Repository navigation
Expand file tree
/
Copy pathoptions.py
More file actions
284 lines (243 loc) · 11 KB
/
Copy pathoptions.py
File metadata and controls
284 lines (243 loc) · 11 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
"""Options for reading various file formats."""
from __future__ import annotations
import warnings
from typing import TYPE_CHECKING
import pyarrow as pa
from datafusion.expr import sort_list_to_raw_sort_list
if TYPE_CHECKING:
from datafusion.expr import SortExpr
from ._internal import options
__all__ = ["CsvReadOptions"]
DEFAULT_MAX_INFER_SCHEMA = 1000
class CsvReadOptions:
"""Options for reading CSV files.
This class provides a builder pattern for configuring CSV reading options.
All methods starting with ``with_`` return ``self`` to allow method chaining.
"""
def __init__(
self,
*,
has_header: bool = True,
delimiter: str = ",",
quote: str = '"',
terminator: str | None = None,
escape: str | None = None,
comment: str | None = None,
newlines_in_values: bool = False,
schema: pa.Schema | None = None,
schema_infer_max_records: int = DEFAULT_MAX_INFER_SCHEMA,
file_extension: str = ".csv",
table_partition_cols: list[tuple[str, pa.DataType]] | None = None,
file_compression_type: str = "",
file_sort_order: list[list[SortExpr]] | None = None,
null_regex: str | None = None,
truncated_rows: bool = False,
) -> None:
"""Initialize CsvReadOptions.
Args:
has_header: Does the CSV file have a header row? If schema inference
is run on a file with no headers, default column names are created.
delimiter: Column delimiter character. Must be a single ASCII character.
quote: Quote character for fields containing delimiters or newlines.
Must be a single ASCII character.
terminator: Optional line terminator character. If ``None``, uses CRLF.
Must be a single ASCII character.
escape: Optional escape character for quotes. Must be a single ASCII
character.
comment: If specified, lines beginning with this character are ignored.
Must be a single ASCII character.
newlines_in_values: Whether newlines in quoted values are supported.
Parsing newlines in quoted values may be affected by execution
behavior such as parallel file scanning. Setting this to ``True``
ensures that newlines in values are parsed successfully, which may
reduce performance.
schema: Optional PyArrow schema representing the CSV files. If ``None``,
the CSV reader will try to infer it based on data in the file.
schema_infer_max_records: Maximum number of rows to read from CSV files
for schema inference if needed.
file_extension: File extension; only files with this extension are
selected for data input.
table_partition_cols: Partition columns as a list of tuples of
(column_name, data_type).
file_compression_type: File compression type. Supported values are
``"gzip"``, ``"bz2"``, ``"xz"``, ``"zstd"``, or empty string for
uncompressed.
file_sort_order: Optional sort order of the files as a list of sort
expressions per file.
null_regex: Optional regex pattern to match null values in the CSV.
truncated_rows: Whether to allow truncated rows when parsing. By default
this is ``False`` and will error if the CSV rows have different
lengths. When set to ``True``, it will allow records with less than
the expected number of columns and fill the missing columns with
nulls. If the record's schema is not nullable, it will still return
an error.
"""
validate_single_character("delimiter", delimiter)
validate_single_character("quote", quote)
validate_single_character("terminator", terminator)
validate_single_character("escape", escape)
validate_single_character("comment", comment)
self.has_header = has_header
self.delimiter = delimiter
self.quote = quote
self.terminator = terminator
self.escape = escape
self.comment = comment
self.newlines_in_values = newlines_in_values
self.schema = schema
self.schema_infer_max_records = schema_infer_max_records
self.file_extension = file_extension
self.table_partition_cols = table_partition_cols or []
self.file_compression_type = file_compression_type
self.file_sort_order = file_sort_order or []
self.null_regex = null_regex
self.truncated_rows = truncated_rows
def with_has_header(self, has_header: bool) -> CsvReadOptions:
"""Configure whether the CSV has a header row."""
self.has_header = has_header
return self
def with_delimiter(self, delimiter: str) -> CsvReadOptions:
"""Configure the column delimiter."""
self.delimiter = delimiter
return self
def with_quote(self, quote: str) -> CsvReadOptions:
"""Configure the quote character."""
self.quote = quote
return self
def with_terminator(self, terminator: str | None) -> CsvReadOptions:
"""Configure the line terminator character."""
self.terminator = terminator
return self
def with_escape(self, escape: str | None) -> CsvReadOptions:
"""Configure the escape character."""
self.escape = escape
return self
def with_comment(self, comment: str | None) -> CsvReadOptions:
"""Configure the comment character."""
self.comment = comment
return self
def with_newlines_in_values(self, newlines_in_values: bool) -> CsvReadOptions:
"""Configure whether newlines in values are supported."""
self.newlines_in_values = newlines_in_values
return self
def with_schema(self, schema: pa.Schema | None) -> CsvReadOptions:
"""Configure the schema."""
self.schema = schema
return self
def with_schema_infer_max_records(
self, schema_infer_max_records: int
) -> CsvReadOptions:
"""Configure maximum records for schema inference."""
self.schema_infer_max_records = schema_infer_max_records
return self
def with_file_extension(self, file_extension: str) -> CsvReadOptions:
"""Configure the file extension filter."""
self.file_extension = file_extension
return self
def with_table_partition_cols(
self, table_partition_cols: list[tuple[str, pa.DataType]]
) -> CsvReadOptions:
"""Configure table partition columns."""
self.table_partition_cols = table_partition_cols
return self
def with_file_compression_type(self, file_compression_type: str) -> CsvReadOptions:
"""Configure file compression type."""
self.file_compression_type = file_compression_type
return self
def with_file_sort_order(
self, file_sort_order: list[list[SortExpr]]
) -> CsvReadOptions:
"""Configure file sort order."""
self.file_sort_order = file_sort_order
return self
def with_null_regex(self, null_regex: str | None) -> CsvReadOptions:
"""Configure null value regex pattern."""
self.null_regex = null_regex
return self
def with_truncated_rows(self, truncated_rows: bool) -> CsvReadOptions:
"""Configure whether to allow truncated rows."""
self.truncated_rows = truncated_rows
return self
def to_inner(self) -> options.CsvReadOptions:
"""Convert this object into the underlying Rust structure.
This is intended for internal use only.
"""
file_sort_order = (
[]
if self.file_sort_order is None
else [
sort_list_to_raw_sort_list(sort_list)
for sort_list in self.file_sort_order
]
)
return options.CsvReadOptions(
has_header=self.has_header,
delimiter=ord(self.delimiter[0]) if self.delimiter else ord(","),
quote=ord(self.quote[0]) if self.quote else ord('"'),
terminator=ord(self.terminator[0]) if self.terminator else None,
escape=ord(self.escape[0]) if self.escape else None,
comment=ord(self.comment[0]) if self.comment else None,
newlines_in_values=self.newlines_in_values,
schema=self.schema,
schema_infer_max_records=self.schema_infer_max_records,
file_extension=self.file_extension,
table_partition_cols=_convert_table_partition_cols(
self.table_partition_cols
),
file_compression_type=self.file_compression_type or "",
file_sort_order=file_sort_order,
null_regex=self.null_regex,
truncated_rows=self.truncated_rows,
)
def validate_single_character(name: str, value: str | None) -> None:
if value is not None and len(value) != 1:
message = f"{name} must be a single character"
raise ValueError(message)
def _convert_table_partition_cols(
table_partition_cols: list[tuple[str, str | pa.DataType]],
) -> list[tuple[str, pa.DataType]]:
warn = False
converted_table_partition_cols = []
for col, data_type in table_partition_cols:
if isinstance(data_type, str):
warn = True
if data_type == "string":
converted_data_type = pa.string()
elif data_type == "int":
converted_data_type = pa.int32()
else:
message = (
f"Unsupported literal data type '{data_type}' for partition "
"column. Supported types are 'string' and 'int'"
)
raise ValueError(message)
else:
converted_data_type = data_type
converted_table_partition_cols.append((col, converted_data_type))
if warn:
message = (
"using literals for table_partition_cols data types is deprecated,"
"use pyarrow types instead"
)
warnings.warn(
message,
category=DeprecationWarning,
stacklevel=2,
)
return converted_table_partition_cols