FM / pyarrow

/usr/local/lib64/python3.6/site-packages/pyarrow/

/usr/local/lib64/python3.6/site-packages/pyarrow

Name	Size	Mode	Actions
include/	-	0755	rm
includes/	-	0755	rm
tensorflow/	-	0755	rm
tests/	-	0755	rm
vendored/	-	0755	rm
__pycache__/	-	0755	rm
array.pxi	79609	0644	edit dl rm
benchmark.pxi	869	0644	edit dl rm
benchmark.py	856	0644	edit dl rm
builder.pxi	2688	0644	edit dl rm
cffi.py	2178	0644	edit dl rm
compat.pxi	1810	0644	edit dl rm
compat.py	1076	0644	edit dl rm
compute.py	22837	0644	edit dl rm
config.pxi	2613	0644	edit dl rm
csv.py	962	0644	edit dl rm
cuda.py	1087	0644	edit dl rm
dataset.py	33333	0644	edit dl rm
error.pxi	7807	0644	edit dl rm
feather.py	9258	0644	edit dl rm
filesystem.py	14468	0644	edit dl rm
flight.py	1794	0644	edit dl rm
fs.py	13444	0644	edit dl rm
gandiva.pyx	18447	0644	edit dl rm
hdfs.py	7527	0644	edit dl rm
io.pxi	64495	0644	edit dl rm
ipc.pxi	28821	0644	edit dl rm
ipc.py	8029	0644	edit dl rm
json.py	858	0644	edit dl rm
jvm.py	9593	0644	edit dl rm
lib.cpython-36m-x86_64-linux-gnu.so	3760528	0755	edit dl rm
lib.pxd	14442	0644	edit dl rm
lib.pyx	4373	0644	edit dl rm
libarrow.so.600	48162600	0755	edit dl rm
libarrow_dataset.so.600	2541120	0755	edit dl rm
libarrow_flight.so.600	12999784	0755	edit dl rm
libarrow_python.so.600	1848920	0755	edit dl rm
libarrow_python_flight.so.600	112728	0755	edit dl rm
libparquet.so.600	4458552	0755	edit dl rm
libplasma.so.600	251296	0755	edit dl rm
lib_api.h	19153	0644	edit dl rm
memory.pxi	7451	0644	edit dl rm
orc.py	5269	0644	edit dl rm
pandas-shim.pxi	7987	0644	edit dl rm
pandas_compat.py	42243	0644	edit dl rm
parquet.py	86844	0644	edit dl rm
plasma-store-server	482776	0755	edit dl rm
plasma.py	6075	0644	edit dl rm
public-api.pxi	12814	0644	edit dl rm
scalar.pxi	29182	0644	edit dl rm
serialization.pxi	19086	0644	edit dl rm
serialization.py	18202	0644	edit dl rm
table.pxi	72277	0644	edit dl rm
tensor.pxi	34311	0644	edit dl rm
types.pxi	79432	0644	edit dl rm
types.py	10381	0644	edit dl rm
util.py	5001	0644	edit dl rm
_compute.cpython-36m-x86_64-linux-gnu.so	717312	0755	edit dl rm
_compute.pxd	1149	0644	edit dl rm
_compute.pyx	41759	0644	edit dl rm
_csv.cpython-36m-x86_64-linux-gnu.so	312168	0755	edit dl rm
_csv.pxd	1602	0644	edit dl rm
_csv.pyx	39297	0644	edit dl rm
_cuda.pxd	1922	0644	edit dl rm
_cuda.pyx	34731	0644	edit dl rm
_dataset.cpython-36m-x86_64-linux-gnu.so	1080168	0755	edit dl rm
_dataset.pxd	1644	0644	edit dl rm
_dataset.pyx	120054	0644	edit dl rm
_dataset_orc.cpython-36m-x86_64-linux-gnu.so	52536	0755	edit dl rm
_dataset_orc.pyx	1345	0644	edit dl rm
_feather.cpython-36m-x86_64-linux-gnu.so	94280	0755	edit dl rm
_feather.pyx	3623	0644	edit dl rm
_flight.cpython-36m-x86_64-linux-gnu.so	1124664	0755	edit dl rm
_flight.pyx	93532	0644	edit dl rm
_fs.cpython-36m-x86_64-linux-gnu.so	469992	0755	edit dl rm
_fs.pxd	2484	0644	edit dl rm
_fs.pyx	40017	0644	edit dl rm
_generated_version.py	142	0644	edit dl rm
_hdfs.cpython-36m-x86_64-linux-gnu.so	127352	0755	edit dl rm
_hdfs.pyx	5471	0644	edit dl rm
_hdfsio.cpython-36m-x86_64-linux-gnu.so	208096	0755	edit dl rm
_hdfsio.pyx	13681	0644	edit dl rm
_json.cpython-36m-x86_64-linux-gnu.so	90616	0755	edit dl rm
_json.pyx	8406	0644	edit dl rm
_orc.cpython-36m-x86_64-linux-gnu.so	109776	0755	edit dl rm
_orc.pxd	2350	0644	edit dl rm
_orc.pyx	5151	0644	edit dl rm
_parquet.cpython-36m-x86_64-linux-gnu.so	507792	0755	edit dl rm
_parquet.pxd	22084	0644	edit dl rm
_parquet.pyx	47997	0644	edit dl rm
_plasma.cpython-36m-x86_64-linux-gnu.so	259168	0755	edit dl rm
_plasma.pyx	29495	0644	edit dl rm
_s3fs.cpython-36m-x86_64-linux-gnu.so	199496	0755	edit dl rm
_s3fs.pyx	11662	0644	edit dl rm
__init__.pxd	2195	0644	edit dl rm
__init__.py	21263	0644	edit dl rm

Edit: /usr/local/lib64/python3.6/site-packages/pyarrow/_json.pyx (8406B)

# 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.

# cython: profile=False
# distutils: language = c++
# cython: language_level = 3

from pyarrow.includes.common cimport *
from pyarrow.includes.libarrow cimport *
from pyarrow.lib cimport (check_status, _Weakrefable, Field, MemoryPool,
                          ensure_type, maybe_unbox_memory_pool,
                          get_input_stream, pyarrow_wrap_table,
                          pyarrow_wrap_data_type, pyarrow_unwrap_data_type,
                          pyarrow_wrap_schema, pyarrow_unwrap_schema)

cdef class ReadOptions(_Weakrefable):
    """
    Options for reading JSON files.

Parameters
    ----------
    use_threads : bool, optional (default True)
        Whether to use multiple threads to accelerate reading
    block_size : int, optional
        How much bytes to process at a time from the input stream.
        This will determine multi-threading granularity as well as
        the size of individual chunks in the Table.
    """
    cdef:
        CJSONReadOptions options

# Avoid mistakingly creating attributes
    __slots__ = ()

def __init__(self, use_threads=None, block_size=None):
        self.options = CJSONReadOptions.Defaults()
        if use_threads is not None:
            self.use_threads = use_threads
        if block_size is not None:
            self.block_size = block_size

@property
    def use_threads(self):
        """
        Whether to use multiple threads to accelerate reading.
        """
        return self.options.use_threads

@use_threads.setter
    def use_threads(self, value):
        self.options.use_threads = value

@property
    def block_size(self):
        """
        How much bytes to process at a time from the input stream.

This will determine multi-threading granularity as well as the size of
        individual chunks in the Table.
        """
        return self.options.block_size

@block_size.setter
    def block_size(self, value):
        self.options.block_size = value

cdef class ParseOptions(_Weakrefable):
    """
    Options for parsing JSON files.

Parameters
    ----------
    explicit_schema : Schema, optional (default None)
        Optional explicit schema (no type inference, ignores other fields).
    newlines_in_values : bool, optional (default False)
        Whether objects may be printed across multiple lines (for example
        pretty printed). If false, input must end with an empty line.
    unexpected_field_behavior : str, default "infer"
        How JSON fields outside of explicit_schema (if given) are treated.

Possible behaviors:

- "ignore": unexpected JSON fields are ignored
         - "error": error out on unexpected JSON fields
         - "infer": unexpected JSON fields are type-inferred and included in
           the output
    """

cdef:
        CJSONParseOptions options

__slots__ = ()

def __init__(self, explicit_schema=None, newlines_in_values=None,
                 unexpected_field_behavior=None):
        self.options = CJSONParseOptions.Defaults()
        if explicit_schema is not None:
            self.explicit_schema = explicit_schema
        if newlines_in_values is not None:
            self.newlines_in_values = newlines_in_values
        if unexpected_field_behavior is not None:
            self.unexpected_field_behavior = unexpected_field_behavior

@property
    def explicit_schema(self):
        """
        Optional explicit schema (no type inference, ignores other fields)
        """
        if self.options.explicit_schema.get() == NULL:
            return None
        else:
            return pyarrow_wrap_schema(self.options.explicit_schema)

@explicit_schema.setter
    def explicit_schema(self, value):
        self.options.explicit_schema = pyarrow_unwrap_schema(value)

@property
    def newlines_in_values(self):
        """
        Whether newline characters are allowed in JSON values.
        Setting this to True reduces the performance of multi-threaded
        JSON reading.
        """
        return self.options.newlines_in_values

@newlines_in_values.setter
    def newlines_in_values(self, value):
        self.options.newlines_in_values = value

@property
    def unexpected_field_behavior(self):
        """
        How JSON fields outside of explicit_schema (if given) are treated.

Possible behaviors:

- "ignore": unexpected JSON fields are ignored
         - "error": error out on unexpected JSON fields
         - "infer": unexpected JSON fields are type-inferred and included in
           the output

Set to "infer" by default.
        """
        v = self.options.unexpected_field_behavior
        if v == CUnexpectedFieldBehavior_Ignore:
            return "ignore"
        elif v == CUnexpectedFieldBehavior_Error:
            return "error"
        elif v == CUnexpectedFieldBehavior_InferType:
            return "infer"
        else:
            raise ValueError('Unexpected value for unexpected_field_behavior')

@unexpected_field_behavior.setter
    def unexpected_field_behavior(self, value):
        cdef CUnexpectedFieldBehavior v

if value == "ignore":
            v = CUnexpectedFieldBehavior_Ignore
        elif value == "error":
            v = CUnexpectedFieldBehavior_Error
        elif value == "infer":
            v = CUnexpectedFieldBehavior_InferType
        else:
            raise ValueError(
                "Unexpected value `{}` for `unexpected_field_behavior`, pass "
                "either `ignore`, `error` or `infer`.".format(value)
            )

self.options.unexpected_field_behavior = v

cdef _get_reader(input_file, shared_ptr[CInputStream]* out):
    use_memory_map = False
    get_input_stream(input_file, use_memory_map, out)

cdef _get_read_options(ReadOptions read_options, CJSONReadOptions* out):
    if read_options is None:
        out[0] = CJSONReadOptions.Defaults()
    else:
        out[0] = read_options.options

cdef _get_parse_options(ParseOptions parse_options, CJSONParseOptions* out):
    if parse_options is None:
        out[0] = CJSONParseOptions.Defaults()
    else:
        out[0] = parse_options.options

def read_json(input_file, read_options=None, parse_options=None,
              MemoryPool memory_pool=None):
    """
    Read a Table from a stream of JSON data.

Parameters
    ----------
    input_file : str, path or file-like object
        The location of JSON data. Currently only the line-delimited JSON
        format is supported.
    read_options : pyarrow.json.ReadOptions, optional
        Options for the JSON reader (see ReadOptions constructor for defaults).
    parse_options : pyarrow.json.ParseOptions, optional
        Options for the JSON parser
        (see ParseOptions constructor for defaults).
    memory_pool : MemoryPool, optional
        Pool to allocate Table memory from.

Returns
    -------
    :class:`pyarrow.Table`
        Contents of the JSON file as a in-memory table.
    """
    cdef:
        shared_ptr[CInputStream] stream
        CJSONReadOptions c_read_options
        CJSONParseOptions c_parse_options
        shared_ptr[CJSONReader] reader
        shared_ptr[CTable] table

_get_reader(input_file, &stream)
    _get_read_options(read_options, &c_read_options)
    _get_parse_options(parse_options, &c_parse_options)

reader = GetResultValue(
        CJSONReader.Make(maybe_unbox_memory_pool(memory_pool),
                         stream, c_read_options, c_parse_options))

with nogil:
        table = GetResultValue(reader.get().Read())

return pyarrow_wrap_table(table)

cmd: