Change syntax of mapping files

This is done to allow escape sequences in the key and value strings.

README.md

@@ -65,12 +65,18 @@ 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
+form `"<key>"="<value>"`. Inside the key and value strings, all escape
-translate `User <garbage<user@example.com>` to `User <user@example.com>`.
+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

@@ -294,7 +294,24 @@ 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 +319,19 @@ 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 +478,8 @@ 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 +494,15 @@ 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

@@ -7,7 +7,18 @@ READLINK="readlink"
 if command -v greadlink > /dev/null; then
   READLINK="greadlink" # Prefer greadlink over readlink
 fi
-ROOT="$(dirname "$($READLINK -f "$(which "$0")")")"
+
+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" \
+	     " how to canonicalize paths in order to be called via a symlink."
+	exit 1
+    fi
+else
+    ROOT="$(dirname "$($READLINK -f "$(which "$0")")")"
+fi
+
 REPO=""
 PFX="hg2git"
 SFX_MAPPING="mapping"
@@ -44,6 +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 "$1" in
     -h|--help)
@@ -59,7 +71,7 @@ if test "z$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)