hebrew 0.1.3 → 0.1.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/lib/hebrew.rb +21 -1
- metadata +4 -4
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: cdc23d69ac6c99a5089730a3980986821a750c9b
|
4
|
+
data.tar.gz: b436b60e4093251483a256677308733488108d95
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 4bebdf8bb10c1101b93811a36d2b21ac12c76068040e02073e35bd5570b084c802c8cc4ecf0bbf23bc5663bb00c8a3ecfe67b9db9d1b9adc2ca124534c88e5b8
|
7
|
+
data.tar.gz: c66e39755a562a5ac674deba0d678c5e115a74fbb16e12d2fdb299deeab608433168a5460d62f5e8e9401510e3f1735e97adf3bb7c89a7dc382e7717547e9b39
|
data/lib/hebrew.rb
CHANGED
@@ -13,7 +13,8 @@ NIKKUD_UTF8 = [0x05b0, 0x05b1, 0x05b2, 0x05b3, 0x05b4, 0x05b5, 0x05b6, 0x05b7, 0
|
|
13
13
|
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')]
|
14
14
|
|
15
15
|
FINALS_UTF8 = []
|
16
|
-
|
16
|
+
HEB_UTF8_START = 1424
|
17
|
+
HEB_UTF8_END = 1535
|
17
18
|
# extend String class
|
18
19
|
class String
|
19
20
|
# this will return the string, stripped of any Hebrew nikkud characters
|
@@ -43,6 +44,25 @@ class String
|
|
43
44
|
}
|
44
45
|
return target
|
45
46
|
end
|
47
|
+
def any_hebrew?
|
48
|
+
case self.encoding
|
49
|
+
when Encoding::UTF_8
|
50
|
+
self.each_codepoint {|cp| return true if is_hebrew_codepoint_utf8(cp) }
|
51
|
+
return false
|
52
|
+
when Encoding::WINDOWS_1255 || Encoding::CP1255
|
53
|
+
self.each_codepoint {|cp| return true if is_hebrew_codepoint_cp1255(cp) }
|
54
|
+
return false
|
55
|
+
else
|
56
|
+
return false
|
57
|
+
end
|
58
|
+
end
|
59
|
+
def is_hebrew_codepoint_utf8(cp)
|
60
|
+
if cp >= HEB_UTF8_START && cp <= HEB_UTF8_END
|
61
|
+
return true
|
62
|
+
else
|
63
|
+
return false
|
64
|
+
end
|
65
|
+
end
|
46
66
|
# TODO: add strip_nikkud!
|
47
67
|
def is_nikkud(c)
|
48
68
|
self.class.is_nikkud_by_encoding(c, self.encoding) # delegate to class method based on instance encoding
|
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: 0.1.
|
4
|
+
version: 0.1.5
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Asaf Bartov
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2014-02-
|
11
|
+
date: 2014-02-18 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
|
@@ -27,12 +27,12 @@ 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: []
|