pennmarc 1.0.25 → 1.0.26
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.rubocop_todo.yml +8 -9
- data/lib/pennmarc/helpers/creator.rb +139 -65
- data/lib/pennmarc/helpers/edition.rb +5 -3
- data/lib/pennmarc/helpers/note.rb +24 -19
- data/lib/pennmarc/helpers/production.rb +113 -20
- data/lib/pennmarc/test/marc_helpers.rb +83 -0
- data/lib/pennmarc/util.rb +98 -69
- data/lib/pennmarc/version.rb +1 -1
- data/lib/pennmarc.rb +7 -0
- data/spec/lib/pennmarc/helpers/access_spec.rb +0 -2
- data/spec/lib/pennmarc/helpers/citation_spec.rb +0 -2
- data/spec/lib/pennmarc/helpers/classification_spec.rb +0 -2
- data/spec/lib/pennmarc/helpers/creator_spec.rb +103 -2
- data/spec/lib/pennmarc/helpers/database_spec.rb +0 -2
- data/spec/lib/pennmarc/helpers/date_spec.rb +0 -2
- data/spec/lib/pennmarc/helpers/edition_spec.rb +4 -2
- data/spec/lib/pennmarc/helpers/format_spec.rb +0 -2
- data/spec/lib/pennmarc/helpers/genre_spec.rb +0 -2
- data/spec/lib/pennmarc/helpers/identifer_spec.rb +0 -2
- data/spec/lib/pennmarc/helpers/inventory_spec.rb +0 -2
- data/spec/lib/pennmarc/helpers/language_spec.rb +0 -2
- data/spec/lib/pennmarc/helpers/link_spec.rb +0 -2
- data/spec/lib/pennmarc/helpers/location_spec.rb +0 -2
- data/spec/lib/pennmarc/helpers/note_spec.rb +22 -29
- data/spec/lib/pennmarc/helpers/production_spec.rb +121 -22
- data/spec/lib/pennmarc/helpers/relation_spec.rb +0 -2
- data/spec/lib/pennmarc/helpers/series_spec.rb +0 -2
- data/spec/lib/pennmarc/helpers/subject_spec.rb +0 -2
- data/spec/lib/pennmarc/helpers/title_spec.rb +0 -2
- data/spec/lib/pennmarc/marc_util_spec.rb +0 -2
- data/spec/lib/pennmarc/parser_spec.rb +1 -1
- data/spec/spec_helper.rb +7 -0
- data/spec/support/fixture_helpers.rb +10 -0
- metadata +4 -3
- data/spec/support/marc_spec_helpers.rb +0 -85
@@ -4,31 +4,47 @@ module PennMARC
|
|
4
4
|
# Extracts data related to a resource's production, distribution, manufacture, and publication.
|
5
5
|
class Production < Helper
|
6
6
|
class << self
|
7
|
-
# Retrieve production values for display from {https://www.
|
8
|
-
# @param [MARC::Record]
|
7
|
+
# Retrieve production values for display from {https://www.loc.gov/marc/bibliographic/bd264.html 264 field}.
|
8
|
+
# @param record [MARC::Record]
|
9
9
|
# @return [Array<String>]
|
10
10
|
def show(record)
|
11
11
|
get_264_or_880_fields(record, '0').uniq
|
12
12
|
end
|
13
13
|
|
14
|
-
# Retrieve
|
15
|
-
#
|
14
|
+
# Retrieve production values for searching. Includes only
|
15
|
+
# {https://www.loc.gov/marc/bibliographic/bd260.html 260} and
|
16
|
+
# {https://www.loc.gov/marc/bibliographic/bd264.html 264}.
|
17
|
+
# @param record [MARC::Record]
|
18
|
+
# @return [Array<String>]
|
19
|
+
def search(record)
|
20
|
+
values = record.fields('260').filter_map do |field|
|
21
|
+
join_subfields(field, &subfield_in?(['b']))
|
22
|
+
end
|
23
|
+
values + record.fields('264').filter_map { |field|
|
24
|
+
next unless field.indicator2 == '1'
|
25
|
+
|
26
|
+
join_subfields(field, &subfield_in?(['b']))
|
27
|
+
}.uniq
|
28
|
+
end
|
29
|
+
|
30
|
+
# Retrieve distribution values for display from {https://www.loc.gov/marc/bibliographic/bd264.html 264 field}.
|
31
|
+
# @param record [MARC::Record]
|
16
32
|
# @return [Array<String>]
|
17
33
|
def distribution_show(record)
|
18
34
|
get_264_or_880_fields(record, '2').uniq
|
19
35
|
end
|
20
36
|
|
21
|
-
# Retrieve manufacture values for display from {https://www.
|
22
|
-
# @param [MARC::Record]
|
37
|
+
# Retrieve manufacture values for display from {https://www.loc.gov/marc/bibliographic/bd264.html 264 field}.
|
38
|
+
# @param record [MARC::Record]
|
23
39
|
# @return [Array<String>]
|
24
40
|
def manufacture_show(record)
|
25
41
|
get_264_or_880_fields(record, '3').uniq
|
26
42
|
end
|
27
43
|
|
28
44
|
# Retrieve publication values. Return publication values from
|
29
|
-
# {https://www.
|
30
|
-
# {https://www.
|
31
|
-
# @param [MARC::Record]
|
45
|
+
# {https://www.loc.gov/marc/bibliographic/bd264.html 264 field} only if none found
|
46
|
+
# {https://www.loc.gov/marc/bibliographic/bd260.html 260}-262 fields.
|
47
|
+
# @param record [MARC::Record]
|
32
48
|
# @return [Array<String>]
|
33
49
|
def publication_values(record)
|
34
50
|
# first get inclusive dates
|
@@ -64,10 +80,10 @@ module PennMARC
|
|
64
80
|
end
|
65
81
|
|
66
82
|
# Retrieve publication values for display from fields
|
67
|
-
# {https://www.
|
68
|
-
# {https://www.
|
69
|
-
# and {https://www.
|
70
|
-
# @param [MARC::Record]
|
83
|
+
# {https://www.loc.gov/marc/bibliographic/bd245.html 245},
|
84
|
+
# {https://www.loc.gov/marc/bibliographic/bd260.html 260}-262 and their linked alternates,
|
85
|
+
# and {https://www.loc.gov/marc/bibliographic/bd264.html 264} and its linked alternate.
|
86
|
+
# @param record [MARC::Record]
|
71
87
|
# @return [Array<String>]
|
72
88
|
def publication_show(record)
|
73
89
|
values = record.fields('245').first(1).flat_map { |field| subfield_values(field, 'f') }
|
@@ -89,10 +105,49 @@ module PennMARC
|
|
89
105
|
values.compact_blank.uniq
|
90
106
|
end
|
91
107
|
|
92
|
-
# Retrieve
|
108
|
+
# Retrieve publication values for citation
|
109
|
+
# {https://www.loc.gov/marc/bibliographic/bd245.html 245},
|
110
|
+
# {https://www.loc.gov/marc/bibliographic/bd260.html 260}-262 and their linked alternates,
|
111
|
+
# and {https://www.loc.gov/marc/bibliographic/bd264.html 264} and its linked alternate.
|
112
|
+
# @param [MARC::Record] record
|
113
|
+
# @param [Boolean] with_year: return results with publication year if true
|
114
|
+
# @return [Array<String>]
|
115
|
+
def publication_citation_show(record, with_year: true)
|
116
|
+
values = record.fields('245').first(1).flat_map { |field| subfield_values(field, 'f') }
|
117
|
+
|
118
|
+
subfields = with_year ? %w[6 8] : %w[6 8 c]
|
119
|
+
values += record.fields(%w[260 261 262]).first(1).map do |field|
|
120
|
+
join_subfields(field, &subfield_not_in?(subfields))
|
121
|
+
end
|
122
|
+
|
123
|
+
subfields = with_year ? %w[a b c] : %w[a b]
|
124
|
+
values += record.fields('264').filter_map do |field|
|
125
|
+
next unless field.indicator2 == '1'
|
126
|
+
|
127
|
+
join_subfields(field, &subfield_in?(subfields))
|
128
|
+
end
|
129
|
+
|
130
|
+
values.compact_blank.uniq
|
131
|
+
end
|
132
|
+
|
133
|
+
# Returns the place of publication for RIS
|
134
|
+
# @param [MARC::Record] record
|
135
|
+
# @return [Array<String>]
|
136
|
+
def publication_ris_place_of_pub(record)
|
137
|
+
get_publication_ris_values(record, 'a')
|
138
|
+
end
|
139
|
+
|
140
|
+
# Returns the publisher for RIS
|
141
|
+
# @param [MARC::Record] record
|
142
|
+
# @return [Array<String>]
|
143
|
+
def publication_ris_publisher(record)
|
144
|
+
get_publication_ris_values(record, 'b')
|
145
|
+
end
|
146
|
+
|
147
|
+
# Retrieve place of publication for display from {https://www.loc.gov/marc/bibliographic/bd752.html 752 field} and
|
93
148
|
# its linked alternate.
|
94
149
|
# @note legacy version returns array of hash objects including data for display link
|
95
|
-
# @param [MARC::Record]
|
150
|
+
# @param record [MARC::Record]
|
96
151
|
# @return [Array<String>]
|
97
152
|
def place_of_publication_show(record)
|
98
153
|
record.fields(%w[752 880]).filter_map { |field|
|
@@ -104,13 +159,32 @@ module PennMARC
|
|
104
159
|
}.uniq
|
105
160
|
end
|
106
161
|
|
162
|
+
# Retrieves place of publication values for searching. Includes
|
163
|
+
# {https://www.loc.gov/marc/bibliographic/bd752.html 752} as well as sf a from
|
164
|
+
# {https://www.loc.gov/marc/bibliographic/bd260.html 260} and
|
165
|
+
# {https://www.loc.gov/marc/bibliographic/bd264.html 264} with an indicator2 of 1.
|
166
|
+
# @param record [MARC::Record]
|
167
|
+
# @return [Array<String>]
|
168
|
+
def place_of_publication_search(record)
|
169
|
+
values = record.fields('260').filter_map do |field|
|
170
|
+
join_subfields(field, &subfield_in?(['a']))
|
171
|
+
end
|
172
|
+
values += record.fields('264').filter_map do |field|
|
173
|
+
next unless field.indicator2 == '1'
|
174
|
+
|
175
|
+
join_subfields(field, &subfield_in?(['a']))
|
176
|
+
end
|
177
|
+
values + record.fields('752').filter_map { |field|
|
178
|
+
join_subfields(field, &subfield_in?(%w[a b c d f g h]))
|
179
|
+
}.uniq
|
180
|
+
end
|
181
|
+
|
107
182
|
private
|
108
183
|
|
109
|
-
# base method to retrieve production values from {https://www.
|
110
|
-
# on indicator2.
|
111
|
-
#
|
112
|
-
# @param [
|
113
|
-
# @param [String] indicator2
|
184
|
+
# base method to retrieve production values from {https://www.loc.gov/marc/bibliographic/bd264.html 264 field}
|
185
|
+
# based on indicator2. "Distribution" and "manufacture" share the same logic except for indicator2.
|
186
|
+
# @param record [MARC::Record]
|
187
|
+
# @param indicator2 [String]
|
114
188
|
# @return [Array<String>]
|
115
189
|
def get_264_or_880_fields(record, indicator2)
|
116
190
|
values = record.fields('264').filter_map do |field|
|
@@ -126,6 +200,25 @@ module PennMARC
|
|
126
200
|
join_subfields(field, &subfield_in?(%w[a b c]))
|
127
201
|
end
|
128
202
|
end
|
203
|
+
|
204
|
+
# Returns the publication value of the given subfield
|
205
|
+
# @param [MARC::Record] record
|
206
|
+
# @param [String] subfield
|
207
|
+
def get_publication_ris_values(record, subfield)
|
208
|
+
values = record.fields('245').first(1).flat_map { |field| subfield_values(field, 'f') }
|
209
|
+
|
210
|
+
values += record.fields(%w[260 261 262]).first(1).map do |field|
|
211
|
+
join_subfields(field, &subfield_in?([subfield]))
|
212
|
+
end
|
213
|
+
|
214
|
+
values += record.fields('264').filter_map do |field|
|
215
|
+
next unless field.indicator2 == '1'
|
216
|
+
|
217
|
+
join_subfields(field, &subfield_in?([subfield]))
|
218
|
+
end
|
219
|
+
|
220
|
+
values.compact_blank.uniq
|
221
|
+
end
|
129
222
|
end
|
130
223
|
end
|
131
224
|
end
|
@@ -0,0 +1,83 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'nokogiri'
|
4
|
+
require 'marc'
|
5
|
+
|
6
|
+
module PennMARC
|
7
|
+
module Test
|
8
|
+
# Helper methods for use in constructing MARC objects for testing
|
9
|
+
module MarcHelpers
|
10
|
+
# Return a MARC::XMLReader that will parse a given file and return MARC::Record objects
|
11
|
+
# @param [String] filename of MARCXML fixture
|
12
|
+
# @return [MARC::Record, NilClass]
|
13
|
+
def record_from(filename)
|
14
|
+
MARC::XMLReader.new(marc_xml_path(filename)).first
|
15
|
+
end
|
16
|
+
|
17
|
+
# Create an isolated MARC::Subfield object for use in specs or as part of a MARC::Field
|
18
|
+
# @param [String] code
|
19
|
+
# @param [String] value
|
20
|
+
# @return [MARC::Subfield]
|
21
|
+
def marc_subfield(code, value)
|
22
|
+
MARC::Subfield.new code.to_s, value
|
23
|
+
end
|
24
|
+
|
25
|
+
# Return a new ControlField (000-009)
|
26
|
+
# @param [String] tag
|
27
|
+
# @param [String] value
|
28
|
+
# @return [MARC::ControlField]
|
29
|
+
def marc_control_field(tag:, value:)
|
30
|
+
MARC::ControlField.new tag, value
|
31
|
+
end
|
32
|
+
|
33
|
+
# Create an isolated MARC::DataField object for use in specs
|
34
|
+
# Can pass in tag, indicators and subfields (using simple hash structure). E.g.,
|
35
|
+
# marc_field(tag: '650', indicator2: '7'),
|
36
|
+
# subfields: { a: 'Tax planning',
|
37
|
+
# m: ['Multiple', 'Subfields']
|
38
|
+
# z: 'United States.',
|
39
|
+
# '0': http://id.loc.gov/authorities/subjects/sh2008112546 }
|
40
|
+
# )
|
41
|
+
# @param [String (frozen)] tag MARC tag, e.g., 001, 665
|
42
|
+
# @param [String (frozen)] indicator1 MARC indicator, e.g., 0
|
43
|
+
# @param [String (frozen)] indicator2
|
44
|
+
# @param [Hash] subfields hash of subfield values as code => value or code => [value, value]
|
45
|
+
# @return [MARC::DataField]
|
46
|
+
def marc_field(tag: 'TST', indicator1: ' ', indicator2: ' ', subfields: {})
|
47
|
+
subfield_objects = subfields.each_with_object([]) do |(code, value), array|
|
48
|
+
Array.wrap(value).map { |v| array << marc_subfield(code, v) }
|
49
|
+
end
|
50
|
+
MARC::DataField.new tag, indicator1, indicator2, *subfield_objects
|
51
|
+
end
|
52
|
+
|
53
|
+
# Return a MARC::Record containing passed in DataFields
|
54
|
+
# @param [Array<MARC::DataField>] fields
|
55
|
+
# @param [String, nil] leader
|
56
|
+
# @return [MARC::Record]
|
57
|
+
def marc_record(fields: [], leader: nil)
|
58
|
+
record = MARC::Record.new
|
59
|
+
fields.each { |field| record << field }
|
60
|
+
record.leader = leader if leader
|
61
|
+
record
|
62
|
+
end
|
63
|
+
|
64
|
+
# Mock map for location lookup using Location helper
|
65
|
+
# The location codes :dent and :stor are the two outermost keys
|
66
|
+
# :specific_location, :library, :display are the inner keys that store location values
|
67
|
+
# @example
|
68
|
+
# location_map[:stor][:library] #=> 'LIBRA'
|
69
|
+
# @return [Hash]
|
70
|
+
def location_map
|
71
|
+
{ dent: { specific_location: 'Levy Dental Medicine Library - Stacks',
|
72
|
+
library: ['Health Sciences Libraries', 'Levy Dental Medicine Library'],
|
73
|
+
display: 'Levy Dental Medicine Library - Stacks' },
|
74
|
+
stor: { specific_location: 'LIBRA',
|
75
|
+
library: 'LIBRA',
|
76
|
+
display: 'LIBRA' },
|
77
|
+
vanp: { specific_location: 'Van Pelt - Stacks',
|
78
|
+
library: 'Van Pelt-Dietrich Library Center',
|
79
|
+
display: 'Van Pelt Library' } }
|
80
|
+
end
|
81
|
+
end
|
82
|
+
end
|
83
|
+
end
|
data/lib/pennmarc/util.rb
CHANGED
@@ -13,16 +13,16 @@ module PennMARC
|
|
13
13
|
period: /\.\s*$/ }.freeze # TODO: revise to exclude "etc."
|
14
14
|
|
15
15
|
# Check if a given record has a field present by tag (e.g., '041')
|
16
|
-
# @param [MARC::Record]
|
17
|
-
# @param [String]
|
16
|
+
# @param record [MARC::Record]
|
17
|
+
# @param marc_field [String]
|
18
18
|
# @return [Boolean]
|
19
19
|
def field_defined?(record, marc_field)
|
20
20
|
record.select { |field| field.tag == marc_field }.any?
|
21
21
|
end
|
22
22
|
|
23
23
|
# Join subfields from a field selected based on a provided proc
|
24
|
-
# @param [MARC::DataField, nil]
|
25
|
-
# @param [Proc]
|
24
|
+
# @param field [MARC::DataField, nil]
|
25
|
+
# @param selector [Proc]
|
26
26
|
# @return [String]
|
27
27
|
def join_subfields(field, &selector)
|
28
28
|
return '' unless field
|
@@ -37,77 +37,75 @@ module PennMARC
|
|
37
37
|
|
38
38
|
# returns true if field has a value that matches
|
39
39
|
# passed-in regex and passed in subfield
|
40
|
-
# @
|
41
|
-
# @param [
|
42
|
-
# @param [
|
43
|
-
# @
|
44
|
-
# @return [TrueClass, FalseClass]
|
40
|
+
# @param field [MARC::DataField]
|
41
|
+
# @param subfield [String|Integer|Symbol]
|
42
|
+
# @param regex [Regexp]
|
43
|
+
# @return [Boolean, nil]
|
45
44
|
def subfield_value?(field, subfield, regex)
|
46
45
|
field&.any? { |sf| sf.code == subfield.to_s && sf.value =~ regex }
|
47
46
|
end
|
48
47
|
|
49
48
|
# returns true if field has no value that matches
|
50
49
|
# passed-in regex and passed in subfield
|
51
|
-
# @param [MARC::DataField]
|
52
|
-
# @param [String|Integer|Symbol]
|
53
|
-
# @param [Regexp]
|
54
|
-
# @return [
|
50
|
+
# @param field [MARC::DataField]
|
51
|
+
# @param subfield [String|Integer|Symbol]
|
52
|
+
# @param regex [Regexp]
|
53
|
+
# @return [Boolean, nil]
|
55
54
|
def no_subfield_value_matches?(field, subfield, regex)
|
56
55
|
field&.none? { |sf| sf.code == subfield.to_s && sf.value =~ regex }
|
57
56
|
end
|
58
57
|
|
59
58
|
# returns true if a given field has a given subfield value in a given array
|
60
|
-
#
|
61
|
-
# @param [
|
62
|
-
# @param [
|
63
|
-
# @
|
64
|
-
# @return [TrueClass, FalseClass]
|
59
|
+
# @param field [MARC:DataField]
|
60
|
+
# @param subfield [String|Integer|Symbol]
|
61
|
+
# @param array [Array]
|
62
|
+
# @return [Boolean]
|
65
63
|
def subfield_value_in?(field, subfield, array)
|
66
64
|
field.any? { |sf| sf.code == subfield.to_s && sf.value.in?(array) }
|
67
65
|
end
|
68
66
|
|
69
67
|
# returns true if a given field does not have a given subfield value in a given array
|
70
|
-
# @param [MARC:DataField]
|
71
|
-
# @param [String|Integer|Symbol]
|
72
|
-
# @param [Array]
|
73
|
-
# @return [
|
68
|
+
# @param field [MARC:DataField]
|
69
|
+
# @param subfield [String|Integer|Symbol]
|
70
|
+
# @param array [Array]
|
71
|
+
# @return [Boolean]
|
74
72
|
def subfield_value_not_in?(field, subfield, array)
|
75
73
|
field.none? { |sf| sf.code == subfield.to_s && sf.value.in?(array) }
|
76
74
|
end
|
77
75
|
|
78
76
|
# returns a lambda checking if passed-in subfield's code is a member of array
|
79
|
-
# @param [Array]
|
77
|
+
# @param array [Array]
|
80
78
|
# @return [Proc]
|
81
79
|
def subfield_in?(array)
|
82
80
|
->(subfield) { array.member?(subfield.code) }
|
83
81
|
end
|
84
82
|
|
85
83
|
# returns a lambda checking if passed-in subfield's code is NOT a member of array
|
86
|
-
# @param [Array]
|
84
|
+
# @param array [Array]
|
87
85
|
# @return [Proc]
|
88
86
|
def subfield_not_in?(array)
|
89
87
|
->(subfield) { !array.member?(subfield.code) }
|
90
88
|
end
|
91
89
|
|
92
90
|
# Check if a field has a given subfield defined
|
93
|
-
# @param [MARC::DataField]
|
94
|
-
# @param [String|Symbol|Integer]
|
95
|
-
# @return [
|
91
|
+
# @param field [MARC::DataField]
|
92
|
+
# @param subfield [String|Symbol|Integer]
|
93
|
+
# @return [Boolean]
|
96
94
|
def subfield_defined?(field, subfield)
|
97
95
|
field.any? { |sf| sf.code == subfield.to_s }
|
98
96
|
end
|
99
97
|
|
100
98
|
# Check if a field does not have a given subfield defined
|
101
|
-
# @param [MARC::DataField]
|
102
|
-
# @param [String|Symbol|Integer]
|
103
|
-
# @return [
|
99
|
+
# @param field [MARC::DataField]
|
100
|
+
# @param subfield [String|Symbol|Integer]
|
101
|
+
# @return [Boolean]
|
104
102
|
def subfield_undefined?(field, subfield)
|
105
103
|
field.none? { |sf| sf.code == subfield.to_s }
|
106
104
|
end
|
107
105
|
|
108
106
|
# Gets all subfield values for a subfield in a given field
|
109
|
-
# @param [MARC::DataField]
|
110
|
-
# @param [String|Symbol]
|
107
|
+
# @param field [MARC::DataField]
|
108
|
+
# @param subfield [String|Symbol] as a string or symbol
|
111
109
|
# @return [Array] subfield values for given subfield code
|
112
110
|
def subfield_values(field, subfield)
|
113
111
|
field.filter_map do |sf|
|
@@ -120,9 +118,9 @@ module PennMARC
|
|
120
118
|
end
|
121
119
|
|
122
120
|
# Get all subfield values for a provided subfield from any occurrence of a provided tag/tags
|
123
|
-
# @param [String|Array]
|
124
|
-
# @param [String|Symbol]
|
125
|
-
# @param [MARC::Record]
|
121
|
+
# @param tag [String|Array] tags to consider
|
122
|
+
# @param subfield [String|Symbol] to take the values from
|
123
|
+
# @param record [MARC::Record]
|
126
124
|
# @return [Array] array of subfield values
|
127
125
|
def subfield_values_for(tag:, subfield:, record:)
|
128
126
|
record.fields(tag).flat_map do |field|
|
@@ -130,24 +128,43 @@ module PennMARC
|
|
130
128
|
end
|
131
129
|
end
|
132
130
|
|
133
|
-
#
|
134
|
-
# @param [String]
|
131
|
+
# Trim punctuation method extracted from Traject macro, to ensure consistent output
|
132
|
+
# @param string [String]
|
133
|
+
# @return [String] string with relevant punctuation removed
|
134
|
+
def trim_punctuation(string)
|
135
|
+
return string unless string
|
136
|
+
|
137
|
+
string = string.sub(%r{ *[ ,/;:] *\Z}, '')
|
138
|
+
|
139
|
+
# trailing period if it is preceded by at least three letters (possibly preceded and followed by whitespace)
|
140
|
+
string = string.sub(/( *[[:word:]]{3,})\. *\Z/, '\1')
|
141
|
+
|
142
|
+
# single square bracket characters if they are the start and/or end chars and there are no internal square
|
143
|
+
# brackets.
|
144
|
+
string = string.sub(/\A\[?([^\[\]]+)\]?\Z/, '\1')
|
145
|
+
|
146
|
+
# trim any leading or trailing whitespace
|
147
|
+
string.strip
|
148
|
+
end
|
149
|
+
|
150
|
+
# @param trailer [Symbol|String] to target for removal
|
151
|
+
# @param string [String] to modify
|
135
152
|
# @return [String]
|
136
153
|
def trim_trailing(trailer, string)
|
137
154
|
string.sub TRAILING_PUNCTUATIONS_PATTERNS[trailer.to_sym], ''
|
138
155
|
end
|
139
156
|
|
140
157
|
# trim trailing punctuation, manipulating string in place
|
141
|
-
# @param [Symbol|String]
|
142
|
-
# @param [String]
|
158
|
+
# @param trailer [Symbol|String] to target for removal
|
159
|
+
# @param string [String] to modify
|
143
160
|
# @return [String, Nil] string to modify
|
144
161
|
def trim_trailing!(trailer, string)
|
145
162
|
string.sub! TRAILING_PUNCTUATIONS_PATTERNS[trailer.to_sym], ''
|
146
163
|
end
|
147
164
|
|
148
165
|
# Intelligently append given punctuation to the end of a string
|
149
|
-
# @param [Symbol]
|
150
|
-
# @param [String]
|
166
|
+
# @param trailer [Symbol]
|
167
|
+
# @param string [String]
|
151
168
|
# @return [String]
|
152
169
|
def append_trailing(trailer, string)
|
153
170
|
return string if string.end_with?('.', '-')
|
@@ -165,9 +182,9 @@ module PennMARC
|
|
165
182
|
# translations of title values. A common need is to extract subfields as selected by
|
166
183
|
# passed-in block from 880 datafield that has a particular subfield 6 value.
|
167
184
|
# See: https://www.loc.gov/marc/bibliographic/bd880.html
|
168
|
-
# @param [MARC::Record]
|
169
|
-
# @param [String|Array]
|
170
|
-
# @param [Proc]
|
185
|
+
# @param record [MARC::Record]
|
186
|
+
# @param subfield6_value [String|Array] either a string to look for in sub6 or an array of them
|
187
|
+
# @param selector [Proc] takes a subfield as argument, returns a boolean
|
171
188
|
# @return [Array] array of linked alternates
|
172
189
|
def linked_alternate(record, subfield6_value, &selector)
|
173
190
|
record.fields('880').filter_map do |field|
|
@@ -180,8 +197,8 @@ module PennMARC
|
|
180
197
|
# Common case of wanting to extract all the subfields besides 6 or 8,
|
181
198
|
# from 880 datafield that has a particular subfield 6 value. We exclude 6 because
|
182
199
|
# that value is the linkage ID itself and 8 because... IDK
|
183
|
-
# @param [MARC::Record]
|
184
|
-
# @param [String|Array]
|
200
|
+
# @param record [MARC::Record]
|
201
|
+
# @param subfield6_value [String|Array] either a string to look for in sub6 or an array of them
|
185
202
|
# @return [Array] array of linked alternates without 8 or 6 values
|
186
203
|
def linked_alternate_not_6_or_8(record, subfield6_value)
|
187
204
|
excluded_subfields = %w[6 8]
|
@@ -191,8 +208,8 @@ module PennMARC
|
|
191
208
|
end
|
192
209
|
|
193
210
|
# Returns the non-6,8 subfields from a datafield and its 880 link.
|
194
|
-
# @param [MARC::Record]
|
195
|
-
# @param [String]
|
211
|
+
# @param record [MARC::Record]
|
212
|
+
# @param tag [String]
|
196
213
|
# @return [Array<String>] values
|
197
214
|
def datafield_and_linked_alternate(record, tag)
|
198
215
|
record.fields(tag).filter_map { |field|
|
@@ -201,23 +218,23 @@ module PennMARC
|
|
201
218
|
end
|
202
219
|
|
203
220
|
# Get the substring of a string up to a given target character
|
204
|
-
# @param [Object]
|
205
|
-
# @param [Object]
|
221
|
+
# @param string [Object] to split
|
222
|
+
# @param target [Object] character to split upon
|
206
223
|
# @return [String (frozen)]
|
207
224
|
def substring_before(string, target)
|
208
225
|
string.scan(target).present? ? string.split(target, 2).first : ''
|
209
226
|
end
|
210
227
|
|
211
228
|
# Get the substring of a string after the first occurrence of a target character
|
212
|
-
# @param [Object]
|
213
|
-
# @param [Object]
|
229
|
+
# @param string [Object] to split
|
230
|
+
# @param target [Object] character to split upon
|
214
231
|
# @return [String (frozen)]
|
215
232
|
def substring_after(string, target)
|
216
233
|
string.scan(target).present? ? string.split(target, 2).second : ''
|
217
234
|
end
|
218
235
|
|
219
236
|
# Join array and normalizing extraneous spaces
|
220
|
-
# @param [Array]
|
237
|
+
# @param array [Array]
|
221
238
|
# @return [String]
|
222
239
|
def join_and_squish(array)
|
223
240
|
array.join(' ').squish
|
@@ -225,7 +242,7 @@ module PennMARC
|
|
225
242
|
|
226
243
|
# If there's a subfield i, extract its value, and if there's something
|
227
244
|
# in parentheses in that value, extract that.
|
228
|
-
# @param [MARC::Field]
|
245
|
+
# @param field [MARC::Field]
|
229
246
|
# @return [String] subfield i without parentheses value
|
230
247
|
def remove_paren_value_from_subfield_i(field)
|
231
248
|
val = field.filter_map { |sf|
|
@@ -243,19 +260,19 @@ module PennMARC
|
|
243
260
|
|
244
261
|
# Translate a relator code using mapping
|
245
262
|
# @todo handle case of receiving a URI? E.g., http://loc.gov/relator/aut
|
246
|
-
# @param [String, NilClass]
|
247
|
-
# @param [Hash]
|
263
|
+
# @param relator_code [String, NilClass]
|
264
|
+
# @param mapping [Hash]
|
248
265
|
# @return [String, NilClass] full relator string
|
249
266
|
def translate_relator(relator_code, mapping)
|
250
267
|
return if relator_code.blank?
|
251
268
|
|
252
|
-
mapping[relator_code
|
269
|
+
mapping[relator_code&.to_sym]
|
253
270
|
end
|
254
271
|
|
255
272
|
# Get 650 & 880 for Provenance and Chronology: prefix should be 'PRO' or 'CHR' and may be preceded by a '%'
|
256
273
|
# @note 11/2018: do not display $5 in PRO or CHR subjs
|
257
|
-
# @param [MARC::Record]
|
258
|
-
# @param [String]
|
274
|
+
# @param record [MARC::Record]
|
275
|
+
# @param prefix [String] to select from subject field
|
259
276
|
# @return [Array] array of values
|
260
277
|
def prefixed_subject_and_alternate(record, prefix)
|
261
278
|
record.fields(%w[650 880]).filter_map { |field|
|
@@ -273,16 +290,16 @@ module PennMARC
|
|
273
290
|
|
274
291
|
# Does the given field specify an allowed source code?
|
275
292
|
#
|
276
|
-
# @param [MARC::DataField]
|
293
|
+
# @param field [MARC::DataField]
|
277
294
|
# @return [Boolean]
|
278
295
|
def valid_subject_genre_source_code?(field)
|
279
296
|
subfield_value_in?(field, '2', PennMARC::HeadingControl::ALLOWED_SOURCE_CODES)
|
280
297
|
end
|
281
298
|
|
282
299
|
# Does a field or its linked alternate match any of the specified tags?
|
283
|
-
# @param [MARC::Field]
|
284
|
-
# @param [Array<String>]
|
285
|
-
# @return [
|
300
|
+
# @param field [MARC::Field]
|
301
|
+
# @param tags [Array<String>]
|
302
|
+
# @return [Boolean]
|
286
303
|
def field_or_its_linked_alternate?(field, tags)
|
287
304
|
return true if field.tag.in? tags
|
288
305
|
return true if field.tag == '880' && subfield_value?(field, '6', /^(#{tags.join('|')})/)
|
@@ -291,7 +308,7 @@ module PennMARC
|
|
291
308
|
end
|
292
309
|
|
293
310
|
# Match any open dates ending a given string to determine join separator for relator term in 1xx/7xx fields.
|
294
|
-
# @param [String]
|
311
|
+
# @param str [String]
|
295
312
|
# @return [String (frozen)]
|
296
313
|
def relator_join_separator(str)
|
297
314
|
/\b\d+-\z/.match?(str) ? ' ' : ', '
|
@@ -302,7 +319,7 @@ module PennMARC
|
|
302
319
|
# {https://www.loc.gov/marc/bibliographic/bd111.html 111}, {https://www.loc.gov/marc/bibliographic/bd411.html 411},
|
303
320
|
# {https://www.loc.gov/marc/bibliographic/bd611.html 611}, {https://www.loc.gov/marc/bibliographic/bd711.html 711},
|
304
321
|
# {https://www.loc.gov/marc/bibliographic/bd811.html 811}
|
305
|
-
# @param [MARC:Field]
|
322
|
+
# @param field [MARC:Field]
|
306
323
|
# @return [String (frozen)]
|
307
324
|
def relator_term_subfield(field)
|
308
325
|
field_or_its_linked_alternate?(field, %w[111 411 611 711 811]) ? 'j' : 'e'
|
@@ -311,10 +328,10 @@ module PennMARC
|
|
311
328
|
# Appends a relator value to the given string. It prioritizes relator codes found in subfield $4
|
312
329
|
# and falls back to the specified relator term subfield (defaulting to 'e') if no valid codes are found in $4.
|
313
330
|
# Use with 1xx/7xx fields.
|
314
|
-
# @param [MARC::Field]
|
315
|
-
# @param [String]
|
316
|
-
# @param [String]
|
317
|
-
# @param [Hash]
|
331
|
+
# @param field [MARC::Field] where relator values are stored
|
332
|
+
# @param joined_subfields [String] the string to which the relator is appended
|
333
|
+
# @param relator_term_sf [String] MARC subfield that stores relator term
|
334
|
+
# @param relator_map [Hash]
|
318
335
|
# @return [String]
|
319
336
|
def append_relator(field:, joined_subfields:, relator_term_sf:, relator_map: Mappers.relator)
|
320
337
|
joined_subfields = trim_trailing(:comma, joined_subfields)
|
@@ -329,5 +346,17 @@ module PennMARC
|
|
329
346
|
|
330
347
|
[joined_subfields, relator].compact_blank.join(join_separator).squish
|
331
348
|
end
|
349
|
+
|
350
|
+
# Returns a relator value of the given field. Like append_relator, it prioritizes relator codes found in subfileld
|
351
|
+
# $4 and falls back to the specified relator term subfield relator_term_sf if no valid codes are found in $4
|
352
|
+
# @param [MARC::Field] field where relator values are stored
|
353
|
+
# @param [String] relator_term_sf MARC subfield that stores relator term
|
354
|
+
# @param [Hash] relator_map
|
355
|
+
# @return [String]
|
356
|
+
def relator(field:, relator_term_sf:, relator_map: Mappers.relator)
|
357
|
+
relator = subfield_values(field, '4').filter_map { |code| translate_relator(code, relator_map) }
|
358
|
+
relator = subfield_values(field, relator_term_sf) if relator.blank?
|
359
|
+
relator.join
|
360
|
+
end
|
332
361
|
end
|
333
362
|
end
|
data/lib/pennmarc/version.rb
CHANGED
data/lib/pennmarc.rb
CHANGED
@@ -2,5 +2,12 @@
|
|
2
2
|
|
3
3
|
$LOAD_PATH.unshift(__dir__) unless $LOAD_PATH.include?(__dir__)
|
4
4
|
|
5
|
+
module PennMARC
|
6
|
+
# Autoload MARC helpers
|
7
|
+
module Test
|
8
|
+
autoload :MarcHelpers, 'pennmarc/test/marc_helpers'
|
9
|
+
end
|
10
|
+
end
|
11
|
+
|
5
12
|
require_relative 'pennmarc/parser'
|
6
13
|
require 'library_stdnums'
|