python - 获取 magic line/shebang 中指定的编码(从模块内)

Question

如果我在“魔法线”或 python 模块的 shebang 中指定字符编码(如 PEP 263 所建议的那样)

# -*- coding: utf-8 -*-

我可以从那个模块中检索这个编码吗？

(使用 Python 2.7.9 在 Windows 7 x64 上工作)

---

我尝试(但没有成功)检索默认编码或 shebang

# -*- coding: utf-8 -*-

import sys
from shebang import shebang

print "sys.getdefaultencoding():", sys.getdefaultencoding()
print "shebang:", shebang( __file__.rstrip("oc"))

将产生:

sys.getdefaultencoding(): ascii

shebang: None

(与 iso-8859-1 相同)

Answer 1

我会借用 Python 3 tokenize.detect_encoding() function在 Python 2 中，稍微调整以符合 Python 2 的期望。我已经更改了函数签名以接受文件名并删除了到目前为止读取的行的包含；你不需要那些用于你的用例:

import re
from codecs import lookup, BOM_UTF8

cookie_re = re.compile(r'^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)')
blank_re = re.compile(br'^[ \t\f]*(?:[#\r\n]|$)')

def _get_normal_name(orig_enc):
    """Imitates get_normal_name in tokenizer.c."""
    # Only care about the first 12 characters.
    enc = orig_enc[:12].lower().replace("_", "-")
    if enc == "utf-8" or enc.startswith("utf-8-"):
        return "utf-8"
    if enc in ("latin-1", "iso-8859-1", "iso-latin-1") or \
       enc.startswith(("latin-1-", "iso-8859-1-", "iso-latin-1-")):
        return "iso-8859-1"
    return orig_enc

def detect_encoding(filename):
    bom_found = False
    encoding = None
    default = 'ascii'

    def find_cookie(line):
        match = cookie_re.match(line)
        if not match:
            return None
        encoding = _get_normal_name(match.group(1))
        try:
            codec = lookup(encoding)
        except LookupError:
            # This behaviour mimics the Python interpreter
            raise SyntaxError(
                "unknown encoding for {!r}: {}".format(
                    filename, encoding))

        if bom_found:
            if encoding != 'utf-8':
                # This behaviour mimics the Python interpreter
                raise SyntaxError(
                    'encoding problem for {!r}: utf-8'.format(filename))
            encoding += '-sig'
        return encoding

    with open(filename, 'rb') as fileobj:        
        first = next(fileobj, '')
        if first.startswith(BOM_UTF8):
            bom_found = True
            first = first[3:]
            default = 'utf-8-sig'
        if not first:
            return default

        encoding = find_cookie(first)
        if encoding:
            return encoding
        if not blank_re.match(first):
            return default

        second = next(fileobj, '')

    if not second:
        return default    
    return find_cookie(second) or default

和原来的函数一样，上面的函数从源文件中读取两行max，如果cookie中的编码无效或者是当存在 UTF-8 BOM 时不是 UTF-8。

演示:

>>> import tempfile
>>> def test(contents):
...     with tempfile.NamedTemporaryFile() as f:
...         f.write(contents)
...         f.flush()
...         return detect_encoding(f.name)
...
>>> test('# -*- coding: utf-8 -*-\n')
'utf-8'
>>> test('#!/bin/env python\n# -*- coding: latin-1 -*-\n')
'iso-8859-1'
>>> test('import this\n')
'ascii'
>>> import codecs
>>> test(codecs.BOM_UTF8 + 'import this\n')
'utf-8-sig'
>>> test(codecs.BOM_UTF8 + '# encoding: latin-1\n')
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "<stdin>", line 5, in test
  File "<string>", line 37, in detect_encoding
  File "<string>", line 24, in find_cookie
SyntaxError: encoding problem for '/var/folders/w0/nl1bwj6163j2pvxswf84xcsjh2pc5g/T/tmpxsqH8L': utf-8
>>> test('# encoding: foobarbaz\n')
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "<stdin>", line 5, in test
  File "<string>", line 37, in detect_encoding
  File "<string>", line 18, in find_cookie
SyntaxError: unknown encoding for '/var/folders/w0/nl1bwj6163j2pvxswf84xcsjh2pc5g/T/tmpHiHdG3': foobarbaz