File: fix_unicode.py

package info (click to toggle)
pypy3 7.3.11%2Bdfsg-2%2Bdeb12u3
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 201,024 kB
  • sloc: python: 1,950,308; ansic: 517,580; sh: 21,417; asm: 14,419; cpp: 4,263; makefile: 4,228; objc: 761; xml: 530; exp: 499; javascript: 314; pascal: 244; lisp: 45; csh: 11; awk: 4
file content (42 lines) | stat: -rw-r--r-- 1,256 bytes parent folder | download | duplicates (30)
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
r"""Fixer for unicode.

* Changes unicode to str and unichr to chr.

* If "...\u..." is not unicode literal change it into "...\\u...".

* Change u"..." into "...".

"""

from ..pgen2 import token
from .. import fixer_base

_mapping = {"unichr" : "chr", "unicode" : "str"}

class FixUnicode(fixer_base.BaseFix):
    BM_compatible = True
    PATTERN = "STRING | 'unicode' | 'unichr'"

    def start_tree(self, tree, filename):
        super(FixUnicode, self).start_tree(tree, filename)
        self.unicode_literals = 'unicode_literals' in tree.future_features

    def transform(self, node, results):
        if node.type == token.NAME:
            new = node.clone()
            new.value = _mapping[node.value]
            return new
        elif node.type == token.STRING:
            val = node.value
            if not self.unicode_literals and val[0] in '\'"' and '\\' in val:
                val = r'\\'.join([
                    v.replace('\\u', r'\\u').replace('\\U', r'\\U')
                    for v in val.split(r'\\')
                ])
            if val[0] in 'uU':
                val = val[1:]
            if val == node.value:
                return node
            new = node.clone()
            new.value = val
            return new