Update docs
diff --git a/docs/dyn/bigquery_v2.jobs.html b/docs/dyn/bigquery_v2.jobs.html
index 0341827..431a220 100644
--- a/docs/dyn/bigquery_v2.jobs.html
+++ b/docs/dyn/bigquery_v2.jobs.html
@@ -173,6 +173,19 @@
"datasetId": "A String", # [Required] The ID of the dataset containing this table.
},
],
+ "schema": { # [Output-only, Experimental] The schema of the results. Present only for successful dry run of non-legacy SQL queries.
+ "fields": [ # Describes the fields in a table.
+ {
+ "fields": [ # [Optional] Describes the nested schema fields if the type property is set to RECORD.
+ # Object with schema name: TableFieldSchema
+ ],
+ "type": "A String", # [Required] The field data type. Possible values include STRING, BYTES, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
+ "description": "A String", # [Optional] The field description. The maximum length is 16K characters.
+ "name": "A String", # [Required] The field name. The name must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_), and must start with a letter or underscore. The maximum length is 128 characters.
+ "mode": "A String", # [Optional] The field mode. Possible values include NULLABLE, REQUIRED and REPEATED. The default value is NULLABLE.
+ },
+ ],
+ },
},
"endTime": "A String", # [Output-only] End time of this job, in milliseconds since the epoch. This field will be present whenever a job is in the DONE state.
"extract": { # [Output-only] Statistics for an extract job.
@@ -189,9 +202,10 @@
"user_email": "A String", # [Output-only] Email address of the user who ran the job.
"configuration": { # [Required] Describes the job configuration.
"load": { # [Pick one] Configures a load job.
+ "sourceFormat": "A String", # [Optional] The format of the data files. For CSV files, specify "CSV". For datastore backups, specify "DATASTORE_BACKUP". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". For Avro, specify "AVRO". The default value is CSV.
"encoding": "A String", # [Optional] The character encoding of the data. The supported values are UTF-8 or ISO-8859-1. The default value is UTF-8. BigQuery decodes the data after the raw, binary data has been split using the values of the quote and fieldDelimiter properties.
"fieldDelimiter": "A String", # [Optional] The separator for fields in a CSV file. The separator can be any ISO-8859-1 single-byte character. To use a character in the range 128-255, you must encode the character as UTF8. BigQuery converts the string to ISO-8859-1 encoding, and then uses the first byte of the encoded string to split the data in its raw, binary state. BigQuery also supports the escape sequence "\t" to specify a tab separator. The default value is a comma (',').
- "sourceFormat": "A String", # [Optional] The format of the data files. For CSV files, specify "CSV". For datastore backups, specify "DATASTORE_BACKUP". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". The default value is CSV.
+ "autodetect": True or False, # [Experimental] Indicates if we should automatically infer the options and schema for CSV and JSON sources.
"destinationTable": { # [Required] The destination table to load the data into.
"projectId": "A String", # [Required] The ID of the project containing this table.
"tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
@@ -219,7 +233,7 @@
"fields": [ # [Optional] Describes the nested schema fields if the type property is set to RECORD.
# Object with schema name: TableFieldSchema
],
- "type": "A String", # [Required] The field data type. Possible values include STRING, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
+ "type": "A String", # [Required] The field data type. Possible values include STRING, BYTES, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
"description": "A String", # [Optional] The field description. The maximum length is 16K characters.
"name": "A String", # [Required] The field name. The name must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_), and must start with a letter or underscore. The maximum length is 128 characters.
"mode": "A String", # [Optional] The field mode. Possible values include NULLABLE, REQUIRED and REPEATED. The default value is NULLABLE.
@@ -272,7 +286,7 @@
"projectId": "A String", # [Optional] The ID of the project containing this dataset.
"datasetId": "A String", # [Required] A unique ID for this dataset, without the project name. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
},
- "useLegacySql": True or False, # [Experimental] Specifies whether to use BigQuery's legacy SQL dialect for this query. The default value is true. If set to false, the query will use BigQuery's updated SQL dialect with improved standards compliance. When using BigQuery's updated SQL, the values of allowLargeResults and flattenResults are ignored. Queries with useLegacySql set to false will be run as if allowLargeResults is true and flattenResults is false.
+ "useLegacySql": True or False, # [Experimental] Specifies whether to use BigQuery's legacy SQL dialect for this query. The default value is true. If set to false, the query will use BigQuery's standard SQL: https://cloud.google.com/bigquery/sql-reference/ When useLegacySql is set to false, the values of allowLargeResults and flattenResults are ignored; query will be run as if allowLargeResults is true and flattenResults is false.
"destinationTable": { # [Optional] Describes the table where the query results should be stored. If not present, a new table will be created to store the results.
"projectId": "A String", # [Required] The ID of the project containing this table.
"tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
@@ -286,28 +300,53 @@
"preserveNulls": True or False, # [Deprecated] This property is deprecated.
"tableDefinitions": { # [Optional] If querying an external data source outside of BigQuery, describes the data format, location and other properties of the data source. By defining these properties, the data source can then be queried as if it were a standard BigQuery table.
"a_key": {
- "compression": "A String", # [Optional] The compression type of the data source. Possible values include GZIP and NONE. The default value is NONE. This setting is ignored for Google Cloud Datastore backups.
+ "compression": "A String", # [Optional] The compression type of the data source. Possible values include GZIP and NONE. The default value is NONE. This setting is ignored for Google Cloud Bigtable, Google Cloud Datastore backups and Avro formats.
"csvOptions": { # Additional properties to set if sourceFormat is set to CSV.
"fieldDelimiter": "A String", # [Optional] The separator for fields in a CSV file. BigQuery converts the string to ISO-8859-1 encoding, and then uses the first byte of the encoded string to split the data in its raw, binary state. BigQuery also supports the escape sequence "\t" to specify a tab separator. The default value is a comma (',').
"encoding": "A String", # [Optional] The character encoding of the data. The supported values are UTF-8 or ISO-8859-1. The default value is UTF-8. BigQuery decodes the data after the raw, binary data has been split using the values of the quote and fieldDelimiter properties.
- "skipLeadingRows": 42, # [Optional] The number of rows at the top of a CSV file that BigQuery will skip when reading the data. The default value is 0. This property is useful if you have header rows in the file that should be skipped.
+ "skipLeadingRows": "A String", # [Optional] The number of rows at the top of a CSV file that BigQuery will skip when reading the data. The default value is 0. This property is useful if you have header rows in the file that should be skipped.
"allowJaggedRows": True or False, # [Optional] Indicates if BigQuery should accept rows that are missing trailing optional columns. If true, BigQuery treats missing trailing columns as null values. If false, records with missing trailing columns are treated as bad records, and if there are too many bad records, an invalid error is returned in the job result. The default value is false.
"quote": """, # [Optional] The value that is used to quote data sections in a CSV file. BigQuery converts the string to ISO-8859-1 encoding, and then uses the first byte of the encoded string to split the data in its raw, binary state. The default value is a double-quote ('"'). If your data does not contain quoted sections, set the property value to an empty string. If your data contains quoted newline characters, you must also set the allowQuotedNewlines property to true.
"allowQuotedNewlines": True or False, # [Optional] Indicates if BigQuery should allow quoted data sections that contain newline characters in a CSV file. The default value is false.
},
- "sourceFormat": "A String", # [Required] The data format. For CSV files, specify "CSV". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". For Google Cloud Datastore backups, specify "DATASTORE_BACKUP".
- "maxBadRecords": 42, # [Optional] The maximum number of bad records that BigQuery can ignore when reading data. If the number of bad records exceeds this value, an invalid error is returned in the job result. The default value is 0, which requires that all records are valid. This setting is ignored for Google Cloud Datastore backups.
- "ignoreUnknownValues": True or False, # [Optional] Indicates if BigQuery should allow extra values that are not represented in the table schema. If true, the extra values are ignored. If false, records with extra columns are treated as bad records, and if there are too many bad records, an invalid error is returned in the job result. The default value is false. The sourceFormat property determines what BigQuery treats as an extra value: CSV: Trailing columns JSON: Named values that don't match any column names Google Cloud Datastore backups: This setting is ignored.
- "sourceUris": [ # [Required] The fully-qualified URIs that point to your data in Google Cloud Storage. Each URI can contain one '*' wildcard character and it must come after the 'bucket' name. Size limits related to load jobs apply to external data sources, plus an additional limit of 10 GB maximum size across all URIs. For Google Cloud Datastore backups, exactly one URI can be specified, and it must end with '.backup_info'. Also, the '*' wildcard character is not allowed.
+ "autodetect": True or False, # [Experimental] Try to detect schema and format options automatically. Any option specified explicitly will be honored.
+ "maxBadRecords": 42, # [Optional] The maximum number of bad records that BigQuery can ignore when reading data. If the number of bad records exceeds this value, an invalid error is returned in the job result. The default value is 0, which requires that all records are valid. This setting is ignored for Google Cloud Bigtable, Google Cloud Datastore backups and Avro formats.
+ "ignoreUnknownValues": True or False, # [Optional] Indicates if BigQuery should allow extra values that are not represented in the table schema. If true, the extra values are ignored. If false, records with extra columns are treated as bad records, and if there are too many bad records, an invalid error is returned in the job result. The default value is false. The sourceFormat property determines what BigQuery treats as an extra value: CSV: Trailing columns JSON: Named values that don't match any column names Google Cloud Bigtable: This setting is ignored. Google Cloud Datastore backups: This setting is ignored. Avro: This setting is ignored.
+ "sourceUris": [ # [Required] The fully-qualified URIs that point to your data in Google Cloud. For Google Cloud Storage URIs: Each URI can contain one '*' wildcard character and it must come after the 'bucket' name. Size limits related to load jobs apply to external data sources. For Google Cloud Bigtable URIs: Exactly one URI can be specified and it has be a fully specified and valid HTTPS URL for a Google Cloud Bigtable table. For Google Cloud Datastore backups, exactly one URI can be specified, and it must end with '.backup_info'. Also, the '*' wildcard character is not allowed.
"A String",
],
- "schema": { # [Optional] The schema for the data. Schema is required for CSV and JSON formats. Schema is disallowed for Google Cloud Datastore backups.
+ "bigtableOptions": { # [Optional] Additional options if sourceFormat is set to BIGTABLE.
+ "ignoreUnspecifiedColumnFamilies": True or False, # [Optional] If field is true, then the column families that are not specified in columnFamilies list are not exposed in the table schema. Otherwise, they are read with BYTES type values. The default value is false.
+ "columnFamilies": [ # [Optional] List of column families to expose in the table schema along with their types. This list restricts the column families that can be referenced in queries and specifies their value types. You can use this list to do type conversions - see the 'type' field for more details. If you leave this list empty, all column families are present in the table schema and their values are read as BYTES. During a query only the column families referenced in that query are read from Bigtable.
+ {
+ "familyId": "A String", # Identifier of the column family.
+ "type": "A String", # [Optional] The type to convert the value in cells of this column family. The values are expected to be encoded using HBase Bytes.toBytes function when using the BINARY encoding value. Following BigQuery types are allowed (case-sensitive) - BYTES STRING INTEGER FLOAT BOOLEAN Defaut type is BYTES. This can be overridden for a specific column by listing that column in 'columns' and specifying a type for it.
+ "onlyReadLatest": True or False, # [Optional] If this is set only the latest version of value are exposed for all columns in this column family. This can be overridden for a specific column by listing that column in 'columns' and specifying a different setting for that column.
+ "columns": [ # [Optional] Lists of columns that should be exposed as individual fields as opposed to a list of (column name, value) pairs. All columns whose qualifier matches a qualifier in this list can be accessed as .. Other columns can be accessed as a list through .Column field.
+ {
+ "encoding": "A String", # [Optional] The encoding of the values when the type is not STRING. Acceptable encoding values are: TEXT - indicates values are alphanumeric text strings. BINARY - indicates values are encoded using HBase Bytes.toBytes family of functions. 'encoding' can also be set at the column family level. However, the setting at this level takes precedence if 'encoding' is set at both levels.
+ "qualifierEncoded": "A String", # [Required] Qualifier of the column. Columns in the parent column family that has this exact qualifier are exposed as . field. If the qualifier is valid UTF-8 string, it can be specified in the qualifier_string field. Otherwise, a base-64 encoded value must be set to qualifier_encoded. The column field name is the same as the column qualifier. However, if the qualifier is not a valid BigQuery field identifier i.e. does not match [a-zA-Z][a-zA-Z0-9_]*, a valid identifier must be provided as field_name.
+ "fieldName": "A String", # [Optional] If the qualifier is not a valid BigQuery field identifier i.e. does not match [a-zA-Z][a-zA-Z0-9_]*, a valid identifier must be provided as the column field name and is used as field name in queries.
+ "onlyReadLatest": True or False, # [Optional] If this is set, only the latest version of value in this column are exposed. 'onlyReadLatest' can also be set at the column family level. However, the setting at this level takes precedence if 'onlyReadLatest' is set at both levels.
+ "qualifierString": "A String",
+ "type": "A String", # [Optional] The type to convert the value in cells of this column. The values are expected to be encoded using HBase Bytes.toBytes function when using the BINARY encoding value. Following BigQuery types are allowed (case-sensitive) - BYTES STRING INTEGER FLOAT BOOLEAN Defaut type is BYTES. 'type' can also be set at the column family level. However, the setting at this level takes precedence if 'type' is set at both levels.
+ },
+ ],
+ "encoding": "A String", # [Optional] The encoding of the values when the type is not STRING. Acceptable encoding values are: TEXT - indicates values are alphanumeric text strings. BINARY - indicates values are encoded using HBase Bytes.toBytes family of functions. This can be overridden for a specific column by listing that column in 'columns' and specifying an encoding for it.
+ },
+ ],
+ },
+ "sourceFormat": "A String", # [Required] The data format. For CSV files, specify "CSV". For Google sheets, specify "GOOGLE_SHEETS". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". For Avro files, specify "AVRO". For Google Cloud Datastore backups, specify "DATASTORE_BACKUP". [Experimental] For Google Cloud Bigtable, specify "BIGTABLE". Please note that reading from Google Cloud Bigtable is experimental and has to be enabled for your project. Please contact Google Cloud Support to enable this for your project.
+ "googleSheetsOptions": { # [Optional] Additional options if sourceFormat is set to GOOGLE_SHEETS.
+ "skipLeadingRows": "A String", # [Optional] The number of rows at the top of a sheet that BigQuery will skip when reading the data. The default value is 0. This property is useful if you have header rows that should be skipped. When autodetect is on, behavior is the following: * skipLeadingRows unspecified - Autodetect tries to detect headers in the first row. If they are not detected, the row is read as data. Otherwise data is read starting from the second row. * skipLeadingRows is 0 - Instructs autodetect that there are no headers and data should be read starting from the first row. * skipLeadingRows = N > 0 - Autodetect skips N-1 rows and tries to detect headers in row N. If headers are not detected, row N is just skipped. Otherwise row N is used to extract column names for the detected schema.
+ },
+ "schema": { # [Optional] The schema for the data. Schema is required for CSV and JSON formats. Schema is disallowed for Google Cloud Bigtable, Cloud Datastore backups, and Avro formats.
"fields": [ # Describes the fields in a table.
{
"fields": [ # [Optional] Describes the nested schema fields if the type property is set to RECORD.
# Object with schema name: TableFieldSchema
],
- "type": "A String", # [Required] The field data type. Possible values include STRING, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
+ "type": "A String", # [Required] The field data type. Possible values include STRING, BYTES, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
"description": "A String", # [Optional] The field description. The maximum length is 16K characters.
"name": "A String", # [Required] The field name. The name must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_), and must start with a letter or underscore. The maximum length is 128 characters.
"mode": "A String", # [Optional] The field mode. Possible values include NULLABLE, REQUIRED and REPEATED. The default value is NULLABLE.
@@ -407,6 +446,19 @@
"datasetId": "A String", # [Required] The ID of the dataset containing this table.
},
],
+ "schema": { # [Output-only, Experimental] The schema of the results. Present only for successful dry run of non-legacy SQL queries.
+ "fields": [ # Describes the fields in a table.
+ {
+ "fields": [ # [Optional] Describes the nested schema fields if the type property is set to RECORD.
+ # Object with schema name: TableFieldSchema
+ ],
+ "type": "A String", # [Required] The field data type. Possible values include STRING, BYTES, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
+ "description": "A String", # [Optional] The field description. The maximum length is 16K characters.
+ "name": "A String", # [Required] The field name. The name must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_), and must start with a letter or underscore. The maximum length is 128 characters.
+ "mode": "A String", # [Optional] The field mode. Possible values include NULLABLE, REQUIRED and REPEATED. The default value is NULLABLE.
+ },
+ ],
+ },
},
"endTime": "A String", # [Output-only] End time of this job, in milliseconds since the epoch. This field will be present whenever a job is in the DONE state.
"extract": { # [Output-only] Statistics for an extract job.
@@ -423,9 +475,10 @@
"user_email": "A String", # [Output-only] Email address of the user who ran the job.
"configuration": { # [Required] Describes the job configuration.
"load": { # [Pick one] Configures a load job.
+ "sourceFormat": "A String", # [Optional] The format of the data files. For CSV files, specify "CSV". For datastore backups, specify "DATASTORE_BACKUP". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". For Avro, specify "AVRO". The default value is CSV.
"encoding": "A String", # [Optional] The character encoding of the data. The supported values are UTF-8 or ISO-8859-1. The default value is UTF-8. BigQuery decodes the data after the raw, binary data has been split using the values of the quote and fieldDelimiter properties.
"fieldDelimiter": "A String", # [Optional] The separator for fields in a CSV file. The separator can be any ISO-8859-1 single-byte character. To use a character in the range 128-255, you must encode the character as UTF8. BigQuery converts the string to ISO-8859-1 encoding, and then uses the first byte of the encoded string to split the data in its raw, binary state. BigQuery also supports the escape sequence "\t" to specify a tab separator. The default value is a comma (',').
- "sourceFormat": "A String", # [Optional] The format of the data files. For CSV files, specify "CSV". For datastore backups, specify "DATASTORE_BACKUP". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". The default value is CSV.
+ "autodetect": True or False, # [Experimental] Indicates if we should automatically infer the options and schema for CSV and JSON sources.
"destinationTable": { # [Required] The destination table to load the data into.
"projectId": "A String", # [Required] The ID of the project containing this table.
"tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
@@ -453,7 +506,7 @@
"fields": [ # [Optional] Describes the nested schema fields if the type property is set to RECORD.
# Object with schema name: TableFieldSchema
],
- "type": "A String", # [Required] The field data type. Possible values include STRING, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
+ "type": "A String", # [Required] The field data type. Possible values include STRING, BYTES, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
"description": "A String", # [Optional] The field description. The maximum length is 16K characters.
"name": "A String", # [Required] The field name. The name must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_), and must start with a letter or underscore. The maximum length is 128 characters.
"mode": "A String", # [Optional] The field mode. Possible values include NULLABLE, REQUIRED and REPEATED. The default value is NULLABLE.
@@ -506,7 +559,7 @@
"projectId": "A String", # [Optional] The ID of the project containing this dataset.
"datasetId": "A String", # [Required] A unique ID for this dataset, without the project name. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
},
- "useLegacySql": True or False, # [Experimental] Specifies whether to use BigQuery's legacy SQL dialect for this query. The default value is true. If set to false, the query will use BigQuery's updated SQL dialect with improved standards compliance. When using BigQuery's updated SQL, the values of allowLargeResults and flattenResults are ignored. Queries with useLegacySql set to false will be run as if allowLargeResults is true and flattenResults is false.
+ "useLegacySql": True or False, # [Experimental] Specifies whether to use BigQuery's legacy SQL dialect for this query. The default value is true. If set to false, the query will use BigQuery's standard SQL: https://cloud.google.com/bigquery/sql-reference/ When useLegacySql is set to false, the values of allowLargeResults and flattenResults are ignored; query will be run as if allowLargeResults is true and flattenResults is false.
"destinationTable": { # [Optional] Describes the table where the query results should be stored. If not present, a new table will be created to store the results.
"projectId": "A String", # [Required] The ID of the project containing this table.
"tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
@@ -520,28 +573,53 @@
"preserveNulls": True or False, # [Deprecated] This property is deprecated.
"tableDefinitions": { # [Optional] If querying an external data source outside of BigQuery, describes the data format, location and other properties of the data source. By defining these properties, the data source can then be queried as if it were a standard BigQuery table.
"a_key": {
- "compression": "A String", # [Optional] The compression type of the data source. Possible values include GZIP and NONE. The default value is NONE. This setting is ignored for Google Cloud Datastore backups.
+ "compression": "A String", # [Optional] The compression type of the data source. Possible values include GZIP and NONE. The default value is NONE. This setting is ignored for Google Cloud Bigtable, Google Cloud Datastore backups and Avro formats.
"csvOptions": { # Additional properties to set if sourceFormat is set to CSV.
"fieldDelimiter": "A String", # [Optional] The separator for fields in a CSV file. BigQuery converts the string to ISO-8859-1 encoding, and then uses the first byte of the encoded string to split the data in its raw, binary state. BigQuery also supports the escape sequence "\t" to specify a tab separator. The default value is a comma (',').
"encoding": "A String", # [Optional] The character encoding of the data. The supported values are UTF-8 or ISO-8859-1. The default value is UTF-8. BigQuery decodes the data after the raw, binary data has been split using the values of the quote and fieldDelimiter properties.
- "skipLeadingRows": 42, # [Optional] The number of rows at the top of a CSV file that BigQuery will skip when reading the data. The default value is 0. This property is useful if you have header rows in the file that should be skipped.
+ "skipLeadingRows": "A String", # [Optional] The number of rows at the top of a CSV file that BigQuery will skip when reading the data. The default value is 0. This property is useful if you have header rows in the file that should be skipped.
"allowJaggedRows": True or False, # [Optional] Indicates if BigQuery should accept rows that are missing trailing optional columns. If true, BigQuery treats missing trailing columns as null values. If false, records with missing trailing columns are treated as bad records, and if there are too many bad records, an invalid error is returned in the job result. The default value is false.
"quote": """, # [Optional] The value that is used to quote data sections in a CSV file. BigQuery converts the string to ISO-8859-1 encoding, and then uses the first byte of the encoded string to split the data in its raw, binary state. The default value is a double-quote ('"'). If your data does not contain quoted sections, set the property value to an empty string. If your data contains quoted newline characters, you must also set the allowQuotedNewlines property to true.
"allowQuotedNewlines": True or False, # [Optional] Indicates if BigQuery should allow quoted data sections that contain newline characters in a CSV file. The default value is false.
},
- "sourceFormat": "A String", # [Required] The data format. For CSV files, specify "CSV". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". For Google Cloud Datastore backups, specify "DATASTORE_BACKUP".
- "maxBadRecords": 42, # [Optional] The maximum number of bad records that BigQuery can ignore when reading data. If the number of bad records exceeds this value, an invalid error is returned in the job result. The default value is 0, which requires that all records are valid. This setting is ignored for Google Cloud Datastore backups.
- "ignoreUnknownValues": True or False, # [Optional] Indicates if BigQuery should allow extra values that are not represented in the table schema. If true, the extra values are ignored. If false, records with extra columns are treated as bad records, and if there are too many bad records, an invalid error is returned in the job result. The default value is false. The sourceFormat property determines what BigQuery treats as an extra value: CSV: Trailing columns JSON: Named values that don't match any column names Google Cloud Datastore backups: This setting is ignored.
- "sourceUris": [ # [Required] The fully-qualified URIs that point to your data in Google Cloud Storage. Each URI can contain one '*' wildcard character and it must come after the 'bucket' name. Size limits related to load jobs apply to external data sources, plus an additional limit of 10 GB maximum size across all URIs. For Google Cloud Datastore backups, exactly one URI can be specified, and it must end with '.backup_info'. Also, the '*' wildcard character is not allowed.
+ "autodetect": True or False, # [Experimental] Try to detect schema and format options automatically. Any option specified explicitly will be honored.
+ "maxBadRecords": 42, # [Optional] The maximum number of bad records that BigQuery can ignore when reading data. If the number of bad records exceeds this value, an invalid error is returned in the job result. The default value is 0, which requires that all records are valid. This setting is ignored for Google Cloud Bigtable, Google Cloud Datastore backups and Avro formats.
+ "ignoreUnknownValues": True or False, # [Optional] Indicates if BigQuery should allow extra values that are not represented in the table schema. If true, the extra values are ignored. If false, records with extra columns are treated as bad records, and if there are too many bad records, an invalid error is returned in the job result. The default value is false. The sourceFormat property determines what BigQuery treats as an extra value: CSV: Trailing columns JSON: Named values that don't match any column names Google Cloud Bigtable: This setting is ignored. Google Cloud Datastore backups: This setting is ignored. Avro: This setting is ignored.
+ "sourceUris": [ # [Required] The fully-qualified URIs that point to your data in Google Cloud. For Google Cloud Storage URIs: Each URI can contain one '*' wildcard character and it must come after the 'bucket' name. Size limits related to load jobs apply to external data sources. For Google Cloud Bigtable URIs: Exactly one URI can be specified and it has be a fully specified and valid HTTPS URL for a Google Cloud Bigtable table. For Google Cloud Datastore backups, exactly one URI can be specified, and it must end with '.backup_info'. Also, the '*' wildcard character is not allowed.
"A String",
],
- "schema": { # [Optional] The schema for the data. Schema is required for CSV and JSON formats. Schema is disallowed for Google Cloud Datastore backups.
+ "bigtableOptions": { # [Optional] Additional options if sourceFormat is set to BIGTABLE.
+ "ignoreUnspecifiedColumnFamilies": True or False, # [Optional] If field is true, then the column families that are not specified in columnFamilies list are not exposed in the table schema. Otherwise, they are read with BYTES type values. The default value is false.
+ "columnFamilies": [ # [Optional] List of column families to expose in the table schema along with their types. This list restricts the column families that can be referenced in queries and specifies their value types. You can use this list to do type conversions - see the 'type' field for more details. If you leave this list empty, all column families are present in the table schema and their values are read as BYTES. During a query only the column families referenced in that query are read from Bigtable.
+ {
+ "familyId": "A String", # Identifier of the column family.
+ "type": "A String", # [Optional] The type to convert the value in cells of this column family. The values are expected to be encoded using HBase Bytes.toBytes function when using the BINARY encoding value. Following BigQuery types are allowed (case-sensitive) - BYTES STRING INTEGER FLOAT BOOLEAN Defaut type is BYTES. This can be overridden for a specific column by listing that column in 'columns' and specifying a type for it.
+ "onlyReadLatest": True or False, # [Optional] If this is set only the latest version of value are exposed for all columns in this column family. This can be overridden for a specific column by listing that column in 'columns' and specifying a different setting for that column.
+ "columns": [ # [Optional] Lists of columns that should be exposed as individual fields as opposed to a list of (column name, value) pairs. All columns whose qualifier matches a qualifier in this list can be accessed as .. Other columns can be accessed as a list through .Column field.
+ {
+ "encoding": "A String", # [Optional] The encoding of the values when the type is not STRING. Acceptable encoding values are: TEXT - indicates values are alphanumeric text strings. BINARY - indicates values are encoded using HBase Bytes.toBytes family of functions. 'encoding' can also be set at the column family level. However, the setting at this level takes precedence if 'encoding' is set at both levels.
+ "qualifierEncoded": "A String", # [Required] Qualifier of the column. Columns in the parent column family that has this exact qualifier are exposed as . field. If the qualifier is valid UTF-8 string, it can be specified in the qualifier_string field. Otherwise, a base-64 encoded value must be set to qualifier_encoded. The column field name is the same as the column qualifier. However, if the qualifier is not a valid BigQuery field identifier i.e. does not match [a-zA-Z][a-zA-Z0-9_]*, a valid identifier must be provided as field_name.
+ "fieldName": "A String", # [Optional] If the qualifier is not a valid BigQuery field identifier i.e. does not match [a-zA-Z][a-zA-Z0-9_]*, a valid identifier must be provided as the column field name and is used as field name in queries.
+ "onlyReadLatest": True or False, # [Optional] If this is set, only the latest version of value in this column are exposed. 'onlyReadLatest' can also be set at the column family level. However, the setting at this level takes precedence if 'onlyReadLatest' is set at both levels.
+ "qualifierString": "A String",
+ "type": "A String", # [Optional] The type to convert the value in cells of this column. The values are expected to be encoded using HBase Bytes.toBytes function when using the BINARY encoding value. Following BigQuery types are allowed (case-sensitive) - BYTES STRING INTEGER FLOAT BOOLEAN Defaut type is BYTES. 'type' can also be set at the column family level. However, the setting at this level takes precedence if 'type' is set at both levels.
+ },
+ ],
+ "encoding": "A String", # [Optional] The encoding of the values when the type is not STRING. Acceptable encoding values are: TEXT - indicates values are alphanumeric text strings. BINARY - indicates values are encoded using HBase Bytes.toBytes family of functions. This can be overridden for a specific column by listing that column in 'columns' and specifying an encoding for it.
+ },
+ ],
+ },
+ "sourceFormat": "A String", # [Required] The data format. For CSV files, specify "CSV". For Google sheets, specify "GOOGLE_SHEETS". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". For Avro files, specify "AVRO". For Google Cloud Datastore backups, specify "DATASTORE_BACKUP". [Experimental] For Google Cloud Bigtable, specify "BIGTABLE". Please note that reading from Google Cloud Bigtable is experimental and has to be enabled for your project. Please contact Google Cloud Support to enable this for your project.
+ "googleSheetsOptions": { # [Optional] Additional options if sourceFormat is set to GOOGLE_SHEETS.
+ "skipLeadingRows": "A String", # [Optional] The number of rows at the top of a sheet that BigQuery will skip when reading the data. The default value is 0. This property is useful if you have header rows that should be skipped. When autodetect is on, behavior is the following: * skipLeadingRows unspecified - Autodetect tries to detect headers in the first row. If they are not detected, the row is read as data. Otherwise data is read starting from the second row. * skipLeadingRows is 0 - Instructs autodetect that there are no headers and data should be read starting from the first row. * skipLeadingRows = N > 0 - Autodetect skips N-1 rows and tries to detect headers in row N. If headers are not detected, row N is just skipped. Otherwise row N is used to extract column names for the detected schema.
+ },
+ "schema": { # [Optional] The schema for the data. Schema is required for CSV and JSON formats. Schema is disallowed for Google Cloud Bigtable, Cloud Datastore backups, and Avro formats.
"fields": [ # Describes the fields in a table.
{
"fields": [ # [Optional] Describes the nested schema fields if the type property is set to RECORD.
# Object with schema name: TableFieldSchema
],
- "type": "A String", # [Required] The field data type. Possible values include STRING, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
+ "type": "A String", # [Required] The field data type. Possible values include STRING, BYTES, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
"description": "A String", # [Optional] The field description. The maximum length is 16K characters.
"name": "A String", # [Required] The field name. The name must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_), and must start with a letter or underscore. The maximum length is 128 characters.
"mode": "A String", # [Optional] The field mode. Possible values include NULLABLE, REQUIRED and REPEATED. The default value is NULLABLE.
@@ -613,7 +691,7 @@
"fields": [ # [Optional] Describes the nested schema fields if the type property is set to RECORD.
# Object with schema name: TableFieldSchema
],
- "type": "A String", # [Required] The field data type. Possible values include STRING, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
+ "type": "A String", # [Required] The field data type. Possible values include STRING, BYTES, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
"description": "A String", # [Optional] The field description. The maximum length is 16K characters.
"name": "A String", # [Required] The field name. The name must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_), and must start with a letter or underscore. The maximum length is 128 characters.
"mode": "A String", # [Optional] The field mode. Possible values include NULLABLE, REQUIRED and REPEATED. The default value is NULLABLE.
@@ -697,6 +775,19 @@
"datasetId": "A String", # [Required] The ID of the dataset containing this table.
},
],
+ "schema": { # [Output-only, Experimental] The schema of the results. Present only for successful dry run of non-legacy SQL queries.
+ "fields": [ # Describes the fields in a table.
+ {
+ "fields": [ # [Optional] Describes the nested schema fields if the type property is set to RECORD.
+ # Object with schema name: TableFieldSchema
+ ],
+ "type": "A String", # [Required] The field data type. Possible values include STRING, BYTES, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
+ "description": "A String", # [Optional] The field description. The maximum length is 16K characters.
+ "name": "A String", # [Required] The field name. The name must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_), and must start with a letter or underscore. The maximum length is 128 characters.
+ "mode": "A String", # [Optional] The field mode. Possible values include NULLABLE, REQUIRED and REPEATED. The default value is NULLABLE.
+ },
+ ],
+ },
},
"endTime": "A String", # [Output-only] End time of this job, in milliseconds since the epoch. This field will be present whenever a job is in the DONE state.
"extract": { # [Output-only] Statistics for an extract job.
@@ -713,9 +804,10 @@
"user_email": "A String", # [Output-only] Email address of the user who ran the job.
"configuration": { # [Required] Describes the job configuration.
"load": { # [Pick one] Configures a load job.
+ "sourceFormat": "A String", # [Optional] The format of the data files. For CSV files, specify "CSV". For datastore backups, specify "DATASTORE_BACKUP". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". For Avro, specify "AVRO". The default value is CSV.
"encoding": "A String", # [Optional] The character encoding of the data. The supported values are UTF-8 or ISO-8859-1. The default value is UTF-8. BigQuery decodes the data after the raw, binary data has been split using the values of the quote and fieldDelimiter properties.
"fieldDelimiter": "A String", # [Optional] The separator for fields in a CSV file. The separator can be any ISO-8859-1 single-byte character. To use a character in the range 128-255, you must encode the character as UTF8. BigQuery converts the string to ISO-8859-1 encoding, and then uses the first byte of the encoded string to split the data in its raw, binary state. BigQuery also supports the escape sequence "\t" to specify a tab separator. The default value is a comma (',').
- "sourceFormat": "A String", # [Optional] The format of the data files. For CSV files, specify "CSV". For datastore backups, specify "DATASTORE_BACKUP". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". The default value is CSV.
+ "autodetect": True or False, # [Experimental] Indicates if we should automatically infer the options and schema for CSV and JSON sources.
"destinationTable": { # [Required] The destination table to load the data into.
"projectId": "A String", # [Required] The ID of the project containing this table.
"tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
@@ -743,7 +835,7 @@
"fields": [ # [Optional] Describes the nested schema fields if the type property is set to RECORD.
# Object with schema name: TableFieldSchema
],
- "type": "A String", # [Required] The field data type. Possible values include STRING, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
+ "type": "A String", # [Required] The field data type. Possible values include STRING, BYTES, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
"description": "A String", # [Optional] The field description. The maximum length is 16K characters.
"name": "A String", # [Required] The field name. The name must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_), and must start with a letter or underscore. The maximum length is 128 characters.
"mode": "A String", # [Optional] The field mode. Possible values include NULLABLE, REQUIRED and REPEATED. The default value is NULLABLE.
@@ -796,7 +888,7 @@
"projectId": "A String", # [Optional] The ID of the project containing this dataset.
"datasetId": "A String", # [Required] A unique ID for this dataset, without the project name. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
},
- "useLegacySql": True or False, # [Experimental] Specifies whether to use BigQuery's legacy SQL dialect for this query. The default value is true. If set to false, the query will use BigQuery's updated SQL dialect with improved standards compliance. When using BigQuery's updated SQL, the values of allowLargeResults and flattenResults are ignored. Queries with useLegacySql set to false will be run as if allowLargeResults is true and flattenResults is false.
+ "useLegacySql": True or False, # [Experimental] Specifies whether to use BigQuery's legacy SQL dialect for this query. The default value is true. If set to false, the query will use BigQuery's standard SQL: https://cloud.google.com/bigquery/sql-reference/ When useLegacySql is set to false, the values of allowLargeResults and flattenResults are ignored; query will be run as if allowLargeResults is true and flattenResults is false.
"destinationTable": { # [Optional] Describes the table where the query results should be stored. If not present, a new table will be created to store the results.
"projectId": "A String", # [Required] The ID of the project containing this table.
"tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
@@ -810,28 +902,53 @@
"preserveNulls": True or False, # [Deprecated] This property is deprecated.
"tableDefinitions": { # [Optional] If querying an external data source outside of BigQuery, describes the data format, location and other properties of the data source. By defining these properties, the data source can then be queried as if it were a standard BigQuery table.
"a_key": {
- "compression": "A String", # [Optional] The compression type of the data source. Possible values include GZIP and NONE. The default value is NONE. This setting is ignored for Google Cloud Datastore backups.
+ "compression": "A String", # [Optional] The compression type of the data source. Possible values include GZIP and NONE. The default value is NONE. This setting is ignored for Google Cloud Bigtable, Google Cloud Datastore backups and Avro formats.
"csvOptions": { # Additional properties to set if sourceFormat is set to CSV.
"fieldDelimiter": "A String", # [Optional] The separator for fields in a CSV file. BigQuery converts the string to ISO-8859-1 encoding, and then uses the first byte of the encoded string to split the data in its raw, binary state. BigQuery also supports the escape sequence "\t" to specify a tab separator. The default value is a comma (',').
"encoding": "A String", # [Optional] The character encoding of the data. The supported values are UTF-8 or ISO-8859-1. The default value is UTF-8. BigQuery decodes the data after the raw, binary data has been split using the values of the quote and fieldDelimiter properties.
- "skipLeadingRows": 42, # [Optional] The number of rows at the top of a CSV file that BigQuery will skip when reading the data. The default value is 0. This property is useful if you have header rows in the file that should be skipped.
+ "skipLeadingRows": "A String", # [Optional] The number of rows at the top of a CSV file that BigQuery will skip when reading the data. The default value is 0. This property is useful if you have header rows in the file that should be skipped.
"allowJaggedRows": True or False, # [Optional] Indicates if BigQuery should accept rows that are missing trailing optional columns. If true, BigQuery treats missing trailing columns as null values. If false, records with missing trailing columns are treated as bad records, and if there are too many bad records, an invalid error is returned in the job result. The default value is false.
"quote": """, # [Optional] The value that is used to quote data sections in a CSV file. BigQuery converts the string to ISO-8859-1 encoding, and then uses the first byte of the encoded string to split the data in its raw, binary state. The default value is a double-quote ('"'). If your data does not contain quoted sections, set the property value to an empty string. If your data contains quoted newline characters, you must also set the allowQuotedNewlines property to true.
"allowQuotedNewlines": True or False, # [Optional] Indicates if BigQuery should allow quoted data sections that contain newline characters in a CSV file. The default value is false.
},
- "sourceFormat": "A String", # [Required] The data format. For CSV files, specify "CSV". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". For Google Cloud Datastore backups, specify "DATASTORE_BACKUP".
- "maxBadRecords": 42, # [Optional] The maximum number of bad records that BigQuery can ignore when reading data. If the number of bad records exceeds this value, an invalid error is returned in the job result. The default value is 0, which requires that all records are valid. This setting is ignored for Google Cloud Datastore backups.
- "ignoreUnknownValues": True or False, # [Optional] Indicates if BigQuery should allow extra values that are not represented in the table schema. If true, the extra values are ignored. If false, records with extra columns are treated as bad records, and if there are too many bad records, an invalid error is returned in the job result. The default value is false. The sourceFormat property determines what BigQuery treats as an extra value: CSV: Trailing columns JSON: Named values that don't match any column names Google Cloud Datastore backups: This setting is ignored.
- "sourceUris": [ # [Required] The fully-qualified URIs that point to your data in Google Cloud Storage. Each URI can contain one '*' wildcard character and it must come after the 'bucket' name. Size limits related to load jobs apply to external data sources, plus an additional limit of 10 GB maximum size across all URIs. For Google Cloud Datastore backups, exactly one URI can be specified, and it must end with '.backup_info'. Also, the '*' wildcard character is not allowed.
+ "autodetect": True or False, # [Experimental] Try to detect schema and format options automatically. Any option specified explicitly will be honored.
+ "maxBadRecords": 42, # [Optional] The maximum number of bad records that BigQuery can ignore when reading data. If the number of bad records exceeds this value, an invalid error is returned in the job result. The default value is 0, which requires that all records are valid. This setting is ignored for Google Cloud Bigtable, Google Cloud Datastore backups and Avro formats.
+ "ignoreUnknownValues": True or False, # [Optional] Indicates if BigQuery should allow extra values that are not represented in the table schema. If true, the extra values are ignored. If false, records with extra columns are treated as bad records, and if there are too many bad records, an invalid error is returned in the job result. The default value is false. The sourceFormat property determines what BigQuery treats as an extra value: CSV: Trailing columns JSON: Named values that don't match any column names Google Cloud Bigtable: This setting is ignored. Google Cloud Datastore backups: This setting is ignored. Avro: This setting is ignored.
+ "sourceUris": [ # [Required] The fully-qualified URIs that point to your data in Google Cloud. For Google Cloud Storage URIs: Each URI can contain one '*' wildcard character and it must come after the 'bucket' name. Size limits related to load jobs apply to external data sources. For Google Cloud Bigtable URIs: Exactly one URI can be specified and it has be a fully specified and valid HTTPS URL for a Google Cloud Bigtable table. For Google Cloud Datastore backups, exactly one URI can be specified, and it must end with '.backup_info'. Also, the '*' wildcard character is not allowed.
"A String",
],
- "schema": { # [Optional] The schema for the data. Schema is required for CSV and JSON formats. Schema is disallowed for Google Cloud Datastore backups.
+ "bigtableOptions": { # [Optional] Additional options if sourceFormat is set to BIGTABLE.
+ "ignoreUnspecifiedColumnFamilies": True or False, # [Optional] If field is true, then the column families that are not specified in columnFamilies list are not exposed in the table schema. Otherwise, they are read with BYTES type values. The default value is false.
+ "columnFamilies": [ # [Optional] List of column families to expose in the table schema along with their types. This list restricts the column families that can be referenced in queries and specifies their value types. You can use this list to do type conversions - see the 'type' field for more details. If you leave this list empty, all column families are present in the table schema and their values are read as BYTES. During a query only the column families referenced in that query are read from Bigtable.
+ {
+ "familyId": "A String", # Identifier of the column family.
+ "type": "A String", # [Optional] The type to convert the value in cells of this column family. The values are expected to be encoded using HBase Bytes.toBytes function when using the BINARY encoding value. Following BigQuery types are allowed (case-sensitive) - BYTES STRING INTEGER FLOAT BOOLEAN Defaut type is BYTES. This can be overridden for a specific column by listing that column in 'columns' and specifying a type for it.
+ "onlyReadLatest": True or False, # [Optional] If this is set only the latest version of value are exposed for all columns in this column family. This can be overridden for a specific column by listing that column in 'columns' and specifying a different setting for that column.
+ "columns": [ # [Optional] Lists of columns that should be exposed as individual fields as opposed to a list of (column name, value) pairs. All columns whose qualifier matches a qualifier in this list can be accessed as .. Other columns can be accessed as a list through .Column field.
+ {
+ "encoding": "A String", # [Optional] The encoding of the values when the type is not STRING. Acceptable encoding values are: TEXT - indicates values are alphanumeric text strings. BINARY - indicates values are encoded using HBase Bytes.toBytes family of functions. 'encoding' can also be set at the column family level. However, the setting at this level takes precedence if 'encoding' is set at both levels.
+ "qualifierEncoded": "A String", # [Required] Qualifier of the column. Columns in the parent column family that has this exact qualifier are exposed as . field. If the qualifier is valid UTF-8 string, it can be specified in the qualifier_string field. Otherwise, a base-64 encoded value must be set to qualifier_encoded. The column field name is the same as the column qualifier. However, if the qualifier is not a valid BigQuery field identifier i.e. does not match [a-zA-Z][a-zA-Z0-9_]*, a valid identifier must be provided as field_name.
+ "fieldName": "A String", # [Optional] If the qualifier is not a valid BigQuery field identifier i.e. does not match [a-zA-Z][a-zA-Z0-9_]*, a valid identifier must be provided as the column field name and is used as field name in queries.
+ "onlyReadLatest": True or False, # [Optional] If this is set, only the latest version of value in this column are exposed. 'onlyReadLatest' can also be set at the column family level. However, the setting at this level takes precedence if 'onlyReadLatest' is set at both levels.
+ "qualifierString": "A String",
+ "type": "A String", # [Optional] The type to convert the value in cells of this column. The values are expected to be encoded using HBase Bytes.toBytes function when using the BINARY encoding value. Following BigQuery types are allowed (case-sensitive) - BYTES STRING INTEGER FLOAT BOOLEAN Defaut type is BYTES. 'type' can also be set at the column family level. However, the setting at this level takes precedence if 'type' is set at both levels.
+ },
+ ],
+ "encoding": "A String", # [Optional] The encoding of the values when the type is not STRING. Acceptable encoding values are: TEXT - indicates values are alphanumeric text strings. BINARY - indicates values are encoded using HBase Bytes.toBytes family of functions. This can be overridden for a specific column by listing that column in 'columns' and specifying an encoding for it.
+ },
+ ],
+ },
+ "sourceFormat": "A String", # [Required] The data format. For CSV files, specify "CSV". For Google sheets, specify "GOOGLE_SHEETS". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". For Avro files, specify "AVRO". For Google Cloud Datastore backups, specify "DATASTORE_BACKUP". [Experimental] For Google Cloud Bigtable, specify "BIGTABLE". Please note that reading from Google Cloud Bigtable is experimental and has to be enabled for your project. Please contact Google Cloud Support to enable this for your project.
+ "googleSheetsOptions": { # [Optional] Additional options if sourceFormat is set to GOOGLE_SHEETS.
+ "skipLeadingRows": "A String", # [Optional] The number of rows at the top of a sheet that BigQuery will skip when reading the data. The default value is 0. This property is useful if you have header rows that should be skipped. When autodetect is on, behavior is the following: * skipLeadingRows unspecified - Autodetect tries to detect headers in the first row. If they are not detected, the row is read as data. Otherwise data is read starting from the second row. * skipLeadingRows is 0 - Instructs autodetect that there are no headers and data should be read starting from the first row. * skipLeadingRows = N > 0 - Autodetect skips N-1 rows and tries to detect headers in row N. If headers are not detected, row N is just skipped. Otherwise row N is used to extract column names for the detected schema.
+ },
+ "schema": { # [Optional] The schema for the data. Schema is required for CSV and JSON formats. Schema is disallowed for Google Cloud Bigtable, Cloud Datastore backups, and Avro formats.
"fields": [ # Describes the fields in a table.
{
"fields": [ # [Optional] Describes the nested schema fields if the type property is set to RECORD.
# Object with schema name: TableFieldSchema
],
- "type": "A String", # [Required] The field data type. Possible values include STRING, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
+ "type": "A String", # [Required] The field data type. Possible values include STRING, BYTES, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
"description": "A String", # [Optional] The field description. The maximum length is 16K characters.
"name": "A String", # [Required] The field name. The name must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_), and must start with a letter or underscore. The maximum length is 128 characters.
"mode": "A String", # [Optional] The field mode. Possible values include NULLABLE, REQUIRED and REPEATED. The default value is NULLABLE.
@@ -922,6 +1039,19 @@
"datasetId": "A String", # [Required] The ID of the dataset containing this table.
},
],
+ "schema": { # [Output-only, Experimental] The schema of the results. Present only for successful dry run of non-legacy SQL queries.
+ "fields": [ # Describes the fields in a table.
+ {
+ "fields": [ # [Optional] Describes the nested schema fields if the type property is set to RECORD.
+ # Object with schema name: TableFieldSchema
+ ],
+ "type": "A String", # [Required] The field data type. Possible values include STRING, BYTES, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
+ "description": "A String", # [Optional] The field description. The maximum length is 16K characters.
+ "name": "A String", # [Required] The field name. The name must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_), and must start with a letter or underscore. The maximum length is 128 characters.
+ "mode": "A String", # [Optional] The field mode. Possible values include NULLABLE, REQUIRED and REPEATED. The default value is NULLABLE.
+ },
+ ],
+ },
},
"endTime": "A String", # [Output-only] End time of this job, in milliseconds since the epoch. This field will be present whenever a job is in the DONE state.
"extract": { # [Output-only] Statistics for an extract job.
@@ -938,9 +1068,10 @@
"user_email": "A String", # [Output-only] Email address of the user who ran the job.
"configuration": { # [Required] Describes the job configuration.
"load": { # [Pick one] Configures a load job.
+ "sourceFormat": "A String", # [Optional] The format of the data files. For CSV files, specify "CSV". For datastore backups, specify "DATASTORE_BACKUP". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". For Avro, specify "AVRO". The default value is CSV.
"encoding": "A String", # [Optional] The character encoding of the data. The supported values are UTF-8 or ISO-8859-1. The default value is UTF-8. BigQuery decodes the data after the raw, binary data has been split using the values of the quote and fieldDelimiter properties.
"fieldDelimiter": "A String", # [Optional] The separator for fields in a CSV file. The separator can be any ISO-8859-1 single-byte character. To use a character in the range 128-255, you must encode the character as UTF8. BigQuery converts the string to ISO-8859-1 encoding, and then uses the first byte of the encoded string to split the data in its raw, binary state. BigQuery also supports the escape sequence "\t" to specify a tab separator. The default value is a comma (',').
- "sourceFormat": "A String", # [Optional] The format of the data files. For CSV files, specify "CSV". For datastore backups, specify "DATASTORE_BACKUP". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". The default value is CSV.
+ "autodetect": True or False, # [Experimental] Indicates if we should automatically infer the options and schema for CSV and JSON sources.
"destinationTable": { # [Required] The destination table to load the data into.
"projectId": "A String", # [Required] The ID of the project containing this table.
"tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
@@ -968,7 +1099,7 @@
"fields": [ # [Optional] Describes the nested schema fields if the type property is set to RECORD.
# Object with schema name: TableFieldSchema
],
- "type": "A String", # [Required] The field data type. Possible values include STRING, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
+ "type": "A String", # [Required] The field data type. Possible values include STRING, BYTES, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
"description": "A String", # [Optional] The field description. The maximum length is 16K characters.
"name": "A String", # [Required] The field name. The name must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_), and must start with a letter or underscore. The maximum length is 128 characters.
"mode": "A String", # [Optional] The field mode. Possible values include NULLABLE, REQUIRED and REPEATED. The default value is NULLABLE.
@@ -1021,7 +1152,7 @@
"projectId": "A String", # [Optional] The ID of the project containing this dataset.
"datasetId": "A String", # [Required] A unique ID for this dataset, without the project name. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
},
- "useLegacySql": True or False, # [Experimental] Specifies whether to use BigQuery's legacy SQL dialect for this query. The default value is true. If set to false, the query will use BigQuery's updated SQL dialect with improved standards compliance. When using BigQuery's updated SQL, the values of allowLargeResults and flattenResults are ignored. Queries with useLegacySql set to false will be run as if allowLargeResults is true and flattenResults is false.
+ "useLegacySql": True or False, # [Experimental] Specifies whether to use BigQuery's legacy SQL dialect for this query. The default value is true. If set to false, the query will use BigQuery's standard SQL: https://cloud.google.com/bigquery/sql-reference/ When useLegacySql is set to false, the values of allowLargeResults and flattenResults are ignored; query will be run as if allowLargeResults is true and flattenResults is false.
"destinationTable": { # [Optional] Describes the table where the query results should be stored. If not present, a new table will be created to store the results.
"projectId": "A String", # [Required] The ID of the project containing this table.
"tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
@@ -1035,28 +1166,53 @@
"preserveNulls": True or False, # [Deprecated] This property is deprecated.
"tableDefinitions": { # [Optional] If querying an external data source outside of BigQuery, describes the data format, location and other properties of the data source. By defining these properties, the data source can then be queried as if it were a standard BigQuery table.
"a_key": {
- "compression": "A String", # [Optional] The compression type of the data source. Possible values include GZIP and NONE. The default value is NONE. This setting is ignored for Google Cloud Datastore backups.
+ "compression": "A String", # [Optional] The compression type of the data source. Possible values include GZIP and NONE. The default value is NONE. This setting is ignored for Google Cloud Bigtable, Google Cloud Datastore backups and Avro formats.
"csvOptions": { # Additional properties to set if sourceFormat is set to CSV.
"fieldDelimiter": "A String", # [Optional] The separator for fields in a CSV file. BigQuery converts the string to ISO-8859-1 encoding, and then uses the first byte of the encoded string to split the data in its raw, binary state. BigQuery also supports the escape sequence "\t" to specify a tab separator. The default value is a comma (',').
"encoding": "A String", # [Optional] The character encoding of the data. The supported values are UTF-8 or ISO-8859-1. The default value is UTF-8. BigQuery decodes the data after the raw, binary data has been split using the values of the quote and fieldDelimiter properties.
- "skipLeadingRows": 42, # [Optional] The number of rows at the top of a CSV file that BigQuery will skip when reading the data. The default value is 0. This property is useful if you have header rows in the file that should be skipped.
+ "skipLeadingRows": "A String", # [Optional] The number of rows at the top of a CSV file that BigQuery will skip when reading the data. The default value is 0. This property is useful if you have header rows in the file that should be skipped.
"allowJaggedRows": True or False, # [Optional] Indicates if BigQuery should accept rows that are missing trailing optional columns. If true, BigQuery treats missing trailing columns as null values. If false, records with missing trailing columns are treated as bad records, and if there are too many bad records, an invalid error is returned in the job result. The default value is false.
"quote": """, # [Optional] The value that is used to quote data sections in a CSV file. BigQuery converts the string to ISO-8859-1 encoding, and then uses the first byte of the encoded string to split the data in its raw, binary state. The default value is a double-quote ('"'). If your data does not contain quoted sections, set the property value to an empty string. If your data contains quoted newline characters, you must also set the allowQuotedNewlines property to true.
"allowQuotedNewlines": True or False, # [Optional] Indicates if BigQuery should allow quoted data sections that contain newline characters in a CSV file. The default value is false.
},
- "sourceFormat": "A String", # [Required] The data format. For CSV files, specify "CSV". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". For Google Cloud Datastore backups, specify "DATASTORE_BACKUP".
- "maxBadRecords": 42, # [Optional] The maximum number of bad records that BigQuery can ignore when reading data. If the number of bad records exceeds this value, an invalid error is returned in the job result. The default value is 0, which requires that all records are valid. This setting is ignored for Google Cloud Datastore backups.
- "ignoreUnknownValues": True or False, # [Optional] Indicates if BigQuery should allow extra values that are not represented in the table schema. If true, the extra values are ignored. If false, records with extra columns are treated as bad records, and if there are too many bad records, an invalid error is returned in the job result. The default value is false. The sourceFormat property determines what BigQuery treats as an extra value: CSV: Trailing columns JSON: Named values that don't match any column names Google Cloud Datastore backups: This setting is ignored.
- "sourceUris": [ # [Required] The fully-qualified URIs that point to your data in Google Cloud Storage. Each URI can contain one '*' wildcard character and it must come after the 'bucket' name. Size limits related to load jobs apply to external data sources, plus an additional limit of 10 GB maximum size across all URIs. For Google Cloud Datastore backups, exactly one URI can be specified, and it must end with '.backup_info'. Also, the '*' wildcard character is not allowed.
+ "autodetect": True or False, # [Experimental] Try to detect schema and format options automatically. Any option specified explicitly will be honored.
+ "maxBadRecords": 42, # [Optional] The maximum number of bad records that BigQuery can ignore when reading data. If the number of bad records exceeds this value, an invalid error is returned in the job result. The default value is 0, which requires that all records are valid. This setting is ignored for Google Cloud Bigtable, Google Cloud Datastore backups and Avro formats.
+ "ignoreUnknownValues": True or False, # [Optional] Indicates if BigQuery should allow extra values that are not represented in the table schema. If true, the extra values are ignored. If false, records with extra columns are treated as bad records, and if there are too many bad records, an invalid error is returned in the job result. The default value is false. The sourceFormat property determines what BigQuery treats as an extra value: CSV: Trailing columns JSON: Named values that don't match any column names Google Cloud Bigtable: This setting is ignored. Google Cloud Datastore backups: This setting is ignored. Avro: This setting is ignored.
+ "sourceUris": [ # [Required] The fully-qualified URIs that point to your data in Google Cloud. For Google Cloud Storage URIs: Each URI can contain one '*' wildcard character and it must come after the 'bucket' name. Size limits related to load jobs apply to external data sources. For Google Cloud Bigtable URIs: Exactly one URI can be specified and it has be a fully specified and valid HTTPS URL for a Google Cloud Bigtable table. For Google Cloud Datastore backups, exactly one URI can be specified, and it must end with '.backup_info'. Also, the '*' wildcard character is not allowed.
"A String",
],
- "schema": { # [Optional] The schema for the data. Schema is required for CSV and JSON formats. Schema is disallowed for Google Cloud Datastore backups.
+ "bigtableOptions": { # [Optional] Additional options if sourceFormat is set to BIGTABLE.
+ "ignoreUnspecifiedColumnFamilies": True or False, # [Optional] If field is true, then the column families that are not specified in columnFamilies list are not exposed in the table schema. Otherwise, they are read with BYTES type values. The default value is false.
+ "columnFamilies": [ # [Optional] List of column families to expose in the table schema along with their types. This list restricts the column families that can be referenced in queries and specifies their value types. You can use this list to do type conversions - see the 'type' field for more details. If you leave this list empty, all column families are present in the table schema and their values are read as BYTES. During a query only the column families referenced in that query are read from Bigtable.
+ {
+ "familyId": "A String", # Identifier of the column family.
+ "type": "A String", # [Optional] The type to convert the value in cells of this column family. The values are expected to be encoded using HBase Bytes.toBytes function when using the BINARY encoding value. Following BigQuery types are allowed (case-sensitive) - BYTES STRING INTEGER FLOAT BOOLEAN Defaut type is BYTES. This can be overridden for a specific column by listing that column in 'columns' and specifying a type for it.
+ "onlyReadLatest": True or False, # [Optional] If this is set only the latest version of value are exposed for all columns in this column family. This can be overridden for a specific column by listing that column in 'columns' and specifying a different setting for that column.
+ "columns": [ # [Optional] Lists of columns that should be exposed as individual fields as opposed to a list of (column name, value) pairs. All columns whose qualifier matches a qualifier in this list can be accessed as .. Other columns can be accessed as a list through .Column field.
+ {
+ "encoding": "A String", # [Optional] The encoding of the values when the type is not STRING. Acceptable encoding values are: TEXT - indicates values are alphanumeric text strings. BINARY - indicates values are encoded using HBase Bytes.toBytes family of functions. 'encoding' can also be set at the column family level. However, the setting at this level takes precedence if 'encoding' is set at both levels.
+ "qualifierEncoded": "A String", # [Required] Qualifier of the column. Columns in the parent column family that has this exact qualifier are exposed as . field. If the qualifier is valid UTF-8 string, it can be specified in the qualifier_string field. Otherwise, a base-64 encoded value must be set to qualifier_encoded. The column field name is the same as the column qualifier. However, if the qualifier is not a valid BigQuery field identifier i.e. does not match [a-zA-Z][a-zA-Z0-9_]*, a valid identifier must be provided as field_name.
+ "fieldName": "A String", # [Optional] If the qualifier is not a valid BigQuery field identifier i.e. does not match [a-zA-Z][a-zA-Z0-9_]*, a valid identifier must be provided as the column field name and is used as field name in queries.
+ "onlyReadLatest": True or False, # [Optional] If this is set, only the latest version of value in this column are exposed. 'onlyReadLatest' can also be set at the column family level. However, the setting at this level takes precedence if 'onlyReadLatest' is set at both levels.
+ "qualifierString": "A String",
+ "type": "A String", # [Optional] The type to convert the value in cells of this column. The values are expected to be encoded using HBase Bytes.toBytes function when using the BINARY encoding value. Following BigQuery types are allowed (case-sensitive) - BYTES STRING INTEGER FLOAT BOOLEAN Defaut type is BYTES. 'type' can also be set at the column family level. However, the setting at this level takes precedence if 'type' is set at both levels.
+ },
+ ],
+ "encoding": "A String", # [Optional] The encoding of the values when the type is not STRING. Acceptable encoding values are: TEXT - indicates values are alphanumeric text strings. BINARY - indicates values are encoded using HBase Bytes.toBytes family of functions. This can be overridden for a specific column by listing that column in 'columns' and specifying an encoding for it.
+ },
+ ],
+ },
+ "sourceFormat": "A String", # [Required] The data format. For CSV files, specify "CSV". For Google sheets, specify "GOOGLE_SHEETS". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". For Avro files, specify "AVRO". For Google Cloud Datastore backups, specify "DATASTORE_BACKUP". [Experimental] For Google Cloud Bigtable, specify "BIGTABLE". Please note that reading from Google Cloud Bigtable is experimental and has to be enabled for your project. Please contact Google Cloud Support to enable this for your project.
+ "googleSheetsOptions": { # [Optional] Additional options if sourceFormat is set to GOOGLE_SHEETS.
+ "skipLeadingRows": "A String", # [Optional] The number of rows at the top of a sheet that BigQuery will skip when reading the data. The default value is 0. This property is useful if you have header rows that should be skipped. When autodetect is on, behavior is the following: * skipLeadingRows unspecified - Autodetect tries to detect headers in the first row. If they are not detected, the row is read as data. Otherwise data is read starting from the second row. * skipLeadingRows is 0 - Instructs autodetect that there are no headers and data should be read starting from the first row. * skipLeadingRows = N > 0 - Autodetect skips N-1 rows and tries to detect headers in row N. If headers are not detected, row N is just skipped. Otherwise row N is used to extract column names for the detected schema.
+ },
+ "schema": { # [Optional] The schema for the data. Schema is required for CSV and JSON formats. Schema is disallowed for Google Cloud Bigtable, Cloud Datastore backups, and Avro formats.
"fields": [ # Describes the fields in a table.
{
"fields": [ # [Optional] Describes the nested schema fields if the type property is set to RECORD.
# Object with schema name: TableFieldSchema
],
- "type": "A String", # [Required] The field data type. Possible values include STRING, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
+ "type": "A String", # [Required] The field data type. Possible values include STRING, BYTES, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
"description": "A String", # [Optional] The field description. The maximum length is 16K characters.
"name": "A String", # [Required] The field name. The name must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_), and must start with a letter or underscore. The maximum length is 128 characters.
"mode": "A String", # [Optional] The field mode. Possible values include NULLABLE, REQUIRED and REPEATED. The default value is NULLABLE.
@@ -1170,6 +1326,19 @@
"datasetId": "A String", # [Required] The ID of the dataset containing this table.
},
],
+ "schema": { # [Output-only, Experimental] The schema of the results. Present only for successful dry run of non-legacy SQL queries.
+ "fields": [ # Describes the fields in a table.
+ {
+ "fields": [ # [Optional] Describes the nested schema fields if the type property is set to RECORD.
+ # Object with schema name: TableFieldSchema
+ ],
+ "type": "A String", # [Required] The field data type. Possible values include STRING, BYTES, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
+ "description": "A String", # [Optional] The field description. The maximum length is 16K characters.
+ "name": "A String", # [Required] The field name. The name must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_), and must start with a letter or underscore. The maximum length is 128 characters.
+ "mode": "A String", # [Optional] The field mode. Possible values include NULLABLE, REQUIRED and REPEATED. The default value is NULLABLE.
+ },
+ ],
+ },
},
"endTime": "A String", # [Output-only] End time of this job, in milliseconds since the epoch. This field will be present whenever a job is in the DONE state.
"extract": { # [Output-only] Statistics for an extract job.
@@ -1186,9 +1355,10 @@
"user_email": "A String", # [Full-projection-only] Email address of the user who ran the job.
"configuration": { # [Full-projection-only] Specifies the job configuration.
"load": { # [Pick one] Configures a load job.
+ "sourceFormat": "A String", # [Optional] The format of the data files. For CSV files, specify "CSV". For datastore backups, specify "DATASTORE_BACKUP". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". For Avro, specify "AVRO". The default value is CSV.
"encoding": "A String", # [Optional] The character encoding of the data. The supported values are UTF-8 or ISO-8859-1. The default value is UTF-8. BigQuery decodes the data after the raw, binary data has been split using the values of the quote and fieldDelimiter properties.
"fieldDelimiter": "A String", # [Optional] The separator for fields in a CSV file. The separator can be any ISO-8859-1 single-byte character. To use a character in the range 128-255, you must encode the character as UTF8. BigQuery converts the string to ISO-8859-1 encoding, and then uses the first byte of the encoded string to split the data in its raw, binary state. BigQuery also supports the escape sequence "\t" to specify a tab separator. The default value is a comma (',').
- "sourceFormat": "A String", # [Optional] The format of the data files. For CSV files, specify "CSV". For datastore backups, specify "DATASTORE_BACKUP". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". The default value is CSV.
+ "autodetect": True or False, # [Experimental] Indicates if we should automatically infer the options and schema for CSV and JSON sources.
"destinationTable": { # [Required] The destination table to load the data into.
"projectId": "A String", # [Required] The ID of the project containing this table.
"tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
@@ -1216,7 +1386,7 @@
"fields": [ # [Optional] Describes the nested schema fields if the type property is set to RECORD.
# Object with schema name: TableFieldSchema
],
- "type": "A String", # [Required] The field data type. Possible values include STRING, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
+ "type": "A String", # [Required] The field data type. Possible values include STRING, BYTES, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
"description": "A String", # [Optional] The field description. The maximum length is 16K characters.
"name": "A String", # [Required] The field name. The name must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_), and must start with a letter or underscore. The maximum length is 128 characters.
"mode": "A String", # [Optional] The field mode. Possible values include NULLABLE, REQUIRED and REPEATED. The default value is NULLABLE.
@@ -1269,7 +1439,7 @@
"projectId": "A String", # [Optional] The ID of the project containing this dataset.
"datasetId": "A String", # [Required] A unique ID for this dataset, without the project name. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
},
- "useLegacySql": True or False, # [Experimental] Specifies whether to use BigQuery's legacy SQL dialect for this query. The default value is true. If set to false, the query will use BigQuery's updated SQL dialect with improved standards compliance. When using BigQuery's updated SQL, the values of allowLargeResults and flattenResults are ignored. Queries with useLegacySql set to false will be run as if allowLargeResults is true and flattenResults is false.
+ "useLegacySql": True or False, # [Experimental] Specifies whether to use BigQuery's legacy SQL dialect for this query. The default value is true. If set to false, the query will use BigQuery's standard SQL: https://cloud.google.com/bigquery/sql-reference/ When useLegacySql is set to false, the values of allowLargeResults and flattenResults are ignored; query will be run as if allowLargeResults is true and flattenResults is false.
"destinationTable": { # [Optional] Describes the table where the query results should be stored. If not present, a new table will be created to store the results.
"projectId": "A String", # [Required] The ID of the project containing this table.
"tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
@@ -1283,28 +1453,53 @@
"preserveNulls": True or False, # [Deprecated] This property is deprecated.
"tableDefinitions": { # [Optional] If querying an external data source outside of BigQuery, describes the data format, location and other properties of the data source. By defining these properties, the data source can then be queried as if it were a standard BigQuery table.
"a_key": {
- "compression": "A String", # [Optional] The compression type of the data source. Possible values include GZIP and NONE. The default value is NONE. This setting is ignored for Google Cloud Datastore backups.
+ "compression": "A String", # [Optional] The compression type of the data source. Possible values include GZIP and NONE. The default value is NONE. This setting is ignored for Google Cloud Bigtable, Google Cloud Datastore backups and Avro formats.
"csvOptions": { # Additional properties to set if sourceFormat is set to CSV.
"fieldDelimiter": "A String", # [Optional] The separator for fields in a CSV file. BigQuery converts the string to ISO-8859-1 encoding, and then uses the first byte of the encoded string to split the data in its raw, binary state. BigQuery also supports the escape sequence "\t" to specify a tab separator. The default value is a comma (',').
"encoding": "A String", # [Optional] The character encoding of the data. The supported values are UTF-8 or ISO-8859-1. The default value is UTF-8. BigQuery decodes the data after the raw, binary data has been split using the values of the quote and fieldDelimiter properties.
- "skipLeadingRows": 42, # [Optional] The number of rows at the top of a CSV file that BigQuery will skip when reading the data. The default value is 0. This property is useful if you have header rows in the file that should be skipped.
+ "skipLeadingRows": "A String", # [Optional] The number of rows at the top of a CSV file that BigQuery will skip when reading the data. The default value is 0. This property is useful if you have header rows in the file that should be skipped.
"allowJaggedRows": True or False, # [Optional] Indicates if BigQuery should accept rows that are missing trailing optional columns. If true, BigQuery treats missing trailing columns as null values. If false, records with missing trailing columns are treated as bad records, and if there are too many bad records, an invalid error is returned in the job result. The default value is false.
"quote": """, # [Optional] The value that is used to quote data sections in a CSV file. BigQuery converts the string to ISO-8859-1 encoding, and then uses the first byte of the encoded string to split the data in its raw, binary state. The default value is a double-quote ('"'). If your data does not contain quoted sections, set the property value to an empty string. If your data contains quoted newline characters, you must also set the allowQuotedNewlines property to true.
"allowQuotedNewlines": True or False, # [Optional] Indicates if BigQuery should allow quoted data sections that contain newline characters in a CSV file. The default value is false.
},
- "sourceFormat": "A String", # [Required] The data format. For CSV files, specify "CSV". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". For Google Cloud Datastore backups, specify "DATASTORE_BACKUP".
- "maxBadRecords": 42, # [Optional] The maximum number of bad records that BigQuery can ignore when reading data. If the number of bad records exceeds this value, an invalid error is returned in the job result. The default value is 0, which requires that all records are valid. This setting is ignored for Google Cloud Datastore backups.
- "ignoreUnknownValues": True or False, # [Optional] Indicates if BigQuery should allow extra values that are not represented in the table schema. If true, the extra values are ignored. If false, records with extra columns are treated as bad records, and if there are too many bad records, an invalid error is returned in the job result. The default value is false. The sourceFormat property determines what BigQuery treats as an extra value: CSV: Trailing columns JSON: Named values that don't match any column names Google Cloud Datastore backups: This setting is ignored.
- "sourceUris": [ # [Required] The fully-qualified URIs that point to your data in Google Cloud Storage. Each URI can contain one '*' wildcard character and it must come after the 'bucket' name. Size limits related to load jobs apply to external data sources, plus an additional limit of 10 GB maximum size across all URIs. For Google Cloud Datastore backups, exactly one URI can be specified, and it must end with '.backup_info'. Also, the '*' wildcard character is not allowed.
+ "autodetect": True or False, # [Experimental] Try to detect schema and format options automatically. Any option specified explicitly will be honored.
+ "maxBadRecords": 42, # [Optional] The maximum number of bad records that BigQuery can ignore when reading data. If the number of bad records exceeds this value, an invalid error is returned in the job result. The default value is 0, which requires that all records are valid. This setting is ignored for Google Cloud Bigtable, Google Cloud Datastore backups and Avro formats.
+ "ignoreUnknownValues": True or False, # [Optional] Indicates if BigQuery should allow extra values that are not represented in the table schema. If true, the extra values are ignored. If false, records with extra columns are treated as bad records, and if there are too many bad records, an invalid error is returned in the job result. The default value is false. The sourceFormat property determines what BigQuery treats as an extra value: CSV: Trailing columns JSON: Named values that don't match any column names Google Cloud Bigtable: This setting is ignored. Google Cloud Datastore backups: This setting is ignored. Avro: This setting is ignored.
+ "sourceUris": [ # [Required] The fully-qualified URIs that point to your data in Google Cloud. For Google Cloud Storage URIs: Each URI can contain one '*' wildcard character and it must come after the 'bucket' name. Size limits related to load jobs apply to external data sources. For Google Cloud Bigtable URIs: Exactly one URI can be specified and it has be a fully specified and valid HTTPS URL for a Google Cloud Bigtable table. For Google Cloud Datastore backups, exactly one URI can be specified, and it must end with '.backup_info'. Also, the '*' wildcard character is not allowed.
"A String",
],
- "schema": { # [Optional] The schema for the data. Schema is required for CSV and JSON formats. Schema is disallowed for Google Cloud Datastore backups.
+ "bigtableOptions": { # [Optional] Additional options if sourceFormat is set to BIGTABLE.
+ "ignoreUnspecifiedColumnFamilies": True or False, # [Optional] If field is true, then the column families that are not specified in columnFamilies list are not exposed in the table schema. Otherwise, they are read with BYTES type values. The default value is false.
+ "columnFamilies": [ # [Optional] List of column families to expose in the table schema along with their types. This list restricts the column families that can be referenced in queries and specifies their value types. You can use this list to do type conversions - see the 'type' field for more details. If you leave this list empty, all column families are present in the table schema and their values are read as BYTES. During a query only the column families referenced in that query are read from Bigtable.
+ {
+ "familyId": "A String", # Identifier of the column family.
+ "type": "A String", # [Optional] The type to convert the value in cells of this column family. The values are expected to be encoded using HBase Bytes.toBytes function when using the BINARY encoding value. Following BigQuery types are allowed (case-sensitive) - BYTES STRING INTEGER FLOAT BOOLEAN Defaut type is BYTES. This can be overridden for a specific column by listing that column in 'columns' and specifying a type for it.
+ "onlyReadLatest": True or False, # [Optional] If this is set only the latest version of value are exposed for all columns in this column family. This can be overridden for a specific column by listing that column in 'columns' and specifying a different setting for that column.
+ "columns": [ # [Optional] Lists of columns that should be exposed as individual fields as opposed to a list of (column name, value) pairs. All columns whose qualifier matches a qualifier in this list can be accessed as .. Other columns can be accessed as a list through .Column field.
+ {
+ "encoding": "A String", # [Optional] The encoding of the values when the type is not STRING. Acceptable encoding values are: TEXT - indicates values are alphanumeric text strings. BINARY - indicates values are encoded using HBase Bytes.toBytes family of functions. 'encoding' can also be set at the column family level. However, the setting at this level takes precedence if 'encoding' is set at both levels.
+ "qualifierEncoded": "A String", # [Required] Qualifier of the column. Columns in the parent column family that has this exact qualifier are exposed as . field. If the qualifier is valid UTF-8 string, it can be specified in the qualifier_string field. Otherwise, a base-64 encoded value must be set to qualifier_encoded. The column field name is the same as the column qualifier. However, if the qualifier is not a valid BigQuery field identifier i.e. does not match [a-zA-Z][a-zA-Z0-9_]*, a valid identifier must be provided as field_name.
+ "fieldName": "A String", # [Optional] If the qualifier is not a valid BigQuery field identifier i.e. does not match [a-zA-Z][a-zA-Z0-9_]*, a valid identifier must be provided as the column field name and is used as field name in queries.
+ "onlyReadLatest": True or False, # [Optional] If this is set, only the latest version of value in this column are exposed. 'onlyReadLatest' can also be set at the column family level. However, the setting at this level takes precedence if 'onlyReadLatest' is set at both levels.
+ "qualifierString": "A String",
+ "type": "A String", # [Optional] The type to convert the value in cells of this column. The values are expected to be encoded using HBase Bytes.toBytes function when using the BINARY encoding value. Following BigQuery types are allowed (case-sensitive) - BYTES STRING INTEGER FLOAT BOOLEAN Defaut type is BYTES. 'type' can also be set at the column family level. However, the setting at this level takes precedence if 'type' is set at both levels.
+ },
+ ],
+ "encoding": "A String", # [Optional] The encoding of the values when the type is not STRING. Acceptable encoding values are: TEXT - indicates values are alphanumeric text strings. BINARY - indicates values are encoded using HBase Bytes.toBytes family of functions. This can be overridden for a specific column by listing that column in 'columns' and specifying an encoding for it.
+ },
+ ],
+ },
+ "sourceFormat": "A String", # [Required] The data format. For CSV files, specify "CSV". For Google sheets, specify "GOOGLE_SHEETS". For newline-delimited JSON, specify "NEWLINE_DELIMITED_JSON". For Avro files, specify "AVRO". For Google Cloud Datastore backups, specify "DATASTORE_BACKUP". [Experimental] For Google Cloud Bigtable, specify "BIGTABLE". Please note that reading from Google Cloud Bigtable is experimental and has to be enabled for your project. Please contact Google Cloud Support to enable this for your project.
+ "googleSheetsOptions": { # [Optional] Additional options if sourceFormat is set to GOOGLE_SHEETS.
+ "skipLeadingRows": "A String", # [Optional] The number of rows at the top of a sheet that BigQuery will skip when reading the data. The default value is 0. This property is useful if you have header rows that should be skipped. When autodetect is on, behavior is the following: * skipLeadingRows unspecified - Autodetect tries to detect headers in the first row. If they are not detected, the row is read as data. Otherwise data is read starting from the second row. * skipLeadingRows is 0 - Instructs autodetect that there are no headers and data should be read starting from the first row. * skipLeadingRows = N > 0 - Autodetect skips N-1 rows and tries to detect headers in row N. If headers are not detected, row N is just skipped. Otherwise row N is used to extract column names for the detected schema.
+ },
+ "schema": { # [Optional] The schema for the data. Schema is required for CSV and JSON formats. Schema is disallowed for Google Cloud Bigtable, Cloud Datastore backups, and Avro formats.
"fields": [ # Describes the fields in a table.
{
"fields": [ # [Optional] Describes the nested schema fields if the type property is set to RECORD.
# Object with schema name: TableFieldSchema
],
- "type": "A String", # [Required] The field data type. Possible values include STRING, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
+ "type": "A String", # [Required] The field data type. Possible values include STRING, BYTES, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
"description": "A String", # [Optional] The field description. The maximum length is 16K characters.
"name": "A String", # [Required] The field name. The name must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_), and must start with a letter or underscore. The maximum length is 128 characters.
"mode": "A String", # [Optional] The field mode. Possible values include NULLABLE, REQUIRED and REPEATED. The default value is NULLABLE.
@@ -1365,7 +1560,7 @@
"projectId": "A String", # [Optional] The ID of the project containing this dataset.
"datasetId": "A String", # [Required] A unique ID for this dataset, without the project name. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
},
- "useLegacySql": True or False, # [Experimental] Specifies whether to use BigQuery's legacy SQL dialect for this query. The default value is true. If set to false, the query will use BigQuery's updated SQL dialect with improved standards compliance. When using BigQuery's updated SQL, the values of allowLargeResults and flattenResults are ignored. Queries with useLegacySql set to false will be run as if allowLargeResults is true and flattenResults is false.
+ "useLegacySql": True or False, # [Experimental] Specifies whether to use BigQuery's legacy SQL dialect for this query. The default value is true. If set to false, the query will use BigQuery's standard SQL: https://cloud.google.com/bigquery/sql-reference/ When useLegacySql is set to false, the values of allowLargeResults and flattenResults are ignored; query will be run as if allowLargeResults is true and flattenResults is false.
"maxResults": 42, # [Optional] The maximum number of rows of data to return per page of results. Setting this flag to a small value such as 1000 and then paging through results might improve reliability when the query result set is large. In addition to this limit, responses are also limited to 10 MB. By default, there is no maximum row count, and only the byte limit applies.
"query": "A String", # [Required] A query string, following the BigQuery query syntax, of the query to execute. Example: "SELECT count(f1) FROM [myProjectId:myDatasetId.myTableId]".
"preserveNulls": True or False, # [Deprecated] This property is deprecated.
@@ -1409,7 +1604,7 @@
"fields": [ # [Optional] Describes the nested schema fields if the type property is set to RECORD.
# Object with schema name: TableFieldSchema
],
- "type": "A String", # [Required] The field data type. Possible values include STRING, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
+ "type": "A String", # [Required] The field data type. Possible values include STRING, BYTES, INTEGER, FLOAT, BOOLEAN, TIMESTAMP or RECORD (where RECORD indicates that the field contains a nested schema).
"description": "A String", # [Optional] The field description. The maximum length is 16K characters.
"name": "A String", # [Required] The field name. The name must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_), and must start with a letter or underscore. The maximum length is 128 characters.
"mode": "A String", # [Optional] The field mode. Possible values include NULLABLE, REQUIRED and REPEATED. The default value is NULLABLE.