bpl_enrich 0.0.6 → 0.0.7
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 +4 -4
- data/lib/bpl_enrich/dates.rb +5 -2
- data/lib/bpl_enrich/version.rb +1 -1
- data/test/dates_test.rb +43 -31
- data/test/dummy/log/test.log +60 -0
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: f724458c14578154f1ec766c46a67d25b2df49c2
|
4
|
+
data.tar.gz: 3b922f75a5646e7e856aa6746c493a7b8982f67b
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 124289eebef362c4332d5e7fdd57baff97c87f125a81a9374ef1f26826debabd15afe62b234c91487b5e944ea1a128e2b47112c14bff6aaff7c5fdee9ffcebfa
|
7
|
+
data.tar.gz: 906c244fe8a40ed92add65908ad2fe390723858738fe1ef83e23bafb953677c427d1be1db99c974c3cdb4e95ebc3542e2723e867a58d549cb085faaccecb44d0
|
data/lib/bpl_enrich/dates.rb
CHANGED
@@ -52,7 +52,7 @@ module BplEnrich
|
|
52
52
|
# weed out obvious bad dates before processing
|
53
53
|
if (value.match(/([Pp]re|[Pp]ost|[Bb]efore|[Aa]fter|[Uu]nknown|[Uu]ndated|n\.d\.)/)) ||
|
54
54
|
(value.match(/\d\d\d\d-\z/)) || # 1975-
|
55
|
-
(value.match(/\d\d-\d\d\/\d\d/)) || # 1975-09-09/10
|
55
|
+
(value.match(/\d\d-\d\d\/\d\d/) && !value.match(/\d\d-\d\d\/\d\d\d\d/)) || # 1975-09-09/10 but not 1975-09/1975-10
|
56
56
|
(value.match(/\d*\(\d*\)/)) || # 1975(1976)
|
57
57
|
(value.scan(/\d\d\d\d/).length > 2) || # 1861/1869/1915
|
58
58
|
(value.scan(/([Ee]arly|[Ll]ate|[Mm]id|[Ww]inter|[Ss]pring|[Ss]ummer|[Ff]all)/).length > 1) ||
|
@@ -91,7 +91,10 @@ module BplEnrich
|
|
91
91
|
# convert weird span indicators ('or','and','||'), remove extraneous text
|
92
92
|
value = value.gsub(/(or|and|\|\|)/,'-').gsub(/[A-Za-z\?\s]/,'')
|
93
93
|
|
94
|
-
if value.match(/\A[12][\d]{3}-[01][\d]-[12][\d]{3}-[01][\d]\z/) #
|
94
|
+
if value.match(/\A[12][\d]{3}-[01][\d]-[0123][\d][\/-][12][\d]{3}-[01][\d]-[0123][\d]\z/) #1939-04-22/1941-11-30 or 1939-04-22-1941-11-30
|
95
|
+
date_data_range_start = value[0..9]
|
96
|
+
date_data_range_end = value[-10..-1]
|
97
|
+
elsif value.match(/\A[12][\d]{3}-[01][\d][\/-][12][\d]{3}-[01][\d]\z/) # 1895-05-1898-01 or 1895-05/1898-01
|
95
98
|
date_data_range_start = value[0..6]
|
96
99
|
date_data_range_end = value[-7..-1]
|
97
100
|
elsif value.match(/\A[12][\d]{3}\/[12][\d]{3}\z/) # 1987/1988
|
data/lib/bpl_enrich/version.rb
CHANGED
data/test/dates_test.rb
CHANGED
@@ -6,80 +6,92 @@ class DatesTest < ActiveSupport::TestCase
|
|
6
6
|
#Month dates
|
7
7
|
result = BplEnrich::Dates.standardize('April 1983')
|
8
8
|
assert_equal '1983-04', result[:single_date]
|
9
|
-
|
10
|
-
|
9
|
+
assert_nil result[:date_range]
|
10
|
+
assert_nil result[:date_note]
|
11
11
|
|
12
12
|
result = BplEnrich::Dates.standardize('April 7, 1983')
|
13
13
|
assert_equal '1983-04-07', result[:single_date]
|
14
|
-
|
15
|
-
|
14
|
+
assert_nil result[:date_range]
|
15
|
+
assert_nil result[:date_note]
|
16
16
|
|
17
17
|
result = BplEnrich::Dates.standardize('April 7.1983 (Easter)')
|
18
18
|
assert_equal '1983-04-07', result[:single_date]
|
19
|
-
|
19
|
+
assert_nil result[:date_range]
|
20
20
|
assert_equal 'April 7.1983 (Easter)', result[:date_note]
|
21
21
|
|
22
22
|
result = BplEnrich::Dates.standardize('1983.April.7 (Easter)')
|
23
23
|
assert_equal '1983-04-07', result[:single_date]
|
24
|
-
|
24
|
+
assert_nil result[:date_range]
|
25
25
|
assert_equal '1983.April.7 (Easter)', result[:date_note]
|
26
26
|
|
27
27
|
result = BplEnrich::Dates.standardize('between April 2014 and May 2014')
|
28
|
-
|
28
|
+
assert_nil result[:single_date]
|
29
29
|
assert_equal '2014-04', result[:date_range][:start]
|
30
30
|
assert_equal '2014-05', result[:date_range][:end]
|
31
|
-
|
31
|
+
assert_nil result[:date_note]
|
32
32
|
|
33
33
|
result = BplEnrich::Dates.standardize('2000-06')
|
34
34
|
assert_equal '2000-06', result[:single_date]
|
35
|
-
|
36
|
-
|
35
|
+
assert_nil result[:date_range]
|
36
|
+
assert_nil result[:date_note]
|
37
37
|
|
38
38
|
result = BplEnrich::Dates.standardize('17 June 1962')
|
39
39
|
assert_equal '1962-06-17', result[:single_date]
|
40
|
-
|
41
|
-
|
40
|
+
assert_nil result[:date_range]
|
41
|
+
assert_nil result[:date_note]
|
42
42
|
|
43
43
|
result = BplEnrich::Dates.standardize('1860/10-1862/04')
|
44
|
-
|
44
|
+
assert_nil result[:single_date]
|
45
45
|
assert_equal '1860-10', result[:date_range][:start]
|
46
46
|
assert_equal '1862-04', result[:date_range][:end]
|
47
|
-
|
47
|
+
assert_nil result[:date_note]
|
48
48
|
|
49
49
|
|
50
50
|
result = BplEnrich::Dates.standardize('[11-12-1928?]')
|
51
51
|
assert_equal '1928-11-12', result[:single_date]
|
52
|
-
|
53
|
-
|
52
|
+
assert_nil result[:date_range]
|
53
|
+
assert_nil result[:date_note]
|
54
54
|
assert_equal 'questionable', result[:date_qualifier]
|
55
55
|
|
56
56
|
result = BplEnrich::Dates.standardize('Circa 2000')
|
57
57
|
assert_equal '2000', result[:single_date]
|
58
|
-
|
59
|
-
|
58
|
+
assert_nil result[:date_range]
|
59
|
+
assert_nil result[:date_note]
|
60
60
|
assert_equal 'approximate', result[:date_qualifier]
|
61
|
-
assert_equal nil, result[:date_note]
|
62
61
|
|
63
62
|
result = BplEnrich::Dates.standardize('1995-01-00')
|
64
63
|
assert_equal '1995-01', result[:single_date]
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
assert_equal nil, result[:date_note]
|
64
|
+
assert_nil result[:date_range]
|
65
|
+
assert_nil result[:date_note]
|
66
|
+
assert_nil result[:date_qualifier]
|
69
67
|
|
70
68
|
result = BplEnrich::Dates.standardize('1996-00-00')
|
71
69
|
assert_equal '1996', result[:single_date]
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
assert_equal nil, result[:date_note]
|
70
|
+
assert_nil result[:date_range]
|
71
|
+
assert_nil result[:date_note]
|
72
|
+
assert_nil result[:date_qualifier]
|
76
73
|
|
77
74
|
result = BplEnrich::Dates.standardize('1997-00')
|
78
75
|
assert_equal '1997', result[:single_date]
|
79
|
-
|
80
|
-
|
81
|
-
|
82
|
-
|
76
|
+
assert_nil result[:date_range]
|
77
|
+
assert_nil result[:date_note]
|
78
|
+
assert_nil result[:date_qualifier]
|
79
|
+
|
80
|
+
# Example 1 from Woods Hole Scientific Community
|
81
|
+
result = BplEnrich::Dates.standardize('1939-04-22/1941-11-30')
|
82
|
+
assert_nil result[:single_date]
|
83
|
+
assert_equal '1939-04-22', result[:date_range][:start]
|
84
|
+
assert_equal '1941-11-30', result[:date_range][:end]
|
85
|
+
assert_nil result[:date_qualifier]
|
86
|
+
assert_nil result[:date_note]
|
87
|
+
|
88
|
+
# Example 2 from Woods Hole Scientific Community... FIXME: Potentially just 1933?
|
89
|
+
result = BplEnrich::Dates.standardize('1933-01-01/1933-12-31')
|
90
|
+
assert_nil result[:single_date]
|
91
|
+
assert_equal '1933-01-01', result[:date_range][:start]
|
92
|
+
assert_equal '1933-12-31', result[:date_range][:end]
|
93
|
+
assert_nil result[:date_qualifier]
|
94
|
+
assert_nil result[:date_note]
|
83
95
|
end
|
84
96
|
|
85
97
|
|
data/test/dummy/log/test.log
CHANGED
@@ -238,3 +238,63 @@ AuthoritiesTest: test_parse_name_for_role
|
|
238
238
|
AuthoritiesTest: test_parse_role
|
239
239
|
--------------------------------
|
240
240
|
[1m[35m (0.1ms)[0m rollback transaction
|
241
|
+
[1m[36m (0.1ms)[0m [1mbegin transaction[0m
|
242
|
+
------------------------------------
|
243
|
+
AuthoritiesTest: test_parse_language
|
244
|
+
------------------------------------
|
245
|
+
[1m[35m (0.1ms)[0m rollback transaction
|
246
|
+
[1m[36m (0.0ms)[0m [1mbegin transaction[0m
|
247
|
+
-----------------------------------------
|
248
|
+
AuthoritiesTest: test_parse_name_for_role
|
249
|
+
-----------------------------------------
|
250
|
+
[1m[35m (0.1ms)[0m rollback transaction
|
251
|
+
[1m[36m (0.0ms)[0m [1mbegin transaction[0m
|
252
|
+
--------------------------------
|
253
|
+
AuthoritiesTest: test_parse_role
|
254
|
+
--------------------------------
|
255
|
+
[1m[35m (0.1ms)[0m rollback transaction
|
256
|
+
[1m[36m (0.0ms)[0m [1mbegin transaction[0m
|
257
|
+
-------------------------------
|
258
|
+
BplEnrichTest: test_strip_value
|
259
|
+
-------------------------------
|
260
|
+
[1m[35m (0.0ms)[0m rollback transaction
|
261
|
+
[1m[36m (0.0ms)[0m [1mbegin transaction[0m
|
262
|
+
--------------------------------
|
263
|
+
LCSHTest: test_lcsh_standardizer
|
264
|
+
--------------------------------
|
265
|
+
[1m[35m (0.0ms)[0m rollback transaction
|
266
|
+
[1m[36m (0.0ms)[0m [1mbegin transaction[0m
|
267
|
+
---------------------------------
|
268
|
+
DatesTest: test_date_standardizer
|
269
|
+
---------------------------------
|
270
|
+
[1m[35m (0.1ms)[0m rollback transaction
|
271
|
+
[1m[36m (0.1ms)[0m [1mbegin transaction[0m
|
272
|
+
------------------------------------
|
273
|
+
AuthoritiesTest: test_parse_language
|
274
|
+
------------------------------------
|
275
|
+
[1m[35m (0.1ms)[0m rollback transaction
|
276
|
+
[1m[36m (0.0ms)[0m [1mbegin transaction[0m
|
277
|
+
-----------------------------------------
|
278
|
+
AuthoritiesTest: test_parse_name_for_role
|
279
|
+
-----------------------------------------
|
280
|
+
[1m[35m (0.1ms)[0m rollback transaction
|
281
|
+
[1m[36m (0.0ms)[0m [1mbegin transaction[0m
|
282
|
+
--------------------------------
|
283
|
+
AuthoritiesTest: test_parse_role
|
284
|
+
--------------------------------
|
285
|
+
[1m[35m (0.1ms)[0m rollback transaction
|
286
|
+
[1m[36m (0.1ms)[0m [1mbegin transaction[0m
|
287
|
+
-------------------------------
|
288
|
+
BplEnrichTest: test_strip_value
|
289
|
+
-------------------------------
|
290
|
+
[1m[35m (0.0ms)[0m rollback transaction
|
291
|
+
[1m[36m (0.0ms)[0m [1mbegin transaction[0m
|
292
|
+
--------------------------------
|
293
|
+
LCSHTest: test_lcsh_standardizer
|
294
|
+
--------------------------------
|
295
|
+
[1m[35m (0.1ms)[0m rollback transaction
|
296
|
+
[1m[36m (0.0ms)[0m [1mbegin transaction[0m
|
297
|
+
---------------------------------
|
298
|
+
DatesTest: test_date_standardizer
|
299
|
+
---------------------------------
|
300
|
+
[1m[35m (0.0ms)[0m rollback transaction
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: bpl_enrich
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.7
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Boston Public Library
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-01-
|
11
|
+
date: 2017-01-25 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rails
|