klookup 0.2.4 → 0.3
Sign up to get free protection for your applications and to get access to all the features.
- data/bin/klookup.cgi +9 -7
- data/data/klookup/data.db +0 -0
- data/lib/klookup.rb +2 -8
- data/lib/klookup/database.rb +18 -7
- data/lib/klookup/database_flatfile.rb +26 -17
- data/lib/klookup/database_sqlite.rb +110 -0
- data/lib/klookup/lookup.rb +6 -1
- data/lib/klookup/lookup_kanji.rb +9 -30
- data/lib/klookup/lookup_radical.rb +4 -0
- data/lib/runicode.rb +39 -0
- data/lib/runicode/utf8.rb +132 -0
- data/test/database_test.rb +287 -61
- data/test/runicode_test.rb +89 -0
- data/test/suite.rb +71 -57
- metadata +18 -13
- data/lib/klookup/database_quickfile.rb +0 -38
data/bin/klookup.cgi
CHANGED
@@ -24,14 +24,16 @@ end
|
|
24
24
|
include KLookup::Lookup
|
25
25
|
|
26
26
|
require 'cgi'
|
27
|
+
|
28
|
+
# GetText is being problematic when it is found.
|
27
29
|
# If the platform doesn't have gettext we can survive
|
28
|
-
begin
|
29
|
-
require 'gettext'
|
30
|
-
include GetText
|
31
|
-
bindtextdomain 'klookup'
|
32
|
-
rescue LoadError
|
33
|
-
|
34
|
-
end
|
30
|
+
#begin
|
31
|
+
# require 'gettext'
|
32
|
+
# include GetText
|
33
|
+
# bindtextdomain 'klookup'
|
34
|
+
#rescue LoadError
|
35
|
+
def _(arg); arg; end
|
36
|
+
#end
|
35
37
|
|
36
38
|
class String
|
37
39
|
#Deletes the characters (NOT bytes) listed in str from the string
|
Binary file
|
data/lib/klookup.rb
CHANGED
@@ -11,19 +11,13 @@
|
|
11
11
|
=end
|
12
12
|
|
13
13
|
begin
|
14
|
-
require '
|
14
|
+
require 'rubygems'
|
15
15
|
rescue LoadError
|
16
|
-
# begin
|
17
|
-
# require 'rubygems'
|
18
|
-
# require 'active_support'
|
19
|
-
# rescue LoadError
|
20
|
-
require 'runicode'
|
21
|
-
# end
|
22
16
|
end
|
23
17
|
|
24
|
-
#This allows regular expressions to work on characters.
|
25
18
|
$KCODE='u'
|
26
19
|
require 'jcode'
|
20
|
+
require 'runicode'
|
27
21
|
|
28
22
|
# Contains Lookup and Database.
|
29
23
|
module KLookup
|
data/lib/klookup/database.rb
CHANGED
@@ -23,10 +23,7 @@ class KLookup::Database
|
|
23
23
|
|
24
24
|
public
|
25
25
|
|
26
|
-
|
27
|
-
#
|
28
|
-
# Priority: LOOKUP_PATH environment variable, Gem load path.
|
29
|
-
def self.open_resource(path, mod='klookup')
|
26
|
+
def self.resource_path(path, mod='klookup')
|
30
27
|
# Choose a directory
|
31
28
|
env=ENV['KLOOKUP_PATH']
|
32
29
|
if env and env != ''
|
@@ -36,12 +33,26 @@ class KLookup::Database
|
|
36
33
|
gem mod
|
37
34
|
dir=Gem.datadir(mod)
|
38
35
|
rescue NameError
|
39
|
-
|
36
|
+
# This is a fallback for older versions of RubyGems (0.8)
|
37
|
+
begin
|
38
|
+
require_gem mod
|
39
|
+
dir=Gem.datadir(mod)
|
40
|
+
rescue NameError
|
41
|
+
raise IOError, 'Could not find resource %s' % path
|
42
|
+
end
|
40
43
|
end
|
41
44
|
end
|
45
|
+
raise Errno::ENOENT if Dir["#{dir}/#{path}"].empty?
|
46
|
+
"#{dir}/#{path}"
|
47
|
+
end
|
42
48
|
|
49
|
+
# Opens a resource.
|
50
|
+
#
|
51
|
+
# Priority: LOOKUP_PATH environment variable, Gem load path.
|
52
|
+
def self.open_resource(path, mod='klookup')
|
43
53
|
# Open a file
|
44
|
-
|
54
|
+
path = resource_path(path, mod)
|
55
|
+
file = open(path)
|
45
56
|
if block_given?
|
46
57
|
yield file
|
47
58
|
else
|
@@ -60,6 +71,6 @@ class KLookup::Database
|
|
60
71
|
alias :is_radical? :undefined
|
61
72
|
|
62
73
|
require 'klookup/database_flatfile'
|
63
|
-
|
74
|
+
require 'klookup/database_sqlite'
|
64
75
|
# require 'klookup/database_unihan'
|
65
76
|
end
|
@@ -50,35 +50,44 @@ class KLookup::Database::FlatFile < KLookup::Database
|
|
50
50
|
kanji = RadK.instance.get_kanji(*args)
|
51
51
|
end
|
52
52
|
unless strokes.nil?
|
53
|
-
return kanji.select {|k|
|
53
|
+
return kanji.select {|k| get_stroke_count(k) == strokes }
|
54
54
|
end
|
55
55
|
return kanji
|
56
56
|
end
|
57
57
|
public
|
58
|
-
def find_kanji(args)
|
58
|
+
def find_kanji(args={})
|
59
|
+
if not args.kind_of?(Hash)
|
60
|
+
raise ArgumentError, 'only takes a hash'
|
61
|
+
elsif (not args[:stroke].nil?) and (not args[:stroke].kind_of?(Integer))
|
62
|
+
raise ArgumentError, ':stroke must be an Integer'
|
63
|
+
end
|
59
64
|
get_kanji(args[:stroke], args[:radical])
|
60
65
|
end
|
61
|
-
def
|
62
|
-
RadK.instance.get_strokes(*args)
|
63
|
-
end
|
64
|
-
def get_stroke_count
|
66
|
+
def get_stroke_count(*args)
|
65
67
|
begin
|
66
68
|
RadK.instance.get_strokes(*args)
|
67
|
-
rescue
|
68
|
-
|
69
|
+
rescue NoMethodError
|
70
|
+
begin
|
71
|
+
KanjiDic.instance.get_strokes(*args)
|
72
|
+
rescue NoMethodError
|
73
|
+
raise ArgumentError, 'character not found'
|
74
|
+
end
|
69
75
|
end
|
70
76
|
end
|
71
|
-
def
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
RadK.instance.get_radicals(*args)
|
77
|
+
def get_radical(kanji)
|
78
|
+
raise ArgumentError if kanji.chars.size > 1
|
79
|
+
raise ArgumentError unless is_kanji?(kanji)
|
80
|
+
RadK.instance.get_radicals(kanji)
|
76
81
|
end
|
77
|
-
def get_reading(
|
78
|
-
|
82
|
+
def get_reading(kanji)
|
83
|
+
raise ArgumentError if kanji.chars.size > 1
|
84
|
+
raise ArgumentError unless is_kanji?(kanji)
|
85
|
+
KanjiDic.instance.get_reading(kanji)
|
79
86
|
end
|
80
|
-
def get_meaning(
|
81
|
-
|
87
|
+
def get_meaning(kanji)
|
88
|
+
raise ArgumentError if kanji.chars.size > 1
|
89
|
+
raise ArgumentError unless is_kanji?(kanji)
|
90
|
+
KanjiDic.instance.get_meaning(kanji)
|
82
91
|
end
|
83
92
|
def is_kanji?(*args)
|
84
93
|
KanjiDic.instance.is_kanji?(*args)
|
@@ -0,0 +1,110 @@
|
|
1
|
+
=begin
|
2
|
+
|
3
|
+
lib/klookup/database_flatfile.rb
|
4
|
+
|
5
|
+
Copyright © Tom Adams 2006
|
6
|
+
|
7
|
+
This programme is free software.
|
8
|
+
You can distribute/modify this program under
|
9
|
+
the terms of the Ruby License.
|
10
|
+
|
11
|
+
=end
|
12
|
+
|
13
|
+
# A singleton class to abstract RadK and KanjiDic.
|
14
|
+
class KLookup::Database::SQLite < KLookup::Database
|
15
|
+
|
16
|
+
require 'singleton'
|
17
|
+
include Singleton
|
18
|
+
|
19
|
+
def initialize
|
20
|
+
require 'sqlite'
|
21
|
+
path = KLookup::Database.resource_path('data.db')
|
22
|
+
@db = ::SQLite::Database.new(path)
|
23
|
+
end
|
24
|
+
|
25
|
+
# Umm...
|
26
|
+
def finalize
|
27
|
+
@db.close
|
28
|
+
end
|
29
|
+
|
30
|
+
def radical_stroke_count
|
31
|
+
@db.execute("select distinct stroke_count from radical order by stroke_count").flatten.collect {|s| s.to_i}
|
32
|
+
end
|
33
|
+
|
34
|
+
def find_radical(args={})
|
35
|
+
raise ArgumentError unless args.kind_of?(Hash)
|
36
|
+
stroke_count = args[:stroke]
|
37
|
+
raise ArgumentError unless stroke_count.kind_of?(Integer) or stroke_count.nil?
|
38
|
+
if stroke_count
|
39
|
+
@db.execute("select radical from radical where stroke_count=?", stroke_count).flatten
|
40
|
+
else
|
41
|
+
@db.execute("select radical from radical").flatten
|
42
|
+
end
|
43
|
+
end
|
44
|
+
|
45
|
+
def find_kanji(args={})
|
46
|
+
raise ArgumentError, 'args must be Hash or nil' unless args.kind_of?(Hash) or args.nil?
|
47
|
+
stroke_count = args[:stroke]
|
48
|
+
raise ArgumentError, ':stroke must be Integer or nil' unless stroke_count.kind_of?(Integer) or stroke_count.nil?
|
49
|
+
radical = args[:radical]
|
50
|
+
radical = [radical] if radical.kind_of?(String)
|
51
|
+
raise ArgumentError, ':radical must be Array, String, or nil' unless radical.kind_of?(Array) or radical.nil?
|
52
|
+
|
53
|
+
kanji = []
|
54
|
+
if stroke_count
|
55
|
+
kanji = @db.execute("select kanji from kanji where stroke_count=?",
|
56
|
+
stroke_count).flatten
|
57
|
+
else
|
58
|
+
kanji = @db.execute("select kanji from kanji").flatten
|
59
|
+
end
|
60
|
+
|
61
|
+
if radical
|
62
|
+
radical.each {|r|
|
63
|
+
raise ArgumentError, ':radical must contain radicals' unless is_radical?(r)
|
64
|
+
new_r = @db.execute("select kanji from mapping where radical=?",
|
65
|
+
r).flatten
|
66
|
+
kanji &= new_r
|
67
|
+
}
|
68
|
+
end
|
69
|
+
kanji
|
70
|
+
end
|
71
|
+
|
72
|
+
def get_stroke_count(character)
|
73
|
+
if is_kanji?(character)
|
74
|
+
@db.get_first_row("select stroke_count from kanji where kanji=?", character).first.to_i
|
75
|
+
elsif is_radical?(character)
|
76
|
+
@db.get_first_row("select stroke_count from radical where radical=?", character).first.to_i
|
77
|
+
else
|
78
|
+
raise ArgumentError
|
79
|
+
end
|
80
|
+
end
|
81
|
+
|
82
|
+
def get_radical(character)
|
83
|
+
raise ArgumentError unless is_kanji?(character)
|
84
|
+
@db.execute("select radical from mapping where kanji=?", character).
|
85
|
+
collect {|r| r.first }
|
86
|
+
end
|
87
|
+
|
88
|
+
def get_reading(character)
|
89
|
+
raise ArgumentError unless is_kanji?(character)
|
90
|
+
reading = @db.execute("select reading from reading where kanji=? and is_name_reading='false'", character).flatten
|
91
|
+
name_reading = @db.execute("select reading from reading where kanji=? and is_name_reading='true'", character).flatten
|
92
|
+
Struct.new(:reading, :name_reading).new(reading, name_reading)
|
93
|
+
end
|
94
|
+
|
95
|
+
def get_meaning(character)
|
96
|
+
raise ArgumentError unless is_kanji?(character)
|
97
|
+
@db.execute("select meaning from meaning where kanji=?", character).flatten
|
98
|
+
end
|
99
|
+
|
100
|
+
def is_kanji?(character)
|
101
|
+
@db.get_first_row("select count(*) from kanji where kanji=?",
|
102
|
+
character).first.to_i >= 1
|
103
|
+
end
|
104
|
+
|
105
|
+
def is_radical?(character)
|
106
|
+
@db.get_first_row("select count(*) from radical where radical=?",
|
107
|
+
character).first.to_i >= 1
|
108
|
+
end
|
109
|
+
|
110
|
+
end
|
data/lib/klookup/lookup.rb
CHANGED
@@ -15,7 +15,12 @@ module KLookup::Lookup
|
|
15
15
|
|
16
16
|
# Returns the default handler for database lookups.
|
17
17
|
def self.default_handler
|
18
|
-
|
18
|
+
begin
|
19
|
+
KLookup::Database::SQLite.instance
|
20
|
+
KLookup::Database::SQLite
|
21
|
+
rescue LoadError
|
22
|
+
KLookup::Database::FlatFile
|
23
|
+
end
|
19
24
|
end
|
20
25
|
|
21
26
|
# Set the handler used by both Kanji and Radical.
|
data/lib/klookup/lookup_kanji.rb
CHANGED
@@ -19,34 +19,9 @@ class KLookup::Lookup::Kanji
|
|
19
19
|
# Returns a string containing the UTF-8 encoded character represented by the
|
20
20
|
# receiver’s value.
|
21
21
|
#
|
22
|
-
#
|
23
|
-
def self.
|
24
|
-
|
25
|
-
when 0xD800..0xDFFF
|
26
|
-
raise RangeError, 'these values are surrogate pairs'
|
27
|
-
when 0x0000..0x007F
|
28
|
-
return "%c" % (val & 0b01111111) # 7
|
29
|
-
when 0x0080..0x07FF
|
30
|
-
byte = []
|
31
|
-
byte[0] = 0b11000000 + ((val >> 6) & 0b11111) # 5
|
32
|
-
byte[1] = 0b10000000 + (val & 0b111111) # 6
|
33
|
-
return "%c%c" % byte
|
34
|
-
when 0x0800..0xFFFF
|
35
|
-
byte = []
|
36
|
-
byte[0] = 0b11100000 + ((val >> 12) & 0b1111) # 4
|
37
|
-
byte[1] = 0b10000000 + ((val >> 6) & 0b111111) # 6
|
38
|
-
byte[2] = 0b10000000 + (val & 0b111111) # 6
|
39
|
-
return "%c%c%c" % byte
|
40
|
-
when 0x00010000..0x0010FFFF
|
41
|
-
byte = []
|
42
|
-
byte[0] = 0b11110000 + ((val >> 18) & 0b11111) # 5
|
43
|
-
byte[1] = 0b10000000 + ((val >> 12) & 0b111111) # 6
|
44
|
-
byte[2] = 0b10000000 + ((val >> 6) & 0b111111) # 6
|
45
|
-
byte[3] = 0b10000000 + (val & 0b111111) # 6
|
46
|
-
return "%c%c%c%c" % byte
|
47
|
-
else
|
48
|
-
raise RangeError, 'out of Unicode range'
|
49
|
-
end
|
22
|
+
# Uses RUnicode's Integer#chr method
|
23
|
+
def self.cp_to_str(val)
|
24
|
+
return val.chr
|
50
25
|
end
|
51
26
|
|
52
27
|
# Returns a regular expression that matches strings in a kana-insensitive
|
@@ -69,9 +44,9 @@ class KLookup::Lookup::Kanji
|
|
69
44
|
re=''
|
70
45
|
str.each_char {|c|
|
71
46
|
if hiragana.include?(c.chars.first)
|
72
|
-
re << "[#{c}#{
|
47
|
+
re << "[#{c}#{cp_to_str(hkhash[c.chars.first])}]"
|
73
48
|
elsif katakana.include?(c.chars.first)
|
74
|
-
re << "[#{c}#{
|
49
|
+
re << "[#{c}#{cp_to_str(khhash[c.chars.first])}]"
|
75
50
|
else
|
76
51
|
re << c
|
77
52
|
end
|
@@ -206,4 +181,8 @@ class KLookup::Lookup::Kanji
|
|
206
181
|
end
|
207
182
|
@meaning
|
208
183
|
end
|
184
|
+
|
185
|
+
def stroke_count
|
186
|
+
@@data.instance.get_stroke_count(@kanji)
|
187
|
+
end
|
209
188
|
end
|
data/lib/runicode.rb
ADDED
@@ -0,0 +1,39 @@
|
|
1
|
+
=begin
|
2
|
+
|
3
|
+
lib/runicode.rb
|
4
|
+
|
5
|
+
Copyright © Tom Adams 2006
|
6
|
+
|
7
|
+
This programme is free software.
|
8
|
+
You can distribute/modify this program under
|
9
|
+
the terms of the Ruby License.
|
10
|
+
|
11
|
+
=end
|
12
|
+
|
13
|
+
$KCODE='u'
|
14
|
+
require 'jcode'
|
15
|
+
|
16
|
+
module RUnicode # :nodoc:
|
17
|
+
end
|
18
|
+
|
19
|
+
# Ruby-based UTF-8 processing
|
20
|
+
require 'runicode/utf8'
|
21
|
+
|
22
|
+
class String # :nodoc:
|
23
|
+
|
24
|
+
#Yields to each codepoint of a string.
|
25
|
+
def each_char
|
26
|
+
raise LocalJumpError unless block_given?
|
27
|
+
each_codepoint {|cp| yield cp.chr}
|
28
|
+
end
|
29
|
+
|
30
|
+
#Collects the codepoints as an array.
|
31
|
+
def codepoints
|
32
|
+
codepoints = []
|
33
|
+
each_codepoint {|c| codepoints << c}
|
34
|
+
return codepoints
|
35
|
+
end
|
36
|
+
|
37
|
+
alias :chars :codepoints
|
38
|
+
|
39
|
+
end
|
@@ -0,0 +1,132 @@
|
|
1
|
+
=begin
|
2
|
+
|
3
|
+
lib/runicode/utf8.rb
|
4
|
+
|
5
|
+
Copyright © Tom Adams 2006
|
6
|
+
|
7
|
+
This programme is free software.
|
8
|
+
You can distribute/modify this program under
|
9
|
+
the terms of the Ruby License.
|
10
|
+
|
11
|
+
=end
|
12
|
+
|
13
|
+
module RUnicode::UTF8 # :nodoc:
|
14
|
+
class ThisShouldNotHappen < Exception # :nodoc:
|
15
|
+
end
|
16
|
+
|
17
|
+
INVALID_BYTES = ((0xC0..0xC1).to_a + (0xF5..0xFE).to_a +
|
18
|
+
[0b11000000, 0b11100000, 0b11110000])
|
19
|
+
|
20
|
+
# Converts one set of bytes making up a character into an integer codepoint
|
21
|
+
def self.bytes_to_char(bytes)
|
22
|
+
case bytes.size
|
23
|
+
when 1 # 0xxxxxxx
|
24
|
+
return bytes.first & 0b01111111
|
25
|
+
when 2 # 110xxxxx 10xxxxxx
|
26
|
+
return ((bytes.first & 0b00011111) << 6) + rest(bytes[1..-1])
|
27
|
+
when 3 # 1110xxxx 10xxxxxx 10xxxxxx
|
28
|
+
return ((bytes.first & 0b00001111) << 12) + rest(bytes[1..-1])
|
29
|
+
when 4 # 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
|
30
|
+
return ((bytes.first & 0b00000111) << 18) + rest(bytes[1..-1])
|
31
|
+
else raise ThisShouldNotHappen
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
# Gives the total value from 10xxxxxx in each byte
|
36
|
+
def self.rest(bytes)
|
37
|
+
val = 0b0
|
38
|
+
bytes.each {|b|
|
39
|
+
val = (val << 6)
|
40
|
+
val += (b & 0b00111111)
|
41
|
+
}
|
42
|
+
val
|
43
|
+
end
|
44
|
+
|
45
|
+
end
|
46
|
+
|
47
|
+
class String # :nodoc:
|
48
|
+
#Passes each character in str to the given block as an Integer. A rewrite of
|
49
|
+
#codepoints.
|
50
|
+
def each_codepoint
|
51
|
+
raise LocalJumpError, 'no block given' unless block_given?
|
52
|
+
|
53
|
+
steal_next = 0
|
54
|
+
current_bytes = nil
|
55
|
+
|
56
|
+
to_s.each_byte {|b|
|
57
|
+
if steal_next==0 # No octets need to be stolen
|
58
|
+
unless current_bytes==nil
|
59
|
+
current_bytes.each {|byte|
|
60
|
+
if RUnicode::UTF8::INVALID_BYTES.include? byte
|
61
|
+
raise IOError, 'ill-formed UTF-8'
|
62
|
+
end
|
63
|
+
}
|
64
|
+
yield RUnicode::UTF8::bytes_to_char(current_bytes)
|
65
|
+
end
|
66
|
+
current_bytes = [b]
|
67
|
+
if b >> 7 == 0b0
|
68
|
+
steal_next = 0
|
69
|
+
elsif b >> 5 == 0b110
|
70
|
+
steal_next = 1
|
71
|
+
elsif b >> 4 == 0b1110
|
72
|
+
steal_next = 2
|
73
|
+
elsif b >> 3 == 0b11110
|
74
|
+
steal_next = 3
|
75
|
+
else
|
76
|
+
raise IOError, 'ill-formed UTF-8'
|
77
|
+
end
|
78
|
+
|
79
|
+
else # We have some octets to steal
|
80
|
+
raise IOError, 'ill-formed UTF-8' unless b >> 6 == 0b10
|
81
|
+
current_bytes << b
|
82
|
+
steal_next -= 1
|
83
|
+
end
|
84
|
+
}
|
85
|
+
|
86
|
+
# One last time:
|
87
|
+
unless current_bytes==nil
|
88
|
+
current_bytes.each {|byte|
|
89
|
+
if RUnicode::UTF8::INVALID_BYTES.include? byte
|
90
|
+
raise IOError, 'ill-formed UTF-8'
|
91
|
+
end
|
92
|
+
}
|
93
|
+
yield RUnicode::UTF8::bytes_to_char(current_bytes)
|
94
|
+
end
|
95
|
+
|
96
|
+
raise IOError, 'ill-formed UTF-8' if steal_next != 0
|
97
|
+
|
98
|
+
end # each_codepoint
|
99
|
+
end
|
100
|
+
|
101
|
+
class Integer # :nodoc:
|
102
|
+
#Returns a string containing the UTF-8 encoded character represented by the
|
103
|
+
#receiver’s value.
|
104
|
+
def chr
|
105
|
+
case to_i
|
106
|
+
when 0xD800..0xDFFF
|
107
|
+
raise RangeError, 'these values are surrogate pairs'
|
108
|
+
when 0x0000..0x007F
|
109
|
+
return "%c" % (to_i & 0b01111111) # 7
|
110
|
+
when 0x0080..0x07FF
|
111
|
+
byte = []
|
112
|
+
byte[0] = 0b11000000 + ((to_i >> 6) & 0b11111) # 5
|
113
|
+
byte[1] = 0b10000000 + (to_i & 0b111111) # 6
|
114
|
+
return "%c%c" % byte
|
115
|
+
when 0x0800..0xFFFF
|
116
|
+
byte = []
|
117
|
+
byte[0] = 0b11100000 + ((to_i >> 12) & 0b1111) # 4
|
118
|
+
byte[1] = 0b10000000 + ((to_i >> 6) & 0b111111) # 6
|
119
|
+
byte[2] = 0b10000000 + (to_i & 0b111111) # 6
|
120
|
+
return "%c%c%c" % byte
|
121
|
+
when 0x00010000..0x0010FFFF
|
122
|
+
byte = []
|
123
|
+
byte[0] = 0b11110000 + ((to_i >> 18) & 0b11111) # 5
|
124
|
+
byte[1] = 0b10000000 + ((to_i >> 12) & 0b111111) # 6
|
125
|
+
byte[2] = 0b10000000 + ((to_i >> 6) & 0b111111) # 6
|
126
|
+
byte[3] = 0b10000000 + (to_i & 0b111111) # 6
|
127
|
+
return "%c%c%c%c" % byte
|
128
|
+
else
|
129
|
+
raise RangeError, 'out of Unicode range'
|
130
|
+
end
|
131
|
+
end
|
132
|
+
end
|
data/test/database_test.rb
CHANGED
@@ -8,62 +8,58 @@ class Database_Test < Test::Unit::TestCase
|
|
8
8
|
@@db = @@dbc.instance
|
9
9
|
end
|
10
10
|
|
11
|
-
# Asserts false with message +msg+ if +exception+ is not raised within
|
12
|
-
# the given block.
|
13
|
-
def must_except(exception=Exception, msg=nil)
|
14
|
-
raise LocalJumpError unless block_given?
|
15
|
-
begin
|
16
|
-
yield
|
17
|
-
rescue exception
|
18
|
-
else
|
19
|
-
assert false, msg
|
20
|
-
end
|
21
|
-
end
|
22
|
-
|
23
|
-
|
24
11
|
def test_open_resource
|
25
|
-
f =
|
26
|
-
|
12
|
+
f = KLookup::Database.open_resource('newradkfile')
|
13
|
+
assert_respond_to f, :each_line, 'valid path'
|
27
14
|
|
28
|
-
f =
|
29
|
-
|
15
|
+
f = KLookup::Database.open_resource('newradkfile', 'klookup')
|
16
|
+
assert_respond_to f, :each_line, 'valid path and valid gem'
|
30
17
|
|
31
18
|
flag=false
|
32
|
-
|
33
|
-
|
19
|
+
KLookup::Database.open_resource('newradkfile') {|f|
|
20
|
+
assert_respond_to f, :each_line
|
34
21
|
flag=true
|
35
22
|
}
|
36
23
|
assert flag, 'using a block'
|
37
24
|
|
38
|
-
|
39
|
-
|
25
|
+
assert_raise(Errno::ENOENT, 'invalid path') {
|
26
|
+
KLookup::Database.open_resource('all your base are belong to us')
|
40
27
|
}
|
41
|
-
|
42
|
-
|
28
|
+
assert_raise(Errno::ENOENT, 'invalid path') {
|
29
|
+
KLookup::Database.open_resource('all your base are belong to us')
|
30
|
+
}
|
31
|
+
assert_raise(Errno::ENOENT, 'invalid gem') {
|
32
|
+
KLookup::Database.open_resource('newradkfile', 'cookies are yummy')
|
43
33
|
}
|
44
34
|
end
|
45
35
|
|
46
36
|
def test_methods_exist
|
47
37
|
[:radical_stroke_count,
|
48
38
|
:find_radical,
|
49
|
-
:find_kanji,
|
50
|
-
:get_stroke_count,
|
51
|
-
:get_radical,
|
52
|
-
:get_reading,
|
53
|
-
:get_meaning,
|
54
|
-
:is_kanji?,
|
55
|
-
:is_radical?
|
39
|
+
:find_kanji,
|
40
|
+
:get_stroke_count,
|
41
|
+
:get_radical,
|
42
|
+
:get_reading,
|
43
|
+
:get_meaning,
|
44
|
+
:is_kanji?,
|
45
|
+
:is_radical?
|
56
46
|
].each {|m|
|
57
|
-
|
47
|
+
assert_respond_to @@db, m
|
58
48
|
}
|
59
|
-
|
49
|
+
# assert_respond_to @@dbc, :open_resource
|
60
50
|
end
|
61
51
|
|
62
52
|
def test_radical_stroke_count
|
63
|
-
|
53
|
+
assert_kind_of Enumerable, @@db.radical_stroke_count
|
64
54
|
assert (@@db.radical_stroke_count.size > 0), 'more than zero'
|
65
|
-
|
66
|
-
assert
|
55
|
+
(1..15).each {|n|
|
56
|
+
assert @@db.radical_stroke_count.include?(n)
|
57
|
+
}
|
58
|
+
@@db.radical_stroke_count.each {|s|
|
59
|
+
assert_kind_of Integer, s
|
60
|
+
}
|
61
|
+
assert_raise(ArgumentError) {
|
62
|
+
@@db.radical_stroke_count(7)
|
67
63
|
}
|
68
64
|
end
|
69
65
|
|
@@ -71,57 +67,287 @@ class Database_Test < Test::Unit::TestCase
|
|
71
67
|
test = @@db.find_radical(:stroke=>11)
|
72
68
|
assert test.include?('鳥')
|
73
69
|
assert (not test.include?('馬'))
|
70
|
+
|
74
71
|
test = @@db.find_radical(:stroke=>10)
|
75
72
|
assert test.include?('馬')
|
76
73
|
assert (not test.include?('鳥'))
|
74
|
+
|
77
75
|
test = @@db.find_radical
|
78
76
|
assert test.include?('鳥')
|
79
77
|
assert test.include?('馬')
|
78
|
+
|
80
79
|
newtest = @@db.find_radical(:stroke=>nil)
|
81
|
-
|
80
|
+
assert_equal test, newtest, 'Sets are identical'
|
82
81
|
test = @@db.find_radical(:stroke=>0)
|
83
|
-
|
82
|
+
assert_equal test.size, 0, 'Size is zero'
|
84
83
|
|
85
|
-
|
84
|
+
assert_raise(ArgumentError, 'not a hash (String)') {
|
86
85
|
@@db.find_radical('cats')
|
87
86
|
}
|
88
|
-
|
87
|
+
assert_raise(ArgumentError, 'not a hash (Integer)') {
|
89
88
|
@@db.find_radical(6)
|
90
89
|
}
|
91
|
-
|
90
|
+
assert_raise(ArgumentError, 'invalid :stroke') {
|
92
91
|
@@db.find_radical(:stroke=>'nobbly knees')
|
93
92
|
}
|
93
|
+
assert_raise(ArgumentError) {
|
94
|
+
@@db.find_radical('動', '詞')
|
95
|
+
}
|
96
|
+
assert_raise(ArgumentError) {
|
97
|
+
@@db.find_radical('動')
|
98
|
+
}
|
99
|
+
|
94
100
|
test = @@db.find_radical(:stroke=>10,:cats=>:dogs)
|
95
101
|
assert test.include?('馬')
|
96
102
|
assert (not test.include?('鳥'))
|
97
103
|
end
|
98
104
|
|
99
105
|
def test_find_kanji
|
106
|
+
# Simple cases
|
107
|
+
test = @@db.find_kanji(:stroke=>11)
|
108
|
+
assert test.include?('猫'), '11 includes 猫'
|
109
|
+
assert (not test.include?('犬')), '11 excludes 犬'
|
110
|
+
|
111
|
+
test = @@db.find_kanji(:stroke=>4)
|
112
|
+
assert test.include?('犬'), '10 includes 犬'
|
113
|
+
assert (not test.include?('猫')), '10 excludes 猫'
|
114
|
+
|
115
|
+
test = @@db.find_kanji(:radical=>['犭'])
|
116
|
+
assert test.include?('猫'), '犭 includes 猫'
|
117
|
+
assert (not test.include?('鳥')), '犭 excludes 鳥'
|
118
|
+
|
119
|
+
test = @@db.find_kanji(:radical=>['犭'],:stroke=>11)
|
120
|
+
assert test.include?('猫'), '犭 (11 strokes) includes 猫'
|
121
|
+
assert (not test.include?('鳥')), '犭 (11 strokes) excludes 鳥'
|
122
|
+
|
123
|
+
test = @@db.find_kanji(:radical=>['犭', '艹', '田'],:stroke=>11)
|
124
|
+
assert test.include?('猫'), '犭艹田 (11 strokes) includes 猫'
|
125
|
+
assert (not test.include?('鳥')), '犭艹田 (11 strokes) excludes 鳥'
|
126
|
+
|
127
|
+
test = @@db.find_kanji(:radical=>['犭', '艹', '田'])
|
128
|
+
assert test.include?('猫'), '犭艹田 (no strokes) includes 猫'
|
129
|
+
assert (not test.include?('鳥')), '犭艹田 (no strokes) excludes 鳥'
|
130
|
+
|
131
|
+
# Uncommon cases
|
132
|
+
test = @@db.find_kanji
|
133
|
+
assert test.include?('猫'), 'all includes 猫'
|
134
|
+
assert test.include?('犬'), 'all includes 犬'
|
135
|
+
|
136
|
+
test = @@db.find_kanji(:radical=>'犭')
|
137
|
+
assert test.include?('猫'), '犭 (not list) includes 猫'
|
138
|
+
assert (not test.include?('鳥')), '犭 (not list) excludes 鳥'
|
139
|
+
|
140
|
+
test = @@db.find_kanji(:radical=>'犭',:stroke=>11)
|
141
|
+
assert test.include?('猫'), '犭 (not list, 11 strokes) includes 猫'
|
142
|
+
assert (not test.include?('鳥')), '犭 (not list, 11 strokes) excludes 鳥'
|
143
|
+
|
144
|
+
test = @@db.find_kanji(:radical=>['犭', '艹', '田'], :stroke=>10)
|
145
|
+
assert_kind_of Enumerable, test, '犭艹田 (10 strokes!) is Enumerable'
|
146
|
+
assert_equal test.size, 0, '犭艹田 (10 strokes!) returns zero results'
|
147
|
+
|
148
|
+
# Extraneous input
|
149
|
+
test = @@db.find_kanji(:stroke=>4,:strokes=>'cat')
|
150
|
+
assert test.include?('犬'), '10 with extraneous input includes 犬'
|
151
|
+
assert (not test.include?('猫')), '10 with extraneous input excludes 猫'
|
152
|
+
|
153
|
+
# Problem cases
|
154
|
+
assert_raise(ArgumentError, ':stroke=>"cat"') {
|
155
|
+
@@db.find_kanji(:stroke=>'cat')
|
156
|
+
}
|
157
|
+
assert_raise(ArgumentError, ':radical=>"cat"') {
|
158
|
+
@@db.find_kanji(:radical=>'cat')
|
159
|
+
}
|
160
|
+
assert_raise(ArgumentError, ':radical=>["cat"]') {
|
161
|
+
@@db.find_kanji(:radical=>['cat'])
|
162
|
+
}
|
163
|
+
assert_raise(ArgumentError, ':radical=>["田犬"]') {
|
164
|
+
@@db.find_kanji(:radical=>['田犬'])
|
165
|
+
}
|
166
|
+
assert_raise(ArgumentError) {
|
167
|
+
@@db.find_kanji('犬', '田')
|
168
|
+
}
|
169
|
+
assert_raise(ArgumentError) {
|
170
|
+
@@db.find_kanji('犬')
|
171
|
+
}
|
100
172
|
end
|
101
173
|
|
102
|
-
|
174
|
+
def test_get_stroke_count
|
175
|
+
# Simple cases
|
176
|
+
|
177
|
+
assert_equal @@db.get_stroke_count('猫'), 11, '猫=11'
|
178
|
+
assert_equal @@db.get_stroke_count('鳥'), 11, '鳥=11'
|
179
|
+
assert_equal @@db.get_stroke_count('犬'), 4, '犬=4'
|
180
|
+
assert_equal @@db.get_stroke_count('田'), 5, '田=5'
|
181
|
+
assert_equal @@db.get_stroke_count('犭'), 3, '犭=3'
|
103
182
|
|
183
|
+
# Problem cases
|
184
|
+
assert_raise(ArgumentError, 'no arguments') {
|
185
|
+
@@db.get_stroke_count()
|
186
|
+
}
|
187
|
+
assert_raise(ArgumentError, ':radical=>"犬"') {
|
188
|
+
@@db.get_stroke_count(:radical=>'犬')
|
189
|
+
}
|
190
|
+
assert_raise(ArgumentError, 'two characters') {
|
191
|
+
@@db.get_stroke_count('犬猫')
|
192
|
+
}
|
193
|
+
assert_raise(ArgumentError) {
|
194
|
+
@@db.get_stroke_count
|
195
|
+
}
|
196
|
+
assert_raise(ArgumentError) {
|
197
|
+
@@db.get_stroke_count('動', '詞')
|
198
|
+
}
|
199
|
+
end
|
104
200
|
|
201
|
+
def test_get_radical
|
202
|
+
#TODO: May not play well with other data sources
|
203
|
+
cat = @@db.get_radical('猫')
|
204
|
+
assert_equal cat.size, 3
|
205
|
+
['犭', '艹', '田'].each {|r|
|
206
|
+
assert cat.include?(r), "contains #{r}"
|
207
|
+
}
|
105
208
|
|
106
|
-
|
107
|
-
|
108
|
-
|
109
|
-
|
110
|
-
|
111
|
-
|
112
|
-
|
113
|
-
db.
|
114
|
-
|
115
|
-
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
|
209
|
+
assert_raise(ArgumentError) {
|
210
|
+
@@db.get_radical('犭')
|
211
|
+
}
|
212
|
+
assert_raise(ArgumentError) {
|
213
|
+
@@db.get_radical('h')
|
214
|
+
}
|
215
|
+
assert_raise(ArgumentError) {
|
216
|
+
@@db.get_radical('猫犬')
|
217
|
+
}
|
218
|
+
assert_raise(ArgumentError) {
|
219
|
+
@@db.get_radical
|
220
|
+
}
|
221
|
+
assert_raise(ArgumentError) {
|
222
|
+
@@db.get_radical('動', '詞')
|
223
|
+
}
|
224
|
+
end
|
225
|
+
|
226
|
+
def test_get_reading
|
227
|
+
#TODO: May not play well with other data sources
|
228
|
+
cat = @@db.get_reading('猫').reading
|
229
|
+
assert cat.size>=2
|
230
|
+
['ねこ', 'ビョウ'].each {|r|
|
231
|
+
assert cat.include?(r), "contains #{r}"
|
232
|
+
}
|
233
|
+
|
234
|
+
rich = @@db.get_reading('富')
|
235
|
+
assert rich.reading.size>=2
|
236
|
+
['とみ', 'フウ'].each {|r|
|
237
|
+
assert rich.reading.include?(r), "contains #{r}"
|
238
|
+
}
|
239
|
+
assert rich.name_reading.size>=2
|
240
|
+
['とん', 'ふっ'].each {|r|
|
241
|
+
assert rich.name_reading.include?(r), "contains #{r}"
|
242
|
+
}
|
243
|
+
|
244
|
+
assert_raise(ArgumentError) {
|
245
|
+
@@db.get_reading('犭')
|
246
|
+
}
|
247
|
+
assert_raise(ArgumentError) {
|
248
|
+
@@db.get_reading('h')
|
249
|
+
}
|
250
|
+
assert_raise(ArgumentError) {
|
251
|
+
@@db.get_reading('猫犬')
|
252
|
+
}
|
253
|
+
assert_raise(ArgumentError) {
|
254
|
+
@@db.get_reading
|
255
|
+
}
|
256
|
+
assert_raise(ArgumentError) {
|
257
|
+
@@db.get_reading('動', '詞')
|
258
|
+
}
|
259
|
+
end
|
260
|
+
|
261
|
+
def test_get_meaning
|
262
|
+
#TODO: May not play well with other data sources
|
263
|
+
pull = @@db.get_meaning('引')
|
264
|
+
assert pull.size>=3
|
265
|
+
['pull', 'tug', 'refer to'].each {|r|
|
266
|
+
assert pull.include?(r), "contains #{r}"
|
267
|
+
}
|
268
|
+
|
269
|
+
comp = @@db.get_meaning('以')
|
270
|
+
assert comp.size>=3
|
271
|
+
['by means of', 'because', 'in view of'].each {|r|
|
272
|
+
assert comp.include?(r), "contains #{r}"
|
273
|
+
}
|
274
|
+
|
275
|
+
assert_raise(ArgumentError) {
|
276
|
+
@@db.get_meaning('犭')
|
277
|
+
}
|
278
|
+
assert_raise(ArgumentError) {
|
279
|
+
@@db.get_meaning('h')
|
280
|
+
}
|
281
|
+
assert_raise(ArgumentError) {
|
282
|
+
@@db.get_meaning('猫犬')
|
283
|
+
}
|
284
|
+
assert_raise(ArgumentError) {
|
285
|
+
@@db.get_meaning
|
286
|
+
}
|
287
|
+
assert_raise(ArgumentError) {
|
288
|
+
@@db.get_meaning('動', '詞')
|
289
|
+
}
|
290
|
+
end
|
291
|
+
|
292
|
+
def test_is_kanji?
|
293
|
+
assert @@db.is_kanji?('猫')
|
294
|
+
assert @@db.is_kanji?('犬')
|
295
|
+
assert @@db.is_kanji?('富')
|
296
|
+
assert @@db.is_kanji?('夢')
|
297
|
+
assert @@db.is_kanji?('田')
|
298
|
+
assert (not @@db.is_kanji?('犭'))
|
299
|
+
assert (not @@db.is_kanji?('t'))
|
300
|
+
assert (not @@db.is_kanji?(''))
|
301
|
+
assert (not @@db.is_kanji?('犬猫'))
|
302
|
+
assert_raise(ArgumentError) {
|
303
|
+
@@db.is_kanji?
|
304
|
+
}
|
305
|
+
assert_raise(ArgumentError) {
|
306
|
+
@@db.is_kanji?('犬','猫')
|
307
|
+
}
|
308
|
+
end
|
309
|
+
|
310
|
+
def test_is_radical?
|
311
|
+
assert @@db.is_radical?('犭')
|
312
|
+
assert @@db.is_radical?('犬')
|
313
|
+
assert @@db.is_radical?('田')
|
314
|
+
assert (not @@db.is_radical?('富'))
|
315
|
+
assert (not @@db.is_radical?('t'))
|
316
|
+
assert (not @@db.is_radical?('夢'))
|
317
|
+
assert (not @@db.is_radical?(''))
|
318
|
+
assert (not @@db.is_radical?('犬田'))
|
319
|
+
assert_raise(ArgumentError) {
|
320
|
+
@@db.is_radical?
|
321
|
+
}
|
322
|
+
assert_raise(ArgumentError) {
|
323
|
+
@@db.is_radical?('犬','田')
|
324
|
+
}
|
325
|
+
end
|
326
|
+
|
327
|
+
end
|
328
|
+
|
329
|
+
|
330
|
+
if $0 == __FILE__
|
331
|
+
require 'test/unit/ui/console/testrunner'
|
332
|
+
results=[]
|
333
|
+
db=KLookup::Database
|
120
334
|
puts
|
121
|
-
|
335
|
+
puts "= Database_Test"
|
336
|
+
# Just use FlatFile for the moment
|
337
|
+
#[:FlatFile].each {|h|
|
338
|
+
db.constants.each {|h|
|
339
|
+
handler = "#{db.to_s}::#{h}"
|
340
|
+
next unless eval(handler).superclass == db
|
341
|
+
puts
|
342
|
+
puts "== Handler: #{handler}"
|
343
|
+
Database_Test.set_handler(eval(handler)) # Database class
|
344
|
+
results << [handler, Test::Unit::UI::Console::TestRunner.run(Database_Test)]
|
345
|
+
puts
|
346
|
+
}
|
122
347
|
|
123
|
-
results.each {|p|
|
124
|
-
|
125
|
-
|
126
|
-
|
127
|
-
}
|
348
|
+
results.each {|p|
|
349
|
+
h,r=p
|
350
|
+
puts "#{r.passed? ? 'PASS' : 'FAIL'} : #{h}"
|
351
|
+
puts (" %s" % r.to_s) unless r.passed?
|
352
|
+
}
|
353
|
+
end
|
@@ -0,0 +1,89 @@
|
|
1
|
+
=begin
|
2
|
+
|
3
|
+
test/runicode_test.rb
|
4
|
+
|
5
|
+
Copyright © Tom Adams 2006
|
6
|
+
|
7
|
+
This programme is free software.
|
8
|
+
You can distribute/modify this program under
|
9
|
+
the terms of the Ruby License.
|
10
|
+
|
11
|
+
=end
|
12
|
+
|
13
|
+
require 'runicode'
|
14
|
+
|
15
|
+
require 'test/unit'
|
16
|
+
|
17
|
+
# RUnicode tests
|
18
|
+
class RUnicode_Test < Test::Unit::TestCase
|
19
|
+
def test_all
|
20
|
+
str = "hello ÂÅ¿ 今日は ���"
|
21
|
+
nstr = ""
|
22
|
+
str.each_codepoint {|c| nstr << c.chr}
|
23
|
+
assert str == nstr, 'Testcase equals testcase.'
|
24
|
+
end
|
25
|
+
|
26
|
+
def test_string_codepoints
|
27
|
+
str = "hello ÂÅ¿ 今日は ���"
|
28
|
+
strcp = []
|
29
|
+
str.each_codepoint {|c| strcp << c}
|
30
|
+
assert str.codepoints == strcp, 'codepoints and each_codepoints give the same values'
|
31
|
+
end
|
32
|
+
|
33
|
+
def test_integer_chr
|
34
|
+
codepoint = 0x00110000 # This is one higher than the highest codepoint
|
35
|
+
begin
|
36
|
+
codepoint.chr
|
37
|
+
assert false, 'Failed to raise exception.'
|
38
|
+
rescue Exception
|
39
|
+
assert $!.is_a?(RangeError), 'Raised correct exception.'
|
40
|
+
end
|
41
|
+
assert (codepoint-1).chr.is_a?(String)
|
42
|
+
end
|
43
|
+
|
44
|
+
#The Unicode Standard, version 4.0--online edition.
|
45
|
+
#Section 3.9, D36.
|
46
|
+
def test_d36
|
47
|
+
# Example strings
|
48
|
+
cp = [0x004D, 0x0430, 0x4E8C, 0x10302]
|
49
|
+
str = [0x4D, 0xD0, 0xB0, 0xE4, 0xBA, 0x8C, 0xF0, 0x90, 0x8C, 0x82]
|
50
|
+
|
51
|
+
new_cp = ''
|
52
|
+
cp.each {|c| new_cp << c.chr}
|
53
|
+
new_str = "%c%c%c%c%c%c%c%c%c%c" % str
|
54
|
+
|
55
|
+
assert new_cp == new_str, 'Strings match.'
|
56
|
+
|
57
|
+
# Table 3-6
|
58
|
+
|
59
|
+
# Non-shortest form
|
60
|
+
#Covered by previous section
|
61
|
+
|
62
|
+
# Surrogate pairs
|
63
|
+
cprange = 0xD800..0xDFFF
|
64
|
+
cprange.each {|cp|
|
65
|
+
begin
|
66
|
+
cp.chr
|
67
|
+
assert false, ('Exception not thrown for U+%04X' % cp)
|
68
|
+
rescue RangeError
|
69
|
+
end
|
70
|
+
}
|
71
|
+
|
72
|
+
# Extra test cases mentioned around D36
|
73
|
+
|
74
|
+
begin
|
75
|
+
# 0b11000000 0b10101111
|
76
|
+
("%c%c" % [0xC0, 0xAF]).codepoints
|
77
|
+
assert false, 'Exception not thrown for invalid 2-byte construct'
|
78
|
+
rescue IOError
|
79
|
+
end
|
80
|
+
begin
|
81
|
+
# 0b11100000 0b10011111 0b10011111
|
82
|
+
("%c%c%c" % [0xE0, 0x9F, 0x80]).codepoints
|
83
|
+
assert false, 'Exception not thrown for invalid 3-byte construct'
|
84
|
+
rescue IOError
|
85
|
+
end
|
86
|
+
# This one should succeed
|
87
|
+
("%c%c%c%c" % [0xF4, 0x80, 0x83, 0x92]).codepoints
|
88
|
+
end
|
89
|
+
end
|
data/test/suite.rb
CHANGED
@@ -10,12 +10,8 @@
|
|
10
10
|
|
11
11
|
=end
|
12
12
|
|
13
|
-
|
14
|
-
|
15
|
-
rescue LoadError
|
16
|
-
end
|
17
|
-
|
18
|
-
require 'database_test.rb'
|
13
|
+
require 'runicode_test'
|
14
|
+
require 'database_test'
|
19
15
|
|
20
16
|
require 'klookup'
|
21
17
|
require 'test/unit'
|
@@ -25,13 +21,13 @@ class Lookup_Test < Test::Unit::TestCase
|
|
25
21
|
|
26
22
|
# Check classes
|
27
23
|
def test_radical_type
|
28
|
-
|
29
|
-
|
24
|
+
assert_kind_of Array, KLookup::Lookup::Radical.strokes, 'KLookup::Lookup::Radical.strokes is an Array'
|
25
|
+
assert_kind_of KLookup::Lookup::Radical, KLookup::Lookup::Radical.new('田'), 'KLookup::Lookup::Radical initilaisation works'
|
30
26
|
end
|
31
27
|
|
32
28
|
# Check to_s behaviour
|
33
29
|
def test_radical_to_s
|
34
|
-
|
30
|
+
assert_equal KLookup::Lookup::Radical.new('田').to_s, '田', 'A field is a field.'
|
35
31
|
end
|
36
32
|
|
37
33
|
def test_radical_list
|
@@ -41,8 +37,8 @@ class Lookup_Test < Test::Unit::TestCase
|
|
41
37
|
|
42
38
|
# Initialisation should work
|
43
39
|
def test_kanji_to_s
|
44
|
-
|
45
|
-
|
40
|
+
assert_equal KLookup::Lookup::Kanji.new('猫').to_s, '猫', 'Cat.'
|
41
|
+
assert_equal KLookup::Lookup::Kanji.new('栗').to_s, '栗', 'Chestnut.'
|
46
42
|
end
|
47
43
|
|
48
44
|
# Lookups should work
|
@@ -62,27 +58,25 @@ class Lookup_Test < Test::Unit::TestCase
|
|
62
58
|
# Checks stroke count works
|
63
59
|
def test_kanji_lookup_stroke
|
64
60
|
# Unmatching stroke counts should result in empty lists
|
65
|
-
|
66
|
-
|
61
|
+
assert_equal KLookup::Lookup::Kanji.lookup(:stroke=>10, :radical=>[KLookup::Lookup::Radical.new('艹'), KLookup::Lookup::Radical.new('犭'), KLookup::Lookup::Radical.new('田')]), [], '10 strokes for grass, left-dog, and field is impossible.'
|
62
|
+
assert_equal KLookup::Lookup::Kanji.lookup(:stroke=>12, :radical=>[KLookup::Lookup::Radical.new('艹'), KLookup::Lookup::Radical.new('犭'), KLookup::Lookup::Radical.new('田')]), [], '12 strokes for grass, left-dog, and field results in no characters.'
|
67
63
|
end
|
68
64
|
|
69
65
|
def test_kanji_radicals
|
70
66
|
cat=KLookup::Lookup::Kanji.new('猫').radicals
|
71
67
|
catr=[KLookup::Lookup::Radical.new('艹'), KLookup::Lookup::Radical.new('犭'), KLookup::Lookup::Radical.new('田')]
|
72
|
-
|
73
|
-
assert false, 'KLookup::Lookup::Kanji#radicals works fine.'
|
74
|
-
end
|
68
|
+
assert (cat.all? {|r| catr.include? r } and cat.size==catr.size), 'KLookup::Lookup::Kanji#radicals works fine.'
|
75
69
|
end
|
76
70
|
|
71
|
+
# TODO: Not compatible with non-KANJIDIC data sources
|
77
72
|
def test_kanji_meaning
|
78
73
|
pull = KLookup::Lookup::Kanji.new('引')
|
79
|
-
|
74
|
+
assert_equal pull.meaning, ['pull','tug','jerk','admit','install','quote',
|
80
75
|
'refer to']
|
81
76
|
origin = KLookup::Lookup::Kanji.new('元')
|
82
|
-
|
77
|
+
assert_equal origin.meaning, ['beginning','former time','origin']
|
83
78
|
i = KLookup::Lookup::Kanji.new('以')
|
84
|
-
|
85
|
-
i.to_s
|
79
|
+
assert_equal i.meaning,['by means of','because','in view of','compared with']
|
86
80
|
end
|
87
81
|
|
88
82
|
def test_kanji_reading
|
@@ -92,30 +86,21 @@ class Lookup_Test < Test::Unit::TestCase
|
|
92
86
|
end
|
93
87
|
|
94
88
|
def test_multiple_kanji
|
95
|
-
|
96
|
-
|
97
|
-
|
98
|
-
rescue Exception
|
99
|
-
assert $!.is_a?(ArgumentError), 'Raised correct exception.'
|
100
|
-
end
|
89
|
+
assert_raise(ArgumentError) {
|
90
|
+
KLookup::Lookup::Kanji.new('馬鹿')
|
91
|
+
}
|
101
92
|
end
|
102
93
|
|
103
94
|
def test_un_kanji
|
104
|
-
|
105
|
-
|
106
|
-
|
107
|
-
rescue ArgumentError
|
108
|
-
# Win
|
109
|
-
end
|
95
|
+
assert_raise(ArgumentError) {
|
96
|
+
KLookup::Lookup::Kanji.new('k')
|
97
|
+
}
|
110
98
|
end
|
111
99
|
|
112
100
|
def test_un_radical
|
113
|
-
|
114
|
-
|
115
|
-
|
116
|
-
rescue ArgumentError
|
117
|
-
# Win
|
118
|
-
end
|
101
|
+
assert_raise(ArgumentError) {
|
102
|
+
KLookup::Lookup::Radical.new('r')
|
103
|
+
}
|
119
104
|
end
|
120
105
|
|
121
106
|
def test_exist
|
@@ -191,28 +176,57 @@ class Lookup_Test < Test::Unit::TestCase
|
|
191
176
|
assert (look.include?(cat) and not look.include?(dog)),
|
192
177
|
'true in block and reading'
|
193
178
|
end
|
179
|
+
|
180
|
+
def test_kanji_stroke_count
|
181
|
+
assert_equal KLookup::Lookup::Kanji.new('猫').stroke_count, 11
|
182
|
+
assert_equal KLookup::Lookup::Kanji.new('犬').stroke_count, 4
|
183
|
+
end
|
184
|
+
|
185
|
+
def test_radical_stroke_count
|
186
|
+
assert_equal KLookup::Lookup::Radical.new('犬').stroke_count, 4
|
187
|
+
assert_equal KLookup::Lookup::Radical.new('犭').stroke_count, 3
|
188
|
+
end
|
194
189
|
end
|
195
190
|
|
191
|
+
if $0 == __FILE__
|
192
|
+
require 'test/unit/ui/console/testrunner'
|
193
|
+
results=[]
|
194
|
+
db_results=[]
|
195
|
+
db=KLookup::Database
|
196
|
+
puts
|
197
|
+
|
198
|
+
db.constants.each {|h|
|
199
|
+
handler = "#{db.to_s}::#{h}"
|
200
|
+
next unless eval(handler).superclass == db
|
201
|
+
puts
|
202
|
+
puts "= Handler: #{handler}"
|
203
|
+
Database_Test.set_handler(eval(handler)) # Database class
|
204
|
+
db_results << [handler,
|
205
|
+
Test::Unit::UI::Console::TestRunner.run(Database_Test)]
|
206
|
+
|
207
|
+
KLookup::Lookup.handler = eval(handler)
|
208
|
+
results << [handler,
|
209
|
+
Test::Unit::UI::Console::TestRunner.run(Lookup_Test)]
|
210
|
+
puts
|
211
|
+
}
|
196
212
|
|
197
|
-
require 'test/unit/ui/console/testrunner'
|
198
|
-
results=[]
|
199
|
-
db=KLookup::Database
|
200
|
-
puts
|
201
|
-
puts "= Lookup_Test"
|
202
|
-
# Just use FlatFile for the moment
|
203
|
-
#[:FlatFile].each {|h|
|
204
|
-
db.constants.each {|h|
|
205
|
-
handler = "#{db.to_s}::#{h}"
|
206
|
-
next unless eval(handler).superclass == db
|
207
213
|
puts
|
208
|
-
puts "
|
209
|
-
|
210
|
-
|
214
|
+
puts "= RUnicode_Test"
|
215
|
+
runicode_results = Test::Unit::UI::Console::TestRunner.run(RUnicode_Test)
|
216
|
+
puts "#{runicode_results.passed? ? 'PASS' : 'FAIL'}"
|
217
|
+
puts ("\t%s" % runicode_results.to_s) unless runicode_results.passed?
|
218
|
+
|
211
219
|
puts
|
212
|
-
|
220
|
+
puts "= Database_Test"
|
221
|
+
db_results.each {|h,r|
|
222
|
+
puts "#{r.passed? ? 'PASS' : 'FAIL'}\t: #{h}"
|
223
|
+
puts ("\t%s" % r.to_s) unless r.passed?
|
224
|
+
}
|
213
225
|
|
214
|
-
|
215
|
-
|
216
|
-
|
217
|
-
|
218
|
-
|
226
|
+
puts
|
227
|
+
puts "= Lookup_Test"
|
228
|
+
results.each {|h,r|
|
229
|
+
puts "#{r.passed? ? 'PASS' : 'FAIL'}\t: #{h}"
|
230
|
+
puts ("\t%s" % r.to_s) unless r.passed?
|
231
|
+
}
|
232
|
+
end
|
metadata
CHANGED
@@ -3,8 +3,8 @@ rubygems_version: 0.9.2
|
|
3
3
|
specification_version: 1
|
4
4
|
name: klookup
|
5
5
|
version: !ruby/object:Gem::Version
|
6
|
-
version: 0.
|
7
|
-
date: 2007-
|
6
|
+
version: "0.3"
|
7
|
+
date: 2007-03-01 00:00:00 +00:00
|
8
8
|
summary: A set of kanji lookup tools and a library.
|
9
9
|
require_paths:
|
10
10
|
- lib
|
@@ -12,7 +12,7 @@ email: tom@holizz.com
|
|
12
12
|
homepage: http://klookup.rubyforge.org/
|
13
13
|
rubyforge_project: klookup
|
14
14
|
description: A character dictionary for Japanese kanji.
|
15
|
-
autorequire:
|
15
|
+
autorequire: klookup
|
16
16
|
default_executable: cklookup
|
17
17
|
bindir: bin
|
18
18
|
has_rdoc: true
|
@@ -29,22 +29,27 @@ post_install_message:
|
|
29
29
|
authors:
|
30
30
|
- Tom Adams
|
31
31
|
files:
|
32
|
+
- data/klookup/data.db
|
32
33
|
- data/klookup/kanjidic
|
33
34
|
- data/klookup/newradkfile
|
34
|
-
- lib/
|
35
|
+
- lib/runicode.rb
|
35
36
|
- lib/klookup
|
36
|
-
- lib/klookup/
|
37
|
-
- lib/klookup/
|
37
|
+
- lib/klookup/database_sqlite.rb
|
38
|
+
- lib/klookup/lookup_kanji.rb
|
38
39
|
- lib/klookup/database.rb
|
39
|
-
- lib/klookup/
|
40
|
-
- lib/klookup/database_flatfile_radk.rb
|
41
|
-
- lib/klookup/database_unihan.rb
|
40
|
+
- lib/klookup/lookup.rb
|
42
41
|
- lib/klookup/database_flatfile_kanjidic.rb
|
42
|
+
- lib/klookup/database_unihan.rb
|
43
|
+
- lib/klookup/database_flatfile_radk.rb
|
44
|
+
- lib/klookup/lookup_radical.rb
|
43
45
|
- lib/klookup/database_flatfile.rb
|
44
|
-
- lib/
|
46
|
+
- lib/runicode
|
47
|
+
- lib/runicode/utf8.rb
|
48
|
+
- lib/klookup.rb
|
45
49
|
test_files:
|
46
|
-
- test/suite.rb
|
47
50
|
- test/database_test.rb
|
51
|
+
- test/runicode_test.rb
|
52
|
+
- test/suite.rb
|
48
53
|
rdoc_options:
|
49
54
|
- - --main
|
50
55
|
- KLookup
|
@@ -61,11 +66,11 @@ requirements: []
|
|
61
66
|
|
62
67
|
dependencies:
|
63
68
|
- !ruby/object:Gem::Dependency
|
64
|
-
name:
|
69
|
+
name: sqlite-ruby
|
65
70
|
version_requirement:
|
66
71
|
version_requirements: !ruby/object:Gem::Version::Requirement
|
67
72
|
requirements:
|
68
73
|
- - ">="
|
69
74
|
- !ruby/object:Gem::Version
|
70
|
-
version:
|
75
|
+
version: 2.2.3
|
71
76
|
version:
|
@@ -1,38 +0,0 @@
|
|
1
|
-
=begin
|
2
|
-
|
3
|
-
lib/klookup/database_flatfile.rb
|
4
|
-
|
5
|
-
Copyright © Tom Adams 2006
|
6
|
-
|
7
|
-
This programme is free software.
|
8
|
-
You can distribute/modify this program under
|
9
|
-
the terms of the Ruby License.
|
10
|
-
|
11
|
-
=end
|
12
|
-
|
13
|
-
# A singleton class to abstract RadK and KanjiDic.
|
14
|
-
class KLookup::Database::QuickFile < KLookup::Database
|
15
|
-
|
16
|
-
require 'singleton'
|
17
|
-
include Singleton
|
18
|
-
|
19
|
-
def radical_stroke_count
|
20
|
-
end
|
21
|
-
def find_radical(opts)
|
22
|
-
end
|
23
|
-
def find_kanji(opts)
|
24
|
-
end
|
25
|
-
def get_stroke_count(character)
|
26
|
-
end
|
27
|
-
def get_radical(character)
|
28
|
-
end
|
29
|
-
def get_reading(character)
|
30
|
-
end
|
31
|
-
def get_meaning(character)
|
32
|
-
end
|
33
|
-
def is_kanji?(character)
|
34
|
-
end
|
35
|
-
def is_radical?(character)
|
36
|
-
end
|
37
|
-
|
38
|
-
end
|