From 1181a0af471fe473919b30f476a253a9ae2282b0 Mon Sep 17 00:00:00 2001
From: Frej Drejhammar <frej.drejhammar@gmail.com>
Date: Fri, 10 May 2019 18:52:57 +0200
Subject: [PATCH] Allow name sanitizer to be disabled with --no-auto-sanitize

Make it possible to completely disable the name sanitizer by the
--no-auto-sanitize flag. Previously the sanitizer was run on user
remapped names. As the sanitizer rewrites perfectly legal git
names (such as __.*) this is probably not what the user wants.

Closes #155.
---
 README.md         |  6 ++++++
 hg-fast-export.py | 10 ++++++++++
 hg-fast-export.sh |  2 ++
 3 files changed, 18 insertions(+)

diff --git a/README.md b/README.md
index 3329b7d..0a5673b 100644
--- a/README.md
+++ b/README.md
@@ -101,6 +101,12 @@ name the -B and -T options allow a mapping file to be specified to
 rename branches and tags (respectively). The syntax of the mapping
 file is the same as for the author mapping.
 
+When the -B and -T flags are used, you will probably want to use the
+-n flag to disable the built-in (broken in many cases) sanitizing of
+branch/tag names. In the future -n will become the default, but in
+order to not break existing incremental conversions, the default
+remains with the old behavior.
+
 Content filtering
 -----------------
 
diff --git a/hg-fast-export.py b/hg-fast-export.py
index 72d9c7f..4709276 100755
--- a/hg-fast-export.py
+++ b/hg-fast-export.py
@@ -31,6 +31,10 @@ cfg_export_boundary=1000
 subrepo_cache={}
 submodule_mappings=None
 
+# True if fast export should automatically try to sanitize
+# author/branch/tag names.
+auto_sanitize = None
+
 def gitmode(flags):
   return 'l' in flags and '120000' or 'x' in flags and '100755' or '100644'
 
@@ -226,6 +230,8 @@ def sanitize_name(name,what="branch", mapping={}):
     if name[0] == '.': return '_'+name[1:]
     return name
 
+  if not auto_sanitize:
+    return mapping.get(name,name)
   n=mapping.get(name,name)
   p=re.compile('([[ ~^:?\\\\*]|\.\.)')
   n=p.sub('_', n)
@@ -532,6 +538,9 @@ if __name__=='__main__':
 
   parser=OptionParser()
 
+  parser.add_option("-n", "--no-auto-sanitize",action="store_false",
+      dest="auto_sanitize",default=True,
+      help="Do not perform built-in (broken in many cases) sanitizing of names")
   parser.add_option("-m","--max",type="int",dest="max",
       help="Maximum hg revision to import")
   parser.add_option("--mapping",dest="mappingfile",
@@ -580,6 +589,7 @@ if __name__=='__main__':
   (options,args)=parser.parse_args()
 
   m=-1
+  auto_sanitize = options.auto_sanitize
   if options.max!=None: m=options.max
 
   if options.marksfile==None: bail(parser,'--marks')
diff --git a/hg-fast-export.sh b/hg-fast-export.sh
index a4cb90e..e1f2f50 100755
--- a/hg-fast-export.sh
+++ b/hg-fast-export.sh
@@ -70,6 +70,8 @@ Options:
 	-B <file> Read branch map from file
 	-T <file> Read tags map from file
 	-M <name> Set the default branch name (defaults to 'master')
+	-n        Do not perform built-in (broken in many cases) sanitizing
+                  of branch/tag names.
 	-o <name> Use <name> as branch namespace to track upstream (eg 'origin')
 	--hg-hash Annotate commits with the hg hash as git notes in the
                   hg namespace.