google-cloud-bigquery 1.19.0 → 1.22.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 65c8bae8c365c4fde7d54e75abe9c15aa4eba702b2e6300371843bc97bbc27f7
-  data.tar.gz: 5457cacd3331a717f63b0d71b907aa5e68702256118cd41d16f90be672f187e4
+  metadata.gz: 5fadedabb79035a0b983765731a3aee2af5ca5480671e4255e8644cfb6e8c68c
+  data.tar.gz: 9ae351ed3987f2a81e8d9046c88ab776e3ac39f37cac5c6961fa3c2daf33b8bb
 SHA512:
-  metadata.gz: b7f0438c001bccc0854ecf13b81909c056635a50489d074c8d91beb13ba3f5e00826663b20371ef7b0669a6cfcb3ee058da8eefc6ffcfd410e9da18d1dd82167
-  data.tar.gz: 05f8d06e52e06625655730e0c31ae57a8b6bec5c771809d73814413db90122477b143d494d0e8236f43782766673a0f0230b48480f9ce0cddb125b55065cc68a
+  metadata.gz: eec1a19be0af9113a94183b9c0eeaa4edf1e08b177be10c449396541d8c6970e4ec666f3fbbb0613107989afc078799beb44655e085f360e3c97846e797bba15
+  data.tar.gz: 5f89e947e34384131026fdafd0bdd05f05ed742f6a52b4c18ae0da83f433da2f2f090a924ff82bdf480b79eac9267b923732144a0b32773e12e8b3b846b61a28

data/CHANGELOG.md

@@ -1,5 +1,47 @@
 # Release History
 
+### 1.22.0 / 2020-09-10
+
+#### Features
+
+* Add support for ML model export
+  * Add model support to Project#extract and #extract_job
+  * Add ExtractJob#model?
+  * Add ExtractJob#ml_tf_saved_model?
+  * Add ExtractJob#ml_xgboost_booster?
+  * Add Model#extract and #extract_job
+
+### 1.21.2 / 2020-07-21
+
+#### Documentation
+
+* Update Data#each samples
+
+### 1.21.1 / 2020-05-28
+
+#### Documentation
+
+* Fix a few broken links
+
+### 1.21.0 / 2020-03-31
+
+#### Features
+
+* Add Job#parent_job_id and Job#script_statistics
+  * Add parent_job to Project#jobs
+  * Add Job#num_child_jobs
+  * Add Job#parent_job_id
+  * Add Job#script_statistics
+
+### 1.20.0 / 2020-03-11
+
+#### Features
+
+* Add Range Partitioning
+  * Add range partitioning methods to Table and Table::Updater
+  * Add range partitioning methods to LoadJob
+  * Add range partitioning methods to QueryJob
+
 ### 1.19.0 / 2020-02-11
 
 #### Features

data/TROUBLESHOOTING.md

@@ -24,14 +24,8 @@ improved, *please* create a new issue on GitHub so we can talk about it.
 
   - [New issue][gh-ruby]
 
-Or, you can ask questions on the [Google Cloud Platform Slack][slack-ruby]. You
-can use the "ruby" channel for general Ruby questions, or use the
-"google-cloud-ruby" channel if you have questions about this gem in particular.
-
 [so-ruby]: http://stackoverflow.com/questions/tagged/google-cloud-platform+ruby+bigquery
 
-[gh-search-ruby]: https://github.com/googlecloudplatform/google-cloud-ruby/issues?q=label%3A%22api%3A+bigquery%22
-
-[gh-ruby]: https://github.com/googlecloudplatform/google-cloud-ruby/issues/new
+[gh-search-ruby]: https://github.com/googleapis/google-cloud-ruby/issues?q=label%3A%22api%3A+bigquery%22
 
-[slack-ruby]: https://gcp-slack.appspot.com/
+[gh-ruby]: https://github.com/googleapis/google-cloud-ruby/issues/new

data/lib/google-cloud-bigquery.rb

@@ -53,9 +53,15 @@ module Google
     #   bigquery = gcloud.bigquery
     #   dataset = bigquery.dataset "my_dataset"
     #   table = dataset.table "my_table"
-    #   table.data.each do |row|
-    #     puts row
+    #
+    #   data = table.data
+    #
+    #   # Iterate over the first page of results
+    #   data.each do |row|
+    #     puts row[:name]
     #   end
+    #   # Retrieve the next page of results
+    #   data = data.next if data.next?
     #
     # @example The default scope can be overridden with the `scope` option:
     #   require "google/cloud"

data/lib/google/cloud/bigquery/convert.rb

@@ -318,7 +318,9 @@ module Google
             "parquet"                => "PARQUET",
             "datastore"              => "DATASTORE_BACKUP",
             "backup"                 => "DATASTORE_BACKUP",
-            "datastore_backup"       => "DATASTORE_BACKUP"
+            "datastore_backup"       => "DATASTORE_BACKUP",
+            "ml_tf_saved_model"      => "ML_TF_SAVED_MODEL",
+            "ml_xgboost_booster"     => "ML_XGBOOST_BOOSTER"
           }[format.to_s.downcase]
           return val unless val.nil?
           format

data/lib/google/cloud/bigquery/copy_job.rb

@@ -272,12 +272,21 @@ module Google
           # Sets the labels to use for the job.
           #
           # @param [Hash] value A hash of user-provided labels associated with
-          #   the job. You can use these to organize and group your jobs. Label
-          #   keys and values can be no longer than 63 characters, can only
-          #   contain lowercase letters, numeric characters, underscores and
-          #   dashes. International characters are allowed. Label values are
-          #   optional. Label keys must start with a letter and each label in
-          #   the list must have a different key.
+          #   the job. You can use these to organize and group your jobs.
+          #
+          #   The labels applied to a resource must meet the following requirements:
+          #
+          #   * Each resource can have multiple labels, up to a maximum of 64.
+          #   * Each label must be a key-value pair.
+          #   * Keys have a minimum length of 1 character and a maximum length of
+          #     63 characters, and cannot be empty. Values can be empty, and have
+          #     a maximum length of 63 characters.
+          #   * Keys and values can contain only lowercase letters, numeric characters,
+          #     underscores, and dashes. All characters must use UTF-8 encoding, and
+          #     international characters are allowed.
+          #   * The key portion of a label must be unique. However, you can use the
+          #     same key with multiple resources.
+          #   * Keys must start with a lowercase letter or international character.
           #
           # @!group Attributes
           def labels= value

data/lib/google/cloud/bigquery/data.rb

@@ -41,9 +41,12 @@ module Google
       #
       #   data.count # 100000
       #   data.total # 164656
+      #
+      #   # Iterate over the first page of results
       #   data.each do |row|
       #     puts row[:word]
       #   end
+      #   # Retrieve the next page of results
       #   data = data.next if data.next?
       #
       class Data < DelegateClass(::Array)
@@ -117,9 +120,12 @@ module Google
         #
         #   data.count # 100000
         #   data.total # 164656
+        #
+        #   # Iterate over the first page of results
         #   data.each do |row|
         #     puts row[:word]
         #   end
+        #   # Retrieve the next page of results
         #   data = data.next if data.next?
         #
         def total
@@ -375,9 +381,12 @@ module Google
         #
         #   data.count # 100000
         #   data.total # 164656
+        #
+        #   # Iterate over the first page of results
         #   data.each do |row|
         #     puts row[:word]
         #   end
+        #   # Retrieve the next page of results
         #   data = data.next if data.next?
         #
         def next?
@@ -402,9 +411,12 @@ module Google
         #
         #   data.count # 100000
         #   data.total # 164656
+        #
+        #   # Iterate over the first page of results
         #   data.each do |row|
         #     puts row[:word]
         #   end
+        #   # Retrieve the next page of results
         #   data = data.next if data.next?
         #
         def next

data/lib/google/cloud/bigquery/dataset.rb

@@ -313,12 +313,19 @@ module Google
         # @param [Hash<String, String>] labels A hash containing key/value
         #   pairs.
         #
-        #   * Label keys and values can be no longer than 63 characters.
-        #   * Label keys and values can contain only lowercase letters, numbers,
-        #     underscores, hyphens, and international characters.
-        #   * Label keys and values cannot exceed 128 bytes in size.
-        #   * Label keys must begin with a letter.
-        #   * Label keys must be unique within a dataset.
+        #   The labels applied to a resource must meet the following requirements:
+        #
+        #   * Each resource can have multiple labels, up to a maximum of 64.
+        #   * Each label must be a key-value pair.
+        #   * Keys have a minimum length of 1 character and a maximum length of
+        #     63 characters, and cannot be empty. Values can be empty, and have
+        #     a maximum length of 63 characters.
+        #   * Keys and values can contain only lowercase letters, numeric characters,
+        #     underscores, and dashes. All characters must use UTF-8 encoding, and
+        #     international characters are allowed.
+        #   * The key portion of a label must be unique. However, you can use the
+        #     same key with multiple resources.
+        #   * Keys must start with a lowercase letter or international character.
         #
         # @example
         #   require "google/cloud/bigquery"
@@ -555,6 +562,40 @@ module Google
         #     end
         #   end
         #
+        # @example With time partitioning and clustering.
+        #   require "google/cloud/bigquery"
+        #
+        #   bigquery = Google::Cloud::Bigquery.new
+        #   dataset = bigquery.dataset "my_dataset"
+        #
+        #   table = dataset.create_table "my_table" do |t|
+        #     t.schema do |schema|
+        #       schema.timestamp "dob", mode: :required
+        #       schema.string "first_name", mode: :required
+        #       schema.string "last_name", mode: :required
+        #     end
+        #     t.time_partitioning_type  = "DAY"
+        #     t.time_partitioning_field = "dob"
+        #     t.clustering_fields = ["last_name", "first_name"]
+        #   end
+        #
+        # @example With range partitioning.
+        #   require "google/cloud/bigquery"
+        #
+        #   bigquery = Google::Cloud::Bigquery.new
+        #   dataset = bigquery.dataset "my_dataset"
+        #
+        #   table = dataset.create_table "my_table" do |t|
+        #     t.schema do |schema|
+        #       schema.integer "my_table_id", mode: :required
+        #       schema.string "my_table_data", mode: :required
+        #     end
+        #     t.range_partitioning_field = "my_table_id"
+        #     t.range_partitioning_start = 0
+        #     t.range_partitioning_interval = 10
+        #     t.range_partitioning_end = 100
+        #   end
+        #
         # @!group Table
         #
         def create_table table_id, name: nil, description: nil
@@ -602,12 +643,20 @@ module Google
         #   SQL](https://cloud.google.com/bigquery/docs/reference/legacy-sql)
         #   dialect. Optional. The default value is false.
         # @param [Array<String>, String] udfs User-defined function resources
-        #   used in the query. May be either a code resource to load from a
-        #   Google Cloud Storage URI (`gs://bucket/path`), or an inline resource
+        #   used in a legacy SQL query. May be either a code resource to load from
+        #   a Google Cloud Storage URI (`gs://bucket/path`), or an inline resource
         #   that contains code for a user-defined function (UDF). Providing an
         #   inline code resource is equivalent to providing a URI for a file
-        #   containing the same code. See [User-Defined
-        #   Functions](https://cloud.google.com/bigquery/docs/reference/standard-sql/user-defined-functions).
+        #   containing the same code.
+        #
+        #   This parameter is used for defining User Defined Function (UDF)
+        #   resources only when using legacy SQL. Users of standard SQL should
+        #   leverage either DDL (e.g. `CREATE [TEMPORARY] FUNCTION ...`) or the
+        #   Routines API to define UDF resources.
+        #
+        #   For additional information on migrating, see: [Migrating to
+        #   standard SQL - Differences in user-defined JavaScript
+        #   functions](https://cloud.google.com/bigquery/docs/reference/standard-sql/migrating-from-legacy-sql#differences_in_user-defined_javascript_functions)
         #
         # @return [Google::Cloud::Bigquery::Table] A new table object.
         #
@@ -1129,20 +1178,36 @@ module Google
         #   is 1,024 characters. If `job_id` is provided, then `prefix` will not
         #   be used.
         # @param [Hash] labels A hash of user-provided labels associated with
-        #   the job. You can use these to organize and group your jobs. Label
-        #   keys and values can be no longer than 63 characters, can only
-        #   contain lowercase letters, numeric characters, underscores and
-        #   dashes. International characters are allowed. Label values are
-        #   optional. Label keys must start with a letter and each label in the
-        #   list must have a different key. See [Requirements for
-        #   labels](https://cloud.google.com/bigquery/docs/creating-managing-labels#requirements).
+        #   the job. You can use these to organize and group your jobs.
+        #
+        #   The labels applied to a resource must meet the following requirements:
+        #
+        #   * Each resource can have multiple labels, up to a maximum of 64.
+        #   * Each label must be a key-value pair.
+        #   * Keys have a minimum length of 1 character and a maximum length of
+        #     63 characters, and cannot be empty. Values can be empty, and have
+        #     a maximum length of 63 characters.
+        #   * Keys and values can contain only lowercase letters, numeric characters,
+        #     underscores, and dashes. All characters must use UTF-8 encoding, and
+        #     international characters are allowed.
+        #   * The key portion of a label must be unique. However, you can use the
+        #     same key with multiple resources.
+        #   * Keys must start with a lowercase letter or international character.
         # @param [Array<String>, String] udfs User-defined function resources
-        #   used in the query. May be either a code resource to load from a
-        #   Google Cloud Storage URI (`gs://bucket/path`), or an inline resource
+        #   used in a legacy SQL query. May be either a code resource to load from
+        #   a Google Cloud Storage URI (`gs://bucket/path`), or an inline resource
         #   that contains code for a user-defined function (UDF). Providing an
         #   inline code resource is equivalent to providing a URI for a file
-        #   containing the same code. See [User-Defined
-        #   Functions](https://cloud.google.com/bigquery/docs/reference/standard-sql/user-defined-functions).
+        #   containing the same code.
+        #
+        #   This parameter is used for defining User Defined Function (UDF)
+        #   resources only when using legacy SQL. Users of standard SQL should
+        #   leverage either DDL (e.g. `CREATE [TEMPORARY] FUNCTION ...`) or the
+        #   Routines API to define UDF resources.
+        #
+        #   For additional information on migrating, see: [Migrating to
+        #   standard SQL - Differences in user-defined JavaScript
+        #   functions](https://cloud.google.com/bigquery/docs/reference/standard-sql/migrating-from-legacy-sql#differences_in_user-defined_javascript_functions)
         # @param [Integer] maximum_billing_tier Deprecated: Change the billing
         #   tier to allow high-compute queries.
         # @yield [job] a job configuration object
@@ -1424,9 +1489,12 @@ module Google
         #
         #   data = dataset.query "SELECT name FROM my_table"
         #
+        #   # Iterate over the first page of results
         #   data.each do |row|
         #     puts row[:name]
         #   end
+        #   # Retrieve the next page of results
+        #   data = data.next if data.next?
         #
         # @example Query using legacy SQL:
         #   require "google/cloud/bigquery"
@@ -1437,9 +1505,12 @@ module Google
         #   data = dataset.query "SELECT name FROM my_table",
         #                        legacy_sql: true
         #
+        #   # Iterate over the first page of results
         #   data.each do |row|
         #     puts row[:name]
         #   end
+        #   # Retrieve the next page of results
+        #   data = data.next if data.next?
         #
         # @example Query using positional query parameters:
         #   require "google/cloud/bigquery"
@@ -1450,9 +1521,12 @@ module Google
         #   data = dataset.query "SELECT name FROM my_table WHERE id = ?",
         #                        params: [1]
         #
+        #   # Iterate over the first page of results
         #   data.each do |row|
         #     puts row[:name]
         #   end
+        #   # Retrieve the next page of results
+        #   data = data.next if data.next?
         #
         # @example Query using named query parameters:
         #   require "google/cloud/bigquery"
@@ -1463,9 +1537,12 @@ module Google
         #   data = dataset.query "SELECT name FROM my_table WHERE id = @id",
         #                        params: { id: 1 }
         #
+        #   # Iterate over the first page of results
         #   data.each do |row|
         #     puts row[:name]
         #   end
+        #   # Retrieve the next page of results
+        #   data = data.next if data.next?
         #
         # @example Query using named query parameters with types:
         #   require "google/cloud/bigquery"
@@ -1478,9 +1555,12 @@ module Google
         #                        params: { ids: [] },
         #                        types: { ids: [:INT64] }
         #
+        #   # Iterate over the first page of results
         #   data.each do |row|
         #     puts row[:name]
         #   end
+        #   # Retrieve the next page of results
+        #   data = data.next if data.next?
         #
         # @example Execute a DDL statement:
         #   require "google/cloud/bigquery"
@@ -1519,9 +1599,12 @@ module Google
         #     query.table = dataset.table "my_table", skip_lookup: true
         #   end
         #
+        #   # Iterate over the first page of results
         #   data.each do |row|
         #     puts row[:name]
         #   end
+        #   # Retrieve the next page of results
+        #   data = data.next if data.next?
         #
         # @!group Data
         #
@@ -1724,13 +1807,21 @@ module Google
         #   is 1,024 characters. If `job_id` is provided, then `prefix` will not
         #   be used.
         # @param [Hash] labels A hash of user-provided labels associated with
-        #   the job. You can use these to organize and group your jobs. Label
-        #   keys and values can be no longer than 63 characters, can only
-        #   contain lowercase letters, numeric characters, underscores and
-        #   dashes. International characters are allowed. Label values are
-        #   optional. Label keys must start with a letter and each label in the
-        #   list must have a different key. See [Requirements for
-        #   labels](https://cloud.google.com/bigquery/docs/creating-managing-labels#requirements).
+        #   the job. You can use these to organize and group your jobs.
+        #
+        #   The labels applied to a resource must meet the following requirements:
+        #
+        #   * Each resource can have multiple labels, up to a maximum of 64.
+        #   * Each label must be a key-value pair.
+        #   * Keys have a minimum length of 1 character and a maximum length of
+        #     63 characters, and cannot be empty. Values can be empty, and have
+        #     a maximum length of 63 characters.
+        #   * Keys and values can contain only lowercase letters, numeric characters,
+        #     underscores, and dashes. All characters must use UTF-8 encoding, and
+        #     international characters are allowed.
+        #   * The key portion of a label must be unique. However, you can use the
+        #     same key with multiple resources.
+        #   * Keys must start with a lowercase letter or international character.
         # @yield [updater] A block for setting the schema and other
         #   options for the destination table. The schema can be omitted if the
         #   destination table already exists, or if you're loading data from a

data/lib/google/cloud/bigquery/external.rb

@@ -45,9 +45,12 @@ module Google
       #   data = bigquery.query "SELECT * FROM my_ext_table",
       #                         external: { my_ext_table: csv_table }
       #
+      #   # Iterate over the first page of results
       #   data.each do |row|
       #     puts row[:name]
       #   end
+      #   # Retrieve the next page of results
+      #   data = data.next if data.next?
       #
       module External
         ##
@@ -138,9 +141,12 @@ module Google
         #   data = bigquery.query "SELECT * FROM my_ext_table",
         #                         external: { my_ext_table: avro_table }
         #
+        #   # Iterate over the first page of results
         #   data.each do |row|
         #     puts row[:name]
         #   end
+        #   # Retrieve the next page of results
+        #   data = data.next if data.next?
         #
         class DataSource
           ##
@@ -575,9 +581,12 @@ module Google
         #   data = bigquery.query "SELECT * FROM my_ext_table",
         #                         external: { my_ext_table: csv_table }
         #
+        #   # Iterate over the first page of results
         #   data.each do |row|
         #     puts row[:name]
         #   end
+        #   # Retrieve the next page of results
+        #   data = data.next if data.next?
         #
         class CsvSource < External::DataSource
           ##
@@ -1037,9 +1046,12 @@ module Google
         #   data = bigquery.query "SELECT * FROM my_ext_table",
         #                         external: { my_ext_table: json_table }
         #
+        #   # Iterate over the first page of results
         #   data.each do |row|
         #     puts row[:name]
         #   end
+        #   # Retrieve the next page of results
+        #   data = data.next if data.next?
         #
         class JsonSource < External::DataSource
           ##
@@ -1173,9 +1185,12 @@ module Google
         #   data = bigquery.query "SELECT * FROM my_ext_table",
         #                         external: { my_ext_table: sheets_table }
         #
+        #   # Iterate over the first page of results
         #   data.each do |row|
         #     puts row[:name]
         #   end
+        #   # Retrieve the next page of results
+        #   data = data.next if data.next?
         #
         class SheetsSource < External::DataSource
           ##
@@ -1318,9 +1333,12 @@ module Google
         #   data = bigquery.query "SELECT * FROM my_ext_table",
         #                         external: { my_ext_table: bigtable_table }
         #
+        #   # Iterate over the first page of results
         #   data.each do |row|
         #     puts row[:name]
         #   end
+        #   # Retrieve the next page of results
+        #   data = data.next if data.next?
         #
         class BigtableSource < External::DataSource
           ##
@@ -1516,9 +1534,12 @@ module Google
           #   data = bigquery.query "SELECT * FROM my_ext_table",
           #                         external: { my_ext_table: bigtable_table }
           #
+          #   # Iterate over the first page of results
           #   data.each do |row|
           #     puts row[:name]
           #   end
+          #   # Retrieve the next page of results
+          #   data = data.next if data.next?
           #
           class ColumnFamily
             ##
@@ -2053,9 +2074,12 @@ module Google
           #   data = bigquery.query "SELECT * FROM my_ext_table",
           #                         external: { my_ext_table: bigtable_table }
           #
+          #   # Iterate over the first page of results
           #   data.each do |row|
           #     puts row[:name]
           #   end
+          #   # Retrieve the next page of results
+          #   data = data.next if data.next?
           #
           class Column
             ##