From 76be528c0d04e9ae5cd3f4dca5c887e5a194509a Mon Sep 17 00:00:00 2001
From: Mark Nauwelaerts <mnauw@users.sourceforge.net>
Date: Mon, 27 Nov 2017 20:49:03 +0100
Subject: [PATCH] Optionally ignore some remote Mercurial revision names

... in particular when these would otherwise map to unsupported refnames.

Fixes mnauw/git-remote-hg#10
---
 README.asciidoc       | 17 +++++++++++++++++
 doc/git-remote-hg.txt |  8 ++++++++
 git-remote-hg         | 28 +++++++++++++++++++++++-----
 test/main.t           | 22 ++++++++++++++++++++++
 4 files changed, 70 insertions(+), 5 deletions(-)

diff --git a/README.asciidoc b/README.asciidoc
index 3bc53b0..d0cdbe2 100644
--- a/README.asciidoc
+++ b/README.asciidoc
@@ -243,6 +243,23 @@ also be enabled on an existing one by the following setting.
 --------------------------------------
 Note, however, that one should then perform a fetch from each relevant remote
 to fully complete the conversion (prior to subsequent pushing).
+
+Some Mercurial names (of branches, bookmarks, tags) may not be a valid git
+refname. See e.g. `man git-check-ref-format` for a rather involved set of rules.
+Moreover, while a slash `/` is allowed, it is not supported to have both a `parent`
+and `parent/child` branch (though only the latter is allowed). So, pending some
+"nice" bidirectional encoding (not even e.g. URL encoding is safe actually), it is more
+likely that only a few instances (out of a whole Mercurial repo) are
+problematic.  This could be handled by a single-branch clone and/or configuring
+a suitable refspec.  However, it might be more convenient to simply filter out a
+few unimportant pesky cases, which can be done by configuring a regural
+expression in following setting:
+--------------------------------------
+% git config remote-hg.ignore-name nasty/nested/name
+--------------------------------------
+Recall also that a config setting can be provided at clone time
+(command line using `--config` option).
+
 --------------------------------------
 % git config --global remote-hg.remove-username-quotes false
 --------------------------------------
diff --git a/doc/git-remote-hg.txt b/doc/git-remote-hg.txt
index 9ae2953..6a8d53b 100644
--- a/doc/git-remote-hg.txt
+++ b/doc/git-remote-hg.txt
@@ -94,6 +94,14 @@ for an existing repo:
 Note that one should perform a fetch from each remote to properly complete the
 conversion to shared marks files.
 
+Mercurial name(s) (of a branch or bookmark) that are not a valid git refname,
+can be ignored by configuring a suitable regular expression, e.g. avoiding
+the invalid '~'
+
+--------------------------------------
+% git config --global remote-hg.ignore-name ~
+--------------------------------------
+
 NOTES
 -----
 
diff --git a/git-remote-hg b/git-remote-hg
index 9e21272..acf620b 100755
--- a/git-remote-hg
+++ b/git-remote-hg
@@ -96,8 +96,8 @@ def check_version(*check):
         return True
     return hg_version >= check
 
-def get_config(config):
-    cmd = ['git', 'config', '--get', config]
+def get_config(config, getall=False):
+    cmd = ['git', 'config', '--get' if not getall else '--get-all', config]
     process = subprocess.Popen(cmd, stdout=subprocess.PIPE)
     output, _ = process.communicate()
     return output
@@ -707,6 +707,22 @@ def do_list(parser):
 
     list_head(repo, cur)
 
+    ignore_ref = get_config('remote-hg.ignore-name', True)
+    ignore_re = []
+    for exp in ignore_ref.splitlines():
+        if exp:
+            try:
+                #warn("checking %s" % (
+                ignore_re.append(re.compile(exp.strip()))
+            except:
+                warn("Invalid regular expression '%s'" % (exp))
+    def ignore(kind, name):
+        for r in ignore_re:
+            if r.search(name):
+                warn("Ignoring matched %s %s" % (kind, name))
+                return True
+        return False
+
     # for export command a ref's old_sha1 is taken from private namespace ref
     # for push command a fake one is provided
     # that avoids having the ref status reported as a new branch/tag
@@ -717,18 +733,20 @@ def do_list(parser):
 
     if track_branches:
         for branch in branches:
-            print "%s refs/heads/branches/%s" % (sha1, gitref(branch))
+            if not ignore('branch', branch):
+                print "%s refs/heads/branches/%s" % (sha1, gitref(branch))
 
     for bmark in bmarks:
         if bmarks[bmark].hex() == '0' * 40:
             warn("Ignoring invalid bookmark '%s'", bmark)
-        else:
+        elif not ignore('bookmark', bmark):
             print "%s refs/heads/%s" % (sha1, gitref(bmark))
 
     for tag, node in repo.tagslist():
         if tag == 'tip':
             continue
-        print "%s refs/tags/%s" % (sha1, gitref(tag))
+        if not ignore('tag', tag):
+            print "%s refs/tags/%s" % (sha1, gitref(tag))
 
     print
 
diff --git a/test/main.t b/test/main.t
index 9a94d11..35624de 100755
--- a/test/main.t
+++ b/test/main.t
@@ -1201,6 +1201,28 @@ test_expect_success 'clone replace directory with a file' '
 	check_files gitrepo "dir_or_file"
 '
 
+test_expect_success 'clone can ignore invalid refnames' '
+	test_when_finished "rm -rf hgrepo gitrepo" &&
+
+	(
+	hg init hgrepo &&
+	cd hgrepo &&
+
+	touch test.txt &&
+	hg add test.txt &&
+	hg commit -m master &&
+	hg branch parent &&
+	echo test >test.txt &&
+	hg commit -m test &&
+	hg branch parent/child &&
+	echo test1 >test.txt &&
+	hg commit -m test1
+	) &&
+
+	git clone -c remote-hg.ignore-name=child "hg::hgrepo" gitrepo &&
+	check_files gitrepo "test.txt"
+'
+
 if test "$CAPABILITY_PUSH" != "t"
 then
 test_done