pragmatic_tokenizer 0.3.2 → 0.3.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/pragmatic_tokenizer/tokenizer.rb +19 -15
- data/lib/pragmatic_tokenizer/version.rb +1 -1
- 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: 93070f0374fe808125850e652cb0f05cdd262c3e
|
|
4
|
+
data.tar.gz: 0e69cfc518e9b734ab35e47d7eb0d656aaa22a76
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: e96d74097ee19c69c03952341be97f425200ea056dabd0b36dfae4387df78ca1920e521aaad1c28aef0e3d07b35d68abd21b54d7e21fcfc110c873b1ee319449
|
|
7
|
+
data.tar.gz: 908a93161d227b7cdca4208157a339c12c075b416ceed0a59757a9227ebde77c1c87e9deae694ba2445cbd1a2dd00f8cb81a91051826de3b8596654272a4e9b4
|
|
@@ -40,21 +40,25 @@ module PragmaticTokenizer
|
|
|
40
40
|
|
|
41
41
|
def tokenize
|
|
42
42
|
return [] unless text
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
|
|
46
|
-
|
|
47
|
-
|
|
48
|
-
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
|
|
43
|
+
tokens = []
|
|
44
|
+
text.scan(/.{,10000}(?=\s|\z)/m).each do |segment|
|
|
45
|
+
tokens << downcase_tokens(
|
|
46
|
+
cleaner(
|
|
47
|
+
remove_short_tokens(
|
|
48
|
+
delete_numbers(
|
|
49
|
+
delete_roman_numerals(
|
|
50
|
+
find_contractions(
|
|
51
|
+
delete_stop_words(
|
|
52
|
+
remove_punctuation(
|
|
53
|
+
split_at_middle_period_1(
|
|
54
|
+
split_at_middle_period_2(
|
|
55
|
+
split_beginning_period(
|
|
56
|
+
shift_no_spaces_between_sentences(
|
|
57
|
+
split_at_forward_slash(
|
|
58
|
+
processor.new(language: language_module).process(text: segment)
|
|
59
|
+
))))))))))))).reject { |t| t.empty? }
|
|
60
|
+
end
|
|
61
|
+
tokens.flatten
|
|
58
62
|
end
|
|
59
63
|
|
|
60
64
|
def domains
|