traject 2.0.0-java
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +18 -0
- data/.travis.yml +27 -0
- data/.yardopts +3 -0
- data/Gemfile +12 -0
- data/LICENSE.txt +20 -0
- data/README.md +461 -0
- data/Rakefile +21 -0
- data/bench/bench.rb +30 -0
- data/bin/traject +16 -0
- data/doc/batch_execution.md +243 -0
- data/doc/extending.md +190 -0
- data/doc/indexing_rules.md +265 -0
- data/doc/other_commands.md +47 -0
- data/doc/settings.md +101 -0
- data/lib/tasks/load_maps.rake +48 -0
- data/lib/traject.rb +11 -0
- data/lib/traject/command_line.rb +301 -0
- data/lib/traject/csv_writer.rb +34 -0
- data/lib/traject/debug_writer.rb +47 -0
- data/lib/traject/delimited_writer.rb +110 -0
- data/lib/traject/indexer.rb +613 -0
- data/lib/traject/indexer/settings.rb +110 -0
- data/lib/traject/json_writer.rb +51 -0
- data/lib/traject/line_writer.rb +63 -0
- data/lib/traject/macros/basic.rb +9 -0
- data/lib/traject/macros/marc21.rb +223 -0
- data/lib/traject/macros/marc21_semantics.rb +584 -0
- data/lib/traject/macros/marc_format_classifier.rb +197 -0
- data/lib/traject/marc_extractor.rb +410 -0
- data/lib/traject/marc_reader.rb +89 -0
- data/lib/traject/mock_reader.rb +97 -0
- data/lib/traject/ndj_reader.rb +40 -0
- data/lib/traject/null_writer.rb +22 -0
- data/lib/traject/qualified_const_get.rb +40 -0
- data/lib/traject/solr_json_writer.rb +277 -0
- data/lib/traject/thread_pool.rb +161 -0
- data/lib/traject/translation_map.rb +267 -0
- data/lib/traject/util.rb +52 -0
- data/lib/traject/version.rb +3 -0
- data/lib/traject/yaml_writer.rb +9 -0
- data/lib/translation_maps/lcc_top_level.yaml +26 -0
- data/lib/translation_maps/marc_genre_007.yaml +9 -0
- data/lib/translation_maps/marc_genre_leader.yaml +22 -0
- data/lib/translation_maps/marc_geographic.yaml +589 -0
- data/lib/translation_maps/marc_instruments.yaml +102 -0
- data/lib/translation_maps/marc_languages.yaml +490 -0
- data/test/debug_writer_test.rb +38 -0
- data/test/delimited_writer_test.rb +104 -0
- data/test/indexer/each_record_test.rb +59 -0
- data/test/indexer/macros_marc21_semantics_test.rb +391 -0
- data/test/indexer/macros_marc21_test.rb +190 -0
- data/test/indexer/macros_test.rb +40 -0
- data/test/indexer/map_record_test.rb +209 -0
- data/test/indexer/read_write_test.rb +101 -0
- data/test/indexer/settings_test.rb +152 -0
- data/test/indexer/to_field_test.rb +77 -0
- data/test/marc_extractor_test.rb +412 -0
- data/test/marc_format_classifier_test.rb +98 -0
- data/test/marc_reader_test.rb +110 -0
- data/test/solr_json_writer_test.rb +248 -0
- data/test/test_helper.rb +90 -0
- data/test/test_support/245_no_ab.marc +1 -0
- data/test/test_support/880_with_no_6.utf8.marc +1 -0
- data/test/test_support/bad_subfield_code.marc +1 -0
- data/test/test_support/bad_utf_byte.utf8.marc +1 -0
- data/test/test_support/date_resort_to_260.marc +1 -0
- data/test/test_support/date_type_r_missing_date2.marc +1 -0
- data/test/test_support/date_with_u.marc +1 -0
- data/test/test_support/demo_config.rb +155 -0
- data/test/test_support/emptyish_record.marc +1 -0
- data/test/test_support/escaped_character_reference.marc8.marc +1 -0
- data/test/test_support/george_eliot.marc +1 -0
- data/test/test_support/hebrew880s.marc +1 -0
- data/test/test_support/louis_armstrong.marc +1 -0
- data/test/test_support/manufacturing_consent.marc +1 -0
- data/test/test_support/manuscript_online_thesis.marc +1 -0
- data/test/test_support/microform_online_conference.marc +1 -0
- data/test/test_support/multi_era.marc +1 -0
- data/test/test_support/multi_geo.marc +1 -0
- data/test/test_support/musical_cage.marc +1 -0
- data/test/test_support/nature.marc +1 -0
- data/test/test_support/one-marc8.mrc +1 -0
- data/test/test_support/online_only.marc +1 -0
- data/test/test_support/packed_041a_lang.marc +1 -0
- data/test/test_support/test_data.utf8.json +30 -0
- data/test/test_support/test_data.utf8.marc.xml +2609 -0
- data/test/test_support/test_data.utf8.mrc +1 -0
- data/test/test_support/test_data.utf8.mrc.gz +0 -0
- data/test/test_support/the_business_ren.marc +1 -0
- data/test/translation_map_test.rb +225 -0
- data/test/translation_maps/bad_ruby.rb +8 -0
- data/test/translation_maps/bad_yaml.yaml +1 -0
- data/test/translation_maps/both_map.rb +1 -0
- data/test/translation_maps/both_map.yaml +1 -0
- data/test/translation_maps/default_literal.rb +10 -0
- data/test/translation_maps/default_passthrough.rb +10 -0
- data/test/translation_maps/marc_040a_translate_test.yaml +1 -0
- data/test/translation_maps/properties_map.properties +5 -0
- data/test/translation_maps/ruby_map.rb +10 -0
- data/test/translation_maps/translate_array_test.yaml +8 -0
- data/test/translation_maps/yaml_map.yaml +7 -0
- data/traject.gemspec +47 -0
- metadata +382 -0
@@ -0,0 +1,98 @@
|
|
1
|
+
require 'test_helper'
|
2
|
+
|
3
|
+
require 'traject/macros/marc_format_classifier'
|
4
|
+
|
5
|
+
MarcFormatClassifier = Traject::Macros::MarcFormatClassifier
|
6
|
+
|
7
|
+
def classifier_for(filename)
|
8
|
+
record = MARC::Reader.new(support_file_path filename).to_a.first
|
9
|
+
return MarcFormatClassifier.new( record )
|
10
|
+
end
|
11
|
+
|
12
|
+
describe "MarcFormatClassifier" do
|
13
|
+
|
14
|
+
it "returns 'Print' when there's no other data" do
|
15
|
+
assert_equal ['Print'], MarcFormatClassifier.new( empty_record ).formats
|
16
|
+
end
|
17
|
+
|
18
|
+
describe "genre" do
|
19
|
+
# We don't have the patience to test every case, just a sampling
|
20
|
+
it "says book" do
|
21
|
+
assert_equal ["Book"], classifier_for("manufacturing_consent.marc").genre
|
22
|
+
end
|
23
|
+
it "says Book for a weird one" do
|
24
|
+
assert_equal ["Book"], classifier_for("microform_online_conference.marc").genre
|
25
|
+
end
|
26
|
+
it "says Musical Recording" do
|
27
|
+
assert_equal ["Musical Recording"], classifier_for("musical_cage.marc").genre
|
28
|
+
end
|
29
|
+
it "says Journal" do
|
30
|
+
assert_equal ["Journal/Newspaper"], classifier_for("the_business_ren.marc").genre
|
31
|
+
end
|
32
|
+
end
|
33
|
+
|
34
|
+
|
35
|
+
describe "print?" do
|
36
|
+
it "says print when it is" do
|
37
|
+
assert classifier_for("manufacturing_consent.marc").print?
|
38
|
+
end
|
39
|
+
it "does not say print for online only" do
|
40
|
+
assert ! classifier_for("online_only.marc").print?
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
describe "online?" do
|
45
|
+
it "says online when it is" do
|
46
|
+
assert classifier_for("online_only.marc").online?
|
47
|
+
assert classifier_for("microform_online_conference.marc").online?
|
48
|
+
assert classifier_for("manuscript_online_thesis.marc").online?
|
49
|
+
end
|
50
|
+
it "does not say online for a print only" do
|
51
|
+
assert ! classifier_for("manufacturing_consent.marc").online?
|
52
|
+
end
|
53
|
+
end
|
54
|
+
|
55
|
+
describe "microform?" do
|
56
|
+
it "says microform when it is" do
|
57
|
+
assert classifier_for("microform_online_conference.marc").microform?
|
58
|
+
end
|
59
|
+
it "does not say microform when it ain't" do
|
60
|
+
assert ! classifier_for("manufacturing_consent.marc").microform?
|
61
|
+
assert ! classifier_for("online_only.marc").microform?
|
62
|
+
end
|
63
|
+
it "catches microform in an 007" do
|
64
|
+
assert classifier_for("nature.marc").microform?
|
65
|
+
end
|
66
|
+
end
|
67
|
+
|
68
|
+
describe "conference?" do
|
69
|
+
it "says conference when it is" do
|
70
|
+
assert classifier_for("microform_online_conference.marc").proceeding?
|
71
|
+
end
|
72
|
+
it "does not say conference when it ain't" do
|
73
|
+
assert ! classifier_for("manufacturing_consent.marc").proceeding?
|
74
|
+
assert ! classifier_for("online_only.marc").proceeding?
|
75
|
+
end
|
76
|
+
end
|
77
|
+
|
78
|
+
describe "thesis?" do
|
79
|
+
it "says thesis when it is" do
|
80
|
+
assert classifier_for("manuscript_online_thesis.marc").thesis?
|
81
|
+
end
|
82
|
+
it "does not say thesis when it ain't" do
|
83
|
+
assert ! classifier_for("manufacturing_consent.marc").thesis?
|
84
|
+
assert ! classifier_for("online_only.marc").thesis?
|
85
|
+
end
|
86
|
+
end
|
87
|
+
|
88
|
+
describe "manuscript_archive?" do
|
89
|
+
it "says manuscript when it is" do
|
90
|
+
assert classifier_for("manuscript_online_thesis.marc").manuscript_archive?
|
91
|
+
end
|
92
|
+
it "does not say manuscript when it ain't" do
|
93
|
+
assert ! classifier_for("manufacturing_consent.marc").manuscript_archive?
|
94
|
+
assert ! classifier_for("online_only.marc").manuscript_archive?
|
95
|
+
end
|
96
|
+
end
|
97
|
+
|
98
|
+
end
|
@@ -0,0 +1,110 @@
|
|
1
|
+
# Encoding: UTF-8
|
2
|
+
|
3
|
+
require 'test_helper'
|
4
|
+
require 'traject/marc_reader'
|
5
|
+
require 'marc'
|
6
|
+
|
7
|
+
describe "Traject::MarcReader" do
|
8
|
+
|
9
|
+
|
10
|
+
it "reads XML" do
|
11
|
+
file = File.new(support_file_path "test_data.utf8.marc.xml")
|
12
|
+
settings = Traject::Indexer::Settings.new("marc_source.type" => "xml")
|
13
|
+
reader = Traject::MarcReader.new(file, settings)
|
14
|
+
|
15
|
+
array = reader.to_a
|
16
|
+
|
17
|
+
assert_equal 30, array.length
|
18
|
+
end
|
19
|
+
|
20
|
+
|
21
|
+
describe "MARC binary" do
|
22
|
+
it "reads" do
|
23
|
+
file = File.new(support_file_path "test_data.utf8.mrc")
|
24
|
+
settings = Traject::Indexer::Settings.new() # binary type is default
|
25
|
+
reader = Traject::MarcReader.new(file, settings)
|
26
|
+
|
27
|
+
array = reader.to_a
|
28
|
+
|
29
|
+
assert_equal 30, array.length
|
30
|
+
|
31
|
+
first = array.first
|
32
|
+
|
33
|
+
assert_kind_of MARC::Record, first
|
34
|
+
|
35
|
+
assert first['245']['a'].encoding.name, "UTF-8"
|
36
|
+
assert_equal "Fikr-i Ayāz /", first['245']['a']
|
37
|
+
end
|
38
|
+
|
39
|
+
it "reads Marc binary in Marc8 encoding, transcoding to UTF-8" do
|
40
|
+
file = File.new(support_file_path("one-marc8.mrc"))
|
41
|
+
settings = Traject::Indexer::Settings.new("marc_source.encoding" => "MARC-8")
|
42
|
+
reader = Traject::MarcReader.new(file, settings)
|
43
|
+
|
44
|
+
array = reader.to_a
|
45
|
+
|
46
|
+
assert_length 1, array
|
47
|
+
|
48
|
+
|
49
|
+
assert_kind_of MARC::Record, array.first
|
50
|
+
a245a = array.first['245']['a']
|
51
|
+
|
52
|
+
assert a245a.encoding.name, "UTF-8"
|
53
|
+
assert a245a.valid_encoding?
|
54
|
+
assert_equal "Por uma outra globalização :", a245a
|
55
|
+
end
|
56
|
+
|
57
|
+
it "replaces unicode character reference in Marc8 transcode" do
|
58
|
+
file = File.new(support_file_path("escaped_character_reference.marc8.marc"))
|
59
|
+
|
60
|
+
settings = Traject::Indexer::Settings.new("marc_source.encoding" => "MARC-8") # binary type is default
|
61
|
+
record = Traject::MarcReader.new(file, settings).to_a.first
|
62
|
+
|
63
|
+
assert_equal "Rio de Janeiro escaped replacement char: \uFFFD .", record['260']['a']
|
64
|
+
end
|
65
|
+
|
66
|
+
it "raises on unrecognized encoding for binary type" do
|
67
|
+
file = File.new(support_file_path "one-marc8.mrc")
|
68
|
+
settings = Traject::Indexer::Settings.new("marc_source.encoding" => "ADFADFADF")
|
69
|
+
assert_raises(ArgumentError) do
|
70
|
+
record = Traject::MarcReader.new(file, settings).to_a.first
|
71
|
+
end
|
72
|
+
end
|
73
|
+
|
74
|
+
it "replaces bad byte in UTF8 marc binary" do
|
75
|
+
file = File.new(support_file_path "bad_utf_byte.utf8.marc")
|
76
|
+
|
77
|
+
settings = Traject::Indexer::Settings.new() # binary type is default
|
78
|
+
reader = Traject::MarcReader.new(file, settings)
|
79
|
+
|
80
|
+
record = reader.to_a.first
|
81
|
+
|
82
|
+
value = record['300']['a']
|
83
|
+
|
84
|
+
assert_equal value.encoding.name, "UTF-8"
|
85
|
+
assert value.valid_encoding?, "Has valid encoding"
|
86
|
+
assert_equal "This is a bad byte: '\uFFFD' and another: '\uFFFD'", value
|
87
|
+
end
|
88
|
+
end
|
89
|
+
|
90
|
+
it "reads JSON" do
|
91
|
+
file = File.new(support_file_path "test_data.utf8.json")
|
92
|
+
settings = Traject::Indexer::Settings.new("marc_source.type" => "json")
|
93
|
+
reader = Traject::MarcReader.new(file, settings)
|
94
|
+
array = reader.to_a
|
95
|
+
|
96
|
+
assert_equal 30, array.length
|
97
|
+
|
98
|
+
first = array.first
|
99
|
+
|
100
|
+
assert_kind_of MARC::Record, first
|
101
|
+
|
102
|
+
assert first['245']['a'].encoding.name, "UTF-8"
|
103
|
+
assert_equal "Fikr-i Ayāz /", first['245']['a']
|
104
|
+
end
|
105
|
+
|
106
|
+
|
107
|
+
|
108
|
+
|
109
|
+
|
110
|
+
end
|
@@ -0,0 +1,248 @@
|
|
1
|
+
require 'test_helper'
|
2
|
+
require 'httpclient'
|
3
|
+
require 'traject/solr_json_writer'
|
4
|
+
require 'thread'
|
5
|
+
require 'json'
|
6
|
+
require 'stringio'
|
7
|
+
require 'logger'
|
8
|
+
|
9
|
+
|
10
|
+
# Some basic tests, using a mocked HTTPClient so we can see what it did --
|
11
|
+
# these tests do not run against a real solr server at present.
|
12
|
+
describe "Traject::SolrJsonWriter" do
|
13
|
+
|
14
|
+
|
15
|
+
#######
|
16
|
+
# A bunch of utilities to help testing
|
17
|
+
#######
|
18
|
+
|
19
|
+
class FakeHTTPClient
|
20
|
+
# Always reply with this status, normally 200, can
|
21
|
+
# be reset for testing error conditions.
|
22
|
+
attr_accessor :response_status
|
23
|
+
attr_accessor :allow_update_json_path
|
24
|
+
|
25
|
+
def initialize(*args)
|
26
|
+
@post_args = []
|
27
|
+
@get_args = []
|
28
|
+
@response_status = 200
|
29
|
+
@allow_update_json_path = true
|
30
|
+
@mutex = Monitor.new
|
31
|
+
end
|
32
|
+
|
33
|
+
def post(*args)
|
34
|
+
@mutex.synchronize do
|
35
|
+
@post_args << args
|
36
|
+
end
|
37
|
+
|
38
|
+
resp = HTTP::Message.new_response("")
|
39
|
+
resp.status = self.response_status
|
40
|
+
|
41
|
+
return resp
|
42
|
+
end
|
43
|
+
|
44
|
+
def get (*args)
|
45
|
+
@mutex.synchronize do
|
46
|
+
@get_args << args
|
47
|
+
end
|
48
|
+
|
49
|
+
resp = HTTP::Message.new_response("")
|
50
|
+
resp.status = self.response_status
|
51
|
+
|
52
|
+
if args.first.end_with?("/update/json") && ! self.allow_update_json_path
|
53
|
+
# Need to test auto-detection of /update/json being available
|
54
|
+
resp.status = 404
|
55
|
+
end
|
56
|
+
|
57
|
+
return resp
|
58
|
+
end
|
59
|
+
|
60
|
+
def post_args
|
61
|
+
@mutex.synchronize do
|
62
|
+
@post_args.dup
|
63
|
+
end
|
64
|
+
end
|
65
|
+
|
66
|
+
def get_args
|
67
|
+
@mutex.synchronize do
|
68
|
+
@get_args.dup
|
69
|
+
end
|
70
|
+
end
|
71
|
+
|
72
|
+
# Everything else, just return nil please
|
73
|
+
def method_missing(*args)
|
74
|
+
end
|
75
|
+
end
|
76
|
+
|
77
|
+
|
78
|
+
def context_with(hash)
|
79
|
+
Traject::Indexer::Context.new(:output_hash => hash)
|
80
|
+
end
|
81
|
+
|
82
|
+
def create_writer(settings = {})
|
83
|
+
settings = {
|
84
|
+
"solr.url" => "http://example.com/solr",
|
85
|
+
"solr_json_writer.http_client" => FakeHTTPClient.new
|
86
|
+
}.merge!(settings)
|
87
|
+
@fake_http_client = settings["solr_json_writer.http_client"]
|
88
|
+
|
89
|
+
writer = Traject::SolrJsonWriter.new(settings)
|
90
|
+
|
91
|
+
return writer
|
92
|
+
end
|
93
|
+
|
94
|
+
# strio = StringIO.new
|
95
|
+
# logger_to_strio(strio)
|
96
|
+
#
|
97
|
+
# Later check for strio.string for contents
|
98
|
+
def logger_to_strio(strio)
|
99
|
+
# Yell makes this hard, let's do it with an ordinary logger, think
|
100
|
+
# it's okay.
|
101
|
+
Logger.new(strio)
|
102
|
+
end
|
103
|
+
|
104
|
+
#########
|
105
|
+
# Actual tests
|
106
|
+
#########
|
107
|
+
|
108
|
+
before do
|
109
|
+
@writer = create_writer
|
110
|
+
end
|
111
|
+
|
112
|
+
it "defaults to 1 bg thread" do
|
113
|
+
assert_equal 1, @writer.thread_pool_size
|
114
|
+
end
|
115
|
+
|
116
|
+
it "adds a document" do
|
117
|
+
@writer.put context_with({"id" => "one", "key" => ["value1", "value2"]})
|
118
|
+
@writer.close
|
119
|
+
|
120
|
+
post_args = @fake_http_client.post_args.first
|
121
|
+
|
122
|
+
refute_nil post_args
|
123
|
+
|
124
|
+
assert_equal "http://example.com/solr/update/json", post_args[0]
|
125
|
+
|
126
|
+
refute_nil post_args[1]
|
127
|
+
posted_json = JSON.parse(post_args[1])
|
128
|
+
|
129
|
+
assert_equal [{"id" => "one", "key" => ["value1", "value2"]}], posted_json
|
130
|
+
end
|
131
|
+
|
132
|
+
it "adds more than a batch in batches" do
|
133
|
+
(Traject::SolrJsonWriter::DEFAULT_BATCH_SIZE + 1).times do |i|
|
134
|
+
doc = {"id" => "doc_#{i}", "key" => "value"}
|
135
|
+
@writer.put context_with(doc)
|
136
|
+
end
|
137
|
+
@writer.close
|
138
|
+
|
139
|
+
post_args = @fake_http_client.post_args
|
140
|
+
|
141
|
+
assert_length 2, post_args, "Makes two posts to Solr for two batches"
|
142
|
+
|
143
|
+
assert_length Traject::SolrJsonWriter::DEFAULT_BATCH_SIZE, JSON.parse(post_args[0][1]), "first batch posted with batch size docs"
|
144
|
+
assert_length 1, JSON.parse(post_args[1][1]), "second batch posted with last remaining doc"
|
145
|
+
end
|
146
|
+
|
147
|
+
it "commits on close when set" do
|
148
|
+
@writer = create_writer("solr.url" => "http://example.com", "solr_writer.commit_on_close" => "true")
|
149
|
+
@writer.put context_with({"id" => "one", "key" => ["value1", "value2"]})
|
150
|
+
@writer.close
|
151
|
+
|
152
|
+
last_solr_get = @fake_http_client.get_args.last
|
153
|
+
|
154
|
+
assert_equal "http://example.com/update/json", last_solr_get[0]
|
155
|
+
assert_equal( {"commit" => "true"}, last_solr_get[1] )
|
156
|
+
end
|
157
|
+
|
158
|
+
describe "skipped records" do
|
159
|
+
it "skips and reports under max_skipped" do
|
160
|
+
strio = StringIO.new
|
161
|
+
@writer = create_writer("solr_writer.max_skipped" => 10, "logger" => logger_to_strio(strio))
|
162
|
+
@fake_http_client.response_status = 500
|
163
|
+
|
164
|
+
10.times do |i|
|
165
|
+
@writer.put context_with("id" => "doc_#{i}", "key" => "value")
|
166
|
+
end
|
167
|
+
@writer.close
|
168
|
+
|
169
|
+
assert_equal 10, @writer.skipped_record_count
|
170
|
+
|
171
|
+
logged = strio.string
|
172
|
+
|
173
|
+
10.times do |i|
|
174
|
+
assert_match /ERROR.*Could not add record doc_#{i} at source file position : Solr error response: 500/, logged
|
175
|
+
end
|
176
|
+
end
|
177
|
+
|
178
|
+
it "raises when skipped more than max_skipped" do
|
179
|
+
@writer = create_writer("solr_writer.max_skipped" => 5)
|
180
|
+
@fake_http_client.response_status = 500
|
181
|
+
|
182
|
+
e = assert_raises(RuntimeError) do
|
183
|
+
6.times do |i|
|
184
|
+
@writer.put context_with("id" => "doc_#{i}", "key" => "value")
|
185
|
+
end
|
186
|
+
@writer.close
|
187
|
+
end
|
188
|
+
|
189
|
+
assert_includes e.message, "Exceeded maximum number of skipped records"
|
190
|
+
end
|
191
|
+
|
192
|
+
it "raises on one skipped record when max_skipped is 0" do
|
193
|
+
@writer = create_writer("solr_writer.max_skipped" => 0)
|
194
|
+
@fake_http_client.response_status = 500
|
195
|
+
|
196
|
+
e = assert_raises(RuntimeError) do
|
197
|
+
@writer.put context_with("id" => "doc_1", "key" => "value")
|
198
|
+
@writer.close
|
199
|
+
end
|
200
|
+
end
|
201
|
+
end
|
202
|
+
|
203
|
+
describe "auto-discovers proper update path" do
|
204
|
+
it "finds /update/json" do
|
205
|
+
assert_equal "http://example.com/solr/update/json", @writer.determine_solr_update_url
|
206
|
+
end
|
207
|
+
|
208
|
+
it "resorts to plain /update" do
|
209
|
+
@fake_http_client = FakeHTTPClient.new
|
210
|
+
@fake_http_client.allow_update_json_path = false
|
211
|
+
|
212
|
+
@writer = create_writer("solr.url" => "http://example.com/solr",
|
213
|
+
"solr_json_writer.http_client" => @fake_http_client)
|
214
|
+
|
215
|
+
assert_equal "http://example.com/solr/update", @writer.determine_solr_update_url
|
216
|
+
end
|
217
|
+
end
|
218
|
+
|
219
|
+
describe "Record id from context" do
|
220
|
+
before do
|
221
|
+
@record = MARC::Reader.new(support_file_path('test_data.utf8.mrc')).first
|
222
|
+
@context = Traject::Indexer::Context.new
|
223
|
+
@writer = create_writer
|
224
|
+
@record_001 = " 00282214 " # from the mrc file
|
225
|
+
end
|
226
|
+
|
227
|
+
it "gets it from 001" do
|
228
|
+
@context.source_record = @record
|
229
|
+
assert_equal @record_001, @writer.record_id_from_context(@context)
|
230
|
+
end
|
231
|
+
|
232
|
+
it "gets it from the id" do
|
233
|
+
@context.output_hash['id'] = 'the_record_id'
|
234
|
+
assert_equal 'the_record_id', @writer.record_id_from_context(@context)
|
235
|
+
end
|
236
|
+
|
237
|
+
it "gets it from both 001 and id" do
|
238
|
+
@context.output_hash['id'] = 'the_record_id'
|
239
|
+
@context.source_record = @record
|
240
|
+
assert_equal [@record_001, 'the_record_id'].join('/'), @writer.record_id_from_context(@context)
|
241
|
+
end
|
242
|
+
|
243
|
+
|
244
|
+
|
245
|
+
end
|
246
|
+
|
247
|
+
|
248
|
+
end
|