From 84b8431608174e74a4c0d2394eb330a6621bc74b Mon Sep 17 00:00:00 2001 From: no author Date: Mon, 26 Sep 2005 02:58:54 +0000 Subject: New Repository, initial import --- lib/coderay/helpers/filetype.rb | 145 ++++++++++++++++++++++++++++++++++ lib/coderay/helpers/gzip_simple.rb | 123 ++++++++++++++++++++++++++++ lib/coderay/helpers/scanner_helper.rb | 63 +++++++++++++++ 3 files changed, 331 insertions(+) create mode 100644 lib/coderay/helpers/filetype.rb create mode 100644 lib/coderay/helpers/gzip_simple.rb create mode 100644 lib/coderay/helpers/scanner_helper.rb (limited to 'lib/coderay/helpers') diff --git a/lib/coderay/helpers/filetype.rb b/lib/coderay/helpers/filetype.rb new file mode 100644 index 0000000..7f34c35 --- /dev/null +++ b/lib/coderay/helpers/filetype.rb @@ -0,0 +1,145 @@ +# =FileType +# +# A simple filetype recognizer +# +# Author: murphy (mail to murphy cYcnus de) +# +# Version: 0.1 (2005.september.1) +# +# ==Documentation +# +# TODO +# +module FileType + + UnknownFileType = Class.new Exception + + class << self + + def [] filename, read_shebang = false + name = File.basename filename + ext = File.extname name + ext.sub!(/^\./, '') # delete the leading dot + + type = + TypeFromExt[ext] || + TypeFromExt[ext.downcase] || + TypeFromName[name] || + TypeFromName[name.downcase] + type ||= shebang(filename) if read_shebang + + type + end + + def shebang filename + begin + File.open filename, 'r' do |f| + first_line = f.gets + first_line[TypeFromShebang] + end + rescue IOError + nil + end + end + + # This works like Hash#fetch. + def fetch filename, default = nil, read_shebang = false + if default and block_given? + warn 'block supersedes default value argument' + end + + unless type = self[filename, read_shebang] + return yield if block_given? + return default if default + raise UnknownFileType, 'Could not determine type of %p.' % filename + end + type + end + + end + + TypeFromExt = { + 'rb' => :ruby, + 'rbw' => :ruby, + 'cpp' => :cpp, + 'c' => :c, + 'h' => :c, + 'xml' => :xml, + 'htm' => :html, + 'html' => :html, + } + + TypeFromShebang = /\b(?:ruby|perl|python|sh)\b/ + + TypeFromName = { + 'Rakefile' => :ruby, + 'Rantfile' => :ruby, + } + +end + +if $0 == __FILE__ + $VERBOSE = true + eval DATA.read, nil, $0, __LINE__+4 +end + +__END__ + +require 'test/unit' + +class TC_FileType < Test::Unit::TestCase + + def test_fetch + assert_raise FileType::UnknownFileType do + FileType.fetch '' + end + + assert_throws :not_found do + FileType.fetch '.' do + throw :not_found + end + end + + assert_equal :default, FileType.fetch('c', :default) + + stderr, fake_stderr = $stderr, Object.new + $err = '' + def fake_stderr.write x + $err << x + end + $stderr = fake_stderr + FileType.fetch('c', :default) { } + assert_equal "block supersedes default value argument\n", $err + $stderr = stderr + end + + def test_ruby + assert_equal :ruby, FileType['test.rb'] + 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'] + assert_not_equal :ruby, FileType['test_rb'] + assert_not_equal :ruby, FileType['Makefile'] + assert_not_equal :ruby, FileType['set.rb/set'] + assert_not_equal :ruby, FileType['~/projects/blabla/rb'] + end + + def test_c + assert_equal :c, FileType['test.c'] + assert_equal :c, FileType['C:\\Program Files\\x\\y\\c\\test.h'] + assert_not_equal :c, FileType['test_c'] + assert_not_equal :c, FileType['Makefile'] + assert_not_equal :c, FileType['set.h/set'] + assert_not_equal :c, FileType['~/projects/blabla/c'] + end + + def test_shebang + dir = './test' + if File.directory? dir + Dir.chdir dir do + assert_equal :c, FileType['test.c'] + end + end + end + +end diff --git a/lib/coderay/helpers/gzip_simple.rb b/lib/coderay/helpers/gzip_simple.rb new file mode 100644 index 0000000..02d1ffd --- /dev/null +++ b/lib/coderay/helpers/gzip_simple.rb @@ -0,0 +1,123 @@ +# =GZip Simple +# +# A simplified interface to the gzip library +zlib+ (from the Ruby Standard Library.) +# +# Author: murphy (mail to murphy cYcnus de) +# +# Version: 0.2 (2005.may.28) +# +# ==Documentation +# +# See +GZip+ module and the +String+ extensions. +# +module GZip + + require 'zlib' + + # The default zipping level. 7 zips good and fast. + DEFAULT_GZIP_LEVEL = 7 + + # Unzips the given string +s+. + # + # Example: + # require 'gzip_simple' + # print GZip.gunzip(File.read('adresses.gz')) + # + def GZip.gunzip s + Zlib::Inflate.inflate s + end + + # Zips the given string +s+. + # + # Example: + # require 'gzip_simple' + # File.open('adresses.gz', 'w') do |file + # file.write GZip.gzip('Mum: 0123 456 789', 9) + # end + # + # If you provide a +level+, you can control how strong + # the string is compressed: + # - 0: no compression, only convert to gzip format + # - 1: compress fast + # - 7: compress more, but still fast (default) + # - 8: compress more, slower + # - 9: compress best, very slow + def GZip.gzip s, level = DEFAULT_GZIP_LEVEL + Zlib::Deflate.new(level).deflate s, Zlib::FINISH + end +end + +# String extensions to use the GZip module. +# +# The methods gzip and gunzip provide an even more simple +# interface to the ZLib: +# +# # create a big string +# x = 'a' * 1000 +# +# # zip it +# x_gz = x.gzip +# +# # test the result +# puts 'Zipped %d bytes to %d bytes.' % [x.size, x_gz.size] +# #-> Zipped 1000 bytes to 19 bytes. +# +# # unzipping works +# p x_gz.gunzip == x #-> true +class String + # Returns the string, unzipped. + # See GZip.gunzip + def gunzip + GZip.gunzip self + end + # Replaces the string with its unzipped value. + # See GZip.gunzip + def gunzip! + replace gunzip + end + + # Returns the string, zipped. + # +level+ is the gzip compression level, see GZip.gzip. + def gzip level = GZip::DEFAULT_GZIP_LEVEL + GZip.gzip self, level + end + # Replaces the string with its zipped value. + # See GZip.gzip. + def gzip!(*args) + replace gzip(*args) + end +end + +if $0 == __FILE__ + eval DATA.read, nil, $0, __LINE__+4 +end + +__END__ +#CODE + +# Testing / Benchmark +x = 'a' * 1000 +x_gz = x.gzip +puts 'Zipped %d bytes to %d bytes.' % [x.size, x_gz.size] #-> Zipped 1000 bytes to 19 bytes. +p x_gz.gunzip == x #-> true + +require 'benchmark' + +INFO = 'packed to %0.3f%%' # :nodoc: + +x = Array.new(100000) { rand(255).chr + 'aaaaaaaaa' + rand(255).chr }.join +Benchmark.bm(10) do |bm| + for level in 0..9 + bm.report "zip #{level}" do + $x = x.gzip level + end + puts INFO % [100.0 * $x.size / x.size] + end + bm.report 'zip' do + $x = x.gzip + end + puts INFO % [100.0 * $x.size / x.size] + bm.report 'unzip' do + $x.gunzip + end +end diff --git a/lib/coderay/helpers/scanner_helper.rb b/lib/coderay/helpers/scanner_helper.rb new file mode 100644 index 0000000..a2e14bb --- /dev/null +++ b/lib/coderay/helpers/scanner_helper.rb @@ -0,0 +1,63 @@ +module CodeRay +module Scanners + + class Scanner + + # A WordList is a Hash with some additional features. + # It is intended to be used for keyword recognition. + class WordList < Hash + + def initialize default = false, case_mode = :case_match + @case_ignore = + case case_mode + when :case_match then false + when :case_ignore then true + else + raise ArgumentError, + "#{self.class.name}.new: second argument must be :case_ignore or :case_match, but #{case_mode} was given." + end + + if @case_ignore + super() do |h, k| + h[k] = h.fetch k.downcase, default + end + else + super default + end + end + + def include? word + self[word] if @case_ignore + has_key? word + end + + def add words, kind = true + words.each do |word| + self[mind_case(word)] = kind + end + self + end + + alias words keys + + def case_ignore? + @case_mode + end + + private + def mind_case word + if @case_ignore + word.downcase + else + word.dup + end + end + + end + + end + +end +end + +# vim:sw=2:ts=2:et:tw=78 -- cgit v1.2.1