[ https://issues.apache.org/jira/browse/SPARK-35945?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Chandra updated SPARK-35945: ---------------------------- Description: My requirement is to process the file which have a multi character row and column delimiter. I tried multiple options but ended up with few issues. File sample: 127'~'127433'~''~''~'2'~'ICR'~'STDLONG'~'NR'~'NR'~'1997-06-25 14:47:37'~''~'NR'~''~'1997-06-25 14:47:37'~'BBB'~''~'Stable'~''~''~''~'Not Rated'~'CreditWatch/Outlook'~'OL'~''~''~''~'#@#@#152'~'308044'~''~''~'2'~'ICR'~'FCLONG'~'NR'~'NR'~'1997-12-05 14:23:33'~'NM'~'NR'~'1997-12-05 14:23:33'~'1997-12-05 14:23:33'~'B+'~'Watch Pos'~'NM'~''~''~''~'Not Rated'~'CreditWatch/Outlook'~'OL'~''~''~''~'#@#@#155'~'308044'~''~''~'2'~'ICR'~'STDLONG'~'NR'~'NR'~'1997-12-05 14:23:34'~'NM'~'NR'~'1997-12-05 14:23:34'~'1997-12-05 14:23:34'~'B+'~'Watch Pos'~'NM'~''~''~''~'Not Rated'~'CreditWatch/Outlook'~'OL'~''~''~''~'#@#[~infrabot] Row delimiter is : #@#@# COlumn Delimiter: '~' Code: df2 = spark.read.load("spRatingData_sample.txt", format="csv", sep="'~'", lineSep="#@#@#") print("two.csv rowcount: {}".format(df2.count())) ERROR: : java.lang.IllegalArgumentException: Delimiter cannot be more than one character: '~' at org.apache.spark.sql.execution.datasources.csv.CSVUtils$.toChar(CSVUtils.scala:118) at org.apache.spark.sql.execution.datasources.csv.CSVOptions.<init>(CSVOptions.scala:87) at org.apache.spark.sql.execution.datasources.csv.CSVOptions.<init>(CSVOptions.scala:45) at org.apache.spark.sql.execution.datasources.csv.CSVFileFormat.inferSchema(CSVFileFormat.scala:58) at org.apache.spark.sql.execution.datasources.DataSource.$anonfun$getOrInferFileFormatSchema$12(DataSource.scala:183) at scala.Option.orElse(Option.scala:447) at org.apache.spark.sql.execution.datasources.DataSource.getOrInferFileFormatSchema(DataSource.scala:180) at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:373) at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:223) at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:211) at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:178) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357) at py4j.Gateway.invoke(Gateway.java:282) at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) at py4j.commands.CallCommand.execute(CallCommand.java:79) at py4j.GatewayConnection.run(GatewayConnection.java:238) at java.lang.Thread.run(Thread.java:748) During handling of the above exception, another exception occurred: Traceback (most recent call last): File "<stdin>", line 4, in <module> File "/usr/lib/spark/python/pyspark/sql/readwriter.py", line 166, in load return self._df(self._jreader.load(path)) File "/usr/lib/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in __call__ File "/usr/lib/spark/python/pyspark/sql/utils.py", line 79, in deco raise IllegalArgumentException(s.split(': ', 1)[1], stackTrace) pyspark.sql.utils.IllegalArgumentException: "Delimiter cannot be more than one character: '~'" was: My requirement is to process the file which have a multi character row and column delimiter. I tried multiple options but ended up with few issues. File sample: 127'~'127433'~''~''~'2'~'ICR'~'STDLONG'~'NR'~'NR'~'1997-06-25 14:47:37'~''~'NR'~''~'1997-06-25 14:47:37'~'BBB'~''~'Stable'~''~''~''~'Not Rated'~'CreditWatch/Outlook'~'OL'~''~''~''~'#@#@#152'~'308044'~''~''~'2'~'ICR'~'FCLONG'~'NR'~'NR'~'1997-12-05 14:23:33'~'NM'~'NR'~'1997-12-05 14:23:33'~'1997-12-05 14:23:33'~'B+'~'Watch Pos'~'NM'~''~''~''~'Not Rated'~'CreditWatch/Outlook'~'OL'~''~''~''~'#@#@#155'~'308044'~''~''~'2'~'ICR'~'STDLONG'~'NR'~'NR'~'1997-12-05 14:23:34'~'NM'~'NR'~'1997-12-05 14:23:34'~'1997-12-05 14:23:34'~'B+'~'Watch Pos'~'NM'~''~''~''~'Not Rated'~'CreditWatch/Outlook'~'OL'~''~''~''~'#@#[~infrabot] Code: df2 = spark.read.load("spRatingData_sample.txt", format="csv", sep="'~'", lineSep="#@#@#") print("two.csv rowcount: {}".format(df2.count())) ERROR: : java.lang.IllegalArgumentException: Delimiter cannot be more than one character: '~' at org.apache.spark.sql.execution.datasources.csv.CSVUtils$.toChar(CSVUtils.scala:118) at org.apache.spark.sql.execution.datasources.csv.CSVOptions.<init>(CSVOptions.scala:87) at org.apache.spark.sql.execution.datasources.csv.CSVOptions.<init>(CSVOptions.scala:45) at org.apache.spark.sql.execution.datasources.csv.CSVFileFormat.inferSchema(CSVFileFormat.scala:58) at org.apache.spark.sql.execution.datasources.DataSource.$anonfun$getOrInferFileFormatSchema$12(DataSource.scala:183) at scala.Option.orElse(Option.scala:447) at org.apache.spark.sql.execution.datasources.DataSource.getOrInferFileFormatSchema(DataSource.scala:180) at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:373) at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:223) at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:211) at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:178) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357) at py4j.Gateway.invoke(Gateway.java:282) at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) at py4j.commands.CallCommand.execute(CallCommand.java:79) at py4j.GatewayConnection.run(GatewayConnection.java:238) at java.lang.Thread.run(Thread.java:748) During handling of the above exception, another exception occurred: Traceback (most recent call last): File "<stdin>", line 4, in <module> File "/usr/lib/spark/python/pyspark/sql/readwriter.py", line 166, in load return self._df(self._jreader.load(path)) File "/usr/lib/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in __call__ File "/usr/lib/spark/python/pyspark/sql/utils.py", line 79, in deco raise IllegalArgumentException(s.split(': ', 1)[1], stackTrace) pyspark.sql.utils.IllegalArgumentException: "Delimiter cannot be more than one character: '~'" > Unable to parse multi character row and column delimited files using Spark > --------------------------------------------------------------------------- > > Key: SPARK-35945 > URL: https://issues.apache.org/jira/browse/SPARK-35945 > Project: Spark > Issue Type: Bug > Components: Spark Submit > Affects Versions: 2.4.4 > Environment: development > Reporter: Chandra > Priority: Major > > My requirement is to process the file which have a multi character row and > column delimiter. > I tried multiple options but ended up with few issues. > > File sample: > 127'~'127433'~''~''~'2'~'ICR'~'STDLONG'~'NR'~'NR'~'1997-06-25 > 14:47:37'~''~'NR'~''~'1997-06-25 14:47:37'~'BBB'~''~'Stable'~''~''~''~'Not > Rated'~'CreditWatch/Outlook'~'OL'~''~''~''~'#@#@#152'~'308044'~''~''~'2'~'ICR'~'FCLONG'~'NR'~'NR'~'1997-12-05 > 14:23:33'~'NM'~'NR'~'1997-12-05 14:23:33'~'1997-12-05 14:23:33'~'B+'~'Watch > Pos'~'NM'~''~''~''~'Not > Rated'~'CreditWatch/Outlook'~'OL'~''~''~''~'#@#@#155'~'308044'~''~''~'2'~'ICR'~'STDLONG'~'NR'~'NR'~'1997-12-05 > 14:23:34'~'NM'~'NR'~'1997-12-05 14:23:34'~'1997-12-05 14:23:34'~'B+'~'Watch > Pos'~'NM'~''~''~''~'Not > Rated'~'CreditWatch/Outlook'~'OL'~''~''~''~'#@#[~infrabot] > > Row delimiter is : #@#@# COlumn Delimiter: '~' > Code: > df2 = spark.read.load("spRatingData_sample.txt", > format="csv", > sep="'~'", > lineSep="#@#@#") > print("two.csv rowcount: {}".format(df2.count())) > > ERROR: > : java.lang.IllegalArgumentException: Delimiter cannot be more than one > character: '~' > at > org.apache.spark.sql.execution.datasources.csv.CSVUtils$.toChar(CSVUtils.scala:118) > at > org.apache.spark.sql.execution.datasources.csv.CSVOptions.<init>(CSVOptions.scala:87) > at > org.apache.spark.sql.execution.datasources.csv.CSVOptions.<init>(CSVOptions.scala:45) > at > org.apache.spark.sql.execution.datasources.csv.CSVFileFormat.inferSchema(CSVFileFormat.scala:58) > at > org.apache.spark.sql.execution.datasources.DataSource.$anonfun$getOrInferFileFormatSchema$12(DataSource.scala:183) > at scala.Option.orElse(Option.scala:447) > at > org.apache.spark.sql.execution.datasources.DataSource.getOrInferFileFormatSchema(DataSource.scala:180) > at > org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:373) > at > org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:223) > at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:211) > at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:178) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:498) > at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) > at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357) > at py4j.Gateway.invoke(Gateway.java:282) > at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) > at py4j.commands.CallCommand.execute(CallCommand.java:79) > at py4j.GatewayConnection.run(GatewayConnection.java:238) > at java.lang.Thread.run(Thread.java:748) > During handling of the above exception, another exception occurred: > Traceback (most recent call last): > File "<stdin>", line 4, in <module> > File "/usr/lib/spark/python/pyspark/sql/readwriter.py", line 166, in load > return self._df(self._jreader.load(path)) > File "/usr/lib/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", > line 1257, in __call__ > File "/usr/lib/spark/python/pyspark/sql/utils.py", line 79, in deco > raise IllegalArgumentException(s.split(': ', 1)[1], stackTrace) > pyspark.sql.utils.IllegalArgumentException: "Delimiter cannot be more than > one character: '~'" -- This message was sent by Atlassian Jira (v8.3.4#803005) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org