BUG: Omnisci string length error, Cast from dictionary-encoded string to none-encoded would be slow

[datapythonista]

This issue has been moved from the Ibis repo: ibis-project/ibis#2338

Omnisci is failing in test_strings.py::test_string[length] with the next error: omnisci.thrift.ttypes.TOmniSciException: TOmniSciException(error_msg='Exception: Cast from dictionary-encoded string to none-encoded would be slow')

This test is failing. xfailing for now, to make the CI in ibis-project/ibis#2335, but we should fix the bug.

Full error:

2020-08-18T11:50:03.4754023Z ________________________ test_string[OmniSciDB-length] _________________________ 2020-08-18T11:50:03.4754332Z 2020-08-18T11:50:03.4754820Z self = 2020-08-18T11:50:03.4755801Z operation = 'SELECT CHAR_LENGTH("string_col") AS tmp\nFROM functional_alltypes' 2020-08-18T11:50:03.4756172Z parameters = None 2020-08-18T11:50:03.4756401Z 2020-08-18T11:50:03.4756708Z def execute(self, operation, parameters=None): 2020-08-18T11:50:03.4757010Z """Execute a SQL statement. 2020-08-18T11:50:03.4757327Z 2020-08-18T11:50:03.4757615Z Parameters 2020-08-18T11:50:03.4758248Z ---------- 2020-08-18T11:50:03.4759135Z operation: str 2020-08-18T11:50:03.4759461Z A SQL query 2020-08-18T11:50:03.4759757Z parameters: dict 2020-08-18T11:50:03.4760065Z Parameters to substitute into ``operation``. 2020-08-18T11:50:03.4760373Z 2020-08-18T11:50:03.4760644Z Returns 2020-08-18T11:50:03.4761106Z ------- 2020-08-18T11:50:03.4761522Z self : Cursor 2020-08-18T11:50:03.4762013Z 2020-08-18T11:50:03.4762471Z Examples 2020-08-18T11:50:03.4762906Z -------- 2020-08-18T11:50:03.4763629Z >>> c = conn.cursor() 2020-08-18T11:50:03.4764013Z >>> c.execute("select symbol, qty from stocks") 2020-08-18T11:50:03.4764321Z >>> list(c) 2020-08-18T11:50:03.4764876Z [('RHAT', 100.0), ('IBM', 1000.0), ('MSFT', 1000.0), ('IBM', 500.0)] 2020-08-18T11:50:03.4765216Z 2020-08-18T11:50:03.4765514Z Passing in ``parameters``: 2020-08-18T11:50:03.4766003Z 2020-08-18T11:50:03.4766325Z >>> c.execute("select symbol qty from stocks where qty <= :max_qty", 2020-08-18T11:50:03.4766653Z ... parameters={"max_qty": 500}) 2020-08-18T11:50:03.4767155Z [('RHAT', 100.0), ('IBM', 500.0)] 2020-08-18T11:50:03.4767511Z """ 2020-08-18T11:50:03.4767817Z 2020-08-18T11:50:03.4768179Z # https://github.com/heavyai/pymapd/issues/263 2020-08-18T11:50:03.4768517Z operation = operation.strip() 2020-08-18T11:50:03.4768819Z 2020-08-18T11:50:03.4769091Z if parameters is not None: 2020-08-18T11:50:03.4769579Z operation = str(_bind_parameters(operation, parameters)) 2020-08-18T11:50:03.4770257Z self.rowcount = -1 2020-08-18T11:50:03.4770769Z try: 2020-08-18T11:50:03.4771075Z result = self.connection._client.sql_execute( 2020-08-18T11:50:03.4771541Z self.connection._session, 2020-08-18T11:50:03.4771827Z operation, 2020-08-18T11:50:03.4772116Z column_format=True, 2020-08-18T11:50:03.4772591Z nonce=None, 2020-08-18T11:50:03.4777503Z first_n=-1, 2020-08-18T11:50:03.4777958Z > at_most_n=-1, 2020-08-18T11:50:03.4778057Z ) 2020-08-18T11:50:03.4778133Z 2020-08-18T11:50:03.4778601Z /usr/share/miniconda/lib/python3.7/site-packages/pymapd/cursor.py:118: 2020-08-18T11:50:03.4778748Z _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 2020-08-18T11:50:03.4778819Z 2020-08-18T11:50:03.4778943Z self = 2020-08-18T11:50:03.4779241Z session = 'w5kKtMXo8LL1wKYX8PJXuDtOzgWlRnFf' 2020-08-18T11:50:03.4779734Z query = 'SELECT CHAR_LENGTH("string_col") AS tmp\nFROM functional_alltypes' 2020-08-18T11:50:03.4780233Z column_format = True, nonce = None, first_n = -1, at_most_n = -1 2020-08-18T11:50:03.4780306Z 2020-08-18T11:50:03.4780443Z def sql_execute(self, session, query, column_format, nonce, first_n, at_most_n): 2020-08-18T11:50:03.4780591Z """ 2020-08-18T11:50:03.4780719Z Parameters: 2020-08-18T11:50:03.4780981Z - session 2020-08-18T11:50:03.4781214Z - query 2020-08-18T11:50:03.4781838Z - column_format 2020-08-18T11:50:03.4782105Z - nonce 2020-08-18T11:50:03.4782518Z - first_n 2020-08-18T11:50:03.4782993Z - at_most_n 2020-08-18T11:50:03.4783120Z 2020-08-18T11:50:03.4783216Z """ 2020-08-18T11:50:03.4783519Z self.send_sql_execute(session, query, column_format, nonce, first_n, at_most_n) 2020-08-18T11:50:03.4783875Z > return self.recv_sql_execute() 2020-08-18T11:50:03.4784118Z 2020-08-18T11:50:03.4784443Z /usr/share/miniconda/lib/python3.7/site-packages/omnisci/thrift/OmniSci.py:1745: 2020-08-18T11:50:03.4784573Z _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 2020-08-18T11:50:03.4784667Z 2020-08-18T11:50:03.4784964Z self = 2020-08-18T11:50:03.4785034Z 2020-08-18T11:50:03.4785150Z def recv_sql_execute(self): 2020-08-18T11:50:03.4785272Z iprot = self._iprot 2020-08-18T11:50:03.4786421Z (fname, mtype, rseqid) = iprot.readMessageBegin() 2020-08-18T11:50:03.4786555Z if mtype == TMessageType.EXCEPTION: 2020-08-18T11:50:03.4786853Z x = TApplicationException() 2020-08-18T11:50:03.4787125Z x.read(iprot) 2020-08-18T11:50:03.4787251Z iprot.readMessageEnd() 2020-08-18T11:50:03.4787375Z raise x 2020-08-18T11:50:03.4787498Z result = sql_execute_result() 2020-08-18T11:50:03.4787941Z result.read(iprot) 2020-08-18T11:50:03.4788089Z iprot.readMessageEnd() 2020-08-18T11:50:03.4788223Z if result.success is not None: 2020-08-18T11:50:03.4788330Z return result.success 2020-08-18T11:50:03.4788461Z if result.e is not None: 2020-08-18T11:50:03.4788589Z > raise result.e 2020-08-18T11:50:03.4789111Z E omnisci.thrift.ttypes.TOmniSciException: TOmniSciException(error_msg='Exception: Cast from dictionary-encoded string to none-encoded would be slow') 2020-08-18T11:50:03.4789409Z 2020-08-18T11:50:03.4790617Z /usr/share/miniconda/lib/python3.7/site-packages/omnisci/thrift/OmniSci.py:1774: TOmniSciException 2020-08-18T11:50:03.4790709Z 2020-08-18T11:50:03.4790839Z The above exception was the direct cause of the following exception: 2020-08-18T11:50:03.4790905Z 2020-08-18T11:50:03.4791186Z self = 2020-08-18T11:50:03.4791503Z query = 'SELECT CHAR_LENGTH("string_col") AS tmp\nFROM functional_alltypes' 2020-08-18T11:50:03.4791642Z results = True, ipc = None, gpu_device = None, kwargs = {} 2020-08-18T11:50:03.4791928Z cursor = , params = {} 2020-08-18T11:50:03.4792073Z execute = > 2020-08-18T11:50:03.4792142Z 2020-08-18T11:50:03.4792391Z def _execute( 2020-08-18T11:50:03.4792503Z self, 2020-08-18T11:50:03.4792614Z query: str, 2020-08-18T11:50:03.4792727Z results: bool = True, 2020-08-18T11:50:03.4792842Z ipc: Optional[bool] = None, 2020-08-18T11:50:03.4792938Z gpu_device: Optional[int] = None, 2020-08-18T11:50:03.4793052Z **kwargs, 2020-08-18T11:50:03.4793161Z ): 2020-08-18T11:50:03.4793268Z """ 2020-08-18T11:50:03.4793381Z Compile and execute Ibis expression. 2020-08-18T11:50:03.4793495Z 2020-08-18T11:50:03.4793805Z Return result in-memory in the appropriate object type. 2020-08-18T11:50:03.4793904Z 2020-08-18T11:50:03.4794011Z Parameters 2020-08-18T11:50:03.4794241Z ---------- 2020-08-18T11:50:03.4794354Z query : string 2020-08-18T11:50:03.4794467Z DML or DDL statement 2020-08-18T11:50:03.4794584Z results : boolean, default False 2020-08-18T11:50:03.4794704Z Pass True if the query as a result set 2020-08-18T11:50:03.4794807Z ipc : bool, optional, default None 2020-08-18T11:50:03.4794933Z Enable Inter Process Communication (IPC) execution type. 2020-08-18T11:50:03.4795065Z `ipc` default value (None) when `gpu_device` is None is interpreted 2020-08-18T11:50:03.4795199Z as False, otherwise it is interpreted as True. 2020-08-18T11:50:03.4795321Z gpu_device : int, optional, default None 2020-08-18T11:50:03.4795437Z GPU device ID. 2020-08-18T11:50:03.4795547Z 2020-08-18T11:50:03.4795653Z Returns 2020-08-18T11:50:03.4795867Z ------- 2020-08-18T11:50:03.4795992Z output : execution type dependent 2020-08-18T11:50:03.4796114Z If IPC is set as True and no GPU device is set: 2020-08-18T11:50:03.4796239Z ``pandas.DataFrame`` 2020-08-18T11:50:03.4796363Z If IPC is set as True and GPU device is set: ``cudf.DataFrame`` 2020-08-18T11:50:03.4796494Z If IPC is set as False and no GPU device is set: 2020-08-18T11:50:03.4796617Z pandas.DataFrame or 2020-08-18T11:50:03.4796741Z geopandas.GeoDataFrame (if it uses geospatial data) 2020-08-18T11:50:03.4796836Z 2020-08-18T11:50:03.4796941Z Raises 2020-08-18T11:50:03.4797173Z ------ 2020-08-18T11:50:03.4797285Z Exception 2020-08-18T11:50:03.4797396Z if execution method fails. 2020-08-18T11:50:03.4797508Z """ 2020-08-18T11:50:03.4797601Z # time context is not implemented for omniscidb yet 2020-08-18T11:50:03.4797860Z kwargs.pop('timecontext', None) 2020-08-18T11:50:03.4798067Z # raise an Exception if kwargs is not empty: 2020-08-18T11:50:03.4798192Z if kwargs: 2020-08-18T11:50:03.4798306Z raise com.IbisInputError( 2020-08-18T11:50:03.4798616Z '"OmniSciDB.execute" method just support the follow parameter:' 2020-08-18T11:50:03.4798918Z ' "query", "results", "ipc" and "gpu_device". The follow extra' 2020-08-18T11:50:03.4799221Z ' parameters was given: "{}".'.format(', '.join(kwargs.keys())) 2020-08-18T11:50:03.4799343Z ) 2020-08-18T11:50:03.4799428Z 2020-08-18T11:50:03.4799539Z if isinstance(query, (DDL, DML)): 2020-08-18T11:50:03.4799660Z query = query.compile() 2020-08-18T11:50:03.4799772Z 2020-08-18T11:50:03.4799886Z if ipc is None and gpu_device is None: 2020-08-18T11:50:03.4800002Z ipc = self.ipc 2020-08-18T11:50:03.4800119Z gpu_device = self.gpu_device 2020-08-18T11:50:03.4800210Z 2020-08-18T11:50:03.4800325Z self._check_execution_type(ipc, gpu_device) 2020-08-18T11:50:03.4800440Z 2020-08-18T11:50:03.4800544Z cursor = ( 2020-08-18T11:50:03.4800654Z OmniSciDBGeoCursor 2020-08-18T11:50:03.4800770Z if FULL_GEO_SUPPORTED 2020-08-18T11:50:03.4800884Z else OmniSciDBDefaultCursor 2020-08-18T11:50:03.4800973Z ) 2020-08-18T11:50:03.4801080Z 2020-08-18T11:50:03.4801267Z params = {} 2020-08-18T11:50:03.4801376Z 2020-08-18T11:50:03.4801487Z if gpu_device is None and not ipc: 2020-08-18T11:50:03.4801606Z execute = self.con.cursor().execute 2020-08-18T11:50:03.4801700Z elif gpu_device is None and ipc: 2020-08-18T11:50:03.4801818Z execute = self.con.select_ipc 2020-08-18T11:50:03.4801933Z else: 2020-08-18T11:50:03.4802383Z params['device_id'] = gpu_device 2020-08-18T11:50:03.4802511Z execute = self.con.select_ipc_gpu 2020-08-18T11:50:03.4802623Z cursor = OmniSciDBGPUCursor 2020-08-18T11:50:03.4802738Z 2020-08-18T11:50:03.4802841Z try: 2020-08-18T11:50:03.4802932Z > result = cursor(execute(query, **params)) 2020-08-18T11:50:03.4803012Z 2020-08-18T11:50:03.4803121Z ibis/omniscidb/client.py:844: 2020-08-18T11:50:03.4803243Z _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 2020-08-18T11:50:03.4803307Z 2020-08-18T11:50:03.4803420Z self = 2020-08-18T11:50:03.4803719Z operation = 'SELECT CHAR_LENGTH("string_col") AS tmp\nFROM functional_alltypes' 2020-08-18T11:50:03.4803845Z parameters = None 2020-08-18T11:50:03.4803895Z 2020-08-18T11:50:03.4804005Z def execute(self, operation, parameters=None): 2020-08-18T11:50:03.4804120Z """Execute a SQL statement. 2020-08-18T11:50:03.4804227Z 2020-08-18T11:50:03.4804328Z Parameters 2020-08-18T11:50:03.4804528Z ---------- 2020-08-18T11:50:03.4804636Z operation: str 2020-08-18T11:50:03.4804747Z A SQL query 2020-08-18T11:50:03.4804855Z parameters: dict 2020-08-18T11:50:03.4804969Z Parameters to substitute into ``operation``. 2020-08-18T11:50:03.4805081Z 2020-08-18T11:50:03.4805181Z Returns 2020-08-18T11:50:03.4805379Z ------- 2020-08-18T11:50:03.4805489Z self : Cursor 2020-08-18T11:50:03.4805595Z 2020-08-18T11:50:03.4805695Z Examples 2020-08-18T11:50:03.4805918Z -------- 2020-08-18T11:50:03.4806030Z >>> c = conn.cursor() 2020-08-18T11:50:03.4806146Z >>> c.execute("select symbol, qty from stocks") 2020-08-18T11:50:03.4806238Z >>> list(c) 2020-08-18T11:50:03.4806528Z [('RHAT', 100.0), ('IBM', 1000.0), ('MSFT', 1000.0), ('IBM', 500.0)] 2020-08-18T11:50:03.4806652Z 2020-08-18T11:50:03.4806758Z Passing in ``parameters``: 2020-08-18T11:50:03.4806866Z 2020-08-18T11:50:03.4806980Z >>> c.execute("select symbol qty from stocks where qty <= :max_qty", 2020-08-18T11:50:03.4807181Z ... parameters={"max_qty": 500}) 2020-08-18T11:50:03.4807442Z [('RHAT', 100.0), ('IBM', 500.0)] 2020-08-18T11:50:03.4807557Z """ 2020-08-18T11:50:03.4807662Z 2020-08-18T11:50:03.4807804Z # https://github.com/heavyai/pymapd/issues/263 2020-08-18T11:50:03.4807932Z operation = operation.strip() 2020-08-18T11:50:03.4808041Z 2020-08-18T11:50:03.4808151Z if parameters is not None: 2020-08-18T11:50:03.4808249Z operation = str(_bind_parameters(operation, parameters)) 2020-08-18T11:50:03.4808499Z self.rowcount = -1 2020-08-18T11:50:03.4808615Z try: 2020-08-18T11:50:03.4808732Z result = self.connection._client.sql_execute( 2020-08-18T11:50:03.4808851Z self.connection._session, 2020-08-18T11:50:03.4808964Z operation, 2020-08-18T11:50:03.4809077Z column_format=True, 2020-08-18T11:50:03.4809164Z nonce=None, 2020-08-18T11:50:03.4809405Z first_n=-1, 2020-08-18T11:50:03.4809640Z at_most_n=-1, 2020-08-18T11:50:03.4809752Z ) 2020-08-18T11:50:03.4809862Z except T.TOmniSciException as e: 2020-08-18T11:50:03.4809978Z > raise _translate_exception(e) from e 2020-08-18T11:50:03.4810305Z E pymapd.exceptions.Error: Exception: Cast from dictionary-encoded string to none-encoded would be slow 2020-08-18T11:50:03.4810461Z 2020-08-18T11:50:03.4810760Z /usr/share/miniconda/lib/python3.7/site-packages/pymapd/cursor.py:121: Error 2020-08-18T11:50:03.4810849Z 2020-08-18T11:50:03.4810942Z During handling of the above exception, another exception occurred: 2020-08-18T11:50:03.4811022Z 2020-08-18T11:50:03.4811137Z backend = 2020-08-18T11:50:03.4811255Z alltypes = DatabaseTable[table] 2020-08-18T11:50:03.4811343Z name: functional_alltypes 2020-08-18T11:50:03.4811450Z schema: 2020-08-18T11:50:03.4811561Z index : int64 2020-08-18T11:50:03.4811672Z Unnamed__0 : int64 2020-08-18T11:50:03.4811781Z id : int32 2020-08-18T11:50:03.4811890Z ... date_string_col : string 2020-08-18T11:50:03.4811997Z string_col : string 2020-08-18T11:50:03.4812084Z timestamp_col : timestamp 2020-08-18T11:50:03.4812190Z year_ : int32 2020-08-18T11:50:03.4812297Z month_ : int32 2020-08-18T11:50:03.4812512Z df = index Unnamed__0 id ... timestamp_col year_ month_ 2020-08-18T11:50:03.4812846Z 0 0 0 6690 ... 2010-11-01 00...05:08:13 2010 1 2020-08-18T11:50:03.4813139Z 7299 7299 7299 3959 ... 2010-01-31 05:09:13 2010 1 2020-08-18T11:50:03.4813201Z 2020-08-18T11:50:03.4813449Z [7300 rows x 15 columns] 2020-08-18T11:50:03.4813566Z result_func = at 0x7fb38c72e170> 2020-08-18T11:50:03.4813684Z expected_func = at 0x7fb38c72e200> 2020-08-18T11:50:03.4813740Z 2020-08-18T11:50:03.4813847Z @pytest.mark.parametrize( 2020-08-18T11:50:03.4814122Z ('result_func', 'expected_func'), 2020-08-18T11:50:03.4814236Z [ 2020-08-18T11:50:03.4814342Z param( 2020-08-18T11:50:03.4814600Z lambda t: t.string_col.contains('6'), 2020-08-18T11:50:03.4814867Z lambda t: t.string_col.str.contains('6'), 2020-08-18T11:50:03.4815087Z id='contains', 2020-08-18T11:50:03.4815198Z ), 2020-08-18T11:50:03.4815308Z param( 2020-08-18T11:50:03.4815559Z lambda t: t.string_col.like('6%'), 2020-08-18T11:50:03.4815823Z lambda t: t.string_col.str.contains('6.*'), 2020-08-18T11:50:03.4816056Z id='like', 2020-08-18T11:50:03.4816166Z ), 2020-08-18T11:50:03.4816250Z param( 2020-08-18T11:50:03.4816498Z lambda t: t.string_col.like('6^%'), 2020-08-18T11:50:03.4816761Z lambda t: t.string_col.str.contains('6%'), 2020-08-18T11:50:03.4817009Z id='complex_like_escape', 2020-08-18T11:50:03.4817220Z ), 2020-08-18T11:50:03.4817338Z param( 2020-08-18T11:50:03.4817615Z lambda t: t.string_col.like('6^%%'), 2020-08-18T11:50:03.4817857Z lambda t: t.string_col.str.contains('6%.*'), 2020-08-18T11:50:03.4818113Z id='complex_like_escape_match', 2020-08-18T11:50:03.4818230Z ), 2020-08-18T11:50:03.4818337Z param( 2020-08-18T11:50:03.4818594Z lambda t: t.string_col.ilike('6%'), 2020-08-18T11:50:03.4818858Z lambda t: t.string_col.str.contains('6.*'), 2020-08-18T11:50:03.4819091Z id='ilike', 2020-08-18T11:50:03.4819200Z ), 2020-08-18T11:50:03.4819283Z param( 2020-08-18T11:50:03.4819551Z lambda t: t.string_col.re_search(r'[[:digit:]]+'), 2020-08-18T11:50:03.4819821Z lambda t: t.string_col.str.contains(r'\d+'), 2020-08-18T11:50:03.4820062Z id='re_search', 2020-08-18T11:50:03.4820185Z marks=pytest.mark.xfail_backends((Spark, PySpark)), 2020-08-18T11:50:03.4820304Z ), 2020-08-18T11:50:03.4820409Z param( 2020-08-18T11:50:03.4820662Z lambda t: t.string_col.re_extract(r'([[:digit:]]+)', 0), 2020-08-18T11:50:03.4820949Z lambda t: t.string_col.str.extract(r'(\d+)', expand=False), 2020-08-18T11:50:03.4821194Z id='re_extract', 2020-08-18T11:50:03.4821405Z marks=pytest.mark.xfail_backends((Spark, PySpark)), 2020-08-18T11:50:03.4821522Z ), 2020-08-18T11:50:03.4821627Z param( 2020-08-18T11:50:03.4821920Z lambda t: t.string_col.re_replace(r'[[:digit:]]+', 'a'), 2020-08-18T11:50:03.4822200Z lambda t: t.string_col.str.replace(r'\d+', 'a'), 2020-08-18T11:50:03.4822415Z id='re_replace', 2020-08-18T11:50:03.4822538Z marks=pytest.mark.xfail_backends((Spark, PySpark)), 2020-08-18T11:50:03.4822654Z ), 2020-08-18T11:50:03.4822763Z param( 2020-08-18T11:50:03.4823028Z lambda t: t.string_col.re_search(r'\\d+'), 2020-08-18T11:50:03.4823293Z lambda t: t.string_col.str.contains(r'\d+'), 2020-08-18T11:50:03.4823536Z id='re_search_spark', 2020-08-18T11:50:03.4823660Z marks=pytest.mark.xpass_backends((Clickhouse, Impala, Spark)), 2020-08-18T11:50:03.4823758Z ), 2020-08-18T11:50:03.4824026Z param( 2020-08-18T11:50:03.4824289Z lambda t: t.string_col.re_extract(r'(\\d+)', 0), 2020-08-18T11:50:03.4824563Z lambda t: t.string_col.str.extract(r'(\d+)', expand=False), 2020-08-18T11:50:03.4824811Z id='re_extract_spark', 2020-08-18T11:50:03.4824933Z marks=pytest.mark.xpass_backends((Clickhouse, Impala, Spark)), 2020-08-18T11:50:03.4825047Z ), 2020-08-18T11:50:03.4825149Z param( 2020-08-18T11:50:03.4825384Z lambda t: t.string_col.re_replace(r'\\d+', 'a'), 2020-08-18T11:50:03.4825653Z lambda t: t.string_col.str.replace(r'\d+', 'a'), 2020-08-18T11:50:03.4825893Z id='re_replace_spark', 2020-08-18T11:50:03.4826014Z marks=pytest.mark.xpass_backends((Clickhouse, Impala, Spark)), 2020-08-18T11:50:03.4826128Z ), 2020-08-18T11:50:03.4826232Z param( 2020-08-18T11:50:03.4826484Z lambda t: t.string_col.re_search(r'\d+'), 2020-08-18T11:50:03.4826748Z lambda t: t.string_col.str.contains(r'\d+'), 2020-08-18T11:50:03.4826964Z id='re_search_spark', 2020-08-18T11:50:03.4827086Z marks=pytest.mark.xfail_backends((Clickhouse, Impala, Spark)), 2020-08-18T11:50:03.4827202Z ), 2020-08-18T11:50:03.4827304Z param( 2020-08-18T11:50:03.4827635Z lambda t: t.string_col.re_extract(r'(\d+)', 0), 2020-08-18T11:50:03.4827977Z lambda t: t.string_col.str.extract(r'(\d+)', expand=False), 2020-08-18T11:50:03.4828369Z id='re_extract_spark', 2020-08-18T11:50:03.4828526Z marks=pytest.mark.xfail_backends((Clickhouse, Impala, Spark)), 2020-08-18T11:50:03.4828620Z ), 2020-08-18T11:50:03.4828722Z param( 2020-08-18T11:50:03.4829007Z lambda t: t.string_col.re_replace(r'\d+', 'a'), 2020-08-18T11:50:03.4829272Z lambda t: t.string_col.str.replace(r'\d+', 'a'), 2020-08-18T11:50:03.4829514Z id='re_replace_spark', 2020-08-18T11:50:03.4829632Z marks=pytest.mark.xfail_backends((Clickhouse, Impala, Spark)), 2020-08-18T11:50:03.4829746Z ), 2020-08-18T11:50:03.4829826Z param( 2020-08-18T11:50:03.4829939Z lambda t: t.string_col.repeat(2), 2020-08-18T11:50:03.4830055Z lambda t: t.string_col * 2, 2020-08-18T11:50:03.4830284Z id='repeat', 2020-08-18T11:50:03.4830393Z ), 2020-08-18T11:50:03.4830495Z param( 2020-08-18T11:50:03.4830752Z lambda t: t.string_col.translate('0', 'a'), 2020-08-18T11:50:03.4831030Z lambda t: t.string_col.str.translate(str.maketrans('0', 'a')), 2020-08-18T11:50:03.4831244Z id='translate', 2020-08-18T11:50:03.4831351Z ), 2020-08-18T11:50:03.4831455Z param( 2020-08-18T11:50:03.4831693Z lambda t: t.string_col.find('a'), 2020-08-18T11:50:03.4832052Z lambda t: t.string_col.str.find('a'), 2020-08-18T11:50:03.4832278Z id='find', 2020-08-18T11:50:03.4832391Z ), 2020-08-18T11:50:03.4832470Z param( 2020-08-18T11:50:03.4832716Z lambda t: t.string_col.lpad(10, 'a'), 2020-08-18T11:50:03.4832990Z lambda t: t.string_col.str.pad(10, fillchar='a', side='left'), 2020-08-18T11:50:03.4833226Z id='lpad', 2020-08-18T11:50:03.4833330Z ), 2020-08-18T11:50:03.4833433Z param( 2020-08-18T11:50:03.4833680Z lambda t: t.string_col.rpad(10, 'a'), 2020-08-18T11:50:03.4833957Z lambda t: t.string_col.str.pad(10, fillchar='a', side='right'), 2020-08-18T11:50:03.4834171Z id='rpad', 2020-08-18T11:50:03.4834277Z ), 2020-08-18T11:50:03.4834379Z param( 2020-08-18T11:50:03.4834627Z lambda t: t.string_col.find_in_set(['1']), 2020-08-18T11:50:03.4834882Z lambda t: t.string_col.str.find('1'), 2020-08-18T11:50:03.4835114Z id='find_in_set', 2020-08-18T11:50:03.4835224Z ), 2020-08-18T11:50:03.4835303Z param( 2020-08-18T11:50:03.4835548Z lambda t: t.string_col.find_in_set(['a']), 2020-08-18T11:50:03.4835803Z lambda t: t.string_col.str.find('a'), 2020-08-18T11:50:03.4836046Z id='find_in_set_all_missing', 2020-08-18T11:50:03.4836157Z ), 2020-08-18T11:50:03.4836257Z param( 2020-08-18T11:50:03.4836370Z lambda t: t.string_col.lower(), 2020-08-18T11:50:03.4836802Z lambda t: t.string_col.str.lower(), 2020-08-18T11:50:03.4837101Z id='lower', 2020-08-18T11:50:03.4837212Z ), 2020-08-18T11:50:03.4837316Z param( 2020-08-18T11:50:03.4837425Z lambda t: t.string_col.upper(), 2020-08-18T11:50:03.4837540Z lambda t: t.string_col.str.upper(), 2020-08-18T11:50:03.4837782Z id='upper', 2020-08-18T11:50:03.4837889Z ), 2020-08-18T11:50:03.4837970Z param( 2020-08-18T11:50:03.4838083Z lambda t: t.string_col.reverse(), 2020-08-18T11:50:03.4838536Z lambda t: t.string_col.str[::-1], 2020-08-18T11:50:03.4838769Z id='reverse', 2020-08-18T11:50:03.4838876Z ), 2020-08-18T11:50:03.4838978Z param( 2020-08-18T11:50:03.4839092Z lambda t: t.string_col.ascii_str(), 2020-08-18T11:50:03.4839437Z lambda t: t.string_col.map(ord).astype('int32'), 2020-08-18T11:50:03.4839711Z id='ascii_str', 2020-08-18T11:50:03.4839820Z ), 2020-08-18T11:50:03.4839923Z param( 2020-08-18T11:50:03.4840032Z lambda t: t.string_col.length(), 2020-08-18T11:50:03.4840297Z lambda t: t.string_col.str.len().astype('int32'), 2020-08-18T11:50:03.4840529Z id='length', 2020-08-18T11:50:03.4840618Z ), 2020-08-18T11:50:03.4840723Z param( 2020-08-18T11:50:03.4840834Z lambda t: t.string_col.strip(), 2020-08-18T11:50:03.4840948Z lambda t: t.string_col.str.strip(), 2020-08-18T11:50:03.4841178Z id='strip', 2020-08-18T11:50:03.4841286Z ), 2020-08-18T11:50:03.4841389Z param( 2020-08-18T11:50:03.4841476Z lambda t: t.string_col.lstrip(), 2020-08-18T11:50:03.4841593Z lambda t: t.string_col.str.lstrip(), 2020-08-18T11:50:03.4841827Z id='lstrip', 2020-08-18T11:50:03.4841939Z ), 2020-08-18T11:50:03.4842044Z param( 2020-08-18T11:50:03.4842153Z lambda t: t.string_col.rstrip(), 2020-08-18T11:50:03.4842268Z lambda t: t.string_col.str.rstrip(), 2020-08-18T11:50:03.4842497Z id='rstrip', 2020-08-18T11:50:03.4842582Z ), 2020-08-18T11:50:03.4842685Z param( 2020-08-18T11:50:03.4842871Z lambda t: t.string_col.capitalize(), 2020-08-18T11:50:03.4842990Z lambda t: t.string_col.str.capitalize(), 2020-08-18T11:50:03.4843408Z id='capitalize', 2020-08-18T11:50:03.4843954Z ), 2020-08-18T11:50:03.4844116Z param( 2020-08-18T11:50:03.4844227Z lambda t: t.date_string_col.substr(2, 3), 2020-08-18T11:50:03.4844371Z lambda t: t.date_string_col.str[2:5], 2020-08-18T11:50:03.4844745Z id='substr', 2020-08-18T11:50:03.4844876Z ), 2020-08-18T11:50:03.4844999Z param( 2020-08-18T11:50:03.4845141Z lambda t: t.date_string_col.left(2), 2020-08-18T11:50:03.4845285Z lambda t: t.date_string_col.str[:2], 2020-08-18T11:50:03.4845536Z id='left', 2020-08-18T11:50:03.4845670Z ), 2020-08-18T11:50:03.4845793Z param( 2020-08-18T11:50:03.4845926Z lambda t: t.date_string_col.right(2), 2020-08-18T11:50:03.4846246Z lambda t: t.date_string_col.str[-2:], 2020-08-18T11:50:03.4846523Z id='right', 2020-08-18T11:50:03.4846652Z ), 2020-08-18T11:50:03.4846774Z param( 2020-08-18T11:50:03.4846882Z lambda t: t.date_string_col[1:3], 2020-08-18T11:50:03.4847025Z lambda t: t.date_string_col.str[1:3], 2020-08-18T11:50:03.4847610Z id='slice', 2020-08-18T11:50:03.4847718Z ), 2020-08-18T11:50:03.4847819Z param( 2020-08-18T11:50:03.4848268Z lambda t: t.date_string_col[t.date_string_col.length() - 1 :], 2020-08-18T11:50:03.4848906Z lambda t: t.date_string_col.str[-1:], 2020-08-18T11:50:03.4849112Z id='expr_slice_begin', 2020-08-18T11:50:03.4849218Z ), 2020-08-18T11:50:03.4849317Z param( 2020-08-18T11:50:03.4849429Z lambda t: t.date_string_col[: t.date_string_col.length()], 2020-08-18T11:50:03.4849551Z lambda t: t.date_string_col, 2020-08-18T11:50:03.4849792Z id='expr_slice_end', 2020-08-18T11:50:03.4849899Z ), 2020-08-18T11:50:03.4849976Z param( 2020-08-18T11:50:03.4851336Z lambda t: t.date_string_col[:], 2020-08-18T11:50:03.4851651Z lambda t: t.date_string_col, 2020-08-18T11:50:03.4851949Z id='expr_empty_slice', 2020-08-18T11:50:03.4852179Z ), 2020-08-18T11:50:03.4852310Z param( 2020-08-18T11:50:03.4852439Z lambda t: t.date_string_col[ 2020-08-18T11:50:03.4852888Z t.date_string_col.length() - 2 : t.date_string_col.length() - 1 2020-08-18T11:50:03.4853157Z ], 2020-08-18T11:50:03.4853655Z lambda t: t.date_string_col.str[-2:-1], 2020-08-18T11:50:03.4856337Z id='expr_slice_begin_end', 2020-08-18T11:50:03.4856613Z ), 2020-08-18T11:50:03.4856764Z param( 2020-08-18T11:50:03.4857073Z lambda t: t.date_string_col.split('/'), 2020-08-18T11:50:03.4857337Z lambda t: t.date_string_col.str.split('/'), 2020-08-18T11:50:03.4857570Z id='split', 2020-08-18T11:50:03.4857678Z ), 2020-08-18T11:50:03.4857760Z param( 2020-08-18T11:50:03.4858031Z lambda t: ibis.literal('-').join(['a', t.string_col, 'c']), 2020-08-18T11:50:03.4858295Z lambda t: 'a-' + t.string_col + '-c', 2020-08-18T11:50:03.4858562Z id='join', 2020-08-18T11:50:03.4858672Z ), 2020-08-18T11:50:03.4858775Z ], 2020-08-18T11:50:03.4858883Z ) 2020-08-18T11:50:03.4858966Z @pytest.mark.xfail_unsupported 2020-08-18T11:50:03.4859084Z def test_string(backend, alltypes, df, result_func, expected_func): 2020-08-18T11:50:03.4859204Z expr = result_func(alltypes) 2020-08-18T11:50:03.4859312Z > result = expr.execute() 2020-08-18T11:50:03.4859385Z 2020-08-18T11:50:03.4859468Z ibis/tests/all/test_string.py:237: