imw 0.2.18 → 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
- data/Gemfile +7 -26
- data/Gemfile.lock +13 -38
- data/{LICENSE → LICENSE.txt} +1 -1
- data/README.textile +35 -0
- data/Rakefile +45 -22
- data/VERSION +1 -1
- data/examples/foo.rb +19 -0
- data/examples/html_selector.rb +22 -0
- data/examples/nes_game_list.csv +625 -0
- data/examples/nes_gamespot.csv +1371 -0
- data/examples/nes_nintendo.csv +624 -0
- data/examples/nes_unlicensed.csv +89 -0
- data/examples/nes_wikipedia.csv +710 -0
- data/examples/nibbler_test.rb +24 -0
- data/examples/script.rb +19 -0
- data/lib/imw.rb +28 -140
- data/lib/imw/error.rb +9 -0
- data/lib/imw/recordizer.rb +8 -0
- data/lib/imw/recordizer/html_selector_recordizer.rb +86 -0
- data/lib/imw/recordizer/string_slice_recordizer.rb +39 -0
- data/lib/imw/resource.rb +3 -119
- data/lib/imw/serializer.rb +7 -0
- data/lib/imw/serializer/json_serializer.rb +17 -0
- data/lib/imw/uri.rb +41 -0
- data/spec/resource_spec.rb +78 -0
- data/spec/uri_spec.rb +55 -0
- metadata +81 -232
- data/README.rdoc +0 -371
- data/bin/imw +0 -5
- data/bin/tsv_to_json.rb +0 -29
- data/etc/imwrc.rb +0 -26
- data/examples/dataset.rb +0 -12
- data/examples/metadata.yml +0 -10
- data/lib/imw/archives.rb +0 -120
- data/lib/imw/archives/rar.rb +0 -19
- data/lib/imw/archives/tar.rb +0 -19
- data/lib/imw/archives/tarbz2.rb +0 -73
- data/lib/imw/archives/targz.rb +0 -73
- data/lib/imw/archives/zip.rb +0 -51
- data/lib/imw/boot.rb +0 -87
- data/lib/imw/compressed_files.rb +0 -94
- data/lib/imw/compressed_files/bz2.rb +0 -16
- data/lib/imw/compressed_files/compressible.rb +0 -75
- data/lib/imw/compressed_files/gz.rb +0 -16
- data/lib/imw/dataset.rb +0 -125
- data/lib/imw/dataset/paths.rb +0 -29
- data/lib/imw/dataset/workflow.rb +0 -195
- data/lib/imw/formats.rb +0 -33
- data/lib/imw/formats/delimited.rb +0 -170
- data/lib/imw/formats/excel.rb +0 -100
- data/lib/imw/formats/json.rb +0 -41
- data/lib/imw/formats/pdf.rb +0 -71
- data/lib/imw/formats/sgml.rb +0 -69
- data/lib/imw/formats/yaml.rb +0 -41
- data/lib/imw/metadata.rb +0 -83
- data/lib/imw/metadata/contains_metadata.rb +0 -54
- data/lib/imw/metadata/dsl.rb +0 -111
- data/lib/imw/metadata/field.rb +0 -37
- data/lib/imw/metadata/has_metadata.rb +0 -98
- data/lib/imw/metadata/has_summary.rb +0 -57
- data/lib/imw/metadata/schema.rb +0 -17
- data/lib/imw/parsers.rb +0 -8
- data/lib/imw/parsers/flat.rb +0 -44
- data/lib/imw/parsers/html_parser.rb +0 -387
- data/lib/imw/parsers/html_parser/matchers.rb +0 -289
- data/lib/imw/parsers/line_parser.rb +0 -87
- data/lib/imw/parsers/regexp_parser.rb +0 -72
- data/lib/imw/repository.rb +0 -12
- data/lib/imw/runner.rb +0 -118
- data/lib/imw/schemes.rb +0 -23
- data/lib/imw/schemes/ftp.rb +0 -142
- data/lib/imw/schemes/hdfs.rb +0 -251
- data/lib/imw/schemes/http.rb +0 -165
- data/lib/imw/schemes/local.rb +0 -409
- data/lib/imw/schemes/remote.rb +0 -119
- data/lib/imw/schemes/s3.rb +0 -143
- data/lib/imw/schemes/sql.rb +0 -129
- data/lib/imw/tools.rb +0 -12
- data/lib/imw/tools/aggregator.rb +0 -148
- data/lib/imw/tools/archiver.rb +0 -220
- data/lib/imw/tools/downloader.rb +0 -63
- data/lib/imw/tools/extension_analyzer.rb +0 -114
- data/lib/imw/tools/summarizer.rb +0 -83
- data/lib/imw/tools/transferer.rb +0 -167
- data/lib/imw/utils.rb +0 -74
- data/lib/imw/utils/dynamically_extendable.rb +0 -137
- data/lib/imw/utils/error.rb +0 -59
- data/lib/imw/utils/extensions/hpricot.rb +0 -34
- data/lib/imw/utils/has_uri.rb +0 -131
- data/lib/imw/utils/log.rb +0 -92
- data/lib/imw/utils/misc.rb +0 -57
- data/lib/imw/utils/paths.rb +0 -146
- data/lib/imw/utils/uri.rb +0 -59
- data/lib/imw/utils/uuid.rb +0 -33
- data/lib/imw/utils/validate.rb +0 -38
- data/lib/imw/utils/version.rb +0 -11
- data/spec/data/formats/delimited/sample.csv +0 -131
- data/spec/data/formats/delimited/sample.tsv +0 -131
- data/spec/data/formats/delimited/with_schema/ace-hardware-locations.tsv +0 -11
- data/spec/data/formats/delimited/with_schema/all-countries-ip-address-to-geolocation-data.tsv +0 -16
- data/spec/data/formats/delimited/with_schema/complete-list-of-starbucks-locations.tsv +0 -11
- data/spec/data/formats/delimited/with_schema/myspace-user-activity-stream-cumulative-word-count-from-from-dec.tsv +0 -22
- data/spec/data/formats/delimited/with_schema/myspace-user-activity-stream-myspace-application-adds-by-zip-cod.tsv +0 -22
- data/spec/data/formats/delimited/with_schema/myspace-user-activity-stream-myspace-application-counts.tsv +0 -12
- data/spec/data/formats/delimited/with_schema/myspace-user-activity-stream-user-count-by-latlong.tsv +0 -13
- data/spec/data/formats/delimited/with_schema/myspace-user-activity-stream-user-count-by-zip-code.tsv +0 -22
- data/spec/data/formats/delimited/with_schema/myspace-user-activity-stream-word-count-by-day-from-december-200.tsv +0 -22
- data/spec/data/formats/delimited/without_schema/ace-hardware-locations.tsv +0 -10
- data/spec/data/formats/delimited/without_schema/all-countries-ip-address-to-geolocation-data.tsv +0 -15
- data/spec/data/formats/delimited/without_schema/complete-list-of-starbucks-locations.tsv +0 -10
- data/spec/data/formats/delimited/without_schema/myspace-user-activity-stream-cumulative-word-count-from-from-dec.tsv +0 -21
- data/spec/data/formats/delimited/without_schema/myspace-user-activity-stream-myspace-application-adds-by-zip-cod.tsv +0 -21
- data/spec/data/formats/delimited/without_schema/myspace-user-activity-stream-myspace-application-counts.tsv +0 -11
- data/spec/data/formats/delimited/without_schema/myspace-user-activity-stream-user-count-by-latlong.tsv +0 -12
- data/spec/data/formats/delimited/without_schema/myspace-user-activity-stream-user-count-by-zip-code.tsv +0 -21
- data/spec/data/formats/delimited/without_schema/myspace-user-activity-stream-word-count-by-day-from-december-200.tsv +0 -21
- data/spec/data/formats/excel/sample.xls +0 -0
- data/spec/data/formats/json/sample.json +0 -1
- data/spec/data/formats/none/sample +0 -650
- data/spec/data/formats/sgml/sample.xml +0 -617
- data/spec/data/formats/text/sample.txt +0 -650
- data/spec/data/formats/yaml/sample.yaml +0 -410
- data/spec/data/schema-tabular.yaml +0 -11
- data/spec/imw/archives/rar_spec.rb +0 -16
- data/spec/imw/archives/tar_spec.rb +0 -16
- data/spec/imw/archives/tarbz2_spec.rb +0 -24
- data/spec/imw/archives/targz_spec.rb +0 -21
- data/spec/imw/archives/zip_spec.rb +0 -16
- data/spec/imw/archives_spec.rb +0 -77
- data/spec/imw/compressed_files/bz2_spec.rb +0 -15
- data/spec/imw/compressed_files/compressible_spec.rb +0 -36
- data/spec/imw/compressed_files/gz_spec.rb +0 -15
- data/spec/imw/compressed_files_spec.rb +0 -47
- data/spec/imw/dataset/paths_spec.rb +0 -32
- data/spec/imw/dataset/workflow_spec.rb +0 -41
- data/spec/imw/formats/delimited_spec.rb +0 -44
- data/spec/imw/formats/excel_spec.rb +0 -55
- data/spec/imw/formats/json_spec.rb +0 -18
- data/spec/imw/formats/sgml_spec.rb +0 -24
- data/spec/imw/formats/yaml_spec.rb +0 -19
- data/spec/imw/metadata/contains_metadata_spec.rb +0 -56
- data/spec/imw/metadata/field_spec.rb +0 -25
- data/spec/imw/metadata/has_metadata_spec.rb +0 -58
- data/spec/imw/metadata/has_summary_spec.rb +0 -32
- data/spec/imw/metadata/schema_spec.rb +0 -24
- data/spec/imw/metadata_spec.rb +0 -86
- data/spec/imw/parsers/line_parser_spec.rb +0 -96
- data/spec/imw/parsers/regexp_parser_spec.rb +0 -42
- data/spec/imw/resource_spec.rb +0 -32
- data/spec/imw/schemes/hdfs_spec.rb +0 -67
- data/spec/imw/schemes/http_spec.rb +0 -19
- data/spec/imw/schemes/local_spec.rb +0 -165
- data/spec/imw/schemes/remote_spec.rb +0 -38
- data/spec/imw/schemes/s3_spec.rb +0 -31
- data/spec/imw/schemes/sql_spec.rb +0 -3
- data/spec/imw/tools/aggregator_spec.rb +0 -71
- data/spec/imw/tools/archiver_spec.rb +0 -120
- data/spec/imw/tools/extension_analyzer_spec.rb +0 -153
- data/spec/imw/tools/summarizer_spec.rb +0 -8
- data/spec/imw/tools/transferer_spec.rb +0 -195
- data/spec/imw/utils/dynamically_extendable_spec.rb +0 -69
- data/spec/imw/utils/has_uri_spec.rb +0 -61
- data/spec/imw/utils/paths_spec.rb +0 -10
- data/spec/imw/utils/shared_paths_spec.rb +0 -29
- data/spec/imw_spec.rb +0 -14
- data/spec/rcov.opts +0 -1
- data/spec/spec_helper.rb +0 -31
- data/spec/support/custom_matchers.rb +0 -28
- data/spec/support/file_contents_matcher.rb +0 -30
- data/spec/support/paths_matcher.rb +0 -66
- data/spec/support/random.rb +0 -213
- data/spec/support/without_regard_to_order_matcher.rb +0 -41
data/lib/imw/tools/archiver.rb
DELETED
@@ -1,220 +0,0 @@
|
|
1
|
-
require 'imw/resource'
|
2
|
-
|
3
|
-
module IMW
|
4
|
-
module Tools
|
5
|
-
|
6
|
-
# Packages an Array of input files into a single output archive.
|
7
|
-
# When the archive is extracted, all the input files given will be
|
8
|
-
# in a single directory with a chosen name. The path to the output
|
9
|
-
# archive determines both the name of the archive and its type (tar,
|
10
|
-
# tar.bz2, zip, &c.).
|
11
|
-
#
|
12
|
-
# If any of the input files are themselves archives, they will first
|
13
|
-
# be extracted, with only their contents winding up in the final
|
14
|
-
# directory (the file hierarchy of the archive will be preserved).
|
15
|
-
# If any of the input files are compressed, they will first be
|
16
|
-
# uncompressed before being added to the directory.
|
17
|
-
#
|
18
|
-
# Both local and remote files can be archived. An exmaple:
|
19
|
-
#
|
20
|
-
# archiver = IMW::Transforms::Archiver.new 'my_archive', '/path/to/my/regular_file.tsv', '/path/to/an/archive.tar.bz2', '/path/to/my_compressed_file.gz', 'http://mywebsite.com/index.html'
|
21
|
-
# archiver.package! '/path/to/my_archive.zip'
|
22
|
-
#
|
23
|
-
# This will create a ZIP archive at
|
24
|
-
# <tt>/path/to/my_archive.zip</tt>. When the ZIP archive is
|
25
|
-
# extracted its contents will look like
|
26
|
-
#
|
27
|
-
# my_archive
|
28
|
-
# |-- regular_file.tsv
|
29
|
-
# |-- archive_file1
|
30
|
-
# |-- archive_dir
|
31
|
-
# | |-- archive_file2
|
32
|
-
# | `-- archive_file3
|
33
|
-
# |-- archive_file3
|
34
|
-
# |-- my_compressed_file
|
35
|
-
# `-- index.html
|
36
|
-
#
|
37
|
-
# Notice that
|
38
|
-
#
|
39
|
-
# - the name of the extracted directory is given by the first
|
40
|
-
# argument to the Archiver when it was instantiated.
|
41
|
-
#
|
42
|
-
# - all files wind up in the top-level of this extracted directory
|
43
|
-
# when possible (<tt>regular_file.tsv</tt>, <tt>index.html</tt>)
|
44
|
-
#
|
45
|
-
# - /path/to/archive.tar.bz2 was not directly included, but its
|
46
|
-
# contents (<tt>archive_file1</tt>,
|
47
|
-
# <tt>archive_dir/archive_file2</tt>,
|
48
|
-
# <tt>archive_dir/archive_file3</tt>) were included instead.
|
49
|
-
#
|
50
|
-
# - /path/to/my_compressed_file.gz was first uncompressed before
|
51
|
-
# being added to the archive.
|
52
|
-
#
|
53
|
-
# - the remote file <tt>http://mywebsite.com/index.html</tt> was
|
54
|
-
# downloaded and included
|
55
|
-
#
|
56
|
-
# This process can take a while when the constituent files are
|
57
|
-
# large because there is quite a lot of preparation done to the
|
58
|
-
# files to make this nice output structure in the final archive.
|
59
|
-
# Further calls to <tt>package!</tt> on the same instance of
|
60
|
-
# Archiver will skip the preparation step (the intermediate
|
61
|
-
# results of which are sitting in IMW's temporary directory) and
|
62
|
-
# directly create the package, saving time when attempting to
|
63
|
-
# create multiple package formats from the same input data.
|
64
|
-
class Archiver
|
65
|
-
|
66
|
-
attr_accessor :name, :local_inputs, :remote_inputs
|
67
|
-
|
68
|
-
def initialize name, *raw_inputs
|
69
|
-
@name = name
|
70
|
-
self.inputs = raw_inputs
|
71
|
-
end
|
72
|
-
|
73
|
-
# Set the inputs for this archiver.
|
74
|
-
#
|
75
|
-
# @param [String, IMW::Resource] new_inputs the inputs to archive, local or remote
|
76
|
-
def inputs= raw_inputs
|
77
|
-
@local_inputs, @remote_inputs = [], []
|
78
|
-
raw_inputs.flatten.each do |raw_input|
|
79
|
-
input = IMW.open(raw_input)
|
80
|
-
if input.is_local?
|
81
|
-
@local_inputs << input
|
82
|
-
else
|
83
|
-
@remote_inputs << input
|
84
|
-
end
|
85
|
-
end
|
86
|
-
@local_inputs.flatten!
|
87
|
-
end
|
88
|
-
|
89
|
-
# Return a list of error messages for this archiver.
|
90
|
-
#
|
91
|
-
# @return [Array] the error messages
|
92
|
-
def errors
|
93
|
-
@errors ||= []
|
94
|
-
end
|
95
|
-
|
96
|
-
# Was this archiver successful (did it not have any errors)?
|
97
|
-
#
|
98
|
-
# @return [true, false]
|
99
|
-
def success?
|
100
|
-
errors.empty?
|
101
|
-
end
|
102
|
-
|
103
|
-
# A temporary directory to work in. Its contents will
|
104
|
-
# ultimately consist of a directory named for the package
|
105
|
-
# containing all the input files.
|
106
|
-
#
|
107
|
-
# @return [String]
|
108
|
-
def tmp_dir
|
109
|
-
@tmp_dir ||= File.join(IMW.path_to(:tmp_root, 'packager'), (Time.now.to_i.to_s + "-" + $$.to_s)) # guaranteed unique on a node
|
110
|
-
end
|
111
|
-
|
112
|
-
# A directory which will contain all the content being packaged,
|
113
|
-
# including the contents of any archives that were included in
|
114
|
-
# the list of files to process.
|
115
|
-
#
|
116
|
-
# @return [String]
|
117
|
-
def dir
|
118
|
-
@dir ||= File.join(tmp_dir, name.to_s)
|
119
|
-
end
|
120
|
-
|
121
|
-
# Remove the +tmp_dir+ entirely, getting rid of all temporary
|
122
|
-
# files.
|
123
|
-
def clean!
|
124
|
-
IMW.announce_if_verbose("Cleaning temporary directory #{tmp_dir}...")
|
125
|
-
FileUtils.rm_rf(tmp_dir)
|
126
|
-
end
|
127
|
-
|
128
|
-
# Copy, decompress, or extract the input paths to the temporary
|
129
|
-
# directory, readying them for packaging.
|
130
|
-
def prepare!
|
131
|
-
FileUtils.mkdir_p dir unless File.exist?(dir)
|
132
|
-
|
133
|
-
local_inputs.each do |existing_file|
|
134
|
-
new_path = File.join(dir, existing_file.basename)
|
135
|
-
case
|
136
|
-
when existing_file.is_archive?
|
137
|
-
IMW.announce_if_verbose("Extracting #{existing_file}...")
|
138
|
-
FileUtils.cd(dir) do
|
139
|
-
existing_file.extract
|
140
|
-
end
|
141
|
-
when existing_file.is_compressed?
|
142
|
-
IMW.announce_if_verbose("Decompressing #{existing_file}...")
|
143
|
-
existing_file.cp(new_path).decompress!
|
144
|
-
else
|
145
|
-
IMW.announce_if_verbose("Copying #{existing_file}...")
|
146
|
-
existing_file.cp(new_path)
|
147
|
-
end
|
148
|
-
end
|
149
|
-
|
150
|
-
remote_inputs.each do |remote_input|
|
151
|
-
IMW.announce_if_verbose("Downloading #{remote_input}...")
|
152
|
-
remote_input.cp(File.join(dir, remote_input.effective_basename))
|
153
|
-
end
|
154
|
-
end
|
155
|
-
|
156
|
-
# Checks to see if all expected files exist in the temporary
|
157
|
-
# directory for this packager.
|
158
|
-
#
|
159
|
-
# @return [true, false]
|
160
|
-
def prepared?
|
161
|
-
local_inputs.each do |existing_file|
|
162
|
-
case
|
163
|
-
when existing_file.is_archive?
|
164
|
-
existing_file.contents.each do |archived_file_path|
|
165
|
-
return false unless File.exist?(File.join(dir, archived_file_path))
|
166
|
-
end
|
167
|
-
when existing_file.is_compressed?
|
168
|
-
return false unless File.exist?(File.join(dir, existing_file.decompressed_basename))
|
169
|
-
else
|
170
|
-
return false unless File.exist?(File.join(dir, existing_file.basename))
|
171
|
-
end
|
172
|
-
end
|
173
|
-
|
174
|
-
remote_inputs.each do |remote_input|
|
175
|
-
return false unless File.exist?(File.join(dir, remote_input.effective_basename))
|
176
|
-
end
|
177
|
-
|
178
|
-
true
|
179
|
-
end
|
180
|
-
|
181
|
-
# Package the contents of the temporary directory to an archive
|
182
|
-
# at +output+ but return exceptions instead of raising them.
|
183
|
-
#
|
184
|
-
# @param [String, IMW::Resource] output the path to the output package
|
185
|
-
# @param [Hash] options
|
186
|
-
# @return [StandardError, IMW::Resource] either the completed package or the error which was raised
|
187
|
-
def package output, options={}
|
188
|
-
begin
|
189
|
-
package! output, options={}
|
190
|
-
rescue StandardError => e
|
191
|
-
return e
|
192
|
-
end
|
193
|
-
end
|
194
|
-
|
195
|
-
# Package the contents of the temporary directory to an archive
|
196
|
-
# at +output+. The extension of +output+ determines the kind of
|
197
|
-
# archive.
|
198
|
-
#
|
199
|
-
# @param [String, IMW::Resource] output the path to the output package
|
200
|
-
# @param [Hash] options
|
201
|
-
# @return [IMW::Resource] the completed package
|
202
|
-
def package! output, options={}
|
203
|
-
prepare! unless prepared?
|
204
|
-
output = IMW.open(output)
|
205
|
-
FileUtils.mkdir_p(output.dirname) unless File.exist?(output.dirname)
|
206
|
-
output.rm! if output.exist?
|
207
|
-
FileUtils.cd(tmp_dir) { IMW.open(output.basename).create(name).mv(output.path) }
|
208
|
-
add_processing_error "Archiver: couldn't create archive #{output.path}" unless output.exists?
|
209
|
-
output
|
210
|
-
end
|
211
|
-
|
212
|
-
protected
|
213
|
-
def add_processing_error error # :nodoc:
|
214
|
-
IMW.logger.warn error
|
215
|
-
errors << error
|
216
|
-
end
|
217
|
-
|
218
|
-
end
|
219
|
-
end
|
220
|
-
end
|
data/lib/imw/tools/downloader.rb
DELETED
@@ -1,63 +0,0 @@
|
|
1
|
-
module IMW
|
2
|
-
module Tools
|
3
|
-
|
4
|
-
# A class to download a collection of resources to a shared
|
5
|
-
# directory.
|
6
|
-
class Downloader
|
7
|
-
|
8
|
-
def initialize dir, *inputs
|
9
|
-
self.dir = dir
|
10
|
-
self.inputs = inputs unless inputs.blank?
|
11
|
-
end
|
12
|
-
|
13
|
-
def self.dir= new_dir
|
14
|
-
@dir = IMW.open(new_dir)
|
15
|
-
raise IMW::PathError.new("#{@dir} must be a local directory") unless @dir.is_local? && @dir.is_directory?
|
16
|
-
@dir
|
17
|
-
end
|
18
|
-
attr_reader :dir
|
19
|
-
|
20
|
-
def inputs= new_inputs
|
21
|
-
@inputs = new_inputs.flatten.compact.map { |raw_input| IMW.open(raw_input) }
|
22
|
-
end
|
23
|
-
attr_reader :inputs
|
24
|
-
|
25
|
-
def downloaded_path_for input
|
26
|
-
dir.join(input.respond_to?(:effective_basename) ? input.effective_basename : input.basename)
|
27
|
-
end
|
28
|
-
|
29
|
-
def download!
|
30
|
-
before_download
|
31
|
-
inputs.each do |input|
|
32
|
-
downloaded_path = downloaded_path_for(input)
|
33
|
-
IMW.log_if_verbose "Downloading #{input} to #{downloaded_path}"
|
34
|
-
input.cp(downloaded_path)
|
35
|
-
end
|
36
|
-
after_download
|
37
|
-
end
|
38
|
-
|
39
|
-
def downloaded?
|
40
|
-
downloaded_resources.all? { |resource| resource.exist? }
|
41
|
-
end
|
42
|
-
|
43
|
-
def downloaded_resources
|
44
|
-
inputs.map do |input|
|
45
|
-
IMW.open(downloaded_path_for(input))
|
46
|
-
end
|
47
|
-
end
|
48
|
-
|
49
|
-
def clean!
|
50
|
-
IMW.log_if_verbose("Deleting downloader directory #{dir}")
|
51
|
-
dir.rm_rf!
|
52
|
-
end
|
53
|
-
|
54
|
-
def before_download
|
55
|
-
end
|
56
|
-
|
57
|
-
def after_download
|
58
|
-
end
|
59
|
-
|
60
|
-
end
|
61
|
-
end
|
62
|
-
end
|
63
|
-
|
@@ -1,114 +0,0 @@
|
|
1
|
-
module IMW
|
2
|
-
module Tools
|
3
|
-
|
4
|
-
# Mixin with some heuristic methods for identifying common
|
5
|
-
# extensions and likely data formats for a collection of files.
|
6
|
-
#
|
7
|
-
# Requires the including class to define a method +resources+
|
8
|
-
# which returns an array of IMW::Resource objects as well as a
|
9
|
-
# method +total_size+ which gives the total size of the resources
|
10
|
-
# (for weighting extensions by size).
|
11
|
-
module ExtensionAnalyzer
|
12
|
-
|
13
|
-
# Return the file counts of each extension.
|
14
|
-
#
|
15
|
-
# @return [Hash]
|
16
|
-
def extension_counts
|
17
|
-
@extension_counts ||= {}.tap do |counts|
|
18
|
-
resources.each do |resource|
|
19
|
-
next if resource.is_directory?
|
20
|
-
counts[resource.extension] = 0 unless counts.has_key?(resource.extension)
|
21
|
-
counts[resource.extension] += 1
|
22
|
-
end
|
23
|
-
end
|
24
|
-
end
|
25
|
-
|
26
|
-
# Return the most common extension by count of files.
|
27
|
-
def most_common_extension_by_count
|
28
|
-
return @most_common_extension_by_count if @most_common_extension_by_count
|
29
|
-
current_count, current_extension = 0, ''
|
30
|
-
extension_counts.each_pair do |extension, count|
|
31
|
-
current_extension = extension if count > current_count
|
32
|
-
end
|
33
|
-
if current_extension.strip.blank? then current_extension = 'flat' end
|
34
|
-
@most_common_extension_by_count = current_extension
|
35
|
-
end
|
36
|
-
|
37
|
-
# Return the file counts of each extension, normalized by the
|
38
|
-
# total number of files.
|
39
|
-
#
|
40
|
-
# @return [Hash]
|
41
|
-
def normalized_extension_counts
|
42
|
-
@normalized_extension_counts ||= {}.tap do |weighted|
|
43
|
-
num_files = resources.reject(&:is_directory?).length.to_f
|
44
|
-
extension_counts.each_pair do |extension, count|
|
45
|
-
weighted[extension] = count.to_f / num_files
|
46
|
-
end
|
47
|
-
end
|
48
|
-
end
|
49
|
-
|
50
|
-
# Return the amount of data corresponding to each extension.
|
51
|
-
#
|
52
|
-
# @return [Hash]
|
53
|
-
def extension_sizes
|
54
|
-
@extension_sizes ||= {}.tap do |sizes|
|
55
|
-
resources.each do |resource|
|
56
|
-
next if resource.is_directory?
|
57
|
-
sizes[resource.extension] = 0 unless sizes.has_key?(resource.extension)
|
58
|
-
sizes[resource.extension] += resource.size
|
59
|
-
end
|
60
|
-
end
|
61
|
-
end
|
62
|
-
|
63
|
-
# Return the most common extension by amount of data.
|
64
|
-
#
|
65
|
-
# @return [String]
|
66
|
-
def most_common_extension_by_size
|
67
|
-
return @most_common_extension_by_size if @most_common_extension_by_size
|
68
|
-
current_size, current_extension = 0, ''
|
69
|
-
extension_sizes.each_pair do |extension, size|
|
70
|
-
if size > current_size
|
71
|
-
current_extension = extension
|
72
|
-
current_size = size
|
73
|
-
end
|
74
|
-
end
|
75
|
-
current_extension = 'flat' if current_extension.strip.blank?
|
76
|
-
@most_common_extension_by_size = current_extension
|
77
|
-
end
|
78
|
-
|
79
|
-
# Return the fractional share of each extension by file size.
|
80
|
-
#
|
81
|
-
# @return [Hash]
|
82
|
-
def normalized_extension_sizes
|
83
|
-
@normalized_extension_sizes ||= {}.tap do |weighted|
|
84
|
-
extension_sizes.each_pair do |extension, size|
|
85
|
-
weighted[extension] = size.to_f / total_size.to_f
|
86
|
-
end
|
87
|
-
end
|
88
|
-
end
|
89
|
-
|
90
|
-
# Return a guess as to the most common extension format for this
|
91
|
-
# Summarizer's resources.
|
92
|
-
#
|
93
|
-
# @return [String]
|
94
|
-
def most_common_extension
|
95
|
-
return most_common_extension_by_size if most_common_extension_by_size == most_common_extension_by_count # no contest
|
96
|
-
count_fraction = (normalized_extension_counts[most_common_extension_by_count] or 0.0)
|
97
|
-
size_fraction = (normalized_extension_sizes[most_common_extension_by_size] or 0.0)
|
98
|
-
return most_common_extension_by_count if count_fraction >= 0.5 and size_fraction < 0.5 # FIXME arbitrary
|
99
|
-
return most_common_extension_by_size if count_fraction < 0.5 and size_fraction >= 0.5
|
100
|
-
most_common_extension_by_size # default to size
|
101
|
-
end
|
102
|
-
|
103
|
-
# Returns a guess as to the most common data format for this
|
104
|
-
# Summarizer's resources.
|
105
|
-
#
|
106
|
-
# @return [String]
|
107
|
-
def most_common_data_format
|
108
|
-
extension = most_common_extension
|
109
|
-
['tar', 'tar.bz2', 'tar.gz', 'tgz', 'tbz2', 'zip', 'rar'].include?(extension) ? 'archive' : extension
|
110
|
-
end
|
111
|
-
end
|
112
|
-
end
|
113
|
-
end
|
114
|
-
|
data/lib/imw/tools/summarizer.rb
DELETED
@@ -1,83 +0,0 @@
|
|
1
|
-
require 'imw/tools/extension_analyzer'
|
2
|
-
|
3
|
-
module IMW
|
4
|
-
module Tools
|
5
|
-
|
6
|
-
# A class for producing summary data about a collection of
|
7
|
-
# resources.
|
8
|
-
#
|
9
|
-
# The Summarizer needs recursively IMW.open all files and
|
10
|
-
# directories given so will be very cumbersome if given many
|
11
|
-
# files. Few large files will not cause a problem.
|
12
|
-
class Summarizer
|
13
|
-
|
14
|
-
# Options for this Summarizer.
|
15
|
-
attr_accessor :options
|
16
|
-
|
17
|
-
# The inputs given to this Summarizer.
|
18
|
-
attr_reader :inputs
|
19
|
-
|
20
|
-
# The resources analyzed, calculated recursively from the
|
21
|
-
# +inputs+.
|
22
|
-
attr_reader :resources
|
23
|
-
|
24
|
-
include IMW::Tools::ExtensionAnalyzer
|
25
|
-
|
26
|
-
# Initialize a new Summarizer with the given +inputs+.
|
27
|
-
#
|
28
|
-
# A Hash of options can be given as the last parameter.
|
29
|
-
#
|
30
|
-
# @param [Array<String, IMW::Resource>] inputs
|
31
|
-
# @return [IMW::Tools::Summarizer]
|
32
|
-
def initialize *inputs
|
33
|
-
self.options = (inputs.last.is_a?(Hash) && inputs.pop) || {}
|
34
|
-
self.inputs = inputs.flatten
|
35
|
-
end
|
36
|
-
|
37
|
-
# Return the total size of all resources.
|
38
|
-
#
|
39
|
-
# @return [Integer]
|
40
|
-
def total_size
|
41
|
-
@total_size ||= resources.map(&:size).inject(0) { |e, sum| sum += e }
|
42
|
-
end
|
43
|
-
|
44
|
-
# Return a summary of the +inputs+ to this Summarizer.
|
45
|
-
#
|
46
|
-
# Will swallow errors.
|
47
|
-
#
|
48
|
-
# @return [Array<Hash>]
|
49
|
-
def summary
|
50
|
-
@summary ||= summary! rescue []
|
51
|
-
end
|
52
|
-
|
53
|
-
# Return a summary of the +inputs+ to this summarizer.
|
54
|
-
#
|
55
|
-
# Delegates to the +summary+ method of each constituent
|
56
|
-
# IMW::Resource in +inputs+.
|
57
|
-
#
|
58
|
-
# @return [Array]
|
59
|
-
def summary!
|
60
|
-
inputs.map do |input|
|
61
|
-
(input.respond_to?(:summary) ? input.summary : {})
|
62
|
-
end
|
63
|
-
end
|
64
|
-
|
65
|
-
protected
|
66
|
-
# Set new inputs for this summarizer.
|
67
|
-
#
|
68
|
-
# Summarizer statistics are cached as instance variables so be
|
69
|
-
# careful about changing inputs and then using old statistics...
|
70
|
-
#
|
71
|
-
# @param [Array<String, IMW::Resource>] new_inputs
|
72
|
-
def inputs= new_inputs
|
73
|
-
@inputs = new_inputs.map do |path_or_resource|
|
74
|
-
input = IMW.open(path_or_resource)
|
75
|
-
end
|
76
|
-
@resources = inputs.map do |input|
|
77
|
-
input.is_local? && input.is_directory? ? input.all_resources : input
|
78
|
-
end.compact.flatten
|
79
|
-
end
|
80
|
-
|
81
|
-
end
|
82
|
-
end
|
83
|
-
end
|