clickhouse 0.1.0 → 0.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c0be7eb44c6eed3df458e031647a9cad1bc40181
-  data.tar.gz: 724c2dbce96c466eaad983d720f7da01a899571d
+  metadata.gz: 382f431988af06b9879728821c0c002676cb930d
+  data.tar.gz: 7fc6c4674ef83c45989bd8d3759ad85629beecee
 SHA512:
-  metadata.gz: 2c2e727bbcffefa01ae315b19cddbddf6050afefaf82f8b5379496d79ba7add71e5aa0fed8b977c2d8fd012a12affbf7179654cd3fe61fac99d49222fb9820b7
-  data.tar.gz: 5893a3e5919b5d19779f4ffd35f3858a10b33e6e2b7eb9510501d9c7e528be01c256890c53d92d329856e0b85fcb36d9a7398a21840c2472df1939a1fb9345d2
+  metadata.gz: 83868f46b3dbbd9e977c6ac14a4badf252f9cc213cfbab9545a777ff241003357bd90241bbea1cedd58871457e0a4c43598385839a827e1815a897848bc5bcab
+  data.tar.gz: 39d8d2ab4a094e5e5f7b3d269d40d6fad75619fd97a3bee5c04b7bd766eff2096398a5c798fad6cf29d6ee0bafbe33d908cd7068e5c0a98e68c37a051d9a79f5

data/CHANGELOG.md

@@ -1,5 +1,13 @@
 ## Clickhouse CHANGELOG
 
+### Version 0.1.1 (October 19, 2016)
+
+* Using the JSONCompact format as query output which does not brake when having a JSON string within the data
+* Ensuring that Clickhouse::Connection::Query#count return an integer
+* Made Clickhouse::Connection::Query#to_select_query public
+* Being able to pass strings as :where or :having option
+* Being able to symbolize the row to hash parsing
+
 ### Version 0.1.0 (October 18, 2016)
 
 * Initial release

data/README.md

@@ -17,6 +17,14 @@ Well, the developers of Clickhouse themselves [discourage](https://github.com/ya
 > TCP transport is more specific, we don't want to expose details.
 Despite we have full compatibility of protocol of different versions of client and server, we want to keep the ability to "break" it for very old clients. And that protocol is not too clean to make a specification.
 
+### Why use the JSONCompact format and not the native format?
+
+Despite of it being the most efficient format, using the native format is also [discouraged] by the Clickhouse developers.
+
+> The most efficient format. Data is written and read by blocks in binary format. For each block, the number of rows, number of columns, column names and types, and parts of columns in this block are recorded one after another. In other words, this format is "columnar" - it doesn't convert columns to rows. This is the format used in the native interface for interaction between servers, for using the command-line client, and for C++ clients.
+>
+> You can use this format to quickly generate dumps that can only be read by the ClickHouse DBMS. It doesn't make sense to work with this format yourself.
+
 ## Installation
 
 Run the following command to install `Clickhouse`:

data/VERSION

@@ -1 +1 @@
-0.1.0
+0.1.1

data/lib/clickhouse/connection/query.rb

@@ -13,7 +13,7 @@ module Clickhouse
 
       def query(query)
         query = query.to_s.gsub(/(;|\bFORMAT \w+)/i, "").strip
-        query += " FORMAT TabSeparatedWithNamesAndTypes"
+        query += " FORMAT JSONCompact"
         parse_response get(query).body.to_s
       end
 
@@ -70,7 +70,20 @@ module Clickhouse
       end
 
       def count(options)
-        select_value options.merge(:select => "COUNT(*)")
+        options = options.merge(:select => "COUNT(*)")
+        select_value(options).to_i
+      end
+
+      def to_select_query(options)
+        to_select_options(options).collect do |(key, value)|
+          next if value.nil? || (value.respond_to?(:empty?) && value.empty?)
+
+          statement = [key.to_s.upcase]
+          statement << "BY" if %W(GROUP ORDER).include?(statement[0])
+          statement << to_segment(key, value)
+          statement.join(" ")
+
+        end.compact.join("\n").force_encoding("UTF-8")
       end
 
     private
@@ -111,7 +124,7 @@ module Clickhouse
         when :select
           [value].flatten.join(", ")
         when :where, :having
-          to_condition_statements(value)
+          value.is_a?(Hash) ? to_condition_statements(value) : value
         else
           value
         end
@@ -136,23 +149,11 @@ module Clickhouse
         end.flatten.join(" AND ")
       end
 
-      def to_select_query(options)
-        to_select_options(options).collect do |(key, value)|
-          next if value.nil? && (!value.respond_to?(:empty?) || value.empty?)
-
-          statement = [key.to_s.upcase]
-          statement << "BY" if %W(GROUP ORDER).include?(statement[0])
-          statement << to_segment(key, value)
-          statement.join(" ")
-
-        end.compact.join("\n").force_encoding("UTF-8")
-      end
-
       def parse_response(response)
-        rows = CSV.parse response, :col_sep => "\t"
-        names = rows.shift
-        types = rows.shift
-        ResultSet.new rows, names, types
+        data = JSON.parse response
+        names = data["meta"].collect{|column| column["name"]}
+        types = data["meta"].collect{|column| column["type"]}
+        ResultSet.new data["data"], names, types
       end
 
     end

data/lib/clickhouse/connection/query/result_row.rb

@@ -5,11 +5,29 @@ module Clickhouse
 
         def initialize(values = [], keys = nil)
           super values
-          @keys = keys || (0..(values.size - 1)).collect{|i| "column#{i}"}
+          @keys = normalize_keys(keys)
         end
 
-        def to_hash
-          @hash ||= Hash[@keys.zip(self)]
+        def to_hash(symbolize = false)
+          @hash ||= begin
+            keys = symbolize ? @keys.collect(&:to_sym) : @keys
+            Hash[keys.zip(self)]
+          end
+        end
+
+      private
+
+        def normalize_keys(keys)
+          if keys
+            keys.collect do |key|
+              key.match(/^any\(([^\)]+)\)$/)
+              $1 || key
+            end
+          else
+            (0..(size - 1)).collect do |index|
+              "column#{index}"
+            end
+          end
         end
 
       end

data/lib/clickhouse/connection/query/result_set.rb

@@ -31,8 +31,8 @@ module Clickhouse
           !empty?
         end
 
-        def to_hashes
-          collect(&:to_hash)
+        def to_hashes(symbolize = false)
+          collect{|row| row.to_hash(symbolize)}
         end
 
       private
@@ -92,7 +92,7 @@ module Clickhouse
         end
 
         def parse_array_value(value)
-          JSON.parse(value)
+          value
         end
 
       end

data/lib/clickhouse/version.rb

@@ -1,7 +1,7 @@
 module Clickhouse
   MAJOR = 0
   MINOR = 1
-  TINY  = 0
+  TINY  = 1
 
   VERSION = [MAJOR, MINOR, TINY].join(".")
 end

data/test/unit/connection/query/test_result_set.rb

@@ -17,7 +17,7 @@ module Unit
                   "d91d1c90\u0000\u0000\u0000",
                   "2016-03-20",
                   "2016-03-20 23:49:11",
-                  "[4,2,5,7]"
+                  [4, 2, 5, 7]
                 ], [
                   "12948140",
                   "9320.11",
@@ -25,7 +25,7 @@ module Unit
                   "d91d217c\u0000\u0000",
                   "2016-03-20",
                   "2016-03-20 23:58:34",
-                  "[6,2,9,8,1]"
+                  [6, 2, 9, 8, 1]
                 ], [
                   "319384",
                   "101.02",
@@ -33,7 +33,7 @@ module Unit
                   "d91d2294\u0000\u0000\u0000",
                   "2016-03-20",
                   "2016-03-20 22:55:39",
-                  "[3,1,2]"
+                  [3, 1, 2]
                 ]
               ],
               %w(

data/test/unit/connection/test_query.rb

@@ -30,21 +30,24 @@ module Unit
 
         describe "#query" do
           it "sends a GET request requesting a TSV response including names and types" do
-            @connection.expects(:get).with("sql FORMAT TabSeparatedWithNamesAndTypes").returns(stub(:status => 200, :body => ""))
+            @connection.expects(:get).with("sql FORMAT JSONCompact").returns(stub(:status => 200, :body => ""))
+            @connection.stubs(:parse_response)
             assert_equal [], @connection.query("sql").to_a
           end
         end
 
         describe "#databases" do
           it "sends a 'SHOW DATABASES' query" do
-            @connection.expects(:get).with("SHOW DATABASES FORMAT TabSeparatedWithNamesAndTypes").returns(stub(:status => 200, :body => ""))
+            @connection.expects(:get).with("SHOW DATABASES FORMAT JSONCompact").returns(stub(:status => 200, :body => "{}"))
+            @connection.stubs(:parse_response).returns([])
             @connection.databases
           end
         end
 
         describe "#tables" do
           it "sends a 'SHOW TABLES' query" do
-            @connection.expects(:get).with("SHOW TABLES FORMAT TabSeparatedWithNamesAndTypes").returns(stub(:status => 200, :body => ""))
+            @connection.expects(:get).with("SHOW TABLES FORMAT JSONCompact").returns(stub(:status => 200, :body => "{}"))
+            @connection.stubs(:parse_response).returns([])
             @connection.tables
           end
         end
@@ -77,7 +80,8 @@ ENGINE = MergeTree(date, 8192)
 
         describe "#describe_table" do
           it "sends a 'DESCRIBE TABLE <name>' query" do
-            @connection.expects(:get).with("DESCRIBE TABLE logs FORMAT TabSeparatedWithNamesAndTypes").returns(stub(:status => 200, :body => ""))
+            @connection.expects(:get).with("DESCRIBE TABLE logs FORMAT JSONCompact").returns(stub(:status => 200, :body => ""))
+            @connection.stubs(:parse_response)
             @connection.describe_table("logs")
           end
         end
@@ -150,15 +154,21 @@ ENGINE = MergeTree(date, 8192)
 
         describe "#select_rows" do
           it "sends a GET request and parses the result set" do
-            body = <<-TSV
-              year\tname
-              UInt16\tString
-              1982\tPaul
-              1947\tAnna
-            TSV
+            body = <<-JAVASCRIPT
+              {
+                "meta": [
+                  {"name": "year", "type": "UInt16"},
+                  {"name": "name", "type": "String"}
+                ],
+                "data": [
+                  [1982, "Paul"],
+                  [1947, "Anna"]
+                ]
+              }
+            JAVASCRIPT
 
             @connection.expects(:to_select_query).with(options = {:from => "logs"})
-            @connection.expects(:get).returns(stub(:body => body.gsub(/^\s+/, "")))
+            @connection.expects(:get).returns(stub(:body => body))
 
             assert_equal [
               [1982, "Paul"],
@@ -179,21 +189,28 @@ ENGINE = MergeTree(date, 8192)
             it "returns an empty array" do
               @connection.expects(:to_select_query)
               @connection.expects(:get).returns(stub(:body => ""))
+              @connection.stubs(:parse_response).returns([])
               assert_equal [], @connection.select_values({})
             end
           end
 
           describe "when getting data" do
             it "returns every first value of every row" do
-              body = <<-TSV
-                year\tname
-                UInt16\tString
-                1982\tPaul
-                1947\tAnna
-              TSV
+              body = <<-JAVASCRIPT
+                {
+                  "meta": [
+                    {"name": "year", "type": "UInt16"},
+                    {"name": "name", "type": "String"}
+                  ],
+                  "data": [
+                    [1982, "Paul"],
+                    [1947, "Anna"]
+                  ]
+                }
+              JAVASCRIPT
 
               @connection.expects(:to_select_query)
-              @connection.expects(:get).returns(stub(:body => body.gsub(/^\s+/, "")))
+              @connection.expects(:get).returns(stub(:body => body))
               assert_equal [
                 1982,
                 1947

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: clickhouse
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
 platform: ruby
 authors:
 - Paul Engel
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-10-17 00:00:00.000000000 Z
+date: 2016-10-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: faraday