azure_search 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: bc148b6807b2928ac0842c5f0839cad1375fa433
+  data.tar.gz: b696a4ceb1c8a277e5bd9639b8fc326ffbfd32cf
+SHA512:
+  metadata.gz: 7f8441c96cae85be15a736906bb1a31c489e201fb20318bdb09107369494ef9bf55d9f23fc657ee97e083b79f5cd921cf5a049fa92c5dbdb4656d2d8b8623a52
+  data.tar.gz: 03f9bfa8c10d7c189620dc21928c995613426f89f6d126d757e27d94c61b7efdeb77b4502e4e13d58786b6be94ca9b5361414bc4d452a0ffbe6535eb845a8942

data/lib/azure_search.rb

@@ -0,0 +1,7 @@
+require 'azure_search/utils'
+require 'azure_search/errors'
+require 'azure_search/version'
+require 'azure_search/index_field'
+require 'azure_search/search_index_client'
+require 'azure_search/index_search_options'
+require 'azure_search/index_batch_operation'

data/lib/azure_search/errors.rb

@@ -0,0 +1,26 @@
+module AzureSearch
+
+  # Defines errors that are raised by AzureSearch client.
+  #
+  # @since 0.1.0
+  module Errors
+
+    # Raised to indicate that a HTTP request needs to be retried.
+    class RetriableHttpError < StandardError
+      # @return [Symbol] The response status code.
+      attr_accessor :code
+      # @return [Symbol] The error message.
+      attr_accessor :message
+
+      def initialize(code, message)
+        self.code = code
+        self.message = message
+      end
+
+      def to_s
+        "RetriableHttpError <#{self.code}>: #{self.message}"
+      end
+    end
+
+  end
+end

data/lib/azure_search/index_batch_operation.rb

@@ -0,0 +1,59 @@
+require 'json'
+
+module AzureSearch
+
+  # Represents a batch operation in an indexing request.
+  class IndexBatchOperation
+    # Encapsulates the supplied document in an IndexUploadOperation.
+    #
+    # @param [Hash] document The document.
+    # @return [Hash] The upload operation as a Hash.
+    def self.upload(document)
+      IndexUploadOperation.new(document).to_hash
+    end
+
+    # Encapsulates a delete request in an IndexDeleteOperation.
+    #
+    # @param [String] key_name The key name.
+    # @param [String] key_value The key value.
+    def self.delete(key_name, key_value)
+      IndexDeleteOperation.new(key_name, key_value).to_hash
+    end
+
+    # @todo Add support for merge & merge_or_upload
+  end
+
+  # Represents an upload operation of a document.
+  class IndexUploadOperation < IndexBatchOperation
+    def initialize(document)
+      @document = document
+    end
+
+    # Returns the upload operation as a Hash.
+    #
+    # @return [Hash] The upload operation.
+    def to_hash
+      @document["@search.action"] = "upload"
+      @document
+    end
+  end
+
+  # Represents a document deletion request.
+  class IndexDeleteOperation < IndexBatchOperation
+    def initialize(key_name, key_value)
+      @key_name = key_name
+      @key_value = key_value
+    end
+
+    # Returns the delete operation as a Hash.
+    #
+    # @return [Hash] The delete operation.
+    def to_hash
+      {
+        @key_name => @key_value,
+        "@search_action" => "delete"
+      }
+    end
+  end
+
+end

data/lib/azure_search/index_field.rb

@@ -0,0 +1,104 @@
+module AzureSearch
+
+  # Represents an Index field definition.
+  class IndexField
+    # Valid EDM (Entity Data Model) data types.
+    VALID_EDM_TYPES = [
+      "Edm.String",
+      "Collection(Edm.String)",
+      "Edm.Boolean",
+      "Edm.Int32",
+      "Edm.Int64",
+      "Edm.Double",
+      "Edm.DateTimeOffset",
+      "Edm.GeographyPoint"
+    ].freeze
+
+    def initialize(name, type)
+      raise "Field name is required." unless !name.empty?
+      @name = name
+      raise "Invalid field type." unless VALID_EDM_TYPES.include? type
+      @type = type
+    end
+
+    # Sets the analyzer name used for search and indexing.
+    #
+    # @param [String] analyzer The analyzer name.
+    # @return [self] The current instance.
+    def analyzer(analyzer)
+      @analyzer = analyzer
+      self
+    end
+
+    # Sets the field to be searchable.
+    #
+    # @param [TrueClass,FalseClass] searchable true or false.
+    # @return [self] The current instance.
+    def searchable(searchable)
+      raise "searchable must be a boolean." unless is_bool? searchable
+      @searchable = searchable
+      self
+    end
+
+    # Sets the field to be filterable.
+    #
+    # @param [TrueClass,FalseClass] filterable true or false.
+    # @return [self] The current instance.
+    def filterable(filterable)
+      raise "filterable must be a boolean." unless is_bool? filterable
+      @filterable = filterable
+      self
+    end
+
+    # Sets the field to be retrievable.
+    #
+    # @param [TrueClass,FalseClass] retrievable true or false.
+    # @return [self] The current instance.
+    def retrievable(retrievable)
+      raise "retrievable must be a boolean." unless is_bool? retrievable
+      @retrievable = retrievable
+      self
+    end
+
+    # Sets the field to be sortable.
+    #
+    # @param [TrueClass,FalseClass] sortable true or false.
+    # @return [self] The current instance.
+    def sortable(sortable)
+      raise "sortable must be a boolean." unless is_bool? sortable
+      @sortable = sortable
+      self
+    end
+
+    # Sets the field to be facetable.
+    #
+    # @param [TrueClass,FalseClass] facetable true or false.
+    # @return [self] The current instance.
+    def facetable(facetable)
+      raise "facetable must be a boolean." unless is_bool? facetable
+      @facetable = facetable
+      self
+    end
+
+    # Sets the field to be the key (Only Edm.String fields can be keys).
+    #
+    # @param [TrueClass,FalseClass] key true or false.
+    # @return [self] The current instance.
+    def key(key)
+      raise "key must be a boolean." unless is_bool? key
+      raise "Only Edm.String fields can be keys." unless @type == "Edm.String"
+      @key = key
+      self
+    end
+
+    # Converts this IndexField to a Hash.
+    #
+    # @return [Hash] Hash representation of IndexField.
+    def to_hash
+      hash = {}
+      instance_variables.each {|var| hash[var.to_s.delete("@")] = instance_variable_get(var) }
+      hash
+    end
+  end
+
+end

data/lib/azure_search/index_search_options.rb

@@ -0,0 +1,177 @@
+require 'azure_search/utils'
+
+module AzureSearch
+
+  # Represents search options that will be sent along with a search request.
+  class IndexSearchOptions
+    SPECIAL_PARAMS = %w(count filter orderby select top skip).freeze
+
+    # Specifies whether to fetch the total count of results.
+    #
+    # @param [TrueClass,FalseClass] val true or false.
+    # @return [self] the current instance.
+    def include_count(val)
+      raise "include_count requires a boolean value." unless is_bool?(val)
+      @count = val
+      self
+    end
+
+    # Sets the structured search expression in standard OData syntax.
+    #
+    # @param [String] val The filter expression.
+    # @return [self] The current instance.
+    def filter(val)
+      raise "filter requires a String." unless val.is_a? String
+      @filter = val
+      self
+    end
+
+    # Sets the list of comma-separated expressions to sort the results by.
+    #
+    # @param [String] val Comma-separated expressions.
+    # @return [self] The current instance.
+    def order_by(val)
+      raise "order_by requires a String." unless val.is_a? String
+      @orderby = val
+      self
+    end
+
+    # Sets the list of comma-separated fields to retrieve.
+    #
+    # @param [String] val Comma-separated fields.
+    # @return [self] The current instance.
+    def select(val)
+      raise "select requires a String." unless val.is_a? String
+      @select = val
+      self
+    end
+
+    # Sets the list of comma-separated field names to search for the specified text.
+    #
+    # @param [String] val Comma-separated field names.
+    # @return [self] The current instance.
+    def search_fields(val)
+      raise "search_fields requires a String." unless val.is_a? String
+      @searchFields = val
+      self
+    end
+
+    # Sets the list of fields to facet by.
+    #
+    # @param [Array] fs The list of fields.
+    # @return [self] The current instance.
+    def facets(fs)
+      raise "facts requires an Array of Strings." unless fs.is_a? Array
+      @facet = fs
+      self
+    end
+
+    # Sets the set of comma-separated field names used for hit highlights.
+    #
+    # @param [String] hl Comma-separated field names.
+    # @return [self] The current instance.
+    def highlight(hl)
+      raise "highlight requires a String." unless hl.is_a? String
+      @highlight = hl
+      self
+    end
+
+    # Sets the string tag that appends to hit highlights (defaults to <em>).
+    #
+    # @param [String] hpt The string tag.
+    # @return [self] The current instance.
+    def highlight_pre_tag(hpt)
+      raise "highlight_pre_tag requires an HTML string." unless has_html?(hpt)
+      @highlightPreTag = hpt
+      self
+    end
+
+    # Sets the string tag that appends to hit highlights (defaults to </em>).
+    #
+    # @param [String] hpt The string tag.
+    # @return [self] The current instance.
+    def highlight_post_tag(hpt)
+      raise "highlight_post_tag requires an HTML string." unless has_html?(hpt)
+      @highlightPostTag = hpt
+      self
+    end
+
+    # Sets the name of a scoring profile to evaluate match scores for matching documents.
+    #
+    # @param [String] sp The scoring profile name.
+    # @return [self] The current instance.
+    def scoring_profile(sp)
+      raise "scoring_profile requires a String." unless sp.is_a? String
+      @scoringProfile = sp
+      self
+    end
+
+    # Sets the values for each parameter defined in a scoring function.
+    #
+    # @param [Array] params The parameters values.
+    # @return [self] The current instance.
+    def scoring_parameters(params)
+      raise "scoring_parameters requires an Array of Strings." unless params.is_a? Array
+      @scoringParameter = params
+      self
+    end
+
+    # Sets the number of search results to retrieve (defaults to 50).
+    #
+    # @param [Integer] val The number of search results.
+    # @return [self] The current instance.
+    def top(val)
+      raise "top requires an Integer." unless val.is_a? Integer
+      @top = val
+      self
+    end
+
+    # Sets the number of search results to skip.
+    #
+    # @param [Integer] val The number to skip (cannot be greater than 100,000).
+    # @return [self] The current instance.
+    def skip(val)
+      raise "skip requires an Integer." unless val.is_a? Integer
+      @skip = val
+      self
+    end
+
+    # Specifies whether any or all of the search terms must be matched.
+    #
+    # @param [String] mode The search mode.
+    # @return [self] The current instance.
+    def search_mode(mode)
+      raise "invalid search mode." unless ["any", "all"].include? mode
+      @searchMode = mode
+      self
+    end
+
+    # Sets the percentage of the index that must be covered by a search query.
+    #
+    # @param [Float] val The percentage (must be between 0 and 100).
+    # @return [self] The current instance.
+    def minimum_coverage(val)
+      raise "minimum_coverage requires a Float." unless val.is_a? Float
+      raise "minimum_coverage must be between 0 and 100" unless val.between?(0, 100)
+      @minimumCoverage = val
+      self
+    end
+
+    # Returns the search options as a Hash.
+    #
+    # @return [Hash] The search options as a Hash.
+    def to_hash
+      hash = {}
+      instance_variables.each {|var|
+        varname = var.to_s.delete("@")
+        if SPECIAL_PARAMS.include? varname
+          hash["$"+varname] = instance_variable_get(var)
+        else
+          hash[varname] = instance_variable_get(var)
+        end
+      }
+      hash
+    end
+  end
+
+end

data/lib/azure_search/search_index_client.rb

@@ -0,0 +1,169 @@
+require 'azure_search/index_search_options'
+require 'azure_search/errors'
+require 'azure_search/utils'
+require 'http'
+
+# Core module common across the entire API.
+#
+# @author Faissal Elamraoui
+# @since 0.1.0
+module AzureSearch
+  API_VERSION = "2016-09-01".freeze
+
+  # Client to perform requests to an Azure Search service.
+  class SearchIndexClient
+    include AzureSearch::Errors
+
+    # @return [Symbol] The search service name.
+    attr_accessor :service_name
+    # @return [Symbol] The index name.
+    attr_accessor :index_name
+    # @return [Symbol] The API key generated for the provisioned Search service.
+    attr_accessor :api_key
+
+    def initialize(service_name, index_name, api_key)
+      if service_name.empty? || index_name.empty? || api_key.empty?
+        raise StandardError, "Must provide service_name, index_name and api_key when creating client."
+      end
+
+      self.service_name = service_name
+      self.index_name = index_name
+      self.api_key = api_key
+    end
+
+    # Checks if the specified index exists.
+    #
+    # @return [TrueClass,FalseClass] true if the index exists, false otherwise.
+    def exists
+      resp = create_request().get(build_index_definition_url())
+      if resp.code == 404
+        return false
+      end
+      raise_on_http_error(resp)
+      return true
+    end
+
+    # Creates the index based on the provided index definition.
+    #
+    # @param [Hash] definition The index definition.
+    # @option definition [String] :name The index name.
+    # @option definition [Array<IndexField>] :fields Array of fields.
+    # @option definition [Array] :suggesters Array of suggesters.
+    def create(definition)
+      raise "Index definition must be a Hash." unless definition.is_a? Hash
+      definition[:name] = self.index_name unless !definition[:name]
+      resp = create_request().post(build_index_list_url(), :json => definition)
+      raise_on_http_error(resp)
+      return JSON.parse(resp.to_s)
+    end
+
+    # Creates or updates the index based on the provided index definition.
+    #
+    # @param [Hash] definition The index definition.
+    # @option definition [String] :name The index name.
+    # @option definition [Array<IndexField>] :fields Array of fields.
+    # @option definition [Array] :suggesters Array of suggesters.
+    def create_or_update(definition)
+      raise "Index definition must be a Hash." unless definition.is_a? Hash
+      definition[:name] = self.index_name unless definition[:name]
+      resp = create_request().put(build_index_definition_url(), :json => definition)
+      raise_on_http_error(resp)
+      return resp.to_s.empty? ? nil : JSON.parse(resp.to_s)
+    end
+
+    # Deletes the specified index.
+    #
+    # @return [TrueClass,FalseClass] true if the index is deleted, false otherwise.
+    def delete
+      resp = create_request().delete(build_index_definition_url())
+      if resp.code == 404
+        return false
+      end
+      raise_on_http_error(resp)
+      return true
+    end
+
+    # Inserts documents in batch.
+    #
+    # @param [Array<IndexBatchOperation>] operations Array of upload operations.
+    # @param [Integer] chunk_size The batch size. Must not exceed 1000 documents.
+    def batch_insert(operations, chunk_size=1000)
+      raise "Batch request must not exceed 1000 documents." unless chunk_size <= 1000
+      operations.each_slice(chunk_size)
+               .to_a
+               .each{|op|
+                 resp = create_request().post(build_indexing_url(), :json => {:value => op})
+                 raise_on_http_error(resp)
+                 resp.to_s
+               }
+    end
+
+    # Search the index for the supplied text.
+    #
+    # @param [String] text The text to search for.
+    # @param [IndexSearchOptions] options Options to configure the search request.
+    #
+    # @return [Hash] Parsed JSON response.
+    def search(text, options)
+      resp = create_request().get(build_index_search_url(text, options))
+      raise_on_http_error(resp)
+      return JSON.parse(resp.to_s)
+    end
+
+    # Lookup an indexed document by key.
+    #
+    # @param [String] key The key.
+    # @return [Hash] The document identified by the supplied key.
+    def lookup(key)
+      resp = create_request().get(build_index_lookup_url(key))
+      raise_on_http_error(resp)
+      doc = JSON.parse(resp.to_s)
+      doc.delete("@odata.context")
+      return doc
+    end
+
+    private
+    def build_index_definition_url
+      "https://#{self.service_name}.search.windows.net/indexes/#{self.index_name}?api-version=#{API_VERSION}"
+    end
+
+    def build_index_list_url
+      "https://#{self.service_name}.search.windows.net/indexes?api-version=#{API_VERSION}"
+    end
+
+    def build_indexing_url
+      "https://#{self.service_name}.search.windows.net/indexes/#{self.index_name}/docs/index?api-version=#{API_VERSION}"
+    end
+
+    def build_index_search_url(text, options)
+      query = {"search" => URI.encode_www_form_component(text)}.merge(options.to_hash)
+      "https://#{self.service_name}.search.windows.net/indexes/#{self.index_name}/docs?api-version=#{API_VERSION}&" << to_query_string(query)
+    end
+
+    def build_index_lookup_url(key)
+      "https://#{self.service_name}.search.windows.net/indexes/#{self.index_name}/docs('#{key}')?api-version=#{API_VERSION}"
+    end
+
+    def create_request
+      HTTP.headers({
+        "Content-Type" => "application/json",
+        "api-key" => self.api_key
+      })
+    end
+
+    def raise_on_http_error(response)
+      status_code = response.code
+      if status_code > 399
+        # 503 means the server is asking for backoff + retry
+        if status_code == 503
+          raise RetriableHttpError.new(status_code, response.to_s)
+        else
+          raise StandardError, "#{response.to_s}"
+        end
+      end
+    end
+
+    def validate_search_option(options)
+    end
+  end
+end

data/lib/azure_search/utils.rb

@@ -0,0 +1,41 @@
+require 'nokogiri'
+
+module AzureSearch
+
+  # Checks if the supplied value is a Boolean.
+  #
+  # @param [Object] value The value to check.
+  # @return [TrueClass,FalseClass] true or false.
+  def is_bool?(value); [true, false].include? value end
+
+  # Checks if the supplied text contains valid HTML.
+  #
+  # @param [String] text The text to check.
+  # @return [TrueClass,FalseClass] true or false.
+  def has_html?(text); Nokogiri::XML(text).errors.empty? end
+
+  # Converts a Hash into query parameters string.
+  #
+  # @param [Hash] params The hash to convert.
+  # @return [String] query string.
+  def to_query_string(params)
+    params.map{|k,v|
+      if v.nil?
+        k.to_s
+      elsif v.respond_to?(:to_ary)
+        v.to_ary.map{|w|
+          str = k.to_s.dup
+          unless w.nil?
+            str << '='
+            str << w.to_s
+          end
+        }.join('&')
+      else
+        str = k.to_s.dup
+        str << '='
+        str << v.to_s
+      end
+    }.join('&')
+  end
+
+end

data/lib/azure_search/version.rb

@@ -0,0 +1,3 @@
+module AzureSearch
+  VERSION = "0.1.0".freeze
+end

metadata

@@ -0,0 +1,123 @@
+--- !ruby/object:Gem::Specification
+name: azure_search
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Faissal Elamraoui
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2017-05-24 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: http
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.2'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.2'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.7'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.7'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.15'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.15'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '12.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '12.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.6'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.6'
+description: This library allows you to interact with Microsoft Azure Search using
+  Ruby.
+email:
+- amr.faissal@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/azure_search.rb
+- lib/azure_search/errors.rb
+- lib/azure_search/index_batch_operation.rb
+- lib/azure_search/index_field.rb
+- lib/azure_search/index_search_options.rb
+- lib/azure_search/search_index_client.rb
+- lib/azure_search/utils.rb
+- lib/azure_search/version.rb
+homepage: https://github.com/amrfaissal/azuresearch-ruby-client.git
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.11
+signing_key: 
+specification_version: 4
+summary: Microsoft Azure Search Client Library for Ruby.
+test_files: []