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

typing: add type annotations to the dirstate classes...

typing: add type annotations to the dirstate classes The basic procedure here was to use `merge-pyi` to merge the `git/dirstate.pyi` file in (after renaming the interface class to match), cleaning up the import statement mess, and then repeating the procedure for `mercurial/dirstate.pyi`. Surprisingly, git's dirstate had more hints inferred in its *.pyi file. After that, it was a manual examination of each method in the interface, and how they were implemented in the core and git classes to verify what was inferred by pytype, and fill in the missing gaps. Since this involved jumping around between three different files, I applied the same type info to all three at the same time. Complex types I rolled up into type aliases in the interface module, and used that as needed. That way if it changes, there's one place to edit. There are some hints still missing, and some documentation that doesn't match the signatures. They should all be marked with TODOs. There are also a bunch of methods on the core class that aren't on the Protocol class that seem like maybe they should be (like `set_tracked()`). There are even more methods missing from the git class. But that's a project for another time.

Matt Harbison - - Load All Authors

File last commit:

r52756:f4733654 default


                r52822:93d872a0

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)