Add a new merge strategy by Fredrik Kuivinen.

I really wanted to try this out, instead of asking for an adjustment
to the 'git merge' driver and waiting.  For now the new strategy is
called 'fredrik' and not in the list of default strategies to be tried.

The script wants Python 2.4 so this commit also adjusts Debian and RPM
build procecure files.

Signed-off-by: Junio C Hamano <junkio@cox.net>

9 files changed, 741 insertions, 7 deletions

diff --git a/.gitignore b/.gitignore
index f42b7e8f7..be9ea5fa9 100644
--- a/.gitignore
+++ b/.gitignore
@@ -43,6 +43,7 @@ git-mailinfo
 git-mailsplit
 git-merge
 git-merge-base
+git-merge-fredrik
 git-merge-index
 git-merge-octopus
 git-merge-one-file
diff --git a/Makefile b/Makefile
index 41461fa81..5b028b1d9 100644
--- a/Makefile
+++ b/Makefile
@@ -48,6 +48,7 @@ ALL_CFLAGS = $(CFLAGS) $(PLATFORM_DEFINES) $(DEFINES)
 prefix = $(HOME)
 bindir = $(prefix)/bin
 template_dir = $(prefix)/share/git-core/templates/
+GIT_PYTHON_DIR = $(prefix)/share/git-core/python
 # DESTDIR=
 
 CC = gcc
@@ -81,6 +82,9 @@ SCRIPT_PERL = \
 	git-archimport.perl git-cvsimport.perl git-relink.perl \
 	git-rename.perl git-shortlog.perl
 
+SCRIPT_PYTHON = \
+	git-merge-fredrik.py
+
 # The ones that do not have to link with lcrypto nor lz.
 SIMPLE_PROGRAMS = \
 	git-get-tar-commit-id git-mailinfo git-mailsplit git-stripspace \
@@ -105,6 +109,9 @@ PROGRAMS = \
 	git-upload-pack git-verify-pack git-write-tree \
 	$(SIMPLE_PROGRAMS)
 
+PYMODULES = \
+	gitMergeCommon.py
+
 ifdef WITH_SEND_EMAIL
 	SCRIPT_PERL += git-send-email.perl
 endif
@@ -150,6 +157,9 @@ endif
 ifndef PERL_PATH
 	PERL_PATH = /usr/bin/perl
 endif
+ifndef PYTHON_PATH
+	PYTHON_PATH = /usr/bin/python
+endif
 
 ifndef NO_OPENSSL
 	LIB_OBJS += epoch.o
@@ -189,7 +199,9 @@ endif
 DEFINES += '-DSHA1_HEADER=$(SHA1_HEADER)'
 
 SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) \
-	  $(patsubst %.perl,%,$(SCRIPT_PERL)) gitk
+	  $(patsubst %.perl,%,$(SCRIPT_PERL)) \
+	  $(patsubst %.py,%,$(SCRIPT_PYTHON)) \
+	  gitk
 
 ### Build rules
 
@@ -214,6 +226,13 @@ $(patsubst %.perl,%,$(SCRIPT_PERL)) : % : %.perl
 	sed -e '1s|#!.*perl|#!$(PERL_PATH)|' $@.perl >$@
 	chmod +x $@
 
+$(patsubst %.py,%,$(SCRIPT_PYTHON)) : % : %.py
+	rm -f $@
+	sed -e '1s|#!.*python|#!$(PYTHON_PATH)|' \
+	    -e 's|@@GIT_PYTHON_PATH@@|$(GIT_PYTHON_DIR)|g' \
+		$@.py >$@
+	chmod +x $@
+
 %.o: %.c
 	$(CC) -o $*.o -c $(ALL_CFLAGS) $<
 %.o: %.S
@@ -274,6 +293,8 @@ install: $(PROGRAMS) $(SCRIPTS)
 	$(INSTALL) git-revert $(DESTDIR)$(bindir)/git-cherry-pick
 	sh ./cmd-rename.sh $(DESTDIR)$(bindir)
 	$(MAKE) -C templates install
+	$(INSTALL) -m755 -d $(DESTDIR)$(GIT_PYTHON_DIR)
+	$(INSTALL) $(PYMODULES) $(DESTDIR)$(GIT_PYTHON_DIR)
 
 install-doc:
 	$(MAKE) -C Documentation install
diff --git a/debian/control b/debian/control
index 6735a0da0..33a8f852b 100644
--- a/debian/control
+++ b/debian/control
@@ -8,7 +8,7 @@ Standards-Version: 3.6.1
 Package: git-core
 Architecture: any
 Depends: ${shlibs:Depends}, ${perl:Depends}, ${misc:Depends}, patch, rcs
-Recommends: rsync, curl, ssh, libmail-sendmail-perl, libemail-valid-perl
+Recommends: rsync, curl, ssh, libmail-sendmail-perl, libemail-valid-perl, python (>= 2.4.0)
 Suggests: cogito
 Conflicts: git, cogito (<< 0.13)
 Description: The git content addressable filesystem
diff --git a/debian/rules b/debian/rules
index 86464bf30..1a53ca239 100755
--- a/debian/rules
+++ b/debian/rules
@@ -41,7 +41,7 @@ MAN_DESTDIR := $(DESTDIR)/$(MANDIR)
 build: debian/build-stamp
 debian/build-stamp:
 	dh_testdir
-	$(MAKE) prefix=$(PREFIX) all doc
+	$(MAKE) prefix=$(PREFIX) PYTHON_PATH=/usr/bin/python2.4 all doc
 	touch debian/build-stamp
 
 debian-clean:
diff --git a/git-core.spec.in b/git-core.spec.in
index ef7cd26b9..b78a46802 100644
--- a/git-core.spec.in
+++ b/git-core.spec.in
@@ -10,7 +10,7 @@ URL: 		http://kernel.org/pub/software/scm/git/
 Source: 	http://kernel.org/pub/software/scm/git/%{name}-%{version}.tar.gz
 BuildRequires:	zlib-devel, openssl-devel, curl-devel  %{!?_without_docs:, xmlto, asciidoc > 6.0.3}
 BuildRoot:	%{_tmppath}/%{name}-%{version}-root
-Requires: 	sh-utils, diffutils, rsync, rcs, mktemp >= 1.5
+Requires: 	sh-utils, diffutils, rsync, rcs, python >= 2.4
 
 %description
 This is a stupid (but extremely fast) directory content manager.  It
diff --git a/git-merge-fredrik.py b/git-merge-fredrik.py
new file mode 100755
index 000000000..920e10ffb
--- /dev/null
+++ b/git-merge-fredrik.py
@@ -0,0 +1,426 @@
+#!/usr/bin/python
+
+import sys, math, random, os, re, signal, tempfile, stat, errno
+from heapq import heappush, heappop
+from sets import Set
+
+sys.path.append('@@GIT_PYTHON_PATH@@')
+from gitMergeCommon import *
+
+alwaysWriteTree = False
+
+# The actual merge code
+# ---------------------
+
+def merge(h1, h2, branch1Name, branch2Name, graph, callDepth=0):
+    '''Merge the commits h1 and h2, return the resulting virtual
+    commit object and a flag indicating the cleaness of the merge.'''
+    assert(isinstance(h1, Commit) and isinstance(h2, Commit))
+    assert(isinstance(graph, Graph))
+
+    def infoMsg(*args):
+        sys.stdout.write('  '*callDepth)
+        printList(args)
+    infoMsg('Merging:')
+    infoMsg(h1)
+    infoMsg(h2)
+    sys.stdout.flush()
+
+    ca = getCommonAncestors(graph, h1, h2)
+    infoMsg('found', len(ca), 'common ancestor(s):')
+    for x in ca:
+        infoMsg(x)
+    sys.stdout.flush()
+
+    Ms = ca[0]
+    for h in ca[1:]:
+        [Ms, ignore] = merge(Ms, h,
+                             'Temporary shared merge branch 1',
+                             'Temporary shared merge branch 2',
+                             graph, callDepth+1)
+        assert(isinstance(Ms, Commit))
+
+    if callDepth == 0:
+        if len(ca) > 1:
+            runProgram(['git-read-tree', h1.tree()])
+            runProgram(['git-update-cache', '-q', '--refresh'])
+        # Use the original index if we only have one common ancestor
+        
+        updateWd = True
+        if alwaysWriteTree:
+            cleanCache = True
+        else:
+            cleanCache = False
+    else:
+        runProgram(['git-read-tree', h1.tree()])
+        updateWd = False
+        cleanCache = True
+
+    [shaRes, clean] = mergeTrees(h1.tree(), h2.tree(), Ms.tree(),
+                                 branch1Name, branch2Name,
+                                 cleanCache, updateWd)
+
+    if clean or alwaysWriteTree:
+        res = Commit(None, [h1, h2], tree=shaRes)
+        graph.addNode(res)
+    else:
+        res = None
+
+    return [res, clean]
+
+getFilesRE = re.compile('([0-9]+) ([a-z0-9]+) ([0-9a-f]{40})\t(.*)')
+def getFilesAndDirs(tree):
+    files = Set()
+    dirs = Set()
+    out = runProgram(['git-ls-tree', '-r', '-z', tree])
+    for l in out.split('\0'):
+        m = getFilesRE.match(l)
+        if m:
+            if m.group(2) == 'tree':
+                dirs.add(m.group(4))
+            elif m.group(2) == 'blob':
+                files.add(m.group(4))
+
+    return [files, dirs]
+
+class CacheEntry:
+    def __init__(self, path):
+        class Stage:
+            def __init__(self):
+                self.sha1 = None
+                self.mode = None
+        
+        self.stages = [Stage(), Stage(), Stage()]
+        self.path = path
+
+unmergedRE = re.compile('^([0-9]+) ([0-9a-f]{40}) ([1-3])\t(.*)$')
+def unmergedCacheEntries():
+    '''Create a dictionary mapping file names to CacheEntry
+    objects. The dictionary contains one entry for every path with a
+    non-zero stage entry.'''
+
+    lines = runProgram(['git-ls-files', '-z', '--unmerged']).split('\0')
+    lines.pop()
+
+    res = {}
+    for l in lines:
+        m = unmergedRE.match(l)
+        if m:
+            mode = int(m.group(1), 8)
+            sha1 = m.group(2)
+            stage = int(m.group(3)) - 1
+            path = m.group(4)
+
+            if res.has_key(path):
+                e = res[path]
+            else:
+                e = CacheEntry(path)
+                res[path] = e
+                
+            e.stages[stage].mode = mode
+            e.stages[stage].sha1 = sha1
+        else:
+            print 'Error: Merge program failed: Unexpected output from', \
+                  'git-ls-files:', l
+            sys.exit(2)
+    return res
+
+def mergeTrees(head, merge, common, branch1Name, branch2Name,
+               cleanCache, updateWd):
+    '''Merge the trees 'head' and 'merge' with the common ancestor
+    'common'. The name of the head branch is 'branch1Name' and the name of
+    the merge branch is 'branch2Name'. Return a tuple (tree, cleanMerge)
+    where tree is the resulting tree and cleanMerge is True iff the
+    merge was clean.'''
+    
+    assert(isSha(head) and isSha(merge) and isSha(common))
+
+    if common == merge:
+        print 'Already uptodate!'
+        return [head, True]
+
+    if updateWd:
+        updateArg = '-u'
+    else:
+        updateArg = '-i'
+    runProgram(['git-read-tree', updateArg, '-m', common, head, merge])
+    cleanMerge = True
+
+    [tree, code] = runProgram('git-write-tree', returnCode=True)
+    tree = tree.rstrip()
+    if code != 0:
+        [files, dirs] = getFilesAndDirs(head)
+        [filesM, dirsM] = getFilesAndDirs(merge)
+        files.union_update(filesM)
+        dirs.union_update(dirsM)
+        
+        cleanMerge = True
+        entries = unmergedCacheEntries()
+        for name in entries:
+            if not processEntry(entries[name], branch1Name, branch2Name,
+                                files, dirs, cleanCache, updateWd):
+                cleanMerge = False
+                
+        if cleanMerge or cleanCache:
+            tree = runProgram('git-write-tree').rstrip()
+        else:
+            tree = None
+    else:
+        cleanMerge = True
+
+    return [tree, cleanMerge]
+
+def processEntry(entry, branch1Name, branch2Name, files, dirs,
+                 cleanCache, updateWd):
+    '''Merge one cache entry. 'files' is a Set with the files in both of
+    the heads that we are going to merge. 'dirs' contains the
+    corresponding data for directories. If 'cleanCache' is True no
+    non-zero stages will be left in the cache for the path
+    corresponding to the entry 'entry'.'''
+
+# cleanCache == True  => Don't leave any non-stage 0 entries in the cache.
+#               False => Leave unmerged entries
+
+# updateWd  == True  => Update the working directory to correspond to the cache
+#              False => Leave the working directory unchanged
+
+# clean     == True  => non-conflict case
+#              False => conflict case
+
+# If cleanCache == False then the cache shouldn't be updated if clean == False
+
+    def updateFile(clean, sha, mode, path):
+        if cleanCache or (not cleanCache and clean):
+            runProgram(['git-update-cache', '--add', '--cacheinfo',
+                        '0%o' % mode, sha, path])
+
+        if updateWd:
+            prog = ['git-cat-file', 'blob', sha]
+            if stat.S_ISREG(mode):
+                try:
+                    os.unlink(path)
+                except OSError:
+                    pass
+                if mode & 0100:
+                    mode = 0777
+                else:
+                    mode = 0666
+                fd = os.open(path, os.O_WRONLY | os.O_TRUNC | os.O_CREAT, mode)
+                proc = subprocess.Popen(prog, stdout=fd)
+                proc.wait()
+                os.close(fd)
+            elif stat.S_ISLNK(mode):
+                linkTarget = runProgram(prog)
+                os.symlink(linkTarget, path)
+            else:
+                assert(False)
+            runProgram(['git-update-cache', '--', path])
+
+    def removeFile(clean, path):
+        if cleanCache or (not cleanCache and clean):
+            runProgram(['git-update-cache', '--force-remove', '--', path])
+
+        if updateWd:
+            try:
+                os.unlink(path)
+            except OSError, e:
+                if e.errno != errno.ENOENT and e.errno != errno.EISDIR:
+                    raise
+
+    def uniquePath(path, branch):
+        newPath = path + '_' + branch
+        suffix = 0
+        while newPath in files or newPath in dirs:
+            suffix += 1
+            newPath = path + '_' + branch + '_' + str(suffix)
+        files.add(newPath)
+        return newPath
+
+    debug('processing', entry.path, 'clean cache:', cleanCache,
+          'wd:', updateWd)
+
+    cleanMerge = True
+
+    path = entry.path
+    oSha = entry.stages[0].sha1
+    oMode = entry.stages[0].mode
+    aSha = entry.stages[1].sha1
+    aMode = entry.stages[1].mode
+    bSha = entry.stages[2].sha1
+    bMode = entry.stages[2].mode
+
+    assert(oSha == None or isSha(oSha))
+    assert(aSha == None or isSha(aSha))
+    assert(bSha == None or isSha(bSha))
+
+    assert(oMode == None or type(oMode) is int)
+    assert(aMode == None or type(aMode) is int)
+    assert(bMode == None or type(bMode) is int)
+
+    if (oSha and (not aSha or not bSha)):
+    #
+    # Case A: Deleted in one
+    #
+        if (not aSha     and not bSha) or \
+           (aSha == oSha and not bSha) or \
+           (not aSha     and bSha == oSha):
+    # Deleted in both or deleted in one and unchanged in the other
+            if aSha:
+                print 'Removing ' + path
+            removeFile(True, path)
+        else:
+    # Deleted in one and changed in the other
+            cleanMerge = False
+            if not aSha:
+                print 'CONFLICT (del/mod): "' + path + '" deleted in', \
+                      branch1Name, 'and modified in', branch2Name, \
+                      '. Version', branch2Name, ' of "' + path + \
+                      '" left in tree'
+                mode = bMode
+                sha = bSha
+            else:
+                print 'CONFLICT (mod/del): "' + path + '" deleted in', \
+                      branch2Name, 'and modified in', branch1Name + \
+                      '. Version', branch1Name, 'of "' + path + \
+                      '" left in tree'
+                mode = aMode
+                sha = aSha
+
+            updateFile(False, sha, mode, path)
+    
+    elif (not oSha and aSha     and not bSha) or \
+         (not oSha and not aSha and bSha):
+    #
+    # Case B: Added in one.
+    #
+        if aSha:
+            addBranch = branch1Name
+            otherBranch = branch2Name
+            mode = aMode
+            sha = aSha
+            conf = 'file/dir'
+        else:
+            addBranch = branch2Name
+            otherBranch = branch1Name
+            mode = bMode
+            sha = bSha
+            conf = 'dir/file'
+    
+        if path in dirs:
+            cleanMerge = False
+            newPath = uniquePath(path, addBranch)
+            print 'CONFLICT (' + conf + \
+                  '): There is a directory with name "' + path + '" in', \
+                  otherBranch + '. Adding "' + path + '" as "' + newPath + '"'
+
+            removeFile(False, path)
+            path = newPath
+        else:
+            print 'Adding "' + path + '"'
+
+        updateFile(True, sha, mode, path)
+    
+    elif not oSha and aSha and bSha:
+    #
+    # Case C: Added in both (check for same permissions).
+    #
+        if aSha == bSha:
+            if aMode != bMode:
+                cleanMerge = False
+                print 'CONFLICT: File "' + path + \
+                      '" added identically in both branches,'
+                print 'CONFLICT: but permissions conflict', '0%o' % aMode, \
+                      '->', '0%o' % bMode
+                print 'CONFLICT: adding with permission:', '0%o' % aMode
+
+                updateFile(False, aSha, aMode, path)
+            else:
+                # This case is handled by git-read-tree
+                assert(False)
+        else:
+            cleanMerge = False
+            newPath1 = uniquePath(path, branch1Name)
+            newPath2 = uniquePath(path, branch2Name)
+            print 'CONFLICT (add/add): File "' + path + \
+                  '" added non-identically in both branches.', \
+                  'Adding "' + newPath1 + '" and "' + newPath2 + '" instead.'
+            removeFile(False, path)
+            updateFile(False, aSha, aMode, newPath1)
+            updateFile(False, bSha, bMode, newPath2)
+
+    elif oSha and aSha and bSha:
+    #
+    # case D: Modified in both, but differently.
+    #
+        print 'Auto-merging', path 
+        orig = runProgram(['git-unpack-file', oSha]).rstrip()
+        src1 = runProgram(['git-unpack-file', aSha]).rstrip()
+        src2 = runProgram(['git-unpack-file', bSha]).rstrip()
+        [out, ret] = runProgram(['merge',
+                                 '-L', branch1Name + '/' + path,
+                                 '-L', 'orig/' + path,
+                                 '-L', branch2Name + '/' + path,
+                                 src1, orig, src2], returnCode=True)
+
+        if aMode == oMode:
+            mode = bMode
+        else:
+            mode = aMode
+
+        sha = runProgram(['git-hash-object', '-t', 'blob', '-w',
+                          src1]).rstrip()
+
+        if ret != 0:
+            cleanMerge = False
+            print 'CONFLICT (content): Merge conflict in "' + path + '".'
+            updateFile(False, sha, mode, path)
+        else:
+            updateFile(True, sha, mode, path)
+
+        os.unlink(orig)
+        os.unlink(src1)
+        os.unlink(src2)
+    else:
+        print 'ERROR: Fatal merge failure.'
+        print "ERROR: Shouldn't happen"
+        sys.exit(2)
+
+    return cleanMerge
+
+def usage():
+    print 'Usage:', sys.argv[0], ' <base>... -- <head> <remote>..'
+    sys.exit(2)
+
+# main entry point as merge strategy module
+# The first parameters up to -- are merge bases, and the rest are heads.
+# This strategy module figures out merge bases itself, so we only
+# get heads.
+
+for nextArg in xrange(1, len(sys.argv)):
+    if sys.argv[nextArg] == '--':
+        if len(sys.argv) != nextArg + 3:
+            print 'Not handling anything other than two heads merge.'
+            sys.exit(2)
+        try:
+            h1 = firstBranch = sys.argv[nextArg + 1]
+            h2 = secondBranch = sys.argv[nextArg + 2]
+	except IndexError:
+            usage()
+        break
+
+print 'Merging', h1, 'with', h2
+h1 = runProgram(['git-rev-parse', '--verify', h1 + '^0']).rstrip()
+h2 = runProgram(['git-rev-parse', '--verify', h2 + '^0']).rstrip()
+
+graph = buildGraph([h1, h2])
+
+[res, clean] = merge(graph.shaMap[h1], graph.shaMap[h2],
+                     firstBranch, secondBranch, graph)
+
+print ''
+
+if clean:
+    sys.exit(0)
+else:
+    print 'Automatic merge failed, fix up by hand'
+    sys.exit(1)
diff --git a/git-merge.sh b/git-merge.sh
index 55b0c7269..a784e0f2c 100755
--- a/git-merge.sh
+++ b/git-merge.sh
@@ -14,7 +14,7 @@ usage () {
 
 # all_strategies='resolve fredrik stupid octopus'
 
-all_strategies='resolve octopus stupid'
+all_strategies='fredrik octopus resolve stupid'
 default_strategies='resolve octopus'
 use_strategies=
 
diff --git a/gitMergeCommon.py b/gitMergeCommon.py
new file mode 100644
index 000000000..dfa49ff7e
--- /dev/null
+++ b/gitMergeCommon.py
@@ -0,0 +1,268 @@
+import sys, re, os, traceback
+from sets import Set
+
+if sys.version_info[0] < 2 or \
+       (sys.version_info[0] == 2 and sys.version_info[1] < 4):
+    print 'Python version 2.4 required, found', \
+          str(sys.version_info[0])+'.'+str(sys.version_info[1])+'.'+ \
+          str(sys.version_info[2])
+    sys.exit(1)
+
+import subprocess
+
+# Debugging machinery
+# -------------------
+
+DEBUG = 0
+functionsToDebug = Set()
+
+def addDebug(func):
+    if type(func) == str:
+        functionsToDebug.add(func)
+    else:
+        functionsToDebug.add(func.func_name)
+
+def debug(*args):
+    if DEBUG:
+        funcName = traceback.extract_stack()[-2][2]
+        if funcName in functionsToDebug:
+            printList(args)
+
+def printList(list):
+    for x in list:
+        sys.stdout.write(str(x))
+        sys.stdout.write(' ')
+    sys.stdout.write('\n')
+
+# Program execution
+# -----------------
+
+class ProgramError(Exception):
+    def __init__(self, progStr, error):
+        self.progStr = progStr
+        self.error = error
+
+addDebug('runProgram')
+def runProgram(prog, input=None, returnCode=False, env=None, pipeOutput=True):
+    debug('runProgram prog:', str(prog), 'input:', str(input))
+    if type(prog) is str:
+        progStr = prog
+    else:
+        progStr = ' '.join(prog)
+    
+    try:
+        if pipeOutput:
+            stderr = subprocess.STDOUT
+            stdout = subprocess.PIPE
+        else:
+            stderr = None
+            stdout = None
+        pop = subprocess.Popen(prog,
+                               shell = type(prog) is str,
+                               stderr=stderr,
+                               stdout=stdout,
+                               stdin=subprocess.PIPE,
+                               env=env)
+    except OSError, e:
+        debug('strerror:', e.strerror)
+        raise ProgramError(progStr, e.strerror)
+
+    if input != None:
+        pop.stdin.write(input)
+    pop.stdin.close()
+
+    if pipeOutput:
+        out = pop.stdout.read()
+    else:
+        out = ''
+
+    code = pop.wait()
+    if returnCode:
+        ret = [out, code]
+    else:
+        ret = out
+    if code != 0 and not returnCode:
+        debug('error output:', out)
+        debug('prog:', prog)
+        raise ProgramError(progStr, out)
+#    debug('output:', out.replace('\0', '\n'))
+    return ret
+
+# Code for computing common ancestors
+# -----------------------------------
+
+currentId = 0
+def getUniqueId():
+    global currentId
+    currentId += 1
+    return currentId
+
+# The 'virtual' commit objects have SHAs which are integers
+shaRE = re.compile('^[0-9a-f]{40}$')
+def isSha(obj):
+    return (type(obj) is str and bool(shaRE.match(obj))) or \
+           (type(obj) is int and obj >= 1)
+
+class Commit:
+    def __init__(self, sha, parents, tree=None):
+        self.parents = parents
+        self.firstLineMsg = None
+        self.children = []
+
+        if tree:
+            tree = tree.rstrip()
+            assert(isSha(tree))
+        self._tree = tree
+
+        if not sha:
+            self.sha = getUniqueId()
+            self.virtual = True
+            self.firstLineMsg = 'virtual commit'
+            assert(isSha(tree))
+        else:
+            self.virtual = False
+            self.sha = sha.rstrip()
+        assert(isSha(self.sha))
+
+    def tree(self):
+        self.getInfo()
+        assert(self._tree != None)
+        return self._tree
+
+    def shortInfo(self):
+        self.getInfo()
+        return str(self.sha) + ' ' + self.firstLineMsg
+
+    def __str__(self):
+        return self.shortInfo()
+
+    def getInfo(self):
+        if self.virtual or self.firstLineMsg != None:
+            return
+        else:
+            info = runProgram(['git-cat-file', 'commit', self.sha])
+            info = info.split('\n')
+            msg = False
+            for l in info:
+                if msg:
+                    self.firstLineMsg = l
+                    break
+                else:
+                    if l.startswith('tree'):
+                        self._tree = l[5:].rstrip()
+                    elif l == '':
+                        msg = True
+
+class Graph:
+    def __init__(self):
+        self.commits = []
+        self.shaMap = {}
+
+    def addNode(self, node):
+        assert(isinstance(node, Commit))
+        self.shaMap[node.sha] = node
+        self.commits.append(node)
+        for p in node.parents:
+            p.children.append(node)
+        return node
+
+    def reachableNodes(self, n1, n2):
+        res = {}
+        def traverse(n):
+            res[n] = True
+            for p in n.parents:
+                traverse(p)
+
+        traverse(n1)
+        traverse(n2)
+        return res
+
+    def fixParents(self, node):
+        for x in range(0, len(node.parents)):
+            node.parents[x] = self.shaMap[node.parents[x]]
+
+# addDebug('buildGraph')
+def buildGraph(heads):
+    debug('buildGraph heads:', heads)
+    for h in heads:
+        assert(isSha(h))
+
+    g = Graph()
+
+    out = runProgram(['git-rev-list', '--parents'] + heads)
+    for l in out.split('\n'):
+        if l == '':
+            continue
+        shas = l.split(' ')
+
+        # This is a hack, we temporarily use the 'parents' attribute
+        # to contain a list of SHA1:s. They are later replaced by proper
+        # Commit objects.
+        c = Commit(shas[0], shas[1:])
+
+        g.commits.append(c)
+        g.shaMap[c.sha] = c
+
+    for c in g.commits:
+        g.fixParents(c)
+
+    for c in g.commits:
+        for p in c.parents:
+            p.children.append(c)
+    return g
+
+# Write the empty tree to the object database and return its SHA1
+def writeEmptyTree():
+    tmpIndex = os.environ['GIT_DIR'] + '/merge-tmp-index'
+    def delTmpIndex():
+        try:
+            os.unlink(tmpIndex)
+        except OSError:
+            pass
+    delTmpIndex()
+    newEnv = os.environ.copy()
+    newEnv['GIT_INDEX_FILE'] = tmpIndex
+    res = runProgram(['git-write-tree'], env=newEnv).rstrip()
+    delTmpIndex()
+    return res
+
+def addCommonRoot(graph):
+    roots = []
+    for c in graph.commits:
+        if len(c.parents) == 0:
+            roots.append(c)
+
+    superRoot = Commit(sha=None, parents=[], tree=writeEmptyTree())
+    graph.addNode(superRoot)
+    for r in roots:
+        r.parents = [superRoot]
+    superRoot.children = roots
+    return superRoot
+
+def getCommonAncestors(graph, commit1, commit2):
+    '''Find the common ancestors for commit1 and commit2'''
+    assert(isinstance(commit1, Commit) and isinstance(commit2, Commit))
+
+    def traverse(start, set):
+        stack = [start]
+        while len(stack) > 0:
+            el = stack.pop()
+            set.add(el)
+            for p in el.parents:
+                if p not in set:
+                    stack.append(p)
+    h1Set = Set()
+    h2Set = Set()
+    traverse(commit1, h1Set)
+    traverse(commit2, h2Set)
+    shared = h1Set.intersection(h2Set)
+
+    if len(shared) == 0:
+        shared = [addCommonRoot(graph)]
+        
+    res = Set()
+
+    for s in shared:
+        if len([c for c in s.children if c in shared]) == 0:
+            res.add(s)
+    return list(res)
diff --git a/read-tree.c b/read-tree.c
index 9ace5bb0a..4db154db2 100644
--- a/read-tree.c
+++ b/read-tree.c
@@ -12,6 +12,7 @@
 
 static int merge = 0;
 static int update = 0;
+static int index_only = 0;
 
 static int head_idx = -1;
 static int merge_size = 0;
@@ -306,6 +307,9 @@ static void verify_uptodate(struct cache_entry *ce)
 {
 	struct stat st;
 
+	if (index_only)
+		return;
+
 	if (!lstat(ce->name, &st)) {
 		unsigned changed = ce_match_stat(ce, &st);
 		if (!changed)
@@ -576,7 +580,7 @@ static int read_cache_unmerged(void)
 	return deleted;
 }
 
-static const char read_tree_usage[] = "git-read-tree (<sha> | -m [-u] <sha1> [<sha2> [<sha3>]])";
+static const char read_tree_usage[] = "git-read-tree (<sha> | -m [-u | -i] <sha1> [<sha2> [<sha3>]])";
 
 static struct cache_file cache_file;
 
@@ -595,12 +599,22 @@ int main(int argc, char **argv)
 	for (i = 1; i < argc; i++) {
 		const char *arg = argv[i];
 
-		/* "-u" means "update", meaning that a merge will update the working directory */
+		/* "-u" means "update", meaning that a merge will update
+		 * the working tree.
+		 */
 		if (!strcmp(arg, "-u")) {
 			update = 1;
 			continue;
 		}
 
+		/* "-i" means "index only", meaning that a merge will
+		 * not even look at the working tree.
+		 */
+		if (!strcmp(arg, "-i")) {
+			index_only = 1;
+			continue;
+		}
+
 		/* This differs from "-m" in that we'll silently ignore unmerged entries */
 		if (!strcmp(arg, "--reset")) {
 			if (stage || merge)
@@ -628,6 +642,10 @@ int main(int argc, char **argv)
 			continue;
 		}
 
+		/* using -u and -i at the same time makes no sense */
+		if (1 < index_only + update)
+			usage(read_tree_usage);
+
 		if (get_sha1(arg, sha1) < 0)
 			usage(read_tree_usage);
 		if (list_tree(sha1) < 0)