将二维列表写入 JSON 文件

Question

我有一个二维列表，如：

data = [[1,2,3], [2,3,4], [4,5,6]]

我想像这样将它写入 JSON 文件：

{
    'data':[
        [1,2,3],
        [2,3,4],
        [4,5,6]
    ]
}

我得到这个json.dumps(data, indent=4, sort_keys=True)：

{
    'data':[
        [
         1,
         2,
         3
        ],
        [
         2,
         3,
         4
        ],
        [
         4,
         5,
         6]
    ]
}

这是另一个问题如何在使用 JSON 模块进行漂亮打印时实现自定义缩进？，但那是字典。

Answer 1

我以为您可以使用我对另一个类似问题的回答来做您想做的事。虽然它适用于json.dumps()，但您指出由于某种原因它不适用于json.dump()。

在调查此事后，我发现链接答案中被覆盖encode()的派生方法json.JSONEncoder仅在调用时dumps()调用，而在dump()调用时不调用。

幸运的是，我能够确定的iterencode()方法确实在这两种情况下被调用-所以是能够通过更多或更少的只是移动的代码来解决这个问题encode()到iterencode()。

下面的代码是修订版，其中包含以下更改：

我对其他问题的回答中代码的修改版本：

from _ctypes import PyObj_FromPtr  # see /sf/answers/1050897011/
import json
import re


class NoIndent(object):
    """ Value wrapper. """
    def __init__(self, value):
        if not isinstance(value, (list, tuple)):
            raise TypeError('Only lists and tuples can be wrapped')
        self.value = value


class MyEncoder(json.JSONEncoder):
    FORMAT_SPEC = '@@{}@@'  # Unique string pattern of NoIndent object ids.
    regex = re.compile(FORMAT_SPEC.format(r'(\d+)'))  # compile(r'@@(\d+)@@')

    def __init__(self, **kwargs):
        # Keyword arguments to ignore when encoding NoIndent wrapped values.
        ignore = {'cls', 'indent'}

        # Save copy of any keyword argument values needed for use here.
        self._kwargs = {k: v for k, v in kwargs.items() if k not in ignore}
        super(MyEncoder, self).__init__(**kwargs)

    def default(self, obj):
        return (self.FORMAT_SPEC.format(id(obj)) if isinstance(obj, NoIndent)
                    else super(MyEncoder, self).default(obj))

    def iterencode(self, obj, **kwargs):
        format_spec = self.FORMAT_SPEC  # Local var to expedite access.

        # Replace any marked-up NoIndent wrapped values in the JSON repr
        # with the json.dumps() of the corresponding wrapped Python object.
        for encoded in super(MyEncoder, self).iterencode(obj, **kwargs):
            match = self.regex.search(encoded)
            if match:
                id = int(match.group(1))
                no_indent = PyObj_FromPtr(id)
                json_repr = json.dumps(no_indent.value, **self._kwargs)
                # Replace the matched id string with json formatted representation
                # of the corresponding Python object.
                encoded = encoded.replace(
                            '"{}"'.format(format_spec.format(id)), json_repr)

            yield encoded

将其应用于您的问题：

# Example of using it to do get the results you want.

alfa = [('a','b','c'), ('d','e','f'), ('g','h','i')]
data = [(1,2,3), (2,3,4), (4,5,6)]

data_struct = {
    'data': [NoIndent(elem) for elem in data],
    'alfa': [NoIndent(elem) for elem in alfa],
}

print(json.dumps(data_struct, cls=MyEncoder, sort_keys=True, indent=4))

# Test custom JSONEncoder with json.dump()
with open('data_struct.json', 'w') as fp:
    json.dump(data_struct, fp, cls=MyEncoder, sort_keys=True, indent=4)
    fp.write('\n')  # Add a newline to very end (optional).

结果输出：

from _ctypes import PyObj_FromPtr  # see https://stackoverflow.com/a/15012814/355230
import json
import re


class NoIndent(object):
    """ Value wrapper. """
    def __init__(self, value):
        if not isinstance(value, (list, tuple)):
            raise TypeError('Only lists and tuples can be wrapped')
        self.value = value


class MyEncoder(json.JSONEncoder):
    FORMAT_SPEC = '@@{}@@'  # Unique string pattern of NoIndent object ids.
    regex = re.compile(FORMAT_SPEC.format(r'(\d+)'))  # compile(r'@@(\d+)@@')

    def __init__(self, **kwargs):
        # Keyword arguments to ignore when encoding NoIndent wrapped values.
        ignore = {'cls', 'indent'}

        # Save copy of any keyword argument values needed for use here.
        self._kwargs = {k: v for k, v in kwargs.items() if k not in ignore}
        super(MyEncoder, self).__init__(**kwargs)

    def default(self, obj):
        return (self.FORMAT_SPEC.format(id(obj)) if isinstance(obj, NoIndent)
                    else super(MyEncoder, self).default(obj))

    def iterencode(self, obj, **kwargs):
        format_spec = self.FORMAT_SPEC  # Local var to expedite access.

        # Replace any marked-up NoIndent wrapped values in the JSON repr
        # with the json.dumps() of the corresponding wrapped Python object.
        for encoded in super(MyEncoder, self).iterencode(obj, **kwargs):
            match = self.regex.search(encoded)
            if match:
                id = int(match.group(1))
                no_indent = PyObj_FromPtr(id)
                json_repr = json.dumps(no_indent.value, **self._kwargs)
                # Replace the matched id string with json formatted representation
                # of the corresponding Python object.
                encoded = encoded.replace(
                            '"{}"'.format(format_spec.format(id)), json_repr)

            yield encoded