Class: Gembuild::GemScraper

Inherits:
Object
  • Object
show all
Defined in:
lib/gembuild/gem_scraper.rb

Overview

This class is used to query for various information from rubygems.org.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(gemname) ⇒ Gembuild::GemScraper

Creates a new GemScraper instance

Examples:

Create a new GemScraper object

Gembuild::GemScraper.new('mina')
# => #<Gembuild::GemScraper:0x00000002f8a500
#  @agent=
#   #<Mechanize
#    #<Mechanize::CookieJar:0x00000002f8a410
#     @store=
#      #<HTTP::CookieJar::HashStore:0x00000002f8a370
#       @gc_index=0,
#       @gc_threshold=150,
#       @jar={},
#       @logger=nil,
#       @mon_count=0,
#       @mon_mutex=#<Mutex:0x00000002f8a320>,
#       @mon_owner=nil>>
#    nil>,
#  @deps="https://rubygems.org/api/v1/dependencies?gems=mina",
#  @gem="https://rubygems.org/gems/mina",
#  @gemname="mina",
#  @url="https://rubygems.org/api/v1/versions/mina.json">

Parameters:

  • gemname (String) —

    The gem about which to query.

Raises:

  • (Gembuild::UndefinedGemName) —

    if the gemname is nil or empty



65
66
67
68
69
70
71
72
73
74
 
# File 'lib/gembuild/gem_scraper.rb', line 65

def initialize(gemname)
  fail Gembuild::UndefinedGemNameError if gemname.nil? || gemname.empty?

  @gemname = gemname
  @agent = Mechanize.new

  @url = "https://rubygems.org/api/v1/versions/#{gemname}.json"
  @deps = "https://rubygems.org/api/v1/dependencies?gems=#{gemname}"
  @gem = "https://rubygems.org/gems/#{gemname}"
end

Instance Attribute Details

#agent ⇒ Mechanize (readonly)

Returns the Mechanize agent.

Returns:

  • (Mechanize) —

    the Mechanize agent



35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
 
# File 'lib/gembuild/gem_scraper.rb', line 35

class GemScraper
  attr_reader :agent, :deps, :gem, :gemname, :url

  # Creates a new GemScraper instance
  #
  # @raise [Gembuild::UndefinedGemName] if the gemname is nil or empty
  #
  # @example Create a new GemScraper object
  #   Gembuild::GemScraper.new('mina')
  #   # => #<Gembuild::GemScraper:0x00000002f8a500
  #   #  @agent=
  #   #   #<Mechanize
  #   #    #<Mechanize::CookieJar:0x00000002f8a410
  #   #     @store=
  #   #      #<HTTP::CookieJar::HashStore:0x00000002f8a370
  #   #       @gc_index=0,
  #   #       @gc_threshold=150,
  #   #       @jar={},
  #   #       @logger=nil,
  #   #       @mon_count=0,
  #   #       @mon_mutex=#<Mutex:0x00000002f8a320>,
  #   #       @mon_owner=nil>>
  #   #    nil>,
  #   #  @deps="https://rubygems.org/api/v1/dependencies?gems=mina",
  #   #  @gem="https://rubygems.org/gems/mina",
  #   #  @gemname="mina",
  #   #  @url="https://rubygems.org/api/v1/versions/mina.json">
  #
  # @param gemname [String] The gem about which to query.
  # @return [Gembuild::GemScraper] a new GemScraper instance
  def initialize(gemname)
    fail Gembuild::UndefinedGemNameError if gemname.nil? || gemname.empty?

    @gemname = gemname
    @agent = Mechanize.new

    @url = "https://rubygems.org/api/v1/versions/#{gemname}.json"
    @deps = "https://rubygems.org/api/v1/dependencies?gems=#{gemname}"
    @gem = "https://rubygems.org/gems/#{gemname}"
  end

  # Query the rubygems version api for the latest version.
  #
  # @raise [Gembuild::GemNotFoundError] if the page returns a 404 (not
  #   found) error.
  #
  # @example Query rubygems.org for version information
  #   s = Gembuild::GemScraper.new('mina')
  #   s.query_latest_version
  #   # => {:authors=>"Rico Sta. Cruz, Michael Galero",
  #   #  :built_at=>"2015-07-08T00:00:00.000Z",
  #   #  :created_at=>"2015-07-08T13:13:33.292Z",
  #   #  :description=>"Really fast deployer and server automation tool.",
  #   #  :downloads_count=>18709,
  #   #  :metadata=>{},
  #   #  :number=>"0.3.7",
  #   #  :summary=>"Really fast deployer and server automation tool.",
  #   #  :platform=>"ruby",
  #   #  :ruby_version=>">= 0",
  #   #  :prerelease=>false,
  #   #  :licenses=>[],
  #   #  :requirements=>[],
  #   #  :sha=>
  #   #   "bd1fa2b56ed1aded882a12f6365a04496f5cf8a14c07f8c4f1f3cfc944ef34f6"
  #   # }
  #
  # @return [Hash] the information about the latest version of the gem
  def query_latest_version
    response = JSON.parse(agent.get(url).body, symbolize_names: true)

    # Skip any release marked as a "prerelease"
    response.shift while response.first[:prerelease]

    response.first
  rescue Mechanize::ResponseCodeError, Net::HTTPNotFound
    raise Gembuild::GemNotFoundError
  end

  # Gets the version number from the parsed response.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [Gem::Version] the current version of the gem
  def get_version_from_response(response)
    Gem::Version.new(response.fetch(:number))
  end

  # Gets a well-formed gem description from the parsed response.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [String] the gem description or summary ending in a full-stop
  def format_description_from_response(response)
    description = response.fetch(:description)
    description = response.fetch(:summary) if description.empty?

    # Replace any newlines or tabs (which would mess up a PKGBUILD) with
    # spaces. Then, make sure there is no
    description = description.gsub(/[[:space:]]+/, ' ').strip

    # Ensure that the description ends in a full-stop.
    description += '.' unless description[-1, 1] == '.'

    description
  end

  # Gets the sha256 checksum returned from the rubygems.org API.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [String] the sha256 sum of the gem file
  def get_checksum_from_response(response)
    response.fetch(:sha)
  end

  # Get the array of licenses under which the gem is licensed.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [Array] the licenses for the gem
  def get_licenses_from_response(response)
    response.fetch(:licenses)
  end

  # Get all other gem dependencies for the given version.
  #
  # @param version [String|Gem::Version] The version for which to get the
  #   dependencies.
  # @return [Array] list of other gems upon which the gem depends
  def get_dependencies_for_version(version)
    version = Gem::Version.new(version) if version.is_a?(String)

    payload = Marshal.load(agent.get(deps).body)

    dependencies = payload.find do |v|
      Gem::Version.new(v[:number]) == version
    end

    dependencies[:dependencies].map(&:first)
  end

  # Scrape the rubygems.org frontend for the gem's homepage URL.
  #
  # @return [String] the homepage URL of the gem
  def scrape_frontend_for_homepage_url
    html = agent.get(gem).body
    links = Nokogiri::HTML(html).css('a')

    homepage_link = links.find do |a|
      a.text.strip == 'Homepage'
    end

    homepage_link[:href]
  end

  # Quick method to get all important information in a single hash for
  # later processing.
  #
  # @return [Hash] hash containing all the information available from the
  #   rubygems.org APIs and website
  def scrape!
    response = query_latest_version
    version = get_version_from_response(response)

    {
      version: version,
      description: format_description_from_response(response),
      checksum: get_checksum_from_response(response),
      license: get_licenses_from_response(response),
      dependencies: get_dependencies_for_version(version),
      homepage: scrape_frontend_for_homepage_url
    }
  end
end

#deps ⇒ String (readonly)

Returns the rubygems URL for getting dependency information.

Returns:

  • (String) —

    the rubygems URL for getting dependency information



35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
 
# File 'lib/gembuild/gem_scraper.rb', line 35

class GemScraper
  attr_reader :agent, :deps, :gem, :gemname, :url

  # Creates a new GemScraper instance
  #
  # @raise [Gembuild::UndefinedGemName] if the gemname is nil or empty
  #
  # @example Create a new GemScraper object
  #   Gembuild::GemScraper.new('mina')
  #   # => #<Gembuild::GemScraper:0x00000002f8a500
  #   #  @agent=
  #   #   #<Mechanize
  #   #    #<Mechanize::CookieJar:0x00000002f8a410
  #   #     @store=
  #   #      #<HTTP::CookieJar::HashStore:0x00000002f8a370
  #   #       @gc_index=0,
  #   #       @gc_threshold=150,
  #   #       @jar={},
  #   #       @logger=nil,
  #   #       @mon_count=0,
  #   #       @mon_mutex=#<Mutex:0x00000002f8a320>,
  #   #       @mon_owner=nil>>
  #   #    nil>,
  #   #  @deps="https://rubygems.org/api/v1/dependencies?gems=mina",
  #   #  @gem="https://rubygems.org/gems/mina",
  #   #  @gemname="mina",
  #   #  @url="https://rubygems.org/api/v1/versions/mina.json">
  #
  # @param gemname [String] The gem about which to query.
  # @return [Gembuild::GemScraper] a new GemScraper instance
  def initialize(gemname)
    fail Gembuild::UndefinedGemNameError if gemname.nil? || gemname.empty?

    @gemname = gemname
    @agent = Mechanize.new

    @url = "https://rubygems.org/api/v1/versions/#{gemname}.json"
    @deps = "https://rubygems.org/api/v1/dependencies?gems=#{gemname}"
    @gem = "https://rubygems.org/gems/#{gemname}"
  end

  # Query the rubygems version api for the latest version.
  #
  # @raise [Gembuild::GemNotFoundError] if the page returns a 404 (not
  #   found) error.
  #
  # @example Query rubygems.org for version information
  #   s = Gembuild::GemScraper.new('mina')
  #   s.query_latest_version
  #   # => {:authors=>"Rico Sta. Cruz, Michael Galero",
  #   #  :built_at=>"2015-07-08T00:00:00.000Z",
  #   #  :created_at=>"2015-07-08T13:13:33.292Z",
  #   #  :description=>"Really fast deployer and server automation tool.",
  #   #  :downloads_count=>18709,
  #   #  :metadata=>{},
  #   #  :number=>"0.3.7",
  #   #  :summary=>"Really fast deployer and server automation tool.",
  #   #  :platform=>"ruby",
  #   #  :ruby_version=>">= 0",
  #   #  :prerelease=>false,
  #   #  :licenses=>[],
  #   #  :requirements=>[],
  #   #  :sha=>
  #   #   "bd1fa2b56ed1aded882a12f6365a04496f5cf8a14c07f8c4f1f3cfc944ef34f6"
  #   # }
  #
  # @return [Hash] the information about the latest version of the gem
  def query_latest_version
    response = JSON.parse(agent.get(url).body, symbolize_names: true)

    # Skip any release marked as a "prerelease"
    response.shift while response.first[:prerelease]

    response.first
  rescue Mechanize::ResponseCodeError, Net::HTTPNotFound
    raise Gembuild::GemNotFoundError
  end

  # Gets the version number from the parsed response.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [Gem::Version] the current version of the gem
  def get_version_from_response(response)
    Gem::Version.new(response.fetch(:number))
  end

  # Gets a well-formed gem description from the parsed response.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [String] the gem description or summary ending in a full-stop
  def format_description_from_response(response)
    description = response.fetch(:description)
    description = response.fetch(:summary) if description.empty?

    # Replace any newlines or tabs (which would mess up a PKGBUILD) with
    # spaces. Then, make sure there is no
    description = description.gsub(/[[:space:]]+/, ' ').strip

    # Ensure that the description ends in a full-stop.
    description += '.' unless description[-1, 1] == '.'

    description
  end

  # Gets the sha256 checksum returned from the rubygems.org API.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [String] the sha256 sum of the gem file
  def get_checksum_from_response(response)
    response.fetch(:sha)
  end

  # Get the array of licenses under which the gem is licensed.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [Array] the licenses for the gem
  def get_licenses_from_response(response)
    response.fetch(:licenses)
  end

  # Get all other gem dependencies for the given version.
  #
  # @param version [String|Gem::Version] The version for which to get the
  #   dependencies.
  # @return [Array] list of other gems upon which the gem depends
  def get_dependencies_for_version(version)
    version = Gem::Version.new(version) if version.is_a?(String)

    payload = Marshal.load(agent.get(deps).body)

    dependencies = payload.find do |v|
      Gem::Version.new(v[:number]) == version
    end

    dependencies[:dependencies].map(&:first)
  end

  # Scrape the rubygems.org frontend for the gem's homepage URL.
  #
  # @return [String] the homepage URL of the gem
  def scrape_frontend_for_homepage_url
    html = agent.get(gem).body
    links = Nokogiri::HTML(html).css('a')

    homepage_link = links.find do |a|
      a.text.strip == 'Homepage'
    end

    homepage_link[:href]
  end

  # Quick method to get all important information in a single hash for
  # later processing.
  #
  # @return [Hash] hash containing all the information available from the
  #   rubygems.org APIs and website
  def scrape!
    response = query_latest_version
    version = get_version_from_response(response)

    {
      version: version,
      description: format_description_from_response(response),
      checksum: get_checksum_from_response(response),
      license: get_licenses_from_response(response),
      dependencies: get_dependencies_for_version(version),
      homepage: scrape_frontend_for_homepage_url
    }
  end
end

#gem ⇒ String (readonly)

Returns the rubygems URL for the frontend.

Returns:

  • (String) —

    the rubygems URL for the frontend



35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
 
# File 'lib/gembuild/gem_scraper.rb', line 35

class GemScraper
  attr_reader :agent, :deps, :gem, :gemname, :url

  # Creates a new GemScraper instance
  #
  # @raise [Gembuild::UndefinedGemName] if the gemname is nil or empty
  #
  # @example Create a new GemScraper object
  #   Gembuild::GemScraper.new('mina')
  #   # => #<Gembuild::GemScraper:0x00000002f8a500
  #   #  @agent=
  #   #   #<Mechanize
  #   #    #<Mechanize::CookieJar:0x00000002f8a410
  #   #     @store=
  #   #      #<HTTP::CookieJar::HashStore:0x00000002f8a370
  #   #       @gc_index=0,
  #   #       @gc_threshold=150,
  #   #       @jar={},
  #   #       @logger=nil,
  #   #       @mon_count=0,
  #   #       @mon_mutex=#<Mutex:0x00000002f8a320>,
  #   #       @mon_owner=nil>>
  #   #    nil>,
  #   #  @deps="https://rubygems.org/api/v1/dependencies?gems=mina",
  #   #  @gem="https://rubygems.org/gems/mina",
  #   #  @gemname="mina",
  #   #  @url="https://rubygems.org/api/v1/versions/mina.json">
  #
  # @param gemname [String] The gem about which to query.
  # @return [Gembuild::GemScraper] a new GemScraper instance
  def initialize(gemname)
    fail Gembuild::UndefinedGemNameError if gemname.nil? || gemname.empty?

    @gemname = gemname
    @agent = Mechanize.new

    @url = "https://rubygems.org/api/v1/versions/#{gemname}.json"
    @deps = "https://rubygems.org/api/v1/dependencies?gems=#{gemname}"
    @gem = "https://rubygems.org/gems/#{gemname}"
  end

  # Query the rubygems version api for the latest version.
  #
  # @raise [Gembuild::GemNotFoundError] if the page returns a 404 (not
  #   found) error.
  #
  # @example Query rubygems.org for version information
  #   s = Gembuild::GemScraper.new('mina')
  #   s.query_latest_version
  #   # => {:authors=>"Rico Sta. Cruz, Michael Galero",
  #   #  :built_at=>"2015-07-08T00:00:00.000Z",
  #   #  :created_at=>"2015-07-08T13:13:33.292Z",
  #   #  :description=>"Really fast deployer and server automation tool.",
  #   #  :downloads_count=>18709,
  #   #  :metadata=>{},
  #   #  :number=>"0.3.7",
  #   #  :summary=>"Really fast deployer and server automation tool.",
  #   #  :platform=>"ruby",
  #   #  :ruby_version=>">= 0",
  #   #  :prerelease=>false,
  #   #  :licenses=>[],
  #   #  :requirements=>[],
  #   #  :sha=>
  #   #   "bd1fa2b56ed1aded882a12f6365a04496f5cf8a14c07f8c4f1f3cfc944ef34f6"
  #   # }
  #
  # @return [Hash] the information about the latest version of the gem
  def query_latest_version
    response = JSON.parse(agent.get(url).body, symbolize_names: true)

    # Skip any release marked as a "prerelease"
    response.shift while response.first[:prerelease]

    response.first
  rescue Mechanize::ResponseCodeError, Net::HTTPNotFound
    raise Gembuild::GemNotFoundError
  end

  # Gets the version number from the parsed response.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [Gem::Version] the current version of the gem
  def get_version_from_response(response)
    Gem::Version.new(response.fetch(:number))
  end

  # Gets a well-formed gem description from the parsed response.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [String] the gem description or summary ending in a full-stop
  def format_description_from_response(response)
    description = response.fetch(:description)
    description = response.fetch(:summary) if description.empty?

    # Replace any newlines or tabs (which would mess up a PKGBUILD) with
    # spaces. Then, make sure there is no
    description = description.gsub(/[[:space:]]+/, ' ').strip

    # Ensure that the description ends in a full-stop.
    description += '.' unless description[-1, 1] == '.'

    description
  end

  # Gets the sha256 checksum returned from the rubygems.org API.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [String] the sha256 sum of the gem file
  def get_checksum_from_response(response)
    response.fetch(:sha)
  end

  # Get the array of licenses under which the gem is licensed.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [Array] the licenses for the gem
  def get_licenses_from_response(response)
    response.fetch(:licenses)
  end

  # Get all other gem dependencies for the given version.
  #
  # @param version [String|Gem::Version] The version for which to get the
  #   dependencies.
  # @return [Array] list of other gems upon which the gem depends
  def get_dependencies_for_version(version)
    version = Gem::Version.new(version) if version.is_a?(String)

    payload = Marshal.load(agent.get(deps).body)

    dependencies = payload.find do |v|
      Gem::Version.new(v[:number]) == version
    end

    dependencies[:dependencies].map(&:first)
  end

  # Scrape the rubygems.org frontend for the gem's homepage URL.
  #
  # @return [String] the homepage URL of the gem
  def scrape_frontend_for_homepage_url
    html = agent.get(gem).body
    links = Nokogiri::HTML(html).css('a')

    homepage_link = links.find do |a|
      a.text.strip == 'Homepage'
    end

    homepage_link[:href]
  end

  # Quick method to get all important information in a single hash for
  # later processing.
  #
  # @return [Hash] hash containing all the information available from the
  #   rubygems.org APIs and website
  def scrape!
    response = query_latest_version
    version = get_version_from_response(response)

    {
      version: version,
      description: format_description_from_response(response),
      checksum: get_checksum_from_response(response),
      license: get_licenses_from_response(response),
      dependencies: get_dependencies_for_version(version),
      homepage: scrape_frontend_for_homepage_url
    }
  end
end

#gemname ⇒ String (readonly)

Returns the rubygem about which to query.

Returns:

  • (String) —

    the rubygem about which to query



35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
 
# File 'lib/gembuild/gem_scraper.rb', line 35

class GemScraper
  attr_reader :agent, :deps, :gem, :gemname, :url

  # Creates a new GemScraper instance
  #
  # @raise [Gembuild::UndefinedGemName] if the gemname is nil or empty
  #
  # @example Create a new GemScraper object
  #   Gembuild::GemScraper.new('mina')
  #   # => #<Gembuild::GemScraper:0x00000002f8a500
  #   #  @agent=
  #   #   #<Mechanize
  #   #    #<Mechanize::CookieJar:0x00000002f8a410
  #   #     @store=
  #   #      #<HTTP::CookieJar::HashStore:0x00000002f8a370
  #   #       @gc_index=0,
  #   #       @gc_threshold=150,
  #   #       @jar={},
  #   #       @logger=nil,
  #   #       @mon_count=0,
  #   #       @mon_mutex=#<Mutex:0x00000002f8a320>,
  #   #       @mon_owner=nil>>
  #   #    nil>,
  #   #  @deps="https://rubygems.org/api/v1/dependencies?gems=mina",
  #   #  @gem="https://rubygems.org/gems/mina",
  #   #  @gemname="mina",
  #   #  @url="https://rubygems.org/api/v1/versions/mina.json">
  #
  # @param gemname [String] The gem about which to query.
  # @return [Gembuild::GemScraper] a new GemScraper instance
  def initialize(gemname)
    fail Gembuild::UndefinedGemNameError if gemname.nil? || gemname.empty?

    @gemname = gemname
    @agent = Mechanize.new

    @url = "https://rubygems.org/api/v1/versions/#{gemname}.json"
    @deps = "https://rubygems.org/api/v1/dependencies?gems=#{gemname}"
    @gem = "https://rubygems.org/gems/#{gemname}"
  end

  # Query the rubygems version api for the latest version.
  #
  # @raise [Gembuild::GemNotFoundError] if the page returns a 404 (not
  #   found) error.
  #
  # @example Query rubygems.org for version information
  #   s = Gembuild::GemScraper.new('mina')
  #   s.query_latest_version
  #   # => {:authors=>"Rico Sta. Cruz, Michael Galero",
  #   #  :built_at=>"2015-07-08T00:00:00.000Z",
  #   #  :created_at=>"2015-07-08T13:13:33.292Z",
  #   #  :description=>"Really fast deployer and server automation tool.",
  #   #  :downloads_count=>18709,
  #   #  :metadata=>{},
  #   #  :number=>"0.3.7",
  #   #  :summary=>"Really fast deployer and server automation tool.",
  #   #  :platform=>"ruby",
  #   #  :ruby_version=>">= 0",
  #   #  :prerelease=>false,
  #   #  :licenses=>[],
  #   #  :requirements=>[],
  #   #  :sha=>
  #   #   "bd1fa2b56ed1aded882a12f6365a04496f5cf8a14c07f8c4f1f3cfc944ef34f6"
  #   # }
  #
  # @return [Hash] the information about the latest version of the gem
  def query_latest_version
    response = JSON.parse(agent.get(url).body, symbolize_names: true)

    # Skip any release marked as a "prerelease"
    response.shift while response.first[:prerelease]

    response.first
  rescue Mechanize::ResponseCodeError, Net::HTTPNotFound
    raise Gembuild::GemNotFoundError
  end

  # Gets the version number from the parsed response.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [Gem::Version] the current version of the gem
  def get_version_from_response(response)
    Gem::Version.new(response.fetch(:number))
  end

  # Gets a well-formed gem description from the parsed response.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [String] the gem description or summary ending in a full-stop
  def format_description_from_response(response)
    description = response.fetch(:description)
    description = response.fetch(:summary) if description.empty?

    # Replace any newlines or tabs (which would mess up a PKGBUILD) with
    # spaces. Then, make sure there is no
    description = description.gsub(/[[:space:]]+/, ' ').strip

    # Ensure that the description ends in a full-stop.
    description += '.' unless description[-1, 1] == '.'

    description
  end

  # Gets the sha256 checksum returned from the rubygems.org API.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [String] the sha256 sum of the gem file
  def get_checksum_from_response(response)
    response.fetch(:sha)
  end

  # Get the array of licenses under which the gem is licensed.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [Array] the licenses for the gem
  def get_licenses_from_response(response)
    response.fetch(:licenses)
  end

  # Get all other gem dependencies for the given version.
  #
  # @param version [String|Gem::Version] The version for which to get the
  #   dependencies.
  # @return [Array] list of other gems upon which the gem depends
  def get_dependencies_for_version(version)
    version = Gem::Version.new(version) if version.is_a?(String)

    payload = Marshal.load(agent.get(deps).body)

    dependencies = payload.find do |v|
      Gem::Version.new(v[:number]) == version
    end

    dependencies[:dependencies].map(&:first)
  end

  # Scrape the rubygems.org frontend for the gem's homepage URL.
  #
  # @return [String] the homepage URL of the gem
  def scrape_frontend_for_homepage_url
    html = agent.get(gem).body
    links = Nokogiri::HTML(html).css('a')

    homepage_link = links.find do |a|
      a.text.strip == 'Homepage'
    end

    homepage_link[:href]
  end

  # Quick method to get all important information in a single hash for
  # later processing.
  #
  # @return [Hash] hash containing all the information available from the
  #   rubygems.org APIs and website
  def scrape!
    response = query_latest_version
    version = get_version_from_response(response)

    {
      version: version,
      description: format_description_from_response(response),
      checksum: get_checksum_from_response(response),
      license: get_licenses_from_response(response),
      dependencies: get_dependencies_for_version(version),
      homepage: scrape_frontend_for_homepage_url
    }
  end
end

#url ⇒ String (readonly)

Returns the rubygems URL to get version information.

Returns:

  • (String) —

    the rubygems URL to get version information



35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
 
# File 'lib/gembuild/gem_scraper.rb', line 35

class GemScraper
  attr_reader :agent, :deps, :gem, :gemname, :url

  # Creates a new GemScraper instance
  #
  # @raise [Gembuild::UndefinedGemName] if the gemname is nil or empty
  #
  # @example Create a new GemScraper object
  #   Gembuild::GemScraper.new('mina')
  #   # => #<Gembuild::GemScraper:0x00000002f8a500
  #   #  @agent=
  #   #   #<Mechanize
  #   #    #<Mechanize::CookieJar:0x00000002f8a410
  #   #     @store=
  #   #      #<HTTP::CookieJar::HashStore:0x00000002f8a370
  #   #       @gc_index=0,
  #   #       @gc_threshold=150,
  #   #       @jar={},
  #   #       @logger=nil,
  #   #       @mon_count=0,
  #   #       @mon_mutex=#<Mutex:0x00000002f8a320>,
  #   #       @mon_owner=nil>>
  #   #    nil>,
  #   #  @deps="https://rubygems.org/api/v1/dependencies?gems=mina",
  #   #  @gem="https://rubygems.org/gems/mina",
  #   #  @gemname="mina",
  #   #  @url="https://rubygems.org/api/v1/versions/mina.json">
  #
  # @param gemname [String] The gem about which to query.
  # @return [Gembuild::GemScraper] a new GemScraper instance
  def initialize(gemname)
    fail Gembuild::UndefinedGemNameError if gemname.nil? || gemname.empty?

    @gemname = gemname
    @agent = Mechanize.new

    @url = "https://rubygems.org/api/v1/versions/#{gemname}.json"
    @deps = "https://rubygems.org/api/v1/dependencies?gems=#{gemname}"
    @gem = "https://rubygems.org/gems/#{gemname}"
  end

  # Query the rubygems version api for the latest version.
  #
  # @raise [Gembuild::GemNotFoundError] if the page returns a 404 (not
  #   found) error.
  #
  # @example Query rubygems.org for version information
  #   s = Gembuild::GemScraper.new('mina')
  #   s.query_latest_version
  #   # => {:authors=>"Rico Sta. Cruz, Michael Galero",
  #   #  :built_at=>"2015-07-08T00:00:00.000Z",
  #   #  :created_at=>"2015-07-08T13:13:33.292Z",
  #   #  :description=>"Really fast deployer and server automation tool.",
  #   #  :downloads_count=>18709,
  #   #  :metadata=>{},
  #   #  :number=>"0.3.7",
  #   #  :summary=>"Really fast deployer and server automation tool.",
  #   #  :platform=>"ruby",
  #   #  :ruby_version=>">= 0",
  #   #  :prerelease=>false,
  #   #  :licenses=>[],
  #   #  :requirements=>[],
  #   #  :sha=>
  #   #   "bd1fa2b56ed1aded882a12f6365a04496f5cf8a14c07f8c4f1f3cfc944ef34f6"
  #   # }
  #
  # @return [Hash] the information about the latest version of the gem
  def query_latest_version
    response = JSON.parse(agent.get(url).body, symbolize_names: true)

    # Skip any release marked as a "prerelease"
    response.shift while response.first[:prerelease]

    response.first
  rescue Mechanize::ResponseCodeError, Net::HTTPNotFound
    raise Gembuild::GemNotFoundError
  end

  # Gets the version number from the parsed response.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [Gem::Version] the current version of the gem
  def get_version_from_response(response)
    Gem::Version.new(response.fetch(:number))
  end

  # Gets a well-formed gem description from the parsed response.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [String] the gem description or summary ending in a full-stop
  def format_description_from_response(response)
    description = response.fetch(:description)
    description = response.fetch(:summary) if description.empty?

    # Replace any newlines or tabs (which would mess up a PKGBUILD) with
    # spaces. Then, make sure there is no
    description = description.gsub(/[[:space:]]+/, ' ').strip

    # Ensure that the description ends in a full-stop.
    description += '.' unless description[-1, 1] == '.'

    description
  end

  # Gets the sha256 checksum returned from the rubygems.org API.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [String] the sha256 sum of the gem file
  def get_checksum_from_response(response)
    response.fetch(:sha)
  end

  # Get the array of licenses under which the gem is licensed.
  #
  # @param response [Hash] The JSON parsed results from rubygems.org.
  # @return [Array] the licenses for the gem
  def get_licenses_from_response(response)
    response.fetch(:licenses)
  end

  # Get all other gem dependencies for the given version.
  #
  # @param version [String|Gem::Version] The version for which to get the
  #   dependencies.
  # @return [Array] list of other gems upon which the gem depends
  def get_dependencies_for_version(version)
    version = Gem::Version.new(version) if version.is_a?(String)

    payload = Marshal.load(agent.get(deps).body)

    dependencies = payload.find do |v|
      Gem::Version.new(v[:number]) == version
    end

    dependencies[:dependencies].map(&:first)
  end

  # Scrape the rubygems.org frontend for the gem's homepage URL.
  #
  # @return [String] the homepage URL of the gem
  def scrape_frontend_for_homepage_url
    html = agent.get(gem).body
    links = Nokogiri::HTML(html).css('a')

    homepage_link = links.find do |a|
      a.text.strip == 'Homepage'
    end

    homepage_link[:href]
  end

  # Quick method to get all important information in a single hash for
  # later processing.
  #
  # @return [Hash] hash containing all the information available from the
  #   rubygems.org APIs and website
  def scrape!
    response = query_latest_version
    version = get_version_from_response(response)

    {
      version: version,
      description: format_description_from_response(response),
      checksum: get_checksum_from_response(response),
      license: get_licenses_from_response(response),
      dependencies: get_dependencies_for_version(version),
      homepage: scrape_frontend_for_homepage_url
    }
  end
end

Instance Method Details

#format_description_from_response(response) ⇒ String

Gets a well-formed gem description from the parsed response.

Parameters:

  • response (Hash) —

    The JSON parsed results from rubygems.org.

Returns:

  • (String) —

    the gem description or summary ending in a full-stop



125
126
127
128
129
130
131
132
133
134
135
136
137
 
# File 'lib/gembuild/gem_scraper.rb', line 125

def format_description_from_response(response)
  description = response.fetch(:description)
  description = response.fetch(:summary) if description.empty?

  # Replace any newlines or tabs (which would mess up a PKGBUILD) with
  # spaces. Then, make sure there is no
  description = description.gsub(/[[:space:]]+/, ' ').strip

  # Ensure that the description ends in a full-stop.
  description += '.' unless description[-1, 1] == '.'

  description
end

#get_checksum_from_response(response) ⇒ String

Gets the sha256 checksum returned from the rubygems.org API.

Parameters:

  • response (Hash) —

    The JSON parsed results from rubygems.org.

Returns:

  • (String) —

    the sha256 sum of the gem file



143
144
145
 
# File 'lib/gembuild/gem_scraper.rb', line 143

def get_checksum_from_response(response)
  response.fetch(:sha)
end

#get_dependencies_for_version(version) ⇒ Array

Get all other gem dependencies for the given version.

Parameters:

  • version (String|Gem::Version) —

    The version for which to get the dependencies.

Returns:

  • (Array) —

    list of other gems upon which the gem depends



160
161
162
163
164
165
166
167
168
169
170
 
# File 'lib/gembuild/gem_scraper.rb', line 160

def get_dependencies_for_version(version)
  version = Gem::Version.new(version) if version.is_a?(String)

  payload = Marshal.load(agent.get(deps).body)

  dependencies = payload.find do |v|
    Gem::Version.new(v[:number]) == version
  end

  dependencies[:dependencies].map(&:first)
end

#get_licenses_from_response(response) ⇒ Array

Get the array of licenses under which the gem is licensed.

Parameters:

  • response (Hash) —

    The JSON parsed results from rubygems.org.

Returns:

  • (Array) —

    the licenses for the gem



151
152
153
 
# File 'lib/gembuild/gem_scraper.rb', line 151

def get_licenses_from_response(response)
  response.fetch(:licenses)
end

#get_version_from_response(response) ⇒ Gem::Version

Gets the version number from the parsed response.

Parameters:

  • response (Hash) —

    The JSON parsed results from rubygems.org.

Returns:

  • (Gem::Version) —

    the current version of the gem



117
118
119
 
# File 'lib/gembuild/gem_scraper.rb', line 117

def get_version_from_response(response)
  Gem::Version.new(response.fetch(:number))
end

#query_latest_version ⇒ Hash

Query the rubygems version api for the latest version.

Examples:

Query rubygems.org for version information

s = Gembuild::GemScraper.new('mina')
s.query_latest_version
# => {:authors=>"Rico Sta. Cruz, Michael Galero",
#  :built_at=>"2015-07-08T00:00:00.000Z",
#  :created_at=>"2015-07-08T13:13:33.292Z",
#  :description=>"Really fast deployer and server automation tool.",
#  :downloads_count=>18709,
#  :metadata=>{},
#  :number=>"0.3.7",
#  :summary=>"Really fast deployer and server automation tool.",
#  :platform=>"ruby",
#  :ruby_version=>">= 0",
#  :prerelease=>false,
#  :licenses=>[],
#  :requirements=>[],
#  :sha=>
#   "bd1fa2b56ed1aded882a12f6365a04496f5cf8a14c07f8c4f1f3cfc944ef34f6"
# }

Returns:

  • (Hash) —

    the information about the latest version of the gem

Raises:



102
103
104
105
106
107
108
109
110
111
 
# File 'lib/gembuild/gem_scraper.rb', line 102

def query_latest_version
  response = JSON.parse(agent.get(url).body, symbolize_names: true)

  # Skip any release marked as a "prerelease"
  response.shift while response.first[:prerelease]

  response.first
rescue Mechanize::ResponseCodeError, Net::HTTPNotFound
  raise Gembuild::GemNotFoundError
end

#scrape! ⇒ Hash

Quick method to get all important information in a single hash for later processing.

Returns:

  • (Hash) —

    hash containing all the information available from the rubygems.org APIs and website



191
192
193
194
195
196
197
198
199
200
201
202
203
 
# File 'lib/gembuild/gem_scraper.rb', line 191

def scrape!
  response = query_latest_version
  version = get_version_from_response(response)

  {
    version: version,
    description: format_description_from_response(response),
    checksum: get_checksum_from_response(response),
    license: get_licenses_from_response(response),
    dependencies: get_dependencies_for_version(version),
    homepage: scrape_frontend_for_homepage_url
  }
end

#scrape_frontend_for_homepage_url ⇒ String

Scrape the rubygems.org frontend for the gem’s homepage URL.

Returns:

  • (String) —

    the homepage URL of the gem



175
176
177
178
179
180
181
182
183
184
 
# File 'lib/gembuild/gem_scraper.rb', line 175

def scrape_frontend_for_homepage_url
  html = agent.get(gem).body
  links = Nokogiri::HTML(html).css('a')

  homepage_link = links.find do |a|
    a.text.strip == 'Homepage'
  end

  homepage_link[:href]
end