Re-implement select_object_content implementation

[harshavardhana]

This change fixes multiple issues

• handles Unicode boundaries properly for special delimiters
• handle zero payloads 'Cont' event messages
• handle error messages properly

[harshavardhana]

PR is updated with further changes @Praveenrajmani @sinhaashish PTAL

[sinhaashish]

Breaking for this DELIMITER_CH = '╦'

data = client.select_object_content('wlk-data-wbrp', '20190612-00690-1/wlk-wbrp-part-0000.csv.gz', options)

  output_serialization=OutputSerialization(
        csv=CSVOutput(QuoteFields="ASNEEDED",
                      RecordDelimiter="\n",
                      FieldDelimiter=DELIMITER_CH,
                      QuoteCharacter='"',
                      QuoteEscapeCharacter='"',)

Traceback (most recent call last):
  File "examples/select_object_content.py", line 70, in <module>
    data = client.select_object_content('wlk-data-wbrp', '20190612-00690-1/wlk-wbrp-part-0000.csv.gz', options)
  File "build/bdist.linux-x86_64/egg/minio/api.py", line 255, in select_object_content
  File "build/bdist.linux-x86_64/egg/minio/xml_marshal.py", line 114, in xml_marshal_select
  File "/usr/lib/python2.7/xml/etree/ElementTree.py", line 820, in write
    serialize(write, self._root, encoding, qnames, namespaces)
  File "/usr/lib/python2.7/xml/etree/ElementTree.py", line 939, in _serialize_xml
    _serialize_xml(write, e, encoding, qnames, None)
  File "/usr/lib/python2.7/xml/etree/ElementTree.py", line 939, in _serialize_xml
    _serialize_xml(write, e, encoding, qnames, None)
  File "/usr/lib/python2.7/xml/etree/ElementTree.py", line 939, in _serialize_xml
    _serialize_xml(write, e, encoding, qnames, None)
  File "/usr/lib/python2.7/xml/etree/ElementTree.py", line 937, in _serialize_xml
    write(_escape_cdata(text, encoding))
  File "/usr/lib/python2.7/xml/etree/ElementTree.py", line 1073, in _escape_cdata
    return text.encode(encoding, "xmlcharrefreplace")
UnicodeDecodeError: 'ascii' codec can't decode byte 0xe2 in position 0: ordinal not in range(128)

[harshavardhana]

Unicode characters should be inputs for python as u'character' in python2, python3 supports them natively.

[harshavardhana]

from minio import Minio
from minio.error import ResponseError

from minio.select.options import (SelectObjectOptions, CSVInput,
                                  JSONInput, RequestProgress,
                                  ParquetInput, InputSerialization,
                                  OutputSerialization, CSVOutput,
                                  JsonOutput)
from minio.select.errors import (SelectCRCValidationError, SelectMessageError)

client = Minio('s3.amazonaws.com',
               access_key='ACCESSKEY',
               secret_key='SECRETKEY')

options = SelectObjectOptions(
    expression="select * from s3object",
    input_serialization=InputSerialization(
        compression_type="GZIP",
        csv=CSVInput(FileHeaderInfo="USE",
                     RecordDelimiter="\n",
                     FieldDelimiter=u'╦',
                     QuoteCharacter='"',
                     QuoteEscapeCharacter='"',
                     Comments="#",
                     AllowQuotedRecordDelimiter="FALSE",
                     ),
        # If input is JSON
        # json=JSONInput(Type="DOCUMENT",)
        ),

    output_serialization=OutputSerialization(
        csv=CSVOutput(QuoteFields="ASNEEDED",
                      RecordDelimiter="\n",
                      FieldDelimiter=u'╦',
                      QuoteCharacter='"',
                      QuoteEscapeCharacter='"',)

        # json = JsonOutput(
        #     RecordDelimiter="\n",
        #     )
        ),
    request_progress=RequestProgress(
        enabled="False"
        )
    )

try:
    data = client.select_object_content('wlk-data-wbrp', '20190612-00690-1/wlk-wbrp-part-0000.csv.gz', options)

    # Get the records
    with open('my-record-file', 'w') as record_data:
        for d in data.stream(10*1024):
            record_data.write(d)

    # Get the stats
    print(data.stats())

except SelectMessageError as err:
    print(err)

except SelectCRCValidationError as err:
    print(err)

except ResponseError as err:
    print(err)

[sinhaashish]

Tested with different inputs and LGTM ,
Just SelectSelectCRCValidationError -> SelectCRCValidationError in examples/select_object_content.py

[Praveenrajmani]

LGTM