icu_tournament 1.1.2 → 1.2.0
Sign up to get free protection for your applications and to get access to all the features.
- data/README.rdoc +3 -8
- data/lib/icu_tournament.rb +4 -1
- data/lib/icu_tournament/federation.rb +66 -72
- data/lib/icu_tournament/player.rb +97 -103
- data/lib/icu_tournament/result.rb +82 -89
- data/lib/icu_tournament/team.rb +45 -52
- data/lib/icu_tournament/tournament.rb +153 -163
- data/lib/icu_tournament/tournament_fcsv.rb +123 -129
- data/lib/icu_tournament/tournament_krause.rb +107 -113
- data/lib/icu_tournament/tournament_sp.rb +93 -99
- data/lib/icu_tournament/util.rb +22 -41
- data/lib/icu_tournament/version.rb +3 -1
- metadata +23 -26
- data/lib/icu_tournament/name.rb +0 -274
- data/spec/name_spec.rb +0 -208
data/lib/icu_tournament/name.rb
DELETED
@@ -1,274 +0,0 @@
|
|
1
|
-
module ICU
|
2
|
-
|
3
|
-
=begin rdoc
|
4
|
-
|
5
|
-
== Names
|
6
|
-
|
7
|
-
This class exists for two main reasons:
|
8
|
-
|
9
|
-
* to normalise to a common format the different ways names are typed in practice
|
10
|
-
* to be able to match two names even if they are not exactly the same
|
11
|
-
|
12
|
-
To create a name object, supply both the first and second names separately to the constructor.
|
13
|
-
|
14
|
-
robert = ICU::Name.new(' robert j ', ' FISHER ')
|
15
|
-
|
16
|
-
Capitalisation, white space and punctuation will all be automatically corrected:
|
17
|
-
|
18
|
-
robert.name # => 'Robert J. Fischer'
|
19
|
-
robert.rname # => 'Fischer, Robert J.' (reversed name)
|
20
|
-
|
21
|
-
To avoid ambiguity when either the first or second names consist of multiple words, it is better to
|
22
|
-
supply the two separately, if known. However, the full name can be supplied alone to the constructor
|
23
|
-
and a guess will be made as to the first and last names.
|
24
|
-
|
25
|
-
bobby = ICU::Name.new(' bobby fischer ')
|
26
|
-
|
27
|
-
bobby.first # => 'Bobby'
|
28
|
-
bobby.last # => 'Fischer'
|
29
|
-
|
30
|
-
Names will match even if one is missing middle initials or if a nickname is used for one of the first names.
|
31
|
-
|
32
|
-
bobby.match(robert) # => true
|
33
|
-
|
34
|
-
Note that the class is aware of only common nicknames (e.g. _Bobby_ and _Robert_, _Bill_ and _William_, etc), not all possibilities.
|
35
|
-
|
36
|
-
Supplying the _match_ method with strings is equivalent to instantiating a Name instance with the same
|
37
|
-
strings and then matching it. So, for example the following are equivalent:
|
38
|
-
|
39
|
-
robert.match('R. J.', 'Fischer') # => true
|
40
|
-
robert.match(ICU::Name('R. J.', 'Fischer')) # => true
|
41
|
-
|
42
|
-
In those examples, the inital _R_ matches the first letter of _Robert_. However, nickname matches will not
|
43
|
-
always work with initials. In the next example, the initial _R_ does not match the first letter _B_ of the
|
44
|
-
nickname _Bobby_.
|
45
|
-
|
46
|
-
bobby.match('R. J.', 'Fischer') # => false
|
47
|
-
|
48
|
-
Some of the ways last names are canonicalised are illustrated below:
|
49
|
-
|
50
|
-
ICU::Name.new('John', 'O Reilly').last # => "O'Reilly"
|
51
|
-
ICU::Name.new('dave', 'mcmanus').last # => "McManus"
|
52
|
-
ICU::Name.new('pete', 'MACMANUS').last # => "MacManus"
|
53
|
-
|
54
|
-
=end
|
55
|
-
|
56
|
-
class Name
|
57
|
-
attr_reader :first, :last
|
58
|
-
|
59
|
-
def initialize(name1='', name2='')
|
60
|
-
@name1 = name1.to_s
|
61
|
-
@name2 = name2.to_s
|
62
|
-
canonicalize
|
63
|
-
end
|
64
|
-
|
65
|
-
def name
|
66
|
-
name = ''
|
67
|
-
name << @first
|
68
|
-
name << ' ' if @first.length > 0 && @last.length > 0
|
69
|
-
name << @last
|
70
|
-
name
|
71
|
-
end
|
72
|
-
|
73
|
-
def rname
|
74
|
-
name = ''
|
75
|
-
name << @last
|
76
|
-
name << ', ' if @first.length > 0 && @last.length > 0
|
77
|
-
name << @first
|
78
|
-
name
|
79
|
-
end
|
80
|
-
|
81
|
-
def to_s
|
82
|
-
rname
|
83
|
-
end
|
84
|
-
|
85
|
-
def match(name1='', name2='')
|
86
|
-
other = Name.new(name1, name2)
|
87
|
-
match_first(first, other.first) && match_last(last, other.last)
|
88
|
-
end
|
89
|
-
|
90
|
-
private
|
91
|
-
|
92
|
-
def canonicalize
|
93
|
-
first, last = partition
|
94
|
-
@first = finish_first(first)
|
95
|
-
@last = finish_last(last)
|
96
|
-
end
|
97
|
-
|
98
|
-
def partition
|
99
|
-
if @name2.length == 0
|
100
|
-
# Only one imput so we must split first and last.
|
101
|
-
parts = @name1.split(/,/)
|
102
|
-
if parts.size > 1
|
103
|
-
last = clean(parts.shift || '')
|
104
|
-
first = clean(parts.join(' '))
|
105
|
-
else
|
106
|
-
parts = clean(@name1).split(/ /)
|
107
|
-
last = parts.pop || ''
|
108
|
-
first = parts.join(' ')
|
109
|
-
end
|
110
|
-
else
|
111
|
-
# Two inputs, so we are given first and last.
|
112
|
-
first = clean(@name1)
|
113
|
-
last = clean(@name2)
|
114
|
-
end
|
115
|
-
[first, last]
|
116
|
-
end
|
117
|
-
|
118
|
-
def clean(name)
|
119
|
-
name.gsub!(/`/, "'")
|
120
|
-
name.gsub!(/[^-a-zA-Z.'\s]/, '')
|
121
|
-
name.gsub!(/\./, ' ')
|
122
|
-
name.gsub!(/\s*-\s*/, '-')
|
123
|
-
name.gsub!(/'+/, "'")
|
124
|
-
name.strip.downcase.split(/\s+/).map do |n|
|
125
|
-
n.sub!(/^-+/, '')
|
126
|
-
n.sub!(/-+$/, '')
|
127
|
-
n.split(/-/).map do |p|
|
128
|
-
p.capitalize!
|
129
|
-
end.join('-')
|
130
|
-
end.join(' ')
|
131
|
-
end
|
132
|
-
|
133
|
-
def finish_first(names)
|
134
|
-
names.gsub(/([A-Z])\b/, '\1.')
|
135
|
-
end
|
136
|
-
|
137
|
-
def finish_last(names)
|
138
|
-
names.gsub!(/\b([A-Z])'([a-z])/) { |m| $1 << "'" << $2.upcase}
|
139
|
-
names.gsub!(/\bMc([a-z])/) { |m| 'Mc' << $1.upcase}
|
140
|
-
names.gsub!(/\bMac([a-z])/) do |m|
|
141
|
-
letter = $1
|
142
|
-
'Mac'.concat(@name2.match("[mM][aA][cC]#{letter}") ? letter : letter.upcase)
|
143
|
-
end
|
144
|
-
names.gsub!(/\bO ([A-Z])/) { |m| "O'" << $1 }
|
145
|
-
names
|
146
|
-
end
|
147
|
-
|
148
|
-
# Match a complete first name.
|
149
|
-
def match_first(first1, first2)
|
150
|
-
# Is this one a walk in the park?
|
151
|
-
return true if first1 == first2
|
152
|
-
|
153
|
-
# No easy ride. Begin by splitting into individual first names.
|
154
|
-
first1 = split_first(first1)
|
155
|
-
first2 = split_first(first2)
|
156
|
-
|
157
|
-
# Get the long list and the short list.
|
158
|
-
long, short = first1.size >= first2.size ? [first1, first2] : [first2, first1]
|
159
|
-
|
160
|
-
# The short one must be a "subset" of the long one.
|
161
|
-
# An extra condition must also be satisfied.
|
162
|
-
extra = false
|
163
|
-
(0..long.size-1).each do |i|
|
164
|
-
lword = long.shift
|
165
|
-
score = match_first_name(lword, short.first)
|
166
|
-
if score >= 0
|
167
|
-
short.shift
|
168
|
-
extra = true if i == 0 || score == 0
|
169
|
-
end
|
170
|
-
break if short.empty? || long.empty?
|
171
|
-
end
|
172
|
-
|
173
|
-
# There's a match if the following is true.
|
174
|
-
short.empty? && extra
|
175
|
-
end
|
176
|
-
|
177
|
-
# Match a complete last name.
|
178
|
-
def match_last(last1, last2)
|
179
|
-
return true if last1 == last2
|
180
|
-
[last1, last2].each do |last|
|
181
|
-
last.downcase! # MacDonaugh and Macdonaugh
|
182
|
-
last.gsub!(/\bmac/, 'mc') # MacDonaugh and McDonaugh
|
183
|
-
last.tr!('-', ' ') # Lowry-O'Reilly and Lowry O'Reilly
|
184
|
-
end
|
185
|
-
last1 == last2
|
186
|
-
end
|
187
|
-
|
188
|
-
# Split a complete first name for matching.
|
189
|
-
def split_first(first)
|
190
|
-
first.tr!('-', ' ') # J. K. and J.-K.
|
191
|
-
first = first.split(/ /) # split on spaces
|
192
|
-
first = [''] if first.size == 0 # in case input was empty string
|
193
|
-
first
|
194
|
-
end
|
195
|
-
|
196
|
-
# Match individual first names or initials.
|
197
|
-
# -1 = no match
|
198
|
-
# 0 = full match
|
199
|
-
# 1 = match involving 1 initial
|
200
|
-
# 2 = match involving 2 initials
|
201
|
-
def match_first_name(first1, first2)
|
202
|
-
initials = 0
|
203
|
-
initials+= 1 if first1.match(/^[A-Z]\.?$/)
|
204
|
-
initials+= 1 if first2.match(/^[A-Z]\.?$/)
|
205
|
-
return initials if first1 == first2
|
206
|
-
return 0 if initials == 0 && match_nick_name(first1, first2)
|
207
|
-
return -1 unless initials > 0
|
208
|
-
return initials if first1[0] == first2[0]
|
209
|
-
-1
|
210
|
-
end
|
211
|
-
|
212
|
-
# Match two first names that might be equivalent nicknames.
|
213
|
-
def match_nick_name(nick1, nick2)
|
214
|
-
compile_nick_names unless @@nc
|
215
|
-
code1 = @@nc[nick1]
|
216
|
-
return false unless code1
|
217
|
-
code1 == @@nc[nick2]
|
218
|
-
end
|
219
|
-
|
220
|
-
# Compile the nick names code hash when matching nick names is first attempted.
|
221
|
-
def compile_nick_names
|
222
|
-
@@nc = Hash.new
|
223
|
-
code = 1
|
224
|
-
@@nl.each do |nicks|
|
225
|
-
nicks.each do |n|
|
226
|
-
throw "duplicate name #{n}" if @@nc[n]
|
227
|
-
@@nc[n] = code
|
228
|
-
end
|
229
|
-
code+= 1
|
230
|
-
end
|
231
|
-
end
|
232
|
-
|
233
|
-
# A array of data for matching nicknames and also a few common misspellings.
|
234
|
-
@@nc = nil
|
235
|
-
@@nl = <<EOF.split(/\n/).reject{|x| x.length == 0 }.map{|x| x.split(' ')}
|
236
|
-
Abdul Abul
|
237
|
-
Alexander Alex
|
238
|
-
Anandagopal Ananda
|
239
|
-
Anne Ann
|
240
|
-
Anthony Tony
|
241
|
-
Benjamin Ben
|
242
|
-
Catherine Cathy Cath
|
243
|
-
Daniel Danial Danny Dan
|
244
|
-
David Dave
|
245
|
-
Deborah Debbie
|
246
|
-
Des Desmond
|
247
|
-
Eamonn Eamon
|
248
|
-
Edward Eddie Ed
|
249
|
-
Eric Erick Erik
|
250
|
-
Frederick Frederic Fred
|
251
|
-
Gerald Gerry
|
252
|
-
Gerhard Gerard Ger
|
253
|
-
James Jim
|
254
|
-
Joanna Joan Joanne
|
255
|
-
John Johnny
|
256
|
-
Jonathan Jon
|
257
|
-
Kenneth Ken Kenny
|
258
|
-
Michael Mike Mick Micky
|
259
|
-
Nicholas Nick Nicolas
|
260
|
-
Nicola Nickie Nicky
|
261
|
-
Patrick Pat Paddy
|
262
|
-
Peter Pete
|
263
|
-
Philippe Philip Phillippe Phillip
|
264
|
-
Rick Ricky
|
265
|
-
Robert Bob Bobby
|
266
|
-
Samual Sam Samuel
|
267
|
-
Stefanie Stef
|
268
|
-
Stephen Steven Steve
|
269
|
-
Terence Terry
|
270
|
-
Thomas Tom Tommy
|
271
|
-
William Will Willy Willie Bill
|
272
|
-
EOF
|
273
|
-
end
|
274
|
-
end
|
data/spec/name_spec.rb
DELETED
@@ -1,208 +0,0 @@
|
|
1
|
-
require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
|
2
|
-
|
3
|
-
module ICU
|
4
|
-
describe Name do
|
5
|
-
context "public methods" do
|
6
|
-
before(:each) do
|
7
|
-
@simple = Name.new('mark j l', 'orr')
|
8
|
-
end
|
9
|
-
|
10
|
-
it "#first returns the first name(s)" do
|
11
|
-
@simple.first.should == 'Mark J. L.'
|
12
|
-
end
|
13
|
-
|
14
|
-
it "#last returns the last name(s)" do
|
15
|
-
@simple.last.should == 'Orr'
|
16
|
-
end
|
17
|
-
|
18
|
-
it "#name returns the full name with first name(s) first" do
|
19
|
-
@simple.name.should == 'Mark J. L. Orr'
|
20
|
-
end
|
21
|
-
|
22
|
-
it "#rname returns the full name with last name(s) first" do
|
23
|
-
@simple.rname.should == 'Orr, Mark J. L.'
|
24
|
-
end
|
25
|
-
|
26
|
-
it "#to_s is the same as rname" do
|
27
|
-
@simple.to_s.should == 'Orr, Mark J. L.'
|
28
|
-
end
|
29
|
-
|
30
|
-
it "#match returns true if and only if two names match" do
|
31
|
-
@simple.match('mark j l orr').should be_true
|
32
|
-
@simple.match('malcolm g l orr').should be_false
|
33
|
-
end
|
34
|
-
end
|
35
|
-
|
36
|
-
context "rdoc expample" do
|
37
|
-
before(:each) do
|
38
|
-
@robert = Name.new(' robert j ', ' FISCHER ')
|
39
|
-
@bobby = Name.new(' bobby fischer ')
|
40
|
-
end
|
41
|
-
|
42
|
-
it "should get Robert" do
|
43
|
-
@robert.name.should == 'Robert J. Fischer'
|
44
|
-
end
|
45
|
-
|
46
|
-
it "should get Bobby" do
|
47
|
-
@bobby.last.should == 'Fischer'
|
48
|
-
@bobby.first.should == 'Bobby'
|
49
|
-
end
|
50
|
-
|
51
|
-
it "should match Robert and Bobby" do
|
52
|
-
@robert.match(@bobby).should be_true
|
53
|
-
@robert.match('R. J.', 'Fischer').should be_true
|
54
|
-
@bobby.match('R. J.', 'Fischer').should be_false
|
55
|
-
end
|
56
|
-
|
57
|
-
it "should canconicalise last names" do
|
58
|
-
Name.new('John', 'O Reilly').last.should == "O'Reilly"
|
59
|
-
Name.new('dave', 'mcmanus').last.should == "McManus"
|
60
|
-
Name.new('pete', 'MACMANUS').last.should == "MacManus"
|
61
|
-
end
|
62
|
-
end
|
63
|
-
|
64
|
-
context "names that are already canonical" do
|
65
|
-
it "should not be altered" do
|
66
|
-
Name.new('Mark J. L.', 'Orr').name.should == 'Mark J. L. Orr'
|
67
|
-
Name.new('Anna-Marie J.-K.', 'Liviu-Dieter').name.should == 'Anna-Marie J.-K. Liviu-Dieter'
|
68
|
-
end
|
69
|
-
end
|
70
|
-
|
71
|
-
context "last names beginning with a single letter followed by a quote" do
|
72
|
-
it "should be handled correctly" do
|
73
|
-
Name.new('una', "O'boyle").name.should == "Una O'Boyle"
|
74
|
-
Name.new('jonathan', 'd`arcy').name.should == "Jonathan D'Arcy"
|
75
|
-
Name.new('erwin e', "L'AMI").name.should == "Erwin E. L'Ami"
|
76
|
-
Name.new('cormac', "o brien").name.should == "Cormac O'Brien"
|
77
|
-
end
|
78
|
-
end
|
79
|
-
|
80
|
-
context "last beginning with Mc" do
|
81
|
-
it "should be handled correctly" do
|
82
|
-
Name.new('shane', "mccabe").name.should == "Shane McCabe"
|
83
|
-
Name.new('shawn', "macDonagh").name.should == "Shawn MacDonagh"
|
84
|
-
Name.new('shawn', "macdonagh").name.should == "Shawn Macdonagh"
|
85
|
-
Name.new('bartlomiej', "macieja").name.should == "Bartlomiej Macieja"
|
86
|
-
end
|
87
|
-
end
|
88
|
-
|
89
|
-
context "doubled barrelled names or initials" do
|
90
|
-
it "should be handled correctly" do
|
91
|
-
Name.new('anna-marie', 'den-otter').name.should == 'Anna-Marie Den-Otter'
|
92
|
-
Name.new('j-k', 'rowling').name.should == 'J.-K. Rowling'
|
93
|
-
Name.new("mark j. - l", 'ORR').name.should == 'Mark J.-L. Orr'
|
94
|
-
Name.new('JOHANNA', "lowry-o'REILLY").name.should == "Johanna Lowry-O'Reilly"
|
95
|
-
Name.new('hannah', "lowry - o reilly").name.should == "Hannah Lowry-O'Reilly"
|
96
|
-
end
|
97
|
-
end
|
98
|
-
|
99
|
-
context "extraneous white space" do
|
100
|
-
it "should be handled correctly" do
|
101
|
-
Name.new(' mark j l ', " \t\r\n orr \n").name.should == 'Mark J. L. Orr'
|
102
|
-
end
|
103
|
-
end
|
104
|
-
|
105
|
-
context "extraneous full stops" do
|
106
|
-
it "should be handled correctly" do
|
107
|
-
Name.new('. mark j..l', 'orr.').name.should == 'Mark J. L. Orr'
|
108
|
-
end
|
109
|
-
end
|
110
|
-
|
111
|
-
context "construction from a single string" do
|
112
|
-
before(:each) do
|
113
|
-
@mark1 = Name.new('ORR, mark j l')
|
114
|
-
@mark2 = Name.new('MARK J L ORR')
|
115
|
-
@oreil = Name.new("O'Reilly, j-k")
|
116
|
-
end
|
117
|
-
|
118
|
-
it "should be possible in simple cases" do
|
119
|
-
@mark1.first.should == 'Mark J. L.'
|
120
|
-
@mark1.last.should == 'Orr'
|
121
|
-
@mark2.first.should == 'Mark J. L.'
|
122
|
-
@mark2.last.should == 'Orr'
|
123
|
-
@oreil.name.should == "J.-K. O'Reilly"
|
124
|
-
end
|
125
|
-
end
|
126
|
-
|
127
|
-
context "construction from an instance" do
|
128
|
-
it "should be possible" do
|
129
|
-
Name.new(Name.new('ORR, mark j l')).name.should == 'Mark J. L. Orr'
|
130
|
-
end
|
131
|
-
end
|
132
|
-
|
133
|
-
context "constuction corner cases" do
|
134
|
-
it "should be handled correctly" do
|
135
|
-
Name.new('Orr').name.should == 'Orr'
|
136
|
-
Name.new('Orr').rname.should == 'Orr'
|
137
|
-
Name.new('').name.should == ''
|
138
|
-
Name.new('').rname.should == ''
|
139
|
-
Name.new.name.should == ''
|
140
|
-
Name.new.rname.should == ''
|
141
|
-
end
|
142
|
-
end
|
143
|
-
|
144
|
-
context "inputs to matching" do
|
145
|
-
before(:all) do
|
146
|
-
@mark = Name.new('Mark', 'Orr')
|
147
|
-
@kram = Name.new('Mark', 'Orr')
|
148
|
-
end
|
149
|
-
|
150
|
-
it "should be flexible" do
|
151
|
-
@mark.match('Mark', 'Orr').should be_true
|
152
|
-
@mark.match('Mark Orr').should be_true
|
153
|
-
@mark.match('Orr, Mark').should be_true
|
154
|
-
@mark.match(@kram).should be_true
|
155
|
-
end
|
156
|
-
end
|
157
|
-
|
158
|
-
context "first name matches" do
|
159
|
-
it "should match when first names are the same" do
|
160
|
-
Name.new('Mark', 'Orr').match('Mark', 'Orr').should be_true
|
161
|
-
end
|
162
|
-
|
163
|
-
it "should be flexible with regards to hyphens in double barrelled names" do
|
164
|
-
Name.new('J.-K.', 'Rowling').match('J. K.', 'Rowling').should be_true
|
165
|
-
Name.new('Joanne-K.', 'Rowling').match('Joanne K.', 'Rowling').should be_true
|
166
|
-
end
|
167
|
-
|
168
|
-
it "should match initials" do
|
169
|
-
Name.new('M. J. L.', 'Orr').match('Mark John Legard', 'Orr').should be_true
|
170
|
-
Name.new('M.', 'Orr').match('Mark', 'Orr').should be_true
|
171
|
-
Name.new('M. J. L.', 'Orr').match('Mark', 'Orr').should be_true
|
172
|
-
Name.new('M.', 'Orr').match('M. J.', 'Orr').should be_true
|
173
|
-
Name.new('M. J. L.', 'Orr').match('M. G.', 'Orr').should be_false
|
174
|
-
end
|
175
|
-
|
176
|
-
it "should not match on full names not in first position or without an exact match" do
|
177
|
-
Name.new('J. M.', 'Orr').match('John', 'Orr').should be_true
|
178
|
-
Name.new('M. J.', 'Orr').match('John', 'Orr').should be_false
|
179
|
-
Name.new('M. John', 'Orr').match('John', 'Orr').should be_true
|
180
|
-
end
|
181
|
-
|
182
|
-
it "should handle common nicknames" do
|
183
|
-
Name.new('William', 'Orr').match('Bill', 'Orr').should be_true
|
184
|
-
Name.new('David', 'Orr').match('Dave', 'Orr').should be_true
|
185
|
-
Name.new('Mick', 'Orr').match('Mike', 'Orr').should be_true
|
186
|
-
end
|
187
|
-
|
188
|
-
it "should not mix up nick names" do
|
189
|
-
Name.new('David', 'Orr').match('Bill', 'Orr').should be_false
|
190
|
-
end
|
191
|
-
end
|
192
|
-
|
193
|
-
context "last name matches" do
|
194
|
-
it "should be flexible with regards to hyphens in double barrelled names" do
|
195
|
-
Name.new('Johanna', "Lowry-O'Reilly").match('Johanna', "Lowry O'Reilly").should be_true
|
196
|
-
end
|
197
|
-
|
198
|
-
it "should be case insensitive in matches involving Macsomething and MacSomething" do
|
199
|
-
Name.new('Alan', 'MacDonagh').match('Alan', 'Macdonagh').should be_true
|
200
|
-
end
|
201
|
-
|
202
|
-
it "should cater for the common mispelling of names beginning with Mc or Mac" do
|
203
|
-
Name.new('Alan', 'McDonagh').match('Alan', 'MacDonagh').should be_true
|
204
|
-
Name.new('Darko', 'Polimac').match('Darko', 'Polimc').should be_false
|
205
|
-
end
|
206
|
-
end
|
207
|
-
end
|
208
|
-
end
|