upstream/mercurial-mirror Files · mercurial/pure/charencode.py

typing: attempt to remove @overloads in the platform module for stdlib methods...

typing: attempt to remove @overloads in the platform module for stdlib methods This is mostly successful, as examining util.pyi, posix.pyi, and windows.pyi after a pytype run shows that the type overloads for `oslink`, `readlink`, `removedirs`, `rename`, `split`, and `unlink` have been removed. (Some of these still have an @overload, but the differences are the variable names, not the types.) However, @overloads remain for `abspath` and `normpath` for some reason. It's useful to redefine these methods for the type checking phase because in addition to excluding str and PathLike variants, some of these functions have optional args in stdlib that aren't implemented in the custom implementation on Windows, and we want the type checking to flag that instead of assuming it's an allowable overload everywhere. One last quirk I noticed that I can't explain- `pycompat.TYPE_CHECKING` is always False, so the conditionals need to check `typing.TYPE_CHECKING` directly. I tried dropping the custom code for assigning `pycompat.TYPE_CHECKING` and simply did `from typing import TYPE_CHECKING` directly in pycompat.py, and used `pycompat.TYPE_CHECKING` for the conditional here... and pytype complained that `pycompat` doesn't have the `TYPE_CHECKING` variable.

Gregory Szorc - - Load All Authors

File last commit:

r49762:b677bccf default


                r50713:3fd5824f

default

Download file

             charencode.py
        
                    86 lines
            
             | 2.2 KiB
            
                | text/x-python
            
             |
                PythonLexer
            
             / mercurial / pure / charencode.py
          
                    History
                
                 |
                  Annotation
                 | Raw
                 |Copy content
                 |Copy permalink

      # charencode.py - miscellaneous character encoding

      #

      #  Copyright 2005-2009 Olivia Mackall <olivia@selenic.com> and others

      #

      # This software may be used and distributed according to the terms of the

      # GNU General Public License version 2 or any later version.

      import array

      from .. import pycompat

      def isasciistr(s):

          try:

              s.decode('ascii')

              return True

          except UnicodeDecodeError:

              return False

      def asciilower(s):

          """convert a string to lowercase if ASCII

          Raises UnicodeDecodeError if non-ASCII characters are found."""

          s.decode('ascii')

          return s.lower()

      def asciiupper(s):

          """convert a string to uppercase if ASCII

          Raises UnicodeDecodeError if non-ASCII characters are found."""

          s.decode('ascii')

          return s.upper()

      _jsonmap = []

      _jsonmap.extend(b"\\u%04x" % x for x in range(32))

      _jsonmap.extend(pycompat.bytechr(x) for x in range(32, 127))

      _jsonmap.append(b'\\u007f')

      _jsonmap[0x09] = b'\\t'

      _jsonmap[0x0A] = b'\\n'

      _jsonmap[0x22] = b'\\"'

      _jsonmap[0x5C] = b'\\\\'

      _jsonmap[0x08] = b'\\b'

      _jsonmap[0x0C] = b'\\f'

      _jsonmap[0x0D] = b'\\r'

      _paranoidjsonmap = _jsonmap[:]

      _paranoidjsonmap[0x3C] = b'\\u003c'  # '<' (e.g. escape "</script>")

      _paranoidjsonmap[0x3E] = b'\\u003e'  # '>'

      _jsonmap.extend(pycompat.bytechr(x) for x in range(128, 256))

      def jsonescapeu8fast(u8chars, paranoid):

          """Convert a UTF-8 byte string to JSON-escaped form (fast path)

          Raises ValueError if non-ASCII characters have to be escaped.

          """

          if paranoid:

              jm = _paranoidjsonmap

          else:

              jm = _jsonmap

          try:

              return b''.join(jm[x] for x in bytearray(u8chars))

          except IndexError:

              raise ValueError

      _utf8strict = r'surrogatepass'

      def jsonescapeu8fallback(u8chars, paranoid):

          """Convert a UTF-8 byte string to JSON-escaped form (slow path)

          Escapes all non-ASCII characters no matter if paranoid is False.

          """

          if paranoid:

              jm = _paranoidjsonmap

          else:

              jm = _jsonmap

          # non-BMP char is represented as UTF-16 surrogate pair

          u16b = u8chars.decode('utf-8', _utf8strict).encode('utf-16', _utf8strict)

          u16codes = array.array('H', u16b)

          u16codes.pop(0)  # drop BOM

          return b''.join(jm[x] if x < 128 else b'\\u%04x' % x for x in u16codes)

	Site-wide shortcuts
/	Use quick search box
g h	Goto home page
g g	Goto my private gists page
g G	Goto my public gists page
g 0-9	Goto bookmarked items from 0-9
n r	New repository page
n g	New gist page

	Repositories
g s	Goto summary page
g c	Goto changelog page
g f	Goto files page
g F	Goto files page with file search activated
g p	Goto pull requests page
g o	Goto repository settings
g O	Goto repository access permissions settings
t s	Toggle sidebar on some pages

				# charencode.py - miscellaneous character encoding
				#
				# Copyright 2005-2009 Olivia Mackall <olivia@selenic.com> and others
				#
				# This software may be used and distributed according to the terms of the
				# GNU General Public License version 2 or any later version.


				import array

				from .. import pycompat


				def isasciistr(s):
				try:
				s.decode('ascii')
				return True
				except UnicodeDecodeError:
				return False


				def asciilower(s):
				"""convert a string to lowercase if ASCII

				Raises UnicodeDecodeError if non-ASCII characters are found."""
				s.decode('ascii')
				return s.lower()


				def asciiupper(s):
				"""convert a string to uppercase if ASCII

				Raises UnicodeDecodeError if non-ASCII characters are found."""
				s.decode('ascii')
				return s.upper()


				_jsonmap = []
				_jsonmap.extend(b"\\u%04x" % x for x in range(32))
				_jsonmap.extend(pycompat.bytechr(x) for x in range(32, 127))
				_jsonmap.append(b'\\u007f')
				_jsonmap[0x09] = b'\\t'
				_jsonmap[0x0A] = b'\\n'
				_jsonmap[0x22] = b'\\"'
				_jsonmap[0x5C] = b'\\\\'
				_jsonmap[0x08] = b'\\b'
				_jsonmap[0x0C] = b'\\f'
				_jsonmap[0x0D] = b'\\r'
				_paranoidjsonmap = _jsonmap[:]
				_paranoidjsonmap[0x3C] = b'\\u003c' # '<' (e.g. escape "</script>")
				_paranoidjsonmap[0x3E] = b'\\u003e' # '>'
				_jsonmap.extend(pycompat.bytechr(x) for x in range(128, 256))


				def jsonescapeu8fast(u8chars, paranoid):
				"""Convert a UTF-8 byte string to JSON-escaped form (fast path)

				Raises ValueError if non-ASCII characters have to be escaped.
				"""
				if paranoid:
				jm = _paranoidjsonmap
				else:
				jm = _jsonmap
				try:
				return b''.join(jm[x] for x in bytearray(u8chars))
				except IndexError:
				raise ValueError


				_utf8strict = r'surrogatepass'


				def jsonescapeu8fallback(u8chars, paranoid):
				"""Convert a UTF-8 byte string to JSON-escaped form (slow path)

				Escapes all non-ASCII characters no matter if paranoid is False.
				"""
				if paranoid:
				jm = _paranoidjsonmap
				else:
				jm = _jsonmap
				# non-BMP char is represented as UTF-16 surrogate pair
				u16b = u8chars.decode('utf-8', _utf8strict).encode('utf-16', _utf8strict)
				u16codes = array.array('H', u16b)
				u16codes.pop(0) # drop BOM
				return b''.join(jm[x] if x < 128 else b'\\u%04x' % x for x in u16codes)