Python之json模块源码剖析
了解一下json序列化解析过程，直接上源码，以下代码是从框架中剥离出来的，可直接跑案例：
"""
json源码剖析
"""
import re
INFINITY = float('inf')
ESCAPE = re.compile(r'[\x00-\x1f\\"\b\f\n\r\t]')
ESCAPE_ASCII = re.compile(r'([\\"]|[^\ -~])')
HAS_UTF8 = re.compile(b'[\x80-\xff]')
ESCAPE_DCT = {
'\\': '\\\\',
'"': '\\"',
'\b': '\\b',
'\f': '\\f',
'\n': '\\n',
'\r': '\\r',
'\t': '\\t',
}
for i in range(0x20):
ESCAPE_DCT.setdefault(chr(i), '\\u{0:04x}'.format(i))
def py_encode_basestring_ascii(s):
"""Return an ASCII-only JSON representation of a Python string
"""
def replace(match):
s = match.group(0)
try:
return ESCAPE_DCT[s]
except KeyError:
n = ord(s)
if n < 0x10000:
return '\\u{0:04x}'.format(n)
else:
# surrogate pair
n -= 0x10000
s1 = 0xd800 | ((n >> 10) & 0x3ff)
s2 = 0xdc00 | (n & 0x3ff)
return '\\u{0:04x}\\u{1:04x}'.format(s1, s2)
return "'" + ESCAPE_ASCII.sub(replace, s) + "'"
def _make_iterencode(markers, _default, _encoder, _indent, _floatstr,
_key_separator, _item_separator, _sort_keys, _skipkeys, _one_shot,
## HACK: hand-optimized bytecode; turn globals into locals
ValueError=ValueError,
dict=dict,
float=float,
id=id,
int=int,
isinstance=isinstance,
list=list,
str=str,
tuple=tuple,
_intstr=int.__str__,
):
if _indent is not None and not isinstance(_indent, str):
_indent = ' ' * _indent
def _iterencode_list(lst, _current_indent_level): # list结构的迭代
if not lst:
yield '[]'
return
if markers is not None:
markerid = id(lst)
if markerid in markers:
raise ValueError("Circular reference detected")
markers[markerid] = lst
buf = '['
if _indent is not None:
_current_indent_level += 1
newline_indent = '\n' + _indent * _current_indent_level
separator = _item_separator + newline_indent
buf += newline_indent
else:
newline_indent = None
separator = _item_separator
first = True
for value in lst:
if first:
first = False
else:
buf = separator
if isinstance(value, str):
yield buf + _encoder(value)
elif value is None:
yield buf + 'null'
elif value is True:
yield buf + 'true'
elif value is False:
yield buf + 'false'
elif isinstance(value, int):
# Subclasses of int/float may override __str__, but we still
# want to encode them as integers/floats in JSON. One example
# within the standard library is IntEnum.
yield buf + _intstr(value)
elif isinstance(value, float):
# see comment above for int
yield buf + _floatstr(value)
else:
yield buf
if isinstance(value, (list, tuple)):
chunks = _iterencode_list(value, _current_indent_level)
elif isinstance(value, dict):
chunks = _iterencode_dict(value, _current_indent_level)
else:
chunks = _iterencode(value, _current_indent_level)
yield from chunks
if newline_indent is not None:
_current_indent_level -= 1
yield '\n' + _indent * _current_indent_level
yield ']'
if markers is not None:
del markers[markerid]
def _iterencode_dict(dct, _current_indent_level): # dict结构的迭代
if not dct:
yield '{}'
return
if markers is not None:
markerid = id(dct)
if markerid in markers:
raise ValueError("Circular reference detected")
markers[markerid] = dct
yield '{'
if _indent is not None:
_current_indent_level += 1
newline_indent = '\n' + _indent * _current_indent_level
item_separator = _item_separator + newline_indent
yield newline_indent
else:
newline_indent = None
item_separator = _item_separator
first = True
if _sort_keys:
items = sorted(dct.items(), key=lambda kv: kv[0])
else:
items = dct.items()
for key, value in items:
if isinstance(key, str):
pass
# JavaScript is weakly typed for these, so it makes sense to
# also allow them. Many encoders seem to do something like this.
elif isinstance(key, float):
# see comment for int/float in _make_iterencode
key = _floatstr(key)
elif key is True:
key = 'true'
elif key is False:
key = 'false'
elif key is None:
key = 'null'
elif isinstance(key, int):
# see comment for int/float in _make_iterencode
key = _intstr(key)
elif _skipkeys:
continue
else:
raise TypeError("key " + repr(key) + " is not a string")
if first:
first = False
else:
yield item_separator
yield _encoder(key)
yield _key_separator
if isinstance(value, str):
yield _encoder(value)
elif value is None:
yield 'null'
elif value is True:
yield 'true'
elif value is False:
yield 'false'
elif isinstance(value, int):
# see comment for int/float in _make_iterencode
yield _intstr(value)
elif isinstance(value, float):
# see comment for int/float in _make_iterencode
yield _floatstr(value)
else:
if isinstance(value, (list, tuple)):
chunks = _iterencode_list(value, _current_indent_level)
elif isinstance(value, dict):
chunks = _iterencode_dict(value, _current_indent_level)
else:
chunks = _iterencode(value, _current_indent_level)
yield from chunks
if newline_indent is not None:
_current_indent_level -= 1
yield '\n' + _indent * _current_indent_level
yield '}'
if markers is not None:
del markers[markerid]
def _iterencode(o, _current_indent_level): # 综合迭达入口（核心）
if isinstance(o, str):
yield _encoder(o)
elif o is None:
yield 'null'
elif o is True:
yield 'true'
elif o is False:
yield 'false'
elif isinstance(o, int):
# see comment for int/float in _make_iterencode
yield _intstr(o)
elif isinstance(o, float):
# see comment for int/float in _make_iterencode
yield _floatstr(o)
elif isinstance(o, (list, tuple)):
yield from _iterencode_list(o, _current_indent_level)
elif isinstance(o, dict):
yield from _iterencode_dict(o, _current_indent_level)
else:
if markers is not None:
markerid = id(o)
if markerid in markers:
raise ValueError("Circular reference detected")
markers[markerid] = o
o = _default(o)
yield from _iterencode(o, _current_indent_level)
if markers is not None:
del markers[markerid]
return _iterencode
class JSONEncoder(object):
"""Extensible JSON encoder for Python data structures.
"""
item_separator = ', '
key_separator = ': '
def __init__(self, *, skipkeys=False, ensure_ascii=True,
check_circular=True, allow_nan=True, sort_keys=False,
indent=None, separators=None, default=None):
"""Constructor for JSONEncoder, with sensible defaults.
"""
self.skipkeys = skipkeys # 非法的key值是否跳过
self.ensure_ascii = ensure_ascii # 序列化时对中文默认使用的ascii编码.想输出真正的中文需要指定ensure_ascii=False
self.check_circular = check_circular # 检查循环引用，防止内存溢出
self.allow_nan = allow_nan # 跳过对nan，Infinity，and-Infinity的编码（不符json规范但是符合JS解释器规范）
self.sort_keys = sort_keys # 输出对key进行排序
self.indent = indent # 格式化输出缩进空格数
if separators is not None: # 指定分隔符
self.item_separator, self.key_separator = separators
elif indent is not None:
self.item_separator = ','
if default is not None:
self.default = default
def default(self, o):
"""
"""
raise TypeError("Object of type '%s' is not JSON serializable" %
o.__class__.__name__)
def encode(self, o):
"""Return a JSON string representation of a Python data structure.
>>> from json.encoder import JSONEncoder
>>> JSONEncoder().encode({"foo": ["bar", "baz"]})
'{"foo": ["bar", "baz"]}'
"""
# This is for extremely simple cases and benchmarks.
# This doesn't pass the iterator directly to ''.join() because the
# exceptions aren't as detailed. The list call should be roughly
# equivalent to the PySequence_Fast that ''.join() would do.
chunks = self.iterencode(o, _one_shot=True) # return ["[{'foo' : ['bar', 'baz'], 'null':'sdfd'}]"]
return ''.join(chunks)
def iterencode(self, o, _one_shot=False):
"""Encode the given object and yield each string
representation as available.
For example::
for chunk in JSONEncoder().iterencode(bigobject):
mysocket.write(chunk)
"""
if self.check_circular:
markers = {}
else:
markers = None
def floatstr(o, allow_nan=self.allow_nan,
_repr=float.__repr__, _inf=INFINITY, _neginf=-INFINITY):
# Check for specials. Note that this type of test is processor
# and/or platform-specific, so do tests which don't depend on the
# internals.
if o != o:
text = 'NaN'
elif o == _inf:
text = 'Infinity'
elif o == _neginf:
text = '-Infinity'
else:
return _repr(o)
if not allow_nan:
raise ValueError(
"Out of range float values are not JSON compliant: " +
repr(o))
return text
# 这里直接使用了py功能实现，另外一个是c实现的具体功能
_encoder = (py_encode_basestring_ascii) # encode_basestring_ascii or
_iterencode = _make_iterencode(
markers, self.default, _encoder, self.indent, floatstr,
self.key_separator, self.item_separator, self.sort_keys,
self.skipkeys, _one_shot)
return _iterencode(o, 0)
if __name__ == '__main__':
# from json.encoder import JSONEncoder # 原始
res = JSONEncoder().encode([{'foo': ["bar", "baz"], None:"sdfd"}])
print("res >>", res)