icss-activesupport-4 0.4.0

data/Rakefile

@@ -0,0 +1,39 @@
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+  gem.name = "icss"
+  gem.homepage = "http://github.com/mrflip/icss"
+  gem.license = "MIT"
+  gem.summary = %Q{Infochimps Simple Schema library: an avro-compatible data description standard. ICSS completely describes a collection of data (and associated assets) in a way that is expressive, scalable and sufficient to drive remarkably complex downstream processes.}
+  gem.description = %Q{Infochimps Simple Schema library: an avro-compatible data description standard. ICSS completely describes a collection of data (and associated assets) in a way that is expressive, scalable and sufficient to drive remarkably complex downstream processes.}
+  gem.email = "coders@infochimps.com"
+  gem.authors = ["Philip (flip) Kromer for Infochimps"]
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'rspec/core'
+require 'rspec/core/rake_task'
+RSpec::Core::RakeTask.new(:spec) do |spec|
+  spec.pattern = FileList['spec/**/*_spec.rb']
+end
+
+RSpec::Core::RakeTask.new(:rcov) do |spec|
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.rcov = true
+end
+
+task :default => :spec
+
+require 'yard'
+YARD::Rake::YardocTask.new

data/TODO.md

@@ -0,0 +1,44 @@
+# Proposed ICSS refactoring:
+
+* one ICSS <=> one Dataset <=> one Catalog Entry
+
+
+geo.lake_body_of_water                 	  
+geo.ocean_body_of_water                	  
+geo.river_body_of_water                	  
+geo.sea_body_of_water                  	
+
+### catalog_entry
+
+Most of it moves to top-level:
+* tags:         move to top-level attribute
+* title:        disappears -- take from `protocol`
+* description:  disappears -- take from `doc`
+* owner:        stays in catalog_entry
+* price:        attach to bulk data target
+
+* messages:     only necessary to select among messages
+* packages:     only necessary to select among packages
+
+move to a new top-level section, `provenance`:
+
+* license
+* link -> becomes sources
+
+moves *to* catalog_entry:
+
+* `under_consideration` 
+* `update_frequency` (?? def. doesn't feel like a top-level thing, but this feels weird too)
+
+
+___________________________________________________________________________
+
+Make the get_data part of culture/books/comics/grand_comics_db a three-liner
+
+menu            	string	Either the actual menu or a URL of the menu.
+accepts_reservations 	string 	"Either Yes/No, or a URL at which reservations can
+be made."
+
+
+tile_x                 	string                           	|	bounding_box            
+tile_y                 	string                           	|	bounding_box            

data/VERSION

@@ -0,0 +1 @@
+0.4.0

data/examples/avro_examples/BulkData.avpr

@@ -0,0 +1,21 @@
+
+{"namespace": "org.apache.avro.test",
+ "protocol": "BulkData",
+
+ "types": [],
+
+ "messages": {
+
+     "read": {
+         "request": [],
+         "response": "bytes"
+     },
+
+     "write": {
+         "request": [ {"name": "data", "type": "bytes"} ],
+         "response": "null"
+     }
+
+ }
+
+}

data/examples/avro_examples/complicated.icss.yaml

@@ -0,0 +1,159 @@
+---
+namespace: util.time
+protocol: chronic
+
+doc: >-
+  An API call to parse human-readable date / time strings
+
+data_assets: []
+      
+code_assets:
+  - location:   code/chronic_endpoint.rb
+    type:       apeyeye_endpoint
+      
+types:
+    - name: a_atsigns_b_params
+      type: record
+      doc:  ""
+      fields:
+        - name: user_a_id
+          type: int
+        - name: user_a_sn
+          type: string
+        - name: user_b_id
+          type: int
+        - name: user_b_sn
+          type: string
+        
+
+    - name: your_mom
+      type: record
+      doc:  "hi"
+      fields:
+        - name: went_to_college
+          type: int
+          
+    - name:     chronic_parse_params
+      type:     record
+      doc:
+        Query API parameters for the /util/time/chronic/parse call
+      fields:
+        - name: context
+          type: string
+          doc: >-
+              <tt>:past</tt> or <tt>:future</tt> (defaults to <tt>:future</tt>)
+              
+              If your string represents a birthday, you can set
+              <tt>:context</tt> to <tt>:past</tt> and if an ambiguous string is
+              given, it will assume it is in the past. Specify <tt>:future</tt>
+              or omit to set a future context.
+              
+        - name: now
+          type: string
+          doc: >-
+            Time (defaults to Time.now)
+            
+            By setting <tt>:now</tt> to a Time, all computations will be based off
+            of that time instead of Time.now. If set to nil, Chronic will use Time.now.
+
+        - name: guess
+          type: boolean
+          doc: >-
+            +true+ or +false+ (defaults to +true+)
+
+            By default, the parser will guess a single point in time for the
+            given date or time. If you'd rather have the entire time span returned,
+            set <tt>:guess</tt> to +false+ and a Chronic::Span will be returned.
+
+        - name: ambiguous_time_range
+          type: int
+          doc: >-
+            Integer or <tt>:none</tt> (defaults to <tt>6</tt> (6am-6pm))
+
+            If an Integer is given, ambiguous times (like 5:00) will be
+            assumed to be within the range of that time in the AM to that time
+            in the PM. For example, if you set it to <tt>7</tt>, then the parser will
+            look for the time between 7am and 7pm. In the case of 5:00, it would
+            assume that means 5:00pm. If <tt>:none</tt> is given, no assumption
+            will be made, and the first matching instance of that time will
+            be used.
+        - name: field_that_is_recursive
+          type: your_mom
+          doc:  wears combat boots
+          
+        - name: field_that_is_an_array
+          type: array
+          items: int
+          doc:  I am an array of primitives
+        - name: field_that_is_a_named_type_holy_fuck
+          type:
+            - type: array
+              items: your_mom
+          doc:  I am an array of Iccs::Type::YourMomType
+            
+    - name: chronic_parse_response
+      type: record
+      doc: |-
+        Query API response for the /util/time/chronic/parse call
+      fields:
+        - name: time
+          doc:  >-
+            The UTC parsed time, as a "ISO 8601 combined date time":http://en.wikipedia.org/wiki/ISO_8601 string.
+          type: string
+        - name: epoch_seconds
+          doc:  >-
+            The UTC parsed time, as "epoch seconds":http://en.wikipedia.org/wiki/Epoch_seconds integer.
+          type: int
+        - name: params
+          doc:  >-
+            Your params, right back atcha'
+          type: string  # map
+        - name: errors
+          doc:  >-
+            Error conditions
+          type: array
+          optional: true
+        - name: whatever
+          doc:  dummy string
+          type:
+            name: embedded_record_def
+            type: record
+            doc:  I am an inline record definition
+            fields:
+            - name: name
+              type: string
+
+messages:
+  parse:
+    request:
+      - name: params
+        type: chronic_parse_params
+    response: chronic_parse_response
+    doc_file:
+      README.md
+
+# 
+# targets:
+#   mysql:
+#     # Name of the data asset, mysql table name will derived from this
+#     - table_name: word_freq_bnc
+#       database: lang_corp_word_freq_bnc
+#       data_assets:
+#         - word_freq_bnc_data_asset
+#         
+#   apidocs:
+#     - dest_path: /language/corpora/word_freq_bnc/token_frequency
+#       
+#   bulkdownload:
+#     - package_name: word_freq_bnc
+#       data_assets:
+#         - word_freq_bnc_data_asset
+#       
+#   catalog:
+#     # Name of the catalogue entry
+#     - name: word_freq_bnc
+#       title: Word Frequencies From the British National Corpus
+#       messages:
+#         - token_frequency
+#       packages:
+#         - word_freq_bnc

data/examples/avro_examples/interop.avsc

@@ -0,0 +1,32 @@
+{ "name":"Interop",
+  "namespace": "org.apache.avro",
+  "type": "record",
+  "fields": [
+      {"name": "intField",    "type": "int"},
+      {"name": "longField",   "type": "long"},
+      {"name": "stringField", "type": "string"},
+      {"name": "boolField",   "type": "boolean"},
+      {"name": "floatField",  "type": "float"},
+      {"name": "doubleField", "type": "double"},
+      {"name": "bytesField",  "type": "bytes"},
+      {"name": "nullField",   "type": "null"},
+      {"name": "arrayField",  "type": {"type": "array", "items": "double"}},
+      {"name": "mapField",    "type":
+        { "type": "map", "values":
+           { "name": "Foo",
+             "type": "record",
+             "fields": [{"name": "label", "type": "string"}]}
+        }},
+      {"name": "unionField", "type":
+         ["boolean", "double", {"type": "array", "items": "bytes"}] },
+      {"name": "enumField", "type":
+         {"name": "Kind", "type": "enum", "symbols": ["A","B","C"]} },
+      {"name": "fixedField", "type":
+         {"name": "MD5", "type": "fixed", "size": 16} },
+      {"name": "recordField", "type":
+       {"name": "Node", "type": "record", 
+        "fields": [
+            {"name": "label", "type": "string"},
+            {"name": "children", "type": {"type": "array", "items": "Node"}}]}}
+  ]
+}

data/examples/avro_examples/mail.avpr

@@ -0,0 +1,20 @@
+{"namespace": "org.apache.avro.test",
+ "protocol": "Mail",
+
+ "types": [
+     {"name": "Message", "type": "record",
+      "fields": [
+          {"name": "to",   "type": "string"},
+          {"name": "from", "type": "string"},
+          {"name": "body", "type": "string"}
+      ]
+     }
+ ],
+
+ "messages": {
+     "send": {
+         "request": [{"name": "message", "type": "Message"}],
+         "response": "string"
+     }
+ }
+}

data/examples/avro_examples/namespace.avpr

@@ -0,0 +1,28 @@
+{"namespace": "org.apache.avro.test.namespace",
+ "protocol": "TestNamespace",
+
+ "types": [
+     {"name": "org.apache.avro.test.util.MD5", "type": "fixed", "size": 16},
+     {"name": "TestRecord", "type": "record",
+      "fields": [ {"name": "hash", "type": "org.apache.avro.test.util.MD5"} ]
+     },
+     {"name": "TestError", "namespace": "org.apache.avro.test.errors",
+      "type": "error", "fields": [ {"name": "message", "type": "string"} ]
+     }
+ ],
+
+ "messages": {
+     "echo": {	
+         "request": [{"name": "record", "type": "TestRecord"}],
+         "response": "TestRecord"
+     },
+
+     "error": {
+         "request": [],
+         "response": "null",
+         "errors": ["org.apache.avro.test.errors.TestError"]
+     }
+
+ }
+
+}

data/examples/avro_examples/org/apache/avro/ipc/HandshakeRequest.avsc

@@ -0,0 +1,11 @@
+{
+    "name": "HandshakeRequest", "namespace":"org.apache.avro.ipc",
+    "type": "record",    
+    "fields": [
+        {"name": "clientHash",
+	 "type": {"name": "MD5", "type": "fixed", "size": 16}},
+        {"name": "clientProtocol", "type": ["null", "string"]},
+        {"name": "serverHash", "type": "MD5"},
+ 	{"name": "meta", "type": ["null", {"type": "map", "values": "bytes"}]}
+ ]
+}

data/examples/avro_examples/org/apache/avro/ipc/HandshakeResponse.avsc

@@ -0,0 +1,15 @@
+{
+    "name": "HandshakeResponse", "namespace": "org.apache.avro.ipc",
+    "type": "record",
+    "fields": [
+        {"name": "match",
+         "type": {"name": "HandshakeMatch", "type": "enum", 
+                  "symbols": ["BOTH", "CLIENT", "NONE"]}},
+        {"name": "serverProtocol",
+         "type": ["null", "string"]},
+        {"name": "serverHash",
+         "type": ["null", {"name": "MD5", "type": "fixed", "size": 16}]},
+ 	{"name": "meta",
+         "type": ["null", {"type": "map", "values": "bytes"}]}
+    ]
+}

data/examples/avro_examples/org/apache/avro/ipc/trace/avroTrace.avdl

@@ -0,0 +1,64 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+/**
+ * A Span is our basic unit of tracing. It tracks the critical points
+ * of a single RPC call and records other call meta-data. It also
+ * allows arbitrary string annotations. Both the client and server create
+ * Span objects, each of which is populated with half of the relevant event
+ * data. They share a span ID, which allows us to merge them into one complete
+ * span later on.
+ */
+@namespace("org.apache.avro.ipc.trace")
+
+protocol AvroTrace {
+  enum SpanEvent { SERVER_RECV, SERVER_SEND, CLIENT_RECV, CLIENT_SEND }
+
+  fixed ID(8);
+
+  record TimestampedEvent {
+    long timeStamp; // Unix time, in nanoseconds
+    union { SpanEvent, string} event;
+  }
+
+  record Span {
+    ID  traceID;  // ID shared by all Spans in a given trace
+    ID spanID;    // Random ID for this Span
+    union { ID, null } parentSpanID; // Parent Span ID (null if root Span)
+    string messageName;       // Function call represented
+    long requestPayloadSize;  // Size (bytes) of the request
+    long responsePayloadSize; // Size (byts) of the response
+    union { string, null} requestorHostname; // Hostname of requestor
+//    int requestorPort;     // Port of the requestor (currently unused)
+    union { string, null } responderHostname; // Hostname of the responder
+//    int responderPort;     // Port of the responder (currently unused)
+    array<TimestampedEvent> events;  // List of critical events
+    boolean complete; // Whether includes data from both sides
+  }
+
+  /**
+   * Get all spans stored on this host.
+   */
+  array<Span> getAllSpans();
+
+  /**
+   * Get spans occuring between start and end. Each is a unix timestamp
+   * in nanosecond units (for consistency with TimestampedEvent).
+   */
+  array<Span> getSpansInRange(long start, long end);
+}