hebrew 0.2.1 → 0.2.6
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/hebrew.rb +26 -0
- metadata +3 -4
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: a509e56919f2055864ca238d0ce48eee1008016ce5d374d94af15493669d8af8
|
|
4
|
+
data.tar.gz: b4dec8e825ae6dbca6c7fc9c4fe0c86e44606892c30f06b7201e3aab49929702
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: ba23fb87e55a1eba175fcbfc081ef7b9ed4ddfe554a079d4c69b52c87d676811f5f76e0c2bc417b1a998323b8dbacc9070d095060e202c0f9ab0218b9d8cd051
|
|
7
|
+
data.tar.gz: 31e495df211f42b7308d0e31b710396d7861e177d1b49a0df714661abc266fa910dfa64c50da99a7d884fdda8e4fb68d0444ffc7165576466da70d5c648e2282
|
data/lib/hebrew.rb
CHANGED
|
@@ -13,6 +13,10 @@ FIANLS_CP1255 = ["\xea".force_encoding('windows-1255'), "\xed".force_encoding('w
|
|
|
13
13
|
FINALS_UTF8 = ["\u05da", "\u05dd", "\u05df", "\u05e3", "\u05e5"]
|
|
14
14
|
HEB_UTF8_START = 1424
|
|
15
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
|
|
16
20
|
|
|
17
21
|
# extend String class
|
|
18
22
|
class String
|
|
@@ -87,6 +91,28 @@ class String
|
|
|
87
91
|
false
|
|
88
92
|
end
|
|
89
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
|
+
if c.codepoints[0] == HEB_UTF8_QUBBUTS
|
|
102
|
+
ret += 'וּ' # replace Qubbuts with vav and shuruk
|
|
103
|
+
else
|
|
104
|
+
ret += c
|
|
105
|
+
end
|
|
106
|
+
ret += 'י' if c.codepoints[0] == HEB_UTF8_XIRIK
|
|
107
|
+
ret += 'ו' if c.codepoints[0] == HEB_UTF8_XOLAM && prev_char != 'ו'
|
|
108
|
+
prev_char = c
|
|
109
|
+
end
|
|
110
|
+
return ret.gsub("\u05b4יי","\u05b4י").gsub("\u05b4י\u05bcי", "\u05b4\u05bcי") # get rid of extraneous yods possibly added because we weren't looking ahead
|
|
111
|
+
else
|
|
112
|
+
return nil # not implemented for other encodings for now.
|
|
113
|
+
end
|
|
114
|
+
end
|
|
115
|
+
|
|
90
116
|
def any_nikkud?
|
|
91
117
|
func = case self.encoding
|
|
92
118
|
when Encoding::UTF_8
|
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: 0.2.
|
|
4
|
+
version: 0.2.6
|
|
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: 2020-10-21 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
|
|
@@ -36,8 +36,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
36
36
|
- !ruby/object:Gem::Version
|
|
37
37
|
version: '0'
|
|
38
38
|
requirements: []
|
|
39
|
-
|
|
40
|
-
rubygems_version: 2.7.7
|
|
39
|
+
rubygems_version: 3.1.2
|
|
41
40
|
signing_key:
|
|
42
41
|
specification_version: 4
|
|
43
42
|
summary: Hebrew string manipulation
|