omelette 0.0.1a
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.gitignore +15 -0
- data/.rspec +3 -0
- data/.travis.yml +6 -0
- data/Gemfile +6 -0
- data/Gemfile.lock +75 -0
- data/LICENSE.txt +21 -0
- data/README.md +43 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/exe/omelette +5 -0
- data/lib/omelette.rb +10 -0
- data/lib/omelette/command_line.rb +10 -0
- data/lib/omelette/importer.rb +284 -0
- data/lib/omelette/importer/context.rb +42 -0
- data/lib/omelette/importer/errors.rb +40 -0
- data/lib/omelette/importer/settings.rb +106 -0
- data/lib/omelette/importer/steps.rb +64 -0
- data/lib/omelette/macros/xpath.rb +14 -0
- data/lib/omelette/null_writer.rb +20 -0
- data/lib/omelette/omeka_json_writer.rb +9 -0
- data/lib/omelette/thread_pool.rb +161 -0
- data/lib/omelette/util.rb +146 -0
- data/lib/omelette/version.rb +3 -0
- data/lib/omelette/xml_reader.rb +27 -0
- data/omelette.gemspec +36 -0
- metadata +213 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: d5c99f1e799db62ab94213b0919b401f00fa7f0f
|
4
|
+
data.tar.gz: 8f89f4fb46dee7a19305f20432acf7ead96aa9bf
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 0d5ab5c28afe2ec4b2cd7d137813465c317ba2a3519baa287719a6fa545aaad1912fa322092de188349555c7fbd53c0264c46155842130389bd7ebfa063b3d79
|
7
|
+
data.tar.gz: b58aa6854cff01fbf7bd79250e128c8f69aa2c03975ee3376c735395d0626fb921589326c0d98d879861645e843c747ab9ce526e507749c32053db1635619efd
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,75 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
omelette (0.0.1a)
|
5
|
+
concurrent-ruby (~> 1.0)
|
6
|
+
hashie (~> 3.5)
|
7
|
+
nokogiri (~> 1.8)
|
8
|
+
rest-client (~> 2.0)
|
9
|
+
thor (~> 0.20)
|
10
|
+
yell (~> 2.0)
|
11
|
+
|
12
|
+
GEM
|
13
|
+
remote: https://rubygems.org/
|
14
|
+
specs:
|
15
|
+
addressable (2.5.2)
|
16
|
+
public_suffix (>= 2.0.2, < 4.0)
|
17
|
+
concurrent-ruby (1.0.5)
|
18
|
+
crack (0.4.3)
|
19
|
+
safe_yaml (~> 1.0.0)
|
20
|
+
diff-lcs (1.3)
|
21
|
+
domain_name (0.5.20170404)
|
22
|
+
unf (>= 0.0.5, < 1.0.0)
|
23
|
+
hashdiff (0.3.7)
|
24
|
+
hashie (3.5.6)
|
25
|
+
http-cookie (1.0.3)
|
26
|
+
domain_name (~> 0.5)
|
27
|
+
mime-types (3.1)
|
28
|
+
mime-types-data (~> 3.2015)
|
29
|
+
mime-types-data (3.2016.0521)
|
30
|
+
mini_portile2 (2.3.0)
|
31
|
+
netrc (0.11.0)
|
32
|
+
nokogiri (1.8.1)
|
33
|
+
mini_portile2 (~> 2.3.0)
|
34
|
+
public_suffix (3.0.1)
|
35
|
+
rake (10.5.0)
|
36
|
+
rest-client (2.0.2)
|
37
|
+
http-cookie (>= 1.0.2, < 2.0)
|
38
|
+
mime-types (>= 1.16, < 4.0)
|
39
|
+
netrc (~> 0.8)
|
40
|
+
rspec (3.7.0)
|
41
|
+
rspec-core (~> 3.7.0)
|
42
|
+
rspec-expectations (~> 3.7.0)
|
43
|
+
rspec-mocks (~> 3.7.0)
|
44
|
+
rspec-core (3.7.0)
|
45
|
+
rspec-support (~> 3.7.0)
|
46
|
+
rspec-expectations (3.7.0)
|
47
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
48
|
+
rspec-support (~> 3.7.0)
|
49
|
+
rspec-mocks (3.7.0)
|
50
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
51
|
+
rspec-support (~> 3.7.0)
|
52
|
+
rspec-support (3.7.0)
|
53
|
+
safe_yaml (1.0.4)
|
54
|
+
thor (0.20.0)
|
55
|
+
unf (0.1.4)
|
56
|
+
unf_ext
|
57
|
+
unf_ext (0.0.7.4)
|
58
|
+
webmock (3.1.0)
|
59
|
+
addressable (>= 2.3.6)
|
60
|
+
crack (>= 0.3.2)
|
61
|
+
hashdiff
|
62
|
+
yell (2.0.7)
|
63
|
+
|
64
|
+
PLATFORMS
|
65
|
+
ruby
|
66
|
+
|
67
|
+
DEPENDENCIES
|
68
|
+
bundler (~> 1.16)
|
69
|
+
omelette!
|
70
|
+
rake (~> 10.0)
|
71
|
+
rspec (~> 3.0)
|
72
|
+
webmock (~> 3.0)
|
73
|
+
|
74
|
+
BUNDLED WITH
|
75
|
+
1.16.0
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2017 Dazhi Jiao
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,43 @@
|
|
1
|
+
# Omelette
|
2
|
+
|
3
|
+
Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/omelette`. To experiment with that code, run `bin/console` for an interactive prompt.
|
4
|
+
|
5
|
+
TODO: Delete this and the text above, and describe your gem
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'omelette'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install omelette
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
TODO: Write usage instructions here
|
26
|
+
|
27
|
+
## Development
|
28
|
+
|
29
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
30
|
+
|
31
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
32
|
+
|
33
|
+
## Contributing
|
34
|
+
|
35
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/omelette. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
|
36
|
+
|
37
|
+
## License
|
38
|
+
|
39
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
40
|
+
|
41
|
+
## Code of Conduct
|
42
|
+
|
43
|
+
Everyone interacting in the Omelette project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/omelette/blob/master/CODE_OF_CONDUCT.md).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "omelette"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start(__FILE__)
|
data/bin/setup
ADDED
data/exe/omelette
ADDED
data/lib/omelette.rb
ADDED
@@ -0,0 +1,284 @@
|
|
1
|
+
require 'yell'
|
2
|
+
require 'omelette/importer/context'
|
3
|
+
require 'omelette/importer/settings'
|
4
|
+
require 'omelette/importer/errors'
|
5
|
+
require 'omelette/importer/steps'
|
6
|
+
require 'omelette/thread_pool'
|
7
|
+
require 'omelette/macros/xpath'
|
8
|
+
|
9
|
+
class Omelette::Importer
|
10
|
+
include Omelette::Macros::Xpath
|
11
|
+
|
12
|
+
attr_writer :reader_class, :writer_class, :writer
|
13
|
+
attr_reader :logger
|
14
|
+
|
15
|
+
def initialize(arg_settings = {})
|
16
|
+
@settings = Settings.new(arg_settings)
|
17
|
+
@import_steps = []
|
18
|
+
@after_processing_steps = []
|
19
|
+
|
20
|
+
@logger = create_logger
|
21
|
+
end
|
22
|
+
|
23
|
+
def elements_map
|
24
|
+
@elements_map ||= Omelette::Util.build_elements_map @settings['omeka_api_root']
|
25
|
+
end
|
26
|
+
|
27
|
+
# Pass a string file path, a Pathname, or a File object, for
|
28
|
+
# a config file to load into indexer.
|
29
|
+
#
|
30
|
+
# Can raise:
|
31
|
+
# * Errno::ENOENT or Errno::EACCES if file path is not accessible
|
32
|
+
# * Omelette::Importer::ConfigLoadError if exception is raised evaluating
|
33
|
+
# the config. A ConfigLoadError has information in it about original
|
34
|
+
# exception, and exactly what config file and line number triggered it.
|
35
|
+
def load_config_file(file_path)
|
36
|
+
File.open file_path do |file|
|
37
|
+
begin
|
38
|
+
self.instance_eval file.read, file_path.to_s
|
39
|
+
rescue ScriptError, StandardError => ex
|
40
|
+
raise ConfigLoadError.new(file_path.to_s, ex)
|
41
|
+
end
|
42
|
+
end
|
43
|
+
end
|
44
|
+
|
45
|
+
def settings(new_settings = nil, &block)
|
46
|
+
@settings.merge! new_settings if new_settings
|
47
|
+
@settings.instance_eval &block if block_given?
|
48
|
+
return @settings
|
49
|
+
end
|
50
|
+
|
51
|
+
def to_element(element_name, element_set_name, aLambda = nil, &block)
|
52
|
+
@import_steps << ToElementStep.new(element_name, element_set_name, elements_map, aLambda, block, Omelette::Util.extract_caller_location(caller.first))
|
53
|
+
end
|
54
|
+
|
55
|
+
# Processes a single item according to extracting rules set up in
|
56
|
+
# this importer. Returns the output hash (a hash whose keys are
|
57
|
+
# string fields, and values are arrays of one or more values in that field)
|
58
|
+
#
|
59
|
+
# This is a convenience shortcut for #map_to_context! -- use that one
|
60
|
+
# if you want to provide addtional context
|
61
|
+
# like position, and/or get back the full context.
|
62
|
+
def map_item(item)
|
63
|
+
context = Context.new(source_item: item, settings: settings)
|
64
|
+
map_to_context! context
|
65
|
+
return context.output_hash
|
66
|
+
end
|
67
|
+
|
68
|
+
def map_to_context!(context)
|
69
|
+
@import_steps.each do |import_step|
|
70
|
+
break if context.skip?
|
71
|
+
|
72
|
+
# set the to_element step for error reporting
|
73
|
+
context.import_step = import_step
|
74
|
+
elements = log_mapping_errors context, import_step do
|
75
|
+
import_step.execute context
|
76
|
+
end
|
77
|
+
add_elements_to_context!(elements, context) if import_step.to_element_step?
|
78
|
+
|
79
|
+
# Unset the import step after it's finished
|
80
|
+
context.import_step = nil
|
81
|
+
end
|
82
|
+
return context
|
83
|
+
end
|
84
|
+
|
85
|
+
# Add the accumulator to the context with the correct field name
|
86
|
+
# Do post-processing on the accumulator (remove nil values, allow empty
|
87
|
+
# fields, etc)
|
88
|
+
#
|
89
|
+
# Only get here if we've got a to_field step; otherwise the
|
90
|
+
# call to get a field_name will throw an error
|
91
|
+
|
92
|
+
ALLOW_NIL_VALUES = 'allow_nil_values'.freeze
|
93
|
+
ALLOW_EMPTY_FIELDS = 'allow_empty_fields'.freeze
|
94
|
+
ALLOW_DUPLICATE_VALUES = 'allow_duplicate_values'.freeze
|
95
|
+
|
96
|
+
def add_elements_to_context!(elements, context)
|
97
|
+
elements.compact! unless settings[ALLOW_NIL_VALUES]
|
98
|
+
return if elements.empty? and not (settings[ALLOW_EMPTY_FIELDS])
|
99
|
+
|
100
|
+
element_name = context.import_step.element_name
|
101
|
+
context.output_hash[element_name] ||= []
|
102
|
+
|
103
|
+
existing_element = context.output_hash[element_name].concat element
|
104
|
+
existing_element.uniq! unless settings[ALLOW_DUPLICATE_VALUES]
|
105
|
+
|
106
|
+
rescue NameError => ex
|
107
|
+
msg = 'Tried to call add_element_to_context with a non-to_element step'
|
108
|
+
msg += context.import_step.inspect
|
109
|
+
logger.error msg
|
110
|
+
raise ArgumentError.new msg
|
111
|
+
end
|
112
|
+
|
113
|
+
def process(files)
|
114
|
+
settings.fill_in_defaults!
|
115
|
+
|
116
|
+
count = 0
|
117
|
+
start_time = batch_start_time = Time.now
|
118
|
+
logger.debug "beginning Omelette::Import*process with settings: #{settings.inspect}"
|
119
|
+
reader = self.reader! files
|
120
|
+
processing_threads = settings['processing_thread_pool'].to_i
|
121
|
+
thread_pool = Omelette::ThreadPool.new processing_threads
|
122
|
+
|
123
|
+
logger.info " Indexer with #{processing_threads} processing threads, reader: #{reader.class.name} and writer: #{writer.class.name}"
|
124
|
+
log_batch_size = settings['log.batch_size'] && settings['log.batch_size'].to_i
|
125
|
+
|
126
|
+
reader.each do |item, item_id; position|
|
127
|
+
count += 1
|
128
|
+
position = count
|
129
|
+
|
130
|
+
thread_pool.raise_collected_exception!
|
131
|
+
|
132
|
+
if settings['debug_ascii_progress'].to_s == 'true'
|
133
|
+
$stderr.write '.' if count % settings['solr_writer.batch_size'].to_i == 0
|
134
|
+
end
|
135
|
+
|
136
|
+
context = Context.new source_item: item, source_item_id: item_id, settings: settings, position: position, logger: logger
|
137
|
+
|
138
|
+
if log_batch_size && (count % log_batch_size == 0)
|
139
|
+
batch_rps = log_batch_size / (Time.now - batch_start_time)
|
140
|
+
overall_rps = count / (Time.now - start_time)
|
141
|
+
logger.send(settings['log.batch_size.severity'].downcase.to_sym, "Omelette::Importer#process, read #{count} records at id:#{context.source_record_id}; #{'%.0f' % batch_rps}/s this batch, #{'%.0f' % overall_rps}/s overall")
|
142
|
+
batch_start_time = Time.now
|
143
|
+
end
|
144
|
+
|
145
|
+
thread_pool.maybe_in_thread_pool(context) do |context|
|
146
|
+
map_to_context! context
|
147
|
+
if context.skip?
|
148
|
+
log_skip context
|
149
|
+
else
|
150
|
+
writer.put context
|
151
|
+
end
|
152
|
+
end
|
153
|
+
end
|
154
|
+
|
155
|
+
$stderr.write "\n" if settings['debug_ascii_progress'].to_s == 'true'
|
156
|
+
|
157
|
+
logger.debug 'Shutting down #processing mapper threadpool...'
|
158
|
+
thread_pool.shutdown_and_wait
|
159
|
+
logger.debug '#processing mapper threadpool shutdown complete.'
|
160
|
+
|
161
|
+
thread_pool.raise_collected_exception!
|
162
|
+
|
163
|
+
|
164
|
+
writer.close if writer.respond_to?(:close)
|
165
|
+
|
166
|
+
@after_processing_steps.each do |step|
|
167
|
+
begin
|
168
|
+
step.execute
|
169
|
+
rescue Exception => e
|
170
|
+
logger.fatal("Unexpected exception #{e} when executing #{step}")
|
171
|
+
raise e
|
172
|
+
end
|
173
|
+
end
|
174
|
+
|
175
|
+
elapsed = Time.now - start_time
|
176
|
+
avg_rps = (count / elapsed)
|
177
|
+
logger.info "finished Indexer#process: #{count} records in #{'%.3f' % elapsed} seconds; #{'%.1f' % avg_rps} records/second overall."
|
178
|
+
|
179
|
+
if writer.respond_to?(:skipped_record_count) && writer.skipped_record_count > 0
|
180
|
+
logger.error "Indexer#process returning 'false' due to #{writer.skipped_record_count} skipped records."
|
181
|
+
return false
|
182
|
+
end
|
183
|
+
|
184
|
+
return true
|
185
|
+
end
|
186
|
+
|
187
|
+
def reader_class
|
188
|
+
unless defined? @reader_class
|
189
|
+
@reader_class = Object.const_get(settings['reader_class_name']) rescue nil
|
190
|
+
end
|
191
|
+
return @reader_class
|
192
|
+
end
|
193
|
+
|
194
|
+
def writer_class
|
195
|
+
writer.class
|
196
|
+
end
|
197
|
+
|
198
|
+
# Instantiate a Omelette Reader, using class set
|
199
|
+
# in #reader_class, initialized with io_stream passed in
|
200
|
+
def reader!(ids)
|
201
|
+
return reader_class.new(ids, settings.merge('logger' => logger))
|
202
|
+
end
|
203
|
+
|
204
|
+
# Instantiate a Writer, suing class set in #writer_class
|
205
|
+
def writer!
|
206
|
+
writer_class = @writer_class || Object.const_get(settings['writer_class_name']) rescue nil
|
207
|
+
writer_class.new(settings.merge('logger' => logger))
|
208
|
+
end
|
209
|
+
|
210
|
+
def writer
|
211
|
+
@writer ||= settings['writer'] || writer!
|
212
|
+
end
|
213
|
+
|
214
|
+
# Log that the current record is being skipped, using
|
215
|
+
# data in context.position and context.skipmessage
|
216
|
+
def log_skip(context)
|
217
|
+
logger.debug "Skipped record #{context.position}: #{context.skipmessage}"
|
218
|
+
end
|
219
|
+
private :log_skip
|
220
|
+
|
221
|
+
def log_mapping_errors(context, import_step)
|
222
|
+
begin
|
223
|
+
yield
|
224
|
+
rescue Exception => ex
|
225
|
+
msg = "Unexpected error on record id `#{context.source_item_id}` at file position #{context.position}\n"
|
226
|
+
msg += " while executing #{import_step.inspect}\n"
|
227
|
+
msg += Omelette::Util.exception_to_log_message(e)
|
228
|
+
|
229
|
+
logger.error msg
|
230
|
+
begin
|
231
|
+
logger.debug "Item: #{context.source_item.to_s}"
|
232
|
+
rescue Exception => item_exception
|
233
|
+
logger.debug "(Could not log item, #{item_exception})"
|
234
|
+
end
|
235
|
+
raise ex
|
236
|
+
end
|
237
|
+
end
|
238
|
+
private :log_mapping_errors
|
239
|
+
|
240
|
+
# Create logger according to settings
|
241
|
+
def create_logger
|
242
|
+
logger_level = settings['log.level'] || 'info'
|
243
|
+
|
244
|
+
# log everything to STDERR or specified logfile
|
245
|
+
logger = Yell::Logger.new(:null)
|
246
|
+
logger.format = logger_format
|
247
|
+
logger.level = logger_level
|
248
|
+
|
249
|
+
logger_destination = settings['log.file'] || 'STDERR'
|
250
|
+
# We intentionally repeat the logger_level
|
251
|
+
# on the adapter, so it will stay there if overall level
|
252
|
+
# is changed.
|
253
|
+
case logger_destination
|
254
|
+
when 'STDERR'
|
255
|
+
logger.adapter :stderr, level: logger_level, format: logger_format
|
256
|
+
when 'STDOUT'
|
257
|
+
logger.adapter :stdout, level: logger_level, format: logger_format
|
258
|
+
else
|
259
|
+
logger.adapter :file, logger_destination, level: logger_level, format: logger_format
|
260
|
+
end
|
261
|
+
|
262
|
+
|
263
|
+
# ADDITIONALLY log error and higher to....
|
264
|
+
if settings['log.error_file']
|
265
|
+
logger.adapter :file, settings['log.error_file'], :level => 'gte.error'
|
266
|
+
end
|
267
|
+
|
268
|
+
return logger
|
269
|
+
end
|
270
|
+
private :create_logger
|
271
|
+
|
272
|
+
def logger_format
|
273
|
+
format = settings['log.format'] || '%d %5L %m'
|
274
|
+
format = case format
|
275
|
+
when 'false' then
|
276
|
+
false
|
277
|
+
when '' then
|
278
|
+
nil
|
279
|
+
else
|
280
|
+
format
|
281
|
+
end
|
282
|
+
end
|
283
|
+
private :logger_format
|
284
|
+
end
|