Class: Traject::CommandLine
- Inherits:
-
Object
- Object
- Traject::CommandLine
- Defined in:
- lib/traject/command_line.rb
Overview
The class that executes for the Traject command line utility.
Warning, does do things like exit entire program on error at present. You probably don't want to use this class for anything but an actual shell command line, if you want to execute indexing directly, just use the Traject::Indexer directly.
A CommandLine object has a single persistent Indexer object it uses
Constant Summary collapse
- @@indexer_class_shortcuts =
{ "basic" => "Traject::Indexer", "marc" => "Traject::Indexer::MarcIndexer", "xml" => "Traject::Indexer::NokogiriIndexer" }
Instance Attribute Summary collapse
-
#console ⇒ Object
Returns the value of attribute console.
-
#indexer ⇒ Object
Returns the value of attribute indexer.
-
#options ⇒ Object
Returns the value of attribute options.
-
#orig_argv ⇒ Object
orig_argv is original one passed in, remaining_argv is after destructive processing by slop, still has file args in it etc.
-
#remaining_argv ⇒ Object
orig_argv is original one passed in, remaining_argv is after destructive processing by slop, still has file args in it etc.
-
#slop ⇒ Object
Returns the value of attribute slop.
Instance Method Summary collapse
- #arg_check! ⇒ Object
- #assemble_settings_hash(options) ⇒ Object
- #command_commit! ⇒ Object
- #command_marcout!(io) ⇒ Object
- #create_slop!(argv) ⇒ Object
-
#execute ⇒ Object
Returns true on success or false on failure; may also raise exceptions; may also exit program directly itself (yeah, could use some normalization).
- #get_input_io(argv) ⇒ Array<#read>, String
-
#initialize(argv = ARGV) ⇒ CommandLine
constructor
A new instance of CommandLine.
- #initialize_indexer! ⇒ Object
- #load_configuration_files!(my_indexer, conf_files) ⇒ Object
Constructor Details
#initialize(argv = ARGV) ⇒ CommandLine
Returns a new instance of CommandLine.
28 29 30 31 32 33 34 35 36 |
# File 'lib/traject/command_line.rb', line 28 def initialize(argv=ARGV) self.console = $stderr self.orig_argv = argv.dup self.slop = create_slop!(argv) self. = self.slop self.remaining_argv = self.slop.arguments end |
Instance Attribute Details
#console ⇒ Object
Returns the value of attribute console.
20 21 22 |
# File 'lib/traject/command_line.rb', line 20 def console @console end |
#indexer ⇒ Object
Returns the value of attribute indexer.
19 20 21 |
# File 'lib/traject/command_line.rb', line 19 def indexer @indexer end |
#options ⇒ Object
Returns the value of attribute options.
18 19 20 |
# File 'lib/traject/command_line.rb', line 18 def @options end |
#orig_argv ⇒ Object
orig_argv is original one passed in, remaining_argv is after destructive processing by slop, still has file args in it etc.
17 18 19 |
# File 'lib/traject/command_line.rb', line 17 def orig_argv @orig_argv end |
#remaining_argv ⇒ Object
orig_argv is original one passed in, remaining_argv is after destructive processing by slop, still has file args in it etc.
17 18 19 |
# File 'lib/traject/command_line.rb', line 17 def remaining_argv @remaining_argv end |
#slop ⇒ Object
Returns the value of attribute slop.
18 19 20 |
# File 'lib/traject/command_line.rb', line 18 def slop @slop end |
Instance Method Details
#arg_check! ⇒ Object
181 182 183 184 185 186 187 188 189 |
# File 'lib/traject/command_line.rb', line 181 def arg_check! if [:command] == "process" && (![:conf] || [:conf].length == 0) self.console.puts "Error: Missing required configuration file" self.console.puts "Exiting..." self.console.puts self.console.puts self.slop.to_s exit 2 end end |
#assemble_settings_hash(options) ⇒ Object
192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 |
# File 'lib/traject/command_line.rb', line 192 def assemble_settings_hash() settings = {} # `-s key=value` command line ([:setting] || []).each do |setting_pair| if m = /\A([^=]+)\=(.*)\Z/.match(setting_pair) key, value = m[1], m[2] settings[key] = value else self.console.puts "Unrecognized setting argument '#{setting_pair}':" self.console.puts "Should be of format -s key=value" exit 3 end end # other command line shortcuts for settings if [:debug] settings["log.level"] = "debug" end if [:'debug-mode'] require 'traject/debug_writer' settings["writer_class_name"] = "Traject::DebugWriter" settings["log.level"] = "debug" settings["processing_thread_pool"] = 0 end if [:writer] settings["writer_class_name"] = [:writer] end if [:reader] settings["reader_class_name"] = [:reader] end if [:solr] settings["solr.url"] = [:solr] end if [:marc_type] settings["marc_source.type"] = [:marc_type] end if [:output_file] settings["output_file"] = [:output_file] end return settings end |
#command_commit! ⇒ Object
91 92 93 94 95 96 97 98 99 100 |
# File 'lib/traject/command_line.rb', line 91 def command_commit! require 'open-uri' raise ArgumentError.new("No solr.url setting provided") if indexer.settings['solr.url'].to_s.empty? url = "#{indexer.settings['solr.url']}/update?commit=true" indexer.logger.info("Sending commit to: #{url}") indexer.logger.info( open(url).read ) return true end |
#command_marcout!(io) ⇒ Object
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 |
# File 'lib/traject/command_line.rb', line 102 def command_marcout!(io) require 'marc' output_type = indexer.settings["marcout.type"].to_s output_type = "binary" if output_type.empty? output_arg = unless indexer.settings["output_file"].to_s.empty? indexer.settings["output_file"] else $stdout end indexer.logger.info(" marcout writing type:#{output_type} to file:#{output_arg}") case output_type when "binary" writer = MARC::Writer.new(output_arg) allow_oversized = indexer.settings["marcout.allow_oversized"] if allow_oversized allow_oversized = (allow_oversized.to_s == "true") writer.allow_oversized = allow_oversized end when "xml" writer = MARC::XMLWriter.new(output_arg) when "human" writer = output_arg.kind_of?(String) ? File.open(output_arg, "w:binary") : output_arg else raise ArgumentError.new("traject marcout unrecognized marcout.type: #{output_type}") end reader = indexer.reader!(io) reader.each do |record| writer.write record end writer.close return true end |
#create_slop!(argv) ⇒ Object
237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 |
# File 'lib/traject/command_line.rb', line 237 def create_slop!(argv) = Slop::Options.new do |o| o. = "traject [options] -c configuration.rb [-c config2.rb] file.mrc" o.on '-v', '--version', "print version information to stderr" o.on '-d', '--debug', "Include debug log, -s log.level=debug" o.on '-h', '--help', "print usage information to stderr" o.array '-c', '--conf', 'configuration file path (repeatable)', :delimiter => nil o.string "-i", '--indexer', "Traject indexer class name or shortcut", :default => "marc" o.array "-s", "--setting", "settings: `-s key=value` (repeatable)", :delimiter => nil o.string "-r", "--reader", "Set reader class, shortcut for -s reader_class_name=" o.string "-o", "--output_file", "output file for Writer classes that write to files" o.string "-w", "--writer", "Set writer class, shortcut for -s writer_class_name=" o.string "-u", "--solr", "Set solr url, shortcut for -s solr.url=" o.string "-t", "--marc_type", "xml, json or binary. shortcut for -s marc_source.type=" o.array "-I", "--load_path", "append paths to ruby $LOAD_PATH", :delimiter => ":" o.string "-x", "--command", "alternate traject command: process (default); marcout; commit", :default => "process" o.on "--stdin", "read input from stdin" o.on "--debug-mode", "debug logging, single threaded, output human readable hashes" end .parse(argv) rescue Slop::Error => e self.console.puts "Error: #{e.}" self.console.puts "Exiting..." self.console.puts self.console.puts .to_s exit 1 end |
#execute ⇒ Object
Returns true on success or false on failure; may also raise exceptions; may also exit program directly itself (yeah, could use some normalization)
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 |
# File 'lib/traject/command_line.rb', line 40 def execute if [:version] self.console.puts "traject version #{Traject::VERSION}" return true end if [:help] self.console.puts slop.to_s return true end ([:load_path] || []).each do |path| $LOAD_PATH << path unless $LOAD_PATH.include? path end arg_check! self.indexer = initialize_indexer! ###### # SAFE TO LOG to indexer.logger starting here, after indexer is set up from conf files # with logging config. ##### indexer.logger.info("traject (#{Traject::VERSION}) executing with: `#{orig_argv.join(' ')}`") # Okay, actual command process! All command_ methods should return true # on success, or false on failure. result = case [:command] when "process" (io, filename) = get_input_io(self.remaining_argv) indexer.settings['command_line.filename'] = filename if filename indexer.process(io) when "marcout" (io, filename) = get_input_io(self.remaining_argv) indexer.settings['command_line.filename'] = filename if filename command_marcout!(io) when "commit" command_commit! else raise ArgumentError.new("Unrecognized traject command: #{[:command]}") end return result rescue Exception => e # Try to log unexpected exceptions if possible indexer && indexer.logger && indexer.logger.fatal("Traject::CommandLine: Unexpected exception, terminating execution: #{Traject::Util.(e)}") rescue nil raise e end |
#get_input_io(argv) ⇒ Array<#read>, String
145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 |
# File 'lib/traject/command_line.rb', line 145 def get_input_io(argv) filename = nil io_arr = nil if [:stdin] indexer.logger.info("Reading from standard input") io_arr = [$stdin] elsif argv.length == 0 io_arr = [File.open(File::NULL, 'r')] indexer.logger.info("Warning, no file input given. Use command-line argument '--stdin' to use standard input ") else io_arr = argv.collect { |path| File.open(path, 'r') } filename = argv.join(",") indexer.logger.info "Reading from #{filename}" end return io_arr, filename end |
#initialize_indexer! ⇒ Object
269 270 271 272 273 274 275 276 277 |
# File 'lib/traject/command_line.rb', line 269 def initialize_indexer! indexer_class_name = @@indexer_class_shortcuts[[:indexer]] || [:indexer] klass = Traject::Indexer.qualified_const_get(indexer_class_name) indexer = klass.new self.assemble_settings_hash(self.) load_configuration_files!(indexer, [:conf]) return indexer end |
#load_configuration_files!(my_indexer, conf_files) ⇒ Object
163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 |
# File 'lib/traject/command_line.rb', line 163 def load_configuration_files!(my_indexer, conf_files) conf_files.each do |conf_path| begin my_indexer.load_config_file(conf_path) rescue Errno::ENOENT, Errno::EACCES => e self.console.puts "Could not read configuration file '#{conf_path}', exiting..." exit 2 rescue Traject::Indexer::ConfigLoadError => e self.console.puts "\n" self.console.puts e. self.console.puts e.config_file_backtrace self.console.puts "\n" self.console.puts "Exiting..." exit 3 end end end |