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

scmutil: explicitly subclass the `Status` protocol...

scmutil: explicitly subclass the `Status` protocol We shouldn't have to explicitly subclass, but PyCharm has a nifty feature that puts a jump point in the gutter to navigate back and forth between the base class and subclasses (and override functions and base class functions) when there's an explicit subclassing. Additionally, PyCharm will immediately flag signature mismatches without a 40m pytype run. It was also hoped that with explicit subclassing, we would get interface checking for free. Unfortunately when I tried adding methods and fields to the Protocol class to test this theory, pytype happily accepted an assignment of the concrete class without the new field and methods, to a variable annotated with the Protocol class with them. It appears that this is what happens when explicit subclassing is used, since dropping that caused pytype to complain. By making the methods abstract here like the `mercurial.wireprototypes` classes in fd200f5bcaea, pytype will complain in that case outlined that a subclass with abstract methods (not replaced by the subclass itself) cannot be instantiated. That doesn't help with the fields. Making an `abstractproperty` likely isn't appropriate in general, because that effectively becomes a read-only property. This seems like a pretty gaping hole, but I think the benefits of explicit subclassing are worth the risk. (Though I guess it shouldn't be surprising, because a class can be both a Protocol and an implementation, so subclassing something with an empty body method doesn't really signal that it is a requirement for the subclass to implement.)

Matt Harbison - - Load All Authors

File last commit:

r52755:607e94e0 default


                r53348:f5d134e5

default

Download file

             charencode.py
        
                    87 lines
            
             | 2.4 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.

      from __future__ import annotations

      import array

      from .. import pycompat

      def isasciistr(s: bytes) -> bool:

          try:

              s.decode('ascii')

              return True

          except UnicodeDecodeError:

              return False

      def asciilower(s: bytes) -> bytes:

          """convert a string to lowercase if ASCII

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

          s.decode('ascii')

          return s.lower()

      def asciiupper(s: bytes) -> bytes:

          """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: bytes, paranoid: bool) -> bytes:

          """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: bytes, paranoid: bool) -> bytes:

          """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.

				from __future__ import annotations

				import array

				from .. import pycompat


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


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

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


				def asciiupper(s: bytes) -> bytes:
				"""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: bytes, paranoid: bool) -> bytes:
				"""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: bytes, paranoid: bool) -> bytes:
				"""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)