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
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
|
"""Convert straight quotation marks to typographic ones
"""
from __future__ import annotations
import re
from typing import Any
from ..common.utils import charCodeAt, isMdAsciiPunct, isPunctChar, isWhiteSpace
from ..token import Token
from .state_core import StateCore
QUOTE_TEST_RE = re.compile(r"['\"]")
QUOTE_RE = re.compile(r"['\"]")
APOSTROPHE = "\u2019" # ’
def replaceAt(string: str, index: int, ch: str) -> str:
# When the index is negative, the behavior is different from the js version.
# But basically, the index will not be negative.
assert index >= 0
return string[:index] + ch + string[index + 1 :]
def process_inlines(tokens: list[Token], state: StateCore) -> None:
stack: list[dict[str, Any]] = []
for i in range(len(tokens)):
token = tokens[i]
thisLevel = token.level
j = 0
for j in range(len(stack))[::-1]:
if stack[j]["level"] <= thisLevel:
break
else:
# When the loop is terminated without a "break".
# Subtract 1 to get the same index as the js version.
j -= 1
stack = stack[: j + 1]
if token.type != "text":
continue
text = token.content
pos = 0
maximum = len(text)
while pos < maximum:
goto_outer = False
lastIndex = pos
t = QUOTE_RE.search(text[lastIndex:])
if not t:
break
canOpen = canClose = True
pos = t.start(0) + lastIndex + 1
isSingle = t.group(0) == "'"
# Find previous character,
# default to space if it's the beginning of the line
lastChar = 0x20
if t.start(0) + lastIndex - 1 >= 0:
lastChar = charCodeAt(text, t.start(0) + lastIndex - 1)
else:
for j in range(i)[::-1]:
# lastChar defaults to 0x20
if tokens[j].type == "softbreak" or tokens[j].type == "hardbreak":
break
# should skip all tokens except 'text', 'html_inline' or 'code_inline'
if not tokens[j].content:
continue
lastChar = charCodeAt(tokens[j].content, len(tokens[j].content) - 1)
break
# Find next character,
# default to space if it's the end of the line
nextChar = 0x20
if pos < maximum:
nextChar = charCodeAt(text, pos)
else:
for j in range(i + 1, len(tokens)):
# nextChar defaults to 0x20
if tokens[j].type == "softbreak" or tokens[j].type == "hardbreak":
break
# should skip all tokens except 'text', 'html_inline' or 'code_inline'
if not tokens[j].content:
continue
nextChar = charCodeAt(tokens[j].content, 0)
break
isLastPunctChar = isMdAsciiPunct(lastChar) or isPunctChar(chr(lastChar))
isNextPunctChar = isMdAsciiPunct(nextChar) or isPunctChar(chr(nextChar))
isLastWhiteSpace = isWhiteSpace(lastChar)
isNextWhiteSpace = isWhiteSpace(nextChar)
if isNextWhiteSpace:
canOpen = False
elif isNextPunctChar:
if not (isLastWhiteSpace or isLastPunctChar):
canOpen = False
if isLastWhiteSpace:
canClose = False
elif isLastPunctChar:
if not (isNextWhiteSpace or isNextPunctChar):
canClose = False
if nextChar == 0x22 and t.group(0) == '"': # 0x22: "
if lastChar >= 0x30 and lastChar <= 0x39: # 0x30: 0, 0x39: 9
# special case: 1"" - count first quote as an inch
canClose = canOpen = False
if canOpen and canClose:
# Replace quotes in the middle of punctuation sequence, but not
# in the middle of the words, i.e.:
#
# 1. foo " bar " baz - not replaced
# 2. foo-"-bar-"-baz - replaced
# 3. foo"bar"baz - not replaced
canOpen = isLastPunctChar
canClose = isNextPunctChar
if not canOpen and not canClose:
# middle of word
if isSingle:
token.content = replaceAt(
token.content, t.start(0) + lastIndex, APOSTROPHE
)
continue
if canClose:
# this could be a closing quote, rewind the stack to get a match
for j in range(len(stack))[::-1]:
item = stack[j]
if stack[j]["level"] < thisLevel:
break
if item["single"] == isSingle and stack[j]["level"] == thisLevel:
item = stack[j]
if isSingle:
openQuote = state.md.options.quotes[2]
closeQuote = state.md.options.quotes[3]
else:
openQuote = state.md.options.quotes[0]
closeQuote = state.md.options.quotes[1]
# replace token.content *before* tokens[item.token].content,
# because, if they are pointing at the same token, replaceAt
# could mess up indices when quote length != 1
token.content = replaceAt(
token.content, t.start(0) + lastIndex, closeQuote
)
tokens[item["token"]].content = replaceAt(
tokens[item["token"]].content, item["pos"], openQuote
)
pos += len(closeQuote) - 1
if item["token"] == i:
pos += len(openQuote) - 1
text = token.content
maximum = len(text)
stack = stack[:j]
goto_outer = True
break
if goto_outer:
goto_outer = False
continue
if canOpen:
stack.append(
{
"token": i,
"pos": t.start(0) + lastIndex,
"single": isSingle,
"level": thisLevel,
}
)
elif canClose and isSingle:
token.content = replaceAt(
token.content, t.start(0) + lastIndex, APOSTROPHE
)
def smartquotes(state: StateCore) -> None:
if not state.md.options.typographer:
return
for token in state.tokens:
if token.type != "inline" or not QUOTE_RE.search(token.content):
continue
assert token.children is not None
process_inlines(token.children, state)
|