hebrew 0.1.7 → 0.2.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/lib/hebrew.rb +70 -5
- metadata +5 -6
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
|
-
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 2cc64efe3ce4523383c76a9265c8e0d015f847c1aaefacb903470ec9c295f342
|
4
|
+
data.tar.gz: e0f065db2c27e3dd0b47669abc629eb228e4f37b118db54afa128203d832e8e5
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: f5143397a2bed96cccc2aead3dee8aac7f7f28637819e1979b61cf37e1bb96712b29e6a7f1f218c6281b4bdda4e67435ce2a5f8d0195c7982bc088adfcdb9fb4
|
7
|
+
data.tar.gz: 8ec1ba901eb082f53f1d8caa1049a5e48302418c48867b11e67e945ef50ef42112e735114fae64df1e0adf0a66296de188ab59cca419779a8d650afc8026aab9
|
data/lib/hebrew.rb
CHANGED
@@ -5,9 +5,7 @@
|
|
5
5
|
|
6
6
|
# codepoints for CP1255 nikkud
|
7
7
|
NIKKUD_CP1255 = [192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 209, 210]
|
8
|
-
#NIKKUD_CP1255 = ["\xc0".force_encoding('windows-1255'), "\xc1".force_encoding('windows-1255'), "\xc2".force_encoding('windows-1255'), "\xc3".force_encoding('windows-1255'), "\xc4".force_encoding('windows-1255'), "\xc5".force_encoding('windows-1255'), "\xc6".force_encoding('windows-1255'), "\xc7".force_encoding('windows-1255'), "\xc8".force_encoding('windows-1255'), "\xc9".force_encoding('windows-1255'), "\xcb".force_encoding('windows-1255'), "\xcc".force_encoding('windows-1255'), "\xd1".force_encoding('windows-1255'), "\xd2".force_encoding('windows-1255')] # wow, this is fugly. Is there a neater way to specify CP1255 literal?
|
9
8
|
NIKKUD_UTF8 = [0x05b0, 0x05b1, 0x05b2, 0x05b3, 0x05b4, 0x05b5, 0x05b6, 0x05b7, 0x05b8, 0x05b9, 0x05bb, 0x05bc, 0x05bd, 0x05bf, 0x05c1, 0x05c2]
|
10
|
-
#NIKKUD_UTF8 = ["\u05b0", "\u05b1", "\u05b2", "\u05b3", "\u05b4", "\u05b5", "\u05b6", "\u05b7", "\u05b8", "\u05b9", "\u05bb", "\u05bc", "\u05c1", "\u05c2"]
|
11
9
|
# TODO: Mac encoding
|
12
10
|
|
13
11
|
FIANLS_CP1255 = ["\xea".force_encoding('windows-1255'), "\xed".force_encoding('windows-1255'), "\xef".force_encoding('windows-1255'), "\xf3".force_encoding('windows-1255'), "\xf5".force_encoding('windows-1255')]
|
@@ -15,9 +13,39 @@ FIANLS_CP1255 = ["\xea".force_encoding('windows-1255'), "\xed".force_encoding('w
|
|
15
13
|
FINALS_UTF8 = ["\u05da", "\u05dd", "\u05df", "\u05e3", "\u05e5"]
|
16
14
|
HEB_UTF8_START = 1424
|
17
15
|
HEB_UTF8_END = 1535
|
16
|
+
HEB_UTF8_XIRIK = 1460
|
17
|
+
HEB_UTF8_XOLAM = 1465
|
18
|
+
HEB_UTF8_QUBBUTS = 1467
|
19
|
+
HEB_UTF8_SHURUK = 1468
|
18
20
|
|
19
21
|
# extend String class
|
20
22
|
class String
|
23
|
+
def strip_hebrew
|
24
|
+
case self.encoding
|
25
|
+
when Encoding::UTF_8
|
26
|
+
strip_hebrew_utf8
|
27
|
+
when Encoding::WINDOWS_1255 || Encoding::CP1255
|
28
|
+
strip_hebrew_cp1255
|
29
|
+
end
|
30
|
+
end
|
31
|
+
def strip_hebrew_utf8
|
32
|
+
target = ''
|
33
|
+
self.each_codepoint {|cp|
|
34
|
+
unless self.class.is_codepoint_nikkud_utf8(cp) or self.is_hebrew_codepoint_utf8(cp)
|
35
|
+
target << cp.chr(Encoding::UTF_8)
|
36
|
+
end
|
37
|
+
}
|
38
|
+
return target
|
39
|
+
end
|
40
|
+
def strip_hebrew_cp1255
|
41
|
+
target = ''.force_encoding('windows-1255')
|
42
|
+
self.each_codepoint {|cp|
|
43
|
+
unless self.class.is_codepoint_nikkud_cp1255(cp) or self.is_hebrew_codepoint_cp1255(cp)
|
44
|
+
target << cp.chr(Encoding::CP1255) # is there a neater way?
|
45
|
+
end
|
46
|
+
}
|
47
|
+
return target
|
48
|
+
end
|
21
49
|
# this will return the string, stripped of any Hebrew nikkud characters
|
22
50
|
def strip_nikkud
|
23
51
|
case self.encoding
|
@@ -31,7 +59,7 @@ class String
|
|
31
59
|
target = ''.force_encoding('windows-1255')
|
32
60
|
self.each_codepoint {|cp|
|
33
61
|
unless self.class.is_codepoint_nikkud_cp1255(cp)
|
34
|
-
target
|
62
|
+
target << cp.chr(Encoding::CP1255) # is there a neater way?
|
35
63
|
end
|
36
64
|
}
|
37
65
|
return target
|
@@ -40,7 +68,7 @@ class String
|
|
40
68
|
target = ''
|
41
69
|
self.each_codepoint {|cp|
|
42
70
|
unless self.class.is_codepoint_nikkud_utf8(cp)
|
43
|
-
target
|
71
|
+
target << cp.chr(Encoding::UTF_8)
|
44
72
|
end
|
45
73
|
}
|
46
74
|
return target
|
@@ -58,6 +86,43 @@ class String
|
|
58
86
|
return false
|
59
87
|
end
|
60
88
|
end
|
89
|
+
|
90
|
+
def falsehood
|
91
|
+
false
|
92
|
+
end
|
93
|
+
|
94
|
+
# this will add matres lectionis (yods and vavs as vowels) after diacritics that denote those vowels. The result won't always be morphologically correct Hebrew, but is useful for generating mostly-likely variants users may search for, when typing inputs (almost no Hebrew users know how to produce diacritics on the keyboard).
|
95
|
+
def naive_full_nikkud
|
96
|
+
ret = ''
|
97
|
+
prev_char = nil
|
98
|
+
case self.encoding
|
99
|
+
when Encoding::UTF_8
|
100
|
+
self.each_char do |c|
|
101
|
+
ret += c
|
102
|
+
ret += 'י' if c.codepoints[0] == HEB_UTF8_XIRIK
|
103
|
+
ret += 'ו' if c.codepoints[0] == HEB_UTF8_QUBBUTS
|
104
|
+
ret += 'ו' if [HEB_UTF8_XOLAM, HEB_UTF8_SHURUK].include?(c.codepoints[0]) && prev_char != 'ו'
|
105
|
+
prev_char = c
|
106
|
+
end
|
107
|
+
return ret.gsub('יי','ִי') # get rid of extraneous yods possibly added because we weren't looking ahead
|
108
|
+
else
|
109
|
+
return nil # not implemented for other encodings for now.
|
110
|
+
end
|
111
|
+
end
|
112
|
+
|
113
|
+
def any_nikkud?
|
114
|
+
func = case self.encoding
|
115
|
+
when Encoding::UTF_8
|
116
|
+
:is_codepoint_nikkud_utf8
|
117
|
+
when Encoding::WINDOWS_1255 || Encoding::CP1255
|
118
|
+
:is_codepoint_nikkud_cp1255
|
119
|
+
else
|
120
|
+
:falsehood
|
121
|
+
end
|
122
|
+
self.each_codepoint{|cp| return true if String.send(func, cp)}
|
123
|
+
return false
|
124
|
+
end
|
125
|
+
|
61
126
|
def is_hebrew_codepoint_cp1255(cp)
|
62
127
|
return ((cp > 191 && cp < 202) or [203, 204, 209, 210].include?(cp))
|
63
128
|
end
|
@@ -77,7 +142,7 @@ class String
|
|
77
142
|
#NIKKUD_CP1255.include?(cp) # cleaner, but much slower
|
78
143
|
end
|
79
144
|
def self.is_codepoint_nikkud_utf8(cp)
|
80
|
-
return ((cp > 0x05af && cp <
|
145
|
+
return ((cp > 0x05af && cp < 0x05bd) or [0x05c1, 0x05c2].include?(cp))
|
81
146
|
#NIKKUD_UTF8.include?(cp) # cleaner, but much slower
|
82
147
|
end
|
83
148
|
# this will return true if the first parameter is a nikkud character in the encoding of the second parameter
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: hebrew
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.2.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Asaf Bartov
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2020-10-20 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
13
|
description: Some useful code to identify, transcode, and manipulate Hebrew text
|
14
14
|
email: asaf.bartov@gmail.com
|
@@ -27,17 +27,16 @@ require_paths:
|
|
27
27
|
- lib
|
28
28
|
required_ruby_version: !ruby/object:Gem::Requirement
|
29
29
|
requirements:
|
30
|
-
- -
|
30
|
+
- - ">="
|
31
31
|
- !ruby/object:Gem::Version
|
32
32
|
version: '0'
|
33
33
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
34
34
|
requirements:
|
35
|
-
- -
|
35
|
+
- - ">="
|
36
36
|
- !ruby/object:Gem::Version
|
37
37
|
version: '0'
|
38
38
|
requirements: []
|
39
|
-
|
40
|
-
rubygems_version: 2.2.1
|
39
|
+
rubygems_version: 3.1.2
|
41
40
|
signing_key:
|
42
41
|
specification_version: 4
|
43
42
|
summary: Hebrew string manipulation
|