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
160
161
162
163
164
165
|
r"""
Parses ascii escape sequences into marked up strings
>>> r = peel_off_esc_code('Amore')
>>> r == ('', {'csi': '\x1b', 'command': 'A', 'seq': '\x1bA'}, 'more')
True
>>> r = peel_off_esc_code('[2Astuff')
>>> r == ('', {'csi': '\x1b[', 'seq': '\x1b[2A', 'intermed': '', 'private': '', 'command': 'A', 'numbers': [2]}, 'stuff')
True
"""
from typing import (
List,
Union,
Tuple,
cast,
Dict,
Any,
Optional,
)
from collections.abc import Mapping
from re import Match
import re
from .termformatconstants import (
FG_NUMBER_TO_COLOR,
BG_NUMBER_TO_COLOR,
NUMBER_TO_STYLE,
RESET_ALL,
RESET_FG,
RESET_BG,
STYLES,
)
Token = dict[str, Union[str, list[int]]]
def remove_ansi(s: str) -> str:
return re.sub(r"(\x9B|\x1B\[)[0-?]*[ -\/]*[@-~]", "", s)
def parse(s: str) -> list[str | dict[str, str | bool | None]]:
r"""
Returns a list of strings or format dictionaries to describe the strings.
May raise a ValueError if it can't be parsed.
>>> parse(">>> []")
['>>> []']
>>> parse("\x1b[33m[\x1b[39m\x1b[33m]\x1b[39m\x1b[33m[\x1b[39m\x1b[33m]\x1b[39m\x1b[33m[\x1b[39m\x1b[33m]\x1b[39m\x1b[33m[\x1b[39m")
[{'fg': 'yellow'}, '[', {'fg': None}, {'fg': 'yellow'}, ']', {'fg': None}, {'fg': 'yellow'}, '[', {'fg': None}, {'fg': 'yellow'}, ']', {'fg': None}, {'fg': 'yellow'}, '[', {'fg': None}, {'fg': 'yellow'}, ']', {'fg': None}, {'fg': 'yellow'}, '[', {'fg': None}]
"""
stuff: list[str | dict[str, str | bool | None]] = []
rest = s
while True:
front, token, rest = peel_off_esc_code(rest)
if front:
stuff.append(front)
if token:
try:
tok = token_type(token)
if tok:
stuff.extend(tok)
except ValueError:
raise ValueError(
"Can't parse escape sequence: %r %r %r %r"
% (s, repr(front), token, repr(rest))
)
if not rest:
break
return stuff
def peel_off_esc_code(s: str) -> tuple[str, Token | None, str]:
r"""Returns processed text, the next token, and unprocessed text
>>> front, d, rest = peel_off_esc_code('some[2Astuff')
>>> front, rest
('some', 'stuff')
>>> d == {'numbers': [2], 'command': 'A', 'intermed': '', 'private': '', 'csi': '\x1b[', 'seq': '\x1b[2A'}
True
"""
# fmt: off
p = r"""(?P<front>.*?)
(?P<seq>
(?P<csi>
(?:[]\[)
|
["""+'\x9b' + r"""])
(?P<private>)
(?P<numbers>
(?:\d+;)*
(?:\d+)?)
(?P<intermed>""" + '[\x20-\x2f]*)' + r"""
(?P<command>""" + '[\x40-\x7e]))' + r"""
(?P<rest>.*)"""
# fmt: on
m1 = re.match(p, s, re.VERBOSE) # multibyte esc seq
m2 = re.match(
"(?P<front>.*?)(?P<seq>(?P<csi>)(?P<command>[\x40-\x5f]))(?P<rest>.*)", s
) # 2 byte escape sequence
m = None # Optional[Match[str]]
if m1 and m2:
m = m1 if len(m1.groupdict()["front"]) <= len(m2.groupdict()["front"]) else m2
# choose the match which has less processed text in order to get the
# first escape sequence
elif m1:
m = m1
elif m2:
m = m2
else:
m = None
if m:
d: dict[str, Any] = m.groupdict()
del d["front"]
del d["rest"]
if "numbers" in d and all(d["numbers"].split(";")):
d["numbers"] = [int(x) for x in d["numbers"].split(";")]
return m.groupdict()["front"], cast(Token, d), m.groupdict()["rest"]
else:
return s, None, ""
def token_type(info: Token) -> list[dict[str, str | bool | None]] | None:
if info["command"] == "m":
# The default action for ESC[m is to act like ESC[0m
# Ref: https://en.wikipedia.org/wiki/ANSI_escape_code#CSI_codes
values = cast(list[int], info["numbers"]) if len(info["numbers"]) else [0]
tokens: list[dict[str, str | bool | None]] = []
for value in values:
if value in FG_NUMBER_TO_COLOR:
tokens.append({"fg": FG_NUMBER_TO_COLOR[value]})
if value in BG_NUMBER_TO_COLOR:
tokens.append({"bg": BG_NUMBER_TO_COLOR[value]})
if value in NUMBER_TO_STYLE:
tokens.append({NUMBER_TO_STYLE[value]: True})
if value == RESET_ALL:
tokens.append(
dict({k: None for k in STYLES}, **{"fg": None, "bg": None})
)
if value == RESET_FG:
tokens.append({"fg": None})
if value == RESET_BG:
tokens.append({"bg": None})
if tokens:
return tokens
else:
raise ValueError("Can't parse escape seq %r" % info)
elif info["command"] == "H": # fix for bpython #76
return [{}]
return None
if __name__ == "__main__":
import doctest
doctest.testmod()
# print(peel_off_esc_code('[2Astuff'))
# print(peel_off_esc_code('Amore'))
print(repr(parse("[31mstuff is the best[32myay")))
|
