java_regex 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/java_regex/exceptions.rb +5 -0
- data/lib/java_regex/translator.rb +69 -0
- data/lib/java_regex.rb +19 -0
- metadata +49 -0
@@ -0,0 +1,69 @@
|
|
1
|
+
# encoding=utf-8
|
2
|
+
class JavaRegex::Translator
|
3
|
+
def self.translate(regex)
|
4
|
+
regex = String.new(regex)
|
5
|
+
characters(regex)
|
6
|
+
character_classes_or_character_sets(regex)
|
7
|
+
word_boundaries(regex)
|
8
|
+
modifiers(regex)
|
9
|
+
unicode_characters!(regex)
|
10
|
+
posix_bracket_expressions!(regex)
|
11
|
+
regex.sub!(/\A(.*)\z/, '\A\1\z')
|
12
|
+
return regex
|
13
|
+
end
|
14
|
+
|
15
|
+
def self.characters(regex)
|
16
|
+
meta_char_start = regex.scan('\Q')
|
17
|
+
meta_char_end = regex.scan('\E')
|
18
|
+
control_char = regex.scan(/\\c[[:upper:]]/)
|
19
|
+
raise JavaRegexException::TranslationError,
|
20
|
+
'"\Q" and "\E" are not supported' unless
|
21
|
+
meta_char_start.empty? and
|
22
|
+
meta_char_end.empty?
|
23
|
+
raise JavaRegexException::TranslationError,
|
24
|
+
'"\cA" through "\cZ" are not supported' unless
|
25
|
+
control_char.empty?
|
26
|
+
end
|
27
|
+
|
28
|
+
def self.character_classes_or_character_sets(regex)
|
29
|
+
literal_hyphen = regex.scan(/\[\\.-.\]/)
|
30
|
+
raise JavaRegexException::TranslationError,
|
31
|
+
'Literal hyphens like [\d-z] are not supported' unless
|
32
|
+
literal_hyphen.empty?
|
33
|
+
end
|
34
|
+
|
35
|
+
def self.word_boundaries(regex)
|
36
|
+
non_ascii = regex.scan(/\\[bB][[:print:][:cntrl:]]/)
|
37
|
+
raise JavaRegexException::TranslationError,
|
38
|
+
'Non-ascii characters following "\b" or "\B" are not supported' unless
|
39
|
+
non_ascii.empty?
|
40
|
+
end
|
41
|
+
|
42
|
+
def self.modifiers(regex)
|
43
|
+
newline = regex.scan(/\\n/)
|
44
|
+
raise JavaRegexException::TranslationError,
|
45
|
+
'Newlines are currently not supported' unless
|
46
|
+
newline.empty?
|
47
|
+
end
|
48
|
+
|
49
|
+
def self.unicode_characters!(regex)
|
50
|
+
re = /\\u([[:xdigit:]]{4})/
|
51
|
+
regex.gsub!(re) { |m| m.gsub!(/\A.*\z/, [Integer("0x#{$1}")].pack('U*')) }
|
52
|
+
end
|
53
|
+
|
54
|
+
def self.posix_bracket_expressions!(regex)
|
55
|
+
regex.gsub!('\p{Lower}', '[[:lower:]]')
|
56
|
+
regex.gsub!('\p{Upper}', '[[:upper:]]')
|
57
|
+
regex.gsub!('\p{Alpha}', '[[:alpha:]]')
|
58
|
+
regex.gsub!('\p{Digit}', '[[:digit:]]')
|
59
|
+
regex.gsub!('\p{Alnum}', '[[:alnum:]]')
|
60
|
+
regex.gsub!('\p{Punct}', '[[:punct:]]')
|
61
|
+
regex.gsub!('\p{Graph}', '[[:graph:]]')
|
62
|
+
regex.gsub!('\p{Print}', '[[:print:]]')
|
63
|
+
regex.gsub!('\p{Blank}', '[[:blank:]]')
|
64
|
+
regex.gsub!('\p{Cntrl}', '[[:cntrl:]]')
|
65
|
+
regex.gsub!('\p{Space}', '[[:space:]]')
|
66
|
+
regex.gsub!('\p{XDigit}', '[[:xdigit:]]')
|
67
|
+
regex.gsub!('\p{ASCII}', '[[:print:][:cntrl:]]')
|
68
|
+
end
|
69
|
+
end
|
data/lib/java_regex.rb
ADDED
@@ -0,0 +1,19 @@
|
|
1
|
+
# encoding=utf-8
|
2
|
+
class JavaRegex
|
3
|
+
attr_accessor :regex
|
4
|
+
|
5
|
+
def initialize(regex)
|
6
|
+
@regex = regex
|
7
|
+
end
|
8
|
+
|
9
|
+
def to_ruby
|
10
|
+
Translator.translate(@regex)
|
11
|
+
end
|
12
|
+
|
13
|
+
def to_ruby_regex
|
14
|
+
Regexp.new(to_ruby())
|
15
|
+
end
|
16
|
+
end
|
17
|
+
|
18
|
+
require 'java_regex/exceptions'
|
19
|
+
require 'java_regex/translator'
|
metadata
ADDED
@@ -0,0 +1,49 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: java_regex
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Dean Morin
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-03-24 00:00:00.000000000 Z
|
13
|
+
dependencies: []
|
14
|
+
description: ! " For the most common cases, either converts to the Ruby equivalent,
|
15
|
+
or\n throws an exception if conversion is not supported.\n"
|
16
|
+
email: morin.dean@gmail.com
|
17
|
+
executables: []
|
18
|
+
extensions: []
|
19
|
+
extra_rdoc_files: []
|
20
|
+
files:
|
21
|
+
- lib/java_regex.rb
|
22
|
+
- lib/java_regex/translator.rb
|
23
|
+
- lib/java_regex/exceptions.rb
|
24
|
+
homepage: http://github.com/deanmorin/java_regex
|
25
|
+
licenses:
|
26
|
+
- MIT
|
27
|
+
post_install_message:
|
28
|
+
rdoc_options: []
|
29
|
+
require_paths:
|
30
|
+
- lib
|
31
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
32
|
+
none: false
|
33
|
+
requirements:
|
34
|
+
- - ! '>='
|
35
|
+
- !ruby/object:Gem::Version
|
36
|
+
version: '0'
|
37
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
38
|
+
none: false
|
39
|
+
requirements:
|
40
|
+
- - ! '>='
|
41
|
+
- !ruby/object:Gem::Version
|
42
|
+
version: '0'
|
43
|
+
requirements: []
|
44
|
+
rubyforge_project:
|
45
|
+
rubygems_version: 1.8.23
|
46
|
+
signing_key:
|
47
|
+
specification_version: 3
|
48
|
+
summary: Converts Java regexes to Ruby regexes
|
49
|
+
test_files: []
|