sportdb-formats 0.1.3 → 0.1.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Manifest.txt +0 -2
- data/Rakefile +1 -0
- data/lib/sportdb/formats/version.rb +1 -1
- data/lib/sportdb/formats.rb +9 -1
- metadata +16 -4
- data/lib/sportdb/formats/date.rb +0 -446
- data/test/test_date.rb +0 -100
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 84244a1e794fcbc1fea7365921dab81a1e33b5b1
|
4
|
+
data.tar.gz: 916eac3f334d3e10b27b0852a2b4634b0f498677
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 3a9d7d0616bd1f3f6dc08314ede6813392b00d622d32f5cf1b9309d9382e1e26f57e3f37bbe35725e92ec9cbe2cff65e56266b826d4f2899955b58e9bb456d98
|
7
|
+
data.tar.gz: 5601d27d90579ffcc96e686ced3cf665b3b73812821dd847da7f7b188ad509b0f145be929f2f90d598da10464d877795aa1a58f7d6c59b590a58e628b688702f
|
data/Manifest.txt
CHANGED
@@ -4,7 +4,6 @@ README.md
|
|
4
4
|
Rakefile
|
5
5
|
lib/sportdb/formats.rb
|
6
6
|
lib/sportdb/formats/datafile.rb
|
7
|
-
lib/sportdb/formats/date.rb
|
8
7
|
lib/sportdb/formats/outline_reader.rb
|
9
8
|
lib/sportdb/formats/season_utils.rb
|
10
9
|
lib/sportdb/formats/version.rb
|
@@ -12,6 +11,5 @@ test/helper.rb
|
|
12
11
|
test/test_csv_reader.rb
|
13
12
|
test/test_datafile.rb
|
14
13
|
test/test_datafile_match.rb
|
15
|
-
test/test_date.rb
|
16
14
|
test/test_outline_reader.rb
|
17
15
|
test/test_season_utils.rb
|
data/Rakefile
CHANGED
data/lib/sportdb/formats.rb
CHANGED
@@ -3,6 +3,15 @@
|
|
3
3
|
|
4
4
|
## 3rd party gems
|
5
5
|
require 'alphabets' # downcase_i18n, unaccent, variants, ...
|
6
|
+
require 'date-formats' ## todo/fix: also allow loading w/ date/formats - why? why not!!!!
|
7
|
+
|
8
|
+
module SportDb
|
9
|
+
## add alias for now for old code; DEPRECATED - remove later!!!!!
|
10
|
+
DateFinder = DateFormats::DateFinder
|
11
|
+
RsssfDateFinder = DateFormats::RsssfDateFinder
|
12
|
+
end # module SportDb
|
13
|
+
|
14
|
+
|
6
15
|
require 'csvreader'
|
7
16
|
|
8
17
|
def read_csv( path )
|
@@ -25,7 +34,6 @@ require 'sportdb/formats/outline_reader'
|
|
25
34
|
require 'sportdb/formats/datafile'
|
26
35
|
require 'sportdb/formats/season_utils'
|
27
36
|
|
28
|
-
require 'sportdb/formats/date'
|
29
37
|
|
30
38
|
## let's put test configuration in its own namespace / module
|
31
39
|
module SportDb
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: sportdb-formats
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.4
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Gerald Bauer
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2019-11-
|
11
|
+
date: 2019-11-07 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: alphabets
|
@@ -24,6 +24,20 @@ dependencies:
|
|
24
24
|
- - ">="
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: 0.1.0
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: date-formats
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 0.1.0
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 0.1.0
|
27
41
|
- !ruby/object:Gem::Dependency
|
28
42
|
name: csvreader
|
29
43
|
requirement: !ruby/object:Gem::Requirement
|
@@ -95,7 +109,6 @@ files:
|
|
95
109
|
- Rakefile
|
96
110
|
- lib/sportdb/formats.rb
|
97
111
|
- lib/sportdb/formats/datafile.rb
|
98
|
-
- lib/sportdb/formats/date.rb
|
99
112
|
- lib/sportdb/formats/outline_reader.rb
|
100
113
|
- lib/sportdb/formats/season_utils.rb
|
101
114
|
- lib/sportdb/formats/version.rb
|
@@ -103,7 +116,6 @@ files:
|
|
103
116
|
- test/test_csv_reader.rb
|
104
117
|
- test/test_datafile.rb
|
105
118
|
- test/test_datafile_match.rb
|
106
|
-
- test/test_date.rb
|
107
119
|
- test/test_outline_reader.rb
|
108
120
|
- test/test_season_utils.rb
|
109
121
|
homepage: https://github.com/sportdb/sport.db
|
data/lib/sportdb/formats/date.rb
DELETED
@@ -1,446 +0,0 @@
|
|
1
|
-
# encoding: utf-8
|
2
|
-
|
3
|
-
#### fix: move to textutils for reuse !!!!!!!!!! - why?? why not ??
|
4
|
-
|
5
|
-
|
6
|
-
module SportDb
|
7
|
-
|
8
|
-
|
9
|
-
class DateFinderBase
|
10
|
-
|
11
|
-
MONTH_EN_TO_MM = {
|
12
|
-
'Jan' => '1', 'January' => '1',
|
13
|
-
'Feb' => '2', 'February' => '2',
|
14
|
-
'Mar' => '3', 'March' => '3',
|
15
|
-
'Apr' => '4', 'April' => '4',
|
16
|
-
'May' => '5',
|
17
|
-
'Jun' => '6', 'June' => '6',
|
18
|
-
'Jul' => '7', 'July' => '7',
|
19
|
-
'Aug' => '8', 'August' => '8',
|
20
|
-
'Sep' => '9', 'Sept' => '9', 'September' => '9',
|
21
|
-
'Oct' => '10', 'October' => '10',
|
22
|
-
'Nov' => '11', 'November' => '11',
|
23
|
-
'Dec' => '12', 'December' =>'12' }
|
24
|
-
|
25
|
-
MONTH_FR_TO_MM = {
|
26
|
-
'Janvier' => '1', 'Janv' => '1', 'Jan' => '1', ## check janv in use??
|
27
|
-
'Février' => '2', 'Févr' => '2', 'Fév' => '2', ## check fevr in use???
|
28
|
-
'Mars' => '3', 'Mar' => '3',
|
29
|
-
'Avril' => '4', 'Avri' => '4', 'Avr' => '4', ## check avri in use??? if not remove
|
30
|
-
'Mai' => '5',
|
31
|
-
'Juin' => '6',
|
32
|
-
'Juillet' => '7', 'Juil' => '7',
|
33
|
-
'Août' => '8',
|
34
|
-
'Septembre' => '9', 'Sept' => '9',
|
35
|
-
'Octobre' => '10', 'Octo' => '10', 'Oct' => '10', ### check octo in use??
|
36
|
-
'Novembre' => '11', 'Nove' => '11', 'Nov' => '11', ## check nove in use??
|
37
|
-
'Décembre' => '12', 'Déce' => '12', 'Déc' => '12' } ## check dece in use??
|
38
|
-
|
39
|
-
MONTH_ES_TO_MM = {
|
40
|
-
'Ene' => '1', 'Enero' => '1',
|
41
|
-
'Feb' => '2',
|
42
|
-
'Mar' => '3', 'Marzo' => '3',
|
43
|
-
'Abr' => '4', 'Abril' => '4',
|
44
|
-
'May' => '5', 'Mayo' => '5',
|
45
|
-
'Jun' => '6', 'Junio' => '6',
|
46
|
-
'Jul' => '7', 'Julio' => '7',
|
47
|
-
'Ago' => '8', 'Agosto' => '8',
|
48
|
-
'Sep' => '9', 'Set' => '9', 'Sept' => '9',
|
49
|
-
'Oct' => '10',
|
50
|
-
'Nov' => '11',
|
51
|
-
'Dic' => '12' }
|
52
|
-
|
53
|
-
private
|
54
|
-
def calc_year( month, day, start_at: ) ## note: start_at required param for now on!!!
|
55
|
-
|
56
|
-
logger.debug " [calc_year] ????-#{month}-#{day} -- start_at: #{start_at}"
|
57
|
-
|
58
|
-
if month >= start_at.month
|
59
|
-
# assume same year as start_at event (e.g. 2013 for 2013/14 season)
|
60
|
-
start_at.year
|
61
|
-
else
|
62
|
-
# assume year+1 as start_at event (e.g. 2014 for 2013/14 season)
|
63
|
-
start_at.year+1
|
64
|
-
end
|
65
|
-
end
|
66
|
-
|
67
|
-
|
68
|
-
def parse_date_time( match_data, opts={} )
|
69
|
-
|
70
|
-
# convert regex match_data captures to hash
|
71
|
-
# - note: cannont use match_data like a hash (e.g. raises exception if key/name not present/found)
|
72
|
-
h = {}
|
73
|
-
# - note: do NOT forget to turn name into symbol for lookup in new hash (name.to_sym)
|
74
|
-
match_data.names.each { |name| h[name.to_sym] = match_data[name] } # or use match_data.names.zip( match_data.captures ) - more cryptic but "elegant"??
|
75
|
-
|
76
|
-
## puts "[parse_date_time] match_data:"
|
77
|
-
## pp h
|
78
|
-
logger.debug " [parse_date_time] hash: >#{h.inspect}<"
|
79
|
-
|
80
|
-
h[ :month ] = MONTH_EN_TO_MM[ h[:month_en] ] if h[:month_en]
|
81
|
-
h[ :month ] = MONTH_ES_TO_MM[ h[:month_es] ] if h[:month_es]
|
82
|
-
h[ :month ] = MONTH_FR_TO_MM[ h[:month_fr] ] if h[:month_fr]
|
83
|
-
|
84
|
-
month = h[:month]
|
85
|
-
day = h[:day]
|
86
|
-
year = h[:year] || calc_year( month.to_i, day.to_i, opts ).to_s
|
87
|
-
|
88
|
-
hours = h[:hours] || '12' # default to 12:00 for HH:MM (hours:minutes)
|
89
|
-
minutes = h[:minutes] || '00'
|
90
|
-
|
91
|
-
value = '%d-%02d-%02d %02d:%02d' % [year.to_i, month.to_i, day.to_i, hours.to_i, minutes.to_i]
|
92
|
-
logger.debug " date: >#{value}<"
|
93
|
-
|
94
|
-
DateTime.strptime( value, '%Y-%m-%d %H:%M' )
|
95
|
-
end
|
96
|
-
|
97
|
-
end # class DateFinderBase
|
98
|
-
|
99
|
-
|
100
|
-
class DateFinder < DateFinderBase
|
101
|
-
|
102
|
-
include LogUtils::Logging
|
103
|
-
|
104
|
-
# todo: make more generic for reuse
|
105
|
-
### fix:
|
106
|
-
### move to textutils
|
107
|
-
## date/fr.yml en.yml etc. ???
|
108
|
-
## why? why not?
|
109
|
-
|
110
|
-
MONTH_FR = 'Janvier|Janv|Jan|' +
|
111
|
-
'Février|Févr|Fév|' +
|
112
|
-
'Mars|Mar|' +
|
113
|
-
'Avril|Avri|Avr|' +
|
114
|
-
'Mai|' +
|
115
|
-
'Juin|' +
|
116
|
-
'Juillet|Juil|' +
|
117
|
-
'Août|' +
|
118
|
-
'Septembre|Sept|' +
|
119
|
-
'Octobre|Octo|Oct|' +
|
120
|
-
'Novembre|Nove|Nov|' +
|
121
|
-
'Décembre|Déce|Déc'
|
122
|
-
|
123
|
-
WEEKDAY_FR = 'Lundi|Lun|L|' +
|
124
|
-
'Mardi|Mar|Ma|' +
|
125
|
-
'Mercredi|Mer|Me|' +
|
126
|
-
'Jeudi|Jeu|J|' +
|
127
|
-
'Vendredi|Ven|V|' +
|
128
|
-
'Samedi|Sam|S|' +
|
129
|
-
'Dimanche|Dim|D|'
|
130
|
-
|
131
|
-
|
132
|
-
MONTH_EN = 'January|Jan|'+
|
133
|
-
'February|Feb|'+
|
134
|
-
'March|Mar|'+
|
135
|
-
'April|Apr|'+
|
136
|
-
'May|'+
|
137
|
-
'June|Jun|'+
|
138
|
-
'July|Jul|'+
|
139
|
-
'August|Aug|'+
|
140
|
-
'September|Sept|Sep|'+
|
141
|
-
'October|Oct|'+
|
142
|
-
'November|Nov|'+
|
143
|
-
'December|Dec'
|
144
|
-
|
145
|
-
###
|
146
|
-
## todo: add days
|
147
|
-
## 1. Sunday - Sun. 2. Monday - Mon.
|
148
|
-
## 3. Tuesday - Tu., Tue., or Tues. 4. Wednesday - Wed.
|
149
|
-
## 5. Thursday - Th., Thu., Thur., or Thurs. 6. Friday - Fri.
|
150
|
-
## 7. Saturday - Sat.
|
151
|
-
|
152
|
-
|
153
|
-
MONTH_ES = 'Enero|Ene|'+
|
154
|
-
'Feb|'+
|
155
|
-
'Marzo|Mar|'+
|
156
|
-
'Abril|Abr|'+
|
157
|
-
'Mayo|May|'+
|
158
|
-
'Junio|Jun|'+
|
159
|
-
'Julio|Jul|'+
|
160
|
-
'Agosto|Ago|'+
|
161
|
-
'Sept|Set|Sep|'+
|
162
|
-
'Oct|'+
|
163
|
-
'Nov|'+
|
164
|
-
'Dic'
|
165
|
-
|
166
|
-
# todo/fix - add de and es too!!
|
167
|
-
# note: in Austria - Jänner - in Deutschland Januar allow both ??
|
168
|
-
# MONTH_DE = 'J[aä]n|Feb|Mär|Apr|Mai|Jun|Jul|Aug|Sep|Okt|Nov|Dez'
|
169
|
-
|
170
|
-
|
171
|
-
# e.g. 2012-09-14 20:30 => YYYY-MM-DD HH:MM
|
172
|
-
# nb: allow 2012-9-3 7:30 e.g. no leading zero required
|
173
|
-
# regex_db
|
174
|
-
DB__DATE_TIME_REGEX = /\b
|
175
|
-
(?<year>\d{4})
|
176
|
-
-
|
177
|
-
(?<month>\d{1,2})
|
178
|
-
-
|
179
|
-
(?<day>\d{1,2})
|
180
|
-
\s+
|
181
|
-
(?<hours>\d{1,2})
|
182
|
-
:
|
183
|
-
(?<minutes>\d{2})
|
184
|
-
\b/x
|
185
|
-
|
186
|
-
# e.g. 2012-09-14 w/ implied hours (set to 12:00)
|
187
|
-
# nb: allow 2012-9-3 e.g. no leading zero required
|
188
|
-
# regex_db2
|
189
|
-
DB__DATE_REGEX = /\b
|
190
|
-
(?<year>\d{4})
|
191
|
-
-
|
192
|
-
(?<month>\d{1,2})
|
193
|
-
-
|
194
|
-
(?<day>\d{1,2})
|
195
|
-
\b/x
|
196
|
-
|
197
|
-
# e.g. 14.09.2012 20:30 => DD.MM.YYYY HH:MM
|
198
|
-
# nb: allow 2.3.2012 e.g. no leading zero required
|
199
|
-
# nb: allow hour as 20.30
|
200
|
-
# regex_de
|
201
|
-
DD_MM_YYYY__DATE_TIME_REGEX = /\b
|
202
|
-
(?<day>\d{1,2})
|
203
|
-
\.
|
204
|
-
(?<month>\d{1,2})
|
205
|
-
\.
|
206
|
-
(?<year>\d{4})
|
207
|
-
\s+
|
208
|
-
(?<hours>\d{1,2})
|
209
|
-
[:.]
|
210
|
-
(?<minutes>\d{2})
|
211
|
-
\b/x
|
212
|
-
|
213
|
-
# e.g. 14.09. 20:30 => DD.MM. HH:MM
|
214
|
-
# nb: allow 2.3.2012 e.g. no leading zero required
|
215
|
-
# nb: allow hour as 20.30 or 3.30 instead of 03.30
|
216
|
-
# regex_de2
|
217
|
-
DD_MM__DATE_TIME_REGEX = /\b
|
218
|
-
(?<day>\d{1,2})
|
219
|
-
\.
|
220
|
-
(?<month>\d{1,2})
|
221
|
-
\.
|
222
|
-
\s+
|
223
|
-
(?<hours>\d{1,2})
|
224
|
-
[:.]
|
225
|
-
(?<minutes>\d{2})
|
226
|
-
\b/x
|
227
|
-
|
228
|
-
# e.g. 14.09.2012 => DD.MM.YYYY w/ implied hours (set to 12:00)
|
229
|
-
# regex_de3
|
230
|
-
DD_MM_YYYY__DATE_REGEX = /\b
|
231
|
-
(?<day>\d{1,2})
|
232
|
-
\.
|
233
|
-
(?<month>\d{1,2})
|
234
|
-
\.
|
235
|
-
(?<year>\d{4})
|
236
|
-
\b/x
|
237
|
-
|
238
|
-
# e.g. 14.09. => DD.MM. w/ implied year and implied hours (set to 12:00)
|
239
|
-
# note: allow end delimiter ] e.g. [Sa 12.01.] or end-of-string ($) too
|
240
|
-
# note: we use a lookahead for last part e.g. (?:\s+|$|[\]]) - do NOT cosume
|
241
|
-
# regex_de4 (use lookahead assert)
|
242
|
-
DD_MM__DATE_REGEX = /\b
|
243
|
-
(?<day>\d{1,2})
|
244
|
-
\.
|
245
|
-
(?<month>\d{1,2})
|
246
|
-
\.
|
247
|
-
(?=\s+|$|[\]])/x ## note: allow end-of-string/line too
|
248
|
-
|
249
|
-
|
250
|
-
# e.g. 12 May 2013 14:00 => D|DD.MMM.YYYY H|HH:MM
|
251
|
-
EN__DD_MONTH_YYYY__DATE_TIME_REGEX = /\b
|
252
|
-
(?<day>\d{1,2})
|
253
|
-
\s
|
254
|
-
(?<month_en>#{MONTH_EN})
|
255
|
-
\s
|
256
|
-
(?<year>\d{4})
|
257
|
-
\s+
|
258
|
-
(?<hours>\d{1,2})
|
259
|
-
:
|
260
|
-
(?<minutes>\d{2})
|
261
|
-
\b/x
|
262
|
-
|
263
|
-
###
|
264
|
-
# fix: pass in lang (e.g. en or es)
|
265
|
-
# only process format for lang plus fallback to en?
|
266
|
-
# e.g. EN__DD_MONTH and ES__DD_MONTH depend on order for match (first listed will match)
|
267
|
-
|
268
|
-
# e.g. 12 May => D|DD.MMM w/ implied year and implied hours
|
269
|
-
EN__DD_MONTH__DATE_REGEX = /\b
|
270
|
-
(?<day>\d{1,2})
|
271
|
-
\s
|
272
|
-
(?<month_en>#{MONTH_EN})
|
273
|
-
\b/x
|
274
|
-
|
275
|
-
|
276
|
-
# e.g. Jun/12 2011 14:00
|
277
|
-
EN__MONTH_DD_YYYY__DATE_TIME_REGEX = /\b
|
278
|
-
(?<month_en>#{MONTH_EN})
|
279
|
-
\/
|
280
|
-
(?<day>\d{1,2})
|
281
|
-
\s
|
282
|
-
(?<year>\d{4})
|
283
|
-
\s+
|
284
|
-
(?<hours>\d{1,2})
|
285
|
-
:
|
286
|
-
(?<minutes>\d{2})
|
287
|
-
\b/x
|
288
|
-
|
289
|
-
# e.g. Jun/12 14:00 w/ implied year H|HH:MM
|
290
|
-
EN__MONTH_DD__DATE_TIME_REGEX = /\b
|
291
|
-
(?<month_en>#{MONTH_EN})
|
292
|
-
\/
|
293
|
-
(?<day>\d{1,2})
|
294
|
-
\s+
|
295
|
-
(?<hours>\d{1,2})
|
296
|
-
:
|
297
|
-
(?<minutes>\d{2})
|
298
|
-
\b/x
|
299
|
-
|
300
|
-
# e.g. Jun/12 2013 w/ implied hours (set to 12:00)
|
301
|
-
EN__MONTH_DD_YYYY__DATE_REGEX = /\b
|
302
|
-
(?<month_en>#{MONTH_EN})
|
303
|
-
\/
|
304
|
-
(?<day>\d{1,2})
|
305
|
-
\s
|
306
|
-
(?<year>\d{4})
|
307
|
-
\b/x
|
308
|
-
|
309
|
-
# e.g. Jun/12 w/ implied year and implied hours (set to 12:00)
|
310
|
-
# note: allow space too e.g Jun 12 -- check if conflicts w/ other formats??? (added for rsssf reader)
|
311
|
-
# -- fix: might eat french weekday mar 12 is mardi (mar) !!! see FR__ pattern
|
312
|
-
# fix: remove space again for now - and use simple en date reader or something!!!
|
313
|
-
## was [\/ ] changed back to \/
|
314
|
-
EN__MONTH_DD__DATE_REGEX = /\b
|
315
|
-
(?<month_en>#{MONTH_EN})
|
316
|
-
\/
|
317
|
-
(?<day>\d{1,2})
|
318
|
-
\b/x
|
319
|
-
|
320
|
-
|
321
|
-
# e.g. 12 Ene w/ implied year and implied hours (set to 12:00)
|
322
|
-
ES__DD_MONTH__DATE_REGEX = /\b
|
323
|
-
(?<day>\d{1,2})
|
324
|
-
\s
|
325
|
-
(?<month_es>#{MONTH_ES})
|
326
|
-
\b/x
|
327
|
-
|
328
|
-
# e.g. Ven 8 Août or [Ven 8 Août] or Ven 8. Août or [Ven 8. Août]
|
329
|
-
### note: do NOT consume [] in regex (use lookahead assert)
|
330
|
-
FR__WEEKDAY_DD_MONTH__DATE_REGEX = /\b
|
331
|
-
(?:#{WEEKDAY_FR}) # note: skip weekday for now; do NOT capture
|
332
|
-
\s+
|
333
|
-
(?<day>\d{1,2})
|
334
|
-
\.? # note: make dot optional
|
335
|
-
\s+
|
336
|
-
(?<month_fr>#{MONTH_FR})
|
337
|
-
(?=\s+|$|[\]])/x ## note: allow end-of-string/line too
|
338
|
-
|
339
|
-
|
340
|
-
|
341
|
-
|
342
|
-
# map table - 1) tag, 2) regex - note: order matters; first come-first matched/served
|
343
|
-
FORMATS = [
|
344
|
-
[ '[YYYY_MM_DD_hh_mm]', DB__DATE_TIME_REGEX ],
|
345
|
-
[ '[YYYY_MM_DD]', DB__DATE_REGEX ],
|
346
|
-
[ '[DD_MM_YYYY_hh_mm]', DD_MM_YYYY__DATE_TIME_REGEX ],
|
347
|
-
[ '[DD_MM_hh_mm]', DD_MM__DATE_TIME_REGEX ],
|
348
|
-
[ '[DD_MM_YYYY]', DD_MM_YYYY__DATE_REGEX ],
|
349
|
-
[ '[DD_MM]', DD_MM__DATE_REGEX ],
|
350
|
-
[ '[FR_WEEKDAY_DD_MONTH]', FR__WEEKDAY_DD_MONTH__DATE_REGEX ],
|
351
|
-
[ '[EN_DD_MONTH_YYYY_hh_mm]', EN__DD_MONTH_YYYY__DATE_TIME_REGEX ],
|
352
|
-
[ '[EN_MONTH_DD_YYYY_hh_mm]', EN__MONTH_DD_YYYY__DATE_TIME_REGEX ],
|
353
|
-
[ '[EN_MONTH_DD_hh_mm]', EN__MONTH_DD__DATE_TIME_REGEX ],
|
354
|
-
[ '[EN_MONTH_DD_YYYY]', EN__MONTH_DD_YYYY__DATE_REGEX ],
|
355
|
-
[ '[EN_MONTH_DD]', EN__MONTH_DD__DATE_REGEX ],
|
356
|
-
[ '[EN_DD_MONTH]', EN__DD_MONTH__DATE_REGEX ],
|
357
|
-
[ '[ES_DD_MONTH]', ES__DD_MONTH__DATE_REGEX ]
|
358
|
-
]
|
359
|
-
|
360
|
-
|
361
|
-
|
362
|
-
def initialize
|
363
|
-
# nothing here for now
|
364
|
-
end
|
365
|
-
|
366
|
-
def find!( line, opts={} )
|
367
|
-
# fix: use more lookahead for all required trailing spaces!!!!!
|
368
|
-
# fix: use <name capturing group> for month,day,year etc.!!!
|
369
|
-
|
370
|
-
#
|
371
|
-
# fix: !!!!
|
372
|
-
# date in [] will become [[DATE.DE4]] - when getting removed will keep ]!!!!
|
373
|
-
# fix: change regex to \[[A-Z0-9.]\] !!!!!! plus add unit test too!!!
|
374
|
-
#
|
375
|
-
|
376
|
-
md = nil
|
377
|
-
FORMATS.each do |format|
|
378
|
-
tag = format[0]
|
379
|
-
pattern = format[1]
|
380
|
-
md=pattern.match( line )
|
381
|
-
if md
|
382
|
-
date = parse_date_time( md, opts )
|
383
|
-
## fix: use md[0] e.g. match for sub! instead of using regex again - why? why not???
|
384
|
-
## fix: use md.begin(0), md.end(0)
|
385
|
-
line.sub!( md[0], tag )
|
386
|
-
## todo/fix: make sure match data will not get changed (e.g. using sub! before parse_date_time)
|
387
|
-
return date
|
388
|
-
end
|
389
|
-
# no match; continue; try next pattern
|
390
|
-
end
|
391
|
-
|
392
|
-
return nil # no match found
|
393
|
-
end
|
394
|
-
|
395
|
-
end # class DateFinder
|
396
|
-
|
397
|
-
|
398
|
-
class RsssfDateFinder < DateFinderBase
|
399
|
-
|
400
|
-
include LogUtils::Logging
|
401
|
-
|
402
|
-
MONTH_EN = 'Jan|'+
|
403
|
-
'Feb|'+
|
404
|
-
'March|Mar|'+
|
405
|
-
'April|Apr|'+
|
406
|
-
'May|'+
|
407
|
-
'June|Jun|'+
|
408
|
-
'July|Jul|'+
|
409
|
-
'Aug|'+
|
410
|
-
'Sept|Sep|'+
|
411
|
-
'Oct|'+
|
412
|
-
'Nov|'+
|
413
|
-
'Dec'
|
414
|
-
|
415
|
-
## e.g.
|
416
|
-
## [Jun 7] or [Aug 12] etc. - not MUST include brackets e.g. []
|
417
|
-
##
|
418
|
-
## check add \b at the beginning and end - why?? why not?? working??
|
419
|
-
EN__MONTH_DD__DATE_REGEX = /\[
|
420
|
-
(?<month_en>#{MONTH_EN})
|
421
|
-
\s
|
422
|
-
(?<day>\d{1,2})
|
423
|
-
\]/x
|
424
|
-
|
425
|
-
def find!( line, opts={} )
|
426
|
-
# fix: use more lookahead for all required trailing spaces!!!!!
|
427
|
-
# fix: use <name capturing group> for month,day,year etc.!!!
|
428
|
-
|
429
|
-
tag = '[EN_MONTH_DD]'
|
430
|
-
pattern = EN__MONTH_DD__DATE_REGEX
|
431
|
-
md = pattern.match( line )
|
432
|
-
if md
|
433
|
-
date = parse_date_time( md, opts )
|
434
|
-
## fix: use md[0] e.g. match for sub! instead of using regex again - why? why not???
|
435
|
-
## fix: use md.begin(0), md.end(0)
|
436
|
-
line.sub!( md[0], tag )
|
437
|
-
## todo/fix: make sure match data will not get changed (e.g. using sub! before parse_date_time)
|
438
|
-
return date
|
439
|
-
end
|
440
|
-
return nil # no match found
|
441
|
-
end
|
442
|
-
|
443
|
-
|
444
|
-
end ## class RsssfDateFinder
|
445
|
-
|
446
|
-
end # module SportDb
|
data/test/test_date.rb
DELETED
@@ -1,100 +0,0 @@
|
|
1
|
-
# encoding: utf-8
|
2
|
-
|
3
|
-
###
|
4
|
-
# to run use
|
5
|
-
# ruby -I ./lib -I ./test test/test_date.rb
|
6
|
-
|
7
|
-
require 'helper'
|
8
|
-
|
9
|
-
class TestDate < MiniTest::Test
|
10
|
-
|
11
|
-
def test_date
|
12
|
-
data = [
|
13
|
-
[ '19.01.2013 22.00', '2013-01-19 22:00' ],
|
14
|
-
[ '21.01.2013 21.30', '2013-01-21 21:30' ],
|
15
|
-
[ '26.01.2013', '2013-01-26' ],
|
16
|
-
[ '[26.01.2013]', '2013-01-26' ],
|
17
|
-
[ '[21.1.]', '2013-01-21 12:00' ]
|
18
|
-
]
|
19
|
-
|
20
|
-
assert_dates( data, start_at: Date.new( 2013, 1, 1 ) )
|
21
|
-
end
|
22
|
-
|
23
|
-
def test_date_fr
|
24
|
-
data = [
|
25
|
-
[ '[Ven 08. Août]', '2014-08-08' ],
|
26
|
-
[ 'Ven 08. Août', '2014-08-08' ],
|
27
|
-
[ 'Ven 8. Août', '2014-08-08' ],
|
28
|
-
[ '[Sam 9. Août]', '2014-08-09' ],
|
29
|
-
[ '[Dim 10. Août]', '2014-08-10' ],
|
30
|
-
[ '[Sam 31. Janv]', '2015-01-31' ],
|
31
|
-
[ '[Sam 7. Févr]', '2015-02-07' ],
|
32
|
-
[ '[Sam 31. Jan]', '2015-01-31' ],
|
33
|
-
[ '[Sam 7. Fév]', '2015-02-07' ],
|
34
|
-
]
|
35
|
-
|
36
|
-
assert_dates( data, start_at: Date.new( 2014, 8, 1 ) )
|
37
|
-
end
|
38
|
-
|
39
|
-
def test_date_en
|
40
|
-
data = [
|
41
|
-
[ 'Jun/12 2011 14:00', '2011-06-12 14:00' ],
|
42
|
-
[ 'Oct/12 2013 16:00', '2013-10-12 16:00' ],
|
43
|
-
|
44
|
-
[ 'Jan/26 2011', '2011-01-26' ],
|
45
|
-
[ 'Jan/26 2011', '2011-01-26 12:00' ],
|
46
|
-
|
47
|
-
[ 'Jan/26', '2013-01-26' ],
|
48
|
-
[ 'Jan/26', '2013-01-26 12:00' ],
|
49
|
-
[ '26 January', '2013-01-26' ],
|
50
|
-
[ '26 January', '2013-01-26 12:00' ],
|
51
|
-
|
52
|
-
[ 'Jun/13', '2013-06-13' ],
|
53
|
-
[ 'Jun/13', '2013-06-13 12:00' ],
|
54
|
-
[ '13 June', '2013-06-13' ],
|
55
|
-
[ '13 June', '2013-06-13 12:00' ]
|
56
|
-
]
|
57
|
-
|
58
|
-
assert_dates( data, start_at: Date.new( 2013, 1, 1 ) )
|
59
|
-
end
|
60
|
-
|
61
|
-
|
62
|
-
private
|
63
|
-
|
64
|
-
def assert_dates( data, opts )
|
65
|
-
data.each do |rec|
|
66
|
-
line = rec[0]
|
67
|
-
str = rec[1]
|
68
|
-
if str.index( ':' )
|
69
|
-
assert_datetime( DateTime.strptime( str, '%Y-%m-%d %H:%M' ), parse_date( line, opts ))
|
70
|
-
else
|
71
|
-
assert_date( DateTime.strptime( str, '%Y-%m-%d' ), parse_date( line, opts ))
|
72
|
-
end
|
73
|
-
end
|
74
|
-
end
|
75
|
-
|
76
|
-
## todo: check if assert_datetime or assert_date exist already? what is the best practice to check dates ???
|
77
|
-
def assert_date( exp, act )
|
78
|
-
assert_equal exp.year, act.year
|
79
|
-
assert_equal exp.month, act.month
|
80
|
-
assert_equal exp.day, act.day
|
81
|
-
end
|
82
|
-
|
83
|
-
def assert_time( exp, act )
|
84
|
-
assert_equal exp.hour, act.hour
|
85
|
-
assert_equal exp.min, act.min
|
86
|
-
end
|
87
|
-
|
88
|
-
def assert_datetime( exp, act )
|
89
|
-
assert_date( exp, act )
|
90
|
-
assert_time( exp, act )
|
91
|
-
end
|
92
|
-
|
93
|
-
|
94
|
-
def parse_date( line, opts={} )
|
95
|
-
# e.g. lets you pass in opts[:start_at] ???
|
96
|
-
finder = SportDb::DateFinder.new
|
97
|
-
finder.find!( line, opts )
|
98
|
-
end
|
99
|
-
|
100
|
-
end # class TestDate
|