MCPcopy Create free account
hub / github.com/apache/arrow / __init__

Method __init__

python/pyarrow/parquet/core.py:1068–1151  ·  view source on GitHub ↗
(self, where, schema, filesystem=None,
                 flavor=None,
                 version='2.6',
                 use_dictionary=True,
                 compression='snappy',
                 write_statistics=True,
                 use_deprecated_int96_timestamps=None,
                 compression_level=None,
                 use_byte_stream_split=False,
                 column_encoding=None,
                 writer_engine_version=None,
                 data_page_version='1.0',
                 use_compliant_nested_type=True,
                 encryption_properties=None,
                 write_batch_size=None,
                 dictionary_pagesize_limit=None,
                 store_schema=True,
                 write_page_index=False,
                 write_page_checksum=False,
                 sorting_columns=None,
                 store_decimal_as_integer=False,
                 write_time_adjusted_to_utc=False,
                 max_rows_per_page=None,
                 bloom_filter_options=None,
                 use_content_defined_chunking=False,
                 **options)

Source from the content-addressed store, hash-verified

1066"""
1067
1068 def __init__(self, where, schema, filesystem=None,
1069 flavor=None,
1070 version='2.6',
1071 use_dictionary=True,
1072 compression='snappy',
1073 write_statistics=True,
1074 use_deprecated_int96_timestamps=None,
1075 compression_level=None,
1076 use_byte_stream_split=False,
1077 column_encoding=None,
1078 writer_engine_version=None,
1079 data_page_version='1.0',
1080 use_compliant_nested_type=True,
1081 encryption_properties=None,
1082 write_batch_size=None,
1083 dictionary_pagesize_limit=None,
1084 store_schema=True,
1085 write_page_index=False,
1086 write_page_checksum=False,
1087 sorting_columns=None,
1088 store_decimal_as_integer=False,
1089 write_time_adjusted_to_utc=False,
1090 max_rows_per_page=None,
1091 bloom_filter_options=None,
1092 use_content_defined_chunking=False,
1093 **options):
1094 if use_deprecated_int96_timestamps is None:
1095 # Use int96 timestamps for Spark
1096 if flavor is not None and 'spark' in flavor:
1097 use_deprecated_int96_timestamps = True
1098 else:
1099 use_deprecated_int96_timestamps = False
1100
1101 self.flavor = flavor
1102 if flavor is not None:
1103 schema, self.schema_changed = _sanitize_schema(schema, flavor)
1104 else:
1105 self.schema_changed = False
1106
1107 self.schema = schema
1108 self.where = where
1109
1110 # If we open a file using a filesystem, store file handle so we can be
1111 # sure to close it when `self.close` is called.
1112 self.file_handle = None
1113
1114 filesystem, path = _resolve_filesystem_and_path(where, filesystem)
1115 if filesystem is not None:
1116 # ARROW-10480: do not auto-detect compression. While
1117 # a filename like foo.parquet.gz is nonconforming, it
1118 # shouldn't implicitly apply compression.
1119 sink = self.file_handle = filesystem.open_output_stream(
1120 path, compression=None)
1121 else:
1122 sink = where
1123 self._metadata_collector = options.pop('metadata_collector', None)
1124 engine_version = 'V2'
1125 self.writer = _parquet.ParquetWriter(

Callers

nothing calls this directly

Calls 3

_sanitize_schemaFunction · 0.85
open_output_streamMethod · 0.45

Tested by

no test coverage detected