wabur 0.4.0d1 → 0.5.0

data/lib/wab/impl/model.rb

@@ -6,7 +6,7 @@ module WAB
   module Impl
 
     # The Model class is used to store data when using the
-    # WAB::Impl::Shell. It is no intended for any other use. The *get* and
+    # WAB::Impl::Shell. It is not intended for any other use. The *get* and
     # *query* methods are the primary means of interacting with the model.
     #
     # The Model is simple in that it stores data in a Hash references by *ref*
@@ -17,9 +17,10 @@ module WAB
       # Create a new Model using the designated directory as the store.
       #
       # dir:: directory to store data in
-      def initialize(dir)
+      def initialize(dir, indent=0)
         @dir = dir.nil? ? nil : File.expand_path(dir)
         @cnt = 0
+        @indent = indent
         @map = {}
         @lock = Thread::Mutex.new
         FileUtils.mkdir_p(@dir) unless @dir.nil? || Dir.exist?(@dir)
@@ -185,7 +186,7 @@ module WAB
       def write_to_file(ref, obj)
         return if @dir.nil?
         obj.native if obj.is_a?(WAB::Data)
-        File.open(File.join(@dir, "%016x.json" % ref), 'wb') { |f| f.write(Oj.dump(obj, mode: :wab, indent: 0)) }
+        File.open(File.join(@dir, "%016x.json" % ref), 'wb') { |f| f.write(Oj.dump(obj, mode: :wab, indent: @indent)) }
       end
 
       def remove_file(ref)

data/lib/wab/impl/shell.rb

@@ -14,6 +14,8 @@ module WAB
       attr_reader :type_key
       attr_reader :path_pos
 
+      attr_accessor :indent
+      
       # Call the Model instance with these methods.
       def_delegators :@model, :get, :query
 
@@ -21,15 +23,18 @@ module WAB
       #
       # config:: Configuration object
       def initialize(config)
-        @pre_path      = config[:path_prefix] || '/v1'
+        @indent       = config[:indent].to_i || 0
+        @pre_path     = config[:path_prefix] || '/v1'
         @path_pos     = @pre_path.split('/').length - 1
         base          = config[:base] || '.'
-        @model        = Model.new((config['store.dir'] || File.join(base, 'data')).gsub('$BASE', base))
+        @model        = Model.new((config['store.dir'] || File.join(base, 'data')).gsub('$BASE', base), indent)
         @type_key     = config[:type_key] || 'kind'
         @logger       = config[:logger]
         @logger.level = config[:verbosity] unless @logger.nil?
         @http_dir     = (config['http.dir'] || File.join(base, 'pages')).gsub('$BASE', base)
         @http_port    = (config['http.port'] || 6363).to_i
+        @export_proxy = config[:export_proxy]
+        @export_proxy = true if @export_proxy.nil? # The default is true if not present.
         @controllers  = {}
 
         requires      = config[:require]
@@ -48,8 +53,13 @@ module WAB
       # Start listening. This should be called after registering Controllers
       # with the Shell.
       def start()
-        server = WEBrick::HTTPServer.new(Port: @http_port, DocumentRoot: @http_dir)
-        server.mount(@pre_path, WAB::Impl::Handler, self)
+        mime_types = WEBrick::HTTPUtils::DefaultMimeTypes
+        mime_types['es6'] = 'application/javascript'
+        server = WEBrick::HTTPServer.new(Port: @http_port,
+                                         DocumentRoot: @http_dir,
+                                         MimeTypes: mime_types)
+        server.mount(@pre_path, Handler, self)
+        server.mount('/', ExportProxy, @http_dir) if @export_proxy
 
         trap 'INT' do server.shutdown end
         server.start

data/lib/wab/impl/templates/opo-rub.conf.template

@@ -0,0 +1,253 @@
+# opo-rub.conf
+
+# This sample configuration file for opod includes all the avaliable options
+# and the default values for those options. All option keys are case
+# insensitive.
+
+# The directory to store the opo data.
+#dir = /var/opo
+dir = opo/data
+
+# A journal is kept if this option is true. When set to false changes in the
+# data are not persisted until a clean exit or a explicit persist command to
+# the opod.
+journal = false
+
+# If sync is true then writes are always synced to disk before
+# returning. Performance is far better if sync is set to false.
+sync = false
+
+# If exit_sync is true then writes are performed on normal shutdown or by
+# ctrl-C unless journalling is already on or sync is true.
+exit_sync = true
+
+# Default format for import and dump. Valid values are JSON, RDF, N-TRiPLES,
+# N-QUADS, TURTLE, or OG, case insensitive. The indent option if for the JSON
+# format only.
+format = JSON
+
+# One or more threads are created to process requests. Set the threads to the
+# value best suited to the machine opo will be running on.
+threads = 2
+
+################################################################################
+# Opo supports an HTTP interface. The HTTP interface includes documentation
+# pages, access helper pages, and REST APIs for interating with opo using
+# either a JSON model of SPARQL when using the triple store model.
+
+# The port to connect to opo on using an HTTP browser. A value of zero
+# indicates no HTTP connectivity.
+http.port = 6363
+
+# Opo can also be used to serve custom pages. Note that built in URL paths
+# take precedence over subdirectories in the provided pages dir. If left blank
+# then no custom pages are served.
+#http.dir =
+http.dir = site
+
+################################################################################
+# Log related options are all prefixed with 'log.'. Log files are written to a
+# specified log directory and rotated as they exceed the maximum size. Log
+# files are in JSON format.
+
+# The directory to write log files to.
+#log.dir = /var/log
+log.dir = opo/log
+
+# The maximum number of archived log files to keep in addition to the current
+# log file.
+log.maxFiles = 3
+
+# Size that when exceeded cause the log files to rotate. Note file may and are
+# usually slightly larger than the maximum size as the maximum size is a
+# trigger to rotate.
+log.maxSize = 100000000
+
+# If true log entries are displayed on the console.
+log.console = true
+
+# if true console log output is in classic format. If false, output is in JSON
+# format.
+log.classic = true
+
+# If true console output is colorized.
+log.colorize = true
+
+# If the syslog address and port in the format 10.10.0.7:1234 is provided log
+# messages are also sent to syslog on the provided address. If the UDP option
+# is true the syslog send is done using UDP instead of TCP.
+log.syslog.address = 
+log.syslog.udp = true
+
+# Logging category or feature based. To log details about specific features
+# turn the category on. Colors can also be set for each category. Supported
+# colors are:
+#   black
+#   red
+#   green
+#   yellow
+#   blue
+#   magenta
+#   cyan
+#   white
+#   gray
+#   dark_red
+#   dark_green
+#   brown
+#   dark_blue
+#   purple
+#   dark_cyan
+
+# The error category.
+log.cats.error.on = true
+log.cats.error.color = red
+
+# The warning category.
+log.cats.warn.on = true
+log.cats.warn.color = yellow
+
+# The mod category is used to log changes or modifications to data in the
+# store. Any insert, update, and delete is logged if true.
+log.cats.mod.on = true
+log.cats.mod.color = dark_green
+
+# The journal category. A log message is published for ever journal
+# entry. Very verbose.
+log.cats.journal.on = false
+log.cats.journal.color = dark_green
+
+# Logging for http is controlled by these options. Note that HTTP logging is
+# finer grained that others.
+log.cats.http_request.on = false
+log.cats.http_request.color = dark_green
+
+log.cats.http_response.on = false
+log.cats.http_response.color = dark_green
+
+log.cats.http_debug.on = false
+log.cats.http_debug.color = purple
+
+log.cats.handler.on = false
+log.cats.handler.color = blue
+#
+###############################################################################
+# Opo is a triple store but also supports JSON imports and exports. RDF is
+# also supported. To provide a mapping from one to the other several options
+# are included.
+
+# When JSON is generated for query responses it will be indented according to
+# this option.
+json.indent = 0
+
+# Opo data types include more types than supported by JSON natively. The JSON
+# detect options control what the JSON parse does when it encounters a value
+# that could be read as a different type.
+
+# A value starting with http:// will be treated as a IRI if this option is true.
+json.detect.iri = true
+
+# If true a string that has the form that matches RFC3339 will be converted to
+# a date-time. Examples are: 2017-01-05T12:34:56+07:00, 2017-01-05T12:34:56Z
+# and 2017-01-05T12:34:56.999999999-07:00.
+json.detect.time.string = true
+
+# Time is stored as UNIX UTC internally. Time zones are not stored. The time
+# format options allow the time format and time zone to be used in the output
+# strings or numbers. Options for time format are:
+# UNIX: seconds from UTC epoch with 9 decimal places for seconds
+# UNIX6: seconds from UTC epoch with 6 decimal places for seconds
+# UNIX3: seconds from UTC epoch with 3 decimal places for seconds
+# UNIX0: seconds from UTC epoch with no decimal places for seconds
+# XSD9: XSD date-time with 9 decimal places for seconds
+# XSD6: XSD date-time with 6 decimal places for seconds
+# XSD3: XSD date-time with 3 decimal places for seconds
+# XSD0: XSD date-time with no decimal places for seconds
+# XSD: XSD date-time with up to 9 decimal places for seconds. trailing 0 are stripped
+# DATE: XSD date-time with up to 9 decimal places for seconds. trailing 0 are
+#           stripped. If hours, minutes, and seconds are 0 then only the date
+#           portion is output.
+time.format = XSD
+time.zone = 0
+
+# A value that has the format of a UUID (123e4567-e89b-12d3-a456-426655440000)
+# be treated as a UUID if this option is true. Providing a slight performance
+# improvment with UUIDs.
+json.detect.uuid = true
+
+# It is common for numbers to be used for times as well. A few extra control
+# parameters are needed to limit the scope of time detection. The min and max
+# values specify the range for detection. The decimals if non-zero sets up a
+# requirement for that specific number of decimal places that must match.
+json.detect.time.number.on = true
+json.detect.time.number.min = 1400000000
+json.detect.time.number.max = 1600000000
+json.detect.time.number.decimals = 9
+
+# JSON imports are converted to triples but not RDF compliant triples. In an
+# RDF triple the subject must be either a blank or a IRI. The predicate must
+# be a IRI. Since imported JSONs do not have namespaces associated with them a
+# default namespace is used to make the JSON literals into IRIs using a
+# default namespace.
+rdf.default.namespace = http://localhost#
+
+################################################################################
+# IRI aliases can be registered. These aliases will take precedence over any
+# prefix defined in a TURTLE import. Note that the commented out sample are
+# most likely out of date. Thats one of the problems with including the date
+# in the URL. It is also an advantage is referring to an older specification.
+ns.dct = http://purl.org/dc/terms/
+ns.foaf = http://xmlns.com/foaf/0.1/
+ns.gr = http://purl.org/goodrelations/v1#
+ns.org = http://www.w3.org/ns/org#
+ns.owl = http://www.w3.org/2002/07/owl#
+ns.prov = http://www.w3.org/ns/prov#
+ns.rdf = http://www.w3.org/1999/02/22-rdf-syntax-ns#
+ns.rdfs = http://www.w3.org/2000/01/rdf-schema#
+ns.skos = http://www.w3.org/2004/02/skos/core#
+ns.time = http://www.w3.org/2006/time#
+ns.vcard = http://www.w3.org/2006/vcard/ns#
+ns.xsd = http://www.w3.org/2001/XMLSchema#
+#ns.xsd = https://www.w3.org/TR/xmlschema11-2/#
+#ns.xsd = https://www.w3.org/TR/xmlschema-2/#
+
+# N-Triples and N-Quads literal strings can have a type associated with the
+# string. Opo attempts to convert the strings to native types if possible. To
+# do so it looks for know IRI prefixes followed by the type. The supported
+# types are 'integer', 'double', 'time', and 'datetime'. The listed
+# type.prefixes are used to form the IRIs that trigger the conversion of a
+# string to the respective native type. A comma separated list is expected.
+type.prefixes = http://www.w3.org/2001/XMLSchema#,http://www.w3.org/TR/xmlschema11-2/#,http://www.w3.org/TR/xmlschema-2/#
+
+# Multiple handlers can be running at the same time if using different
+# paths. The view conf.js would have to change to use one path or the other by
+# setting the wab.pathPrefix value.
+
+handler.ui.path = /v1/ui/**
+handler.ui.class = UIController
+%{handlers}
+################################################################################
+# When using opo-rub or other opo version with embedded interpreters the
+# 'embed' options can be used. The handler options are also extended to
+# support calling the embedded interpreter.
+
+# The load path is set to include the project lib directory.
+embed.load_path = lib
+
+# The Ruby requires. Generally whatever class in the lib directory that should
+# be imported.
+embed.require = ui_controller
+
+embed.setup = puts 'Ruby Started'
+embed.cleanup = puts 'Ruby Finished'
+
+# Field to expect the type, class, or kind of record in the stored JSON.
+embed.type_key = kind
+
+# Position in the URL path that identifies the record type or kind. The first
+# position is 0.
+embed.path_pos = 1
+
+# This sets up the WABuR gem as an alternate source for the wab default
+# index.html, CSS, JavaScript, and fonts are loaded from the gem's export
+# directory is they are not found in the site directory.
+embed.alternative_source = WAB.get_export

data/lib/wab/impl/templates/opo.conf.template

@@ -0,0 +1,224 @@
+# opo.conf
+
+# This sample configuration file for opod includes all the avaliable options
+# and the default values for those options. All option keys are case
+# insensitive.
+
+# The directory to store the opo data.
+#dir = /var/opo
+dir = opo/data
+
+# A journal is kept if this option is true. When set to false changes in the
+# data are not persisted until a clean exit or a explicit persist command to
+# the opod.
+journal = false
+
+# If sync is true then writes are always synced to disk before
+# returning. Performance is far better if sync is set to false.
+sync = false
+
+# If exit_sync is true then writes are performed on normal shutdown or by
+# ctrl-C unless journalling is already on or sync is true.
+exit_sync = true
+
+# Default format for import and dump. Valid values are JSON, RDF, N-TRiPLES,
+# N-QUADS, TURTLE, or OG, case insensitive. The indent option if for the JSON
+# format only.
+format = JSON
+
+# One or more threads are created to process requests. Set the threads to the
+# value best suited to the machine opo will be running on.
+threads = 2
+
+################################################################################
+# Opo supports an HTTP interface. The HTTP interface includes documentation
+# pages, access helper pages, and REST APIs for interating with opo using
+# either a JSON model of SPARQL when using the triple store model.
+
+# The port to connect to opo on using an HTTP browser. A value of zero
+# indicates no HTTP connectivity.
+http.port = 6363
+
+# Opo can also be used to serve custom pages. Note that built in URL paths
+# take precedence over subdirectories in the provided pages dir. If left blank
+# then no custom pages are served.
+#http.dir =
+http.dir = site
+
+################################################################################
+# Log related options are all prefixed with 'log.'. Log files are written to a
+# specified log directory and rotated as they exceed the maximum size. Log
+# files are in JSON format.
+
+# The directory to write log files to.
+#log.dir = /var/log
+log.dir = opo/log
+
+# The maximum number of archived log files to keep in addition to the current
+# log file.
+log.maxFiles = 3
+
+# Size that when exceeded cause the log files to rotate. Note file may and are
+# usually slightly larger than the maximum size as the the maximum size is a
+# trigger to rotate.
+log.maxSize = 100000000
+
+# If true log entries are displayed on the console.
+log.console = true
+
+# if true console log out is in classic format. If false output is in JSON
+# format.
+log.classic = true
+
+# If true console output is colorized.
+log.colorize = true
+
+# If the syslog address and port in the format 10.10.0.7:1234 is provided log
+# messages are also send to syslog on the provided address. If the UDP option
+# is true the syslog send is done using UDP instead of TCP.
+log.syslog.address = 
+log.syslog.udp = true
+
+# Logging category or feature based. To log details about specific features
+# turn the category on. Colors can also be set for each category. Supported
+# colors are:
+#   black
+#   red
+#   green
+#   yellow
+#   blue
+#   magenta
+#   cyan
+#   white
+#   gray
+#   dark_red
+#   dark_green
+#   brown
+#   dark_blue
+#   purple
+#   dark_cyan
+
+# The error category.
+log.cats.error.on = true
+log.cats.error.color = red
+
+# The warning category.
+log.cats.warn.on = true
+log.cats.warn.color = yellow
+
+# The mod category is used to log changes or modifications to data in the
+# store. Any insert, update, and delete is logged if true.
+log.cats.mod.on = true
+log.cats.mod.color = dark_green
+
+# The journal category. A log message is published for ever journal
+# entry. Very verbose.
+log.cats.journal.on = false
+log.cats.journal.color = dark_green
+
+# Logging for http is controlled by these options. Note that HTTP logging is
+# finer grained that others.
+log.cats.http_request.on = false
+log.cats.http_request.color = dark_green
+
+log.cats.http_response.on = false
+log.cats.http_response.color = dark_green
+
+log.cats.http_debug.on = false
+log.cats.http_debug.color = purple
+
+log.cats.handler.on = false
+log.cats.handler.color = blue
+#
+###############################################################################
+# Opo is a triple store but also supports JSON imports and exports. RDF is
+# also supported. To provide a mapping from one to the other several options
+# are included.
+
+# When JSON is generated for query responses it will be indented according to
+# this option.
+json.indent = 0
+
+# Opo data types include more types than supported by JSON natively. The JSON
+# detect options control what the JSON parse does when it encounters a value
+# that could be read as a different type.
+
+# A value starting with http:// will be treated as a IRI if this option is true.
+json.detect.iri = true
+
+# If true a string that has the form that matches RFC3339 will be converted to
+# a date-time. Examples are: 2017-01-05T12:34:56+07:00, 2017-01-05T12:34:56Z
+# and 2017-01-05T12:34:56.999999999-07:00.
+json.detect.time.string = true
+
+# Time is stored as UNIX UTC internally. Time zones are not stored. The time
+# format options allow the time format and time zone to be used in the output
+# strings or numbers. Options for time format are:
+# UNIX: seconds from UTC epoch with 9 decimal places for seconds
+# UNIX6: seconds from UTC epoch with 6 decimal places for seconds
+# UNIX3: seconds from UTC epoch with 3 decimal places for seconds
+# UNIX0: seconds from UTC epoch with no decimal places for seconds
+# XSD9: XSD date-time with 9 decimal places for seconds
+# XSD6: XSD date-time with 6 decimal places for seconds
+# XSD3: XSD date-time with 3 decimal places for seconds
+# XSD0: XSD date-time with no decimal places for seconds
+# XSD: XSD date-time with up to 9 decimal places for seconds. trailing 0 are stripped
+# DATE: XSD date-time with up to 9 decimal places for seconds. trailing 0 are
+#           stripped. If hours, minutes, and seconds are 0 then only the date
+#           portion is output.
+time.format = XSD
+time.zone = 0
+
+# A value that has the format of a UUID (123e4567-e89b-12d3-a456-426655440000)
+# be treated as a UUID if this option is true. Providing a slight performance
+# improvment with UUIDs.
+json.detect.uuid = true
+
+# It is common for numbers to be used for times as well. A few extra control
+# parameters are needed to limit the scope of time detection. The min and max
+# values specify the range for detection. The decimals if non-zero sets up a
+# requirement for that specific number of decimal places that must match.
+json.detect.time.number.on = true
+json.detect.time.number.min = 1400000000
+json.detect.time.number.max = 1600000000
+json.detect.time.number.decimals = 9
+
+# JSON imports are converted to triples but not RDF compliant triples. In an
+# RDF triple the subject must be either a blank or a IRI. The predicate must
+# be a IRI. Since imported JSONs do not have namespaces associated with them a
+# default namespace is used to make the JSON literals into IRIs using a
+# default namespace.
+rdf.default.namespace = http://localhost#
+
+################################################################################
+# IRI aliases can be registered. These aliases will take precedence over any
+# prefix defined in a TURTLE import. Note that the commented out sample are
+# most likely out of date. Thats one of the problems with including the date
+# in the URL. It is also an advantage is referring to an older specification.
+ns.dct = http://purl.org/dc/terms/
+ns.foaf = http://xmlns.com/foaf/0.1/
+ns.gr = http://purl.org/goodrelations/v1#
+ns.org = http://www.w3.org/ns/org#
+ns.owl = http://www.w3.org/2002/07/owl#
+ns.prov = http://www.w3.org/ns/prov#
+ns.rdf = http://www.w3.org/1999/02/22-rdf-syntax-ns#
+ns.rdfs = http://www.w3.org/2000/01/rdf-schema#
+ns.skos = http://www.w3.org/2004/02/skos/core#
+ns.time = http://www.w3.org/2006/time#
+ns.vcard = http://www.w3.org/2006/vcard/ns#
+ns.xsd = http://www.w3.org/2001/XMLSchema#
+#ns.xsd = https://www.w3.org/TR/xmlschema11-2/#
+#ns.xsd = https://www.w3.org/TR/xmlschema-2/#
+
+# N-Triples and N-Quads literal strings can have a type associated with the
+# string. Opo attempts to convert the strings to native types if possible. To
+# do so it looks for know IRI prefixes followed by the type. The supported
+# types are 'integer', 'double', 'time', and 'datetime'. The listed
+# type.prefixes are used to form the IRIs that trigger the conversion of a
+# string to the respective native type. A comma separated list is expected.
+type.prefixes = http://www.w3.org/2001/XMLSchema#,http://www.w3.org/TR/xmlschema11-2/#,http://www.w3.org/TR/xmlschema-2/#
+
+handler.ruby.path = /v1/**
+handler.ruby.max_out = 10
+handler.ruby.cmd = lib/spawn.rb -I lib
+handler.ruby.timeout = 5.0