Python PostgresHook.run方法代码示例

# 需要导入模块: from airflow.hooks.postgres_hook import PostgresHook [as 别名]
# 或者: from airflow.hooks.postgres_hook.PostgresHook import run [as 别名]
class PostgresOperator(BaseOperator):
    """
    Executes sql code in a specific Postgres database

    :param postgres_conn_id: reference to a specific postgres database
    :type postgres_conn_id: string
    :param sql: the sql code to be executed
    :type sql: Can receive a str representing a sql statement,
        a list of str (sql statements), or reference to a template file.
        Template reference are recognized by str ending in '.sql'
    """

    template_fields = ('sql',)
    template_ext = ('.sql',)
    ui_color = '#ededed'

    @apply_defaults
    def __init__(
            self, sql,
            postgres_conn_id='postgres_default', autocommit=False,
            parameters=None,
            *args, **kwargs):
        super(PostgresOperator, self).__init__(*args, **kwargs)
        self.sql = sql
        self.postgres_conn_id = postgres_conn_id
        self.autocommit = autocommit
        self.parameters = parameters

    def execute(self, context):
        _log.info('Executing: ' + str(self.sql))
        self.hook = PostgresHook(postgres_conn_id=self.postgres_conn_id)
        self.hook.run(self.sql, self.autocommit, parameters=self.parameters)

# 需要导入模块: from airflow.hooks.postgres_hook import PostgresHook [as 别名]
# 或者: from airflow.hooks.postgres_hook.PostgresHook import run [as 别名]
class PostgresOperator(BaseOperator):
    """
    Executes sql code in a specific Postgres database

    :param sql: the sql code to be executed. (templated)
    :type sql: Can receive a str representing a sql statement,
        a list of str (sql statements), or reference to a template file.
        Template reference are recognized by str ending in '.sql'
    :param postgres_conn_id: reference to a specific postgres database
    :type postgres_conn_id: str
    :param autocommit: if True, each command is automatically committed.
        (default value: False)
    :type autocommit: bool
    :param parameters: (optional) the parameters to render the SQL query with.
    :type parameters: mapping or iterable
    :param database: name of database which overwrite defined one in connection
    :type database: str
    """

    template_fields = ('sql',)
    template_ext = ('.sql',)
    ui_color = '#ededed'

    @apply_defaults
    def __init__(
            self, sql,
            postgres_conn_id='postgres_default', autocommit=False,
            parameters=None,
            database=None,
            *args, **kwargs):
        super().__init__(*args, **kwargs)
        self.sql = sql
        self.postgres_conn_id = postgres_conn_id
        self.autocommit = autocommit
        self.parameters = parameters
        self.database = database

    def execute(self, context):
        self.log.info('Executing: %s', self.sql)
        self.hook = PostgresHook(postgres_conn_id=self.postgres_conn_id,
                                 schema=self.database)
        self.hook.run(self.sql, self.autocommit, parameters=self.parameters)
        for output in self.hook.conn.notices:
            self.log.info(output)

# 需要导入模块: from airflow.hooks.postgres_hook import PostgresHook [as 别名]
# 或者: from airflow.hooks.postgres_hook.PostgresHook import run [as 别名]

#.........这里部分代码省略.........
                 CA cert bundle than the one used by botocore.
    :type verify: bool or str
    :param unload_options: reference to a list of UNLOAD options
    :type unload_options: list
    """

    template_fields = ()
    template_ext = ()
    ui_color = '#ededed'

    @apply_defaults
    def __init__(
            self,
            schema,
            table,
            s3_bucket,
            s3_key,
            redshift_conn_id='redshift_default',
            aws_conn_id='aws_default',
            verify=None,
            unload_options=tuple(),
            autocommit=False,
            include_header=False,
            *args, **kwargs):
        super().__init__(*args, **kwargs)
        self.schema = schema
        self.table = table
        self.s3_bucket = s3_bucket
        self.s3_key = s3_key
        self.redshift_conn_id = redshift_conn_id
        self.aws_conn_id = aws_conn_id
        self.verify = verify
        self.unload_options = unload_options
        self.autocommit = autocommit
        self.include_header = include_header

        if self.include_header and \
           'PARALLEL OFF' not in [uo.upper().strip() for uo in unload_options]:
            self.unload_options = list(unload_options) + ['PARALLEL OFF', ]

    def execute(self, context):
        self.hook = PostgresHook(postgres_conn_id=self.redshift_conn_id)
        self.s3 = S3Hook(aws_conn_id=self.aws_conn_id, verify=self.verify)
        credentials = self.s3.get_credentials()
        unload_options = '\n\t\t\t'.join(self.unload_options)

        if self.include_header:
            self.log.info("Retrieving headers from %s.%s...",
                          self.schema, self.table)

            columns_query = """SELECT column_name
                                        FROM information_schema.columns
                                        WHERE table_schema = '{schema}'
                                        AND   table_name = '{table}'
                                        ORDER BY ordinal_position
                            """.format(schema=self.schema,
                                       table=self.table)

            cursor = self.hook.get_conn().cursor()
            cursor.execute(columns_query)
            rows = cursor.fetchall()
            columns = [row[0] for row in rows]
            column_names = ', '.join("{0}".format(c) for c in columns)
            column_headers = ', '.join("\\'{0}\\'".format(c) for c in columns)
            column_castings = ', '.join("CAST({0} AS text) AS {0}".format(c)
                                        for c in columns)

            select_query = """SELECT {column_names} FROM
                                    (SELECT 2 sort_order, {column_castings}
                                     FROM {schema}.{table}
                                    UNION ALL
                                    SELECT 1 sort_order, {column_headers})
                                 ORDER BY sort_order"""\
                            .format(column_names=column_names,
                                    column_castings=column_castings,
                                    column_headers=column_headers,
                                    schema=self.schema,
                                    table=self.table)
        else:
            select_query = "SELECT * FROM {schema}.{table}"\
                .format(schema=self.schema,
                        table=self.table)

        unload_query = """
                    UNLOAD ('{select_query}')
                    TO 's3://{s3_bucket}/{s3_key}/{table}_'
                    with credentials
                    'aws_access_key_id={access_key};aws_secret_access_key={secret_key}'
                    {unload_options};
                    """.format(select_query=select_query,
                               table=self.table,
                               s3_bucket=self.s3_bucket,
                               s3_key=self.s3_key,
                               access_key=credentials.access_key,
                               secret_key=credentials.secret_key,
                               unload_options=unload_options)

        self.log.info('Executing UNLOAD command...')
        self.hook.run(unload_query, self.autocommit)
        self.log.info("UNLOAD command complete...")

# 需要导入模块: from airflow.hooks.postgres_hook import PostgresHook [as 别名]
# 或者: from airflow.hooks.postgres_hook.PostgresHook import run [as 别名]
class RedshiftToS3Transfer(BaseOperator):
    """
    Executes an UNLOAD command to s3 as a CSV with headers
    :param schema: reference to a specific schema in redshift database
    :type schema: string
    :param table: reference to a specific table in redshift database
    :type table: string
    :param s3_bucket: reference to a specific S3 bucket
    :type s3_bucket: string
    :param s3_key: reference to a specific S3 key
    :type s3_key: string
    :param redshift_conn_id: reference to a specific redshift database
    :type redshift_conn_id: string
    :param s3_conn_id: reference to a specific S3 connection
    :type s3_conn_id: string
    :param options: reference to a list of UNLOAD options
    :type options: list
    """

    template_fields = ()
    template_ext = ()
    ui_color = '#ededed'

    @apply_defaults
    def __init__(
            self,
            schema,
            table,
            s3_bucket,
            s3_key,
            redshift_conn_id='redshift_default',
            s3_conn_id='s3_default',
            unload_options=tuple(),
            autocommit=False,
            parameters=None,
            *args, **kwargs):
        super(RedshiftToS3Transfer, self).__init__(*args, **kwargs)
        self.schema = schema
        self.table = table
        self.s3_bucket = s3_bucket
        self.s3_key = s3_key
        self.redshift_conn_id = redshift_conn_id
        self.s3_conn_id = s3_conn_id
        self.unload_options = unload_options
        self.autocommit = autocommit
        self.parameters = parameters

    def execute(self, context):
        self.hook = PostgresHook(postgres_conn_id=self.redshift_conn_id)
        self.s3 = S3Hook(s3_conn_id=self.s3_conn_id)
        a_key, s_key = self.s3.get_credentials()
        unload_options = ('\n\t\t\t').join(self.unload_options)

        _log.info("Retrieving headers from %s.%s..." % (self.schema, self.table))

        columns_query = """SELECT column_name
                            FROM information_schema.columns
                            WHERE table_schema = '{0}'
                            AND   table_name = '{1}'
                            ORDER BY ordinal_position
                        """.format(self.schema, self.table)

        cursor = self.hook.get_conn().cursor()
        cursor.execute(columns_query)
        rows = cursor.fetchall()
        columns = map(lambda row: row[0], rows)
        column_names = (', ').join(map(lambda c: "\\'{0}\\'".format(c), columns))
        column_castings = (', ').join(map(lambda c: "CAST({0} AS text) AS {0}".format(c),
                                            columns))

        unload_query = """
                        UNLOAD ('SELECT {0}
                        UNION ALL
                        SELECT {1} FROM {2}.{3}')
                        TO 's3://{4}/{5}/{3}_'
                        with
                        credentials 'aws_access_key_id={6};aws_secret_access_key={7}'
                        {8};
                        """.format(column_names, column_castings, self.schema, self.table,
                                self.s3_bucket, self.s3_key, a_key, s_key, unload_options)

        _log.info('Executing UNLOAD command...')
        self.hook.run(unload_query, self.autocommit)
        _log.info("UNLOAD command complete...")

# 需要导入模块: from airflow.hooks.postgres_hook import PostgresHook [as 别名]
# 或者: from airflow.hooks.postgres_hook.PostgresHook import run [as 别名]
class S3ToRedshiftTransfer(BaseOperator):
    """
    Executes an COPY command to load files from s3 to Redshift

    :param schema: reference to a specific schema in redshift database
    :type schema: string
    :param table: reference to a specific table in redshift database
    :type table: string
    :param s3_bucket: reference to a specific S3 bucket
    :type s3_bucket: string
    :param s3_key: reference to a specific S3 key
    :type s3_key: string
    :param redshift_conn_id: reference to a specific redshift database
    :type redshift_conn_id: string
    :param aws_conn_id: reference to a specific S3 connection
    :type aws_conn_id: string
    :param copy_options: reference to a list of COPY options
    :type copy_options: list
    """

    template_fields = ()
    template_ext = ()
    ui_color = '#ededed'

    @apply_defaults
    def __init__(
            self,
            schema,
            table,
            s3_bucket,
            s3_key,
            redshift_conn_id='redshift_default',
            aws_conn_id='aws_default',
            copy_options=tuple(),
            autocommit=False,
            parameters=None,
            *args, **kwargs):
        super(S3ToRedshiftTransfer, self).__init__(*args, **kwargs)
        self.schema = schema
        self.table = table
        self.s3_bucket = s3_bucket
        self.s3_key = s3_key
        self.redshift_conn_id = redshift_conn_id
        self.aws_conn_id = aws_conn_id
        self.copy_options = copy_options
        self.autocommit = autocommit
        self.parameters = parameters

    def execute(self, context):
        self.hook = PostgresHook(postgres_conn_id=self.redshift_conn_id)
        self.s3 = S3Hook(aws_conn_id=self.aws_conn_id)
        credentials = self.s3.get_credentials()
        copy_options = '\n\t\t\t'.join(self.copy_options)

        copy_query = """
            COPY {schema}.{table}
            FROM 's3://{s3_bucket}/{s3_key}/{table}'
            with credentials
            'aws_access_key_id={access_key};aws_secret_access_key={secret_key}'
            {copy_options};
        """.format(schema=self.schema,
                   table=self.table,
                   s3_bucket=self.s3_bucket,
                   s3_key=self.s3_key,
                   access_key=credentials.access_key,
                   secret_key=credentials.secret_key,
                   copy_options=copy_options)

        self.log.info('Executing COPY command...')
        self.hook.run(copy_query, self.autocommit)
        self.log.info("COPY command complete...")

# 需要导入模块: from airflow.hooks.postgres_hook import PostgresHook [as 别名]
# 或者: from airflow.hooks.postgres_hook.PostgresHook import run [as 别名]
class S3ToRedshiftTransfer(BaseOperator):
    """
    Executes an COPY command to load files from s3 to Redshift

    :param schema: reference to a specific schema in redshift database
    :type schema: string
    :param table: reference to a specific table in redshift database
    :type table: string
    :param s3_bucket: reference to a specific S3 bucket
    :type s3_bucket: string
    :param s3_key: reference to a specific S3 key
    :type s3_key: string
    :param redshift_conn_id: reference to a specific redshift database
    :type redshift_conn_id: string
    :param aws_conn_id: reference to a specific S3 connection
    :type aws_conn_id: string
    :parame verify: Whether or not to verify SSL certificates for S3 connection.
        By default SSL certificates are verified.
        You can provide the following values:
        - False: do not validate SSL certificates. SSL will still be used
                 (unless use_ssl is False), but SSL certificates will not be
                 verified.
        - path/to/cert/bundle.pem: A filename of the CA cert bundle to uses.
                 You can specify this argument if you want to use a different
                 CA cert bundle than the one used by botocore.
    :type verify: bool or str
    :param copy_options: reference to a list of COPY options
    :type copy_options: list
    """

    template_fields = ()
    template_ext = ()
    ui_color = '#ededed'

    @apply_defaults
    def __init__(
            self,
            schema,
            table,
            s3_bucket,
            s3_key,
            redshift_conn_id='redshift_default',
            aws_conn_id='aws_default',
            verify=None,
            copy_options=tuple(),
            autocommit=False,
            parameters=None,
            *args, **kwargs):
        super(S3ToRedshiftTransfer, self).__init__(*args, **kwargs)
        self.schema = schema
        self.table = table
        self.s3_bucket = s3_bucket
        self.s3_key = s3_key
        self.redshift_conn_id = redshift_conn_id
        self.aws_conn_id = aws_conn_id
        self.verify = verify
        self.copy_options = copy_options
        self.autocommit = autocommit
        self.parameters = parameters

    def execute(self, context):
        self.hook = PostgresHook(postgres_conn_id=self.redshift_conn_id)
        self.s3 = S3Hook(aws_conn_id=self.aws_conn_id, verify=self.verify)
        credentials = self.s3.get_credentials()
        copy_options = '\n\t\t\t'.join(self.copy_options)

        copy_query = """
            COPY {schema}.{table}
            FROM 's3://{s3_bucket}/{s3_key}/{table}'
            with credentials
            'aws_access_key_id={access_key};aws_secret_access_key={secret_key}'
            {copy_options};
        """.format(schema=self.schema,
                   table=self.table,
                   s3_bucket=self.s3_bucket,
                   s3_key=self.s3_key,
                   access_key=credentials.access_key,
                   secret_key=credentials.secret_key,
                   copy_options=copy_options)

        self.log.info('Executing COPY command...')
        self.hook.run(copy_query, self.autocommit)
        self.log.info("COPY command complete...")

# 需要导入模块: from airflow.hooks.postgres_hook import PostgresHook [as 别名]
# 或者: from airflow.hooks.postgres_hook.PostgresHook import run [as 别名]

#.........这里部分代码省略.........
    :param aws_conn_id: reference to a specific S3 connection
    :type aws_conn_id: string
    :param unload_options: reference to a list of UNLOAD options
    :type unload_options: list
    """

    template_fields = ()
    template_ext = ()
    ui_color = '#ededed'

    @apply_defaults
    def __init__(
            self,
            schema,
            table,
            s3_bucket,
            s3_key,
            redshift_conn_id='redshift_default',
            aws_conn_id='aws_default',
            unload_options=tuple(),
            autocommit=False,
            parameters=None,
            include_header=False,
            *args, **kwargs):
        super(RedshiftToS3Transfer, self).__init__(*args, **kwargs)
        self.schema = schema
        self.table = table
        self.s3_bucket = s3_bucket
        self.s3_key = s3_key
        self.redshift_conn_id = redshift_conn_id
        self.aws_conn_id = aws_conn_id
        self.unload_options = unload_options
        self.autocommit = autocommit
        self.parameters = parameters
        self.include_header = include_header

        if self.include_header and \
           'PARALLEL OFF' not in [uo.upper().strip() for uo in unload_options]:
            self.unload_options = list(unload_options) + ['PARALLEL OFF', ]

    def execute(self, context):
        self.hook = PostgresHook(postgres_conn_id=self.redshift_conn_id)
        self.s3 = S3Hook(aws_conn_id=self.aws_conn_id)
        credentials = self.s3.get_credentials()
        unload_options = '\n\t\t\t'.join(self.unload_options)

        if self.include_header:
            self.log.info("Retrieving headers from %s.%s...",
                          self.schema, self.table)

            columns_query = """SELECT column_name
                                        FROM information_schema.columns
                                        WHERE table_schema = '{schema}'
                                        AND   table_name = '{table}'
                                        ORDER BY ordinal_position
                            """.format(schema=self.schema,
                                       table=self.table)

            cursor = self.hook.get_conn().cursor()
            cursor.execute(columns_query)
            rows = cursor.fetchall()
            columns = [row[0] for row in rows]
            column_names = ', '.join("{0}".format(c) for c in columns)
            column_headers = ', '.join("\\'{0}\\'".format(c) for c in columns)
            column_castings = ', '.join("CAST({0} AS text) AS {0}".format(c)
                                        for c in columns)

            select_query = """SELECT {column_names} FROM
                                    (SELECT 2 sort_order, {column_castings}
                                     FROM {schema}.{table}
                                    UNION ALL
                                    SELECT 1 sort_order, {column_headers})
                                 ORDER BY sort_order"""\
                            .format(column_names=column_names,
                                    column_castings=column_castings,
                                    column_headers=column_headers,
                                    schema=self.schema,
                                    table=self.table)
        else:
            select_query = "SELECT * FROM {schema}.{table}"\
                .format(schema=self.schema,
                        table=self.table)

        unload_query = """
                    UNLOAD ('{select_query}')
                    TO 's3://{s3_bucket}/{s3_key}/{table}_'
                    with credentials
                    'aws_access_key_id={access_key};aws_secret_access_key={secret_key}'
                    {unload_options};
                    """.format(select_query=select_query,
                               table=self.table,
                               s3_bucket=self.s3_bucket,
                               s3_key=self.s3_key,
                               access_key=credentials.access_key,
                               secret_key=credentials.secret_key,
                               unload_options=unload_options)

        self.log.info('Executing UNLOAD command...')
        self.hook.run(unload_query, self.autocommit)
        self.log.info("UNLOAD command complete...")