upstream/mercurial-mirror Files · mercurial/pure/base85.py

copy: add flag for disabling copy tracing...

copy: add flag for disabling copy tracing Copy tracing can be up to 80% of rebase time when rebasing stacks of commits in large repos (hundreds of thousands of files). This provides the option of turning off the majority of copy tracing. It does not turn off _forwardcopies() since that is used to carry copy information inside a commit across a rebase. This will affect the situation where a user edits a file, then rebases on top of commits that have moved that file. The move will not be detected and the user will have to manually resolve the issue (possibly by redoing the rebase with this flag off). The reason to have a flag instead of trying to fix the actual copy tracing performance is that copy tracing is fundamentally an O(number of files in the repo) operation. In order to know if file X in the rebase source was copied anywhere, we have to walk the filelog for every new file that exists in the rebase destination (i.e. a file in the destination that is not in the common ancestor). Without an index that lets us trace forward (i.e. from file Y in the common ancestor forward to the rebase destination), it will never be an O(number of changes in my branch) operation. In mozilla-central, rebasing a 3 commit stack across 20,000 revs goes from 39s to 11s.

Patrick Mezard - - Load All Authors

File last commit:

r16598:20a9d823 stable


                r26013:38f92d12

default

Download file

             base85.py
        
                    75 lines
            
             | 1.9 KiB
            
                | text/x-python
            
             |
                PythonLexer
            
             / mercurial / pure / base85.py
          
                    History
                
                 |
                  Annotation
                 | Raw
                 |Copy content
                 |Copy permalink

      # base85.py: pure python base85 codec

      #

      # Copyright (C) 2009 Brendan Cully <brendan@kublai.com>

      #

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

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

      import struct

      _b85chars = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ" \

                  "abcdefghijklmnopqrstuvwxyz!#$%&()*+-;<=>?@^_`{|}~"

      _b85chars2 = [(a + b) for a in _b85chars for b in _b85chars]

      _b85dec = {}

      def _mkb85dec():

          for i, c in enumerate(_b85chars):

              _b85dec[c] = i

      def b85encode(text, pad=False):

          """encode text in base85 format"""

          l = len(text)

          r = l % 4

          if r:

              text += '\0' * (4 - r)

          longs = len(text) >> 2

          words = struct.unpack('>%dL' % (longs), text)

          out = ''.join(_b85chars[(word // 52200625) % 85] +

                        _b85chars2[(word // 7225) % 7225] +

                        _b85chars2[word % 7225]

                        for word in words)

          if pad:

              return out

          # Trim padding

          olen = l % 4

          if olen:

              olen += 1

          olen += l // 4 * 5

          return out[:olen]

      def b85decode(text):

          """decode base85-encoded text"""

          if not _b85dec:

              _mkb85dec()

          l = len(text)

          out = []

          for i in range(0, len(text), 5):

              chunk = text[i:i + 5]

              acc = 0

              for j, c in enumerate(chunk):

                  try:

                      acc = acc * 85 + _b85dec[c]

                  except KeyError:

                      raise ValueError('bad base85 character at position %d'

                                       % (i + j))

              if acc > 4294967295:

                  raise ValueError('Base85 overflow in hunk starting at byte %d' % i)

              out.append(acc)

          # Pad final chunk if necessary

          cl = l % 5

          if cl:

              acc *= 85 ** (5 - cl)

              if cl > 1:

                  acc += 0xffffff >> (cl - 2) * 8

              out[-1] = acc

          out = struct.pack('>%dL' % (len(out)), *out)

          if cl:

              out = out[:-(5 - cl)]

          return out

	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

				# base85.py: pure python base85 codec
				#
				# Copyright (C) 2009 Brendan Cully <brendan@kublai.com>
				#
				# This software may be used and distributed according to the terms of the
				# GNU General Public License version 2 or any later version.

				import struct

				_b85chars = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ" \
				"abcdefghijklmnopqrstuvwxyz!#$%&()*+-;<=>?@^_`{\|}~"
				_b85chars2 = [(a + b) for a in _b85chars for b in _b85chars]
				_b85dec = {}

				def _mkb85dec():
				for i, c in enumerate(_b85chars):
				_b85dec[c] = i

				def b85encode(text, pad=False):
				"""encode text in base85 format"""
				l = len(text)
				r = l % 4
				if r:
				text += '\0' * (4 - r)
				longs = len(text) >> 2
				words = struct.unpack('>%dL' % (longs), text)

				out = ''.join(_b85chars[(word // 52200625) % 85] +
				_b85chars2[(word // 7225) % 7225] +
				_b85chars2[word % 7225]
				for word in words)

				if pad:
				return out

				# Trim padding
				olen = l % 4
				if olen:
				olen += 1
				olen += l // 4 * 5
				return out[:olen]

				def b85decode(text):
				"""decode base85-encoded text"""
				if not _b85dec:
				_mkb85dec()

				l = len(text)
				out = []
				for i in range(0, len(text), 5):
				chunk = text[i:i + 5]
				acc = 0
				for j, c in enumerate(chunk):
				try:
				acc = acc * 85 + _b85dec[c]
				except KeyError:
				raise ValueError('bad base85 character at position %d'
				% (i + j))
				if acc > 4294967295:
				raise ValueError('Base85 overflow in hunk starting at byte %d' % i)
				out.append(acc)

				# Pad final chunk if necessary
				cl = l % 5
				if cl:
				acc = 85 * (5 - cl)
				if cl > 1:
				acc += 0xffffff >> (cl - 2) * 8
				out[-1] = acc

				out = struct.pack('>%dL' % (len(out)), *out)
				if cl:
				out = out[:-(5 - cl)]

				return out