pennmarc 1.0.30 → 1.0.32
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile +0 -1
- data/Gemfile.lock +0 -2
- data/lib/pennmarc/heading_control.rb +9 -5
- data/lib/pennmarc/helpers/access.rb +4 -4
- data/lib/pennmarc/helpers/citation.rb +2 -2
- data/lib/pennmarc/helpers/classification.rb +10 -7
- data/lib/pennmarc/helpers/creator.rb +27 -25
- data/lib/pennmarc/helpers/database.rb +8 -8
- data/lib/pennmarc/helpers/date.rb +5 -5
- data/lib/pennmarc/helpers/edition.rb +7 -7
- data/lib/pennmarc/helpers/format.rb +36 -40
- data/lib/pennmarc/helpers/genre.rb +5 -5
- data/lib/pennmarc/helpers/identifier.rb +18 -18
- data/lib/pennmarc/helpers/inventory.rb +7 -7
- data/lib/pennmarc/helpers/inventory_entry/base.rb +2 -2
- data/lib/pennmarc/helpers/language.rb +4 -4
- data/lib/pennmarc/helpers/link.rb +6 -6
- data/lib/pennmarc/helpers/location.rb +14 -14
- data/lib/pennmarc/helpers/note.rb +2 -2
- data/lib/pennmarc/helpers/production.rb +7 -6
- data/lib/pennmarc/helpers/relation.rb +14 -14
- data/lib/pennmarc/helpers/series.rb +19 -19
- data/lib/pennmarc/helpers/subject.rb +28 -28
- data/lib/pennmarc/helpers/title.rb +18 -18
- data/lib/pennmarc/mappings/headings_override.yml +12 -8
- data/lib/pennmarc/parser.rb +5 -5
- data/lib/pennmarc/test/marc_helpers.rb +11 -11
- data/lib/pennmarc/util.rb +18 -18
- data/lib/pennmarc/version.rb +1 -1
- data/pennmarc.gemspec +0 -1
- data/spec/lib/pennmarc/heading_control_spec.rb +17 -10
- data/spec/lib/pennmarc/helpers/creator_spec.rb +15 -12
- data/spec/lib/pennmarc/marc_util_spec.rb +12 -0
- data/spec/support/fixture_helpers.rb +1 -1
- metadata +2 -16
@@ -30,8 +30,8 @@ module PennMARC
|
|
30
30
|
# 69X, including any linked 880 fields. Fields must have an indicator2 value in {VALID_SOURCE_INDICATORS}.
|
31
31
|
# @todo this includes subfields that may not be desired like 1 (uri) and 2 (source code) but this might be OK for
|
32
32
|
# a search (non-display) field?
|
33
|
-
# @param [Hash]
|
34
|
-
# @param [MARC::Record]
|
33
|
+
# @param relator_map [Hash]
|
34
|
+
# @param record [MARC::Record]
|
35
35
|
# @return [Array<String>] array of all subject values for search
|
36
36
|
def search(record, relator_map: Mappers.relator)
|
37
37
|
subject_fields(record, type: :search).filter_map { |field|
|
@@ -61,8 +61,8 @@ module PennMARC
|
|
61
61
|
# All Subjects for faceting
|
62
62
|
#
|
63
63
|
# @note this is ported mostly form MG's new-style Subject parsing
|
64
|
-
# @param [MARC::Record]
|
65
|
-
# @param [Boolean]
|
64
|
+
# @param record [MARC::Record]
|
65
|
+
# @param override [Boolean] remove undesirable terms or not
|
66
66
|
# @return [Array<String>] array of all subject values for faceting
|
67
67
|
def facet(record, override: true)
|
68
68
|
values = subject_fields(record, type: :facet).filter_map { |field|
|
@@ -77,8 +77,8 @@ module PennMARC
|
|
77
77
|
# All Subjects for display. This includes all {DISPLAY_TAGS} and {LOCAL_TAGS}. For tags that specify a source,
|
78
78
|
# only those with an allowed source code (see ALLOWED_SOURCE_CODES) are included.
|
79
79
|
#
|
80
|
-
# @param [MARC::Record]
|
81
|
-
# @param [Boolean]
|
80
|
+
# @param record [MARC::Record]
|
81
|
+
# @param override [Boolean] to remove undesirable terms or not
|
82
82
|
# @return [Array] array of all subject values for display
|
83
83
|
def show(record, override: true)
|
84
84
|
values = subject_fields(record, type: :all).filter_map { |field|
|
@@ -92,8 +92,8 @@ module PennMARC
|
|
92
92
|
|
93
93
|
# Get Subjects from "Children" ontology
|
94
94
|
#
|
95
|
-
# @param [MARC::Record]
|
96
|
-
# @param [Boolean]
|
95
|
+
# @param record [MARC::Record]
|
96
|
+
# @param override [Boolean] remove undesirable terms or not
|
97
97
|
# @return [Array] array of children's subject values for display
|
98
98
|
def childrens_show(record, override: true)
|
99
99
|
values = subject_fields(record, type: :display, options: { tags: DISPLAY_TAGS, indicator2: '1' })
|
@@ -108,8 +108,8 @@ module PennMARC
|
|
108
108
|
|
109
109
|
# Get Subjects from "MeSH" ontology
|
110
110
|
#
|
111
|
-
# @param [MARC::Record]
|
112
|
-
# @param [Boolean]
|
111
|
+
# @param record [MARC::Record]
|
112
|
+
# @param override [Boolean] remove undesirable terms or not
|
113
113
|
# @return [Array] array of MeSH subject values for display
|
114
114
|
def medical_show(record, override: true)
|
115
115
|
values = subject_fields(record, type: :display, options: { tags: DISPLAY_TAGS, indicator2: '2' })
|
@@ -125,8 +125,8 @@ module PennMARC
|
|
125
125
|
# Get Subject values from {DISPLAY_TAGS} where indicator2 is 4 and {LOCAL_TAGS}. Do not include any values where
|
126
126
|
# sf2 includes "penncoi" (Community of Interest).
|
127
127
|
#
|
128
|
-
# @param [MARC::Record]
|
129
|
-
# @param [Boolean]
|
128
|
+
# @param record [MARC::Record]
|
129
|
+
# @param override [Boolean] to remove undesirable terms
|
130
130
|
# @return [Array] array of local subject values for display
|
131
131
|
def local_show(record, override: true)
|
132
132
|
local_fields = subject_fields(record, type: :display, options: { tags: DISPLAY_TAGS, indicator2: '4' }) +
|
@@ -149,9 +149,9 @@ module PennMARC
|
|
149
149
|
# - facet
|
150
150
|
# - display
|
151
151
|
# - local
|
152
|
-
# @param [MARC::Record]
|
153
|
-
# @param [String, Symbol] type of fields desired
|
154
|
-
# @param [Hash] options to be passed to the selector method
|
152
|
+
# @param record [MARC::Record]
|
153
|
+
# @param type [String, Symbol] type of fields desired
|
154
|
+
# @param options [Hash] options to be passed to the selector method
|
155
155
|
# @return [Array<MARC::DataField>] selected fields
|
156
156
|
def subject_fields(record, type:, options: {})
|
157
157
|
selector_method = case type.to_sym
|
@@ -171,8 +171,8 @@ module PennMARC
|
|
171
171
|
# Format a term hash as a string for display
|
172
172
|
#
|
173
173
|
# @todo support search field formatting?
|
174
|
-
# @param [Symbol]
|
175
|
-
# @param [Hash]
|
174
|
+
# @param type [Symbol]
|
175
|
+
# @param term [Hash] components and information as a hash
|
176
176
|
# @return [String]
|
177
177
|
def format_term(type:, term:)
|
178
178
|
return unless type.in? %i[facet display]
|
@@ -194,7 +194,7 @@ module PennMARC
|
|
194
194
|
# indicator 2 is '7' - indicating "source specified", the specified source must be in our approved source code
|
195
195
|
# list.
|
196
196
|
# @see Util.valid_subject_genre_source_code?
|
197
|
-
# @param [MARC::DataField]
|
197
|
+
# @param field [MARC::DataField]
|
198
198
|
# @return [Boolean] whether a MARC field is intended for display under general "Subjects"
|
199
199
|
def subject_general_display_field?(field)
|
200
200
|
return false unless field.tag.in?(DISPLAY_TAGS + LOCAL_TAGS) && field.respond_to?(:indicator2)
|
@@ -206,14 +206,14 @@ module PennMARC
|
|
206
206
|
true
|
207
207
|
end
|
208
208
|
|
209
|
-
# @param [MARC::DataField]
|
209
|
+
# @param field [MARC::DataField]
|
210
210
|
# @return [Boolean] whether a MARC field is a local subject field (69X)
|
211
211
|
def subject_local_field?(field)
|
212
212
|
field.tag.in? LOCAL_TAGS
|
213
213
|
end
|
214
214
|
|
215
|
-
# @param [MARC::DataField]
|
216
|
-
# @param [Hash]
|
215
|
+
# @param field [MARC::DataField]
|
216
|
+
# @param options [Hash] include :tags and :indicator2 values
|
217
217
|
# @return [Boolean] whether a MARC field should be considered for display
|
218
218
|
def subject_display_field?(field, options)
|
219
219
|
return false unless field.respond_to?(:indicator2)
|
@@ -223,7 +223,7 @@ module PennMARC
|
|
223
223
|
false
|
224
224
|
end
|
225
225
|
|
226
|
-
# @param [MARC::DataField]
|
226
|
+
# @param field [MARC::DataField]
|
227
227
|
# @return [Boolean]
|
228
228
|
def subject_facet_field?(field)
|
229
229
|
return false unless field.respond_to?(:indicator2)
|
@@ -241,7 +241,7 @@ module PennMARC
|
|
241
241
|
# because we're using (where? - MK) "subdivision count" as a heuristic for the quality level of the
|
242
242
|
# heading. - MG
|
243
243
|
# @todo do i need all this?
|
244
|
-
# @param [MARC::DataField]
|
244
|
+
# @param field [MARC::DataField]
|
245
245
|
# @return [Hash{Symbol => Integer, Array, Boolean}, Nil]
|
246
246
|
def build_subject_hash(field)
|
247
247
|
term_info = { count: 0, parts: [], append: [], uri: nil,
|
@@ -291,7 +291,7 @@ module PennMARC
|
|
291
291
|
|
292
292
|
# Determine if a field should be considered for Subject search inclusion. It must be either contained in
|
293
293
|
# {SEARCH_TAGS}, be an 880 field otherwise linked to a valid Search tag, or be in {LOCAL_TAGS}.
|
294
|
-
# @param [MARC::DataField]
|
294
|
+
# @param field [MARC::DataField]
|
295
295
|
# @return [Boolean]
|
296
296
|
def subject_search_field?(field)
|
297
297
|
return false unless field.respond_to?(:indicator2) && VALID_SOURCE_INDICATORS.include?(field.indicator2)
|
@@ -305,7 +305,7 @@ module PennMARC
|
|
305
305
|
end
|
306
306
|
|
307
307
|
# Is a given tag a subject search field? Yes if it is contained in {SEARCH_TAGS} or starts with 69.
|
308
|
-
# @param [String,
|
308
|
+
# @param tag [String, nil]
|
309
309
|
# @return [Boolean]
|
310
310
|
def subject_search_tag?(tag)
|
311
311
|
return false if tag.blank?
|
@@ -317,7 +317,7 @@ module PennMARC
|
|
317
317
|
# when we've only encountered one subfield, assume that it might be a poorly-coded record
|
318
318
|
# with a bunch of subdivisions mashed together, and attempt to convert it to a consistent
|
319
319
|
# form.
|
320
|
-
# @param [String]
|
320
|
+
# @param first_part [String]
|
321
321
|
# @return [String, nil] normalized string
|
322
322
|
def normalize_single_subfield(first_part)
|
323
323
|
first_part.gsub!(/([[[:alnum:]])])(\s+--\s*|\s*--\s+)([[[:upper:]][[:digit:]]])/, '\1--\3')
|
@@ -326,8 +326,8 @@ module PennMARC
|
|
326
326
|
end
|
327
327
|
|
328
328
|
# removes trailing comma or period, manipulating the string in place
|
329
|
-
# @param [String,
|
330
|
-
# @return [String,
|
329
|
+
# @param subject_part [String, nil]
|
330
|
+
# @return [String, nil]
|
331
331
|
def trim_trailing_commas_or_periods!(subject_part)
|
332
332
|
return if subject_part.blank?
|
333
333
|
|
@@ -35,7 +35,7 @@ module PennMARC
|
|
35
35
|
class << self
|
36
36
|
# Main Title Search field. Takes from {https://www.loc.gov/marc/bibliographic/bd245.html 245} and linked 880.
|
37
37
|
# @note Ported from get_title_1_search_values.
|
38
|
-
# @param [MARC::Record]
|
38
|
+
# @param record [MARC::Record]
|
39
39
|
# @return [Array<String>] array of title values for search
|
40
40
|
def search(record)
|
41
41
|
record.fields(%w[245 880]).filter_map { |field|
|
@@ -47,7 +47,7 @@ module PennMARC
|
|
47
47
|
|
48
48
|
# Auxiliary Title Search field. Takes from many fields defined in {AUX_TITLE_TAGS} that contain title-like
|
49
49
|
# information.
|
50
|
-
# @param [MARC::Record]
|
50
|
+
# @param record [MARC::Record]
|
51
51
|
# @return [Array<String>] array of auxiliary title values for search
|
52
52
|
def search_aux(record)
|
53
53
|
values = search_aux_values(record: record, title_type: :main, &subfield_not_in?(%w[c 6 8])) +
|
@@ -60,7 +60,7 @@ module PennMARC
|
|
60
60
|
# Journal Title Search field. Takes from {https://www.loc.gov/marc/bibliographic/bd245.html 245} and linked 880.
|
61
61
|
# We do not return any values if the {https://www.loc.gov/marc/bibliographic/bdleader.html MARC leader}
|
62
62
|
# indicates that the record is not a serial.
|
63
|
-
# @param [MARC::Record]
|
63
|
+
# @param record [MARC::Record]
|
64
64
|
# @return [Array<String>] journal title information for search
|
65
65
|
def journal_search(record)
|
66
66
|
return [] if not_a_serial?(record)
|
@@ -75,7 +75,7 @@ module PennMARC
|
|
75
75
|
# Auxiliary Journal Title Search field. Takes from many fields defined in {AUX_TITLE_TAGS} that contain title-like
|
76
76
|
# information. Does not return any titles if the {https://www.loc.gov/marc/bibliographic/bdleader.html MARC leader}
|
77
77
|
# indicates that the record is not a serial.
|
78
|
-
# @param [MARC::Record]
|
78
|
+
# @param record [MARC::Record]
|
79
79
|
# @return [Array<String>] auxiliary journal title information for search
|
80
80
|
def journal_search_aux(record)
|
81
81
|
values = search_aux_values(record: record, title_type: :main, journal: true, &subfield_not_in?(%w[c 6 8])) +
|
@@ -90,7 +90,7 @@ module PennMARC
|
|
90
90
|
# {https://www.oclc.org/bibformats/en/2xx/245.html#punctuation punctuation practices}.
|
91
91
|
# @todo still consider ǂh? medium, which OCLC doc says DO NOT USE...but that is OCLC...
|
92
92
|
# @todo is punctuation handling still as desired? treatment here is described in spreadsheet from 2011
|
93
|
-
# @param [MARC::Record]
|
93
|
+
# @param record [MARC::Record]
|
94
94
|
# @return [String] single title for display
|
95
95
|
def show(record)
|
96
96
|
field = record.fields('245').first
|
@@ -117,7 +117,7 @@ module PennMARC
|
|
117
117
|
# title_sort_tl (text left justified). It is not yet clear why this distinction is useful. For now, use a
|
118
118
|
# properly normalized (leading articles and punctuation removed) single title value here.
|
119
119
|
# @todo refactor to reduce complexity
|
120
|
-
# @param [MARC::Record]
|
120
|
+
# @param record [MARC::Record]
|
121
121
|
# @return [String] title value for sorting
|
122
122
|
def sort(record)
|
123
123
|
title_field = record.fields('245').first
|
@@ -152,7 +152,7 @@ module PennMARC
|
|
152
152
|
|
153
153
|
# @note this is simplified from legacy practice as a linking hash is not returned. I believe this only supported
|
154
154
|
# title browse and we will not be supporting that at this time
|
155
|
-
# @param [MARC::Record]
|
155
|
+
# @param record [MARC::Record]
|
156
156
|
# @return [Array<String>] Array of standardized titles as strings
|
157
157
|
def standardized_show(record)
|
158
158
|
standardized_titles = record.fields(%w[130 240]).map do |field|
|
@@ -181,7 +181,7 @@ module PennMARC
|
|
181
181
|
# Data comes from 246 ({https://www.oclc.org/bibformats/en/2xx/246.htm OCLC docs}) and 740
|
182
182
|
# ({https://www.oclc.org/bibformats/en/7xx/740.html OCLC docs)}
|
183
183
|
#
|
184
|
-
# @param [MARC::Record]
|
184
|
+
# @param record [MARC::Record]
|
185
185
|
# @return [Array<String>] Array of other titles as strings
|
186
186
|
def other_show(record)
|
187
187
|
other_titles = record.fields('246').map do |field|
|
@@ -207,7 +207,7 @@ module PennMARC
|
|
207
207
|
# @note Ported from get_former_title_display. That method returns a hash for constructing a search link.
|
208
208
|
# We may need to do something like that eventually.
|
209
209
|
# @todo what are e and w subfields?
|
210
|
-
# @param [MARC::Record]
|
210
|
+
# @param record [MARC::Record]
|
211
211
|
# @return [Array<String>] array of former titles
|
212
212
|
def former_show(record)
|
213
213
|
record.fields
|
@@ -221,7 +221,7 @@ module PennMARC
|
|
221
221
|
end
|
222
222
|
|
223
223
|
# Determine if the record is a "Host" bibliographic record for other bib records ("bound-withs")
|
224
|
-
# @param [MARC::Record]
|
224
|
+
# @param record [MARC::Record]
|
225
225
|
# @return [Boolean]
|
226
226
|
def host_bib_record?(record)
|
227
227
|
record.fields('245').any? do |f|
|
@@ -235,7 +235,7 @@ module PennMARC
|
|
235
235
|
# Create prefix/filing hash for representing a title value with filing characters removed, with special
|
236
236
|
# consideration for bracketed titles
|
237
237
|
# @todo Is this still useful?
|
238
|
-
# @param [String]
|
238
|
+
# @param title [String]
|
239
239
|
# @return [Hash]
|
240
240
|
def handle_bracket_prefix(title)
|
241
241
|
if title.starts_with? '['
|
@@ -246,14 +246,14 @@ module PennMARC
|
|
246
246
|
end
|
247
247
|
|
248
248
|
# Evaluate {https://www.loc.gov/marc/bibliographic/bdleader.html MARC leader} to determine if record is a serial.
|
249
|
-
# @param [MARC::Record]
|
249
|
+
# @param record [MARC::Record]
|
250
250
|
# @return [Boolean]
|
251
251
|
def not_a_serial?(record)
|
252
252
|
!record.leader[6..7].ends_with?('s')
|
253
253
|
end
|
254
254
|
|
255
|
-
# @param [MARC::DataField]
|
256
|
-
# @param [String]
|
255
|
+
# @param field [MARC::DataField]
|
256
|
+
# @param value [String]
|
257
257
|
# @return [Boolean]
|
258
258
|
def indicators_are_not_value?(field, value)
|
259
259
|
field.indicator1 != value && field.indicator2 != value
|
@@ -263,10 +263,10 @@ module PennMARC
|
|
263
263
|
# {https://www.loc.gov/marc/bibliographic/bdleader.html MARC leader} indicates that the record is not a serial.
|
264
264
|
# We take special consideration for the {https://www.loc.gov/marc/bibliographic/bd505.html 505 field}, extracting
|
265
265
|
# values only when indicator1 and indicator2 are both '0'.
|
266
|
-
# @param [MARC::Record]
|
267
|
-
# @param [Symbol]
|
268
|
-
# @param [Boolean]
|
269
|
-
# @
|
266
|
+
# @param record [MARC::Record]
|
267
|
+
# @param title_type [Symbol]
|
268
|
+
# @param journal [Boolean]
|
269
|
+
# @param join_selector [Proc]
|
270
270
|
# @return [Array<String>]
|
271
271
|
def search_aux_values(record:, title_type:, journal: false, &join_selector)
|
272
272
|
return [] if journal && not_a_serial?(record)
|
@@ -1,8 +1,12 @@
|
|
1
|
-
|
2
|
-
"
|
3
|
-
|
4
|
-
|
5
|
-
"
|
6
|
-
|
7
|
-
"
|
8
|
-
"
|
1
|
+
# Important!: These terms should be listed in an order of decreasing complexity so that terms that may be contained in
|
2
|
+
# other terms are not replaced first, e.g., if "Aliens" is listed first, "Illegal Aliens" will get overrode to
|
3
|
+
# read "Illegal Noncitizens".
|
4
|
+
# Also, use lower case only in the key to support efficient case-insensitive matching.
|
5
|
+
"illegal alien children": Undocumented immigrant children
|
6
|
+
"alien detention centers": Immigrant detention centers
|
7
|
+
"alien criminals": Noncitizen criminals
|
8
|
+
"alien property": Foreign-owned property
|
9
|
+
"illegal aliens": Undocumented immigrants
|
10
|
+
"alien labor": Foreign workers
|
11
|
+
gypsies: Romanies
|
12
|
+
aliens: Noncitizens
|
data/lib/pennmarc/parser.rb
CHANGED
@@ -12,7 +12,7 @@ module PennMARC
|
|
12
12
|
# Access point for magic calls to helper methods
|
13
13
|
class Parser
|
14
14
|
# Allow calls to `respond_to?` on parser instances to respond accurately by checking helper classes
|
15
|
-
# @param [String, Symbol]
|
15
|
+
# @param name [String, Symbol]
|
16
16
|
# @return [Boolean]
|
17
17
|
def respond_to_missing?(name, include_private = false)
|
18
18
|
helper, method_name = parse_call(name)
|
@@ -26,9 +26,9 @@ module PennMARC
|
|
26
26
|
# Call helper class methods, passing along additional arguments as needed, e.g.:
|
27
27
|
# #title_show -> PennMARC::Title.show
|
28
28
|
# #subject_facet -> PennMARC::Subject.facet
|
29
|
-
# @param [Symbol]
|
30
|
-
# @param [MARC::Record]
|
31
|
-
# @param [Array]
|
29
|
+
# @param name [Symbol]
|
30
|
+
# @param record [MARC::Record]
|
31
|
+
# @param opts [Array]
|
32
32
|
def method_missing(name, record, *opts)
|
33
33
|
helper, method_name = parse_call(name)
|
34
34
|
raise NoMethodError unless helper && method_name
|
@@ -44,7 +44,7 @@ module PennMARC
|
|
44
44
|
private
|
45
45
|
|
46
46
|
# Parse out a method call name in the way method_missing is configured to handle
|
47
|
-
# @param [String, Symbol]
|
47
|
+
# @param name [String, Symbol]
|
48
48
|
# @return [Array]
|
49
49
|
def parse_call(name)
|
50
50
|
call = name.to_s.split('_')
|
@@ -8,23 +8,23 @@ module PennMARC
|
|
8
8
|
# Helper methods for use in constructing MARC objects for testing
|
9
9
|
module MarcHelpers
|
10
10
|
# Return a MARC::XMLReader that will parse a given file and return MARC::Record objects
|
11
|
-
# @param [String] filename of MARCXML fixture
|
11
|
+
# @param filename [String] filename of MARCXML fixture
|
12
12
|
# @return [MARC::Record, NilClass]
|
13
13
|
def record_from(filename)
|
14
14
|
MARC::XMLReader.new(marc_xml_path(filename)).first
|
15
15
|
end
|
16
16
|
|
17
17
|
# Create an isolated MARC::Subfield object for use in specs or as part of a MARC::Field
|
18
|
-
# @param [String]
|
19
|
-
# @param [String]
|
18
|
+
# @param code [String]
|
19
|
+
# @param value [String]
|
20
20
|
# @return [MARC::Subfield]
|
21
21
|
def marc_subfield(code, value)
|
22
22
|
MARC::Subfield.new code.to_s, value
|
23
23
|
end
|
24
24
|
|
25
25
|
# Return a new ControlField (000-009)
|
26
|
-
# @param [String]
|
27
|
-
# @param [String]
|
26
|
+
# @param tag [String]
|
27
|
+
# @param value [String]
|
28
28
|
# @return [MARC::ControlField]
|
29
29
|
def marc_control_field(tag:, value:)
|
30
30
|
MARC::ControlField.new tag, value
|
@@ -38,10 +38,10 @@ module PennMARC
|
|
38
38
|
# z: 'United States.',
|
39
39
|
# '0': http://id.loc.gov/authorities/subjects/sh2008112546 }
|
40
40
|
# )
|
41
|
-
# @param [String (frozen)]
|
42
|
-
# @param [String (frozen)]
|
43
|
-
# @param [String (frozen)]
|
44
|
-
# @param [Hash]
|
41
|
+
# @param tag [String (frozen)] MARC tag, e.g., 001, 665
|
42
|
+
# @param indicator1 [String (frozen)] MARC indicator 1, e.g., 0
|
43
|
+
# @param indicator2 [String (frozen)]
|
44
|
+
# @param subfields [Hash] hash of subfield values as code => value or code => [value, value]
|
45
45
|
# @return [MARC::DataField]
|
46
46
|
def marc_field(tag: 'TST', indicator1: ' ', indicator2: ' ', subfields: {})
|
47
47
|
subfield_objects = subfields.each_with_object([]) do |(code, value), array|
|
@@ -51,8 +51,8 @@ module PennMARC
|
|
51
51
|
end
|
52
52
|
|
53
53
|
# Return a MARC::Record containing passed in DataFields
|
54
|
-
# @param [Array<MARC::DataField>]
|
55
|
-
# @param [String, nil]
|
54
|
+
# @param fields [Array<MARC::DataField>]
|
55
|
+
# @param leader [String, nil]
|
56
56
|
# @return [MARC::Record]
|
57
57
|
def marc_record(fields: [], leader: nil)
|
58
58
|
record = MARC::Record.new
|
data/lib/pennmarc/util.rb
CHANGED
@@ -56,7 +56,7 @@ module PennMARC
|
|
56
56
|
end
|
57
57
|
|
58
58
|
# returns true if a given field has a given subfield value in a given array
|
59
|
-
# @param field [MARC
|
59
|
+
# @param field [MARC::DataField]
|
60
60
|
# @param subfield [String|Integer|Symbol]
|
61
61
|
# @param array [Array]
|
62
62
|
# @return [Boolean]
|
@@ -118,9 +118,9 @@ module PennMARC
|
|
118
118
|
end
|
119
119
|
|
120
120
|
# Get all subfield values for a provided subfield from any occurrence of a provided tag/tags
|
121
|
-
# @param tag [String
|
122
|
-
# @param subfield [String
|
123
|
-
# @param record [MARC::Record]
|
121
|
+
# @param tag [String,Array] tags to consider
|
122
|
+
# @param subfield [String,Symbol] subfield to take the values from
|
123
|
+
# @param record [MARC::Record] source
|
124
124
|
# @return [Array] array of subfield values
|
125
125
|
def subfield_values_for(tag:, subfield:, record:)
|
126
126
|
record.fields(tag).flat_map do |field|
|
@@ -155,8 +155,8 @@ module PennMARC
|
|
155
155
|
end
|
156
156
|
|
157
157
|
# trim trailing punctuation, manipulating string in place
|
158
|
-
# @param trailer [Symbol
|
159
|
-
# @param string [String] to modify
|
158
|
+
# @param trailer [Symbol,String] trailer to target for removal
|
159
|
+
# @param string [String] string to modify
|
160
160
|
# @return [String, Nil] string to modify
|
161
161
|
def trim_trailing!(trailer, string)
|
162
162
|
string.sub! TRAILING_PUNCTUATIONS_PATTERNS[trailer.to_sym], ''
|
@@ -218,17 +218,17 @@ module PennMARC
|
|
218
218
|
end
|
219
219
|
|
220
220
|
# Get the substring of a string up to a given target character
|
221
|
-
# @param string [
|
222
|
-
# @param target [
|
223
|
-
# @return [String (frozen)]
|
221
|
+
# @param string [String] string to split
|
222
|
+
# @param target [String] character to split upon
|
223
|
+
# @return [String (frozen), nil]
|
224
224
|
def substring_before(string, target)
|
225
225
|
string.scan(target).present? ? string.split(target, 2).first : ''
|
226
226
|
end
|
227
227
|
|
228
228
|
# Get the substring of a string after the first occurrence of a target character
|
229
|
-
# @param string [
|
230
|
-
# @param target [
|
231
|
-
# @return [String (frozen)]
|
229
|
+
# @param string [String] string to split
|
230
|
+
# @param target [String] character to split upon
|
231
|
+
# @return [String (frozen), nil]
|
232
232
|
def substring_after(string, target)
|
233
233
|
string.scan(target).present? ? string.split(target, 2).second : ''
|
234
234
|
end
|
@@ -262,7 +262,7 @@ module PennMARC
|
|
262
262
|
# @todo handle case of receiving a URI? E.g., http://loc.gov/relator/aut
|
263
263
|
# @param relator_code [String, NilClass]
|
264
264
|
# @param mapping [Hash]
|
265
|
-
# @return [String,
|
265
|
+
# @return [String, nil] full relator string
|
266
266
|
def translate_relator(relator_code, mapping)
|
267
267
|
return if relator_code.blank?
|
268
268
|
|
@@ -272,7 +272,7 @@ module PennMARC
|
|
272
272
|
# Get 650 & 880 for Provenance and Chronology: prefix should be 'PRO' or 'CHR' and may be preceded by a '%'
|
273
273
|
# @note 11/2018: do not display $5 in PRO or CHR subjs
|
274
274
|
# @param record [MARC::Record]
|
275
|
-
# @param prefix [String] to select from subject field
|
275
|
+
# @param prefix [String] prefix to select from subject field
|
276
276
|
# @return [Array] array of values
|
277
277
|
def prefixed_subject_and_alternate(record, prefix)
|
278
278
|
record.fields(%w[650 880]).filter_map { |field|
|
@@ -340,7 +340,7 @@ module PennMARC
|
|
340
340
|
|
341
341
|
relator = subfield_values(field, '4').filter_map { |code| translate_relator(code, relator_map) }
|
342
342
|
|
343
|
-
relator = subfield_values(field, relator_term_sf) if relator.blank?
|
343
|
+
relator = subfield_values(field, relator_term_sf).map { |term| trim_trailing(:comma, term) } if relator.blank?
|
344
344
|
|
345
345
|
relator = append_trailing(:period, relator.join(', ')) if relator.present?
|
346
346
|
|
@@ -349,9 +349,9 @@ module PennMARC
|
|
349
349
|
|
350
350
|
# Returns a relator value of the given field. Like append_relator, it prioritizes relator codes found in subfileld
|
351
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]
|
353
|
-
# @param [String]
|
354
|
-
# @param [Hash]
|
352
|
+
# @param field [MARC::Field] where relator values are stored
|
353
|
+
# @param relator_term_sf [String] MARC subfield that stores relator term
|
354
|
+
# @param relator_map [Hash]
|
355
355
|
# @return [String]
|
356
356
|
def relator(field:, relator_term_sf:, relator_map: Mappers.relator)
|
357
357
|
relator = subfield_values(field, '4').filter_map { |code| translate_relator(code, relator_map) }
|
data/lib/pennmarc/version.rb
CHANGED
data/pennmarc.gemspec
CHANGED
@@ -21,7 +21,6 @@ Gem::Specification.new do |s|
|
|
21
21
|
s.add_dependency 'activesupport', '~> 7'
|
22
22
|
s.add_dependency 'library_stdnums', '~> 1.6'
|
23
23
|
s.add_dependency 'marc', '~> 1.2'
|
24
|
-
s.add_dependency 'multi_string_replace', '~> 2.0'
|
25
24
|
s.add_dependency 'nokogiri', '~> 1.15'
|
26
25
|
|
27
26
|
s.metadata['rubygems_mfa_required'] = 'false'
|
@@ -1,8 +1,8 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
3
|
describe 'PennMARC::HeadingControl' do
|
4
|
-
let(:replace_term) { PennMARC::Mappers.heading_overrides.
|
5
|
-
let(:replaced_term) { PennMARC::Mappers.heading_overrides.
|
4
|
+
let(:replace_term) { PennMARC::Mappers.heading_overrides.keys[2] }
|
5
|
+
let(:replaced_term) { PennMARC::Mappers.heading_overrides.values[2] }
|
6
6
|
let(:remove_term) { PennMARC::Mappers.headings_to_remove.first }
|
7
7
|
|
8
8
|
describe '.process' do
|
@@ -23,15 +23,22 @@ describe 'PennMARC::HeadingControl' do
|
|
23
23
|
end
|
24
24
|
end
|
25
25
|
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
|
26
|
+
PennMARC::Mappers.heading_overrides.each do |target, replacement|
|
27
|
+
context "with the \"#{target}\" term" do
|
28
|
+
it 'replaces the term in isolation' do
|
29
|
+
values = [target]
|
30
|
+
expect(PennMARC::HeadingControl.term_override(values)).to eq [replacement]
|
31
|
+
end
|
32
|
+
|
33
|
+
it 'replaces the term when used with other headings' do
|
34
|
+
values = ["#{target}--History"]
|
35
|
+
expect(PennMARC::HeadingControl.term_override(values)).to eq ["#{replacement}--History"]
|
36
|
+
end
|
31
37
|
|
32
|
-
|
33
|
-
|
34
|
-
|
38
|
+
it 'replaces the term regardless of case' do
|
39
|
+
values = ["#{target.titleize}--History"]
|
40
|
+
expect(PennMARC::HeadingControl.term_override(values)).to eq ["#{replacement}--History"]
|
41
|
+
end
|
35
42
|
end
|
36
43
|
end
|
37
44
|
|
@@ -9,9 +9,9 @@ describe 'PennMARC::Creator' do
|
|
9
9
|
|
10
10
|
context 'with a single author record' do
|
11
11
|
let(:fields) do
|
12
|
-
[marc_field(tag: '100', subfields: { a: 'Surname, Name', '0': 'http://cool.uri/12345',
|
12
|
+
[marc_field(tag: '100', subfields: { a: 'Surname, Name,', '0': 'http://cool.uri/12345',
|
13
13
|
e: 'author', d: '1900-2000' }),
|
14
|
-
marc_field(tag: '880', subfields: { a: 'Surname, Alternative', '6': '100' })]
|
14
|
+
marc_field(tag: '880', subfields: { a: 'Surname, Alternative,', '6': '100' })]
|
15
15
|
end
|
16
16
|
|
17
17
|
it 'contains the expected search field values for a single author work' do
|
@@ -109,18 +109,21 @@ describe 'PennMARC::Creator' do
|
|
109
109
|
end
|
110
110
|
end
|
111
111
|
|
112
|
-
context 'with
|
112
|
+
context 'with five author records - abbreviated names' do
|
113
113
|
let(:fields) do
|
114
|
-
[marc_field(tag: '100', subfields: { a: 'Surname, Alex', '0': 'http://cool.uri/12345', d: '1900-2000',
|
114
|
+
[marc_field(tag: '100', subfields: { a: 'Surname, Alex, ', '0': 'http://cool.uri/12345', d: '1900-2000',
|
115
115
|
e: 'author.', '4': 'http://cool.uri/vocabulary/relators/aut' }),
|
116
|
-
marc_field(tag: '110', subfields: { a: 'Second, NameX', '0': 'http://cool.uri/12345', d: '1901-2010',
|
116
|
+
marc_field(tag: '110', subfields: { a: 'Second, NameX, ', '0': 'http://cool.uri/12345', d: '1901-2010',
|
117
117
|
e: 'author.', '4': 'http://cool.uri/vocabulary/relators/aut' }),
|
118
|
-
marc_field(tag: '700', subfields: { a: 'Alt, Alternative', '6': '100', d: '1970-' })
|
118
|
+
marc_field(tag: '700', subfields: { a: 'Alt, Alternative', '6': '100', d: '1970-' }),
|
119
|
+
marc_field(tag: '100', subfields: { a: 'Name with no comma', e: 'author' }),
|
120
|
+
marc_field(tag: '100', subfields: { a: 'Name ends with comma,', e: 'author' })]
|
119
121
|
end
|
120
122
|
|
121
123
|
it 'returns single author values with no URIs anywhere' do
|
122
124
|
values = helper.authors_list(record, first_initial_only: true)
|
123
|
-
expect(values).to contain_exactly 'Surname, A.', 'Second, N.', 'Alt, A.'
|
125
|
+
expect(values).to contain_exactly 'Surname, A.', 'Second, N.', 'Alt, A.',
|
126
|
+
'Name ends with comma', 'Name with no comma'
|
124
127
|
end
|
125
128
|
end
|
126
129
|
end
|
@@ -132,14 +135,14 @@ describe 'PennMARC::Creator' do
|
|
132
135
|
let(:fields) do
|
133
136
|
[marc_field(tag: '100', subfields: { a: 'Hamilton, Alex', '0': 'http://cool.uri/12345', d: '1900-2000',
|
134
137
|
e: 'author.' }),
|
135
|
-
marc_field(tag: '100', subfields: { a: 'Lincoln, Abraham', b: 'I', c: 'laureate', d: '1968', e: 'author',
|
136
|
-
j: 'pseud', q: 'Fuller Name', u: 'affiliation', '3': 'materials',
|
138
|
+
marc_field(tag: '100', subfields: { a: 'Lincoln, Abraham, ', b: 'I', c: 'laureate', d: '1968', e: 'author',
|
139
|
+
j: 'pseud', q: 'Fuller Name, ', u: 'affiliation', '3': 'materials',
|
137
140
|
'4': 'aut' }),
|
138
141
|
marc_field(tag: '700', subfields: { a: 'Einstein, Albert', '6': '100', d: '1970-', '4': 'trl',
|
139
142
|
e: 'translator' }),
|
140
143
|
marc_field(tag: '700', subfields: { a: 'Franklin, Ben', '6': '100', d: '1970-', '4': 'edt' }),
|
141
144
|
marc_field(tag: '710', subfields: { a: 'Jefferson, Thomas', '6': '100', d: '1870-', '4': 'edt' }),
|
142
|
-
marc_field(tag: '700', subfields: { a: 'Dickens, Charles', '6': '100', d: '1970-', '4': 'com' })]
|
145
|
+
marc_field(tag: '700', subfields: { a: 'Dickens, Charles, ', '6': '100', d: '1970-', '4': 'com' })]
|
143
146
|
end
|
144
147
|
|
145
148
|
it 'returns two authors and four contributors' do
|
@@ -153,7 +156,7 @@ describe 'PennMARC::Creator' do
|
|
153
156
|
|
154
157
|
context 'with two authors and four contributors records, with full information and relator' do
|
155
158
|
let(:fields) do
|
156
|
-
[marc_field(tag: '100', subfields: { a: 'Hamilton, Alex', '0': 'http://cool.uri/12345', d: '1900-2000',
|
159
|
+
[marc_field(tag: '100', subfields: { a: 'Hamilton, Alex, ', '0': 'http://cool.uri/12345', d: '1900-2000',
|
157
160
|
e: 'author.', '4': 'aut' }),
|
158
161
|
marc_field(tag: '100', subfields: { a: 'Lincoln, Abraham', b: 'I', c: 'laureate', d: '1968', e: 'author',
|
159
162
|
j: 'pseud', q: 'Fuller Name', u: 'affiliation', '3': 'materials',
|
@@ -164,7 +167,7 @@ describe 'PennMARC::Creator' do
|
|
164
167
|
marc_field(tag: '710', subfields: { a: 'Jefferson, Thomas', '6': '100', d: '1870-', '4': 'edt' }),
|
165
168
|
marc_field(tag: '700', subfields: { a: 'Dickens, Charles', '6': '100', d: '1970-', '4': 'com' }),
|
166
169
|
marc_field(tag: '880', subfields: { a: '狄更斯', '6': '700', d: '1970-', '4': 'com' }),
|
167
|
-
marc_field(tag: '700', subfields: { a: 'Twain, Mark', '6': '100', d: '1870-' })]
|
170
|
+
marc_field(tag: '700', subfields: { a: 'Twain, Mark,', '6': '100', d: '1870-' })]
|
168
171
|
end
|
169
172
|
|
170
173
|
it 'returns four contributors' do
|