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

revlog: improve the robustness of the splitting process...

revlog: improve the robustness of the splitting process The previous "in-place" splitting, preserving the splitting on transaction failure had a couple of issue in case of transaction rollback: - a race windows that could still lead to a crash and data loss - it corrupted the `fncache`. So instead, we use a new approach that we summarized as "we do a backup of the inline revlog pre-split, and we restore this in case of failure". To make readers live easier, we don't overwrite the inline index file until transaction finalization. (once the transaction get into its finalization phase, it is not expected to rollback, unless some crash happens). To do so, we write the index of the split index in a temporary file that we use until transaction finalization. We also keep a backup of the initial inline file to be able to rollback the split if needed. As a result, transaction rollback cancel the split and no longer corrupt fncache. We also no longer have a small inconsistency windows where the transaction could be unrecoverable.

Gregory Szorc - - Load All Authors

File last commit:

r49762:b677bccf default


                r51242:87f0155d

stable

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)