twfilter 0.1.0
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 +7 -0
- data/CHANGELOG.md +37 -0
- data/LICENSE +19 -0
- data/NOTICES.md +93 -0
- data/README.md +364 -0
- data/lib/twfilter/block.rb +36 -0
- data/lib/twfilter/checks/erhua.rb +40 -0
- data/lib/twfilter/checks/lexicon.rb +83 -0
- data/lib/twfilter/checks/script.rb +71 -0
- data/lib/twfilter/checks/shape.rb +40 -0
- data/lib/twfilter/checks/wenyan.rb +32 -0
- data/lib/twfilter/data/MANIFEST.json +85 -0
- data/lib/twfilter/data/cantonese.txt +17 -0
- data/lib/twfilter/data/converted_orthography.txt +14 -0
- data/lib/twfilter/data/erhua_headed.txt +14 -0
- data/lib/twfilter/data/erhua_tailed.txt +36 -0
- data/lib/twfilter/data/foreign_topics.txt +80 -0
- data/lib/twfilter/data/mainland_exceptions.tsv +6 -0
- data/lib/twfilter/data/mainland_hard.tsv +149 -0
- data/lib/twfilter/data/mainland_soft.tsv +38 -0
- data/lib/twfilter/data/moe_common.txt +4808 -0
- data/lib/twfilter/data/moe_exception.txt +12 -0
- data/lib/twfilter/data/moe_rare.txt +18356 -0
- data/lib/twfilter/data/moe_secondary.txt +6343 -0
- data/lib/twfilter/data/regional_hard.tsv +19 -0
- data/lib/twfilter/data/simplified_only.txt +3785 -0
- data/lib/twfilter/data/taiwan_grammar.txt +20 -0
- data/lib/twfilter/data/taiwan_lexicon.txt +51 -0
- data/lib/twfilter/data/taiwan_markers.txt +66 -0
- data/lib/twfilter/data/taiwan_particles.txt +7 -0
- data/lib/twfilter/data/variants_used_in_taiwan.txt +16 -0
- data/lib/twfilter/data/wenyan.txt +4 -0
- data/lib/twfilter/errors.rb +12 -0
- data/lib/twfilter/evidence.rb +44 -0
- data/lib/twfilter/finding.rb +42 -0
- data/lib/twfilter/han.rb +30 -0
- data/lib/twfilter/policy.rb +68 -0
- data/lib/twfilter/punctuation.rb +106 -0
- data/lib/twfilter/sentences.rb +32 -0
- data/lib/twfilter/subject.rb +28 -0
- data/lib/twfilter/tables.rb +140 -0
- data/lib/twfilter/version.rb +5 -0
- data/lib/twfilter.rb +57 -0
- data/licenses/APACHE-2.0.txt +202 -0
- data/sig/twfilter.rbs +215 -0
- metadata +137 -0
|
@@ -0,0 +1,19 @@
|
|
|
1
|
+
唔係 不是 0 13957
|
|
2
|
+
唔好 不要 0 4235
|
|
3
|
+
唔該 謝謝 0 2759
|
|
4
|
+
同埋 以及 0 2067
|
|
5
|
+
唔知 不知道 0 1972
|
|
6
|
+
屋苑 社區 0 1426
|
|
7
|
+
俾我 給我 0 1247
|
|
8
|
+
落到實處 落實 0 932
|
|
9
|
+
邊個 哪個 0 684
|
|
10
|
+
俾你 給你 0 674
|
|
11
|
+
咩事 什麼事 0 351
|
|
12
|
+
士多啤梨 草莓 0 68
|
|
13
|
+
雪櫃 冰箱 0 67
|
|
14
|
+
沙律 沙拉 0 34
|
|
15
|
+
三文治 三明治 0 29
|
|
16
|
+
車厘子 櫻桃 0 14
|
|
17
|
+
公屋 國宅 0 9
|
|
18
|
+
居屋 國宅 0 9
|
|
19
|
+
組屋 國宅 0 9
|