From e728ed013e15f76b96c10e0228c195fed184696d Mon Sep 17 00:00:00 2001
From: Rob Browning <rlb@defaultvalue.org>
Date: Fri, 4 Oct 2013 20:58:07 -0500
Subject: [PATCH] Be more careful when testing that repeated saves can produce
 the same tree.

Previously, test.sh would run multiple saves with no intervening
modifications, and check to see that the top-level "save -t" hash
didn't change, but with the addition of metadata this may fail on some
platforms where the test process itself (the save runs, etc.) affects
atime values.  That's because save is pulling the metadata for
unindexed parent directories directly from the filesystem.  And note
that atime is only special here because the test itself may
incidentally alter it -- we would see the same problem if any of the
other metdata for one of the unindexed parent directories changed
during the test run (i.e. mtime, uid, gid, ...).

To fix this, move the relevant test code from test.sh to
test-redundant-saves.sh, and use a newly added subdir-hash tool so
that we can compare the hashes of the roots of the indexed subtrees
instead of the top-level "save -t" hashes, ignoring the unindexed
parents entirely.

Thanks to Robert Edmonds <edmonds@debian.org> for running rc3 through
the Debian buildds which lead to the kFreeBSD test failure that
demonstrated the problem.

Signed-off-by: Rob Browning <rlb@defaultvalue.org>
---
 Makefile                  |  1 +
 t/subtree-hash            | 31 +++++++++++++++++++++
 t/test-redundant-saves.sh | 57 +++++++++++++++++++++++++++++++++++++++
 t/test.sh                 | 13 ---------
 4 files changed, 89 insertions(+), 13 deletions(-)
 create mode 100755 t/subtree-hash
 create mode 100755 t/test-redundant-saves.sh

diff --git a/Makefile b/Makefile
index d8686ff..c0310b0 100644
--- a/Makefile
+++ b/Makefile
@@ -91,6 +91,7 @@ runtests-cmdline: all
 	t/test-restore-single-file.sh
 	t/test-rm-between-index-and-save.sh
 	t/test-command-without-init-fails.sh
+	t/test-redundant-saves.sh
 	t/test.sh
 
 stupid:
diff --git a/t/subtree-hash b/t/subtree-hash
new file mode 100755
index 0000000..45e727c
--- /dev/null
+++ b/t/subtree-hash
@@ -0,0 +1,31 @@
+#!/usr/bin/env bash
+
+set -eo pipefail
+
+# Usage: subtree-hash ROOT_HASH [SUBDIR ...]
+
+subtree_hash()
+{
+    root_hash="$1"
+    if test "$#" -eq 1; then
+        echo $root_hash
+    else
+        subdir="$2"
+        subtree_info="$(git ls-tree "$root_hash" | grep -E "	$subdir\$")" || true
+        if test "$(echo "$subtree_info" | wc -l)" -ne 1; then
+            echo "Found more than one matching line in subtree $root_hash" 1>&2
+            return 1
+        fi
+
+        subtree_hash="$(echo "$subtree_info" | cut -d' ' -f 3 | cut -d$'\t' -f 1)" || true
+        if test -z "$subtree_hash"; then
+            echo "Unable to find subtree hash in git output: $subtree_info" 1>&2
+            return 1
+        fi
+
+        shift 2
+        subtree_hash "$subtree_hash" "$@"
+    fi
+}
+
+subtree_hash "$@"
diff --git a/t/test-redundant-saves.sh b/t/test-redundant-saves.sh
new file mode 100755
index 0000000..5bf00b1
--- /dev/null
+++ b/t/test-redundant-saves.sh
@@ -0,0 +1,57 @@
+#!/usr/bin/env bash
+
+# Test that running save more than once with no other changes produces
+# the exact same tree.
+
+# Note: we can't compare the top-level hash (i.e. the output of "save
+# -t" because that currently pulls the metadata for unindexed parent
+# directories directly from the filesystem, and the relevant atimes
+# may change between runs.  So instead we extract the roots of the
+# indexed trees for comparison via t/subtree-hash.
+
+. ./wvtest-bup.sh
+
+set -eo pipefail
+
+WVSTART 'all'
+
+top="$(pwd)"
+tmpdir="$(wvmktempdir)"
+export BUP_DIR="$tmpdir/bup"
+export GIT_DIR="$BUP_DIR"
+
+bup() { "$top/bup" "$@"; }
+
+mkdir -p "$tmpdir/src"
+mkdir -p "$tmpdir/src/d"
+mkdir -p "$tmpdir/src/d/e"
+touch "$tmpdir/src/"{f,b,a,d}
+touch "$tmpdir/src/d/z"
+
+WVPASS bup init
+WVPASS bup index -u "$tmpdir/src"
+
+declare -a indexed_top
+IFS=/
+indexed_top="${tmpdir##/}"
+indexed_top=(${indexed_top%%/})
+unset IFS
+
+tree1=$(bup save -t "$tmpdir/src") || WVFAIL
+indexed_tree1="$(t/subtree-hash "$tree1" "${indexed_top[@]}" src)"
+
+WVPASSEQ "$(cd "$tmpdir/src" && bup index -m)" ""
+
+tree2=$(bup save -t "$tmpdir/src") || WVFAIL
+indexed_tree2="$(t/subtree-hash "$tree2" "${indexed_top[@]}" src)"
+
+WVPASSEQ "$indexed_tree1" "$indexed_tree2"
+
+WVPASSEQ "$(bup index -s / | grep ^D)" ""
+
+tree3=$(bup save -t /) || WVFAIL
+indexed_tree3="$(t/subtree-hash "$tree3" "${indexed_top[@]}")"
+
+WVPASSEQ "$indexed_tree3" "$indexed_tree3"
+
+rm -rf "$tmpdir"
diff --git a/t/test.sh b/t/test.sh
index 3656689..8352845 100755
--- a/t/test.sh
+++ b/t/test.sh
@@ -123,19 +123,6 @@ WVPASSEQ "$(cd $D && bup index -m)" \
 f
 a
 ./"
-tree1=$(bup save -t $D) || WVFAIL
-WVPASSEQ "$(cd $D && bup index -m)" ""
-tree2=$(bup save -t $D) || WVFAIL
-if ! [[ $(uname) =~ CYGWIN ]]; then
-    # On Cygwin, the access time may change.
-    WVPASSEQ "$tree1" "$tree2"
-fi
-WVPASSEQ "$(bup index -s / | grep ^D)" ""
-tree3=$(bup save -t /) || WVFAIL
-if ! [[ $(uname) =~ CYGWIN ]]; then
-    # On Cygwin, the access time may change.
-    WVPASSEQ "$tree1" "$tree3"
-fi
 WVPASS bup save -r :$BUP_DIR -n r-test $D
 WVFAIL bup save -r :$BUP_DIR/fake/path -n r-test $D
 WVFAIL bup save -r :$BUP_DIR -n r-test $D/fake/path
-- 
2.39.2