namae 0.9.3 → 0.10.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.travis.yml +5 -0
- data/Gemfile +2 -2
- data/features/lists.feature +36 -2
- data/lib/namae/parser.rb +10 -5
- data/lib/namae/parser.y +10 -5
- data/lib/namae/version.rb +2 -2
- data/namae.gemspec +3 -3
- data/spec/namae/parser_spec.rb +21 -0
- metadata +3 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 7e3498b418afe338293a9fe9c7b4c8747ee014b2
|
4
|
+
data.tar.gz: cac2386cd67b385330b50a8d722429100020b2e6
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: a2001bf45ca48aa8d9d1a8f31143a3687f5013ffa4e8be7837c7efa08a5acb9257cd8e7685a0ee19f89a49d8e4bf841a596cc99e734087d6bb32828c025b0e34
|
7
|
+
data.tar.gz: e7b62fc3a1278938f42e5fcee152cf47ba06e5378f3bedef6bc238d3983a11d2ffc25bc7ec6c8dd90655dc6ca29f976d62e2c3dd710d6cd0700056481244f1d3
|
data/.travis.yml
CHANGED
data/Gemfile
CHANGED
@@ -21,8 +21,8 @@ group :optional do
|
|
21
21
|
end
|
22
22
|
|
23
23
|
group :debug do
|
24
|
-
gem 'debugger', '~>1.6', :platform => [:
|
25
|
-
gem 'byebug', '~>3.5', :platform =>
|
24
|
+
gem 'debugger', '~>1.6', :platform => [:mri_19]
|
25
|
+
gem 'byebug', '~>3.5', :platform => :mri if RUBY_VERSION > '2.0'
|
26
26
|
gem 'rubinius-compiler', '~>2.0', :platform => :rbx
|
27
27
|
gem 'rubinius-debugger', '~>2.0', :platform => :rbx
|
28
28
|
end
|
data/features/lists.feature
CHANGED
@@ -30,6 +30,22 @@ Feature: Parse a list of names
|
|
30
30
|
| Dennis | Ritchie |
|
31
31
|
| Donald | Knuth |
|
32
32
|
|
33
|
+
@list
|
34
|
+
Scenario: A list of names separated by semicolons
|
35
|
+
When I parse the names "John D. Smith; Jack R. Johnson; Emily Tanner"
|
36
|
+
Then there should be 3 names
|
37
|
+
And the names should be:
|
38
|
+
| given | family |
|
39
|
+
| John D. | Smith |
|
40
|
+
| Jack R. | Johnson |
|
41
|
+
| Emily | Tanner |
|
42
|
+
When I parse the names "Smith, John D.; Johnson, Jack R.; Tanner, Emily"
|
43
|
+
Then there should be 3 names
|
44
|
+
And the names should be:
|
45
|
+
| given | family |
|
46
|
+
| John D. | Smith |
|
47
|
+
| Jack R. | Johnson |
|
48
|
+
| Emily | Tanner |
|
33
49
|
|
34
50
|
@list
|
35
51
|
Scenario: A list of sort-order names with initials separated by commas
|
@@ -51,6 +67,24 @@ Feature: Parse a list of names
|
|
51
67
|
| Dennis | Ritchie |
|
52
68
|
| Donald | Knuth |
|
53
69
|
|
70
|
+
@list
|
71
|
+
Scenario: A list of mixed names separated by semicolons, commas and 'and'
|
72
|
+
Given a parser that prefers commas as separators
|
73
|
+
When I parse the names "John D. Smith, Jack R. Johnson & Emily Tanner"
|
74
|
+
Then there should be 3 names
|
75
|
+
And the names should be:
|
76
|
+
| given | family |
|
77
|
+
| John D. | Smith |
|
78
|
+
| Jack R. | Johnson |
|
79
|
+
| Emily | Tanner |
|
80
|
+
When I parse the names "C. Foster; C. Hamel, C. Desroches"
|
81
|
+
Then there should be 3 names
|
82
|
+
And the names should be:
|
83
|
+
| given | family |
|
84
|
+
| C. | Foster |
|
85
|
+
| C. | Hamel |
|
86
|
+
| C. | Desroches |
|
87
|
+
|
54
88
|
@list
|
55
89
|
Scenario: A list of display-order names separated by commas and 'and'
|
56
90
|
Given a parser that prefers commas as separators
|
@@ -64,7 +98,7 @@ Feature: Parse a list of names
|
|
64
98
|
|
65
99
|
@list @wip
|
66
100
|
Scenario: A list of names separated by commas
|
67
|
-
|
101
|
+
Given a parser that prefers commas as separators
|
68
102
|
When I parse the names "G. Proctor, M. Cooper, P. Sanders & B. Malcom"
|
69
103
|
Then the names should be:
|
70
104
|
| given | family |
|
@@ -81,7 +115,7 @@ Feature: Parse a list of names
|
|
81
115
|
| B | Malcom |
|
82
116
|
|
83
117
|
Scenario: A list of names with particles separated by commas
|
84
|
-
|
118
|
+
Given a parser that prefers commas as separators
|
85
119
|
When I parse the names "Di Proctor, M., von Cooper, P."
|
86
120
|
Then the names should be:
|
87
121
|
| given | family |
|
data/lib/namae/parser.rb
CHANGED
@@ -23,7 +23,8 @@ module_eval(<<'...end parser.y/module_eval...', 'parser.y', 107)
|
|
23
23
|
:debug => false,
|
24
24
|
:prefer_comma_as_separator => false,
|
25
25
|
:comma => ',',
|
26
|
-
:
|
26
|
+
:stops => ',;',
|
27
|
+
:separator => /\s*(\band\b|\&|;)\s*/i,
|
27
28
|
:title => /\s*\b(sir|lord|count(ess)?|(prof|dr|md|ph\.?d)\.?)(\s+|$)/i,
|
28
29
|
:suffix => /\s*\b(JR|Jr|jr|SR|Sr|sr|[IVX]{2,})(\.|\b)/,
|
29
30
|
:appellation => /\s*\b((mrs?|ms|fr|hr)\.?|miss|herr|frau)(\s+|$)/i
|
@@ -42,6 +43,10 @@ module_eval(<<'...end parser.y/module_eval...', 'parser.y', 107)
|
|
42
43
|
options[:comma]
|
43
44
|
end
|
44
45
|
|
46
|
+
def stops
|
47
|
+
options[:stops]
|
48
|
+
end
|
49
|
+
|
45
50
|
def title
|
46
51
|
options[:title]
|
47
52
|
end
|
@@ -142,7 +147,7 @@ module_eval(<<'...end parser.y/module_eval...', 'parser.y', 107)
|
|
142
147
|
nil
|
143
148
|
when input.scan(separator)
|
144
149
|
consume_separator
|
145
|
-
when input.scan(/\s
|
150
|
+
when input.scan(/\s*#{comma}\s*/)
|
146
151
|
if @commas.zero? && !seen_full_name? || @commas == 1 && suffix?
|
147
152
|
consume_comma
|
148
153
|
else
|
@@ -156,11 +161,11 @@ module_eval(<<'...end parser.y/module_eval...', 'parser.y', 107)
|
|
156
161
|
consume_word(:SUFFIX, input.matched.strip)
|
157
162
|
when input.scan(appellation)
|
158
163
|
[:APPELLATION, input.matched.strip]
|
159
|
-
when input.scan(/((\\\w+)?\{[^\}]*\})*[[:upper:]][^\s#{
|
164
|
+
when input.scan(/((\\\w+)?\{[^\}]*\})*[[:upper:]][^\s#{stops}]*/)
|
160
165
|
consume_word(:UWORD, input.matched)
|
161
|
-
when input.scan(/((\\\w+)?\{[^\}]*\})*[[:lower:]][^\s#{
|
166
|
+
when input.scan(/((\\\w+)?\{[^\}]*\})*[[:lower:]][^\s#{stops}]*/)
|
162
167
|
consume_word(:LWORD, input.matched)
|
163
|
-
when input.scan(/(\\\w+)?\{[^\}]*\}[^\s#{
|
168
|
+
when input.scan(/(\\\w+)?\{[^\}]*\}[^\s#{stops}]*/)
|
164
169
|
consume_word(:PWORD, input.matched)
|
165
170
|
when input.scan(/('[^'\n]+')|("[^"\n]+")/)
|
166
171
|
consume_word(:NICK, input.matched[1...-1])
|
data/lib/namae/parser.y
CHANGED
@@ -114,7 +114,8 @@ require 'strscan'
|
|
114
114
|
:debug => false,
|
115
115
|
:prefer_comma_as_separator => false,
|
116
116
|
:comma => ',',
|
117
|
-
:
|
117
|
+
:stops => ',;',
|
118
|
+
:separator => /\s*(\band\b|\&|;)\s*/i,
|
118
119
|
:title => /\s*\b(sir|lord|count(ess)?|(prof|dr|md|ph\.?d)\.?)(\s+|$)/i,
|
119
120
|
:suffix => /\s*\b(JR|Jr|jr|SR|Sr|sr|[IVX]{2,})(\.|\b)/,
|
120
121
|
:appellation => /\s*\b((mrs?|ms|fr|hr)\.?|miss|herr|frau)(\s+|$)/i
|
@@ -133,6 +134,10 @@ require 'strscan'
|
|
133
134
|
options[:comma]
|
134
135
|
end
|
135
136
|
|
137
|
+
def stops
|
138
|
+
options[:stops]
|
139
|
+
end
|
140
|
+
|
136
141
|
def title
|
137
142
|
options[:title]
|
138
143
|
end
|
@@ -233,7 +238,7 @@ require 'strscan'
|
|
233
238
|
nil
|
234
239
|
when input.scan(separator)
|
235
240
|
consume_separator
|
236
|
-
when input.scan(/\s
|
241
|
+
when input.scan(/\s*#{comma}\s*/)
|
237
242
|
if @commas.zero? && !seen_full_name? || @commas == 1 && suffix?
|
238
243
|
consume_comma
|
239
244
|
else
|
@@ -247,11 +252,11 @@ require 'strscan'
|
|
247
252
|
consume_word(:SUFFIX, input.matched.strip)
|
248
253
|
when input.scan(appellation)
|
249
254
|
[:APPELLATION, input.matched.strip]
|
250
|
-
when input.scan(/((\\\w+)?\{[^\}]*\})*[[:upper:]][^\s#{
|
255
|
+
when input.scan(/((\\\w+)?\{[^\}]*\})*[[:upper:]][^\s#{stops}]*/)
|
251
256
|
consume_word(:UWORD, input.matched)
|
252
|
-
when input.scan(/((\\\w+)?\{[^\}]*\})*[[:lower:]][^\s#{
|
257
|
+
when input.scan(/((\\\w+)?\{[^\}]*\})*[[:lower:]][^\s#{stops}]*/)
|
253
258
|
consume_word(:LWORD, input.matched)
|
254
|
-
when input.scan(/(\\\w+)?\{[^\}]*\}[^\s#{
|
259
|
+
when input.scan(/(\\\w+)?\{[^\}]*\}[^\s#{stops}]*/)
|
255
260
|
consume_word(:PWORD, input.matched)
|
256
261
|
when input.scan(/('[^'\n]+')|("[^"\n]+")/)
|
257
262
|
consume_word(:NICK, input.matched[1...-1])
|
data/lib/namae/version.rb
CHANGED
data/namae.gemspec
CHANGED
@@ -2,16 +2,16 @@
|
|
2
2
|
# DO NOT EDIT THIS FILE DIRECTLY
|
3
3
|
# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
|
4
4
|
# -*- encoding: utf-8 -*-
|
5
|
-
# stub: namae 0.
|
5
|
+
# stub: namae 0.10.0 ruby lib
|
6
6
|
|
7
7
|
Gem::Specification.new do |s|
|
8
8
|
s.name = "namae"
|
9
|
-
s.version = "0.
|
9
|
+
s.version = "0.10.0"
|
10
10
|
|
11
11
|
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
12
12
|
s.require_paths = ["lib"]
|
13
13
|
s.authors = ["Sylvester Keil", "Dan Collis-Puro"]
|
14
|
-
s.date = "2015-
|
14
|
+
s.date = "2015-04-26"
|
15
15
|
s.description = " Namae (\u{540d}\u{524d}) is a parser for human names. It recognizes personal names of various cultural backgrounds and tries to split them into their component parts (e.g., given and family names, honorifics etc.). "
|
16
16
|
s.email = ["sylvester@keil.or.at", "dan@collispuro.com"]
|
17
17
|
s.extra_rdoc_files = [
|
data/spec/namae/parser_spec.rb
CHANGED
@@ -44,6 +44,27 @@ module Namae
|
|
44
44
|
end
|
45
45
|
end
|
46
46
|
|
47
|
+
describe 'when the next input is ", "' do
|
48
|
+
before { parser.send(:input).string = ', ' }
|
49
|
+
it 'returns a COMMA token' do
|
50
|
+
expect(parser.send(:next_token)).to eq([:COMMA, :COMMA])
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
describe 'when the next input is "; "' do
|
55
|
+
before { parser.send(:input).string = '; ' }
|
56
|
+
it 'returns an AND token' do
|
57
|
+
expect(parser.send(:next_token)).to eq([:AND, :AND])
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
describe 'when the next input is "foo;"' do
|
62
|
+
before { parser.send(:input).string = 'foo;' }
|
63
|
+
it 'returns an LWORD token "foo"' do
|
64
|
+
expect(parser.send(:next_token)).to eq([:LWORD, 'foo'])
|
65
|
+
end
|
66
|
+
end
|
67
|
+
|
47
68
|
describe 'when the next input is " \'foo bar\' "' do
|
48
69
|
before { parser.send(:input).string = " 'foo bar' " }
|
49
70
|
it 'returns a NICK token' do
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: namae
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.10.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Sylvester Keil
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2015-
|
12
|
+
date: 2015-04-26 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: simplecov
|
@@ -134,3 +134,4 @@ signing_key:
|
|
134
134
|
specification_version: 4
|
135
135
|
summary: Namae (名前) parses personal names and splits them into their component parts.
|
136
136
|
test_files: []
|
137
|
+
has_rdoc:
|