请考虑以下代码:
>>> 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'$special'
的JSON对象在一行上呈现,如下所示。
{
"y": {"$special": "b"},
"z": {
"q": false,
"p": true
},
"x": [
1,
{"$special": "a"},
2
]
}
我已经开始实现自定义JSONEncoder
并将其作为json.dumps
参数传递给cls
,但JSONEncoder
上的两个方法都有问题:
为JSONEncoder
的每个部分调用data
default
方法,但返回值不是原始JSON字符串,因此似乎没有调整格式的方法。
JSONEncoder
encode
方法会返回一个原始JSON字符串,但只对整个data
调用一次。
我有什么方法可以JSONEncoder
做我想做的事吗?
答案 0 :(得分:2)
json
模块的设计并不是为了让您对输出有太多的控制权。缩进主要是为了在调试时提供可读性。
不是让json
产生输出,而是使用标准库tokenize
module 转换输出:
import tokenize
from io import BytesIO
def inline_special(json_data):
def adjust(t, ld,):
"""Adjust token line number by offset"""
(sl, sc), (el, ec) = t.start, t.end
return t._replace(start=(sl + ld, sc), end=(el + ld, ec))
def transform():
with BytesIO(json_data.encode('utf8')) as b:
held = [] # to defer newline tokens
lastend = None # to track the end pos of the prev token
loffset = 0 # line offset to adjust tokens by
tokens = tokenize.tokenize(b.readline)
for tok in tokens:
if tok.type == tokenize.NL:
# hold newlines until we know there's no special key coming
held.append(adjust(tok, loffset))
elif (tok.type == tokenize.STRING and
tok.string == '"$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
}
}
答案 1 :(得分:1)
我发现以下基于正则表达式的解决方案最简单,尽管...... 基于正则表达式。
import json
import re
data = {
'x': [1, {'$special': 'a'}, 2],
'y': {'$special': 'b'},
'z': {'p': True, 'q': False}
}
text = json.dumps(data, indent=2)
pattern = re.compile(r"""
{
\s*
"\$special"
\s*
:
\s*
"
((?:[^"]|\\"))* # Captures zero or more NotQuote or EscapedQuote
"
\s*
}
""", re.VERBOSE)
print(pattern.sub(r'{"$special": "\1"}', text))
输出如下。
{
"x": [
1,
{"$special": "a"},
2
],
"y": {"$special": "b"},
"z": {
"q": false,
"p": true
}
}
答案 2 :(得分:0)
您可以这样做,但您基本上必须从_make_iterencode
复制/修改很多代码,因为编码功能并非真正被设计为部分覆盖。
基本上,从json.encoder
复制整个_make_iterencode
并进行更改,以便在没有换行缩进的情况下打印特殊字典。然后monkeypatch json包使用你的修改版本,运行json转储,然后撤消monkeypatch(如果你想)。
import json
import json.encoder
def _make_iterencode(markers, _default, _encoder, _indent, _floatstr,
...
def _iterencode_dict(dct, _current_indent_level):
...
if _indent is not None:
_current_indent_level += 1
if '$special' in dct:
newline_indent = ''
item_separator = _item_separator
else:
newline_indent = '\n' + (' ' * (_indent * _current_indent_level))
item_separator = _item_separator + newline_indent
yield newline_indent
...
if newline_indent is not None:
_current_indent_level -= 1
if '$special' not in dct:
yield '\n' + (' ' * (_indent * _current_indent_level))
def main():
data = {
'x': [1, {'$special': 'a'}, 2],
'y': {'$special': 'b'},
'z': {'p': True, 'q': False},
}
orig_make_iterencoder = json.encoder._make_iterencode
json.encoder._make_iterencode = _make_iterencode
print(json.dumps(data, indent=2))
json.encoder._make_iterencode = orig_make_iterencoder
功能很长,所以我只发布了需要更改的部分。
{{1}}