[PATCH v3 1/1] clone: report duplicate entries on case-insensitive filesystems

From: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Date: Aug 10, 2018, 15:36 UTC
Message-ID: <20180810153608.30051-2-pclouds@gmail.com>
In-Reply-To: <20180810153608.30051-1-pclouds@gmail.com>

Paths that only differ in case work fine in a case-sensitive filesystems, but if those repos are cloned in a case-insensitive one, you'll get problems. The first thing to notice is "git status" will never be clean with no indication what exactly is "dirty".

This patch helps the situation a bit by pointing out the problem at clone time. Even though this patch talks about case sensitivity, the patch makes no assumption about folding rules by the filesystem. It simply observes that if an entry has been already checked out at clone time when we're about to write a new path, some folding rules are behind this.

This patch is tested with vim-colorschemes repository on a JFS partition with case insensitive support on Linux. This repository has two files darkBlue.vim and darkblue.vim.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 builtin/clone.c |  1 +
 cache.h         |  2 ++
 entry.c         | 32 ++++++++++++++++++++++++++++++++
 unpack-trees.c  | 22 ++++++++++++++++++++++
 unpack-trees.h  |  1 +
 5 files changed, 58 insertions(+)

diff --git a/builtin/clone.c b/builtin/clone.c
index 9ebb5acf56..38d5609282 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -748,6 +748,7 @@ static int checkout(int submodule_progress)
 	memset(&opts, 0, sizeof opts);
 	opts.update = 1;
 	opts.merge = 1;
+	opts.clone = 1;
 	opts.fn = oneway_merge;
 	opts.verbose_update = (option_verbosity >= 0);
 	opts.src_index = &the_index;
diff --git a/cache.h b/cache.h
index 8dc7134f00..cdf0984707 100644
--- a/cache.h
+++ b/cache.h
@@ -1515,9 +1515,11 @@ struct checkout {
 	const char *base_dir;
 	int base_dir_len;
 	struct delayed_checkout *delayed_checkout;
+	int *nr_duplicates;
 	unsigned force:1,
 		 quiet:1,
 		 not_new:1,
+		 clone:1,
 		 refresh_cache:1;
 };
 #define CHECKOUT_INIT { NULL, "" }
diff --git a/entry.c b/entry.c
index b5d1d3cf23..f2d73e6255 100644
--- a/entry.c
+++ b/entry.c
@@ -399,6 +399,35 @@ static int check_path(const char *path, int len, struct stat *st, int skiplen)
 	return lstat(path, st);
 }
 
+static void mark_duplicate_entries(const struct checkout *state,
+				   struct cache_entry *ce, struct stat *st)
+{
+	int i;
+	int *count = state->nr_duplicates;
+
+	if (!count)
+		BUG("state->nr_duplicates must not be NULL");
+
+	ce->ce_flags |= CE_MATCHED;
+	(*count)++;
+
+#if !defined(GIT_WINDOWS_NATIVE) /* inode is always zero on Windows */
+	for (i = 0; i < state->istate->cache_nr; i++) {
+		struct cache_entry *dup = state->istate->cache[i];
+
+		if (dup->ce_flags & (CE_MATCHED | CE_VALID | CE_SKIP_WORKTREE))
+			continue;
+
+		if (ce_uptodate(dup) &&
+		    dup->ce_stat_data.sd_ino == st->st_ino) {
+			dup->ce_flags |= CE_MATCHED;
+			(*count)++;
+			break;
+		}
+	}
+#endif
+}
+
 /*
  * Write the contents from ce out to the working tree.
  *
@@ -455,6 +484,9 @@ int checkout_entry(struct cache_entry *ce,
 			return -1;
 		}
 
+		if (state->clone)
+			mark_duplicate_entries(state, ce, &st);
+
 		/*
 		 * We unlink the old file, to get the new one with the
 		 * right permissions (including umask, which is nasty
diff --git a/unpack-trees.c b/unpack-trees.c
index f9efee0836..d4fece913c 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -344,12 +344,20 @@ static int check_updates(struct unpack_trees_options *o)
 	struct index_state *index = &o->result;
 	struct checkout state = CHECKOUT_INIT;
 	int i;
+	int nr_duplicates = 0;
 
 	state.force = 1;
 	state.quiet = 1;
 	state.refresh_cache = 1;
 	state.istate = index;
 
+	if (o->clone) {
+		state.clone = 1;
+		state.nr_duplicates = &nr_duplicates;
+		for (i = 0; i < index->cache_nr; i++)
+			index->cache[i]->ce_flags &= ~CE_MATCHED;
+	}
+
 	progress = get_progress(o);
 
 	if (o->update)
@@ -414,6 +422,20 @@ static int check_updates(struct unpack_trees_options *o)
 	errs |= finish_delayed_checkout(&state);
 	if (o->update)
 		git_attr_set_direction(GIT_ATTR_CHECKIN, NULL);
+
+	if (o->clone && state.nr_duplicates) {
+		warning(_("the following paths have collided and only one from the same\n"
+			  "colliding group is in the working tree:\n"));
+		for (i = 0; i < index->cache_nr; i++) {
+			struct cache_entry *ce = index->cache[i];
+
+			if (!(ce->ce_flags & CE_MATCHED))
+				continue;
+			fprintf(stderr, "  '%s'\n", ce->name);
+			ce->ce_flags &= ~CE_MATCHED;
+		}
+	}
+
 	return errs != 0;
 }
 
diff --git a/unpack-trees.h b/unpack-trees.h
index c2b434c606..d940f1c5c2 100644
--- a/unpack-trees.h
+++ b/unpack-trees.h
@@ -42,6 +42,7 @@ struct unpack_trees_options {
 	unsigned int reset,
 		     merge,
 		     update,
+		     clone,
 		     index_only,
 		     nontrivial_merge,
 		     trivial_merges_only,

-- 
2.18.0.915.gd571298aae