python - 在一行中格式化某些 JSON 对象

Question

考虑以下代码:

>>> import json
>>> data = {
...     'x': [1, {'$special': 'a'}, 2],
...     'y': {'$special': 'b'},
...     'z': {'p': True, 'q': False}
... }
>>> print(json.dumps(data, indent=2))
{
  "y": {
    "$special": "b"
  },
  "z": {
    "q": false,
    "p": true
  },
  "x": [
    1,
    {
      "$special": "a"
    },
    2
  ]
}

我想要的是格式化 JSON，以便只有一个属性 '$special' 的 JSON 对象呈现在一行上，如下所示。

{
  "y": {"$special": "b"},
  "z": {
    "q": false,
    "p": true
  },
  "x": [
    1,
    {"$special": "a"},
    2
  ]
}

我尝试过实现自定义 JSONEncoder并将其作为 cls 参数传递给 json.dumps，但是 JSONEncoder 上的两种方法各有一个问题:

• JSONEncoder default为 data 的每个部分调用方法，但返回值不是原始 JSON 字符串，因此似乎没有任何方法可以调整其格式。

• JSONEncoder encode方法确实会返回原始 JSON 字符串，但对于整个 data 只调用一次。

有什么方法可以让 JSONEncoder 做我想做的事吗？

Answer 1

json 模块的设计并不是为了让您对输出有那么多的控制；缩进主要是为了在调试时提高可读性。

不是让 json 产生输出，您可以使用标准库转换输出 tokenize module :

import tokenize
from io import BytesIO


def inline_special(json_data):
    def adjust(t, ld,):
        """Adjust token line number by offset"""
        (sl, sc), (el, ec) = t.start, t.end
        return t._replace(start=(sl + ld, sc), end=(el + ld, ec))

    def transform():
        with BytesIO(json_data.encode('utf8')) as b:
            held = []  # to defer newline tokens
            lastend = None  # to track the end pos of the prev token
            loffset = 0     # line offset to adjust tokens by
            tokens = tokenize.tokenize(b.readline)
            for tok in tokens:
                if tok.type == tokenize.NL:
                    # hold newlines until we know there's no special key coming
                    held.append(adjust(tok, loffset))
                elif (tok.type == tokenize.STRING and
                        tok.string == '"$special"'):
                    # special string, collate tokens until the next rbrace
                    # held newlines are discarded, adjust the line offset
                    loffset -= len(held)
                    held = []
                    text = [tok.string]
                    while tok.exact_type != tokenize.RBRACE:
                        tok = next(tokens)
                        if tok.type != tokenize.NL:
                            text.append(tok.string)
                            if tok.string in ':,':
                                text.append(' ')
                        else:
                            loffset -= 1  # following lines all shift
                    line, col = lastend
                    text = ''.join(text)
                    endcol = col + len(text)
                    yield tokenize.TokenInfo(
                        tokenize.STRING, text, (line, col), (line, endcol),
                        '')
                    # adjust any remaining tokens on this line
                    while tok.type != tokenize.NL:
                        tok = next(tokens)
                        yield tok._replace(
                            start=(line, endcol),
                            end=(line, endcol + len(tok.string)))
                        endcol += len(tok.string)
                else:
                    # uninteresting token, yield any held newlines
                    if held:
                        yield from held
                        held = []
                    # adjust and remember last position
                    tok = adjust(tok, loffset)
                    lastend = tok.end
                    yield tok

    return tokenize.untokenize(transform()).decode('utf8')

这会成功地重新格式化您的样本:

import json

data = {
    'x': [1, {'$special': 'a'}, 2],
    'y': {'$special': 'b'},
    'z': {'p': True, 'q': False}
}

>>> print(inline_special(json.dumps(data, indent=2)))
{
  "x": [
    1,
    {"$special": "a"},
    2
  ],
  "y": {"$special": "b"},
  "z": {
    "p": true,
    "q": false
  }
}