Adapt to changes in Mercurial 4.6

Starting with Mercurial 4.6 repo.lookup() no longer accepts raw hashes
for lookups.

README.md

@@ -24,6 +24,16 @@ you want to report a security bug. That way the next person having the
 same problem can benefit from the time spent solving the problem the
 first time.
 
+System Requirements
+-------------------
+
+This project depends on Python 2.7 and the Mercurial 4.6 package. If
+Python is not installed, install it before proceeding. The Mercurial
+package can be installed with `pip install mercurial`.
+
+If you're on Windows, run the following commands in git bash (Git for
+Windows).
+
 Usage
 -----
 
@@ -33,7 +43,8 @@ Using hg-fast-export is quite simple for a mercurial repository <repo>:
 mkdir repo-git # or whatever
 cd repo-git
 git init
-hg-fast-export.sh -r <repo>
+hg-fast-export.sh -r <local-repo>
+git checkout HEAD
 ```
 
 Please note that hg-fast-export does not automatically check out the
@@ -65,12 +76,18 @@ As mercurial appears to be much less picky about the syntax of the
 author information than git, an author mapping file can be given to
 hg-fast-export to fix up malformed author strings. The file is
 specified using the -A option. The file should contain lines of the
-form `FromAuthor=ToAuthor`. The example authors.map below will
-translate `User <garbage<user@example.com>` to `User <user@example.com>`.
+form `"<key>"="<value>"`. Inside the key and value strings, all escape
+sequences understood by the python `string_escape` encoding are
+supported. (Versions of fast-export prior to v171002 had a different
+syntax, the old syntax can be enabled by the flag
+`--mappings-are-raw`.)
+
+The example authors.map below will translate `User
+<garbage<tab><user@example.com>` to `User <user@example.com>`.
 
 ```
 -- Start of authors.map --
-User <garbage<user@example.com>=User <user@example.com>
+"User <garbage\t<user@example.com>"="User <user@example.com>"
 -- End of authors.map --
 ```
 

hg-fast-export.py

@@ -4,6 +4,7 @@
 # License: MIT <http://www.opensource.org/licenses/mit-license.php>
 
 from mercurial import node
+from mercurial.scmutil import revsymbol
 from hg2git import setup_repo,fixup_user,get_branch,get_changeset
 from hg2git import load_cache,save_cache,get_git_sha1,set_default_branch,set_origin_name
 from optparse import OptionParser
@@ -78,7 +79,7 @@ def get_filechanges(repo,revision,parents,mleft):
   l,c,r=[],[],[]
   for p in parents:
     if p<0: continue
-    mright=repo.changectx(p).manifest()
+    mright=revsymbol(repo,str(p)).manifest()
     l,c,r=split_dict(mleft,mright,l,c,r)
   l.sort()
   c.sort()
@@ -153,9 +154,13 @@ def sanitize_name(name,what="branch", mapping={}):
   # modifying names which previously were not touched it will break
   # preexisting setups which are doing incremental imports.
   #
-  # Use the -B and -T options to mangle branch and tag names
-  # instead. If you have a source repository where this is too much
-  # work to do manually, write a tool that does it for you.
+  # Fast-export tries to not inflict arbitrary naming policy on the
+  # user, instead it aims to provide mechanisms allowing the user to
+  # apply their own policy. Therefore do not add a transform which can
+  # already be implemented with the -B and -T options to mangle branch
+  # and tag names. If you have a source repository where this is too
+  # much work to do manually, write a tool that does it for you.
+  #
 
   def dot(name):
     if not name: return name
@@ -206,7 +211,7 @@ def export_commit(ui,repo,revision,old_marks,max,count,authors,
   wr(desc)
   wr()
 
-  ctx=repo.changectx(str(revision))
+  ctx=revsymbol(repo,str(revision))
   man=ctx.manifest()
   added,changed,removed,type=[],[],[],''
 
@@ -221,7 +226,7 @@ def export_commit(ui,repo,revision,old_marks,max,count,authors,
       # later non-merge revision: feed in changed manifest
       # if we have exactly one parent, just take the changes from the
       # manifest without expensively comparing checksums
-      f=repo.status(repo.lookup(parents[0]),revnode)[:3]
+      f=repo.status(parents[0],revnode)[:3]
       added,changed,removed=f[1],f[0],f[2]
       type='simple delta'
     else: # a merge with two parents
@@ -258,7 +263,7 @@ def export_note(ui,repo,revision,count,authors,encoding,is_first):
   if is_first:
     wr('from refs/notes/hg^0')
   wr('N inline :%d' % (revision+1))
-  hg_hash=repo.changectx(str(revision)).hex()
+  hg_hash=revsymbol(repo,str(revision)).hex()
   wr('data %d' % (len(hg_hash)))
   wr_no_nl(hg_hash)
   wr()
@@ -294,7 +299,24 @@ def export_tags(ui,repo,old_marks,mapping_cache,count,authors,tagsmap):
     count=checkpoint(count)
   return count
 
-def load_mapping(name, filename):
+def load_mapping(name, filename, mapping_is_raw):
+  raw_regexp=re.compile('^([^=]+)[ ]*=[ ]*(.+)$')
+  string_regexp='"(((\\.)|(\\")|[^"])*)"'
+  quoted_regexp=re.compile('^'+string_regexp+'[ ]*=[ ]*'+string_regexp+'$')
+
+  def parse_raw_line(line):
+    m=raw_regexp.match(line)
+    if m==None:
+      return None
+    return (m.group(1).strip(), m.group(2).strip())
+
+  def parse_quoted_line(line):
+    m=quoted_regexp.match(line)
+    if m==None:
+      return None
+    return (m.group(1).decode('string_escape'),
+            m.group(5).decode('string_escape'))
+
   cache={}
   if not os.path.exists(filename):
     sys.stderr.write('Could not open mapping file [%s]\n' % (filename))
@@ -302,18 +324,19 @@ def load_mapping(name, filename):
   f=open(filename,'r')
   l=0
   a=0
-  lre=re.compile('^([^=]+)[ ]*=[ ]*(.+)$')
   for line in f.readlines():
     l+=1
     line=line.strip()
-    if line=='' or line[0]=='#':
+    if l==1 and line[0]=='#' and line=='# quoted-escaped-strings':
       continue
-    m=lre.match(line)
+    elif line=='' or line[0]=='#':
+      continue
+    m=parse_raw_line(line) if mapping_is_raw else parse_quoted_line(line)
     if m==None:
       sys.stderr.write('Invalid file format in [%s], line %d\n' % (filename,l))
       continue
     # put key:value in cache, key without ^:
-    cache[m.group(1).strip()]=m.group(2).strip()
+    cache[m[0]]=m[1]
     a+=1
   f.close()
   sys.stderr.write('Loaded %d %s\n' % (a, name))
@@ -460,6 +483,8 @@ if __name__=='__main__':
       help="Assume commit and author strings retrieved from Mercurial are encoded in <encoding>")
   parser.add_option("--fe",dest="fn_encoding",
       help="Assume file names from Mercurial are encoded in <filename_encoding>")
+  parser.add_option("--mappings-are-raw",dest="raw_mappings", default=False,
+      help="Assume mappings are raw <key>=<value> lines")
 
   (options,args)=parser.parse_args()
 
@@ -474,15 +499,15 @@ if __name__=='__main__':
 
   a={}
   if options.authorfile!=None:
-    a=load_mapping('authors', options.authorfile)
+    a=load_mapping('authors', options.authorfile, options.raw_mappings)
 
   b={}
   if options.branchesfile!=None:
-    b=load_mapping('branches', options.branchesfile)
+    b=load_mapping('branches', options.branchesfile, options.raw_mappings)
 
   t={}
   if options.tagsfile!=None:
-    t=load_mapping('tags', options.tagsfile)
+    t=load_mapping('tags', options.tagsfile, True)
 
   if options.default_branch!=None:
     set_default_branch(options.default_branch)

hg-fast-export.sh

@@ -8,7 +8,7 @@ if command -v greadlink > /dev/null; then
   READLINK="greadlink" # Prefer greadlink over readlink
 fi
 
-if ! $READLINK -f "$(which "$0")" >& /dev/null; then
+if ! $READLINK -f "$(which "$0")" > /dev/null 2>&1 ; then
     ROOT="$(dirname "$(which "$0")")"
     if [ ! -f "$ROOT/hg-fast-export.py" ] ; then
 	echo "hg-fast-exports requires a readlink implementation which knows" \
@@ -55,6 +55,7 @@ Options:
 	              Mercurial are encoded in <encoding>
 	--fe <filename_encoding> Assume filenames from Mercurial are encoded 
 	                         in <filename_encoding>
+	--mappings-are-raw Assume mappings are raw <key>=<value> lines
 "
 case "$1" in
     -h|--help)
@@ -70,7 +71,7 @@ if test "z$IS_BARE" != ztrue; then
    # This is not a bare repo, cd to the toplevel
    TOPLEVEL=$(git rev-parse --show-toplevel) \
        || (echo "Could not find git repo toplevel" ; exit 1)
-   cd $TOPLEVEL || exit 1
+   cd "$TOPLEVEL" || exit 1
 fi
 GIT_DIR=$(git rev-parse --git-dir) || (echo "Could not find git repo" ; exit 1)
 
@@ -152,7 +153,7 @@ $(
   exec 4>&3 3>&1 1>&4 4>&-
   {
     _e1=0
-    GIT_DIR="$GIT_DIR" $PYTHON "$ROOT/hg-fast-export.py" \
+    GIT_DIR="$GIT_DIR" "$PYTHON" "$ROOT/hg-fast-export.py" \
       --repo "$REPO" \
       --marks "$GIT_DIR/$PFX-$SFX_MARKS" \
       --mapping "$GIT_DIR/$PFX-$SFX_MAPPING" \

hg2git.py

@@ -4,6 +4,9 @@
 # License: MIT <http://www.opensource.org/licenses/mit-license.php>
 
 from mercurial import hg,util,ui,templatefilters
+from mercurial import error as hgerror
+from mercurial.scmutil import revsymbol,binnode
+
 import re
 import os
 import sys
@@ -69,7 +72,15 @@ def get_branch(name):
   return name
 
 def get_changeset(ui,repo,revision,authors={},encoding=''):
-  node=repo.lookup(revision)
+  # Starting with Mercurial 4.6 lookup no longer accepts raw hashes
+  # for lookups. Work around it by changing our behaviour depending on
+  # how it fails
+  try:
+    node=repo.lookup(revision)
+  except hgerror.ProgrammingError:
+    node=binnode(revsymbol(repo,str(revision))) # We were given a numeric rev
+  except hgerror.RepoLookupError:
+    node=revision # We got a raw hash
   (manifest,user,(time,timezone),files,desc,extra)=repo.changelog.read(node)
   if encoding:
     user=user.decode(encoding).encode('utf8')