lucid_works 0.7.18 → 0.9.4

data/config/locales/en.yml

@@ -6,140 +6,187 @@ en:
     # and is used by human_attribute_name
     #
     attributes:
-      lucid_works:
-        collection:
-          info:
-            collection_name: Collection name
-            data_dir: Data directory
-            free_disk_bytes: Free disk bytes
-            free_disk_space: Free disk space
-            index_directory: Index directory
-            index_has_deletions: Index has deletions
-            index_is_current: Index is current
-            index_is_optimized: Optimized
-            index_last_modified: Index last modified
-            index_max_doc: Index max doc
-            index_num_docs: Documents indexed
-            index_size: Index size
-            index_size_bytes: Index size
-            index_version: Index version
-            instance_dir: Instance directory
-            root_dir: Root directory
-            total_disk_bytes: Total disk bytes
-            total_disk_space: Total disk space
-          name: Name
-          settings:
-            auto_complete: Auto complete
-            boost_recent: Boost recent
-            boosts: Boosts
-            click_boost_data: Click boost data
-            click_boost_field: Click boost field
-            click_enabled: Click scoring enabled
-            de_duplication: De-duplication
-            default_sort: Default sort
-            display_facets: Display facets
-            elevations: elevations
-            index_time_stopwords: Exclude stop words from index
-            query_parser: Query parser
-            query_time_stopwords: Include stop words in searches
-            query_time_synonyms: Use synonyms
-            search_server_list: Search server list
-            show_similar: Show "find similar" links
-            spellcheck: Spell-check
-            ssl: SSL
-            stopword_list: Stopword list
-            synonym_list: Synonym list
-            unknown_type_handling: Default field type
-            unsupervised_feedback: Unsupervised feedback
-            unsupervised_feedback_emphasis: Unsupervised feedback emphasis
-            update_server_list: Update server list
-        datasource:
-          subtype:
-            web:
-              url: Custom legend for url
-          aliases: Site Aliases Mappings
-          auth: Authentication credentials
-          authorization: Authorization
-          bounds: Constrain to
-          commit_on_finish: Commit when crawl finishes
-          commit_within: Commit within
-          commit_within_min: Commit within (minutes)
-          connector_type: Connector Type
-          deleteAfter: Delete logs after
-          domain: Domain
-          excluded_urls: Excluded URLs
-          fail_unsupported_file_types: Fail unsupported file types
-          history:
-            crawl_started: Started
-            crawl_state: State
-            crawl_stopped: Stopped
-            num_deleted: Deleted
-            num_failed: Failed
-            num_new: New
-            num_unchanged: Unchanged
-            num_updated: Updated
-          host: Domain Name
-          ignore_robots: Ignore robots.txt
-          include_datasource_metadata: Include data source metadata
-          included_urls: Included URLs
-          kdcserver: Kerberos KDC server
-          log_extra_detail: Log extra detail
-          max_bytes: Skip files larger than (bytes)
-          my_site_base_url: MySite URL
-          password: Password
-          proxy_host: Proxy host
-          proxy_password: Proxy password
-          proxy_port: Proxy port
-          proxy_username: Proxy user name
-          realm: Realm
-          sharepoint_url: SharePoint URL
-          status:
-            crawl_started: Last crawl started
-            crawl_state: State
-            crawl_stopped: Last crawl stopped
-            doc_count: Documents indexed
-            job_id: Job ID
-            num_deleted: Deleted docs
-            num_failed: Failed docs
-            num_new: New docs
-            num_total: Total docs
-            num_unchanged: Unchanged docs
-            num_updated: Updated docs
-          type: Type
-          url: URL
-          use_sp_search_visibility: Use SP Search Visibility
-          username: Username
-          warn_unknown_mime_types: Log warnings for unknown mime types
-          windowsdomain: Windows domain
-        field:
-          copy_fields: Copy this field to fields
-          default_boost: Default boost
-          default_value: Default value
-          dynamic_base: Dynamically generated from
-          editable: Editable
-          facet: Facet
-          field_type: Field type
-          highlight: Highlight
-          include_in_results: Include in results
-          index_for_autocomplete: Index for autocomplete
-          index_for_spellcheck: Index for spell checking
-          indexing_options: Index term frequencies and positions
-          indexed: Indexed
-          multi_valued: Multi-valued
-          name: Name
-          omit_positions: Omit positions
-          omit_tf: Omit term frequencies and positions
-          query_time_stopword_handling: Enable stopword handling
-          search_by_default: Search by default
-          short_field_boost: Short field boost
-          stored: Stored
-          synonym_expasion: Enable synonym expansion
-          term_vectors: Term vectors
-          use_for_deduplication: Use for de-duplication
-          use_in_find_similar: Use in 'find similar'
-        fieldtype:
-          name: Name
-          _class: Class
+      collection:
+        name: Name
+        num_shards: Number of shards
+      collection/info:
+        collection_name: Collection name
+        data_dir: Data directory
+        free_disk_bytes: Free disk bytes
+        free_disk_space: Free disk space
+        index_directory: Index directory
+        index_has_deletions: Index has deletions
+        index_is_current: Index is current
+        index_is_optimized: Optimized
+        index_last_modified: Index last modified
+        index_max_doc: Index max doc
+        index_num_docs: Documents indexed
+        index_size: Index size
+        index_size_bytes: Index size
+        index_version: Index version
+        instance_dir: Instance directory
+        root_dir: Root directory
+        total_disk_bytes: Total disk bytes
+        total_disk_space: Total disk space
+      collection/settings:
+        auto_complete: Auto complete
+        boost_recent: Boost recent
+        boosts: Boosts
+        click_boost_data: Click boost data
+        click_boost_field: Click boost field
+        click_enabled: Click scoring enabled
+        de_duplication: De-duplication
+        default_sort: Default sort
+        display_facets: Display facets
+        elevations: elevations
+        index_time_stopwords: Exclude stop words from index
+        main_index_ram_buffer_size_mb: RAM buffer size (MB)
+        main_index_merge_factor: Merge factor
+        query_parser: Query parser
+        query_time_stopwords: Include stop words in searches
+        query_time_synonyms: Use synonyms
+        search_server_list: Search server list
+        show_similar: Show "find similar" links
+        spellcheck: Spell-check
+        ssl: SSL
+        stopword_list: Stopword list
+        synonym_list: Synonym list
+        unknown_type_handling: Default field type
+        unsupervised_feedback: Unsupervised feedback
+        unsupervised_feedback_emphasis: Unsupervised feedback emphasis
+        update_server_list: Update server list
+      datasource:
+        ad_cache_groups: Cache groups
+        ad_credentials: Credentials
+        ad_group_filter: Group filter
+        ad_url: Active Directory URL
+        ad_user_base_dn: User base DN
+        ad_user_filter: User filter
+        ad_user_principal_name: User principal name
+        ad_group_base_dn: Group base DN
+        aliases: Site Aliases Mappings
+        auth: Authentication credentials
+        authorization: Authorization
+        bounds: Constrain to
+        commit_on_finish: Commit when crawl finishes
+        commit_within: Commit within
+        commit_within_sec: Commit within (seconds)
+        connector_type: Connector Type
+        deleteAfter: Delete logs after
+        delta_sql_query: Delta SQL query
+        domain: Domain
+        enable_security_trimming: Enable security trimming
+        excluded_urls: Excluded URLs
+        fail_unsupported_file_types: Fail unsupported file types
+        feed_unpublished_documents: Feed unpublished documents
+        groupname_format_in_ace: Group name format in ACE
+        host: Domain Name
+        ignore_robots: Ignore robots.txt
+        include_datasource_metadata: Include data source metadata
+        included_urls: Included URLs
+        kdcserver: Kerberos KDC server
+        ldap_auth_type: LDAP authentication type
+        ldap_cache_groups_membership: LDAP cache group membership
+        ldap_cache_refresh_interval: LDAP cache refresh interval
+        ldap_cache_size: LDAP cache size
+        ldap_read_groups_type: LDAP read groups type
+        ldap_search_base: LDAP search base
+        ldap_server_host_address: LDAP server host
+        ldap_server_port_number: LDAP server port
+        ldap_server_use_ssl: LDAP server use SSL
+        log_extra_detail: Log extra detail
+        max_bytes: Skip files larger than (bytes)
+        my_site_base_url: MySite URL
+        output_args: Output arguments
+        output_url: Output URL
+        password: Password
+        proxy_host: Proxy host
+        proxy_password: Proxy password
+        proxy_port: Proxy port
+        proxy_username: Proxy user name
+        push_acls: Push ACLs
+        realm: Realm
+        sharepoint_url: SharePoint URL
+        sleep: Sleep (ms)
+        sql_select_statement: SQL SELECT statement
+        type: Type
+        url: URL
+        use_sp_search_visibility: Use SP Search Visibility
+        username: Username
+        username_format_in_ace: Username format in ACE
+        warn_unknown_mime_types: Log warnings for unknown mime types
+        windowsdomain: Windows domain
+      datasource/history:
+        crawl_started: Started
+        crawl_state: State
+        crawl_stopped: Stopped
+        num_deleted: Deleted
+        num_failed: Failed
+        num_new: New
+        num_unchanged: Unchanged
+        num_updated: Updated
+        num_not_found: Not found
+        num_filter_denied: Filter denied
+        num_access_denied: Access denied
+        num_robots_denied: Robots denied
+      datasource/status:
+        crawl_started: Last crawl started
+        crawl_state: State
+        crawl_stopped: Last crawl stopped
+        doc_count: Documents indexed
+        job_id: Job ID
+        num_deleted: Deleted docs
+        num_failed: Failed docs
+        num_new: New docs
+        num_total: Total docs
+        num_unchanged: Unchanged docs
+        num_updated: Updated docs
+        num_not_found: Not found docs
+        num_filter_denied: Filter denied docs
+        num_access_denied: Access denied docs
+        num_robots_denied: Robots denied docs
+      field:
+        copy_fields: Copy this field to fields
+        default_boost: Default boost
+        default_value: Default value
+        dynamic_base: Dynamically generated from
+        editable: Editable
+        facet: Facet
+        field_type: Field type
+        highlight: Highlight
+        include_in_results: Include in results
+        index_for_autocomplete: Index for autocomplete
+        index_for_spellcheck: Index for spell checking
+        indexing_options: Index term frequencies and positions
+        indexed: Indexed
+        multi_valued: Multi-valued
+        name: Name
+        omit_positions: Omit positions
+        omit_tf: Omit term frequencies and positions
+        query_time_stopword_handling: Enable stopword handling
+        search_by_default: Search by default
+        short_field_boost: Short field boost
+        stored: Stored
+        synonym_expasion: Enable synonym expansion
+        term_vectors: Term vectors
+        use_for_deduplication: Use for de-duplication
+        use_in_find_similar: Use in 'find similar'
+      dynamicfield:
+        copy_fields: Copy this field to fields
+        field_type: Field type
+        index_for_autocomplete: Index for autocomplete
+        index_for_spellcheck: Index for spell checking
+        indexing_options: Index term frequencies and positions
+        indexed: Indexed
+        multi_valued: Multi-valued
+        name: Name
+        omit_positions: Omit positions
+        omit_tf: Omit term frequencies and positions
+        stored: Stored
+        term_vectors: Term vectors
+      fieldtype:
+        name: Name
+        _class: Class
     #
     # This section containts two things:
     # Model names wich support ActiveModel <model>.model_name.human
@@ -148,112 +195,47 @@ en:
     # or from class LucidWorks::Base.human_attribute_value(attribute, value)
     #
     models:
-      lucid_works:
-        activity:
-          one: Activity
-          other: Activities
-          type:
-            autocomplete: Generate autocomplete index
-            click: Process click logs
-            optimize: Optimize index
-        collection:
-          one: Collection
-          other: Collections
-          settings:
-            de_duplication:
-              'off': 'Off'
-              overwrite: Overwrite
-              tag: Tag
-            one: Settings
-            other: Settings
-        datasource:
-          one: Data source
-          other: Data sources
-          status:
-            crawl_state:
-              ABORTED: Aborted
-              ABORTING: Aborting
-              EXCEPTION: Exception
-              FINISHED: Finished
-              IDLE: Idle
-              RUNNING: Running
-              STOPPED: Stopped
-              STOPPING: Stopping
-          type:
-            external: External
-            file: File system
-            ftp: FTP
-            hdfs: Hadoop file system
-            jdbc: Database
-            kfs: Kosmos file system
-            lucidworkslogs: LucidWorks Solr Logs
-            s3: Hadoop S3 Block FS
-            s3n: Hadoop S3 Native FS
-            sharepoint: SharePoint
-            smb: Windows Share
-            solrxml: Solr XML
-            web: Web site
-        field:
-          one: Field
-          other: Fields
-          indexing_options:
-            document_only: none
-            document_termfreq: term frequencies
-            document_termfreq_termpos: term frequencies and positions
-        fieldtype:
-          one: Field type
-          other: Field types
-        jdbcdriver:
-          one: JDBC driver
-          other: JDBC drivers
-  #
-  # These hints appear next to fields in SimpleForm forms
-  #
-  simple_form:
-    hints:
+      activity:
+        one: Activity
+        other: Activities
+        type:
+          autocomplete: Generate autocomplete index
+          click: Process click logs
+          optimize: Optimize index
       collection:
-        name: ! 'Collection names may use the characters: A-Z, a-z, 0-9, dash and
-          underscore'
-
+        one: Collection
+        other: Collections
+        settings:
+          de_duplication:
+            'off': 'Off'
+            overwrite: Overwrite
+            tag: Tag
+          one: Settings
+          other: Settings
       datasource:
-        crawl_depth: Leave blank or set to -1 to crawl with no depth limit.
-        exclude_paths: A list of regular expressions, one per line, e.g. .*\.pdf will
-          ignore filenames ending in .pdf.
-        include_paths: A list of regular expressions, one per line.
-        max_bytes: Default = 10 MiB. Set to -1 to indicate no file size limit.
-
-      # Custom datasource hints
-      external_datasource:
-      file_datasource:
-        path: Full pathname to folder
-      ftp_datasource:
-      hdfs_datasource:
-        url: "Please include protocol: hdfs://<hostname>"
-      jdbc_datasource:
-        delta_sql_query: "$ in this query will be replaced by the last successful import time."
-        driver: "Database drivers may be uploaded on the Indexing -> JDBC Drivers page.
-          Drivers are collection specific.
-          JDBC4 drivers will appear in the selector automatically.
-          To use a JDBC3 driver, select \"Other\" and enter the Java class name of the driver."
-        url: "e.g. jdbc:mysql://hostname/database_name"
-      kfs_datasource:
-      lucidworkslogs_datasource:
-      s3_datasource:
-        url: "Please include protocol: s3://<hostname>/path/to/filesystem"
-      s3n_datasource:
-        url: "Please include protocol: s3n://<hostname>/path/to/filesystem"
-      sharepoint_datasource:
-      smb_datasource:
-        url: "Format: smb://<hostname or ip address>/<path to folder>/"
-      solrxml:
-      web_datasource:
-        include_paths: A list of regular expressions, one per line, e.g. http://example\.com/.*
-          will match everything within the site only.
-        url: e.g. http://cnn.com. Please include protocol (http/https).
-
+        one: Data source
+        other: Data sources
+        status:
+          crawl_state:
+            ABORTED: Aborted
+            ABORTING: Aborting
+            EXCEPTION: Exception
+            FINISHED: Finished
+            IDLE: Idle
+            RUNNING: Running
+            STOPPED: Stopped
+            STOPPING: Stopping
+            UNKNOWN: Unknown
       field:
-        copy_fields: A list of fields separated by spaces.
+        one: Field
+        other: Fields
+        indexing_options:
+          document_only: none
+          document_termfreq: term frequencies
+          document_termfreq_termpos: term frequencies and positions
+      fieldtype:
+        one: Field type
+        other: Field types
       jdbcdriver:
-        file: select the jar file of your database driver
-      synonym:
-        mapping: ! 'Example: car, automobile, auto'
+        one: JDBC driver
+        other: JDBC drivers

data/lib/lucid_works/activity.rb

@@ -24,6 +24,7 @@ module LucidWorks
 
     def frequency
       case period
+      when 1.minute.seconds..59.minutes.seconds then 'every'
       when 1.weeks.seconds then 'weekly'
       when 1.days.seconds then 'daily'
       when 1.hours.seconds then 'hourly'
@@ -37,6 +38,7 @@ module LucidWorks
     #
     def frequency=(frequency)
       self.period = case frequency
+      when 'every' then period
       when 'hourly' then 1.hours.seconds.to_i
       when 'daily' then 1.days.seconds.to_i
       when 'weekly' then 1.weeks.seconds.to_i
@@ -50,7 +52,6 @@ module LucidWorks
     #
     def next_start
       return start_time if (now = Time.now) <= start_time 
-      # require 'ruby-debug'; debugger
       time_since_start = now - start_time
       last_interval_num = (time_since_start / period).to_i
       next_interval_num =  if (time_since_start % period) == 0
@@ -104,8 +105,10 @@ module LucidWorks
       self.frequency = all_attributes['frequency']
       self.start_time = 
         case all_attributes['frequency']
+        when 'every'
+          self.period = all_attributes['period'].to_i
+          now.ceil(period)
         when 'weekly'
-          # require 'ruby-debug'; debugger
           start = now.beginning_of_week.advance(all_attributes['start'])
           start < now ? start.advance(:weeks => 1) : start 
         when 'daily'                                                       
@@ -115,7 +118,7 @@ module LucidWorks
           start = now.change(:min => 0).advance(all_attributes['start'])
           start < now ? start.advance(:hours => 1) : start 
         when 'custom'
-          # don't change this activity's start_time
+          # don't change this schedule's start_time
         else
           puts "*** frequency: <#{all_attributes[:frequency]}>"
           raise "unexpected frequency encountered"
@@ -170,8 +173,8 @@ module LucidWorks
       end
     end
 
-    def t_type
-      I18n.t(type, :scope => 'activemodel.models.lucid_works.collection.activity.type')
+    def t_type(i18n_options = {})
+      I18n.t type, {:scope => 'activemodel.models.collection.activity.type'}.merge(i18n_options)
     end
 
     def start

data/lib/lucid_works/base.rb

@@ -47,7 +47,7 @@ module LucidWorks
 
     class << self
       attr_accessor :collection_name # :nodoc:
-      attr_accessor_with_default :singleton, false
+      attr_accessor :singleton
       
       # The attributes for a model are ascertained in on of two ways.
       # Without a schema, the attributes list is automatically generated when the the object is retrieved from the server.
@@ -127,11 +127,11 @@ module LucidWorks
 
         url = case kind_of_find
           when :all;       collection_url(parent)
-          when :one;       "#{parent.uri}/#{collection_name}/#{id}"
-          when :singleton; "#{parent.uri}/#{singleton_name}"
+          when :one;       member_url(parent, id)
+          when :singleton; member_url(parent)
         end
 
-        raw_response = ActiveSupport::Notifications.instrument("lucid_works.request") do |payload|
+        raw_response = ActiveSupport::Notifications.instrument("api.lucid_works") do |payload|
           begin
             payload[:method]   = :get
             payload[:uri]      = url
@@ -178,7 +178,7 @@ module LucidWorks
 
             if kind_of_find == :all && association_info[:retrieveable_en_masse]
               all_targets_path = "#{collection_url(parent)}/all/#{target_name}"
-              raw_response = ActiveSupport::Notifications.instrument("lucid_works.request") do |payload|
+              raw_response = ActiveSupport::Notifications.instrument("api.lucid_works") do |payload|
                 begin
                   payload[:method]   = :get
                   payload[:uri]      = all_targets_path
@@ -265,6 +265,14 @@ module LucidWorks
         "#{parent.uri}/#{collection_name}"
       end
 
+      def member_url(parent, id = nil) # :nodoc:
+        if singleton
+          "#{parent.uri}/#{singleton_name}"
+        else
+          "#{parent.uri}/#{collection_name}/#{id}"
+        end
+      end
+
       def singleton_name # :nodoc:
         name.underscore.gsub(/^.*\//, '')
       end
@@ -291,13 +299,14 @@ module LucidWorks
       @associations = {}
       @persisted = options.delete(:persisted) || singleton? || false
       @attributes = {}.with_indifferent_access
+      @singleton = false
       load_attributes(options)
     end
 
     def save
       return false unless valid?
-      _run_save_callbacks do
-        ActiveSupport::Notifications.instrument("lucid_works.request") do |payload|
+      run_callbacks :save do
+        ActiveSupport::Notifications.instrument("api.lucid_works") do |payload|
           method, uri = persisted? ? [:put, member_url] : [:post, collection_url]
           data = encode
           payload[:method] = method
@@ -324,15 +333,19 @@ module LucidWorks
       end
     end
 
-    def update_attributes(attrs_and_values)
+    def attributes=(attrs_and_values)
       attrs_and_values.each do |attr,value|
         self.send("#{attr}=", value)
       end
+    end
+
+    def update_attributes(attrs_and_values)
+      self.attributes = attrs_and_values
       save
     end
 
     def destroy(options={})
-      ActiveSupport::Notifications.instrument("lucid_works.request") do |payload|
+      ActiveSupport::Notifications.instrument("api.lucid_works") do |payload|
         begin
           payload[:method]   = :delete
           payload[:uri]      = member_url
@@ -371,11 +384,7 @@ module LucidWorks
     end
 
     def member_url # :nodoc:
-      if singleton?
-        "#{parent.uri}/#{self.class.singleton_name}"
-      else
-        "#{parent.uri}/#{collection_name}/#{self.id}"
-      end
+      self.class.member_url(parent, self.id)
     end
     
     alias :uri :member_url
@@ -398,7 +407,7 @@ module LucidWorks
     end
 
     def singleton? # :nodoc:
-      self.class.singleton
+      !!self.class.singleton
     end
 
     def collection_name # :nodoc:
@@ -424,6 +433,8 @@ module LucidWorks
           next
         elsif self.class.respond_to?(:belongs_to_association_name) && attr.to_sym == self.class.belongs_to_association_name
           next # Dont overwrite our connection to our parent
+        elsif schema.model.associations.keys.include?(attr.to_sym)
+          next # There is an association with the same name. The association takes precedence.
         end
         attribute = schema.find_or_create_attribute(attr)
         send "#{attribute.name}=", value
@@ -439,7 +450,7 @@ module LucidWorks
       data = JSON.parse(response) rescue nil
       if data.is_a?(Hash) && data['errors']
         data['errors'].each do |error|
-          key = error['key'].blank? ? 'base' : error['key']
+          key = error['key'].blank? ? 'base' : LucidWorks::Schema::Attribute.sanitize_name(error['key'])
           # When core implements FOCUS-2262 start checking for error['code'] and lookup a translation.
           self.errors.add(key, error['message'])
         end