File size: 4,089 Bytes
9c6594c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
from __future__ import annotations

import re

from collections.abc import Mapping
from datetime import date
from datetime import datetime
from datetime import time
from datetime import timedelta
from datetime import timezone
from typing import Collection

from tomlkit._compat import decode


RFC_3339_LOOSE = re.compile(
    "^"
    r"(([0-9]+)-(\d{2})-(\d{2}))?"  # Date
    "("
    "([Tt ])?"  # Separator
    r"(\d{2}):(\d{2}):(\d{2})(\.([0-9]+))?"  # Time
    r"(([Zz])|([\+|\-]([01][0-9]|2[0-3]):([0-5][0-9])))?"  # Timezone
    ")?"
    "$"
)

RFC_3339_DATETIME = re.compile(
    "^"
    "([0-9]+)-(0[1-9]|1[012])-(0[1-9]|[12][0-9]|3[01])"  # Date
    "[Tt ]"  # Separator
    r"([01][0-9]|2[0-3]):([0-5][0-9]):([0-5][0-9]|60)(\.([0-9]+))?"  # Time
    r"(([Zz])|([\+|\-]([01][0-9]|2[0-3]):([0-5][0-9])))?"  # Timezone
    "$"
)

RFC_3339_DATE = re.compile("^([0-9]+)-(0[1-9]|1[012])-(0[1-9]|[12][0-9]|3[01])$")

RFC_3339_TIME = re.compile(
    r"^([01][0-9]|2[0-3]):([0-5][0-9]):([0-5][0-9]|60)(\.([0-9]+))?$"
)

_utc = timezone(timedelta(), "UTC")


def parse_rfc3339(string: str) -> datetime | date | time:
    m = RFC_3339_DATETIME.match(string)
    if m:
        year = int(m.group(1))
        month = int(m.group(2))
        day = int(m.group(3))
        hour = int(m.group(4))
        minute = int(m.group(5))
        second = int(m.group(6))
        microsecond = 0

        if m.group(7):
            microsecond = int((f"{m.group(8):<06s}")[:6])

        if m.group(9):
            # Timezone
            tz = m.group(9)
            if tz.upper() == "Z":
                tzinfo = _utc
            else:
                sign = m.group(11)[0]
                hour_offset, minute_offset = int(m.group(12)), int(m.group(13))
                offset = timedelta(seconds=hour_offset * 3600 + minute_offset * 60)
                if sign == "-":
                    offset = -offset

                tzinfo = timezone(offset, f"{sign}{m.group(12)}:{m.group(13)}")

            return datetime(
                year, month, day, hour, minute, second, microsecond, tzinfo=tzinfo
            )
        else:
            return datetime(year, month, day, hour, minute, second, microsecond)

    m = RFC_3339_DATE.match(string)
    if m:
        year = int(m.group(1))
        month = int(m.group(2))
        day = int(m.group(3))

        return date(year, month, day)

    m = RFC_3339_TIME.match(string)
    if m:
        hour = int(m.group(1))
        minute = int(m.group(2))
        second = int(m.group(3))
        microsecond = 0

        if m.group(4):
            microsecond = int((f"{m.group(5):<06s}")[:6])

        return time(hour, minute, second, microsecond)

    raise ValueError("Invalid RFC 339 string")


# https://toml.io/en/v1.0.0#string
CONTROL_CHARS = frozenset(chr(c) for c in range(0x20)) | {chr(0x7F)}
_escaped = {
    "b": "\b",
    "t": "\t",
    "n": "\n",
    "f": "\f",
    "r": "\r",
    '"': '"',
    "\\": "\\",
}
_compact_escapes = {
    **{v: f"\\{k}" for k, v in _escaped.items()},
    '"""': '""\\"',
}
_basic_escapes = CONTROL_CHARS | {'"', "\\"}


def _unicode_escape(seq: str) -> str:
    return "".join(f"\\u{ord(c):04x}" for c in seq)


def escape_string(s: str, escape_sequences: Collection[str] = _basic_escapes) -> str:
    s = decode(s)

    res = []
    start = 0

    def flush(inc=1):
        if start != i:
            res.append(s[start:i])

        return i + inc

    found_sequences = {seq for seq in escape_sequences if seq in s}

    i = 0
    while i < len(s):
        for seq in found_sequences:
            seq_len = len(seq)
            if s[i:].startswith(seq):
                start = flush(seq_len)
                res.append(_compact_escapes.get(seq) or _unicode_escape(seq))
                i += seq_len - 1  # fast-forward escape sequence
        i += 1

    flush()

    return "".join(res)


def merge_dicts(d1: dict, d2: dict) -> dict:
    for k, v in d2.items():
        if k in d1 and isinstance(d1[k], dict) and isinstance(v, Mapping):
            merge_dicts(d1[k], v)
        else:
            d1[k] = d2[k]