cantonese 0.1.2 → 0.2.0
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/cantonese/scraper/word_scraper.rb +7 -4
- data/lib/cantonese/version.rb +1 -1
- data/spec/scraper/word_scraper_spec.rb +8 -2
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 4ddaa4f96c77b0c35bb61e83b2feef43a234f844
|
|
4
|
+
data.tar.gz: 5684236f0d3ba3626de4a10ebdc1ac9eeeac3734
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: a02f42b7aac35e3e2071114a868be195d592f2a93eb087f304afa058700d62664d5595160ea57d208b49bb2c3eb0f7cbc4b973b3e70b41933ee9682d87be0f81
|
|
7
|
+
data.tar.gz: efc2ba3e781a25a0a2cf72c75d52eda78298a6d0818cbbc382f1832042a240ccfce9989ba6f2a10331806eb911c40bde627e80e731f16c345fe82d0e9098cf03
|
|
@@ -30,14 +30,15 @@ module Cantonese
|
|
|
30
30
|
classified = doc.search("//*[@class = 't' and .='字音分類:']/following-sibling::td[1]").text rescue nil
|
|
31
31
|
big5 = doc.search("//*[@class = 't' and .='大五碼:']/following-sibling::td[1]").text rescue nil
|
|
32
32
|
chanjie = doc.search("//*[@class = 't' and .='倉頡碼:']/following-sibling::td[1]").text rescue nil
|
|
33
|
-
|
|
33
|
+
rank_and_frequency = doc.search("//*[@class = 't' and .='頻序 / 頻次:']/following-sibling::td[1]").text rescue nil
|
|
34
34
|
combination = doc.search("//text()[.='配搭點:']/following-sibling::a").collect{|a| a.text}
|
|
35
|
+
rank, frequency = rank_and_frequency.split("/").collect{|word| word.strip.to_i }
|
|
35
36
|
|
|
36
37
|
syllable = doc.search('//form/table[1]/tr[position()>1]').collect do |row|
|
|
37
38
|
sound = row.search("./td[1]")
|
|
38
|
-
initial = sound.xpath("./*[@color='red']").text rescue
|
|
39
|
-
final = sound.xpath("./*[@color='green']").text rescue
|
|
40
|
-
tone = sound.xpath("./*[@color='blue']").text rescue
|
|
39
|
+
initial = sound.xpath("./*[@color='red']").text rescue ""
|
|
40
|
+
final = sound.xpath("./*[@color='green']").text rescue ""
|
|
41
|
+
tone = sound.xpath("./*[@color='blue']").text rescue ""
|
|
41
42
|
sound_text = sound.text
|
|
42
43
|
pronunciation = "http://humanum.arts.cuhk.edu.hk/Lexis/lexi-can/sound/#{sound_text}.wav"
|
|
43
44
|
|
|
@@ -52,6 +53,7 @@ module Cantonese
|
|
|
52
53
|
end
|
|
53
54
|
|
|
54
55
|
{
|
|
56
|
+
:full => "#{initial}#{final}#{tone}",
|
|
55
57
|
:initial => initial,
|
|
56
58
|
:final => final,
|
|
57
59
|
:tone => tone,
|
|
@@ -68,6 +70,7 @@ module Cantonese
|
|
|
68
70
|
:classified => classified,
|
|
69
71
|
:big5 => big5,
|
|
70
72
|
:chanjie => chanjie,
|
|
73
|
+
:rank => rank,
|
|
71
74
|
:frequency => frequency,
|
|
72
75
|
:syllable => syllable,
|
|
73
76
|
:combination => combination
|
data/lib/cantonese/version.rb
CHANGED
|
@@ -15,11 +15,14 @@ describe Cantonese::Scraper::WordScraper do
|
|
|
15
15
|
|
|
16
16
|
expect(word[:big5]).to eq("A440")
|
|
17
17
|
expect(word[:chanjie]).to eq("一")
|
|
18
|
-
|
|
18
|
+
|
|
19
|
+
expect(word[:rank]).to eq(2)
|
|
20
|
+
expect(word[:frequency]).to eq(166396)
|
|
19
21
|
expect(word[:combination]).to be_a(Array)
|
|
20
22
|
expect(word[:combination]).to be_include("山")
|
|
21
23
|
|
|
22
24
|
expect(word[:syllable]).to be_a(Array)
|
|
25
|
+
expect(word[:syllable][0][:full]).to eq("jat1")
|
|
23
26
|
expect(word[:syllable][0][:initial]).to eq("j")
|
|
24
27
|
expect(word[:syllable][0][:final]).to eq("at")
|
|
25
28
|
expect(word[:syllable][0][:tone]).to eq("1")
|
|
@@ -40,17 +43,20 @@ describe Cantonese::Scraper::WordScraper do
|
|
|
40
43
|
|
|
41
44
|
expect(word[:big5]).to eq("A569")
|
|
42
45
|
expect(word[:chanjie]).to eq("一弓口")
|
|
43
|
-
expect(word[:
|
|
46
|
+
expect(word[:rank]).to eq(36)
|
|
47
|
+
expect(word[:frequency]).to eq(40754)
|
|
44
48
|
expect(word[:combination]).to be_a(Array)
|
|
45
49
|
expect(word[:combination]).to be_include("不")
|
|
46
50
|
|
|
47
51
|
expect(word[:syllable]).to be_a(Array)
|
|
52
|
+
expect(word[:syllable][0][:full]).to eq("hak1")
|
|
48
53
|
expect(word[:syllable][0][:initial]).to eq("h")
|
|
49
54
|
expect(word[:syllable][0][:final]).to eq("ak")
|
|
50
55
|
expect(word[:syllable][0][:tone]).to eq("1")
|
|
51
56
|
expect(word[:syllable][0][:examples]).to be_a(Array)
|
|
52
57
|
expect(word[:syllable][0][:examples]).to be_include("可汗")
|
|
53
58
|
|
|
59
|
+
expect(word[:syllable][1][:full]).to eq("ho2")
|
|
54
60
|
expect(word[:syllable][1][:initial]).to eq("h")
|
|
55
61
|
expect(word[:syllable][1][:final]).to eq("o")
|
|
56
62
|
expect(word[:syllable][1][:tone]).to eq("2")
|