google-cloud-bigquery - Class Google::Cloud::Bigquery::External::CsvSource (v1.38.1)

Version 1.38.1

• 1.50.0 (latest)
• 1.49.1
• 1.48.1
• 1.47.0
• 1.46.1
• 1.45.0
• 1.44.2
• 1.43.1
• 1.42.0
• 1.41.0
• 1.40.0
• 1.39.0
• 1.38.1

Reference documentation and code samples for the google-cloud-bigquery class Google::Cloud::Bigquery::External::CsvSource.

CsvSource

CsvSource is a subclass of DataSource and represents a CSV external data source that can be queried from directly, such as Google Cloud Storage or Google Drive, even though the data is not stored in BigQuery. Instead of loading or streaming the data, this object references the external data source.

Inherits

• Google::Cloud::Bigquery::External::DataSource

Example

require "google/cloud/bigquery"

bigquery = Google::Cloud::Bigquery.new

csv_url = "gs://bucket/path/to/data.csv"
csv_table = bigquery.external csv_url do |csv|
  csv.autodetect = true
  csv.skip_leading_rows = 1
end

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?

Methods

#delimiter

def delimiter() -> String

The separator for fields in a CSV file.

Returns

• (String)

Example

require "google/cloud/bigquery"

bigquery = Google::Cloud::Bigquery.new

csv_url = "gs://bucket/path/to/data.csv"
csv_table = bigquery.external csv_url do |csv|
  csv.delimiter = "|"
end

csv_table.delimiter #=> "|"

#delimiter=

def delimiter=(new_delimiter)

Set the separator for fields in a CSV file.

Parameter

• new_delimiter (String) — New delimiter value

Example

require "google/cloud/bigquery"

bigquery = Google::Cloud::Bigquery.new

csv_url = "gs://bucket/path/to/data.csv"
csv_table = bigquery.external csv_url do |csv|
  csv.delimiter = "|"
end

csv_table.delimiter #=> "|"

#encoding

def encoding() -> String

The character encoding of the data.

Returns

• (String)

Example

require "google/cloud/bigquery"

bigquery = Google::Cloud::Bigquery.new

csv_url = "gs://bucket/path/to/data.csv"
csv_table = bigquery.external csv_url do |csv|
  csv.encoding = "UTF-8"
end

csv_table.encoding #=> "UTF-8"

#encoding=

def encoding=(new_encoding)

Set the character encoding of the data.

Parameter

• new_encoding (String) — New encoding value

Example

require "google/cloud/bigquery"

bigquery = Google::Cloud::Bigquery.new

csv_url = "gs://bucket/path/to/data.csv"
csv_table = bigquery.external csv_url do |csv|
  csv.encoding = "UTF-8"
end

csv_table.encoding #=> "UTF-8"

#fields

def fields() -> Array<Schema::Field>

The fields of the schema.

Returns

• (Array<Schema::Field>) — An array of field objects.

#headers

def headers() -> Array<Symbol>

The names of the columns in the schema.

Returns

• (Array<Symbol>) — An array of column names.

#iso8859_1?

def iso8859_1?() -> Boolean

Checks if the character encoding of the data is "ISO-8859-1".

Returns

• (Boolean)

Example

require "google/cloud/bigquery"

bigquery = Google::Cloud::Bigquery.new

csv_url = "gs://bucket/path/to/data.csv"
csv_table = bigquery.external csv_url do |csv|
  csv.encoding = "ISO-8859-1"
end

csv_table.encoding #=> "ISO-8859-1"
csv_table.iso8859_1? #=> true

#jagged_rows

def jagged_rows() -> Boolean

Indicates if BigQuery should accept rows that are missing trailing optional columns.

Returns

• (Boolean)

Example

require "google/cloud/bigquery"

bigquery = Google::Cloud::Bigquery.new

csv_url = "gs://bucket/path/to/data.csv"
csv_table = bigquery.external csv_url do |csv|
  csv.jagged_rows = true
end

csv_table.jagged_rows #=> true

#jagged_rows=

def jagged_rows=(new_jagged_rows)

Set whether BigQuery should accept rows that are missing trailing optional columns.

Parameter

• new_jagged_rows (Boolean) — New jagged_rows value

Example

require "google/cloud/bigquery"

bigquery = Google::Cloud::Bigquery.new

csv_url = "gs://bucket/path/to/data.csv"
csv_table = bigquery.external csv_url do |csv|
  csv.jagged_rows = true
end

csv_table.jagged_rows #=> true

#param_types

def param_types() -> Hash

The types of the fields in the data in the schema, using the same format as the optional query parameter types.

Returns

• (Hash) — A hash with field names as keys, and types as values.

#quote

def quote() -> String

The value that is used to quote data sections in a CSV file.

Returns

• (String)

Example

require "google/cloud/bigquery"

bigquery = Google::Cloud::Bigquery.new

csv_url = "gs://bucket/path/to/data.csv"
csv_table = bigquery.external csv_url do |csv|
  csv.quote = "'"
end

csv_table.quote #=> "'"

#quote=

def quote=(new_quote)

Set the value that is used to quote data sections in a CSV file.

Parameter

• new_quote (String) — New quote value

Example

require "google/cloud/bigquery"

bigquery = Google::Cloud::Bigquery.new

csv_url = "gs://bucket/path/to/data.csv"
csv_table = bigquery.external csv_url do |csv|
  csv.quote = "'"
end

csv_table.quote #=> "'"

#quoted_newlines

def quoted_newlines() -> Boolean

Indicates if BigQuery should allow quoted data sections that contain newline characters in a CSV file.

Returns

• (Boolean)

Example

require "google/cloud/bigquery"

bigquery = Google::Cloud::Bigquery.new

csv_url = "gs://bucket/path/to/data.csv"
csv_table = bigquery.external csv_url do |csv|
  csv.quoted_newlines = true
end

csv_table.quoted_newlines #=> true

#quoted_newlines=

def quoted_newlines=(new_quoted_newlines)

Set whether BigQuery should allow quoted data sections that contain newline characters in a CSV file.

Parameter

• new_quoted_newlines (Boolean) — New quoted_newlines value

Example

require "google/cloud/bigquery"

bigquery = Google::Cloud::Bigquery.new

csv_url = "gs://bucket/path/to/data.csv"
csv_table = bigquery.external csv_url do |csv|
  csv.quoted_newlines = true
end

csv_table.quoted_newlines #=> true

#schema

def schema(replace: false) { |schema| ... } -> Google::Cloud::Bigquery::Schema

The schema for the data.

Parameter

• replace (Boolean) (defaults to: false) — Whether to replace the existing schema with the new schema. If true, the fields will replace the existing schema. If false, the fields will be added to the existing schema. The default value is false.

Yields

• (schema) — a block for setting the schema

Yield Parameter

• schema (Schema) — the object accepting the schema

Returns

• (Google::Cloud::Bigquery::Schema)

Example

require "google/cloud/bigquery"

bigquery = Google::Cloud::Bigquery.new

csv_url = "gs://bucket/path/to/data.csv"
csv_table = bigquery.external csv_url do |csv|
  csv.schema do |schema|
    schema.string "name", mode: :required
    schema.string "email", mode: :required
    schema.integer "age", mode: :required
    schema.boolean "active", mode: :required
  end
end

#schema=

def schema=(new_schema)

Set the schema for the data.

Parameter

• new_schema (Schema) — The schema object.

Example

require "google/cloud/bigquery"

bigquery = Google::Cloud::Bigquery.new

csv_shema = bigquery.schema do |schema|
  schema.string "name", mode: :required
  schema.string "email", mode: :required
  schema.integer "age", mode: :required
  schema.boolean "active", mode: :required
end

csv_url = "gs://bucket/path/to/data.csv"
csv_table = bigquery.external csv_url
csv_table.schema = csv_shema

#skip_leading_rows

def skip_leading_rows() -> Integer

The number of rows at the top of a CSV file that BigQuery will skip when reading the data.

Returns

• (Integer)

Example

require "google/cloud/bigquery"

bigquery = Google::Cloud::Bigquery.new

csv_url = "gs://bucket/path/to/data.csv"
csv_table = bigquery.external csv_url do |csv|
  csv.skip_leading_rows = 1
end

csv_table.skip_leading_rows #=> 1

#skip_leading_rows=

def skip_leading_rows=(row_count)

Set the number of rows at the top of a CSV file that BigQuery will skip when reading the data.

Parameter

• row_count (Integer) — New skip_leading_rows value

Example

require "google/cloud/bigquery"

bigquery = Google::Cloud::Bigquery.new

csv_url = "gs://bucket/path/to/data.csv"
csv_table = bigquery.external csv_url do |csv|
  csv.skip_leading_rows = 1
end

csv_table.skip_leading_rows #=> 1

#utf8?

def utf8?() -> Boolean

Checks if the character encoding of the data is "UTF-8". This is the default.

Returns

• (Boolean)

Example

require "google/cloud/bigquery"

bigquery = Google::Cloud::Bigquery.new

csv_url = "gs://bucket/path/to/data.csv"
csv_table = bigquery.external csv_url do |csv|
  csv.encoding = "UTF-8"
end

csv_table.encoding #=> "UTF-8"
csv_table.utf8? #=> true