]
@exclude = Array(@exclude) unless @exclude == :all
@include = options[:include]
@include = Array(@include) unless @include == :all
end
def include_text_token? text, kind
(@include == :all || @include.include?(kind)) &&
!(@exclude == :all || @exclude.include?(kind))
end
end
end
end
if $0 == __FILE__
$VERBOSE = true
$: << File.join(File.dirname(__FILE__), '..')
eval DATA.read, nil, $0, __LINE__ + 4
end
__END__
require 'test/unit'
class TokenClassFilterTest < Test::Unit::TestCase
def test_creation
assert CodeRay::Encoders::TokenClassFilter < CodeRay::Encoders::Encoder
assert CodeRay::Encoders::TokenClassFilter < CodeRay::Encoders::Filter
filter = nil
assert_nothing_raised do
filter = CodeRay.encoder :token_class_filter
end
assert_instance_of CodeRay::Encoders::TokenClassFilter, filter
end
def test_filtering_text_tokens
tokens = CodeRay::Tokens.new
for i in 1..10
tokens << [i.to_s, :index]
tokens << [' ', :space] if i < 10
end
assert_equal 10, CodeRay::Encoders::TokenClassFilter.new.encode_tokens(tokens, :exclude => :space).size
assert_equal 10, tokens.token_class_filter(:exclude => :space).size
assert_equal 9, CodeRay::Encoders::TokenClassFilter.new.encode_tokens(tokens, :include => :space).size
assert_equal 9, tokens.token_class_filter(:include => :space).size
assert_equal 0, CodeRay::Encoders::TokenClassFilter.new.encode_tokens(tokens, :exclude => :all).size
assert_equal 0, tokens.token_class_filter(:exclude => :all).size
end
def test_filtering_block_tokens
tokens = CodeRay::Tokens.new
10.times do |i|
tokens << [:open, :index]
tokens << [i.to_s, :content]
tokens << [:close, :index]
end
assert_equal 20, CodeRay::Encoders::TokenClassFilter.new.encode_tokens(tokens, :include => :blubb).size
assert_equal 20, tokens.token_class_filter(:include => :blubb).size
assert_equal 30, CodeRay::Encoders::TokenClassFilter.new.encode_tokens(tokens, :exclude => :index).size
assert_equal 30, tokens.token_class_filter(:exclude => :index).size
end
end

View File

@ -29,6 +29,7 @@ module Encoders
end
def finish options
@out = ''
@doc.write @out, options[:pretty], options[:transitive], true
@out
end

View File

@ -0,0 +1,95 @@
module CodeRay
# A little hack to enable CodeRay highlighting in RedCloth.
#
# Usage:
# require 'coderay'
# require 'coderay/for_redcloth'
# RedCloth.new('@[ruby]puts "Hello, World!"@').to_html
#
# Make sure you have RedCloth 4.0.3 activated, for example by calling
# require 'rubygems'
# before RedCloth is loaded and before calling CodeRay.for_redcloth.
module ForRedCloth
def self.install
gem 'RedCloth', '>= 4.0.3' if defined? gem
require 'redcloth'
unless RedCloth::VERSION.to_s >= '4.0.3'
if defined? gem
raise 'CodeRay.for_redcloth needs RedCloth version 4.0.3 or later. ' +
"You have #{RedCloth::VERSION}. Please gem install RedCloth."
else
$".delete 'redcloth.rb' # sorry, but it works
require 'rubygems'
return install # retry
end
end
unless RedCloth::VERSION.to_s >= '4.2.2'
warn 'CodeRay.for_redcloth works best with RedCloth version 4.2.2 or later.'
end
RedCloth::TextileDoc.send :include, ForRedCloth::TextileDoc
RedCloth::Formatters::HTML.module_eval do
def unescape(html)
replacements = {
'&amp;' => '&',
'&quot;' => '"',
'&gt;' => '>',
'&lt;' => '<',
}
html.gsub(/&(?:amp|quot|[gl]t);/) { |entity| replacements[entity] }
end
undef code, bc_open, bc_close, escape_pre
def code(opts) # :nodoc:
opts[:block] = true
if !opts[:lang] && RedCloth::VERSION.to_s >= '4.2.0'
# simulating pre-4.2 behavior
if opts[:text].sub!(/\A\[(\w+)\]/, '')
if CodeRay::Scanners[$1].plugin_id == 'plaintext'
opts[:text] = $& + opts[:text]
else
opts[:lang] = $1
end
end
end
if opts[:lang] && !filter_coderay
require 'coderay'
@in_bc ||= nil
format = @in_bc ? :div : :span
opts[:text] = unescape(opts[:text]) unless @in_bc
highlighted_code = CodeRay.encode opts[:text], opts[:lang], format, :stream => true
highlighted_code.sub!(/\A<(span|div)/) { |m| m + pba(@in_bc || opts) }
highlighted_code
else
"<code#{pba(opts)}>#{opts[:text]}</code>"
end
end
def bc_open(opts) # :nodoc:
opts[:block] = true
@in_bc = opts
opts[:lang] ? '' : "<pre#{pba(opts)}>"
end
def bc_close(opts) # :nodoc:
opts = @in_bc
@in_bc = nil
opts[:lang] ? '' : "</pre>\n"
end
def escape_pre(text)
if @in_bc ||= nil
text
else
html_esc(text, :html_escape_preformatted)
end
end
end
end
module TextileDoc # :nodoc:
attr_accessor :filter_coderay
end
end
end
CodeRay::ForRedCloth.install

View File

@ -1,3 +1,4 @@
#!/usr/bin/env ruby
module CodeRay
# = FileType
@ -33,12 +34,14 @@ module FileType
# That means you can get filetypes from files that don't exist.
def [] filename, read_shebang = false
name = File.basename filename
ext = File.extname name
ext.sub!(/^\./, '') # delete the leading dot
ext = File.extname(name).sub(/^\./, '') # from last dot, delete the leading dot
ext2 = filename.to_s[/\.(.*)/, 1] # from first dot
type =
TypeFromExt[ext] ||
TypeFromExt[ext.downcase] ||
(TypeFromExt[ext2] if ext2) ||
(TypeFromExt[ext2.downcase] if ext2) ||
TypeFromName[name] ||
TypeFromName[name.downcase]
type ||= shebang(filename) if read_shebang
@ -49,8 +52,11 @@ module FileType
def shebang filename
begin
File.open filename, 'r' do |f|
first_line = f.gets
first_line[TypeFromShebang]
if first_line = f.gets
if type = first_line[TypeFromShebang]
type.to_sym
end
end
end
rescue IOError
nil
@ -77,30 +83,46 @@ module FileType
end
TypeFromExt = {
'rb' => :ruby,
'rbw' => :ruby,
'rake' => :ruby,
'mab' => :ruby,
'cpp' => :c,
'c' => :c,
'css' => :css,
'diff' => :diff,
'dpr' => :delphi,
'groovy' => :groovy,
'gvy' => :groovy,
'h' => :c,
'java' => :java,
'js' => :javascript,
'xml' => :xml,
'htm' => :html,
'html' => :html,
'html.erb' => :rhtml,
'java' => :java,
'js' => :java_script,
'json' => :json,
'mab' => :ruby,
'pas' => :delphi,
'patch' => :diff,
'php' => :php,
'php3' => :php,
'php4' => :php,
'php5' => :php,
'xhtml' => :xhtml,
'py' => :python,
'py3' => :python,
'pyw' => :python,
'rake' => :ruby,
'raydebug' => :debug,
'rb' => :ruby,
'rbw' => :ruby,
'rhtml' => :rhtml,
'ss' => :scheme,
'rxml' => :ruby,
'sch' => :scheme,
'sql' => :sql,
'ss' => :scheme,
'xhtml' => :xhtml,
'xml' => :xml,
'yaml' => :yaml,
'yml' => :yaml,
}
for cpp_alias in %w[cc cpp cp cxx c++ C hh hpp h++ cu]
TypeFromExt[cpp_alias] = :cpp
end
TypeFromShebang = /\b(?:ruby|perl|python|sh)\b/
@ -115,15 +137,16 @@ end
if $0 == __FILE__
$VERBOSE = true
eval DATA.read, nil, $0, __LINE__+4
eval DATA.read, nil, $0, __LINE__ + 4
end
__END__
require 'test/unit'
class TC_FileType < Test::Unit::TestCase
class FileTypeTests < Test::Unit::TestCase
include CodeRay
def test_fetch
assert_raise FileType::UnknownFileType do
FileType.fetch ''
@ -150,6 +173,8 @@ class TC_FileType < Test::Unit::TestCase
def test_ruby
assert_equal :ruby, FileType['test.rb']
assert_equal :ruby, FileType['test.java.rb']
assert_equal :java, FileType['test.rb.java']
assert_equal :ruby, FileType['C:\\Program Files\\x\\y\\c\\test.rbw']
assert_equal :ruby, FileType['/usr/bin/something/Rakefile']
assert_equal :ruby, FileType['~/myapp/gem/Rantfile']
@ -169,11 +194,23 @@ class TC_FileType < Test::Unit::TestCase
assert_not_equal :c, FileType['~/projects/blabla/c']
end
def test_cpp
assert_equal :cpp, FileType['test.c++']
assert_equal :cpp, FileType['test.cxx']
assert_equal :cpp, FileType['test.hh']
assert_equal :cpp, FileType['test.hpp']
assert_equal :cpp, FileType['test.cu']
assert_equal :cpp, FileType['test.C']
assert_not_equal :cpp, FileType['test.c']
assert_not_equal :cpp, FileType['test.h']
end
def test_html
assert_equal :html, FileType['test.htm']
assert_equal :xhtml, FileType['test.xhtml']
assert_equal :xhtml, FileType['test.html.xhtml']
assert_equal :rhtml, FileType['_form.rhtml']
assert_equal :rhtml, FileType['_form.html.erb']
end
def test_yaml
@ -183,7 +220,16 @@ class TC_FileType < Test::Unit::TestCase
assert_not_equal :yaml, FileType['YAML']
end
def test_shebang
def test_pathname
require 'pathname'
pn = Pathname.new 'test.rb'
assert_equal :ruby, FileType[pn]
dir = Pathname.new '/etc/var/blubb'
assert_equal :ruby, FileType[dir + pn]
assert_equal :cpp, FileType[dir + 'test.cpp']
end
def test_no_shebang
dir = './test'
if File.directory? dir
Dir.chdir dir do
@ -191,5 +237,19 @@ class TC_FileType < Test::Unit::TestCase
end
end
end
def test_shebang_empty_file
require 'tmpdir'
tmpfile = File.join(Dir.tmpdir, 'bla')
File.open(tmpfile, 'w') { } # touch
assert_equal nil, FileType[tmpfile]
end
def test_shebang
require 'tmpdir'
tmpfile = File.join(Dir.tmpdir, 'bla')
File.open(tmpfile, 'w') { |f| f.puts '#!/usr/bin/env ruby' }
assert_equal :ruby, FileType[tmpfile, true]
end
end

View File

@ -2,7 +2,7 @@
#
# A simplified interface to the gzip library +zlib+ (from the Ruby Standard Library.)
#
# Author: murphy (mail to murphy cYcnus de)
# Author: murphy (mail to murphy rubychan de)
#
# Version: 0.2 (2005.may.28)
#

View File

@ -2,8 +2,6 @@ module CodeRay
# = PluginHost
#
# $Id: plugin.rb 220 2007-01-01 02:58:58Z murphy $
#
# A simple subclass plugin system.
#
# Example:
@ -22,7 +20,7 @@ module CodeRay
#
# Generators[:fancy] #-> FancyGenerator
# # or
# require_plugin 'Generators/fancy'
# CodeRay.require_plugin 'Generators/fancy'
module PluginHost
# Raised if Encoders::[] fails because:
@ -135,9 +133,13 @@ module PluginHost
# map :navy => :dark_blue
# default :gray
# end
def default id
id = validate_id id
plugin_hash[nil] = id
def default id = nil
if id
id = validate_id id
plugin_hash[nil] = id
else
plugin_hash[nil]
end
end
# Every plugin must register itself for one or more
@ -174,7 +176,7 @@ module PluginHost
def inspect
map = plugin_hash.dup
map.each do |id, plugin|
map[id] = plugin.to_s[/(?>[\w_]+)$/]
map[id] = plugin.to_s[/(?>\w+)$/]
end
"#{name}[#{host_id}]#{map.inspect}"
end
@ -212,7 +214,7 @@ protected
mapfile = path_to '_map'
if File.exist? mapfile
require mapfile
elsif $DEBUG
elsif $VERBOSE
warn 'no _map.rb found for %s' % name
end
end
@ -241,7 +243,7 @@ protected
id
elsif id.is_a? String
if id[/\w+/] == id
id.to_sym
id.downcase.to_sym
else
raise ArgumentError, "Invalid id: '#{id}' given."
end
@ -278,6 +280,16 @@ module Plugin
def register_for *ids
plugin_host.register self, *ids
end
# Returns the title of the plugin, or sets it to the
# optional argument +title+.
def title title = nil
if title
@title = title.to_s
else
@title ||= name[/([^:]+)$/, 1]
end
end
# The host for this Plugin class.
def plugin_host host = nil
@ -299,15 +311,23 @@ module Plugin
#
# The above example loads the file myplugin/my_helper.rb relative to the
# file in which MyPlugin was defined.
#
# You can also load a helper from a different plugin:
#
# helper 'other_plugin/helper_name'
def helper *helpers
for helper in helpers
self::PLUGIN_HOST.require_helper plugin_id, helper.to_s
if helper.is_a?(String) && helper[/\//]
self::PLUGIN_HOST.require_helper $`, $'
else
self::PLUGIN_HOST.require_helper plugin_id, helper.to_s
end
end
end
# Returns the pulgin id used by the engine.
def plugin_id
name[/[\w_]+$/].downcase
name[/\w+$/].downcase
end
end
@ -318,7 +338,7 @@ end
# CodeRay.require_plugin '<Host ID>/<Plugin ID>'
#
# Returns the loaded plugin.
def require_plugin path
def self.require_plugin path
host_id, plugin_id = path.split '/', 2
host = PluginHost.host_by_id(host_id)
raise PluginHost::HostNotFound,

View File

@ -98,15 +98,22 @@ class CaseIgnoringWordList < WordList
# Creates a new case-insensitive WordList with +default+ as default value.
#
# You can activate caching to store the results for every [] request.
# This speeds up subsequent lookups for the same word, but also
# uses memory.
def initialize default = false, caching = false
if caching
super(default, false) do |h, k|
h[k] = h.fetch k.downcase, default
end
else
def self.[] key # :nodoc:
super(key.downcase)
end
super(default, false)
extend Uncached
end
end
module Uncached # :nodoc:
def [] key
super(key.downcase)
end
end
@ -120,4 +127,12 @@ class CaseIgnoringWordList < WordList
end
end
end
__END__
# check memory consumption
END {
ObjectSpace.each_object(CodeRay::CaseIgnoringWordList) do |wl|
p wl.inject(0) { |memo, key, value| memo + key.size + 24 }
end
}

View File

@ -4,8 +4,6 @@ module CodeRay
# = Scanners
#
# $Id: scanner.rb 222 2007-01-01 16:26:17Z murphy $
#
# This module holds the Scanner class and its subclasses.
# For example, the Ruby scanner is named CodeRay::Scanners::Ruby
# can be found in coderay/scanners/ruby.
@ -45,6 +43,7 @@ module CodeRay
# You can also use +map+, +any?+, +find+ and even +sort_by+,
# if you want.
class Scanner < StringScanner
extend Plugin
plugin_host Scanners
@ -57,6 +56,8 @@ module CodeRay
#
# Define @default_options for subclasses.
DEFAULT_OPTIONS = { :stream => false }
KINDS_NOT_LOC = [:comment, :doctype]
class << self
@ -66,7 +67,19 @@ module CodeRay
end
def normify code
code = code.to_s.to_unix
code = code.to_s
if code.respond_to? :force_encoding
debug, $DEBUG = $DEBUG, false
begin
code.force_encoding 'utf-8'
code[/\z/] # raises an ArgumentError when code contains a non-UTF-8 char
rescue ArgumentError
code.force_encoding 'binary'
ensure
$DEBUG = debug
end
end
code.to_unix
end
def file_extension extension = nil
@ -75,7 +88,7 @@ module CodeRay
else
@file_extension ||= plugin_id.to_s
end
end
end
end
@ -104,9 +117,10 @@ module CodeRay
#
# Else, a Tokens object is used.
def initialize code='', options = {}, &block
@options = self.class::DEFAULT_OPTIONS.merge options
raise "I am only the basic Scanner class. I can't scan "\
"anything. :( Use my subclasses." if self.class == Scanner
@options = self.class::DEFAULT_OPTIONS.merge options
super Scanner.normify(code)
@ -121,6 +135,7 @@ module CodeRay
"but :stream is #{@options[:stream]}" if block_given?
@tokens ||= Tokens.new
end
@tokens.scanner = self
setup
end
@ -140,6 +155,11 @@ module CodeRay
alias code string
alias code= string=
# Returns the Plugin ID for this scanner.
def lang
self.class.plugin_id
end
# Scans the code and returns all tokens in a Tokens object.
def tokenize new_string=nil, options = {}
options = @options.merge(options)
@ -178,6 +198,24 @@ module CodeRay
def line
string[0..pos].count("\n") + 1
end
def column pos = self.pos
return 0 if pos <= 0
string = string()
if string.respond_to?(:bytesize) && (defined?(@bin_string) || string.bytesize != string.size)
@bin_string ||= string.dup.force_encoding('binary')
string = @bin_string
end
pos - (string.rindex(?\n, pos) || 0)
end
def marshal_dump
@options
end
def marshal_load options
@options = options
end
protected
@ -202,6 +240,7 @@ module CodeRay
def reset_instance
@tokens.clear unless @options[:keep_tokens]
@cached_tokens = nil
@bin_string = nil if defined? @bin_string
end
# Scanner error with additional status information
@ -214,7 +253,7 @@ module CodeRay
tokens:
%s
current line: %d pos = %d
current line: %d column: %d pos: %d
matched: %p state: %p
bol? = %p, eos? = %p
@ -229,10 +268,10 @@ surrounding code:
msg,
tokens.size,
tokens.last(10).map { |t| t.inspect }.join("\n"),
line, pos,
line, column, pos,
matched, state, bol?, eos?,
string[pos-ambit,ambit],
string[pos,ambit],
string[pos - ambit, ambit],
string[pos, ambit],
]
end

View File

@ -0,0 +1,23 @@
module CodeRay
module Scanners
map \
:h => :c,
:cplusplus => :cpp,
:'c++' => :cpp,
:ecma => :java_script,
:ecmascript => :java_script,
:ecma_script => :java_script,
:irb => :ruby,
:javascript => :java_script,
:js => :java_script,
:nitro => :nitro_xhtml,
:pascal => :delphi,
:plain => :plaintext,
:xhtml => :html,
:yml => :yaml
default :plain
end
end

View File

@ -3,42 +3,50 @@ module Scanners
class C < Scanner
register_for :c
include Streamable
register_for :c
file_extension 'c'
RESERVED_WORDS = [
'asm', 'break', 'case', 'continue', 'default', 'do', 'else',
'for', 'goto', 'if', 'return', 'switch', 'while',
'struct', 'union', 'enum', 'typedef',
'static', 'register', 'auto', 'extern',
'sizeof',
'volatile', 'const', # C89
'inline', 'restrict', # C99
'asm', 'break', 'case', 'continue', 'default', 'do',
'else', 'enum', 'for', 'goto', 'if', 'return',
'sizeof', 'struct', 'switch', 'typedef', 'union', 'while',
'restrict', # added in C99
]
PREDEFINED_TYPES = [
'int', 'long', 'short', 'char', 'void',
'int', 'long', 'short', 'char',
'signed', 'unsigned', 'float', 'double',
'bool', 'complex', # C99
'bool', 'complex', # added in C99
]
PREDEFINED_CONSTANTS = [
'EOF', 'NULL',
'true', 'false', # C99
'true', 'false', # added in C99
]
DIRECTIVES = [
'auto', 'extern', 'register', 'static', 'void',
'const', 'volatile', # added in C89
'inline', # added in C99
]
IDENT_KIND = WordList.new(:ident).
add(RESERVED_WORDS, :reserved).
add(PREDEFINED_TYPES, :pre_type).
add(DIRECTIVES, :directive).
add(PREDEFINED_CONSTANTS, :pre_constant)
ESCAPE = / [rbfnrtv\n\\'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} /x
ESCAPE = / [rbfntv\n\\'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} /x
UNICODE_ESCAPE = / u[a-fA-F0-9]{4} | U[a-fA-F0-9]{8} /x
def scan_tokens tokens, options
state = :initial
label_expected = true
case_expected = false
label_expected_before_preproc_line = nil
in_preproc_line = false
until eos?
@ -49,8 +57,13 @@ module Scanners
when :initial
if scan(/ \s+ | \\\n /x)
kind = :space
if match = scan(/ \s+ | \\\n /x)
if in_preproc_line && match != "\\\n" && match.index(?\n)
in_preproc_line = false
label_expected = label_expected_before_preproc_line
end
tokens << [match, :space]
next
elsif scan(%r! // [^\n\\]* (?: \\. [^\n\\]* )* | /\* (?: .*? \*/ | .* ) !mx)
kind = :comment
@ -59,16 +72,32 @@ module Scanners
match << scan_until(/ ^\# (?:elif|else|endif) .*? $ | \z /xm) unless eos?
kind = :comment
elsif scan(/ [-+*\/=<>?:;,!&^|()\[\]{}~%]+ | \.(?!\d) /x)
elsif match = scan(/ [-+*=<>?:;,!&^|()\[\]{}~%]+ | \/=? | \.(?!\d) /x)
label_expected = match =~ /[;\{\}]/
if case_expected
label_expected = true if match == ':'
case_expected = false
end
kind = :operator
elsif match = scan(/ [A-Za-z_][A-Za-z_0-9]* /x)
kind = IDENT_KIND[match]
if kind == :ident and check(/:(?!:)/)
match << scan(/:/)
if kind == :ident && label_expected && !in_preproc_line && scan(/:(?!:)/)
kind = :label
match << matched
else
label_expected = false
if kind == :reserved
case match
when 'case', 'default'
case_expected = true
end
end
end
elsif scan(/\$/)
kind = :ident
elsif match = scan(/L?"/)
tokens << [:open, :string]
if match[0] == ?L
@ -78,23 +107,30 @@ module Scanners
state = :string
kind = :delimiter
elsif scan(/#\s*(\w*)/)
kind = :preprocessor # FIXME multiline preprocs
elsif scan(/#[ \t]*(\w*)/)
kind = :preprocessor
in_preproc_line = true
label_expected_before_preproc_line = label_expected
state = :include_expected if self[1] == 'include'
elsif scan(/ L?' (?: [^\'\n\\] | \\ #{ESCAPE} )? '? /ox)
label_expected = false
kind = :char
elsif scan(/0[xX][0-9A-Fa-f]+/)
label_expected = false
kind = :hex
elsif scan(/(?:0[0-7]+)(?![89.eEfF])/)
label_expected = false
kind = :oct
elsif scan(/(?:\d+)(?![.eEfF])/)
elsif scan(/(?:\d+)(?![.eEfF])L?L?/)
label_expected = false
kind = :integer
elsif scan(/\d[fF]?|\d*\.\d+(?:[eE][+-]?\d+)?[fF]?|\d+[eE][+-]?\d+[fF]?/)
label_expected = false
kind = :float
else
@ -110,6 +146,7 @@ module Scanners
tokens << ['"', :delimiter]
tokens << [:close, :string]
state = :initial
label_expected = false
next
elsif scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox)
kind = :char
@ -117,6 +154,7 @@ module Scanners
tokens << [:close, :string]
kind = :error
state = :initial
label_expected = false
else
raise_inspect "else case \" reached; %p not handled." % peek(1), tokens
end
@ -131,8 +169,8 @@ module Scanners
state = :initial if match.index ?\n
else
getch
kind = :error
state = :initial
next
end
@ -142,7 +180,7 @@ module Scanners
end
match ||= matched
if $DEBUG and not kind
if $CODERAY_DEBUG and not kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens
end

View File

@ -0,0 +1,228 @@
module CodeRay
module Scanners
class CPlusPlus < Scanner
include Streamable
register_for :cpp
file_extension 'cpp'
title 'C++'
# http://www.cppreference.com/wiki/keywords/start
RESERVED_WORDS = [
'and', 'and_eq', 'asm', 'bitand', 'bitor', 'break',
'case', 'catch', 'class', 'compl', 'const_cast',
'continue', 'default', 'delete', 'do', 'dynamic_cast', 'else',
'enum', 'export', 'for', 'goto', 'if', 'namespace', 'new',
'not', 'not_eq', 'or', 'or_eq', 'reinterpret_cast', 'return',
'sizeof', 'static_cast', 'struct', 'switch', 'template',
'throw', 'try', 'typedef', 'typeid', 'typename', 'union',
'while', 'xor', 'xor_eq'
]
PREDEFINED_TYPES = [
'bool', 'char', 'double', 'float', 'int', 'long',
'short', 'signed', 'unsigned', 'wchar_t', 'string'
]
PREDEFINED_CONSTANTS = [
'false', 'true',
'EOF', 'NULL',
]
PREDEFINED_VARIABLES = [
'this'
]
DIRECTIVES = [
'auto', 'const', 'explicit', 'extern', 'friend', 'inline', 'mutable', 'operator',
'private', 'protected', 'public', 'register', 'static', 'using', 'virtual', 'void',
'volatile'
]
IDENT_KIND = WordList.new(:ident).
add(RESERVED_WORDS, :reserved).
add(PREDEFINED_TYPES, :pre_type).
add(PREDEFINED_VARIABLES, :local_variable).
add(DIRECTIVES, :directive).
add(PREDEFINED_CONSTANTS, :pre_constant)
ESCAPE = / [rbfntv\n\\'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} /x
UNICODE_ESCAPE = / u[a-fA-F0-9]{4} | U[a-fA-F0-9]{8} /x
def scan_tokens tokens, options
state = :initial
label_expected = true
case_expected = false
label_expected_before_preproc_line = nil
in_preproc_line = false
until eos?
kind = nil
match = nil
case state
when :initial
if match = scan(/ \s+ | \\\n /x)
if in_preproc_line && match != "\\\n" && match.index(?\n)
in_preproc_line = false
label_expected = label_expected_before_preproc_line
end
tokens << [match, :space]
next
elsif scan(%r! // [^\n\\]* (?: \\. [^\n\\]* )* | /\* (?: .*? \*/ | .* ) !mx)
kind = :comment
elsif match = scan(/ \# \s* if \s* 0 /x)
match << scan_until(/ ^\# (?:elif|else|endif) .*? $ | \z /xm) unless eos?
kind = :comment
elsif match = scan(/ [-+*=<>?:;,!&^|()\[\]{}~%]+ | \/=? | \.(?!\d) /x)
label_expected = match =~ /[;\{\}]/
if case_expected
label_expected = true if match == ':'
case_expected = false
end
kind = :operator
elsif match = scan(/ [A-Za-z_][A-Za-z_0-9]* /x)
kind = IDENT_KIND[match]
if kind == :ident && label_expected && !in_preproc_line && scan(/:(?!:)/)
kind = :label
match << matched
else
label_expected = false
if kind == :reserved
case match
when 'class'
state = :class_name_expected
when 'case', 'default'
case_expected = true
end
end
end
elsif scan(/\$/)
kind = :ident
elsif match = scan(/L?"/)
tokens << [:open, :string]
if match[0] == ?L
tokens << ['L', :modifier]
match = '"'
end
state = :string
kind = :delimiter
elsif scan(/#[ \t]*(\w*)/)
kind = :preprocessor
in_preproc_line = true
label_expected_before_preproc_line = label_expected
state = :include_expected if self[1] == 'include'
elsif scan(/ L?' (?: [^\'\n\\] | \\ #{ESCAPE} )? '? /ox)
label_expected = false
kind = :char
elsif scan(/0[xX][0-9A-Fa-f]+/)
label_expected = false
kind = :hex
elsif scan(/(?:0[0-7]+)(?![89.eEfF])/)
label_expected = false
kind = :oct
elsif scan(/(?:\d+)(?![.eEfF])L?L?/)
label_expected = false
kind = :integer
elsif scan(/\d[fF]?|\d*\.\d+(?:[eE][+-]?\d+)?[fF]?|\d+[eE][+-]?\d+[fF]?/)
label_expected = false
kind = :float
else
getch
kind = :error
end
when :string
if scan(/[^\\"]+/)
kind = :content
elsif scan(/"/)
tokens << ['"', :delimiter]
tokens << [:close, :string]
state = :initial
label_expected = false
next
elsif scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox)
kind = :char
elsif scan(/ \\ | $ /x)
tokens << [:close, :string]
kind = :error
state = :initial
label_expected = false
else
raise_inspect "else case \" reached; %p not handled." % peek(1), tokens
end
when :include_expected
if scan(/<[^>\n]+>?|"[^"\n\\]*(?:\\.[^"\n\\]*)*"?/)
kind = :include
state = :initial
elsif match = scan(/\s+/)
kind = :space
state = :initial if match.index ?\n
else
state = :initial
next
end
when :class_name_expected
if scan(/ [A-Za-z_][A-Za-z_0-9]* /x)
kind = :class
state = :initial
elsif match = scan(/\s+/)
kind = :space
else
getch
kind = :error
state = :initial
end
else
raise_inspect 'Unknown state', tokens
end
match ||= matched
if $CODERAY_DEBUG and not kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens
end
raise_inspect 'Empty token', tokens unless match
tokens << [match, kind]
end
if state == :string
tokens << [:close, :string]
end
tokens
end
end
end
end

View File

@ -0,0 +1,210 @@
module CodeRay
module Scanners
class CSS < Scanner
register_for :css
KINDS_NOT_LOC = [
:comment,
:class, :pseudo_class, :type,
:constant, :directive,
:key, :value, :operator, :color, :float,
:error, :important,
]
module RE
NonASCII = /[\x80-\xFF]/
Hex = /[0-9a-fA-F]/
Unicode = /\\#{Hex}{1,6}(?:\r\n|\s)?/ # differs from standard because it allows uppercase hex too
Escape = /#{Unicode}|\\[^\r\n\f0-9a-fA-F]/
NMChar = /[-_a-zA-Z0-9]|#{NonASCII}|#{Escape}/
NMStart = /[_a-zA-Z]|#{NonASCII}|#{Escape}/
NL = /\r\n|\r|\n|\f/
String1 = /"(?:[^\n\r\f\\"]|\\#{NL}|#{Escape})*"?/ # FIXME: buggy regexp
String2 = /'(?:[^\n\r\f\\']|\\#{NL}|#{Escape})*'?/ # FIXME: buggy regexp
String = /#{String1}|#{String2}/
HexColor = /#(?:#{Hex}{6}|#{Hex}{3})/
Color = /#{HexColor}/
Num = /-?(?:[0-9]+|[0-9]*\.[0-9]+)/
Name = /#{NMChar}+/
Ident = /-?#{NMStart}#{NMChar}*/
AtKeyword = /@#{Ident}/
Percentage = /#{Num}%/
reldimensions = %w[em ex px]
absdimensions = %w[in cm mm pt pc]
Unit = Regexp.union(*(reldimensions + absdimensions))
Dimension = /#{Num}#{Unit}/
Comment = %r! /\* (?: .*? \*/ | .* ) !mx
Function = /(?:url|alpha)\((?:[^)\n\r\f]|\\\))*\)?/
Id = /##{Name}/
Class = /\.#{Name}/
PseudoClass = /:#{Name}/
AttributeSelector = /\[[^\]]*\]?/
end
def scan_tokens tokens, options
value_expected = nil
states = [:initial]
until eos?
kind = nil
match = nil
if scan(/\s+/)
kind = :space
elsif case states.last
when :initial, :media
if scan(/(?>#{RE::Ident})(?!\()|\*/ox)
kind = :type
elsif scan RE::Class
kind = :class
elsif scan RE::Id
kind = :constant
elsif scan RE::PseudoClass
kind = :pseudo_class
elsif match = scan(RE::AttributeSelector)
# TODO: Improve highlighting inside of attribute selectors.
tokens << [:open, :string]
tokens << [match[0,1], :delimiter]
tokens << [match[1..-2], :content] if match.size > 2
tokens << [match[-1,1], :delimiter] if match[-1] == ?]
tokens << [:close, :string]
next
elsif match = scan(/@media/)
kind = :directive
states.push :media_before_name
end
when :block
if scan(/(?>#{RE::Ident})(?!\()/ox)
if value_expected
kind = :value
else
kind = :key
end
end
when :media_before_name
if scan RE::Ident
kind = :type
states[-1] = :media_after_name
end
when :media_after_name
if scan(/\{/)
kind = :operator
states[-1] = :media
end
when :comment
if scan(/(?:[^*\s]|\*(?!\/))+/)
kind = :comment
elsif scan(/\*\//)
kind = :comment
states.pop
elsif scan(/\s+/)
kind = :space
end
else
raise_inspect 'Unknown state', tokens
end
elsif scan(/\/\*/)
kind = :comment
states.push :comment
elsif scan(/\{/)
value_expected = false
kind = :operator
states.push :block
elsif scan(/\}/)
value_expected = false
if states.last == :block || states.last == :media
kind = :operator
states.pop
else
kind = :error
end
elsif match = scan(/#{RE::String}/o)
tokens << [:open, :string]
tokens << [match[0, 1], :delimiter]
tokens << [match[1..-2], :content] if match.size > 2
tokens << [match[-1, 1], :delimiter] if match.size >= 2
tokens << [:close, :string]
next
elsif match = scan(/#{RE::Function}/o)
tokens << [:open, :string]
start = match[/^\w+\(/]
tokens << [start, :delimiter]
if match[-1] == ?)
tokens << [match[start.size..-2], :content]
tokens << [')', :delimiter]
else
tokens << [match[start.size..-1], :content]
end
tokens << [:close, :string]
next
elsif scan(/(?: #{RE::Dimension} | #{RE::Percentage} | #{RE::Num} )/ox)
kind = :float
elsif scan(/#{RE::Color}/o)
kind = :color
elsif scan(/! *important/)
kind = :important
elsif scan(/rgb\([^()\n]*\)?/)
kind = :color
elsif scan(/#{RE::AtKeyword}/o)
kind = :directive
elsif match = scan(/ [+>:;,.=()\/] /x)
if match == ':'
value_expected = true
elsif match == ';'
value_expected = false
end
kind = :operator
else
getch
kind = :error
end
match ||= matched
if $CODERAY_DEBUG and not kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens
end
raise_inspect 'Empty token', tokens unless match
tokens << [match, kind]
end
tokens
end
end
end
end

View File

@ -6,6 +6,8 @@ module Scanners
include Streamable
register_for :debug
file_extension 'raydebug'
title 'CodeRay Token Dump'
protected
def scan_tokens tokens, options
@ -30,8 +32,8 @@ module Scanners
opened_tokens << kind
match = :open
elsif scan(/ > /x)
kind = opened_tokens.pop
elsif !opened_tokens.empty? && scan(/ > /x)
kind = opened_tokens.pop || :error
match = :close
else
@ -41,7 +43,7 @@ module Scanners
end
match ||= matched
if $DEBUG and not kind
if $CODERAY_DEBUG and not kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens
end

View File

@ -4,6 +4,7 @@ module Scanners
class Delphi < Scanner
register_for :delphi
file_extension 'pas'
RESERVED_WORDS = [
'and', 'array', 'as', 'at', 'asm', 'at', 'begin', 'case', 'class',
@ -29,11 +30,11 @@ module Scanners
'virtual', 'write', 'writeonly'
]
IDENT_KIND = CaseIgnoringWordList.new(:ident, caching=true).
IDENT_KIND = CaseIgnoringWordList.new(:ident).
add(RESERVED_WORDS, :reserved).
add(DIRECTIVES, :directive)
NAME_FOLLOWS = CaseIgnoringWordList.new(false, caching=true).
NAME_FOLLOWS = CaseIgnoringWordList.new(false).
add(%w(procedure function .))
private
@ -129,7 +130,7 @@ module Scanners
end
match ||= matched
if $DEBUG and not kind
if $CODERAY_DEBUG and not kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens, state
end

View File

@ -0,0 +1,105 @@
module CodeRay
module Scanners
class Diff < Scanner
register_for :diff
title 'diff output'
def scan_tokens tokens, options
line_kind = nil
state = :initial
until eos?
kind = match = nil
if match = scan(/\n/)
if line_kind
tokens << [:end_line, line_kind]
line_kind = nil
end
tokens << [match, :space]
next
end
case state
when :initial
if match = scan(/--- |\+\+\+ |=+|_+/)
tokens << [:begin_line, line_kind = :head]
tokens << [match, :head]
next unless match = scan(/.+/)
kind = :plain
elsif match = scan(/Index: |Property changes on: /)
tokens << [:begin_line, line_kind = :head]
tokens << [match, :head]
next unless match = scan(/.+/)
kind = :plain
elsif match = scan(/Added: /)
tokens << [:begin_line, line_kind = :head]
tokens << [match, :head]
next unless match = scan(/.+/)
kind = :plain
state = :added
elsif match = scan(/\\ /)
tokens << [:begin_line, line_kind = :change]
tokens << [match, :change]
next unless match = scan(/.+/)
kind = :plain
elsif scan(/(@@)((?>[^@\n]*))(@@)/)
tokens << [:begin_line, line_kind = :change]
tokens << [self[1], :change]
tokens << [self[2], :plain]
tokens << [self[3], :change]
next unless match = scan(/.+/)
kind = :plain
elsif match = scan(/\+/)
tokens << [:begin_line, line_kind = :insert]
tokens << [match, :insert]
next unless match = scan(/.+/)
kind = :plain
elsif match = scan(/-/)
tokens << [:begin_line, line_kind = :delete]
tokens << [match, :delete]
next unless match = scan(/.+/)
kind = :plain
elsif scan(/ .*/)
kind = :comment
elsif scan(/.+/)
tokens << [:begin_line, line_kind = :head]
kind = :plain
else
raise_inspect 'else case rached'
end
when :added
if match = scan(/ \+/)
tokens << [:begin_line, line_kind = :insert]
tokens << [match, :insert]
next unless match = scan(/.+/)
kind = :plain
else
state = :initial
next
end
end
match ||= matched
if $CODERAY_DEBUG and not kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens
end
raise_inspect 'Empty token', tokens unless match
tokens << [match, kind]
end
tokens << [:end_line, line_kind] if line_kind
tokens
end
end
end
end

View File

@ -0,0 +1,264 @@
module CodeRay
module Scanners
load :java
class Groovy < Java
include Streamable
register_for :groovy
# TODO: Check this!
GROOVY_KEYWORDS = %w[
as assert def in
]
KEYWORDS_EXPECTING_VALUE = WordList.new.add %w[
case instanceof new return throw typeof while as assert in
]
GROOVY_MAGIC_VARIABLES = %w[ it ]
IDENT_KIND = Java::IDENT_KIND.dup.
add(GROOVY_KEYWORDS, :keyword).
add(GROOVY_MAGIC_VARIABLES, :local_variable)
ESCAPE = / [bfnrtv$\n\\'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} /x
UNICODE_ESCAPE = / u[a-fA-F0-9]{4} /x # no 4-byte unicode chars? U[a-fA-F0-9]{8}
REGEXP_ESCAPE = / [bfnrtv\n\\'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} | \d | [bBdDsSwW\/] /x
# TODO: interpretation inside ', ", /
STRING_CONTENT_PATTERN = {
"'" => /(?>\\[^\\'\n]+|[^\\'\n]+)+/,
'"' => /[^\\$"\n]+/,
"'''" => /(?>[^\\']+|'(?!''))+/,
'"""' => /(?>[^\\$"]+|"(?!""))+/,
'/' => /[^\\$\/\n]+/,
}
def scan_tokens tokens, options
state = :initial
inline_block_stack = []
inline_block_paren_depth = nil
string_delimiter = nil
import_clause = class_name_follows = last_token = after_def = false
value_expected = true
until eos?
kind = nil
match = nil
case state
when :initial
if match = scan(/ \s+ | \\\n /x)
tokens << [match, :space]
if match.index ?\n
import_clause = after_def = false
value_expected = true unless value_expected
end
next
elsif scan(%r! // [^\n\\]* (?: \\. [^\n\\]* )* | /\* (?: .*? \*/ | .* ) !mx)
value_expected = true
after_def = false
kind = :comment
elsif bol? && scan(/ \#!.* /x)
kind = :doctype
elsif import_clause && scan(/ (?!as) #{IDENT} (?: \. #{IDENT} )* (?: \.\* )? /ox)
after_def = value_expected = false
kind = :include
elsif match = scan(/ #{IDENT} | \[\] /ox)
kind = IDENT_KIND[match]
value_expected = (kind == :keyword) && KEYWORDS_EXPECTING_VALUE[match]
if last_token == '.'
kind = :ident
elsif class_name_follows
kind = :class
class_name_follows = false
elsif after_def && check(/\s*[({]/)
kind = :method
after_def = false
elsif kind == :ident && last_token != '?' && check(/:/)
kind = :key
else
class_name_follows = true if match == 'class' || (import_clause && match == 'as')
import_clause = match == 'import'
after_def = true if match == 'def'
end
elsif scan(/;/)
import_clause = after_def = false
value_expected = true
kind = :operator
elsif scan(/\{/)
class_name_follows = after_def = false
value_expected = true
kind = :operator
if !inline_block_stack.empty?
inline_block_paren_depth += 1
end
# TODO: ~'...', ~"..." and ~/.../ style regexps
elsif match = scan(/ \.\.<? | \*?\.(?!\d)@? | \.& | \?:? | [,?:(\[] | -[->] | \+\+ |
&& | \|\| | \*\*=? | ==?~ | <=?>? | [-+*%^~&|>=!]=? | <<<?=? | >>>?=? /x)
value_expected = true
value_expected = :regexp if match == '~'
after_def = false
kind = :operator
elsif match = scan(/ [)\]}] /x)
value_expected = after_def = false
if !inline_block_stack.empty? && match == '}'
inline_block_paren_depth -= 1
if inline_block_paren_depth == 0 # closing brace of inline block reached
tokens << [match, :inline_delimiter]
tokens << [:close, :inline]
state, string_delimiter, inline_block_paren_depth = inline_block_stack.pop
next
end
end
kind = :operator
elsif check(/[\d.]/)
after_def = value_expected = false
if scan(/0[xX][0-9A-Fa-f]+/)
kind = :hex
elsif scan(/(?>0[0-7]+)(?![89.eEfF])/)
kind = :oct
elsif scan(/\d+[fFdD]|\d*\.\d+(?:[eE][+-]?\d+)?[fFdD]?|\d+[eE][+-]?\d+[fFdD]?/)
kind = :float
elsif scan(/\d+[lLgG]?/)
kind = :integer
end
elsif match = scan(/'''|"""/)
after_def = value_expected = false
state = :multiline_string
tokens << [:open, :string]
string_delimiter = match
kind = :delimiter
# TODO: record.'name'
elsif match = scan(/["']/)
after_def = value_expected = false
state = match == '/' ? :regexp : :string
tokens << [:open, state]
string_delimiter = match
kind = :delimiter
elsif value_expected && (match = scan(/\//))
after_def = value_expected = false
tokens << [:open, :regexp]
state = :regexp
string_delimiter = '/'
kind = :delimiter
elsif scan(/ @ #{IDENT} /ox)
after_def = value_expected = false
kind = :annotation
elsif scan(/\//)
after_def = false
value_expected = true
kind = :operator
else
getch
kind = :error
end
when :string, :regexp, :multiline_string
if scan(STRING_CONTENT_PATTERN[string_delimiter])
kind = :content
elsif match = scan(state == :multiline_string ? /'''|"""/ : /["'\/]/)
tokens << [match, :delimiter]
if state == :regexp
# TODO: regexp modifiers? s, m, x, i?
modifiers = scan(/[ix]+/)
tokens << [modifiers, :modifier] if modifiers && !modifiers.empty?
end
state = :string if state == :multiline_string
tokens << [:close, state]
string_delimiter = nil
after_def = value_expected = false
state = :initial
next
elsif (state == :string || state == :multiline_string) &&
(match = scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox))
if string_delimiter[0] == ?' && !(match == "\\\\" || match == "\\'")
kind = :content
else
kind = :char
end
elsif state == :regexp && scan(/ \\ (?: #{REGEXP_ESCAPE} | #{UNICODE_ESCAPE} ) /mox)
kind = :char
elsif match = scan(/ \$ #{IDENT} /mox)
tokens << [:open, :inline]
tokens << ['$', :inline_delimiter]
match = match[1..-1]
tokens << [match, IDENT_KIND[match]]
tokens << [:close, :inline]
next
elsif match = scan(/ \$ \{ /x)
tokens << [:open, :inline]
tokens << ['${', :inline_delimiter]
inline_block_stack << [state, string_delimiter, inline_block_paren_depth]
inline_block_paren_depth = 1
state = :initial
next
elsif scan(/ \$ /mx)
kind = :content
elsif scan(/ \\. /mx)
kind = :content
elsif scan(/ \\ | \n /x)
tokens << [:close, state]
kind = :error
after_def = value_expected = false
state = :initial
else
raise_inspect "else case \" reached; %p not handled." % peek(1), tokens
end
else
raise_inspect 'Unknown state', tokens
end
match ||= matched
if $CODERAY_DEBUG and not kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens
end
raise_inspect 'Empty token', tokens unless match
last_token = match unless [:space, :comment, :doctype].include? kind
tokens << [match, kind]
end
if [:multiline_string, :string, :regexp].include? state
tokens << [:close, state]
end
tokens
end
end
end
end

View File

@ -2,12 +2,17 @@ module CodeRay
module Scanners
# HTML Scanner
#
# $Id$
class HTML < Scanner
include Streamable
register_for :html
KINDS_NOT_LOC = [
:comment, :doctype, :preprocessor,
:tag, :attribute_name, :operator,
:attribute_value, :delimiter, :content,
:plain, :entity, :error
]
ATTR_NAME = /[\w.:-]+/
ATTR_VALUE_UNQUOTED = ATTR_NAME
@ -65,14 +70,14 @@ module Scanners
if scan(/<!--.*?-->/m)
kind = :comment
elsif scan(/<!DOCTYPE.*?>/m)
kind = :preprocessor
kind = :doctype
elsif scan(/<\?xml.*?\?>/m)
kind = :preprocessor
elsif scan(/<\?.*?\?>|<%.*?%>/m)
kind = :comment
elsif scan(/<\/[-\w_.:]*>/m)
elsif scan(/<\/[-\w.:]*>/m)
kind = :tag
elsif match = scan(/<[-\w_.:]+>?/m)
elsif match = scan(/<[-\w.:]+>?/m)
kind = :tag
state = :attribute unless match[-1] == ?>
elsif scan(/[^<>&]+/)
@ -154,7 +159,7 @@ module Scanners
end
match ||= matched
if $DEBUG and not kind
if $CODERAY_DEBUG and not kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens, state
end

View File

@ -0,0 +1,176 @@
module CodeRay
module Scanners
class Java < Scanner
include Streamable
register_for :java
helper :builtin_types
# http://java.sun.com/docs/books/tutorial/java/nutsandbolts/_keywords.html
KEYWORDS = %w[
assert break case catch continue default do else
finally for if instanceof import new package
return switch throw try typeof while
debugger export
]
RESERVED = %w[ const goto ]
CONSTANTS = %w[ false null true ]
MAGIC_VARIABLES = %w[ this super ]
TYPES = %w[
boolean byte char class double enum float int interface long
short void
] << '[]' # because int[] should be highlighted as a type
DIRECTIVES = %w[
abstract extends final implements native private protected public
static strictfp synchronized throws transient volatile
]
IDENT_KIND = WordList.new(:ident).
add(KEYWORDS, :keyword).
add(RESERVED, :reserved).
add(CONSTANTS, :pre_constant).
add(MAGIC_VARIABLES, :local_variable).
add(TYPES, :type).
add(BuiltinTypes::List, :pre_type).
add(BuiltinTypes::List.select { |builtin| builtin[/(Error|Exception)$/] }, :exception).
add(DIRECTIVES, :directive)
ESCAPE = / [bfnrtv\n\\'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} /x
UNICODE_ESCAPE = / u[a-fA-F0-9]{4} | U[a-fA-F0-9]{8} /x
STRING_CONTENT_PATTERN = {
"'" => /[^\\']+/,
'"' => /[^\\"]+/,
'/' => /[^\\\/]+/,
}
IDENT = /[a-zA-Z_][A-Za-z_0-9]*/
def scan_tokens tokens, options
state = :initial
string_delimiter = nil
import_clause = class_name_follows = last_token_dot = false
until eos?
kind = nil
match = nil
case state
when :initial
if match = scan(/ \s+ | \\\n /x)
tokens << [match, :space]
next
elsif match = scan(%r! // [^\n\\]* (?: \\. [^\n\\]* )* | /\* (?: .*? \*/ | .* ) !mx)
tokens << [match, :comment]
next
elsif import_clause && scan(/ #{IDENT} (?: \. #{IDENT} )* /ox)
kind = :include
elsif match = scan(/ #{IDENT} | \[\] /ox)
kind = IDENT_KIND[match]
if last_token_dot
kind = :ident
elsif class_name_follows
kind = :class
class_name_follows = false
else
import_clause = true if match == 'import'
class_name_follows = true if match == 'class' || match == 'interface'
end
elsif scan(/ \.(?!\d) | [,?:()\[\]}] | -- | \+\+ | && | \|\| | \*\*=? | [-+*\/%^~&|<>=!]=? | <<<?=? | >>>?=? /x)
kind = :operator
elsif scan(/;/)
import_clause = false
kind = :operator
elsif scan(/\{/)
class_name_follows = false
kind = :operator
elsif check(/[\d.]/)
if scan(/0[xX][0-9A-Fa-f]+/)
kind = :hex
elsif scan(/(?>0[0-7]+)(?![89.eEfF])/)
kind = :oct
elsif scan(/\d+[fFdD]|\d*\.\d+(?:[eE][+-]?\d+)?[fFdD]?|\d+[eE][+-]?\d+[fFdD]?/)
kind = :float
elsif scan(/\d+[lL]?/)
kind = :integer
end
elsif match = scan(/["']/)
tokens << [:open, :string]
state = :string
string_delimiter = match
kind = :delimiter
elsif scan(/ @ #{IDENT} /ox)
kind = :annotation
else
getch
kind = :error
end
when :string
if scan(STRING_CONTENT_PATTERN[string_delimiter])
kind = :content
elsif match = scan(/["'\/]/)
tokens << [match, :delimiter]
tokens << [:close, state]
string_delimiter = nil
state = :initial
next
elsif state == :string && (match = scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox))
if string_delimiter == "'" && !(match == "\\\\" || match == "\\'")
kind = :content
else
kind = :char
end
elsif scan(/\\./m)
kind = :content
elsif scan(/ \\ | $ /x)
tokens << [:close, :delimiter]
kind = :error
state = :initial
else
raise_inspect "else case \" reached; %p not handled." % peek(1), tokens
end
else
raise_inspect 'Unknown state', tokens
end
match ||= matched
if $CODERAY_DEBUG and not kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens
end
raise_inspect 'Empty token', tokens unless match
last_token_dot = match == '.'
tokens << [match, kind]
end
if state == :string
tokens << [:close, state]
end
tokens
end
end
end
end

View File

@ -0,0 +1,419 @@
module CodeRay
module Scanners
module Java::BuiltinTypes # :nodoc:
List = %w[
AbstractAction AbstractBorder AbstractButton AbstractCellEditor AbstractCollection
AbstractColorChooserPanel AbstractDocument AbstractExecutorService AbstractInterruptibleChannel
AbstractLayoutCache AbstractList AbstractListModel AbstractMap AbstractMethodError AbstractPreferences
AbstractQueue AbstractQueuedSynchronizer AbstractSelectableChannel AbstractSelectionKey AbstractSelector
AbstractSequentialList AbstractSet AbstractSpinnerModel AbstractTableModel AbstractUndoableEdit
AbstractWriter AccessControlContext AccessControlException AccessController AccessException Accessible
AccessibleAction AccessibleAttributeSequence AccessibleBundle AccessibleComponent AccessibleContext
AccessibleEditableText AccessibleExtendedComponent AccessibleExtendedTable AccessibleExtendedText
AccessibleHyperlink AccessibleHypertext AccessibleIcon AccessibleKeyBinding AccessibleObject
AccessibleRelation AccessibleRelationSet AccessibleResourceBundle AccessibleRole AccessibleSelection
AccessibleState AccessibleStateSet AccessibleStreamable AccessibleTable AccessibleTableModelChange
AccessibleText AccessibleTextSequence AccessibleValue AccountException AccountExpiredException
AccountLockedException AccountNotFoundException Acl AclEntry AclNotFoundException Action ActionEvent
ActionListener ActionMap ActionMapUIResource Activatable ActivateFailedException ActivationDesc
ActivationException ActivationGroup ActivationGroupDesc ActivationGroupID ActivationGroup_Stub
ActivationID ActivationInstantiator ActivationMonitor ActivationSystem Activator ActiveEvent
ActivityCompletedException ActivityRequiredException Adjustable AdjustmentEvent AdjustmentListener
Adler32 AffineTransform AffineTransformOp AlgorithmParameterGenerator AlgorithmParameterGeneratorSpi
AlgorithmParameters AlgorithmParameterSpec AlgorithmParametersSpi AllPermission AlphaComposite
AlreadyBoundException AlreadyConnectedException AncestorEvent AncestorListener AnnotatedElement
Annotation AnnotationFormatError AnnotationTypeMismatchException AppConfigurationEntry Appendable Applet
AppletContext AppletInitializer AppletStub Arc2D Area AreaAveragingScaleFilter ArithmeticException Array
ArrayBlockingQueue ArrayIndexOutOfBoundsException ArrayList Arrays ArrayStoreException ArrayType
AssertionError AsyncBoxView AsynchronousCloseException AtomicBoolean AtomicInteger AtomicIntegerArray
AtomicIntegerFieldUpdater AtomicLong AtomicLongArray AtomicLongFieldUpdater AtomicMarkableReference
AtomicReference AtomicReferenceArray AtomicReferenceFieldUpdater AtomicStampedReference Attribute
AttributeChangeNotification AttributeChangeNotificationFilter AttributedCharacterIterator
AttributedString AttributeException AttributeInUseException AttributeList AttributeModificationException
AttributeNotFoundException Attributes AttributeSet AttributeSetUtilities AttributeValueExp AudioClip
AudioFileFormat AudioFileReader AudioFileWriter AudioFormat AudioInputStream AudioPermission AudioSystem
AuthenticationException AuthenticationNotSupportedException Authenticator AuthorizeCallback
AuthPermission AuthProvider Autoscroll AWTError AWTEvent AWTEventListener AWTEventListenerProxy
AWTEventMulticaster AWTException AWTKeyStroke AWTPermission BackingStoreException
BadAttributeValueExpException BadBinaryOpValueExpException BadLocationException BadPaddingException
BadStringOperationException BandCombineOp BandedSampleModel BaseRowSet BasicArrowButton BasicAttribute
BasicAttributes BasicBorders BasicButtonListener BasicButtonUI BasicCheckBoxMenuItemUI BasicCheckBoxUI
BasicColorChooserUI BasicComboBoxEditor BasicComboBoxRenderer BasicComboBoxUI BasicComboPopup
BasicControl BasicDesktopIconUI BasicDesktopPaneUI BasicDirectoryModel BasicEditorPaneUI
BasicFileChooserUI BasicFormattedTextFieldUI BasicGraphicsUtils BasicHTML BasicIconFactory
BasicInternalFrameTitlePane BasicInternalFrameUI BasicLabelUI BasicListUI BasicLookAndFeel
BasicMenuBarUI BasicMenuItemUI BasicMenuUI BasicOptionPaneUI BasicPanelUI BasicPasswordFieldUI
BasicPermission BasicPopupMenuSeparatorUI BasicPopupMenuUI BasicProgressBarUI BasicRadioButtonMenuItemUI
BasicRadioButtonUI BasicRootPaneUI BasicScrollBarUI BasicScrollPaneUI BasicSeparatorUI BasicSliderUI
BasicSpinnerUI BasicSplitPaneDivider BasicSplitPaneUI BasicStroke BasicTabbedPaneUI BasicTableHeaderUI
BasicTableUI BasicTextAreaUI BasicTextFieldUI BasicTextPaneUI BasicTextUI BasicToggleButtonUI
BasicToolBarSeparatorUI BasicToolBarUI BasicToolTipUI BasicTreeUI BasicViewportUI BatchUpdateException
BeanContext BeanContextChild BeanContextChildComponentProxy BeanContextChildSupport
BeanContextContainerProxy BeanContextEvent BeanContextMembershipEvent BeanContextMembershipListener
BeanContextProxy BeanContextServiceAvailableEvent BeanContextServiceProvider
BeanContextServiceProviderBeanInfo BeanContextServiceRevokedEvent BeanContextServiceRevokedListener
BeanContextServices BeanContextServicesListener BeanContextServicesSupport BeanContextSupport
BeanDescriptor BeanInfo Beans BevelBorder Bidi BigDecimal BigInteger BinaryRefAddr BindException Binding
BitSet Blob BlockingQueue BlockView BMPImageWriteParam Book Boolean BooleanControl Border BorderFactory
BorderLayout BorderUIResource BoundedRangeModel Box BoxLayout BoxView BreakIterator
BrokenBarrierException Buffer BufferCapabilities BufferedImage BufferedImageFilter BufferedImageOp
BufferedInputStream BufferedOutputStream BufferedReader BufferedWriter BufferOverflowException
BufferStrategy BufferUnderflowException Button ButtonGroup ButtonModel ButtonUI Byte
ByteArrayInputStream ByteArrayOutputStream ByteBuffer ByteChannel ByteLookupTable ByteOrder CachedRowSet
CacheRequest CacheResponse Calendar Callable CallableStatement Callback CallbackHandler
CancelablePrintJob CancellationException CancelledKeyException CannotProceedException
CannotRedoException CannotUndoException Canvas CardLayout Caret CaretEvent CaretListener CellEditor
CellEditorListener CellRendererPane Certificate CertificateEncodingException CertificateException
CertificateExpiredException CertificateFactory CertificateFactorySpi CertificateNotYetValidException
CertificateParsingException CertPath CertPathBuilder CertPathBuilderException CertPathBuilderResult
CertPathBuilderSpi CertPathParameters CertPathTrustManagerParameters CertPathValidator
CertPathValidatorException CertPathValidatorResult CertPathValidatorSpi CertSelector CertStore
CertStoreException CertStoreParameters CertStoreSpi ChangedCharSetException ChangeEvent ChangeListener
Channel Channels Character CharacterCodingException CharacterIterator CharArrayReader CharArrayWriter
CharBuffer CharConversionException CharSequence Charset CharsetDecoder CharsetEncoder CharsetProvider
Checkbox CheckboxGroup CheckboxMenuItem CheckedInputStream CheckedOutputStream Checksum Choice
ChoiceCallback ChoiceFormat Chromaticity Cipher CipherInputStream CipherOutputStream CipherSpi Class
ClassCastException ClassCircularityError ClassDefinition ClassDesc ClassFileTransformer ClassFormatError
ClassLoader ClassLoaderRepository ClassLoadingMXBean ClassNotFoundException Clip Clipboard
ClipboardOwner Clob Cloneable CloneNotSupportedException Closeable ClosedByInterruptException
ClosedChannelException ClosedSelectorException CMMException CoderMalfunctionError CoderResult CodeSigner
CodeSource CodingErrorAction CollationElementIterator CollationKey Collator Collection
CollectionCertStoreParameters Collections Color ColorChooserComponentFactory ColorChooserUI
ColorConvertOp ColorModel ColorSelectionModel ColorSpace ColorSupported ColorType ColorUIResource
ComboBoxEditor ComboBoxModel ComboBoxUI ComboPopup CommunicationException Comparable Comparator
CompilationMXBean Compiler CompletionService Component ComponentAdapter ComponentColorModel
ComponentEvent ComponentInputMap ComponentInputMapUIResource ComponentListener ComponentOrientation
ComponentSampleModel ComponentUI ComponentView Composite CompositeContext CompositeData
CompositeDataSupport CompositeName CompositeType CompositeView CompoundBorder CompoundControl
CompoundEdit CompoundName Compression ConcurrentHashMap ConcurrentLinkedQueue ConcurrentMap
ConcurrentModificationException Condition Configuration ConfigurationException ConfirmationCallback
ConnectException ConnectIOException Connection ConnectionEvent ConnectionEventListener
ConnectionPendingException ConnectionPoolDataSource ConsoleHandler Constructor Container
ContainerAdapter ContainerEvent ContainerListener ContainerOrderFocusTraversalPolicy ContentHandler
ContentHandlerFactory ContentModel Context ContextNotEmptyException ContextualRenderedImageFactory
Control ControlFactory ControllerEventListener ConvolveOp CookieHandler Copies CopiesSupported
CopyOnWriteArrayList CopyOnWriteArraySet CountDownLatch CounterMonitor CounterMonitorMBean CRC32
CredentialException CredentialExpiredException CredentialNotFoundException CRL CRLException CRLSelector
CropImageFilter CSS CubicCurve2D Currency Cursor Customizer CyclicBarrier DatabaseMetaData DataBuffer
DataBufferByte DataBufferDouble DataBufferFloat DataBufferInt DataBufferShort DataBufferUShort
DataFlavor DataFormatException DatagramChannel DatagramPacket DatagramSocket DatagramSocketImpl
DatagramSocketImplFactory DataInput DataInputStream DataLine DataOutput DataOutputStream DataSource
DataTruncation DatatypeConfigurationException DatatypeConstants DatatypeFactory Date DateFormat
DateFormatSymbols DateFormatter DateTimeAtCompleted DateTimeAtCreation DateTimeAtProcessing
DateTimeSyntax DebugGraphics DecimalFormat DecimalFormatSymbols DefaultBoundedRangeModel
DefaultButtonModel DefaultCaret DefaultCellEditor DefaultColorSelectionModel DefaultComboBoxModel
DefaultDesktopManager DefaultEditorKit DefaultFocusManager DefaultFocusTraversalPolicy DefaultFormatter
DefaultFormatterFactory DefaultHighlighter DefaultKeyboardFocusManager DefaultListCellRenderer
DefaultListModel DefaultListSelectionModel DefaultLoaderRepository DefaultMenuLayout DefaultMetalTheme
DefaultMutableTreeNode DefaultPersistenceDelegate DefaultSingleSelectionModel DefaultStyledDocument
DefaultTableCellRenderer DefaultTableColumnModel DefaultTableModel DefaultTextUI DefaultTreeCellEditor
DefaultTreeCellRenderer DefaultTreeModel DefaultTreeSelectionModel Deflater DeflaterOutputStream Delayed
DelayQueue DelegationPermission Deprecated Descriptor DescriptorAccess DescriptorSupport DESedeKeySpec
DesignMode DESKeySpec DesktopIconUI DesktopManager DesktopPaneUI Destination Destroyable
DestroyFailedException DGC DHGenParameterSpec DHKey DHParameterSpec DHPrivateKey DHPrivateKeySpec
DHPublicKey DHPublicKeySpec Dialog Dictionary DigestException DigestInputStream DigestOutputStream
Dimension Dimension2D DimensionUIResource DirContext DirectColorModel DirectoryManager DirObjectFactory
DirStateFactory DisplayMode DnDConstants Doc DocAttribute DocAttributeSet DocFlavor DocPrintJob Document
DocumentBuilder DocumentBuilderFactory Documented DocumentEvent DocumentFilter DocumentListener
DocumentName DocumentParser DomainCombiner DOMLocator DOMResult DOMSource Double DoubleBuffer
DragGestureEvent DragGestureListener DragGestureRecognizer DragSource DragSourceAdapter
DragSourceContext DragSourceDragEvent DragSourceDropEvent DragSourceEvent DragSourceListener
DragSourceMotionListener Driver DriverManager DriverPropertyInfo DropTarget DropTargetAdapter
DropTargetContext DropTargetDragEvent DropTargetDropEvent DropTargetEvent DropTargetListener DSAKey
DSAKeyPairGenerator DSAParameterSpec DSAParams DSAPrivateKey DSAPrivateKeySpec DSAPublicKey
DSAPublicKeySpec DTD DTDConstants DuplicateFormatFlagsException Duration DynamicMBean ECField ECFieldF2m
ECFieldFp ECGenParameterSpec ECKey ECParameterSpec ECPoint ECPrivateKey ECPrivateKeySpec ECPublicKey
ECPublicKeySpec EditorKit Element ElementIterator ElementType Ellipse2D EllipticCurve EmptyBorder
EmptyStackException EncodedKeySpec Encoder EncryptedPrivateKeyInfo Entity Enum
EnumConstantNotPresentException EnumControl Enumeration EnumMap EnumSet EnumSyntax EOFException Error
ErrorListener ErrorManager EtchedBorder Event EventContext EventDirContext EventHandler EventListener
EventListenerList EventListenerProxy EventObject EventQueue EventSetDescriptor Exception
ExceptionInInitializerError ExceptionListener Exchanger ExecutionException Executor
ExecutorCompletionService Executors ExecutorService ExemptionMechanism ExemptionMechanismException
ExemptionMechanismSpi ExpandVetoException ExportException Expression ExtendedRequest ExtendedResponse
Externalizable FactoryConfigurationError FailedLoginException FeatureDescriptor Fidelity Field
FieldPosition FieldView File FileCacheImageInputStream FileCacheImageOutputStream FileChannel
FileChooserUI FileDescriptor FileDialog FileFilter FileHandler FileImageInputStream
FileImageOutputStream FileInputStream FileLock FileLockInterruptionException FilenameFilter FileNameMap
FileNotFoundException FileOutputStream FilePermission FileReader FileSystemView FileView FileWriter
Filter FilteredImageSource FilteredRowSet FilterInputStream FilterOutputStream FilterReader FilterWriter
Finishings FixedHeightLayoutCache FlatteningPathIterator FlavorEvent FlavorException FlavorListener
FlavorMap FlavorTable Float FloatBuffer FloatControl FlowLayout FlowView Flushable FocusAdapter
FocusEvent FocusListener FocusManager FocusTraversalPolicy Font FontFormatException FontMetrics
FontRenderContext FontUIResource Format FormatConversionProvider FormatFlagsConversionMismatchException
Formattable FormattableFlags Formatter FormatterClosedException FormSubmitEvent FormView Frame Future
FutureTask GapContent GarbageCollectorMXBean GatheringByteChannel GaugeMonitor GaugeMonitorMBean
GeneralPath GeneralSecurityException GenericArrayType GenericDeclaration GenericSignatureFormatError
GlyphJustificationInfo GlyphMetrics GlyphVector GlyphView GradientPaint GraphicAttribute Graphics
Graphics2D GraphicsConfigTemplate GraphicsConfiguration GraphicsDevice GraphicsEnvironment GrayFilter
GregorianCalendar GridBagConstraints GridBagLayout GridLayout Group Guard GuardedObject GZIPInputStream
GZIPOutputStream Handler HandshakeCompletedEvent HandshakeCompletedListener HasControls HashAttributeSet
HashDocAttributeSet HashMap HashPrintJobAttributeSet HashPrintRequestAttributeSet
HashPrintServiceAttributeSet HashSet Hashtable HeadlessException HierarchyBoundsAdapter
HierarchyBoundsListener HierarchyEvent HierarchyListener Highlighter HostnameVerifier HTML HTMLDocument
HTMLEditorKit HTMLFrameHyperlinkEvent HTMLWriter HttpRetryException HttpsURLConnection HttpURLConnection
HyperlinkEvent HyperlinkListener ICC_ColorSpace ICC_Profile ICC_ProfileGray ICC_ProfileRGB Icon
IconUIResource IconView Identity IdentityHashMap IdentityScope IIOByteBuffer IIOException IIOImage
IIOInvalidTreeException IIOMetadata IIOMetadataController IIOMetadataFormat IIOMetadataFormatImpl
IIOMetadataNode IIOParam IIOParamController IIOReadProgressListener IIOReadUpdateListener
IIOReadWarningListener IIORegistry IIOServiceProvider IIOWriteProgressListener IIOWriteWarningListener
IllegalAccessError IllegalAccessException IllegalArgumentException IllegalBlockingModeException
IllegalBlockSizeException IllegalCharsetNameException IllegalClassFormatException
IllegalComponentStateException IllegalFormatCodePointException IllegalFormatConversionException
IllegalFormatException IllegalFormatFlagsException IllegalFormatPrecisionException
IllegalFormatWidthException IllegalMonitorStateException IllegalPathStateException
IllegalSelectorException IllegalStateException IllegalThreadStateException Image ImageCapabilities
ImageConsumer ImageFilter ImageGraphicAttribute ImageIcon ImageInputStream ImageInputStreamImpl
ImageInputStreamSpi ImageIO ImageObserver ImageOutputStream ImageOutputStreamImpl ImageOutputStreamSpi
ImageProducer ImageReader ImageReaderSpi ImageReaderWriterSpi ImageReadParam ImageTranscoder
ImageTranscoderSpi ImageTypeSpecifier ImageView ImageWriteParam ImageWriter ImageWriterSpi
ImagingOpException IncompatibleClassChangeError IncompleteAnnotationException IndexColorModel
IndexedPropertyChangeEvent IndexedPropertyDescriptor IndexOutOfBoundsException Inet4Address Inet6Address
InetAddress InetSocketAddress Inflater InflaterInputStream InheritableThreadLocal Inherited
InitialContext InitialContextFactory InitialContextFactoryBuilder InitialDirContext InitialLdapContext
InlineView InputContext InputEvent InputMap InputMapUIResource InputMethod InputMethodContext
InputMethodDescriptor InputMethodEvent InputMethodHighlight InputMethodListener InputMethodRequests
InputMismatchException InputStream InputStreamReader InputSubset InputVerifier Insets InsetsUIResource
InstanceAlreadyExistsException InstanceNotFoundException InstantiationError InstantiationException
Instrument Instrumentation InsufficientResourcesException IntBuffer Integer IntegerSyntax InternalError
InternalFrameAdapter InternalFrameEvent InternalFrameFocusTraversalPolicy InternalFrameListener
InternalFrameUI InternationalFormatter InterruptedException InterruptedIOException
InterruptedNamingException InterruptibleChannel IntrospectionException Introspector
InvalidActivityException InvalidAlgorithmParameterException InvalidApplicationException
InvalidAttributeIdentifierException InvalidAttributesException InvalidAttributeValueException
InvalidClassException InvalidDnDOperationException InvalidKeyException InvalidKeySpecException
InvalidMarkException InvalidMidiDataException InvalidNameException InvalidObjectException
InvalidOpenTypeException InvalidParameterException InvalidParameterSpecException
InvalidPreferencesFormatException InvalidPropertiesFormatException InvalidRelationIdException
InvalidRelationServiceException InvalidRelationTypeException InvalidRoleInfoException
InvalidRoleValueException InvalidSearchControlsException InvalidSearchFilterException
InvalidTargetObjectTypeException InvalidTransactionException InvocationEvent InvocationHandler
InvocationTargetException IOException ItemEvent ItemListener ItemSelectable Iterable Iterator
IvParameterSpec JApplet JarEntry JarException JarFile JarInputStream JarOutputStream JarURLConnection
JButton JCheckBox JCheckBoxMenuItem JColorChooser JComboBox JComponent JdbcRowSet JDesktopPane JDialog
JEditorPane JFileChooser JFormattedTextField JFrame JInternalFrame JLabel JLayeredPane JList JMenu
JMenuBar JMenuItem JMException JMRuntimeException JMXAuthenticator JMXConnectionNotification
JMXConnector JMXConnectorFactory JMXConnectorProvider JMXConnectorServer JMXConnectorServerFactory
JMXConnectorServerMBean JMXConnectorServerProvider JMXPrincipal JMXProviderException
JMXServerErrorException JMXServiceURL JobAttributes JobHoldUntil JobImpressions JobImpressionsCompleted
JobImpressionsSupported JobKOctets JobKOctetsProcessed JobKOctetsSupported JobMediaSheets
JobMediaSheetsCompleted JobMediaSheetsSupported JobMessageFromOperator JobName JobOriginatingUserName
JobPriority JobPrioritySupported JobSheets JobState JobStateReason JobStateReasons Joinable JoinRowSet
JOptionPane JPanel JPasswordField JPEGHuffmanTable JPEGImageReadParam JPEGImageWriteParam JPEGQTable
JPopupMenu JProgressBar JRadioButton JRadioButtonMenuItem JRootPane JScrollBar JScrollPane JSeparator
JSlider JSpinner JSplitPane JTabbedPane JTable JTableHeader JTextArea JTextComponent JTextField
JTextPane JToggleButton JToolBar JToolTip JTree JViewport JWindow KerberosKey KerberosPrincipal
KerberosTicket Kernel Key KeyAdapter KeyAgreement KeyAgreementSpi KeyAlreadyExistsException
KeyboardFocusManager KeyEvent KeyEventDispatcher KeyEventPostProcessor KeyException KeyFactory
KeyFactorySpi KeyGenerator KeyGeneratorSpi KeyListener KeyManagementException KeyManager
KeyManagerFactory KeyManagerFactorySpi Keymap KeyPair KeyPairGenerator KeyPairGeneratorSpi KeyRep
KeySpec KeyStore KeyStoreBuilderParameters KeyStoreException KeyStoreSpi KeyStroke Label LabelUI
LabelView LanguageCallback LastOwnerException LayeredHighlighter LayoutFocusTraversalPolicy
LayoutManager LayoutManager2 LayoutQueue LDAPCertStoreParameters LdapContext LdapName
LdapReferralException Lease Level LimitExceededException Line Line2D LineBorder LineBreakMeasurer
LineEvent LineListener LineMetrics LineNumberInputStream LineNumberReader LineUnavailableException
LinkageError LinkedBlockingQueue LinkedHashMap LinkedHashSet LinkedList LinkException LinkLoopException
LinkRef List ListCellRenderer ListDataEvent ListDataListener ListenerNotFoundException ListIterator
ListModel ListResourceBundle ListSelectionEvent ListSelectionListener ListSelectionModel ListUI ListView
LoaderHandler Locale LocateRegistry Lock LockSupport Logger LoggingMXBean LoggingPermission LoginContext
LoginException LoginModule LogManager LogRecord LogStream Long LongBuffer LookAndFeel LookupOp
LookupTable Mac MacSpi MalformedInputException MalformedLinkException MalformedObjectNameException
MalformedParameterizedTypeException MalformedURLException ManagementFactory ManagementPermission
ManageReferralControl ManagerFactoryParameters Manifest Map MappedByteBuffer MarshalException
MarshalledObject MaskFormatter Matcher MatchResult Math MathContext MatteBorder MBeanAttributeInfo
MBeanConstructorInfo MBeanException MBeanFeatureInfo MBeanInfo MBeanNotificationInfo MBeanOperationInfo
MBeanParameterInfo MBeanPermission MBeanRegistration MBeanRegistrationException MBeanServer
MBeanServerBuilder MBeanServerConnection MBeanServerDelegate MBeanServerDelegateMBean MBeanServerFactory
MBeanServerForwarder MBeanServerInvocationHandler MBeanServerNotification MBeanServerNotificationFilter
MBeanServerPermission MBeanTrustPermission Media MediaName MediaPrintableArea MediaSize MediaSizeName
MediaTracker MediaTray Member MemoryCacheImageInputStream MemoryCacheImageOutputStream MemoryHandler
MemoryImageSource MemoryManagerMXBean MemoryMXBean MemoryNotificationInfo MemoryPoolMXBean MemoryType
MemoryUsage Menu MenuBar MenuBarUI MenuComponent MenuContainer MenuDragMouseEvent MenuDragMouseListener
MenuElement MenuEvent MenuItem MenuItemUI MenuKeyEvent MenuKeyListener MenuListener MenuSelectionManager
MenuShortcut MessageDigest MessageDigestSpi MessageFormat MetaEventListener MetalBorders MetalButtonUI
MetalCheckBoxIcon MetalCheckBoxUI MetalComboBoxButton MetalComboBoxEditor MetalComboBoxIcon
MetalComboBoxUI MetalDesktopIconUI MetalFileChooserUI MetalIconFactory MetalInternalFrameTitlePane
MetalInternalFrameUI MetalLabelUI MetalLookAndFeel MetalMenuBarUI MetalPopupMenuSeparatorUI
MetalProgressBarUI MetalRadioButtonUI MetalRootPaneUI MetalScrollBarUI MetalScrollButton
MetalScrollPaneUI MetalSeparatorUI MetalSliderUI MetalSplitPaneUI MetalTabbedPaneUI MetalTextFieldUI
MetalTheme MetalToggleButtonUI MetalToolBarUI MetalToolTipUI MetalTreeUI MetaMessage Method
MethodDescriptor MGF1ParameterSpec MidiChannel MidiDevice MidiDeviceProvider MidiEvent MidiFileFormat
MidiFileReader MidiFileWriter MidiMessage MidiSystem MidiUnavailableException MimeTypeParseException
MinimalHTMLWriter MissingFormatArgumentException MissingFormatWidthException MissingResourceException
Mixer MixerProvider MLet MLetMBean ModelMBean ModelMBeanAttributeInfo ModelMBeanConstructorInfo
ModelMBeanInfo ModelMBeanInfoSupport ModelMBeanNotificationBroadcaster ModelMBeanNotificationInfo
ModelMBeanOperationInfo ModificationItem Modifier Monitor MonitorMBean MonitorNotification
MonitorSettingException MouseAdapter MouseDragGestureRecognizer MouseEvent MouseInfo MouseInputAdapter
MouseInputListener MouseListener MouseMotionAdapter MouseMotionListener MouseWheelEvent
MouseWheelListener MultiButtonUI MulticastSocket MultiColorChooserUI MultiComboBoxUI MultiDesktopIconUI
MultiDesktopPaneUI MultiDoc MultiDocPrintJob MultiDocPrintService MultiFileChooserUI
MultiInternalFrameUI MultiLabelUI MultiListUI MultiLookAndFeel MultiMenuBarUI MultiMenuItemUI
MultiOptionPaneUI MultiPanelUI MultiPixelPackedSampleModel MultipleDocumentHandling MultipleMaster
MultiPopupMenuUI MultiProgressBarUI MultiRootPaneUI MultiScrollBarUI MultiScrollPaneUI MultiSeparatorUI
MultiSliderUI MultiSpinnerUI MultiSplitPaneUI MultiTabbedPaneUI MultiTableHeaderUI MultiTableUI
MultiTextUI MultiToolBarUI MultiToolTipUI MultiTreeUI MultiViewportUI MutableAttributeSet
MutableComboBoxModel MutableTreeNode Name NameAlreadyBoundException NameCallback NameClassPair
NameNotFoundException NameParser NamespaceChangeListener NamespaceContext Naming NamingEnumeration
NamingEvent NamingException NamingExceptionEvent NamingListener NamingManager NamingSecurityException
NavigationFilter NegativeArraySizeException NetPermission NetworkInterface NoClassDefFoundError
NoConnectionPendingException NodeChangeEvent NodeChangeListener NoInitialContextException
NoninvertibleTransformException NonReadableChannelException NonWritableChannelException
NoPermissionException NoRouteToHostException NoSuchAlgorithmException NoSuchAttributeException
NoSuchElementException NoSuchFieldError NoSuchFieldException NoSuchMethodError NoSuchMethodException
NoSuchObjectException NoSuchPaddingException NoSuchProviderException NotActiveException
NotBoundException NotCompliantMBeanException NotContextException Notification NotificationBroadcaster
NotificationBroadcasterSupport NotificationEmitter NotificationFilter NotificationFilterSupport
NotificationListener NotificationResult NotOwnerException NotSerializableException NotYetBoundException
NotYetConnectedException NullCipher NullPointerException Number NumberFormat NumberFormatException
NumberFormatter NumberOfDocuments NumberOfInterveningJobs NumberUp NumberUpSupported NumericShaper
OAEPParameterSpec Object ObjectChangeListener ObjectFactory ObjectFactoryBuilder ObjectInput
ObjectInputStream ObjectInputValidation ObjectInstance ObjectName ObjectOutput ObjectOutputStream
ObjectStreamClass ObjectStreamConstants ObjectStreamException ObjectStreamField ObjectView ObjID
Observable Observer OceanTheme OpenDataException OpenMBeanAttributeInfo OpenMBeanAttributeInfoSupport
OpenMBeanConstructorInfo OpenMBeanConstructorInfoSupport OpenMBeanInfo OpenMBeanInfoSupport
OpenMBeanOperationInfo OpenMBeanOperationInfoSupport OpenMBeanParameterInfo
OpenMBeanParameterInfoSupport OpenType OperatingSystemMXBean Operation OperationNotSupportedException
OperationsException Option OptionalDataException OptionPaneUI OrientationRequested OutOfMemoryError
OutputDeviceAssigned OutputKeys OutputStream OutputStreamWriter OverlappingFileLockException
OverlayLayout Override Owner Pack200 Package PackedColorModel Pageable PageAttributes
PagedResultsControl PagedResultsResponseControl PageFormat PageRanges PagesPerMinute PagesPerMinuteColor
Paint PaintContext PaintEvent Panel PanelUI Paper ParagraphView ParameterBlock ParameterDescriptor
ParameterizedType ParameterMetaData ParseException ParsePosition Parser ParserConfigurationException
ParserDelegator PartialResultException PasswordAuthentication PasswordCallback PasswordView Patch
PathIterator Pattern PatternSyntaxException PBEKey PBEKeySpec PBEParameterSpec PDLOverrideSupported
Permission PermissionCollection Permissions PersistenceDelegate PersistentMBean PhantomReference Pipe
PipedInputStream PipedOutputStream PipedReader PipedWriter PixelGrabber PixelInterleavedSampleModel
PKCS8EncodedKeySpec PKIXBuilderParameters PKIXCertPathBuilderResult PKIXCertPathChecker
PKIXCertPathValidatorResult PKIXParameters PlainDocument PlainView Point Point2D PointerInfo Policy
PolicyNode PolicyQualifierInfo Polygon PooledConnection Popup PopupFactory PopupMenu PopupMenuEvent
PopupMenuListener PopupMenuUI Port PortableRemoteObject PortableRemoteObjectDelegate
PortUnreachableException Position Predicate PreferenceChangeEvent PreferenceChangeListener Preferences
PreferencesFactory PreparedStatement PresentationDirection Principal Printable PrinterAbortException
PrinterException PrinterGraphics PrinterInfo PrinterIOException PrinterIsAcceptingJobs PrinterJob
PrinterLocation PrinterMakeAndModel PrinterMessageFromOperator PrinterMoreInfo
PrinterMoreInfoManufacturer PrinterName PrinterResolution PrinterState PrinterStateReason
PrinterStateReasons PrinterURI PrintEvent PrintException PrintGraphics PrintJob PrintJobAdapter
PrintJobAttribute PrintJobAttributeEvent PrintJobAttributeListener PrintJobAttributeSet PrintJobEvent
PrintJobListener PrintQuality PrintRequestAttribute PrintRequestAttributeSet PrintService
PrintServiceAttribute PrintServiceAttributeEvent PrintServiceAttributeListener PrintServiceAttributeSet
PrintServiceLookup PrintStream PrintWriter PriorityBlockingQueue PriorityQueue PrivateClassLoader
PrivateCredentialPermission PrivateKey PrivateMLet PrivilegedAction PrivilegedActionException
PrivilegedExceptionAction Process ProcessBuilder ProfileDataException ProgressBarUI ProgressMonitor
ProgressMonitorInputStream Properties PropertyChangeEvent PropertyChangeListener
PropertyChangeListenerProxy PropertyChangeSupport PropertyDescriptor PropertyEditor
PropertyEditorManager PropertyEditorSupport PropertyPermission PropertyResourceBundle
PropertyVetoException ProtectionDomain ProtocolException Provider ProviderException Proxy ProxySelector
PSource PSSParameterSpec PublicKey PushbackInputStream PushbackReader QName QuadCurve2D Query QueryEval
QueryExp Queue QueuedJobCount Random RandomAccess RandomAccessFile Raster RasterFormatException RasterOp
RC2ParameterSpec RC5ParameterSpec Rdn Readable ReadableByteChannel Reader ReadOnlyBufferException
ReadWriteLock RealmCallback RealmChoiceCallback Receiver Rectangle Rectangle2D RectangularShape
ReentrantLock ReentrantReadWriteLock Ref RefAddr Reference Referenceable ReferenceQueue
ReferenceUriSchemesSupported ReferralException ReflectionException ReflectPermission Refreshable
RefreshFailedException Region RegisterableService Registry RegistryHandler RejectedExecutionException
RejectedExecutionHandler Relation RelationException RelationNotFoundException RelationNotification
RelationService RelationServiceMBean RelationServiceNotRegisteredException RelationSupport
RelationSupportMBean RelationType RelationTypeNotFoundException RelationTypeSupport Remote RemoteCall
RemoteException RemoteObject RemoteObjectInvocationHandler RemoteRef RemoteServer RemoteStub
RenderableImage RenderableImageOp RenderableImageProducer RenderContext RenderedImage
RenderedImageFactory Renderer RenderingHints RepaintManager ReplicateScaleFilter RequestingUserName
RequiredModelMBean RescaleOp ResolutionSyntax Resolver ResolveResult ResourceBundle ResponseCache Result
ResultSet ResultSetMetaData Retention RetentionPolicy ReverbType RGBImageFilter RMIClassLoader
RMIClassLoaderSpi RMIClientSocketFactory RMIConnection RMIConnectionImpl RMIConnectionImpl_Stub
RMIConnector RMIConnectorServer RMIFailureHandler RMIIIOPServerImpl RMIJRMPServerImpl
RMISecurityException RMISecurityManager RMIServer RMIServerImpl RMIServerImpl_Stub
RMIServerSocketFactory RMISocketFactory Robot Role RoleInfo RoleInfoNotFoundException RoleList
RoleNotFoundException RoleResult RoleStatus RoleUnresolved RoleUnresolvedList RootPaneContainer
RootPaneUI RoundingMode RoundRectangle2D RowMapper RowSet RowSetEvent RowSetInternal RowSetListener
RowSetMetaData RowSetMetaDataImpl RowSetReader RowSetWarning RowSetWriter RSAKey RSAKeyGenParameterSpec
RSAMultiPrimePrivateCrtKey RSAMultiPrimePrivateCrtKeySpec RSAOtherPrimeInfo RSAPrivateCrtKey
RSAPrivateCrtKeySpec RSAPrivateKey RSAPrivateKeySpec RSAPublicKey RSAPublicKeySpec RTFEditorKit
RuleBasedCollator Runnable Runtime RuntimeErrorException RuntimeException RuntimeMBeanException
RuntimeMXBean RuntimeOperationsException RuntimePermission SampleModel Sasl SaslClient SaslClientFactory
SaslException SaslServer SaslServerFactory Savepoint SAXParser SAXParserFactory SAXResult SAXSource
SAXTransformerFactory Scanner ScatteringByteChannel ScheduledExecutorService ScheduledFuture
ScheduledThreadPoolExecutor Schema SchemaFactory SchemaFactoryLoader SchemaViolationException Scrollable
Scrollbar ScrollBarUI ScrollPane ScrollPaneAdjustable ScrollPaneConstants ScrollPaneLayout ScrollPaneUI
SealedObject SearchControls SearchResult SecretKey SecretKeyFactory SecretKeyFactorySpi SecretKeySpec
SecureCacheResponse SecureClassLoader SecureRandom SecureRandomSpi Security SecurityException
SecurityManager SecurityPermission Segment SelectableChannel SelectionKey Selector SelectorProvider
Semaphore SeparatorUI Sequence SequenceInputStream Sequencer SerialArray SerialBlob SerialClob
SerialDatalink SerialException Serializable SerializablePermission SerialJavaObject SerialRef
SerialStruct ServerCloneException ServerError ServerException ServerNotActiveException ServerRef
ServerRuntimeException ServerSocket ServerSocketChannel ServerSocketFactory ServiceNotFoundException
ServicePermission ServiceRegistry ServiceUI ServiceUIFactory ServiceUnavailableException Set
SetOfIntegerSyntax Severity Shape ShapeGraphicAttribute SheetCollate Short ShortBuffer
ShortBufferException ShortLookupTable ShortMessage Sides Signature SignatureException SignatureSpi
SignedObject Signer SimpleAttributeSet SimpleBeanInfo SimpleDateFormat SimpleDoc SimpleFormatter
SimpleTimeZone SimpleType SinglePixelPackedSampleModel SingleSelectionModel Size2DSyntax
SizeLimitExceededException SizeRequirements SizeSequence Skeleton SkeletonMismatchException
SkeletonNotFoundException SliderUI Socket SocketAddress SocketChannel SocketException SocketFactory
SocketHandler SocketImpl SocketImplFactory SocketOptions SocketPermission SocketSecurityException
SocketTimeoutException SoftBevelBorder SoftReference SortControl SortedMap SortedSet
SortingFocusTraversalPolicy SortKey SortResponseControl Soundbank SoundbankReader SoundbankResource
Source SourceDataLine SourceLocator SpinnerDateModel SpinnerListModel SpinnerModel SpinnerNumberModel
SpinnerUI SplitPaneUI Spring SpringLayout SQLData SQLException SQLInput SQLInputImpl SQLOutput
SQLOutputImpl SQLPermission SQLWarning SSLContext SSLContextSpi SSLEngine SSLEngineResult SSLException
SSLHandshakeException SSLKeyException SSLPeerUnverifiedException SSLPermission SSLProtocolException
SslRMIClientSocketFactory SslRMIServerSocketFactory SSLServerSocket SSLServerSocketFactory SSLSession
SSLSessionBindingEvent SSLSessionBindingListener SSLSessionContext SSLSocket SSLSocketFactory Stack
StackOverflowError StackTraceElement StandardMBean StartTlsRequest StartTlsResponse StateEdit
StateEditable StateFactory Statement StreamCorruptedException StreamHandler StreamPrintService
StreamPrintServiceFactory StreamResult StreamSource StreamTokenizer StrictMath String StringBuffer
StringBufferInputStream StringBuilder StringCharacterIterator StringContent
StringIndexOutOfBoundsException StringMonitor StringMonitorMBean StringReader StringRefAddr
StringSelection StringTokenizer StringValueExp StringWriter Stroke Struct Stub StubDelegate
StubNotFoundException Style StyleConstants StyleContext StyledDocument StyledEditorKit StyleSheet
Subject SubjectDelegationPermission SubjectDomainCombiner SupportedValuesAttribute SuppressWarnings
SwingConstants SwingPropertyChangeSupport SwingUtilities SyncFactory SyncFactoryException
SyncFailedException SynchronousQueue SyncProvider SyncProviderException SyncResolver SynthConstants
SynthContext Synthesizer SynthGraphicsUtils SynthLookAndFeel SynthPainter SynthStyle SynthStyleFactory
SysexMessage System SystemColor SystemFlavorMap TabableView TabbedPaneUI TabExpander TableCellEditor
TableCellRenderer TableColumn TableColumnModel TableColumnModelEvent TableColumnModelListener
TableHeaderUI TableModel TableModelEvent TableModelListener TableUI TableView TabSet TabStop TabularData
TabularDataSupport TabularType TagElement Target TargetDataLine TargetedNotification Templates
TemplatesHandler TextAction TextArea TextAttribute TextComponent TextEvent TextField TextHitInfo
TextInputCallback TextLayout TextListener TextMeasurer TextOutputCallback TextSyntax TextUI TexturePaint
Thread ThreadDeath ThreadFactory ThreadGroup ThreadInfo ThreadLocal ThreadMXBean ThreadPoolExecutor
Throwable Tie TileObserver Time TimeLimitExceededException TimeoutException Timer
TimerAlarmClockNotification TimerMBean TimerNotification TimerTask Timestamp TimeUnit TimeZone
TitledBorder ToolBarUI Toolkit ToolTipManager ToolTipUI TooManyListenersException Track
TransactionalWriter TransactionRequiredException TransactionRolledbackException Transferable
TransferHandler TransformAttribute Transformer TransformerConfigurationException TransformerException
TransformerFactory TransformerFactoryConfigurationError TransformerHandler Transmitter Transparency
TreeCellEditor TreeCellRenderer TreeExpansionEvent TreeExpansionListener TreeMap TreeModel
TreeModelEvent TreeModelListener TreeNode TreePath TreeSelectionEvent TreeSelectionListener
TreeSelectionModel TreeSet TreeUI TreeWillExpandListener TrustAnchor TrustManager TrustManagerFactory
TrustManagerFactorySpi Type TypeInfoProvider TypeNotPresentException Types TypeVariable UID UIDefaults
UIManager UIResource UndeclaredThrowableException UndoableEdit UndoableEditEvent UndoableEditListener
UndoableEditSupport UndoManager UnexpectedException UnicastRemoteObject UnknownError
UnknownFormatConversionException UnknownFormatFlagsException UnknownGroupException UnknownHostException
UnknownObjectException UnknownServiceException UnmappableCharacterException UnmarshalException
UnmodifiableClassException UnmodifiableSetException UnrecoverableEntryException
UnrecoverableKeyException Unreferenced UnresolvedAddressException UnresolvedPermission
UnsatisfiedLinkError UnsolicitedNotification UnsolicitedNotificationEvent
UnsolicitedNotificationListener UnsupportedAddressTypeException UnsupportedAudioFileException
UnsupportedCallbackException UnsupportedCharsetException UnsupportedClassVersionError
UnsupportedEncodingException UnsupportedFlavorException UnsupportedLookAndFeelException
UnsupportedOperationException URI URIException URIResolver URISyntax URISyntaxException URL
URLClassLoader URLConnection URLDecoder URLEncoder URLStreamHandler URLStreamHandlerFactory
UTFDataFormatException Util UtilDelegate Utilities UUID Validator ValidatorHandler ValueExp ValueHandler
ValueHandlerMultiFormat VariableHeightLayoutCache Vector VerifyError VetoableChangeListener
VetoableChangeListenerProxy VetoableChangeSupport View ViewFactory ViewportLayout ViewportUI
VirtualMachineError Visibility VMID VoiceStatus Void VolatileImage WeakHashMap WeakReference WebRowSet
WildcardType Window WindowAdapter WindowConstants WindowEvent WindowFocusListener WindowListener
WindowStateListener WrappedPlainView WritableByteChannel WritableRaster WritableRenderedImage
WriteAbortedException Writer X500Principal X500PrivateCredential X509Certificate X509CertSelector
X509CRL X509CRLEntry X509CRLSelector X509EncodedKeySpec X509ExtendedKeyManager X509Extension
X509KeyManager X509TrustManager XAConnection XADataSource XAException XAResource Xid XMLConstants
XMLDecoder XMLEncoder XMLFormatter XMLGregorianCalendar XMLParseException XmlReader XmlWriter XPath
XPathConstants XPathException XPathExpression XPathExpressionException XPathFactory
XPathFactoryConfigurationException XPathFunction XPathFunctionException XPathFunctionResolver
XPathVariableResolver ZipEntry ZipException ZipFile ZipInputStream ZipOutputStream ZoneView
]
end
end
end

View File

@ -0,0 +1,224 @@
module CodeRay
module Scanners
class JavaScript < Scanner
include Streamable
register_for :java_script
file_extension 'js'
# The actual JavaScript keywords.
KEYWORDS = %w[
break case catch continue default delete do else
finally for function if in instanceof new
return switch throw try typeof var void while with
]
PREDEFINED_CONSTANTS = %w[
false null true undefined
]
MAGIC_VARIABLES = %w[ this arguments ] # arguments was introduced in JavaScript 1.4
KEYWORDS_EXPECTING_VALUE = WordList.new.add %w[
case delete in instanceof new return throw typeof with
]
# Reserved for future use.
RESERVED_WORDS = %w[
abstract boolean byte char class debugger double enum export extends
final float goto implements import int interface long native package
private protected public short static super synchronized throws transient
volatile
]
IDENT_KIND = WordList.new(:ident).
add(RESERVED_WORDS, :reserved).
add(PREDEFINED_CONSTANTS, :pre_constant).
add(MAGIC_VARIABLES, :local_variable).
add(KEYWORDS, :keyword)
ESCAPE = / [bfnrtv\n\\'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} /x
UNICODE_ESCAPE = / u[a-fA-F0-9]{4} | U[a-fA-F0-9]{8} /x
REGEXP_ESCAPE = / [bBdDsSwW] /x
STRING_CONTENT_PATTERN = {
"'" => /[^\\']+/,
'"' => /[^\\"]+/,
'/' => /[^\\\/]+/,
}
KEY_CHECK_PATTERN = {
"'" => / [^\\']* (?: \\.? [^\\']* )* '? \s* : /x,
'"' => / [^\\"]* (?: \\.? [^\\"]* )* "? \s* : /x,
}
def scan_tokens tokens, options
state = :initial
string_delimiter = nil
value_expected = true
key_expected = false
function_expected = false
until eos?
kind = nil
match = nil
case state
when :initial
if match = scan(/ \s+ | \\\n /x)
value_expected = true if !value_expected && match.index(?\n)
tokens << [match, :space]
next
elsif scan(%r! // [^\n\\]* (?: \\. [^\n\\]* )* | /\* (?: .*? \*/ | .* ) !mx)
value_expected = true
kind = :comment
elsif check(/\.?\d/)
key_expected = value_expected = false
if scan(/0[xX][0-9A-Fa-f]+/)
kind = :hex
elsif scan(/(?>0[0-7]+)(?![89.eEfF])/)
kind = :oct
elsif scan(/\d+[fF]|\d*\.\d+(?:[eE][+-]?\d+)?[fF]?|\d+[eE][+-]?\d+[fF]?/)
kind = :float
elsif scan(/\d+/)
kind = :integer
end
elsif value_expected && match = scan(/<([[:alpha:]]\w*) (?: [^\/>]*\/> | .*?<\/\1>)/xim)
# FIXME: scan over nested tags
xml_scanner.tokenize match
value_expected = false
next
elsif match = scan(/ [-+*=<>?:;,!&^|(\[{~%]+ | \.(?!\d) /x)
value_expected = true
last_operator = match[-1]
key_expected = (last_operator == ?{) || (last_operator == ?,)
function_expected = false
kind = :operator
elsif scan(/ [)\]}]+ /x)
function_expected = key_expected = value_expected = false
kind = :operator
elsif match = scan(/ [$a-zA-Z_][A-Za-z_0-9$]* /x)
kind = IDENT_KIND[match]
value_expected = (kind == :keyword) && KEYWORDS_EXPECTING_VALUE[match]
# TODO: labels
if kind == :ident
if match.index(?$) # $ allowed inside an identifier
kind = :predefined
elsif function_expected
kind = :function
elsif check(/\s*[=:]\s*function\b/)
kind = :function
elsif key_expected && check(/\s*:/)
kind = :key
end
end
function_expected = (kind == :keyword) && (match == 'function')
key_expected = false
elsif match = scan(/["']/)
if key_expected && check(KEY_CHECK_PATTERN[match])
state = :key
else
state = :string
end
tokens << [:open, state]
string_delimiter = match
kind = :delimiter
elsif value_expected && (match = scan(/\/(?=\S)/))
tokens << [:open, :regexp]
state = :regexp
string_delimiter = '/'
kind = :delimiter
elsif scan(/ \/ /x)
value_expected = true
key_expected = false
kind = :operator
else
getch
kind = :error
end
when :string, :regexp, :key
if scan(STRING_CONTENT_PATTERN[string_delimiter])
kind = :content
elsif match = scan(/["'\/]/)
tokens << [match, :delimiter]
if state == :regexp
modifiers = scan(/[gim]+/)
tokens << [modifiers, :modifier] if modifiers && !modifiers.empty?
end
tokens << [:close, state]
string_delimiter = nil
key_expected = value_expected = false
state = :initial
next
elsif state != :regexp && (match = scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox))
if string_delimiter == "'" && !(match == "\\\\" || match == "\\'")
kind = :content
else
kind = :char
end
elsif state == :regexp && scan(/ \\ (?: #{ESCAPE} | #{REGEXP_ESCAPE} | #{UNICODE_ESCAPE} ) /mox)
kind = :char
elsif scan(/\\./m)
kind = :content
elsif scan(/ \\ | $ /x)
tokens << [:close, state]
kind = :error
key_expected = value_expected = false
state = :initial
else
raise_inspect "else case \" reached; %p not handled." % peek(1), tokens
end
else
raise_inspect 'Unknown state', tokens
end
match ||= matched
if $CODERAY_DEBUG and not kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens
end
raise_inspect 'Empty token', tokens unless match
tokens << [match, kind]
end
if [:string, :regexp].include? state
tokens << [:close, state]
end
tokens
end
protected
def reset_instance
super
@xml_scanner.reset if defined? @xml_scanner
end
def xml_scanner
@xml_scanner ||= CodeRay.scanner :xml, :tokens => @tokens, :keep_tokens => true, :keep_state => true
end
end
end
end

View File

@ -0,0 +1,112 @@
module CodeRay
module Scanners
class JSON < Scanner
include Streamable
register_for :json
file_extension 'json'
KINDS_NOT_LOC = [
:float, :char, :content, :delimiter,
:error, :integer, :operator, :value,
]
CONSTANTS = %w( true false null )
IDENT_KIND = WordList.new(:key).add(CONSTANTS, :value)
ESCAPE = / [bfnrt\\"\/] /x
UNICODE_ESCAPE = / u[a-fA-F0-9]{4} /x
def scan_tokens tokens, options
state = :initial
stack = []
string_delimiter = nil
key_expected = false
until eos?
kind = nil
match = nil
case state
when :initial
if match = scan(/ \s+ | \\\n /x)
tokens << [match, :space]
next
elsif match = scan(/ [:,\[{\]}] /x)
kind = :operator
case match
when '{' then stack << :object; key_expected = true
when '[' then stack << :array
when ':' then key_expected = false
when ',' then key_expected = true if stack.last == :object
when '}', ']' then stack.pop # no error recovery, but works for valid JSON
end
elsif match = scan(/ true | false | null /x)
kind = IDENT_KIND[match]
elsif match = scan(/-?(?:0|[1-9]\d*)/)
kind = :integer
if scan(/\.\d+(?:[eE][-+]?\d+)?|[eE][-+]?\d+/)
match << matched
kind = :float
end
elsif match = scan(/"/)
state = key_expected ? :key : :string
tokens << [:open, state]
kind = :delimiter
else
getch
kind = :error
end
when :string, :key
if scan(/[^\\"]+/)
kind = :content
elsif scan(/"/)
tokens << ['"', :delimiter]
tokens << [:close, state]
state = :initial
next
elsif scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox)
kind = :char
elsif scan(/\\./m)
kind = :content
elsif scan(/ \\ | $ /x)
tokens << [:close, :delimiter]
kind = :error
state = :initial
else
raise_inspect "else case \" reached; %p not handled." % peek(1), tokens
end
else
raise_inspect 'Unknown state', tokens
end
match ||= matched
if $CODERAY_DEBUG and not kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens
end
raise_inspect 'Empty token', tokens unless match
tokens << [match, kind]
end
if [:string, :key].include? state
tokens << [:close, state]
end
tokens
end
end
end
end

View File

@ -5,13 +5,15 @@ module Scanners
load :ruby
# Nitro XHTML Scanner
#
# $Id$
class NitroXHTML < Scanner
include Streamable
register_for :nitro_xhtml
file_extension :xhtml
title 'Nitro XHTML'
KINDS_NOT_LOC = HTML::KINDS_NOT_LOC
NITRO_RUBY_BLOCK = /
<\?r
(?>
@ -119,6 +121,7 @@ module Scanners
else
raise_inspect 'else-case reached!', tokens
end
end

View File

@ -0,0 +1,527 @@
module CodeRay
module Scanners
load :html
# Original by Stefan Walk.
class PHP < Scanner
register_for :php
file_extension 'php'
KINDS_NOT_LOC = HTML::KINDS_NOT_LOC
def setup
@html_scanner = CodeRay.scanner :html, :tokens => @tokens, :keep_tokens => true, :keep_state => true
end
def reset_instance
super
@html_scanner.reset
end
module Words
# according to http://www.php.net/manual/en/reserved.keywords.php
KEYWORDS = %w[
abstract and array as break case catch class clone const continue declare default do else elseif
enddeclare endfor endforeach endif endswitch endwhile extends final for foreach function global
goto if implements interface instanceof namespace new or private protected public static switch
throw try use var while xor
cfunction old_function
]
TYPES = %w[ int integer float double bool boolean string array object resource ]
LANGUAGE_CONSTRUCTS = %w[
die echo empty exit eval include include_once isset list
require require_once return print unset
]
CLASSES = %w[ Directory stdClass __PHP_Incomplete_Class exception php_user_filter Closure ]
# according to http://php.net/quickref.php on 2009-04-21;
# all functions with _ excluded (module functions) and selected additional functions
BUILTIN_FUNCTIONS = %w[
abs acos acosh addcslashes addslashes aggregate array arsort ascii2ebcdic asin asinh asort assert atan atan2
atanh basename bcadd bccomp bcdiv bcmod bcmul bcpow bcpowmod bcscale bcsqrt bcsub bin2hex bindec
bindtextdomain bzclose bzcompress bzdecompress bzerrno bzerror bzerrstr bzflush bzopen bzread bzwrite
calculhmac ceil chdir checkdate checkdnsrr chgrp chmod chop chown chr chroot clearstatcache closedir closelog
compact constant copy cos cosh count crc32 crypt current date dcgettext dcngettext deaggregate decbin dechex
decoct define defined deg2rad delete dgettext die dirname diskfreespace dl dngettext doubleval each
ebcdic2ascii echo empty end ereg eregi escapeshellarg escapeshellcmd eval exec exit exp explode expm1 extract
fclose feof fflush fgetc fgetcsv fgets fgetss file fileatime filectime filegroup fileinode filemtime fileowner
fileperms filepro filesize filetype floatval flock floor flush fmod fnmatch fopen fpassthru fprintf fputcsv
fputs fread frenchtojd fscanf fseek fsockopen fstat ftell ftok ftruncate fwrite getallheaders getcwd getdate
getenv gethostbyaddr gethostbyname gethostbynamel getimagesize getlastmod getmxrr getmygid getmyinode getmypid
getmyuid getopt getprotobyname getprotobynumber getrandmax getrusage getservbyname getservbyport gettext
gettimeofday gettype glob gmdate gmmktime gmstrftime gregoriantojd gzclose gzcompress gzdecode gzdeflate
gzencode gzeof gzfile gzgetc gzgets gzgetss gzinflate gzopen gzpassthru gzputs gzread gzrewind gzseek gztell
gzuncompress gzwrite hash header hebrev hebrevc hexdec htmlentities htmlspecialchars hypot iconv idate
implode include intval ip2long iptcembed iptcparse isset
jddayofweek jdmonthname jdtofrench jdtogregorian jdtojewish jdtojulian jdtounix jewishtojd join jpeg2wbmp
juliantojd key krsort ksort lcfirst lchgrp lchown levenshtein link linkinfo list localeconv localtime log
log10 log1p long2ip lstat ltrim mail main max md5 metaphone mhash microtime min mkdir mktime msql natcasesort
natsort next ngettext nl2br nthmac octdec opendir openlog
ord overload pack passthru pathinfo pclose pfsockopen phpcredits phpinfo phpversion pi png2wbmp popen pos pow
prev print printf putenv quotemeta rad2deg rand range rawurldecode rawurlencode readdir readfile readgzfile
readline readlink realpath recode rename require reset rewind rewinddir rmdir round rsort rtrim scandir
serialize setcookie setlocale setrawcookie settype sha1 shuffle signeurlpaiement sin sinh sizeof sleep snmpget
snmpgetnext snmprealwalk snmpset snmpwalk snmpwalkoid sort soundex split spliti sprintf sqrt srand sscanf stat
strcasecmp strchr strcmp strcoll strcspn strftime stripcslashes stripos stripslashes stristr strlen
strnatcasecmp strnatcmp strncasecmp strncmp strpbrk strpos strptime strrchr strrev strripos strrpos strspn
strstr strtok strtolower strtotime strtoupper strtr strval substr symlink syslog system tan tanh tempnam
textdomain time tmpfile touch trim uasort ucfirst ucwords uksort umask uniqid unixtojd unlink unpack
unserialize unset urldecode urlencode usleep usort vfprintf virtual vprintf vsprintf wordwrap
array_change_key_case array_chunk array_combine array_count_values array_diff array_diff_assoc
array_diff_key array_diff_uassoc array_diff_ukey array_fill array_fill_keys array_filter array_flip
array_intersect array_intersect_assoc array_intersect_key array_intersect_uassoc array_intersect_ukey
array_key_exists array_keys array_map array_merge array_merge_recursive array_multisort array_pad
array_pop array_product array_push array_rand array_reduce array_reverse array_search array_shift
array_slice array_splice array_sum array_udiff array_udiff_assoc array_udiff_uassoc array_uintersect
array_uintersect_assoc array_uintersect_uassoc array_unique array_unshift array_values array_walk
array_walk_recursive
assert_options base_convert base64_decode base64_encode
chunk_split class_exists class_implements class_parents
count_chars debug_backtrace debug_print_backtrace debug_zval_dump
error_get_last error_log error_reporting extension_loaded
file_exists file_get_contents file_put_contents load_file
func_get_arg func_get_args func_num_args function_exists
get_browser get_called_class get_cfg_var get_class get_class_methods get_class_vars
get_current_user get_declared_classes get_declared_interfaces get_defined_constants
get_defined_functions get_defined_vars get_extension_funcs get_headers get_html_translation_table
get_include_path get_included_files get_loaded_extensions get_magic_quotes_gpc get_magic_quotes_runtime
get_meta_tags get_object_vars get_parent_class get_required_filesget_resource_type
gc_collect_cycles gc_disable gc_enable gc_enabled
halt_compiler headers_list headers_sent highlight_file highlight_string
html_entity_decode htmlspecialchars_decode
in_array include_once inclued_get_data
is_a is_array is_binary is_bool is_buffer is_callable is_dir is_double is_executable is_file is_finite
is_float is_infinite is_int is_integer is_link is_long is_nan is_null is_numeric is_object is_readable
is_real is_resource is_scalar is_soap_fault is_string is_subclass_of is_unicode is_uploaded_file
is_writable is_writeable
locale_get_default locale_set_default
number_format override_function parse_str parse_url
php_check_syntax php_ini_loaded_file php_ini_scanned_files php_logo_guid php_sapi_name
php_strip_whitespace php_uname
preg_filter preg_grep preg_last_error preg_match preg_match_all preg_quote preg_replace
preg_replace_callback preg_split print_r
require_once register_shutdown_function register_tick_function
set_error_handler set_exception_handler set_file_buffer set_include_path
set_magic_quotes_runtime set_time_limit shell_exec
str_getcsv str_ireplace str_pad str_repeat str_replace str_rot13 str_shuffle str_split str_word_count
strip_tags substr_compare substr_count substr_replace
time_nanosleep time_sleep_until
token_get_all token_name trigger_error
unregister_tick_function use_soap_error_handler user_error
utf8_decode utf8_encode var_dump var_export
version_compare
zend_logo_guid zend_thread_id zend_version
create_function call_user_func_array
posix_access posix_ctermid posix_get_last_error posix_getcwd posix_getegid
posix_geteuid posix_getgid posix_getgrgid posix_getgrnam posix_getgroups
posix_getlogin posix_getpgid posix_getpgrp posix_getpid posix_getppid
posix_getpwnam posix_getpwuid posix_getrlimit posix_getsid posix_getuid
posix_initgroups posix_isatty posix_kill posix_mkfifo posix_mknod
posix_setegid posix_seteuid posix_setgid posix_setpgid posix_setsid
posix_setuid posix_strerror posix_times posix_ttyname posix_uname
pcntl_alarm pcntl_exec pcntl_fork pcntl_getpriority pcntl_setpriority
pcntl_signal pcntl_signal_dispatch pcntl_sigprocmask pcntl_sigtimedwait
pcntl_sigwaitinfo pcntl_wait pcntl_waitpid pcntl_wexitstatus pcntl_wifexited
pcntl_wifsignaled pcntl_wifstopped pcntl_wstopsig pcntl_wtermsig
]
# TODO: more built-in PHP functions?
EXCEPTIONS = %w[
E_ERROR E_WARNING E_PARSE E_NOTICE E_CORE_ERROR E_CORE_WARNING E_COMPILE_ERROR E_COMPILE_WARNING
E_USER_ERROR E_USER_WARNING E_USER_NOTICE E_DEPRECATED E_USER_DEPRECATED E_ALL E_STRICT
]
CONSTANTS = %w[
null true false self parent
__LINE__ __DIR__ __FILE__ __LINE__
__CLASS__ __NAMESPACE__ __METHOD__ __FUNCTION__
PHP_VERSION PHP_MAJOR_VERSION PHP_MINOR_VERSION PHP_RELEASE_VERSION PHP_VERSION_ID PHP_EXTRA_VERSION PHP_ZTS
PHP_DEBUG PHP_MAXPATHLEN PHP_OS PHP_SAPI PHP_EOL PHP_INT_MAX PHP_INT_SIZE DEFAULT_INCLUDE_PATH
PEAR_INSTALL_DIR PEAR_EXTENSION_DIR PHP_EXTENSION_DIR PHP_PREFIX PHP_BINDIR PHP_LIBDIR PHP_DATADIR
PHP_SYSCONFDIR PHP_LOCALSTATEDIR PHP_CONFIG_FILE_PATH PHP_CONFIG_FILE_SCAN_DIR PHP_SHLIB_SUFFIX
PHP_OUTPUT_HANDLER_START PHP_OUTPUT_HANDLER_CONT PHP_OUTPUT_HANDLER_END
__COMPILER_HALT_OFFSET__
EXTR_OVERWRITE EXTR_SKIP EXTR_PREFIX_SAME EXTR_PREFIX_ALL EXTR_PREFIX_INVALID EXTR_PREFIX_IF_EXISTS
EXTR_IF_EXISTS SORT_ASC SORT_DESC SORT_REGULAR SORT_NUMERIC SORT_STRING CASE_LOWER CASE_UPPER COUNT_NORMAL
COUNT_RECURSIVE ASSERT_ACTIVE ASSERT_CALLBACK ASSERT_BAIL ASSERT_WARNING ASSERT_QUIET_EVAL CONNECTION_ABORTED
CONNECTION_NORMAL CONNECTION_TIMEOUT INI_USER INI_PERDIR INI_SYSTEM INI_ALL M_E M_LOG2E M_LOG10E M_LN2 M_LN10
M_PI M_PI_2 M_PI_4 M_1_PI M_2_PI M_2_SQRTPI M_SQRT2 M_SQRT1_2 CRYPT_SALT_LENGTH CRYPT_STD_DES CRYPT_EXT_DES
CRYPT_MD5 CRYPT_BLOWFISH DIRECTORY_SEPARATOR SEEK_SET SEEK_CUR SEEK_END LOCK_SH LOCK_EX LOCK_UN LOCK_NB
HTML_SPECIALCHARS HTML_ENTITIES ENT_COMPAT ENT_QUOTES ENT_NOQUOTES INFO_GENERAL INFO_CREDITS
INFO_CONFIGURATION INFO_MODULES INFO_ENVIRONMENT INFO_VARIABLES INFO_LICENSE INFO_ALL CREDITS_GROUP
CREDITS_GENERAL CREDITS_SAPI CREDITS_MODULES CREDITS_DOCS CREDITS_FULLPAGE CREDITS_QA CREDITS_ALL STR_PAD_LEFT
STR_PAD_RIGHT STR_PAD_BOTH PATHINFO_DIRNAME PATHINFO_BASENAME PATHINFO_EXTENSION PATH_SEPARATOR CHAR_MAX
LC_CTYPE LC_NUMERIC LC_TIME LC_COLLATE LC_MONETARY LC_ALL LC_MESSAGES ABDAY_1 ABDAY_2 ABDAY_3 ABDAY_4 ABDAY_5
ABDAY_6 ABDAY_7 DAY_1 DAY_2 DAY_3 DAY_4 DAY_5 DAY_6 DAY_7 ABMON_1 ABMON_2 ABMON_3 ABMON_4 ABMON_5 ABMON_6
ABMON_7 ABMON_8 ABMON_9 ABMON_10 ABMON_11 ABMON_12 MON_1 MON_2 MON_3 MON_4 MON_5 MON_6 MON_7 MON_8 MON_9
MON_10 MON_11 MON_12 AM_STR PM_STR D_T_FMT D_FMT T_FMT T_FMT_AMPM ERA ERA_YEAR ERA_D_T_FMT ERA_D_FMT ERA_T_FMT
ALT_DIGITS INT_CURR_SYMBOL CURRENCY_SYMBOL CRNCYSTR MON_DECIMAL_POINT MON_THOUSANDS_SEP MON_GROUPING
POSITIVE_SIGN NEGATIVE_SIGN INT_FRAC_DIGITS FRAC_DIGITS P_CS_PRECEDES P_SEP_BY_SPACE N_CS_PRECEDES
N_SEP_BY_SPACE P_SIGN_POSN N_SIGN_POSN DECIMAL_POINT RADIXCHAR THOUSANDS_SEP THOUSEP GROUPING YESEXPR NOEXPR
YESSTR NOSTR CODESET LOG_EMERG LOG_ALERT LOG_CRIT LOG_ERR LOG_WARNING LOG_NOTICE LOG_INFO LOG_DEBUG LOG_KERN
LOG_USER LOG_MAIL LOG_DAEMON LOG_AUTH LOG_SYSLOG LOG_LPR LOG_NEWS LOG_UUCP LOG_CRON LOG_AUTHPRIV LOG_LOCAL0
LOG_LOCAL1 LOG_LOCAL2 LOG_LOCAL3 LOG_LOCAL4 LOG_LOCAL5 LOG_LOCAL6 LOG_LOCAL7 LOG_PID LOG_CONS LOG_ODELAY
LOG_NDELAY LOG_NOWAIT LOG_PERROR
]
PREDEFINED = %w[
$GLOBALS $_SERVER $_GET $_POST $_FILES $_REQUEST $_SESSION $_ENV
$_COOKIE $php_errormsg $HTTP_RAW_POST_DATA $http_response_header
$argc $argv
]
IDENT_KIND = CaseIgnoringWordList.new(:ident).
add(KEYWORDS, :reserved).
add(TYPES, :pre_type).
add(LANGUAGE_CONSTRUCTS, :reserved).
add(BUILTIN_FUNCTIONS, :predefined).
add(CLASSES, :pre_constant).
add(EXCEPTIONS, :exception).
add(CONSTANTS, :pre_constant)
VARIABLE_KIND = WordList.new(:local_variable).
add(PREDEFINED, :predefined)
end
module RE
PHP_START = /
<script\s+[^>]*?language\s*=\s*"php"[^>]*?> |
<script\s+[^>]*?language\s*=\s*'php'[^>]*?> |
<\?php\d? |
<\?(?!xml)
/xi
PHP_END = %r!
</script> |
\?>
!xi
HTML_INDICATOR = /<!DOCTYPE html|<(?:html|body|div|p)[> ]/i
IDENTIFIER = /[a-z_\x7f-\xFF][a-z0-9_\x7f-\xFF]*/i
VARIABLE = /\$#{IDENTIFIER}/
OPERATOR = /
\.(?!\d)=? | # dot that is not decimal point, string concatenation
&& | \|\| | # logic
:: | -> | => | # scope, member, dictionary
\\(?!\n) | # namespace
\+\+ | -- | # increment, decrement
[,;?:()\[\]{}] | # simple delimiters
[-+*\/%&|^]=? | # ordinary math, binary logic, assignment shortcuts
[~$] | # whatever
=& | # reference assignment
[=!]=?=? | <> | # comparison and assignment
<<=? | >>=? | [<>]=? # comparison and shift
/x
end
def scan_tokens tokens, options
if check(RE::PHP_START) || # starts with <?
(match?(/\s*<\S/) && exist?(RE::PHP_START)) || # starts with tag and contains <?
exist?(RE::HTML_INDICATOR) ||
check(/.{1,100}#{RE::PHP_START}/om) # PHP start after max 100 chars
# is HTML with embedded PHP, so start with HTML
states = [:initial]
else
# is just PHP, so start with PHP surrounded by HTML
states = [:initial, :php]
end
label_expected = true
case_expected = false
heredoc_delimiter = nil
delimiter = nil
modifier = nil
until eos?
match = nil
kind = nil
case states.last
when :initial # HTML
if scan RE::PHP_START
kind = :inline_delimiter
label_expected = true
states << :php
else
match = scan_until(/(?=#{RE::PHP_START})/o) || scan_until(/\z/)
@html_scanner.tokenize match unless match.empty?
next
end
when :php
if match = scan(/\s+/)
tokens << [match, :space]
next
elsif scan(%r! (?m: \/\* (?: .*? \*\/ | .* ) ) | (?://|\#) .*? (?=#{RE::PHP_END}|$) !xo)
kind = :comment
elsif match = scan(RE::IDENTIFIER)
kind = Words::IDENT_KIND[match]
if kind == :ident && label_expected && check(/:(?!:)/)
kind = :label
label_expected = true
else
label_expected = false
if kind == :ident && match =~ /^[A-Z]/
kind = :constant
elsif kind == :reserved
case match
when 'class'
states << :class_expected
when 'function'
states << :function_expected
when 'case', 'default'
case_expected = true
end
elsif match == 'b' && check(/['"]/) # binary string literal
modifier = match
next
end
end
elsif scan(/(?:\d+\.\d*|\d*\.\d+)(?:e[-+]?\d+)?|\d+e[-+]?\d+/i)
label_expected = false
kind = :float
elsif scan(/0x[0-9a-fA-F]+/)
label_expected = false
kind = :hex
elsif scan(/\d+/)
label_expected = false
kind = :integer
elsif scan(/'/)
tokens << [:open, :string]
if modifier
tokens << [modifier, :modifier]
modifier = nil
end
kind = :delimiter
states.push :sqstring
elsif match = scan(/["`]/)
tokens << [:open, :string]
if modifier
tokens << [modifier, :modifier]
modifier = nil
end
delimiter = match
kind = :delimiter
states.push :dqstring
elsif match = scan(RE::VARIABLE)
label_expected = false
kind = Words::VARIABLE_KIND[match]
elsif scan(/\{/)
kind = :operator
label_expected = true
states.push :php
elsif scan(/\}/)
if states.size == 1
kind = :error
else
states.pop
if states.last.is_a?(::Array)
delimiter = states.last[1]
states[-1] = states.last[0]
tokens << [matched, :delimiter]
tokens << [:close, :inline]
next
else
kind = :operator
label_expected = true
end
end
elsif scan(/@/)
label_expected = false
kind = :exception
elsif scan RE::PHP_END
kind = :inline_delimiter
states = [:initial]
elsif match = scan(/<<<(?:(#{RE::IDENTIFIER})|"(#{RE::IDENTIFIER})"|'(#{RE::IDENTIFIER})')/o)
tokens << [:open, :string]
warn 'heredoc in heredoc?' if heredoc_delimiter
heredoc_delimiter = Regexp.escape(self[1] || self[2] || self[3])
kind = :delimiter
states.push self[3] ? :sqstring : :dqstring
heredoc_delimiter = /#{heredoc_delimiter}(?=;?$)/
elsif match = scan(/#{RE::OPERATOR}/o)
label_expected = match == ';'
if case_expected
label_expected = true if match == ':'
case_expected = false
end
kind = :operator
else
getch
kind = :error
end
when :sqstring
if scan(heredoc_delimiter ? /[^\\\n]+/ : /[^'\\]+/)
kind = :content
elsif !heredoc_delimiter && scan(/'/)
tokens << [matched, :delimiter]
tokens << [:close, :string]
delimiter = nil
label_expected = false
states.pop
next
elsif heredoc_delimiter && match = scan(/\n/)
kind = :content
if scan heredoc_delimiter
tokens << ["\n", :content]
tokens << [matched, :delimiter]
tokens << [:close, :string]
heredoc_delimiter = nil
label_expected = false
states.pop
next
end
elsif scan(heredoc_delimiter ? /\\\\/ : /\\[\\'\n]/)
kind = :char
elsif scan(/\\./m)
kind = :content
elsif scan(/\\/)
kind = :error
end
when :dqstring
if scan(heredoc_delimiter ? /[^${\\\n]+/ : (delimiter == '"' ? /[^"${\\]+/ : /[^`${\\]+/))
kind = :content
elsif !heredoc_delimiter && scan(delimiter == '"' ? /"/ : /`/)
tokens << [matched, :delimiter]
tokens << [:close, :string]
delimiter = nil
label_expected = false
states.pop
next
elsif heredoc_delimiter && match = scan(/\n/)
kind = :content
if scan heredoc_delimiter
tokens << ["\n", :content]
tokens << [matched, :delimiter]
tokens << [:close, :string]
heredoc_delimiter = nil
label_expected = false
states.pop
next
end
elsif scan(/\\(?:x[0-9A-Fa-f]{1,2}|[0-7]{1,3})/)
kind = :char
elsif scan(heredoc_delimiter ? /\\[nrtvf\\$]/ : (delimiter == '"' ? /\\[nrtvf\\$"]/ : /\\[nrtvf\\$`]/))
kind = :char
elsif scan(/\\./m)
kind = :content
elsif scan(/\\/)
kind = :error
elsif match = scan(/#{RE::VARIABLE}/o)
kind = :local_variable
if check(/\[#{RE::IDENTIFIER}\]/o)
tokens << [:open, :inline]
tokens << [match, :local_variable]
tokens << [scan(/\[/), :operator]
tokens << [scan(/#{RE::IDENTIFIER}/o), :ident]
tokens << [scan(/\]/), :operator]
tokens << [:close, :inline]
next
elsif check(/\[/)
match << scan(/\[['"]?#{RE::IDENTIFIER}?['"]?\]?/o)
kind = :error
elsif check(/->#{RE::IDENTIFIER}/o)
tokens << [:open, :inline]
tokens << [match, :local_variable]
tokens << [scan(/->/), :operator]
tokens << [scan(/#{RE::IDENTIFIER}/o), :ident]
tokens << [:close, :inline]
next
elsif check(/->/)
match << scan(/->/)
kind = :error
end
elsif match = scan(/\{/)
if check(/\$/)
kind = :delimiter
states[-1] = [states.last, delimiter]
delimiter = nil
states.push :php
tokens << [:open, :inline]
else
kind = :string
end
elsif scan(/\$\{#{RE::IDENTIFIER}\}/o)
kind = :local_variable
elsif scan(/\$/)
kind = :content
end
when :class_expected
if scan(/\s+/)
kind = :space
elsif match = scan(/#{RE::IDENTIFIER}/o)
kind = :class
states.pop
else
states.pop
next
end
when :function_expected
if scan(/\s+/)
kind = :space
elsif scan(/&/)
kind = :operator
elsif match = scan(/#{RE::IDENTIFIER}/o)
kind = :function
states.pop
else
states.pop
next
end
else
raise_inspect 'Unknown state!', tokens, states
end
match ||= matched
if $CODERAY_DEBUG and not kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens, states
end
raise_inspect 'Empty token', tokens, states unless match
tokens << [match, kind]
end
tokens
end
end
end
end

View File

@ -4,9 +4,12 @@ module Scanners
class Plaintext < Scanner
register_for :plaintext, :plain
title 'Plain text'
include Streamable
KINDS_NOT_LOC = [:plain]
def scan_tokens tokens, options
text = (scan_until(/\z/) || '')
tokens << [text, :plain]

View File

@ -0,0 +1,285 @@
module CodeRay
module Scanners
# Bases on pygments' PythonLexer, see
# http://dev.pocoo.org/projects/pygments/browser/pygments/lexers/agile.py.
class Python < Scanner
include Streamable
register_for :python
file_extension 'py'
KEYWORDS = [
'and', 'as', 'assert', 'break', 'class', 'continue', 'def',
'del', 'elif', 'else', 'except', 'finally', 'for',
'from', 'global', 'if', 'import', 'in', 'is', 'lambda', 'not',
'or', 'pass', 'raise', 'return', 'try', 'while', 'with', 'yield',
'nonlocal', # new in Python 3
]
OLD_KEYWORDS = [
'exec', 'print', # gone in Python 3
]
PREDEFINED_METHODS_AND_TYPES = %w[
__import__ abs all any apply basestring bin bool buffer
bytearray bytes callable chr classmethod cmp coerce compile
complex delattr dict dir divmod enumerate eval execfile exit
file filter float frozenset getattr globals hasattr hash hex id
input int intern isinstance issubclass iter len list locals
long map max min next object oct open ord pow property range
raw_input reduce reload repr reversed round set setattr slice
sorted staticmethod str sum super tuple type unichr unicode
vars xrange zip
]
PREDEFINED_EXCEPTIONS = %w[
ArithmeticError AssertionError AttributeError
BaseException DeprecationWarning EOFError EnvironmentError
Exception FloatingPointError FutureWarning GeneratorExit IOError
ImportError ImportWarning IndentationError IndexError KeyError
KeyboardInterrupt LookupError MemoryError NameError
NotImplemented NotImplementedError OSError OverflowError
OverflowWarning PendingDeprecationWarning ReferenceError
RuntimeError RuntimeWarning StandardError StopIteration
SyntaxError SyntaxWarning SystemError SystemExit TabError
TypeError UnboundLocalError UnicodeDecodeError
UnicodeEncodeError UnicodeError UnicodeTranslateError
UnicodeWarning UserWarning ValueError Warning ZeroDivisionError
]
PREDEFINED_VARIABLES_AND_CONSTANTS = [
'False', 'True', 'None', # "keywords" since Python 3
'self', 'Ellipsis', 'NotImplemented',
]
IDENT_KIND = WordList.new(:ident).
add(KEYWORDS, :keyword).
add(OLD_KEYWORDS, :old_keyword).
add(PREDEFINED_METHODS_AND_TYPES, :predefined).
add(PREDEFINED_VARIABLES_AND_CONSTANTS, :pre_constant).
add(PREDEFINED_EXCEPTIONS, :exception)
NAME = / [^\W\d] \w* /x
ESCAPE = / [abfnrtv\n\\'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} /x
UNICODE_ESCAPE = / u[a-fA-F0-9]{4} | U[a-fA-F0-9]{8} | N\{[-\w ]+\} /x
OPERATOR = /
\.\.\. | # ellipsis
\.(?!\d) | # dot but not decimal point
[,;:()\[\]{}] | # simple delimiters
\/\/=? | \*\*=? | # special math
[-+*\/%&|^]=? | # ordinary math and binary logic
[~`] | # binary complement and inspection
<<=? | >>=? | [<>=]=? | != # comparison and assignment
/x
STRING_DELIMITER_REGEXP = Hash.new do |h, delimiter|
h[delimiter] = Regexp.union delimiter
end
STRING_CONTENT_REGEXP = Hash.new do |h, delimiter|
h[delimiter] = / [^\\\n]+? (?= \\ | $ | #{Regexp.escape(delimiter)} ) /x
end
DEF_NEW_STATE = WordList.new(:initial).
add(%w(def), :def_expected).
add(%w(import from), :include_expected).
add(%w(class), :class_expected)
DESCRIPTOR = /
#{NAME}
(?: \. #{NAME} )*
| \*
/x
def scan_tokens tokens, options
state = :initial
string_delimiter = nil
string_raw = false
import_clause = class_name_follows = last_token_dot = false
unicode = string.respond_to?(:encoding) && string.encoding.name == 'UTF-8'
from_import_state = []
until eos?
kind = nil
match = nil
if state == :string
if scan(STRING_DELIMITER_REGEXP[string_delimiter])
tokens << [matched, :delimiter]
tokens << [:close, :string]
state = :initial
next
elsif string_delimiter.size == 3 && scan(/\n/)
kind = :content
elsif scan(STRING_CONTENT_REGEXP[string_delimiter])
kind = :content
elsif !string_raw && scan(/ \\ #{ESCAPE} /ox)
kind = :char
elsif scan(/ \\ #{UNICODE_ESCAPE} /ox)
kind = :char
elsif scan(/ \\ . /x)
kind = :content
elsif scan(/ \\ | $ /x)
tokens << [:close, :string]
kind = :error
state = :initial
else
raise_inspect "else case \" reached; %p not handled." % peek(1), tokens, state
end
elsif match = scan(/ [ \t]+ | \\\n /x)
tokens << [match, :space]
next
elsif match = scan(/\n/)
tokens << [match, :space]
state = :initial if state == :include_expected
next
elsif match = scan(/ \# [^\n]* /mx)
tokens << [match, :comment]
next
elsif state == :initial
if scan(/#{OPERATOR}/o)
kind = :operator
elsif match = scan(/(u?r?|b)?("""|"|'''|')/i)
tokens << [:open, :string]
string_delimiter = self[2]
string_raw = false
modifiers = self[1]
unless modifiers.empty?
string_raw = !!modifiers.index(?r)
tokens << [modifiers, :modifier]
match = string_delimiter
end
state = :string
kind = :delimiter
# TODO: backticks
elsif match = scan(unicode ? /#{NAME}/uo : /#{NAME}/o)
kind = IDENT_KIND[match]
# TODO: keyword arguments
kind = :ident if last_token_dot
if kind == :old_keyword
kind = check(/\(/) ? :ident : :keyword
elsif kind == :predefined && check(/ *=/)
kind = :ident
elsif kind == :keyword
state = DEF_NEW_STATE[match]
from_import_state << match.to_sym if state == :include_expected
end
elsif scan(/@[a-zA-Z0-9_.]+[lL]?/)
kind = :decorator
elsif scan(/0[xX][0-9A-Fa-f]+[lL]?/)
kind = :hex
elsif scan(/0[bB][01]+[lL]?/)
kind = :bin
elsif match = scan(/(?:\d*\.\d+|\d+\.\d*)(?:[eE][+-]?\d+)?|\d+[eE][+-]?\d+/)
kind = :float
if scan(/[jJ]/)
match << matched
kind = :imaginary
end
elsif scan(/0[oO][0-7]+|0[0-7]+(?![89.eE])[lL]?/)
kind = :oct
elsif match = scan(/\d+([lL])?/)
kind = :integer
if self[1] == nil && scan(/[jJ]/)
match << matched
kind = :imaginary
end
else
getch
kind = :error
end
elsif state == :def_expected
state = :initial
if match = scan(unicode ? /#{NAME}/uo : /#{NAME}/o)
kind = :method
else
next
end
elsif state == :class_expected
state = :initial
if match = scan(unicode ? /#{NAME}/uo : /#{NAME}/o)
kind = :class
else
next
end
elsif state == :include_expected
if match = scan(unicode ? /#{DESCRIPTOR}/uo : /#{DESCRIPTOR}/o)
kind = :include
if match == 'as'
kind = :keyword
from_import_state << :as
elsif from_import_state.first == :from && match == 'import'
kind = :keyword
from_import_state << :import
elsif from_import_state.last == :as
# kind = match[0,1][unicode ? /[[:upper:]]/u : /[[:upper:]]/] ? :class : :method
kind = :ident
from_import_state.pop
elsif IDENT_KIND[match] == :keyword
unscan
match = nil
state = :initial
next
end
elsif match = scan(/,/)
from_import_state.pop if from_import_state.last == :as
kind = :operator
else
from_import_state = []
state = :initial
next
end
else
raise_inspect 'Unknown state', tokens, state
end
match ||= matched
if $CODERAY_DEBUG and not kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens, state
end
raise_inspect 'Empty token', tokens, state unless match
last_token_dot = match == '.'
tokens << [match, kind]
end
if state == :string
tokens << [:close, :string]
end
tokens
end
end
end
end

View File

@ -5,12 +5,13 @@ module Scanners
load :ruby
# RHTML Scanner
#
# $Id$
class RHTML < Scanner
include Streamable
register_for :rhtml
title 'HTML ERB Template'
KINDS_NOT_LOC = HTML::KINDS_NOT_LOC
ERB_RUBY_BLOCK = /
<%(?!%)[=-]?

View File

@ -21,6 +21,10 @@ module Scanners
file_extension 'rb'
helper :patterns
if not defined? EncodingError
EncodingError = Class.new Exception
end
private
def scan_tokens tokens, options
@ -31,9 +35,10 @@ module Scanners
state = :initial
depth = nil
inline_block_stack = []
unicode = string.respond_to?(:encoding) && string.encoding.name == 'UTF-8'
patterns = Patterns # avoid constant lookup
until eos?
match = nil
kind = nil
@ -124,14 +129,15 @@ module Scanners
# {{{
if match = scan(/[ \t\f]+/)
kind = :space
match << scan(/\s*/) unless eos? or heredocs
match << scan(/\s*/) unless eos? || heredocs
value_expected = true if match.index(?\n)
tokens << [match, kind]
next
elsif match = scan(/\\?\n/)
kind = :space
if match == "\n"
value_expected = true # FIXME not quite true
value_expected = true
state = :initial if state == :undef_comma_expected
end
if heredocs
@ -146,17 +152,21 @@ module Scanners
tokens << [match, kind]
next
elsif bol? && match = scan(/\#!.*/)
tokens << [match, :doctype]
next
elsif match = scan(/\#.*/) or
( bol? and match = scan(/#{patterns::RUBYDOC_OR_DATA}/o) )
kind = :comment
value_expected = true
tokens << [match, kind]
next
elsif state == :initial
# IDENTS #
if match = scan(/#{patterns::METHOD_NAME}/o)
if match = scan(unicode ? /#{patterns::METHOD_NAME}/uo :
/#{patterns::METHOD_NAME}/o)
if last_token_dot
kind = if match[/^[A-Z]/] and not match?(/\(/) then :constant else :ident end
else
@ -165,13 +175,12 @@ module Scanners
kind = :constant
elsif kind == :reserved
state = patterns::DEF_NEW_STATE[match]
value_expected = :set if patterns::KEYWORDS_EXPECTING_VALUE[match]
end
end
## experimental!
value_expected = :set if
patterns::REGEXP_ALLOWED[match] or check(/#{patterns::VALUE_FOLLOWS}/o)
value_expected = :set if check(/#{patterns::VALUE_FOLLOWS}/o)
elsif last_token_dot and match = scan(/#{patterns::METHOD_NAME_OPERATOR}/o)
elsif last_token_dot and match = scan(/#{patterns::METHOD_NAME_OPERATOR}|\(/o)
kind = :ident
value_expected = :set if check(/#{patterns::VALUE_FOLLOWS}/o)
@ -190,6 +199,7 @@ module Scanners
depth -= 1
if depth == 0 # closing brace of inline block reached
state, depth, heredocs = inline_block_stack.pop
heredocs = nil if heredocs && heredocs.empty?
tokens << [match, :inline_delimiter]
kind = :inline
match = :close
@ -211,8 +221,9 @@ module Scanners
interpreted = true
state = patterns::StringState.new :regexp, interpreted, match
elsif match = scan(/#{patterns::NUMERIC}/o)
kind = if self[1] then :float else :integer end
# elsif match = scan(/[-+]?#{patterns::NUMERIC}/o)
elsif match = value_expected ? scan(/[-+]?#{patterns::NUMERIC}/o) : scan(/#{patterns::NUMERIC}/o)
kind = self[1] ? :float : :integer
elsif match = scan(/#{patterns::SYMBOL}/o)
case delim = match[1]
@ -273,6 +284,21 @@ module Scanners
kind = :class_variable
else
if !unicode
# check for unicode
debug, $DEBUG = $DEBUG, false
begin
if check(/./mu).size > 1
# seems like we should try again with unicode
unicode = true
end
rescue
# bad unicode char; use getch
ensure
$DEBUG = debug
end
next if unicode
end
kind = :error
match = getch
@ -280,12 +306,29 @@ module Scanners
elsif state == :def_expected
state = :initial
if match = scan(/(?>#{patterns::METHOD_NAME_EX})(?!\.|::)/o)
if scan(/self\./)
tokens << ['self', :pre_constant]
tokens << ['.', :operator]
end
if match = scan(unicode ? /(?>#{patterns::METHOD_NAME_EX})(?!\.|::)/uo :
/(?>#{patterns::METHOD_NAME_EX})(?!\.|::)/o)
kind = :method
else
next
end
elsif state == :module_expected
if match = scan(/<</)
kind = :operator
else
state = :initial
if match = scan(/ (?:#{patterns::IDENT}::)* #{patterns::IDENT} /ox)
kind = :class
else
next
end
end
elsif state == :undef_expected
state = :undef_comma_expected
if match = scan(/#{patterns::METHOD_NAME_EX}/o)
@ -307,6 +350,18 @@ module Scanners
next
end
elsif state == :alias_expected
match = scan(unicode ? /(#{patterns::METHOD_NAME_OR_SYMBOL})([ \t]+)(#{patterns::METHOD_NAME_OR_SYMBOL})/uo :
/(#{patterns::METHOD_NAME_OR_SYMBOL})([ \t]+)(#{patterns::METHOD_NAME_OR_SYMBOL})/o)
if match
tokens << [self[1], (self[1][0] == ?: ? :symbol : :method)]
tokens << [self[2], :space]
tokens << [self[3], (self[3][0] == ?: ? :symbol : :method)]
end
state = :initial
next
elsif state == :undef_comma_expected
if match = scan(/,/)
kind = :operator
@ -316,25 +371,15 @@ module Scanners
next
end
elsif state == :module_expected
if match = scan(/<</)
kind = :operator
else
state = :initial
if match = scan(/ (?:#{patterns::IDENT}::)* #{patterns::IDENT} /ox)
kind = :class
else
next
end
end
end
# }}}
value_expected = value_expected == :set
last_token_dot = last_token_dot == :set
if $DEBUG and not kind
unless kind == :error
value_expected = value_expected == :set
last_token_dot = last_token_dot == :set
end
if $CODERAY_DEBUG and not kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens, state
end

View File

@ -1,3 +1,4 @@
# encoding: utf-8
module CodeRay
module Scanners
@ -14,19 +15,14 @@ module Scanners
DEF_KEYWORDS = %w[ def ]
UNDEF_KEYWORDS = %w[ undef ]
ALIAS_KEYWORDS = %w[ alias ]
MODULE_KEYWORDS = %w[class module]
DEF_NEW_STATE = WordList.new(:initial).
add(DEF_KEYWORDS, :def_expected).
add(UNDEF_KEYWORDS, :undef_expected).
add(ALIAS_KEYWORDS, :alias_expected).
add(MODULE_KEYWORDS, :module_expected)
IDENTS_ALLOWING_REGEXP = %w[
and or not while until unless if then elsif when sub sub! gsub gsub!
scan slice slice! split
]
REGEXP_ALLOWED = WordList.new(false).
add(IDENTS_ALLOWING_REGEXP, :set)
PREDEFINED_CONSTANTS = %w[
nil true false self
DATA ARGV ARGF __FILE__ __LINE__
@ -36,24 +32,25 @@ module Scanners
add(RESERVED_WORDS, :reserved).
add(PREDEFINED_CONSTANTS, :pre_constant)
IDENT = /[a-z_][\w_]*/i
IDENT = 'ä'[/[[:alpha:]]/] == 'ä' ? /[[:alpha:]_][[:alnum:]_]*/ : /[^\W\d]\w*/
METHOD_NAME = / #{IDENT} [?!]? /ox
METHOD_NAME_OPERATOR = /
\*\*? # multiplication and power
| [-+]@? # plus, minus
| [\/%&|^`~] # division, modulo or format strings, &and, |or, ^xor, `system`, tilde
| [-+~]@? # plus, minus, tilde with and without at sign
| [\/%&|^`] # division, modulo or format strings, and, or, xor, system
| \[\]=? # array getter and setter
| << | >> # append or shift left, shift right
| <=?>? | >=? # comparison, rocket operator
| ===? # simple equality and case equality
| ===? | =~ # simple equality, case equality, match
| ![~=@]? # negation with and without at sign, not-equal and not-match
/ox
METHOD_NAME_EX = / #{IDENT} (?:[?!]|=(?!>))? | #{METHOD_NAME_OPERATOR} /ox
INSTANCE_VARIABLE = / @ #{IDENT} /ox
CLASS_VARIABLE = / @@ #{IDENT} /ox
OBJECT_VARIABLE = / @@? #{IDENT} /ox
GLOBAL_VARIABLE = / \$ (?: #{IDENT} | [1-9]\d* | 0\w* | [~&+`'=\/,;_.<>!@$?*":\\] | -[a-zA-Z_0-9] ) /ox
PREFIX_VARIABLE = / #{GLOBAL_VARIABLE} |#{OBJECT_VARIABLE} /ox
PREFIX_VARIABLE = / #{GLOBAL_VARIABLE} | #{OBJECT_VARIABLE} /ox
VARIABLE = / @?@? #{IDENT} | #{GLOBAL_VARIABLE} /ox
QUOTE_TO_TYPE = {
@ -63,7 +60,7 @@ module Scanners
QUOTE_TO_TYPE.default = :string
REGEXP_MODIFIERS = /[mixounse]*/
REGEXP_SYMBOLS = /[|?*+?(){}\[\].^$]/
REGEXP_SYMBOLS = /[|?*+(){}\[\].^$]/
DECIMAL = /\d+(?:_\d+)*/
OCTAL = /0_?[0-7]+(?:_[0-7]+)*/
@ -73,7 +70,7 @@ module Scanners
EXPONENT = / [eE] [+-]? #{DECIMAL} /ox
FLOAT_SUFFIX = / #{EXPONENT} | \. #{DECIMAL} #{EXPONENT}? /ox
FLOAT_OR_INT = / #{DECIMAL} (?: #{FLOAT_SUFFIX} () )? /ox
NUMERIC = / [-+]? (?: (?=0) (?: #{OCTAL} | #{HEXADECIMAL} | #{BINARY} ) | #{FLOAT_OR_INT} ) /ox
NUMERIC = / (?: (?=0) (?: #{OCTAL} | #{HEXADECIMAL} | #{BINARY} ) | #{FLOAT_OR_INT} ) /ox
SYMBOL = /
:
@ -83,26 +80,32 @@ module Scanners
| ['"]
)
/ox
METHOD_NAME_OR_SYMBOL = / #{METHOD_NAME_EX} | #{SYMBOL} /ox
# TODO investigste \M, \c and \C escape sequences
# (?: M-\\C-|C-\\M-|M-\\c|c\\M-|c|C-|M-)? (?: \\ (?: [0-7]{3} | x[0-9A-Fa-f]{2} | . ) )
# assert_equal(225, ?\M-a)
# assert_equal(129, ?\M-\C-a)
ESCAPE = /
SIMPLE_ESCAPE = /
[abefnrstv]
| M-\\C-|C-\\M-|M-\\c|c\\M-|c|C-|M-
| [0-7]{1,3}
| x[0-9A-Fa-f]{1,2}
| .
| .?
/mx
CONTROL_META_ESCAPE = /
(?: M-|C-|c )
(?: \\ (?: M-|C-|c ) )*
(?: [^\\] | \\ #{SIMPLE_ESCAPE} )?
/mox
ESCAPE = /
#{CONTROL_META_ESCAPE} | #{SIMPLE_ESCAPE}
/mox
CHARACTER = /
\?
(?:
[^\s\\]
| \\ #{ESCAPE}
)
/mx
/mox
# NOTE: This is not completely correct, but
# nobody needs heredoc delimiters ending with \n.
@ -129,25 +132,29 @@ module Scanners
/mx
# Checks for a valid value to follow. This enables
# fancy_allowed in method calls.
# value_expected in method calls without parentheses.
VALUE_FOLLOWS = /
\s+
(?>[ \t\f\v]+)
(?:
[%\/][^\s=]
|
<<-?\S
|
#{CHARACTER}
| <<-?\S
| [-+] \d
| #{CHARACTER}
)
/x
KEYWORDS_EXPECTING_VALUE = WordList.new.add(%w[
and end in or unless begin
defined? ensure redo super until
break do next rescue then
when case else for retry
while elsif if not return
yield
])
RUBYDOC_OR_DATA = / #{RUBYDOC} | #{DATA} /xo
RDOC_DATA_START = / ^=begin (?!\S) | ^__END__$ /x
# FIXME: \s and = are only a workaround, they are still allowed
# as delimiters.
FANCY_START_SAVE = / % ( [qQwWxsr] | (?![a-zA-Z0-9\s=]) ) ([^a-zA-Z0-9]) /mx
FANCY_START_CORRECT = / % ( [qQwWxsr] | (?![a-zA-Z0-9]) ) ([^a-zA-Z0-9]) /mx
FancyStringType = {
@ -170,17 +177,18 @@ module Scanners
{ }
] ]
CLOSING_PAREN.values.each { |o| o.freeze } # debug, if I try to change it with <<
CLOSING_PAREN.each { |k,v| k.freeze; v.freeze } # debug, if I try to change it with <<
OPENING_PAREN = CLOSING_PAREN.invert
STRING_PATTERN = Hash.new { |h, k|
STRING_PATTERN = Hash.new do |h, k|
delim, interpreted = *k
delim_pattern = Regexp.escape(delim.dup)
delim_pattern = Regexp.escape(delim.dup) # dup: workaround for old Ruby
if closing_paren = CLOSING_PAREN[delim]
delim_pattern = delim_pattern[0..-1] if defined? JRUBY_VERSION # JRuby fix
delim_pattern << Regexp.escape(closing_paren)
end
delim_pattern << '\\\\' unless delim == '\\'
special_escapes =
case interpreted
when :regexp_symbols
@ -188,18 +196,18 @@ module Scanners
when :words
'| \s'
end
h[k] =
if interpreted and not delim == '#'
/ (?= [#{delim_pattern}\\] | \# [{$@] #{special_escapes} ) /mx
/ (?= [#{delim_pattern}] | \# [{$@] #{special_escapes} ) /mx
else
/ (?= [#{delim_pattern}\\] #{special_escapes} ) /mx
/ (?= [#{delim_pattern}] #{special_escapes} ) /mx
end
}
end
HEREDOC_PATTERN = Hash.new { |h, k|
HEREDOC_PATTERN = Hash.new do |h, k|
delim, interpreted, indented = *k
delim_pattern = Regexp.escape(delim.dup)
delim_pattern = Regexp.escape(delim.dup) # dup: workaround for old Ruby
delim_pattern = / \n #{ '(?>[\ \t]*)' if indented } #{ Regexp.new delim_pattern } $ /x
h[k] =
if interpreted
@ -207,12 +215,12 @@ module Scanners
else
/ (?= #{delim_pattern}() | \\ ) /mx
end
}
end
def initialize kind, interpreted, delim, heredoc = false
if heredoc
pattern = HEREDOC_PATTERN[ [delim, interpreted, heredoc == :indented] ]
delim = nil
delim = nil
else
pattern = STRING_PATTERN[ [delim, interpreted] ]
if paren = CLOSING_PAREN[delim]

View File

@ -5,8 +5,11 @@ module CodeRay
# Thanks to murphy for putting CodeRay into public.
class Scheme < Scanner
# TODO: function defs
# TODO: built-in functions
register_for :scheme
file_extension :scm
file_extension 'scm'
CORE_FORMS = %w[
lambda let let* letrec syntax-case define-syntax let-syntax
@ -120,7 +123,7 @@ module CodeRay
end
match ||= matched
if $DEBUG and not kind
if $CODERAY_DEBUG and not kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens
end

View File

@ -0,0 +1,162 @@
module CodeRay module Scanners
# by Josh Goebel
class SQL < Scanner
register_for :sql
RESERVED_WORDS = %w(
create database table index trigger drop primary key set select
insert update delete replace into
on from values before and or if exists case when
then else as group order by avg where
join inner outer union engine not
like end using collate show columns begin
)
PREDEFINED_TYPES = %w(
char varchar enum binary text tinytext mediumtext
longtext blob tinyblob mediumblob longblob timestamp
date time datetime year double decimal float int
integer tinyint mediumint bigint smallint unsigned bit
bool boolean hex bin oct
)
PREDEFINED_FUNCTIONS = %w( sum cast abs pi count min max avg )
DIRECTIVES = %w( auto_increment unique default charset )
PREDEFINED_CONSTANTS = %w( null true false )
IDENT_KIND = CaseIgnoringWordList.new(:ident).
add(RESERVED_WORDS, :reserved).
add(PREDEFINED_TYPES, :pre_type).
add(PREDEFINED_CONSTANTS, :pre_constant).
add(PREDEFINED_FUNCTIONS, :predefined).
add(DIRECTIVES, :directive)
ESCAPE = / [rbfntv\n\\\/'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} | . /mx
UNICODE_ESCAPE = / u[a-fA-F0-9]{4} | U[a-fA-F0-9]{8} /x
STRING_PREFIXES = /[xnb]|_\w+/i
def scan_tokens tokens, options
state = :initial
string_type = nil
string_content = ''
until eos?
kind = nil
match = nil
if state == :initial
if scan(/ \s+ | \\\n /x)
kind = :space
elsif scan(/^(?:--\s?|#).*/)
kind = :comment
elsif scan(%r! /\* (?: .*? \*/ | .* ) !mx)
kind = :comment
elsif scan(/ [-+*\/=<>;,!&^|()\[\]{}~%] | \.(?!\d) /x)
kind = :operator
elsif scan(/(#{STRING_PREFIXES})?([`"'])/o)
prefix = self[1]
string_type = self[2]
tokens << [:open, :string]
tokens << [prefix, :modifier] if prefix
match = string_type
state = :string
kind = :delimiter
elsif match = scan(/ @? [A-Za-z_][A-Za-z_0-9]* /x)
kind = match[0] == ?@ ? :variable : IDENT_KIND[match.downcase]
elsif scan(/0[xX][0-9A-Fa-f]+/)
kind = :hex
elsif scan(/0[0-7]+(?![89.eEfF])/)
kind = :oct
elsif scan(/(?>\d+)(?![.eEfF])/)
kind = :integer
elsif scan(/\d[fF]|\d*\.\d+(?:[eE][+-]?\d+)?|\d+[eE][+-]?\d+/)
kind = :float
else
getch
kind = :error
end
elsif state == :string
if match = scan(/[^\\"'`]+/)
string_content << match
next
elsif match = scan(/["'`]/)
if string_type == match
if peek(1) == string_type # doubling means escape
string_content << string_type << getch
next
end
unless string_content.empty?
tokens << [string_content, :content]
string_content = ''
end
tokens << [matched, :delimiter]
tokens << [:close, :string]
state = :initial
string_type = nil
next
else
string_content << match
end
next
elsif scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox)
unless string_content.empty?
tokens << [string_content, :content]
string_content = ''
end
kind = :char
elsif match = scan(/ \\ . /mox)
string_content << match
next
elsif scan(/ \\ | $ /x)
unless string_content.empty?
tokens << [string_content, :content]
string_content = ''
end
kind = :error
state = :initial
else
raise "else case \" reached; %p not handled." % peek(1), tokens
end
else
raise 'else-case reached', tokens
end
match ||= matched
unless kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens, state
end
raise_inspect 'Empty token', tokens unless match
tokens << [match, kind]
end
tokens
end
end
end end

View File

@ -5,13 +5,12 @@ module Scanners
# XML Scanner
#
# $Id$
#
# Currently this is the same scanner as Scanners::HTML.
class XML < HTML
register_for :xml
file_extension 'xml'
end
end

View File

@ -0,0 +1,140 @@
module CodeRay
module Scanners
# YAML Scanner
#
# Based on the YAML scanner from Syntax by Jamis Buck.
class YAML < Scanner
register_for :yaml
file_extension 'yml'
KINDS_NOT_LOC = :all
def scan_tokens tokens, options
value_expected = nil
state = :initial
key_indent = indent = 0
until eos?
kind = nil
match = nil
key_indent = nil if bol?
if match = scan(/ +[\t ]*/)
kind = :space
elsif match = scan(/\n+/)
kind = :space
state = :initial if match.index(?\n)
elsif match = scan(/#.*/)
kind = :comment
elsif bol? and case
when match = scan(/---|\.\.\./)
tokens << [:open, :head]
tokens << [match, :head]
tokens << [:close, :head]
next
when match = scan(/%.*/)
tokens << [match, :doctype]
next
end
elsif state == :value and case
when !check(/(?:"[^"]*")(?=: |:$)/) && scan(/"/)
tokens << [:open, :string]
tokens << [matched, :delimiter]
tokens << [matched, :content] if scan(/ [^"\\]* (?: \\. [^"\\]* )* /mx)
tokens << [matched, :delimiter] if scan(/"/)
tokens << [:close, :string]
next
when match = scan(/[|>][-+]?/)
tokens << [:open, :string]
tokens << [match, :delimiter]
string_indent = key_indent || column(pos - match.size - 1)
tokens << [matched, :content] if scan(/(?:\n+ {#{string_indent + 1}}.*)+/)
tokens << [:close, :string]
next
when match = scan(/(?![!"*&]).+?(?=$|\s+#)/)
tokens << [match, :string]
string_indent = key_indent || column(pos - match.size - 1)
tokens << [matched, :string] if scan(/(?:\n+ {#{string_indent + 1}}.*)+/)
next
end
elsif case
when match = scan(/[-:](?= |$)/)
state = :value if state == :colon && (match == ':' || match == '-')
state = :value if state == :initial && match == '-'
kind = :operator
when match = scan(/[,{}\[\]]/)
kind = :operator
when state == :initial && match = scan(/[\w.() ]*\S(?=: |:$)/)
kind = :key
key_indent = column(pos - match.size - 1)
# tokens << [key_indent.inspect, :debug]
state = :colon
when match = scan(/(?:"[^"\n]*"|'[^'\n]*')(?=: |:$)/)
tokens << [:open, :key]
tokens << [match[0,1], :delimiter]
tokens << [match[1..-2], :content]
tokens << [match[-1,1], :delimiter]
tokens << [:close, :key]
key_indent = column(pos - match.size - 1)
# tokens << [key_indent.inspect, :debug]
state = :colon
next
when scan(/(![\w\/]+)(:([\w:]+))?/)
tokens << [self[1], :type]
if self[2]
tokens << [':', :operator]
tokens << [self[3], :class]
end
next
when scan(/&\S+/)
kind = :variable
when scan(/\*\w+/)
kind = :global_variable
when scan(/<</)
kind = :class_variable
when scan(/\d\d:\d\d:\d\d/)
kind = :oct
when scan(/\d\d\d\d-\d\d-\d\d\s\d\d:\d\d:\d\d(\.\d+)? [-+]\d\d:\d\d/)
kind = :oct
when scan(/:\w+/)
kind = :symbol
when scan(/[^:\s]+(:(?! |$)[^:\s]*)* .*/)
kind = :error
when scan(/[^:\s]+(:(?! |$)[^:\s]*)*/)
kind = :error
end
else
getch
kind = :error
end
match ||= matched
if $CODERAY_DEBUG and not kind
raise_inspect 'Error token %p in line %d' %
[[match, kind], line], tokens, state
end
raise_inspect 'Empty token', tokens, state unless match
tokens << [match, kind]
end
tokens
end
end
end
end

View File

@ -8,7 +8,7 @@ module Styles
code_background = '#f8f8f8'
numbers_background = '#def'
border_color = 'silver'
normal_color = '#100'
normal_color = '#000'
CSS_MAIN_STYLES = <<-MAIN
.CodeRay {
@ -32,6 +32,7 @@ table.CodeRay td { padding: 2px 4px; vertical-align: top }
text-align: right;
}
.CodeRay .line_numbers tt { font-weight: bold }
.CodeRay .line_numbers .highlighted { color: red }
.CodeRay .no { padding: 0px 4px }
.CodeRay .code { width: 100% }
@ -46,28 +47,32 @@ ol.CodeRay li { white-space: pre }
.af { color:#00C }
.an { color:#007 }
.at { color:#f08 }
.av { color:#700 }
.aw { color:#C00 }
.bi { color:#509; font-weight:bold }
.c { color:#666; }
.c { color:#888; }
.ch { color:#04D }
.ch .k { color:#04D }
.ch .dl { color:#039 }
.cl { color:#B06; font-weight:bold }
.cm { color:#A08; font-weight:bold }
.co { color:#036; font-weight:bold }
.cr { color:#0A0 }
.cv { color:#369 }
.de { color:#B0B; }
.df { color:#099; font-weight:bold }
.di { color:#088; font-weight:bold }
.dl { color:black }
.do { color:#970 }
.dt { color:#34b }
.ds { color:#D42; font-weight:bold }
.e { color:#666; font-weight:bold }
.en { color:#800; font-weight:bold }
.er { color:#F00; background-color:#FAA }
.ex { color:#F00; font-weight:bold }
.ex { color:#C00; font-weight:bold }
.fl { color:#60E; font-weight:bold }
.fu { color:#06B; font-weight:bold }
.gv { color:#d70; font-weight:bold }
@ -75,11 +80,13 @@ ol.CodeRay li { white-space: pre }
.i { color:#00D; font-weight:bold }
.ic { color:#B44; font-weight:bold }
.il { background: #eee }
.il .il { background: #ddd }
.il .il .il { background: #ccc }
.il .idl { font-weight: bold; color: #888 }
.il { background: #ddd; color: black }
.il .il { background: #ccc }
.il .il .il { background: #bbb }
.il .idl { background: #ddd; font-weight: bold; color: #666 }
.idl { background-color: #bbb; font-weight: bold; color: #666; }
.im { color:#f00; }
.in { color:#B2B; font-weight:bold }
.iv { color:#33B }
.la { color:#970; font-weight:bold }
@ -89,9 +96,15 @@ ol.CodeRay li { white-space: pre }
.op { }
.pc { color:#038; font-weight:bold }
.pd { color:#369; font-weight:bold }
.pp { color:#579 }
.pt { color:#339; font-weight:bold }
.r { color:#080; font-weight:bold }
.pp { color:#579; }
.ps { color:#00C; font-weight:bold }
.pt { color:#074; font-weight:bold }
.r, .kw { color:#080; font-weight:bold }
.ke { color: #808; }
.ke .dl { color: #606; }
.ke .ch { color: #80f; }
.vl { color: #088; }
.rx { background-color:#fff0ff }
.rx .k { color:#808 }
@ -99,14 +112,15 @@ ol.CodeRay li { white-space: pre }
.rx .mod { color:#C2C }
.rx .fu { color:#404; font-weight: bold }
.s { background-color:#fff0f0 }
.s .s { background-color:#ffe0e0 }
.s .s .s { background-color:#ffd0d0 }
.s .k { color:#D20 }
.s .dl { color:#710 }
.s { background-color:#fff0f0; color: #D20; }
.s .s { background-color:#ffe0e0 }
.s .s .s { background-color:#ffd0d0 }
.s .k { }
.s .ch { color: #b0b; }
.s .dl { color: #710; }
.sh { background-color:#f0fff0 }
.sh .k { color:#2B2 }
.sh { background-color:#f0fff0; color:#2B2 }
.sh .k { }
.sh .dl { color:#161 }
.sy { color:#A60 }
@ -119,6 +133,16 @@ ol.CodeRay li { white-space: pre }
.ty { color:#339; font-weight:bold }
.v { color:#036 }
.xt { color:#444 }
.ins { background: #afa; }
.del { background: #faa; }
.chg { color: #aaf; background: #007; }
.head { color: #f8f; background: #505 }
.ins .ins { color: #080; font-weight:bold }
.del .del { color: #800; font-weight:bold }
.chg .chg { color: #66f; }
.head .head { color: #f4f; }
TOKENS
end

View File

@ -84,6 +84,9 @@ ol.CodeRay li { white-space: pre; }
.pp { color:#579; }
.pt { color:#66f; font-weight:bold; }
.r { color:#5de; font-weight:bold; }
.r, .kw { color:#5de; font-weight:bold }
.ke { color: #808; }
.rx { background-color:#221133; }
.rx .k { color:#f8f; }
@ -111,6 +114,16 @@ ol.CodeRay li { white-space: pre; }
.ty { color:#339; font-weight:bold; }
.v { color:#036; }
.xt { color:#444; }
.ins { background: #afa; }
.del { background: #faa; }
.chg { color: #aaf; background: #007; }
.head { color: #f8f; background: #505 }
.ins .ins { color: #080; font-weight:bold }
.del .del { color: #800; font-weight:bold }
.chg .chg { color: #66f; }
.head .head { color: #f4f; }
TOKENS
end

View File

@ -4,6 +4,7 @@ module CodeRay
h[k] = k.to_s
end
ClassOfKind.update with = {
:annotation => 'at',
:attribute_name => 'an',
:attribute_name_fat => 'af',
:attribute_value => 'av',
@ -14,12 +15,15 @@ module CodeRay
:class_variable => 'cv',
:color => 'cr',
:comment => 'c',
:complex => 'cm',
:constant => 'co',
:content => 'k',
:decorator => 'de',
:definition => 'df',
:delimiter => 'dl',
:directive => 'di',
:doc => 'do',
:doctype => 'dt',
:doc_string => 'ds',
:entity => 'en',
:error => 'er',
@ -29,12 +33,16 @@ module CodeRay
:function => 'fu',
:global_variable => 'gv',
:hex => 'hx',
:imaginary => 'cm',
:important => 'im',
:include => 'ic',
:inline => 'il',
:inline_delimiter => 'idl',
:instance_variable => 'iv',
:integer => 'i',
:interpreted => 'in',
:keyword => 'kw',
:key => 'ke',
:label => 'la',
:local_variable => 'lv',
:modifier => 'mod',
@ -44,6 +52,7 @@ module CodeRay
:pre_type => 'pt',
:predefined => 'pd',
:preprocessor => 'pp',
:pseudo_class => 'ps',
:regexp => 'rx',
:reserved => 'r',
:shell => 'sh',
@ -54,7 +63,13 @@ module CodeRay
:tag_special => 'ts',
:type => 'ty',
:variable => 'v',
:value => 'vl',
:xml_text => 'xt',
:insert => 'ins',
:delete => 'del',
:change => 'chg',
:head => 'head',
:ident => :NO_HIGHLIGHT, # 'id'
#:operator => 'op',
@ -62,7 +77,7 @@ module CodeRay
:space => :NO_HIGHLIGHT, # 'sp'
:plain => :NO_HIGHLIGHT,
}
ClassOfKind[:procedure] = ClassOfKind[:method] = ClassOfKind[:function]
ClassOfKind[:method] = ClassOfKind[:function]
ClassOfKind[:open] = ClassOfKind[:close] = ClassOfKind[:delimiter]
ClassOfKind[:nesting_delimiter] = ClassOfKind[:delimiter]
ClassOfKind[:escape] = ClassOfKind[:delimiter]

View File

@ -14,7 +14,7 @@ module CodeRay
#
# [:comment, '# It looks like this']
# [:float, '3.1415926']
# [:error, 'äöü']
# [:error, '$^']
#
# Some scanners also yield some kind of sub-tokens, represented by special
# token texts, namely :open and :close .
@ -46,47 +46,10 @@ module CodeRay
#
# Tokens' subclass TokenStream allows streaming to save memory.
class Tokens < Array
class << self
# Convert the token to a string.
#
# This format is used by Encoders.Tokens.
# It can be reverted using read_token.
def write_token text, type
if text.is_a? String
"#{type}\t#{escape(text)}\n"
else
":#{text}\t#{type}\t\n"
end
end
# Read a token from the string.
#
# Inversion of write_token.
#
# TODO Test this!
def read_token token
type, text = token.split("\t", 2)
if type[0] == ?:
[text.to_sym, type[1..-1].to_sym]
else
[type.to_sym, unescape(text)]
end
end
# Escapes a string for use in write_token.
def escape text
text.gsub(/[\n\\]/, '\\\\\&')
end
# Unescapes a string created by escape.
def unescape text
text.gsub(/\\[\n\\]/) { |m| m[1,1] }
end
end
# The Scanner instance that created the tokens.
attr_accessor :scanner
# Whether the object is a TokenStream.
#
# Returns false.
@ -146,7 +109,6 @@ module CodeRay
encode :text, options
end
# Redirects unknown methods to encoder calls.
#
# For example, if you call +tokens.html+, the HTML encoder
@ -167,7 +129,6 @@ module CodeRay
# for example, consecutive //-comment lines could already be
# joined in one comment token by the Scanner.
def optimize
print ' Tokens#optimize: before: %d - ' % size if $DEBUG
last_kind = last_text = nil
new = self.class.new
for text, kind in self
@ -186,8 +147,6 @@ module CodeRay
end
end
new << [last_text, last_kind] if last_kind
print 'after: %d (%d saved = %2.0f%%)' %
[new.size, size - new.size, 1.0 - (new.size.to_f / size)] if $DEBUG
new
end
@ -200,25 +159,29 @@ module CodeRay
#
# TODO: Test this!
def fix
tokens = self.class.new
# Check token nesting using a stack of kinds.
opened = []
for token, kind in self
if token == :open
opened.push kind
elsif token == :close
for type, kind in self
case type
when :open
opened.push [:close, kind]
when :begin_line
opened.push [:end_line, kind]
when :close, :end_line
expected = opened.pop
if kind != expected
if [type, kind] != expected
# Unexpected :close; decide what to do based on the kind:
# - token was opened earlier: also close tokens in between
# - token was never opened: delete the :close (skip with next)
# - token was never opened: delete the :close (just skip it)
next unless opened.rindex expected
tokens << [:close, kind] until (kind = opened.pop) == expected
# - token was opened earlier: also close tokens in between
tokens << token until (token = opened.pop) == expected
end
end
tokens << [token, kind]
tokens << [type, kind]
end
# Close remaining opened tokens
tokens << [:close, kind] while kind = opened.pop
tokens << token while token = opened.pop
tokens
end
@ -226,6 +189,8 @@ module CodeRay
replace fix
end
# TODO: Scanner#split_into_lines
#
# Makes sure that:
# - newlines are single tokens
# (which means all other token are single-line)
@ -353,7 +318,7 @@ module CodeRay
#
# Returns self.
def << token
@callback.call token
@callback.call(*token)
@size += 1
self
end
@ -376,8 +341,48 @@ module CodeRay
end
# Token name abbreviations
require 'coderay/token_classes'
end
if $0 == __FILE__
$VERBOSE = true
$: << File.join(File.dirname(__FILE__), '..')
eval DATA.read, nil, $0, __LINE__ + 4
end
__END__
require 'test/unit'
class TokensTest < Test::Unit::TestCase
def test_creation
assert CodeRay::Tokens < Array
tokens = nil
assert_nothing_raised do
tokens = CodeRay::Tokens.new
end
assert_kind_of Array, tokens
end
def test_adding_tokens
tokens = CodeRay::Tokens.new
assert_nothing_raised do
tokens << ['string', :type]
tokens << ['()', :operator]
end
assert_equal tokens.size, 2
end
def test_dump_undump
tokens = CodeRay::Tokens.new
assert_nothing_raised do
tokens << ['string', :type]
tokens << ['()', :operator]
end
tokens2 = nil
assert_nothing_raised do
tokens2 = tokens.dump.undump
end
assert_equal tokens, tokens2
end
end