pragmatic_tokenizer 0.1.9 → 0.1.10
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
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 4b2dd34906b6a89945200b65353a772089c2fdb2
|
|
4
|
+
data.tar.gz: dceed8cdbb9cefcd822ddf68cc99073b76aa9506
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 21d892cc075635b1d1ba42c122421bb237bbc01b35ab2068648fb8c4eb9725a2174f22b89a41976d9df06546bdf92e1d4f4f8520a409edf1d6c2c62df1faf8cc
|
|
7
|
+
data.tar.gz: 2750c610896eeb49f8218e666be12f6deeb5675fd6bef7678f826d07031fa0fba94fd5113e0473f263899f20d5e740c4117748d48621e2a51fe1c3f835275a1a
|
|
@@ -14,6 +14,7 @@ module PragmaticTokenizer
|
|
|
14
14
|
shift_special_quotes(text)
|
|
15
15
|
shift_colon(text)
|
|
16
16
|
shift_bracket(text)
|
|
17
|
+
shift_semicolon(text)
|
|
17
18
|
convert_dbl_quotes(text)
|
|
18
19
|
convert_sgl_quotes(text)
|
|
19
20
|
tokens = separate_full_stop(text.squeeze(' ').split.map { |t| convert_sym_to_punct(t.downcase) })
|
|
@@ -74,6 +75,10 @@ module PragmaticTokenizer
|
|
|
74
75
|
text.gsub!(/:/o, ' :') || text
|
|
75
76
|
end
|
|
76
77
|
|
|
78
|
+
def shift_semicolon(text)
|
|
79
|
+
text.gsub!(/([;])/o) { ' ' + $1 + ' ' } || text
|
|
80
|
+
end
|
|
81
|
+
|
|
77
82
|
def shift_ellipse(text)
|
|
78
83
|
text.gsub!(/(\.\.\.+)/o) { ' ' + $1 + ' ' } || text
|
|
79
84
|
end
|
|
@@ -65,7 +65,13 @@ module PragmaticTokenizer
|
|
|
65
65
|
|
|
66
66
|
def cleaner(tokens)
|
|
67
67
|
return tokens unless clean
|
|
68
|
-
tokens.delete_if { |t| t =~ /\A_+\z/ ||
|
|
68
|
+
tokens.delete_if { |t| t =~ /\A_+\z/ ||
|
|
69
|
+
t =~ /\A-+\z/ ||
|
|
70
|
+
PragmaticTokenizer::Languages::Common::SPECIAL_CHARACTERS.include?(t) ||
|
|
71
|
+
t =~ /\A\.{2,}\z/ || t.include?("\\") ||
|
|
72
|
+
t.length > 50 ||
|
|
73
|
+
(t.length > 1 && t =~ /[#&*+<=>@^|~]/i)
|
|
74
|
+
}
|
|
69
75
|
end
|
|
70
76
|
|
|
71
77
|
def remove_punctuation(tokens)
|