pennmarc 1.0.0 → 1.0.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.rubocop.yml +3 -0
- data/.rubocop_todo.yml +37 -21
- data/Gemfile.lock +3 -0
- data/README.md +12 -2
- data/lib/pennmarc/helpers/creator.rb +24 -20
- data/lib/pennmarc/helpers/edition.rb +15 -13
- data/lib/pennmarc/helpers/format.rb +3 -3
- data/lib/pennmarc/helpers/genre.rb +5 -4
- data/lib/pennmarc/helpers/helper.rb +1 -0
- data/lib/pennmarc/helpers/identifier.rb +32 -15
- data/lib/pennmarc/helpers/language.rb +3 -3
- data/lib/pennmarc/helpers/location.rb +10 -10
- data/lib/pennmarc/helpers/note.rb +0 -2
- data/lib/pennmarc/helpers/relation.rb +7 -7
- data/lib/pennmarc/helpers/series.rb +19 -31
- data/lib/pennmarc/helpers/subject.rb +11 -11
- data/lib/pennmarc/helpers/title.rb +1 -1
- data/lib/pennmarc/mappers.rb +31 -0
- data/lib/pennmarc/parser.rb +36 -62
- data/lib/pennmarc/util.rb +10 -11
- data/lib/pennmarc/version.rb +5 -0
- data/pennmarc.gemspec +5 -1
- data/spec/lib/pennmarc/helpers/creator_spec.rb +9 -9
- data/spec/lib/pennmarc/helpers/edition_spec.rb +3 -2
- data/spec/lib/pennmarc/helpers/format_spec.rb +1 -1
- data/spec/lib/pennmarc/helpers/genre_spec.rb +1 -1
- data/spec/lib/pennmarc/helpers/identifer_spec.rb +43 -14
- data/spec/lib/pennmarc/helpers/language_spec.rb +1 -1
- data/spec/lib/pennmarc/helpers/location_spec.rb +8 -8
- data/spec/lib/pennmarc/helpers/relation_spec.rb +2 -2
- data/spec/lib/pennmarc/helpers/series_spec.rb +6 -5
- data/spec/lib/pennmarc/helpers/subject_spec.rb +1 -1
- data/spec/lib/pennmarc/parser_spec.rb +22 -1
- metadata +7 -8
- data/legacy/indexer.rb +0 -568
- data/legacy/marc.rb +0 -2964
- data/legacy/test_file_output.json +0 -49
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 33527bf43532170690b9b591097fb03f854130b3383debfafe931417d0394f52
|
4
|
+
data.tar.gz: a18a5be08df6d7b74d2aaa61275cdecdedec6caa4b5e8b2b81c99e91411ce093
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 627a4da06351037f520bc02b0a9fd61ce6cfdec35c563f2b29e3c1c01b4ad76766f155630cafe680b010783ea4f4c285df2d499fd784b7ee4f3cb4948cd421dd
|
7
|
+
data.tar.gz: c966233bb00009a14babc5bc92f0399e75640e886f7c32d176fea8983813aca8936d0e8fab98576a797afaf0b60c5f24268c2ae4e2d8cca31900e590db0a9bc6
|
data/.rubocop.yml
CHANGED
data/.rubocop_todo.yml
CHANGED
@@ -1,12 +1,36 @@
|
|
1
1
|
# This configuration was generated by
|
2
2
|
# `rubocop --auto-gen-config --auto-gen-only-exclude --exclude-limit 10000`
|
3
|
-
# on 2023-
|
3
|
+
# on 2023-08-25 13:55:25 UTC using RuboCop version 1.51.0.
|
4
4
|
# The point is for the user to remove these configuration records
|
5
5
|
# one by one as the offenses are removed from the code base.
|
6
6
|
# Note that changes in the inspected code, or installation of new
|
7
7
|
# versions of RuboCop, may require this file to be generated again.
|
8
8
|
|
9
|
-
# Offense count:
|
9
|
+
# Offense count: 2
|
10
|
+
# This cop supports safe autocorrection (--autocorrect).
|
11
|
+
# Configuration parameters: EnforcedStyle, IndentationWidth.
|
12
|
+
# SupportedStyles: with_first_argument, with_fixed_indentation
|
13
|
+
Layout/ArgumentAlignment:
|
14
|
+
Exclude:
|
15
|
+
- 'spec/lib/pennmarc/helpers/series_spec.rb'
|
16
|
+
|
17
|
+
# Offense count: 1
|
18
|
+
# This cop supports safe autocorrection (--autocorrect).
|
19
|
+
# Configuration parameters: EnforcedStyle.
|
20
|
+
# SupportedStyles: empty_lines, no_empty_lines
|
21
|
+
Layout/EmptyLinesAroundBlockBody:
|
22
|
+
Exclude:
|
23
|
+
- 'spec/lib/pennmarc/helpers/identifer_spec.rb'
|
24
|
+
|
25
|
+
# Offense count: 1
|
26
|
+
# This cop supports safe autocorrection (--autocorrect).
|
27
|
+
# Configuration parameters: EnforcedStyle.
|
28
|
+
# SupportedStyles: final_newline, final_blank_line
|
29
|
+
Layout/TrailingEmptyLines:
|
30
|
+
Exclude:
|
31
|
+
- 'spec/lib/pennmarc/helpers/identifer_spec.rb'
|
32
|
+
|
33
|
+
# Offense count: 22
|
10
34
|
# Configuration parameters: AllowedMethods, AllowedPatterns, CountRepeatedAttributes, Max.
|
11
35
|
Metrics/AbcSize:
|
12
36
|
Exclude:
|
@@ -50,7 +74,7 @@ Metrics/CyclomaticComplexity:
|
|
50
74
|
- 'lib/pennmarc/helpers/title.rb'
|
51
75
|
- 'lib/pennmarc/util.rb'
|
52
76
|
|
53
|
-
# Offense count:
|
77
|
+
# Offense count: 24
|
54
78
|
# Configuration parameters: CountComments, Max, CountAsOne, AllowedMethods, AllowedPatterns.
|
55
79
|
Metrics/MethodLength:
|
56
80
|
Exclude:
|
@@ -86,6 +110,14 @@ Metrics/PerceivedComplexity:
|
|
86
110
|
- 'lib/pennmarc/helpers/title.rb'
|
87
111
|
- 'lib/pennmarc/util.rb'
|
88
112
|
|
113
|
+
# Offense count: 4
|
114
|
+
# This cop supports safe autocorrection (--autocorrect).
|
115
|
+
# Configuration parameters: EnforcedStyle, BlockForwardingName.
|
116
|
+
# SupportedStyles: anonymous, explicit
|
117
|
+
Naming/BlockForwarding:
|
118
|
+
Exclude:
|
119
|
+
- 'lib/pennmarc/util.rb'
|
120
|
+
|
89
121
|
# Offense count: 1
|
90
122
|
# Configuration parameters: NamePrefix, ForbiddenPrefixes, AllowedMethods, MethodDefinitionMacros.
|
91
123
|
# NamePrefix: is_, has_, have_
|
@@ -96,7 +128,7 @@ Naming/PredicateName:
|
|
96
128
|
Exclude:
|
97
129
|
- 'lib/pennmarc/helpers/relation.rb'
|
98
130
|
|
99
|
-
# Offense count:
|
131
|
+
# Offense count: 1
|
100
132
|
# Configuration parameters: EnforcedStyle, CheckMethodNames, CheckSymbols, AllowedIdentifiers, AllowedPatterns.
|
101
133
|
# SupportedStyles: snake_case, normalcase, non_integer
|
102
134
|
# AllowedIdentifiers: capture3, iso8601, rfc1123_date, rfc822, rfc2822, rfc3339, x86_64
|
@@ -104,14 +136,6 @@ Naming/VariableNumber:
|
|
104
136
|
Exclude:
|
105
137
|
- 'lib/pennmarc/util.rb'
|
106
138
|
|
107
|
-
# Offense count: 7
|
108
|
-
# Configuration parameters: MinSize.
|
109
|
-
Performance/CollectionLiteralInLoop:
|
110
|
-
Exclude:
|
111
|
-
- 'lib/pennmarc/helpers/creator.rb'
|
112
|
-
- 'lib/pennmarc/helpers/edition.rb'
|
113
|
-
- 'lib/pennmarc/helpers/series.rb'
|
114
|
-
|
115
139
|
# Offense count: 6
|
116
140
|
# Configuration parameters: Max, CountAsOne.
|
117
141
|
RSpec/ExampleLength:
|
@@ -135,17 +159,9 @@ RSpec/NestedGroups:
|
|
135
159
|
- 'spec/lib/pennmarc/helpers/format_spec.rb'
|
136
160
|
|
137
161
|
# Offense count: 2
|
138
|
-
# This cop supports unsafe autocorrection (--autocorrect-all).
|
139
|
-
# Configuration parameters: Include.
|
140
|
-
# Include: app/**/*.rb, config/**/*.rb, db/**/*.rb, lib/**/*.rb
|
141
|
-
Rails/Output:
|
142
|
-
Exclude:
|
143
|
-
- 'lib/pennmarc/helpers/date.rb'
|
144
|
-
|
145
|
-
# Offense count: 1
|
146
162
|
# This cop supports safe autocorrection (--autocorrect).
|
147
163
|
# Configuration parameters: Max, AllowHeredoc, AllowURI, URISchemes, IgnoreCopDirectives, AllowedPatterns.
|
148
164
|
# URISchemes: http, https
|
149
165
|
Layout/LineLength:
|
150
166
|
Exclude:
|
151
|
-
- 'lib/pennmarc/helpers/
|
167
|
+
- 'spec/lib/pennmarc/helpers/creator_spec.rb'
|
data/Gemfile.lock
CHANGED
@@ -21,6 +21,8 @@ GEM
|
|
21
21
|
minitest (5.18.0)
|
22
22
|
nokogiri (1.15.2-arm64-darwin)
|
23
23
|
racc (~> 1.4)
|
24
|
+
nokogiri (1.15.2-x64-mingw-ucrt)
|
25
|
+
racc (~> 1.4)
|
24
26
|
nokogiri (1.15.2-x86_64-linux)
|
25
27
|
racc (~> 1.4)
|
26
28
|
parallel (1.23.0)
|
@@ -101,6 +103,7 @@ GEM
|
|
101
103
|
PLATFORMS
|
102
104
|
arm64-darwin-21
|
103
105
|
arm64-darwin-22
|
106
|
+
x64-mingw-ucrt
|
104
107
|
x86_64-linux
|
105
108
|
|
106
109
|
DEPENDENCIES
|
data/README.md
CHANGED
@@ -53,6 +53,12 @@ To run rubocop with the configuration:
|
|
53
53
|
rubocop
|
54
54
|
```
|
55
55
|
|
56
|
+
#### To regenerate `.rubocop_todo.yml`:
|
57
|
+
```shell
|
58
|
+
bundle exec rubocop --auto-gen-config --auto-gen-only-exclude --exclude-limit 10000
|
59
|
+
```
|
60
|
+
|
61
|
+
|
56
62
|
### Testing
|
57
63
|
|
58
64
|
Testing is done with `rspec`. Test coverage should approach 100% given the relative simplicity of this gem.
|
@@ -63,6 +69,12 @@ To run the test suite:
|
|
63
69
|
rspec
|
64
70
|
```
|
65
71
|
|
72
|
+
## Publishing the Gem
|
73
|
+
|
74
|
+
1. Update the version in `pennmarc.gemspec`
|
75
|
+
2. Run `gem build pennmarc.gemspec` with the latest code
|
76
|
+
3. Run `gem push pennmarc-{version number here}`(e.g. `gem push pennmarc-1.0.0`) to push to RubyGems. You will need access and MFA setup with RubyGems.
|
77
|
+
|
66
78
|
## QA
|
67
79
|
|
68
80
|
### Checking output of an arbitrary MARC XML file
|
@@ -75,8 +87,6 @@ MARC_FILE=path/to/marc.xml bundle exec rake pennmarc:parse
|
|
75
87
|
|
76
88
|
## TODO
|
77
89
|
- rake task or some similar command to return a full set of values extracted from a specified marcxml file
|
78
|
-
- hosting of yard output files?
|
79
|
-
- mappings (locations, call number, languages)
|
80
90
|
- Pipeline to run tests and publish to Rubygems
|
81
91
|
- rubocop check
|
82
92
|
- rdoc/yard coverage checks?
|
@@ -24,17 +24,18 @@ module PennMARC
|
|
24
24
|
# indicator1 tell us the order of the name?
|
25
25
|
# @note ported from get_author_creator_1_search_values
|
26
26
|
# @param [MARC::Record] record
|
27
|
-
# @param [Hash]
|
27
|
+
# @param [Hash] relator_map
|
28
28
|
# @return [Array<String>] array of author/creator values for indexing
|
29
|
-
def search(record,
|
29
|
+
def search(record, relator_map: Mappers.relator)
|
30
|
+
creator_subfields = %w[a 1 4 6 8]
|
30
31
|
acc = record.fields(TAGS).map do |field|
|
31
32
|
pieces = field.filter_map do |sf|
|
32
33
|
if sf.code == 'a'
|
33
34
|
convert_name_order(sf.value)
|
34
|
-
elsif
|
35
|
+
elsif creator_subfields.exclude?(sf.code)
|
35
36
|
sf.value
|
36
37
|
elsif sf.code == '4'
|
37
|
-
relator = translate_relator(sf.value,
|
38
|
+
relator = translate_relator(sf.value, relator_map)
|
38
39
|
next if relator.blank?
|
39
40
|
|
40
41
|
relator
|
@@ -48,12 +49,13 @@ module PennMARC
|
|
48
49
|
end
|
49
50
|
end
|
50
51
|
# a second iteration over the same fields produces name entries with the names not reordered
|
52
|
+
secondary_subfields = %w[4 6 8]
|
51
53
|
acc += record.fields(TAGS).map do |field|
|
52
54
|
pieces = field.filter_map do |sf|
|
53
|
-
if
|
55
|
+
if secondary_subfields.exclude?(sf.code)
|
54
56
|
sf.value
|
55
57
|
elsif sf.code == '4'
|
56
|
-
relator = translate_relator(sf.value,
|
58
|
+
relator = translate_relator(sf.value, relator_map)
|
57
59
|
next if relator.blank?
|
58
60
|
|
59
61
|
relator
|
@@ -88,11 +90,11 @@ module PennMARC
|
|
88
90
|
# All author/creator values for display (like #show, but multivalued?) - no 880 linkage
|
89
91
|
# @note ported from get_author_creator_values (indexed as author_creator_a) - shown on results page
|
90
92
|
# @param [MARC::Record] record
|
91
|
-
# @param [Hash]
|
93
|
+
# @param [Hash] relator_map
|
92
94
|
# @return [Array<String>] array of author/creator values for display
|
93
|
-
def values(record,
|
95
|
+
def values(record, relator_map: Mappers.relator)
|
94
96
|
record.fields(TAGS).map do |field|
|
95
|
-
name_from_main_entry(field,
|
97
|
+
name_from_main_entry(field, relator_map)
|
96
98
|
end
|
97
99
|
end
|
98
100
|
|
@@ -109,8 +111,7 @@ module PennMARC
|
|
109
111
|
end
|
110
112
|
end
|
111
113
|
|
112
|
-
# Author/Creator sort. Does not map and include any relator
|
113
|
-
# codes.
|
114
|
+
# Author/Creator sort. Does not map and include any relator codes.
|
114
115
|
# @todo This includes any URI from ǂ0 which could help to disambiguate in sorts, but ǂ1 is excluded...
|
115
116
|
# @note ported from get_author_creator_sort_values
|
116
117
|
# @param [MARC::Record] record
|
@@ -143,11 +144,11 @@ module PennMARC
|
|
143
144
|
# Conference for display, intended for results display
|
144
145
|
# @note ported from get_conference_values
|
145
146
|
# @param [MARC::Record] record
|
146
|
-
# @param [Hash]
|
147
|
+
# @param [Hash] relator_map
|
147
148
|
# @return [Array<String>] array of conference values
|
148
|
-
def conference_show(record,
|
149
|
+
def conference_show(record, relator_map: Mappers.relator)
|
149
150
|
record.fields('111').filter_map do |field|
|
150
|
-
name_from_main_entry field,
|
151
|
+
name_from_main_entry field, relator_map
|
151
152
|
end
|
152
153
|
end
|
153
154
|
|
@@ -188,19 +189,21 @@ module PennMARC
|
|
188
189
|
# 'a', 'b', 'c', 'd', 'j', and 'q'. Then appends resulting string with joined subfields 'e', 'u', '3', and '4'.
|
189
190
|
# @note legacy version returns array of hash objects including data for display link
|
190
191
|
# @param [MARC::Record] record
|
191
|
-
# @ param [Hash]
|
192
|
+
# @ param [Hash] relator_map
|
192
193
|
# @return [Array<String>]
|
193
|
-
def contributor_show(record,
|
194
|
+
def contributor_show(record, relator_map: Mappers.relator)
|
195
|
+
indicator_2_options = ['', ' ', '0']
|
194
196
|
contributors = record.fields(%w[700 710]).filter_map do |field|
|
195
|
-
next unless
|
197
|
+
next unless indicator_2_options.member?(field.indicator2)
|
196
198
|
next if subfield_defined? field, 'i'
|
197
199
|
|
198
200
|
contributor = join_subfields(field, &subfield_in?(%w[a b c d j q]))
|
201
|
+
contributor_append_subfields = %w[e u 3 4]
|
199
202
|
contributor_append = field.filter_map { |subfield|
|
200
|
-
next unless
|
203
|
+
next unless contributor_append_subfields.member?(subfield.code)
|
201
204
|
|
202
205
|
if subfield.code == '4'
|
203
|
-
", #{translate_relator(subfield.value,
|
206
|
+
", #{translate_relator(subfield.value, relator_map)}"
|
204
207
|
else
|
205
208
|
" #{subfield.value}"
|
206
209
|
end
|
@@ -243,8 +246,9 @@ module PennMARC
|
|
243
246
|
# @param [MARC::Field] field
|
244
247
|
# @return [String] joined subfield values for value from field
|
245
248
|
def name_from_main_entry(field, mapping)
|
249
|
+
name_subfields = %w[0 1 4 6 8]
|
246
250
|
s = field.filter_map { |sf|
|
247
|
-
if
|
251
|
+
if name_subfields.exclude?(sf.code)
|
248
252
|
" #{sf.value}"
|
249
253
|
elsif sf.code == '4'
|
250
254
|
relator = translate_relator(sf.value, mapping)
|
@@ -34,47 +34,49 @@ module PennMARC
|
|
34
34
|
# display.
|
35
35
|
# https://www.loc.gov/marc/bibliographic/bd775.html
|
36
36
|
# @param [MARC::Record] record
|
37
|
-
# @param [Hash]
|
37
|
+
# @param [Hash] relator_map
|
38
38
|
# @return [Array<String>] array of other edition strings
|
39
|
-
def other_show(record,
|
39
|
+
def other_show(record, relator_map: Mappers.relator)
|
40
40
|
values = record.fields('775').filter_map do |field|
|
41
41
|
next unless subfield_defined?(field, :i)
|
42
42
|
|
43
|
-
other_edition_value(field,
|
43
|
+
other_edition_value(field, relator_map)
|
44
44
|
end
|
45
|
-
values
|
45
|
+
values + record.fields('880').filter_map do |field|
|
46
46
|
next unless field.indicator2.blank? && subfield_value_in?(field, '6', %w[775]) &&
|
47
47
|
subfield_defined?(field, 'i')
|
48
48
|
|
49
|
-
other_edition_value(field,
|
49
|
+
other_edition_value(field, relator_map)
|
50
50
|
end
|
51
|
-
values
|
52
51
|
end
|
53
52
|
|
54
53
|
private
|
55
54
|
|
56
55
|
# Assemble a string of relevant edition information.
|
57
56
|
# @param [MARC::DataField] field
|
58
|
-
# @param [Hash]
|
57
|
+
# @param [Hash] relator_map
|
59
58
|
# @return [String (frozen)] assembled other version string
|
60
|
-
def other_edition_value(field,
|
59
|
+
def other_edition_value(field, relator_map)
|
61
60
|
subi = remove_paren_value_from_subfield_i(field) || ''
|
61
|
+
excluded_subfields = %w[6 8]
|
62
|
+
other_edition_subfields = %w[s x z]
|
62
63
|
other_editions = field.filter_map { |sf|
|
63
|
-
next if
|
64
|
+
next if excluded_subfields.member?(sf.code)
|
64
65
|
|
65
|
-
if
|
66
|
+
if other_edition_subfields.member?(sf.code)
|
66
67
|
" #{sf.value}"
|
67
68
|
elsif sf.code == 't'
|
68
|
-
relator = translate_relator(sf.value,
|
69
|
+
relator = translate_relator(sf.value, relator_map)
|
69
70
|
next if relator.blank?
|
70
71
|
|
71
72
|
" #{relator}. "
|
72
73
|
end
|
73
74
|
}.join
|
75
|
+
other_editions_append_subfields = %w[i h s t x z e f o r w y 7]
|
74
76
|
other_editions_append = field.filter_map { |sf|
|
75
|
-
next if
|
77
|
+
next if excluded_subfields.member?(sf.code)
|
76
78
|
|
77
|
-
if
|
79
|
+
if other_editions_append_subfields.exclude?(sf.code)
|
78
80
|
" #{sf.value}"
|
79
81
|
elsif sf.code == 'h'
|
80
82
|
" (#{sf.value}) "
|
@@ -68,10 +68,10 @@ module PennMARC
|
|
68
68
|
# for this helper method
|
69
69
|
# @note ported from get_format
|
70
70
|
# @param [MARC::Record] record
|
71
|
-
# @param [Hash]
|
71
|
+
# @param [Hash] location_map
|
72
72
|
# @return [Array<String>] format values for faceting
|
73
73
|
|
74
|
-
def facet(record,
|
74
|
+
def facet(record, location_map: Mappers.location)
|
75
75
|
formats = []
|
76
76
|
format_code = leader_format(record.leader)
|
77
77
|
f007 = record.fields('007').map(&:value)
|
@@ -88,7 +88,7 @@ module PennMARC
|
|
88
88
|
end
|
89
89
|
|
90
90
|
# get all specific_location values from inventory info
|
91
|
-
locations = Location.location record: record,
|
91
|
+
locations = Location.location record: record, location_map: location_map,
|
92
92
|
display_value: :specific_location
|
93
93
|
|
94
94
|
if include_manuscripts?(locations)
|
@@ -34,8 +34,9 @@ module PennMARC
|
|
34
34
|
|
35
35
|
next if field.tag == '880' && subfield_values(field, '6').exclude?('655')
|
36
36
|
|
37
|
+
subfields = %w[a b]
|
37
38
|
sub_with_hyphens = field.find_all(&subfield_not_in?(%w[0 2 5 6 8 c e w])).map { |sf|
|
38
|
-
sep =
|
39
|
+
sep = subfields.exclude?(sf.code) ? ' -- ' : ' '
|
39
40
|
sep + sf.value
|
40
41
|
}.join.lstrip
|
41
42
|
"#{sub_with_hyphens} #{field.find_all(&subfield_in?(%w[e w])).join(' -- ')}".strip
|
@@ -46,10 +47,10 @@ module PennMARC
|
|
46
47
|
# @todo the Genre facet in Franklin is pretty ugly. It could be cleaned up by limiting the subfields included
|
47
48
|
# here and cleaning up punctuation.
|
48
49
|
# @param [MARC::Record] record
|
49
|
-
# @param [Hash]
|
50
|
+
# @param [Hash] location_map
|
50
51
|
# @return [Array<String>]
|
51
|
-
def facet(record,
|
52
|
-
locations = Location.location record: record,
|
52
|
+
def facet(record, location_map: Mappers.location)
|
53
|
+
locations = Location.location record: record, location_map: location_map,
|
53
54
|
display_value: :specific_location
|
54
55
|
manuscript = Format.include_manuscripts?(locations)
|
55
56
|
video = record.fields('007').any? { |field| field.value.starts_with? 'v' }
|
@@ -33,14 +33,12 @@ module PennMARC
|
|
33
33
|
#
|
34
34
|
# @param [MARC::Record] record
|
35
35
|
# @return [Array<String>]
|
36
|
-
# @todo look into z subfield for 020 field, should we show cancelled isbn?
|
37
36
|
def isbn_show(record)
|
38
37
|
isbn_values = record.fields('020').filter_map do |field|
|
39
|
-
joined_isbn = join_subfields(field, &subfield_in?(%w[a
|
38
|
+
joined_isbn = join_subfields(field, &subfield_in?(%w[a]))
|
40
39
|
joined_isbn.presence
|
41
40
|
end
|
42
|
-
isbn_values
|
43
|
-
isbn_values
|
41
|
+
isbn_values + linked_alternate(record, '020', &subfield_in?(%w[a]))
|
44
42
|
end
|
45
43
|
|
46
44
|
# Get ISSN values for display from the {https://www.oclc.org/bibformats/en/0xx/022.html 022 field} and related
|
@@ -50,11 +48,10 @@ module PennMARC
|
|
50
48
|
# @return [Array<String>]
|
51
49
|
def issn_show(record)
|
52
50
|
issn_values = record.fields('022').filter_map do |field|
|
53
|
-
joined_issn = join_subfields(field, &subfield_in?(%w[a
|
51
|
+
joined_issn = join_subfields(field, &subfield_in?(%w[a]))
|
54
52
|
joined_issn.presence
|
55
53
|
end
|
56
|
-
issn_values
|
57
|
-
issn_values
|
54
|
+
issn_values + linked_alternate(record, '022', &subfield_in?(%w[a]))
|
58
55
|
end
|
59
56
|
|
60
57
|
# Get numeric OCLC ID of first {https://www.oclc.org/bibformats/en/0xx/035.html 035 field}
|
@@ -85,17 +82,22 @@ module PennMARC
|
|
85
82
|
|
86
83
|
# Get publisher issued identifiers from fields {https://www.oclc.org/bibformats/en/0xx/024.html 024},
|
87
84
|
# {https://www.oclc.org/bibformats/en/0xx/024.html 028}, and related
|
88
|
-
# {https://www.oclc.org/bibformats/en/8xx/880.html 880 field}.
|
85
|
+
# {https://www.oclc.org/bibformats/en/8xx/880.html 880 field}. We do not return DOI values stored in 024 ǂ2,
|
86
|
+
# see {PennMARC::Identifier.doi_show} for parsing DOI values.
|
89
87
|
#
|
90
88
|
# @param [MARC::Record] record
|
91
89
|
# @return [Array<string>]
|
92
90
|
def publisher_number_show(record)
|
93
|
-
|
94
|
-
|
95
|
-
|
91
|
+
record.fields(%w[024 028 880]).filter_map do |field|
|
92
|
+
next if field.tag == '880' && subfield_value_not_in?(field, '6', %w[024 028])
|
93
|
+
|
94
|
+
# do not return doi values from 024 ǂ2
|
95
|
+
if field.tag == '024' && subfield_value_in?(field, '2', %w[doi])
|
96
|
+
join_subfields(field, &subfield_not_in?(%w[a 2 5 6])).presence
|
97
|
+
else
|
98
|
+
join_subfields(field, &subfield_not_in?(%w[5 6])).presence
|
99
|
+
end
|
96
100
|
end
|
97
|
-
publisher_numbers += linked_alternate(record, %w[024 028], &subfield_not_in?(%w[5 6]))
|
98
|
-
publisher_numbers
|
99
101
|
end
|
100
102
|
|
101
103
|
# Get publisher issued identifiers for searching of a record. Values extracted from fields
|
@@ -119,6 +121,21 @@ module PennMARC
|
|
119
121
|
end
|
120
122
|
end
|
121
123
|
|
124
|
+
# Retrieve DOI values stored in {https://www.oclc.org/bibformats/en/0xx/024.html 024}.
|
125
|
+
# Penn MARC records give the first indicator a value of '7' and ǂ2 a value of 'doi' to denote that ǂa is a doi.
|
126
|
+
# @param [MARC::Record] record
|
127
|
+
# @return [Array<String>]
|
128
|
+
def doi_show(record)
|
129
|
+
record.fields('024').filter_map do |field|
|
130
|
+
# skip unless indicator1 is '7'
|
131
|
+
next unless field.indicator1.in?(%w[7])
|
132
|
+
# skip unless ǂ2 is the string literal 'doi'
|
133
|
+
next unless subfield_value_in?(field, '2', %w[doi])
|
134
|
+
|
135
|
+
join_subfields(field, &subfield_in?(%w[a]))
|
136
|
+
end
|
137
|
+
end
|
138
|
+
|
122
139
|
private
|
123
140
|
|
124
141
|
# Determine if subfield 'a' is an OCLC id.
|
@@ -126,11 +143,11 @@ module PennMARC
|
|
126
143
|
# @param [MARC::Subfield]
|
127
144
|
# @return [TrueClass, FalseClass]
|
128
145
|
def subfield_a_is_oclc?(subfield)
|
129
|
-
subfield.code == 'a' && subfield.value =~ /^\(OCoLC\).*/
|
146
|
+
subfield.code == 'a' && (subfield.value =~ /^\(OCoLC\).*/).present?
|
130
147
|
end
|
131
148
|
|
132
149
|
# Normalize isbn value using {https://github.com/billdueber/library_stdnums library_stdnums gem}.
|
133
|
-
# Converts ISBN10 (ten-digit) to validated ISBN13 (
|
150
|
+
# Converts ISBN10 (ten-digit) to validated ISBN13 (thirteen-digit) and returns both values. If passed
|
134
151
|
# ISBN13 parameter, only returns validated ISBN13 value.
|
135
152
|
#
|
136
153
|
# @param [String] isbn
|
@@ -25,12 +25,12 @@ module PennMARC
|
|
25
25
|
# the 008 control field. Language facet and search values will typically be the same.
|
26
26
|
#
|
27
27
|
# @param [MARC::Record] record
|
28
|
-
# @param [Hash]
|
28
|
+
# @param [Hash] language_map hash for language code translation
|
29
29
|
# @return [String] nice value for language
|
30
|
-
def search(record,
|
30
|
+
def search(record, language_map: Mappers.language)
|
31
31
|
control_field = record['008']&.value
|
32
32
|
language_code = control_field[35..37]
|
33
|
-
|
33
|
+
language_map[language_code.to_sym || UNDETERMINED_CODE]
|
34
34
|
end
|
35
35
|
end
|
36
36
|
end
|
@@ -10,10 +10,10 @@ module PennMARC
|
|
10
10
|
# @see https://developers.exlibrisgroup.com/alma/apis/docs/bibs/R0VUIC9hbG1hd3MvdjEvYmlicy97bW1zX2lkfQ==/
|
11
11
|
# Alma documentation for these added fields
|
12
12
|
# @param [MARC::Record] record
|
13
|
-
# @param [Hash]
|
13
|
+
# @param [Hash] location_map hash with location_code as key and location hash as value
|
14
14
|
# @return [Array<String>] Array of library locations retrieved from location_map
|
15
|
-
def library(record,
|
16
|
-
location(record: record,
|
15
|
+
def library(record, location_map: Mappers.location)
|
16
|
+
location(record: record, location_map: location_map, display_value: 'library')
|
17
17
|
end
|
18
18
|
|
19
19
|
# Retrieves the specific location from enriched marc 'itm' or 'hld' fields, giving priority to the item location
|
@@ -23,10 +23,10 @@ module PennMARC
|
|
23
23
|
# @see https://developers.exlibrisgroup.com/alma/apis/docs/bibs/R0VUIC9hbG1hd3MvdjEvYmlicy97bW1zX2lkfQ==/
|
24
24
|
# Alma documentation for these added fields
|
25
25
|
# @param [MARC::Record] record
|
26
|
-
# @param [Hash]
|
26
|
+
# @param [Hash] location_map hash with location_code as key and location hash as value
|
27
27
|
# @return [Array<String>] Array of specific locations retrieved from location_map
|
28
|
-
def specific_location(record,
|
29
|
-
location(record: record,
|
28
|
+
def specific_location(record, location_map: Mappers.location)
|
29
|
+
location(record: record, location_map: location_map, display_value: 'specific_location')
|
30
30
|
end
|
31
31
|
|
32
32
|
# Base method to retrieve location data from enriched marc 'itm' or 'hld' fields, giving priority to the item
|
@@ -36,9 +36,9 @@ module PennMARC
|
|
36
36
|
# Alma documentation for these added fields
|
37
37
|
# @param [MARC::Record] record
|
38
38
|
# @param [Symbol | String] display_value field in location hash to retrieve
|
39
|
-
# @param [Hash]
|
39
|
+
# @param [Hash] location_map hash with location_code as key and location hash as value
|
40
40
|
# @return [Array<String>]
|
41
|
-
def location(record:, display_value:,
|
41
|
+
def location(record:, display_value:, location_map:)
|
42
42
|
# get enriched marc location tag and subfield code
|
43
43
|
location_tag_and_subfield_code(record) => {tag:, subfield_code:}
|
44
44
|
|
@@ -56,9 +56,9 @@ module PennMARC
|
|
56
56
|
# sometimes "happening locations" are mistakenly used in holdings records.
|
57
57
|
# that's a data problem that should be fixed.
|
58
58
|
# here, if we encounter a code we can't map, we ignore it, for faceting purposes
|
59
|
-
next unless
|
59
|
+
next unless location_map.key?(subfield.value.to_sym)
|
60
60
|
|
61
|
-
|
61
|
+
location_map[subfield.value.to_sym][display_value.to_sym]
|
62
62
|
}.flatten.compact_blank
|
63
63
|
}.uniq
|
64
64
|
locations << 'Online library' if record.fields(PennMARC::EnrichedMarc::TAG_ELECTRONIC_INVENTORY).any?
|
@@ -11,8 +11,6 @@ module PennMARC
|
|
11
11
|
# {https://www.oclc.org/bibformats/en/5xx/550.html 550}, {https://www.oclc.org/bibformats/en/5xx/580.html 580},
|
12
12
|
# {https://www.oclc.org/bibformats/en/5xx/586.html 586}, {https://www.oclc.org/bibformats/en/5xx/588.html 588},
|
13
13
|
# and their linked alternates.
|
14
|
-
# @todo legacy implementation used conditional to separate join logic for 588 field. However, this doesn't seem
|
15
|
-
# necessary because 588 only has subfields 'a', '5', '6', and '8'. Do we need to look into this?
|
16
14
|
# @param [MARC::Record] record
|
17
15
|
# @return [Array<String>]
|
18
16
|
def notes_show(record)
|
@@ -46,15 +46,15 @@ module PennMARC
|
|
46
46
|
# Get related work from {RELATED_WORK_FIELDS} in the 7XX range. Require presence of sf t (title) and absence of
|
47
47
|
# an indicator2 value. Prefix returned values with sf i value. Also map relator codes found in sf 4. Ignore sf 0.
|
48
48
|
# @param [MARC::Record] record
|
49
|
-
# @param [Hash]
|
49
|
+
# @param [Hash] relator_map
|
50
50
|
# @return [Array]
|
51
|
-
def related_work_show(record,
|
51
|
+
def related_work_show(record, relator_map: Mappers.relator)
|
52
52
|
values = record.fields(RELATED_WORK_FIELDS).filter_map do |field|
|
53
53
|
next if field.indicator2.present?
|
54
54
|
|
55
55
|
next unless subfield_defined?(field, 't')
|
56
56
|
|
57
|
-
values_with_title_prefix(field, sf_exclude: %w[0 4 6 8 i], relator_map:
|
57
|
+
values_with_title_prefix(field, sf_exclude: %w[0 4 6 8 i], relator_map: relator_map)
|
58
58
|
end
|
59
59
|
values + record.fields('880').filter_map do |field|
|
60
60
|
next if field.indicator2.present?
|
@@ -63,7 +63,7 @@ module PennMARC
|
|
63
63
|
|
64
64
|
next unless subfield_defined?(field, 't')
|
65
65
|
|
66
|
-
values_with_title_prefix(field, sf_exclude: %w[0 4 6 8 i], relator_map:
|
66
|
+
values_with_title_prefix(field, sf_exclude: %w[0 4 6 8 i], relator_map: relator_map)
|
67
67
|
end
|
68
68
|
end
|
69
69
|
|
@@ -71,13 +71,13 @@ module PennMARC
|
|
71
71
|
# "Analytical Entry" meaning that the record is contained by the matching field. Map relator codes in sf 4. Ignore
|
72
72
|
# values in sf 0, 5, 6, and 8.
|
73
73
|
# @param [MARC::Record] record
|
74
|
-
# @param [Hash]
|
74
|
+
# @param [Hash] relator_map
|
75
75
|
# @return [Array]
|
76
|
-
def contains_show(record,
|
76
|
+
def contains_show(record, relator_map: Mappers.relator)
|
77
77
|
acc = record.fields(CONTAINS_FIELDS).filter_map do |field|
|
78
78
|
next unless field.indicator2 == '2'
|
79
79
|
|
80
|
-
values_with_title_prefix(field, sf_exclude: %w[0 4 5 6 8 i], relator_map:
|
80
|
+
values_with_title_prefix(field, sf_exclude: %w[0 4 5 6 8 i], relator_map: relator_map)
|
81
81
|
end
|
82
82
|
acc + record.fields('880').filter_map do |field|
|
83
83
|
next unless field.indicator2 == '2'
|