hebrew 0.2.0 → 0.2.1
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 +5 -5
- data/lib/hebrew.rb +26 -2
- metadata +3 -3
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
|
-
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
2
|
+
SHA256:
|
|
3
|
+
metadata.gz: '0801a90c50ccf260e20daa15b9c9691b18fc3dc6908a2221614f4c1ab6a3f453'
|
|
4
|
+
data.tar.gz: 9b4309ede2544c914b134cfdd06c81e806d2908ba41105f7799f7e3d3e25bec3
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 2e6885a12245311fa51f8610fe43c8903763251bf718b2db053c9b97deb741f64b83f5f5245dcd3a56fbcb668e614b5e284f41f287ef2278f9dc347c1f6f8ea0
|
|
7
|
+
data.tar.gz: 44dab01c3339147f11ad69567a6087d3f48680c44b226e03839a14d39c36c19fd3a39d0c2de9a0ea9ad2dd290cd63a740c0b3cec7d9f59b69a7eccf2b1d25fbd
|
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')]
|
|
@@ -18,6 +16,32 @@ HEB_UTF8_END = 1535
|
|
|
18
16
|
|
|
19
17
|
# extend String class
|
|
20
18
|
class String
|
|
19
|
+
def strip_hebrew
|
|
20
|
+
case self.encoding
|
|
21
|
+
when Encoding::UTF_8
|
|
22
|
+
strip_hebrew_utf8
|
|
23
|
+
when Encoding::WINDOWS_1255 || Encoding::CP1255
|
|
24
|
+
strip_hebrew_cp1255
|
|
25
|
+
end
|
|
26
|
+
end
|
|
27
|
+
def strip_hebrew_utf8
|
|
28
|
+
target = ''
|
|
29
|
+
self.each_codepoint {|cp|
|
|
30
|
+
unless self.class.is_codepoint_nikkud_utf8(cp) or self.is_hebrew_codepoint_utf8(cp)
|
|
31
|
+
target << cp.chr(Encoding::UTF_8)
|
|
32
|
+
end
|
|
33
|
+
}
|
|
34
|
+
return target
|
|
35
|
+
end
|
|
36
|
+
def strip_hebrew_cp1255
|
|
37
|
+
target = ''.force_encoding('windows-1255')
|
|
38
|
+
self.each_codepoint {|cp|
|
|
39
|
+
unless self.class.is_codepoint_nikkud_cp1255(cp) or self.is_hebrew_codepoint_cp1255(cp)
|
|
40
|
+
target << cp.chr(Encoding::CP1255) # is there a neater way?
|
|
41
|
+
end
|
|
42
|
+
}
|
|
43
|
+
return target
|
|
44
|
+
end
|
|
21
45
|
# this will return the string, stripped of any Hebrew nikkud characters
|
|
22
46
|
def strip_nikkud
|
|
23
47
|
case self.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: 0.2.
|
|
4
|
+
version: 0.2.1
|
|
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: 2019-09-05 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
|
|
@@ -37,7 +37,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
37
37
|
version: '0'
|
|
38
38
|
requirements: []
|
|
39
39
|
rubyforge_project:
|
|
40
|
-
rubygems_version: 2.
|
|
40
|
+
rubygems_version: 2.7.7
|
|
41
41
|
signing_key:
|
|
42
42
|
specification_version: 4
|
|
43
43
|
summary: Hebrew string manipulation
|