cmess 0.1.2.288 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- data/ChangeLog +4 -0
- data/README +10 -1
- data/lib/cmess/cli.rb +7 -7
- data/lib/cmess/guess_encoding/automatic.rb +8 -6
- data/lib/cmess/version.rb +3 -3
- metadata +43 -45
data/ChangeLog
CHANGED
data/README
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
== VERSION
|
|
4
4
|
|
|
5
|
-
This documentation refers to cmess version 0.
|
|
5
|
+
This documentation refers to cmess version 0.2.0
|
|
6
6
|
|
|
7
7
|
|
|
8
8
|
== DESCRIPTION
|
|
@@ -24,6 +24,15 @@ decode_entities:: Decode HTML entities in a string.
|
|
|
24
24
|
TODO: well, more of the description... ;-)
|
|
25
25
|
|
|
26
26
|
|
|
27
|
+
== LINKS
|
|
28
|
+
|
|
29
|
+
<b></b>
|
|
30
|
+
Documentation:: <http://prometheus.rubyforge.org/cmess>
|
|
31
|
+
Source code (old):: <http://prometheus.rubyforge.org/svn/scratch/cmess>
|
|
32
|
+
Source code:: <http://github.com/blackwinter/cmess>
|
|
33
|
+
Rubyforge project:: <http://rubyforge.org/projects/prometheus>
|
|
34
|
+
|
|
35
|
+
|
|
27
36
|
== AUTHORS
|
|
28
37
|
|
|
29
38
|
* Jens Wille <mailto:jens.wille@uni-koeln.de>
|
data/lib/cmess/cli.rb
CHANGED
|
@@ -3,9 +3,9 @@
|
|
|
3
3
|
# #
|
|
4
4
|
# A component of cmess, the encoding tool-box. #
|
|
5
5
|
# #
|
|
6
|
-
# Copyright (C) 2007 University of Cologne,
|
|
7
|
-
#
|
|
8
|
-
#
|
|
6
|
+
# Copyright (C) 2007-2009 University of Cologne, #
|
|
7
|
+
# Albertus-Magnus-Platz, #
|
|
8
|
+
# 50932 Cologne, Germany #
|
|
9
9
|
# #
|
|
10
10
|
# Authors: #
|
|
11
11
|
# Jens Wille <jens.wille@uni-koeln.de> #
|
|
@@ -51,10 +51,10 @@ module CMess::CLI
|
|
|
51
51
|
def open_file_or_std(file, mode = 'r')
|
|
52
52
|
if file == '-'
|
|
53
53
|
case mode
|
|
54
|
-
when 'r'
|
|
55
|
-
when 'w'
|
|
56
|
-
when 'a'
|
|
57
|
-
else
|
|
54
|
+
when 'r' then STDIN
|
|
55
|
+
when 'w' then STDOUT
|
|
56
|
+
when 'a' then STDERR
|
|
57
|
+
else raise ArgumentError, "don't know how to handle mode '#{mode}'"
|
|
58
58
|
end
|
|
59
59
|
else
|
|
60
60
|
ensure_readable(file) unless mode == 'w'
|
|
@@ -1,9 +1,11 @@
|
|
|
1
|
+
# encoding: utf-8
|
|
2
|
+
|
|
1
3
|
#--
|
|
2
4
|
###############################################################################
|
|
3
5
|
# #
|
|
4
6
|
# A component of cmess, the encoding tool-box. #
|
|
5
7
|
# #
|
|
6
|
-
# Copyright (C) 2007-
|
|
8
|
+
# Copyright (C) 2007-2009 University of Cologne, #
|
|
7
9
|
# Albertus-Magnus-Platz, #
|
|
8
10
|
# 50932 Cologne, Germany #
|
|
9
11
|
# #
|
|
@@ -30,7 +32,7 @@
|
|
|
30
32
|
###############################################################################
|
|
31
33
|
#++
|
|
32
34
|
|
|
33
|
-
$KCODE = 'u'
|
|
35
|
+
$KCODE = 'u' unless RUBY_VERSION >= '1.9'
|
|
34
36
|
|
|
35
37
|
require 'yaml'
|
|
36
38
|
require 'iconv'
|
|
@@ -262,10 +264,10 @@ class CMess::GuessEncoding::Automatic
|
|
|
262
264
|
encodings UTF_16BE, UTF_16LE, UTF_16 do
|
|
263
265
|
if relative_byte_count(byte_count[0]) > 0.25
|
|
264
266
|
case first_byte
|
|
265
|
-
when 0x0
|
|
266
|
-
when 0xfe
|
|
267
|
-
when 0xff
|
|
268
|
-
else
|
|
267
|
+
when 0x0 then UTF_32
|
|
268
|
+
when 0xfe then UTF_16BE
|
|
269
|
+
when 0xff then UTF_16LE
|
|
270
|
+
else UTF_16
|
|
269
271
|
end
|
|
270
272
|
end
|
|
271
273
|
end
|
data/lib/cmess/version.rb
CHANGED
|
@@ -3,7 +3,7 @@
|
|
|
3
3
|
# #
|
|
4
4
|
# A component of cmess, the encoding tool-box. #
|
|
5
5
|
# #
|
|
6
|
-
# Copyright (C) 2007-
|
|
6
|
+
# Copyright (C) 2007-2009 University of Cologne, #
|
|
7
7
|
# Albertus-Magnus-Platz, #
|
|
8
8
|
# 50932 Cologne, Germany #
|
|
9
9
|
# #
|
|
@@ -29,8 +29,8 @@
|
|
|
29
29
|
module CMess::Version
|
|
30
30
|
|
|
31
31
|
MAJOR = 0
|
|
32
|
-
MINOR =
|
|
33
|
-
TINY =
|
|
32
|
+
MINOR = 2
|
|
33
|
+
TINY = 0
|
|
34
34
|
|
|
35
35
|
class << self
|
|
36
36
|
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: cmess
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.
|
|
4
|
+
version: 0.2.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Jens Wille
|
|
@@ -9,7 +9,7 @@ autorequire:
|
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
11
|
|
|
12
|
-
date:
|
|
12
|
+
date: 2009-05-08 00:00:00 +02:00
|
|
13
13
|
default_executable:
|
|
14
14
|
dependencies:
|
|
15
15
|
- !ruby/object:Gem::Dependency
|
|
@@ -32,13 +32,13 @@ dependencies:
|
|
|
32
32
|
- !ruby/object:Gem::Version
|
|
33
33
|
version: "0"
|
|
34
34
|
version:
|
|
35
|
-
description: "Assist with handling messed up encodings (Currently includes the
|
|
35
|
+
description: "\n Assist with handling messed up encodings (Currently includes the\n following tools: bconv, cinderella, decode_entities, guess_encoding)\n "
|
|
36
36
|
email: jens.wille@uni-koeln.de
|
|
37
37
|
executables:
|
|
38
|
+
- guess_encoding
|
|
38
39
|
- cinderella
|
|
39
40
|
- bconv
|
|
40
41
|
- decode_entities
|
|
41
|
-
- guess_encoding
|
|
42
42
|
extensions: []
|
|
43
43
|
|
|
44
44
|
extra_rdoc_files:
|
|
@@ -46,71 +46,69 @@ extra_rdoc_files:
|
|
|
46
46
|
- ChangeLog
|
|
47
47
|
- README
|
|
48
48
|
files:
|
|
49
|
-
- lib/cmess.rb
|
|
50
|
-
- lib/cmess/bconv.rb
|
|
51
|
-
- lib/cmess/version.rb
|
|
52
|
-
- lib/cmess/guess_encoding.rb
|
|
53
|
-
- lib/cmess/cli.rb
|
|
54
|
-
- lib/cmess/cinderella.rb
|
|
55
|
-
- lib/cmess/decode_entities.rb
|
|
56
49
|
- lib/cmess/guess_encoding/manual.rb
|
|
57
|
-
- lib/cmess/guess_encoding/encoding.rb
|
|
58
50
|
- lib/cmess/guess_encoding/automatic.rb
|
|
51
|
+
- lib/cmess/guess_encoding/encoding.rb
|
|
52
|
+
- lib/cmess/decode_entities.rb
|
|
53
|
+
- lib/cmess/cli.rb
|
|
54
|
+
- lib/cmess/cinderella.rb
|
|
55
|
+
- lib/cmess/bconv.rb
|
|
56
|
+
- lib/cmess/guess_encoding.rb
|
|
57
|
+
- lib/cmess/version.rb
|
|
58
|
+
- lib/cmess.rb
|
|
59
|
+
- bin/guess_encoding
|
|
59
60
|
- bin/cinderella
|
|
60
61
|
- bin/bconv
|
|
61
62
|
- bin/decode_entities
|
|
62
|
-
-
|
|
63
|
+
- Rakefile
|
|
63
64
|
- COPYING
|
|
64
|
-
- README
|
|
65
65
|
- ChangeLog
|
|
66
|
-
-
|
|
67
|
-
- example/
|
|
68
|
-
- example/cinderella/crop
|
|
69
|
-
- example/cinderella/empty6-slash.txt
|
|
70
|
-
- example/cinderella/pot
|
|
71
|
-
- example/cinderella/crop_repaired
|
|
72
|
-
- example/cinderella/empty6-slash_repaired.txt
|
|
73
|
-
- example/guess_encoding
|
|
74
|
-
- example/guess_encoding/de.utf-8.txt
|
|
66
|
+
- README
|
|
67
|
+
- example/guess_encoding/en.utf-8.txt
|
|
75
68
|
- example/guess_encoding/fr.utf-8.txt
|
|
76
69
|
- example/guess_encoding/check_results
|
|
77
|
-
- example/guess_encoding/en.utf-8.txt
|
|
78
70
|
- example/guess_encoding/it.utf-8.txt
|
|
79
|
-
-
|
|
80
|
-
-
|
|
81
|
-
-
|
|
82
|
-
-
|
|
83
|
-
-
|
|
84
|
-
-
|
|
85
|
-
- data/
|
|
86
|
-
- data/csets/unicode/latin_extended_additional.yaml
|
|
87
|
-
- data/csets/unicode/cyrillic-supplement.yaml
|
|
88
|
-
- data/csets/unicode/spacing_modifier_letters.yaml
|
|
89
|
-
- data/csets/unicode/letterlike_symbols.yaml
|
|
90
|
-
- data/csets/unicode/greek.yaml
|
|
71
|
+
- example/guess_encoding/de.utf-8.txt
|
|
72
|
+
- example/cinderella/pot
|
|
73
|
+
- example/cinderella/empty6-slash_repaired.txt
|
|
74
|
+
- example/cinderella/crop
|
|
75
|
+
- example/cinderella/empty6-slash.txt
|
|
76
|
+
- example/cinderella/crop_repaired
|
|
77
|
+
- data/chartab.yaml
|
|
91
78
|
- data/csets/unicode/latin-extended-c.yaml
|
|
92
|
-
- data/csets/unicode/
|
|
93
|
-
- data/csets/unicode/latin-extended-d.yaml
|
|
79
|
+
- data/csets/unicode/spacing_modifier_letters.yaml
|
|
94
80
|
- data/csets/unicode/latin_extended_a.yaml
|
|
95
|
-
- data/csets/unicode/
|
|
81
|
+
- data/csets/unicode/ipa_extensions.yaml
|
|
96
82
|
- data/csets/unicode/latin_1_supplement.yaml
|
|
83
|
+
- data/csets/unicode/greek.yaml
|
|
84
|
+
- data/csets/unicode/latin_extended_b.yaml
|
|
85
|
+
- data/csets/unicode/latin-extended-d.yaml
|
|
97
86
|
- data/csets/unicode/basic_latin.yaml
|
|
87
|
+
- data/csets/unicode/latin_extended_additional.yaml
|
|
98
88
|
- data/csets/unicode/cyrillic.yaml
|
|
89
|
+
- data/csets/unicode/cyrillic-supplement.yaml
|
|
90
|
+
- data/csets/unicode/letterlike_symbols.yaml
|
|
91
|
+
- data/csets/iso_8859-1.yaml
|
|
92
|
+
- data/csets/utf8.yaml
|
|
93
|
+
- data/csets/utf-8.yaml
|
|
94
|
+
- data/csets/latin1.yaml
|
|
95
|
+
- data/csets/iso_8859-15.yaml
|
|
99
96
|
- data/test_chars.yaml
|
|
100
|
-
- data/chartab.yaml
|
|
101
97
|
has_rdoc: true
|
|
102
98
|
homepage: http://prometheus.rubyforge.org/cmess
|
|
99
|
+
licenses: []
|
|
100
|
+
|
|
103
101
|
post_install_message:
|
|
104
102
|
rdoc_options:
|
|
103
|
+
- --all
|
|
104
|
+
- --main
|
|
105
|
+
- README
|
|
105
106
|
- --line-numbers
|
|
106
107
|
- --inline-source
|
|
107
108
|
- --title
|
|
108
109
|
- cmess Application documentation
|
|
109
110
|
- --charset
|
|
110
111
|
- UTF-8
|
|
111
|
-
- --main
|
|
112
|
-
- README
|
|
113
|
-
- --all
|
|
114
112
|
require_paths:
|
|
115
113
|
- lib
|
|
116
114
|
required_ruby_version: !ruby/object:Gem::Requirement
|
|
@@ -128,9 +126,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
128
126
|
requirements: []
|
|
129
127
|
|
|
130
128
|
rubyforge_project: prometheus
|
|
131
|
-
rubygems_version: 1.
|
|
129
|
+
rubygems_version: 1.3.3
|
|
132
130
|
signing_key:
|
|
133
|
-
specification_version:
|
|
131
|
+
specification_version: 3
|
|
134
132
|
summary: "Assist with handling messed up encodings (Currently includes the following tools: bconv, cinderella, decode_entities, guess_encoding)"
|
|
135
133
|
test_files: []
|
|
136
134
|
|