upstream/mercurial-mirror Files · mercurial/ancestor.py

findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes....

findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes. We speed up 'findrenames' for the usecase when a user specifies they want a similarity of 100% by matching files by their exact SHA1 hash value. This reduces the number of comparisons required to find exact matches from O(n^2) to O(n). While it would be nice if we could just use mercurial's pre-calculated SHA1 hash for existing files, this hash includes the file's ancestor information making it unsuitable for our purposes. Instead, we calculate the hash of old content from scratch. The following benchmarks were taken on the current head of crew: addremove 100% similarity: rm -rf *; hg up -C; mv tests tests.new hg --time addremove -s100 --dry-run before: real 176.350 secs (user 128.890+0.000 sys 47.430+0.000) after: real 2.130 secs (user 1.890+0.000 sys 0.240+0.000) addremove 75% similarity: rm -rf *; hg up -C; mv tests tests.new; \ for i in tests.new/*; do echo x >> $i; done hg --time addremove -s75 --dry-run before: real 264.560 secs (user 215.130+0.000 sys 49.410+0.000) after: real 218.710 secs (user 172.790+0.000 sys 45.870+0.000)

Matt Mackall - - Load All Authors

File last commit:

r10264:d6512b3e default


                r11060:e6df0177

default

Download file

             ancestor.py
        
                    86 lines
            
             | 2.4 KiB
            
                | text/x-python
            
             |
                PythonLexer
            
             / mercurial / ancestor.py
          
                    History
                
                 |
                  Annotation
                 | Raw
                 |Copy content
                 |Copy permalink

      # ancestor.py - generic DAG ancestor algorithm for mercurial

      #

      # Copyright 2006 Matt Mackall <mpm@selenic.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 heapq

      def ancestor(a, b, pfunc):

          """

          return a minimal-distance ancestor of nodes a and b, or None if there is no

          such ancestor. Note that there can be several ancestors with the same

          (minimal) distance, and the one returned is arbitrary.

          pfunc must return a list of parent vertices for a given vertex

          """

          if a == b:

              return a

          # find depth from root of all ancestors

          parentcache = {}

          visit = [a, b]

          depth = {}

          while visit:

              vertex = visit[-1]

              pl = pfunc(vertex)

              parentcache[vertex] = pl

              if not pl:

                  depth[vertex] = 0

                  visit.pop()

              else:

                  for p in pl:

                      if p == a or p == b: # did we find a or b as a parent?

                          return p # we're done

                      if p not in depth:

                          visit.append(p)

                  if visit[-1] == vertex:

                      depth[vertex] = min([depth[p] for p in pl]) - 1

                      visit.pop()

          # traverse ancestors in order of decreasing distance from root

          def ancestors(vertex):

              h = [(depth[vertex], vertex)]

              seen = set()

              while h:

                  d, n = heapq.heappop(h)

                  if n not in seen:

                      seen.add(n)

                      yield (d, n)

                      for p in parentcache[n]:

                          heapq.heappush(h, (depth[p], p))

          def generations(vertex):

              sg, s = None, set()

              for g, v in ancestors(vertex):

                  if g != sg:

                      if sg:

                          yield sg, s

                      sg, s = g, set((v,))

                  else:

                      s.add(v)

              yield sg, s

          x = generations(a)

          y = generations(b)

          gx = x.next()

          gy = y.next()

          # increment each ancestor list until it is closer to root than

          # the other, or they match

          try:

              while 1:

                  if gx[0] == gy[0]:

                      for v in gx[1]:

                          if v in gy[1]:

                              return v

                      gy = y.next()

                      gx = x.next()

                  elif gx[0] > gy[0]:

                      gy = y.next()

                  else:

                      gx = x.next()

          except StopIteration:

              return None

	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

				# ancestor.py - generic DAG ancestor algorithm for mercurial
				#
				# Copyright 2006 Matt Mackall <mpm@selenic.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 heapq

				def ancestor(a, b, pfunc):
				"""
				return a minimal-distance ancestor of nodes a and b, or None if there is no
				such ancestor. Note that there can be several ancestors with the same
				(minimal) distance, and the one returned is arbitrary.

				pfunc must return a list of parent vertices for a given vertex
				"""

				if a == b:
				return a

				# find depth from root of all ancestors
				parentcache = {}
				visit = [a, b]
				depth = {}
				while visit:
				vertex = visit[-1]
				pl = pfunc(vertex)
				parentcache[vertex] = pl
				if not pl:
				depth[vertex] = 0
				visit.pop()
				else:
				for p in pl:
				if p == a or p == b: # did we find a or b as a parent?
				return p # we're done
				if p not in depth:
				visit.append(p)
				if visit[-1] == vertex:
				depth[vertex] = min([depth[p] for p in pl]) - 1
				visit.pop()

				# traverse ancestors in order of decreasing distance from root
				def ancestors(vertex):
				h = [(depth[vertex], vertex)]
				seen = set()
				while h:
				d, n = heapq.heappop(h)
				if n not in seen:
				seen.add(n)
				yield (d, n)
				for p in parentcache[n]:
				heapq.heappush(h, (depth[p], p))

				def generations(vertex):
				sg, s = None, set()
				for g, v in ancestors(vertex):
				if g != sg:
				if sg:
				yield sg, s
				sg, s = g, set((v,))
				else:
				s.add(v)
				yield sg, s

				x = generations(a)
				y = generations(b)
				gx = x.next()
				gy = y.next()

				# increment each ancestor list until it is closer to root than
				# the other, or they match
				try:
				while 1:
				if gx[0] == gy[0]:
				for v in gx[1]:
				if v in gy[1]:
				return v
				gy = y.next()
				gx = x.next()
				elif gx[0] > gy[0]:
				gy = y.next()
				else:
				gx = x.next()
				except StopIteration:
				return None