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