def dump(data, abspath, pk_protocol=py23.pk_protocol,
overwrite=False, enable_verbose=True):
"""Dump picklable object to file.
Provides multiple choice to customize the behavior.
:param data: picklable python object.
:type data: dict or list
:param abspath: ``save as`` path, file extension has to be ``.pickle`` or ``.gz``
(for compressed Pickle)
:type abspath: string
:param pk_protocol: default = your python version, use 2, to make a
py2.x/3.x compatible pickle file. But 3 is faster.
:type pk_protocol: int
:param overwrite: default ``False``, If ``True``, when you dump to existing
file, it silently overwrite it. If ``False``, an alert message is shown.
Default setting ``False`` is to prevent overwrite file by mistake.
:type overwrite: boolean
:param enable_verbose: default True, help-message-display trigger.
:type enable_verbose: boolean
Usage::
>>> from dataIO import pk
>>> data = {"a": 1, "b": 2}
>>> dump(data, "test.pickle", overwrite=True)
Dump to `test.pickle` ...
Complete! Elapse 0.002432 sec
**中文文档**
将Python中可被序列化的"字典", "列表"以及他们的组合, 按照Json的编码方式写入文件
文件
参数列表
:param data: 可Pickle化的Python对象
:type data: ``字典`` 或 ``列表``
:param abspath: Pickle文件绝对路径, 扩展名需为 ``.pickle`` 或 ``.gz``, 其中 ``.gz``
是被压缩后的Pickle文件
:type abspath: ``字符串``
:param pk_protocol: 默认值为你的Python大版本号, 使用2可以使得Python2/3都能
兼容你的Pickle文件。不过Python3的速度更快。
:type pk_protocol: int
:param overwrite: 默认 ``False``, 当为``True``时, 如果写入路径已经存在, 则会
自动覆盖原文件。而为``False``时, 则会打印警告文件, 防止误操作覆盖源文件。
:type overwrite: "布尔值"
:param enable_verbose: 默认 ``True``, 信息提示的开关, 批处理时建议关闭
:type enable_verbose: ``布尔值``
"""
prt("\nDump to '%s' ..." % abspath, enable_verbose)
abspath = lower_ext(str(abspath))
is_pickle = is_pickle_file(abspath)
if os.path.exists(abspath):
if not overwrite: # 存在, 并且overwrite=False
prt(" Stop! File exists and overwrite is not allowed",
enable_verbose)
return
st = time.clock()
content = pickle.dumps(data, pk_protocol)
if is_pickle:
textfile.writebytes(content, abspath)
else:
compress.write_gzip(content, abspath)
prt(" Complete! Elapse %.6f sec." % (time.clock() - st), enable_verbose)
def dump(data,
abspath,
pk_protocol=py23.pk_protocol,
overwrite=False,
enable_verbose=True):
"""Dump picklable object to file.
Provides multiple choice to customize the behavior.
:param data: picklable python object.
:type data: dict or list
:param abspath: ``save as`` path, file extension has to be ``.pickle`` or ``.gz``
(for compressed Pickle)
:type abspath: string
:param pk_protocol: default = your python version, use 2, to make a
py2.x/3.x compatible pickle file. But 3 is faster.
:type pk_protocol: int
:param overwrite: default ``False``, If ``True``, when you dump to existing
file, it silently overwrite it. If ``False``, an alert message is shown.
Default setting ``False`` is to prevent overwrite file by mistake.
:type overwrite: boolean
:param enable_verbose: default True, help-message-display trigger.
:type enable_verbose: boolean
Usage::
>>> from dataIO import pk
>>> data = {"a": 1, "b": 2}
>>> dump(data, "test.pickle", overwrite=True)
Dump to `test.pickle` ...
Complete! Elapse 0.002432 sec
**中文文档**
将Python中可被序列化的"字典", "列表"以及他们的组合, 按照Json的编码方式写入文件
文件
参数列表
:param data: 可Pickle化的Python对象
:type data: ``字典`` 或 ``列表``
:param abspath: Pickle文件绝对路径, 扩展名需为 ``.pickle`` 或 ``.gz``, 其中 ``.gz``
是被压缩后的Pickle文件
:type abspath: ``字符串``
:param pk_protocol: 默认值为你的Python大版本号, 使用2可以使得Python2/3都能
兼容你的Pickle文件。不过Python3的速度更快。
:type pk_protocol: int
:param overwrite: 默认 ``False``, 当为``True``时, 如果写入路径已经存在, 则会
自动覆盖原文件。而为``False``时, 则会打印警告文件, 防止误操作覆盖源文件。
:type overwrite: "布尔值"
:param enable_verbose: 默认 ``True``, 信息提示的开关, 批处理时建议关闭
:type enable_verbose: ``布尔值``
"""
prt("\nDump to '%s' ..." % abspath, enable_verbose)
abspath = lower_ext(str(abspath))
is_pickle = is_pickle_file(abspath)
if os.path.exists(abspath):
if not overwrite: # 存在, 并且overwrite=False
prt(" Stop! File exists and overwrite is not allowed",
enable_verbose)
return
st = time.clock()
content = pickle.dumps(data, pk_protocol)
if is_pickle:
textfile.writebytes(content, abspath)
else:
compress.write_gzip(content, abspath)
prt(" Complete! Elapse %.6f sec." % (time.clock() - st), enable_verbose)
def dump(data, abspath,
indent_format=False,
float_precision=None,
overwrite=False,
enable_verbose=True):
"""Dump Json serializable object to file.
Provides multiple choice to customize the behavior.
:param data: Serializable python object.
:type data: dict or list
:param abspath: ``save as`` path, file extension has to be ``.json`` or ``.gz``
(for compressed Json)
:type abspath: string
:param indent_format: default ``False``, If ``True``, then dump to human
readable format, but it's slower, the file is larger
:type indent_format: boolean
:param float_precision: default ``None``, limit flotas to N-decimal points.
:type float_precision: integer
:param overwrite: default ``False``, If ``True``, when you dump to existing
file, it silently overwrite it. If ``False``, an alert message is shown.
Default setting ``False`` is to prevent overwrite file by mistake.
:type overwrite: boolean
:param enable_verbose: default True, help-message-display trigger.
:type enable_verbose: boolean
Usage::
>>> from dataIO import js
>>> data = {"a": 1, "b": 2}
>>> dump(data, "test.json", overwrite=True)
Dumping to 'test.json'...
Complete! Elapse 0.002432 sec
**中文文档**
将Python中可被序列化的"字典", "列表"以及他们的组合, 按照Json的编码方式写入文件
文件
参数列表
:param js: 可Json化的Python对象
:type js: ``字典`` 或 ``列表``
:param abspath: Json文件绝对路径, 扩展名需为 ``.json`` 或 ``.gz``, 其中 ``.gz``
是被压缩后的Json文件
:type abspath: ``字符串``
:param indent_format: 默认 ``False``, 当为 ``True`` 时, Json编码时会对Key进行
排序, 并进行缩进排版。但是这样写入速度较慢, 文件体积也更大。
:type indent_format: "布尔值"
:param overwrite: 默认 ``False``, 当为``True``时, 如果写入路径已经存在, 则会
自动覆盖原文件。而为``False``时, 则会打印警告文件, 防止误操作覆盖源文件。
:type overwrite: "布尔值"
:param float_precision: 默认 ``None``, 当为任意整数时, 则会保留小数点后N位
:type float_precision: "整数"
:param enable_verbose: 默认 ``True``, 信息提示的开关, 批处理时建议关闭
:type enable_verbose: ``布尔值``
"""
prt("\nDump to '%s' ..." % abspath, enable_verbose)
abspath = lower_ext(str(abspath))
is_json = is_json_file(abspath)
if os.path.exists(abspath):
if not overwrite: # 存在, 并且overwrite=False
prt(" Stop! File exists and overwrite is not allowed",
enable_verbose)
return
if float_precision is not None:
encoder.FLOAT_REPR = lambda x: format(x, ".%sf" % float_precision)
indent_format = True
else:
encoder.FLOAT_REPR = repr
if indent_format:
sort_keys = True
indent = 4
else:
sort_keys = False
indent = None
st = time.clock()
js = json.dumps(data, sort_keys=sort_keys, indent=indent)
content = js.encode("utf-8")
if is_json:
textfile.writebytes(content, abspath)
else:
compress.write_gzip(content, abspath)
prt(" Complete! Elapse %.6f sec." % (time.clock() - st), enable_verbose)
def dump(data,
abspath,
indent_format=False,
float_precision=None,
ensure_ascii=True,
overwrite=False,
enable_verbose=True):
"""Dump Json serializable object to file.
Provides multiple choice to customize the behavior.
:param data: Serializable python object.
:type data: dict or list
:param abspath: ``save as`` path, file extension has to be ``.json`` or ``.gz``
(for compressed Json)
:type abspath: string
:param indent_format: default ``False``, If ``True``, then dump to human
readable format, but it's slower, the file is larger
:type indent_format: boolean
:param float_precision: default ``None``, limit flotas to N-decimal points.
:type float_precision: integer
:param overwrite: default ``False``, If ``True``, when you dump to existing
file, it silently overwrite it. If ``False``, an alert message is shown.
Default setting ``False`` is to prevent overwrite file by mistake.
:type overwrite: boolean
:param enable_verbose: default True, help-message-display trigger.
:type enable_verbose: boolean
Usage::
>>> from dataIO import js
>>> data = {"a": 1, "b": 2}
>>> dump(data, "test.json", overwrite=True)
Dumping to 'test.json'...
Complete! Elapse 0.002432 sec
**中文文档**
将Python中可被序列化的"字典", "列表"以及他们的组合, 按照Json的编码方式写入文件
文件
参数列表
:param js: 可Json化的Python对象
:type js: ``字典`` 或 ``列表``
:param abspath: Json文件绝对路径, 扩展名需为 ``.json`` 或 ``.gz``, 其中 ``.gz``
是被压缩后的Json文件
:type abspath: ``字符串``
:param indent_format: 默认 ``False``, 当为 ``True`` 时, Json编码时会对Key进行
排序, 并进行缩进排版。但是这样写入速度较慢, 文件体积也更大。
:type indent_format: "布尔值"
:param overwrite: 默认 ``False``, 当为``True``时, 如果写入路径已经存在, 则会
自动覆盖原文件。而为``False``时, 则会打印警告文件, 防止误操作覆盖源文件。
:type overwrite: "布尔值"
:param float_precision: 默认 ``None``, 当为任意整数时, 则会保留小数点后N位
:type float_precision: "整数"
:param enable_verbose: 默认 ``True``, 信息提示的开关, 批处理时建议关闭
:type enable_verbose: ``布尔值``
"""
#prt("\nDump to '%s' ..." % abspath, enable_verbose)
abspath = lower_ext(str(abspath))
is_json = is_json_file(abspath)
if os.path.exists(abspath):
if not overwrite: # 存在, 并且overwrite=False
prt(" Stop! File exists and overwrite is not allowed",
enable_verbose)
return
if float_precision is not None:
encoder.FLOAT_REPR = lambda x: format(x, ".%sf" % float_precision)
indent_format = True
else:
encoder.FLOAT_REPR = repr
if indent_format:
sort_keys = True
indent = 4
else:
sort_keys = False
indent = None
st = time.process_time()
js = json.dumps(data,
sort_keys=sort_keys,
indent=indent,
ensure_ascii=ensure_ascii)
content = js.encode("utf-8")
if is_json:
textfile.writebytes(content, abspath)
else:
compress.write_gzip(content, abspath)
def test_gzip():
compress.write_gzip(b, path)
b1 = compress.read_gzip(path)
assert b == b1
os.remove(path)
