[PATCH] diff-helper: Fix R/C score parsing under -z flag.

The score number that follow R/C status were parsed but the
parse pointer was not updated, causing the entire line to become
unrecognized.  This patch fixes this problem.

There was a test missing to catch this breakage, which this
commit adds as t4009-diff-rename-4.sh.  The diff-raw tests used
in related t4005-diff-rename-2.sh (the same test without -z) and
t4007-rename-3.sh were stricter than necessarily, despite that
the comment for the tests said otherwise.  This patch also
corrects them.

The documentation is updated to say that the status can
optionally be followed by a number called "score"; it does not
have to stay similarity index forever and there is no reason to
limit it only to C and R.

Signed-off-by: Junio C Hamano <junkio@cox.net>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 210 insertions, 8 deletions

diff --git a/t/t4005-diff-rename-2.sh b/t/t4005-diff-rename-2.sh
index a51985518..5ac29d1f9 100644
--- a/t/t4005-diff-rename-2.sh
+++ b/t/t4005-diff-rename-2.sh
@@ -8,11 +8,17 @@ test_description='Same rename detection as t4003 but testing diff-raw.
 '
 . ./test-lib.sh
 
+_x40='[0-9a-f][0-9a-f][0-9a-f][0-9a-f][0-9a-f]'
+_x40="$_x40$_x40$_x40$_x40$_x40$_x40$_x40$_x40"
+sanitize_diff_raw='s/ '"$_x40"' '"$_x40"' \([A-Z]\)[0-9]*	/ X X \1#	/'
 compare_diff_raw () {
     # When heuristics are improved, the score numbers would change.
     # Ignore them while comparing.
-    sed -e 's/ \([CR]\)[0-9]*	/\1#/' <"$1" >.tmp-1
-    sed -e 's/ \([CR]\)[0-9]*	/\1#/' <"$2" >.tmp-2
+    # Also we do not check SHA1 hash generation in this test, which
+    # is a job for t0000-basic.sh
+
+    sed -e "$sanitize_diff_raw" <"$1" >.tmp-1
+    sed -e "$sanitize_diff_raw" <"$2" >.tmp-2
     diff -u .tmp-1 .tmp-2 && rm -f .tmp-1 .tmp-2
 }
 
@@ -109,11 +115,6 @@ test_expect_success \
     'validate output from rename/copy detection (#2)' \
     'compare_diff_raw current expected'
 
-test_expect_success \
-    'prepare work tree once again' \
-    'cat ../../COPYING >COPYING &&
-     git-update-cache --add --remove COPYING COPYING.1'
-
 # make sure diff-helper can grok it.
 mv expected diff-raw
 GIT_DIFF_OPTS=--unified=0 git-diff-helper <diff-raw >current
@@ -151,6 +152,11 @@ test_expect_success \
 # anything about rezrov nor COPYING, since the revised again diff-raw
 # nows how to say Copy.
 
+test_expect_success \
+    'prepare work tree once again' \
+    'cat ../../COPYING >COPYING &&
+     git-update-cache --add --remove COPYING COPYING.1'
+
 git-diff-cache -C $tree >current
 cat >expected <<\EOF
 :100644 100644 6ff87c4664981e4397625791c8ea3bbb5f2279a3 0603b3238a076dc6c8022aedc6648fa523a17178 C1234	COPYING	COPYING.1
diff --git a/t/t4007-rename-3.sh b/t/t4007-rename-3.sh
index 518892b90..76ae7201f 100644
--- a/t/t4007-rename-3.sh
+++ b/t/t4007-rename-3.sh
@@ -10,7 +10,7 @@ test_description='Rename interaction with pathspec.
 
 _x40='[0-9a-f][0-9a-f][0-9a-f][0-9a-f][0-9a-f]'
 _x40="$_x40$_x40$_x40$_x40$_x40$_x40$_x40$_x40"
-sanitize_diff_raw='s/ \('"$_x40"'\) \1 \([CR]\)[0-9]*	/ \1 \1 \2#	/'
+sanitize_diff_raw='s/ '"$_x40"' '"$_x40"' \([A-Z]\)[0-9]*	/ X X \1#	/'
 compare_diff_raw () {
     # When heuristics are improved, the score numbers would change.
     # Ignore them while comparing.
diff --git a/t/t4009-diff-rename-4.sh b/t/t4009-diff-rename-4.sh
new file mode 100644
index 000000000..01d276692
--- /dev/null
+++ b/t/t4009-diff-rename-4.sh
@@ -0,0 +1,196 @@
+#!/bin/sh
+#
+# Copyright (c) 2005 Junio C Hamano
+#
+
+test_description='Same rename detection as t4003 but testing diff-raw -z.
+
+'
+. ./test-lib.sh
+
+_x40='[0-9a-f][0-9a-f][0-9a-f][0-9a-f][0-9a-f]'
+_x40="$_x40$_x40$_x40$_x40$_x40$_x40$_x40$_x40"
+sanitize_diff_raw='/^:/s/ '"$_x40"' '"$_x40"' \([A-Z]\)[0-9]*$/ X X \1#/'
+compare_diff_raw () {
+    # When heuristics are improved, the score numbers would change.
+    # Ignore them while comparing.
+    # Also we do not check SHA1 hash generation in this test, which
+    # is a job for t0000-basic.sh
+
+    tr '\0' '\012' <"$1" | sed -e "$sanitize_diff_raw" >.tmp-1
+    tr '\0' '\012' <"$2" | sed -e "$sanitize_diff_raw" >.tmp-2
+    diff -u .tmp-1 .tmp-2 && rm -f .tmp-1 .tmp-2
+}
+
+compare_diff_patch () {
+    # When heuristics are improved, the score numbers would change.
+    # Ignore them while comparing.
+    sed -e '/^similarity index [0-9]*%$/d' <"$1" >.tmp-1
+    sed -e '/^similarity index [0-9]*%$/d' <"$2" >.tmp-2
+    diff -u .tmp-1 .tmp-2 && rm -f .tmp-1 .tmp-2
+}
+
+test_expect_success \
+    'prepare reference tree' \
+    'cat ../../COPYING >COPYING &&
+     echo frotz >rezrov &&
+    git-update-cache --add COPYING rezrov &&
+    tree=$(git-write-tree) &&
+    echo $tree'
+
+test_expect_success \
+    'prepare work tree' \
+    'sed -e 's/HOWEVER/However/' <COPYING >COPYING.1 &&
+    sed -e 's/GPL/G.P.L/g' <COPYING >COPYING.2 &&
+    rm -f COPYING &&
+    git-update-cache --add --remove COPYING COPYING.?'
+
+# tree has COPYING and rezrov.  work tree has COPYING.1 and COPYING.2,
+# both are slightly edited, and unchanged rezrov.  We say COPYING.1
+# and COPYING.2 are based on COPYING, and do not say anything about
+# rezrov.
+
+git-diff-cache -z -M $tree >current
+
+cat >expected <<\EOF
+:100644 100644 6ff87c4664981e4397625791c8ea3bbb5f2279a3 0603b3238a076dc6c8022aedc6648fa523a17178 C1234
+COPYING
+COPYING.1
+:100644 100644 6ff87c4664981e4397625791c8ea3bbb5f2279a3 06c67961bbaed34a127f76d261f4c0bf73eda471 R1234
+COPYING
+COPYING.2
+EOF
+
+test_expect_success \
+    'validate output from rename/copy detection (#1)' \
+    'compare_diff_raw current expected'
+
+# make sure diff-helper can grok it.
+mv current diff-raw
+GIT_DIFF_OPTS=--unified=0 git-diff-helper -z <diff-raw >current
+cat >expected <<\EOF
+diff --git a/COPYING b/COPYING.1
+copy from COPYING
+copy to COPYING.1
+--- a/COPYING
++++ b/COPYING.1
+@@ -6 +6 @@
+- HOWEVER, in order to allow a migration to GPLv3 if that seems like
++ However, in order to allow a migration to GPLv3 if that seems like
+diff --git a/COPYING b/COPYING.2
+rename old COPYING
+rename new COPYING.2
+--- a/COPYING
++++ b/COPYING.2
+@@ -2 +2 @@
+- Note that the only valid version of the GPL as far as this project
++ Note that the only valid version of the G.P.L as far as this project
+@@ -6 +6 @@
+- HOWEVER, in order to allow a migration to GPLv3 if that seems like
++ HOWEVER, in order to allow a migration to G.P.Lv3 if that seems like
+@@ -12 +12 @@
+-	This file is licensed under the GPL v2, or a later version
++	This file is licensed under the G.P.L v2, or a later version
+EOF
+
+test_expect_success \
+    'validate output from diff-helper (#1)' \
+    'compare_diff_patch current expected'
+
+################################################################
+
+test_expect_success \
+    'prepare work tree again' \
+    'mv COPYING.2 COPYING &&
+     git-update-cache --add --remove COPYING COPYING.1 COPYING.2'
+
+# tree has COPYING and rezrov.  work tree has COPYING and COPYING.1,
+# both are slightly edited, and unchanged rezrov.  We say COPYING.1
+# is based on COPYING and COPYING is still there, and do not say anything
+# about rezrov.
+
+git-diff-cache -z -C $tree >current
+cat >expected <<\EOF
+:100644 100644 6ff87c4664981e4397625791c8ea3bbb5f2279a3 06c67961bbaed34a127f76d261f4c0bf73eda471 M
+COPYING
+:100644 100644 6ff87c4664981e4397625791c8ea3bbb5f2279a3 0603b3238a076dc6c8022aedc6648fa523a17178 C1234
+COPYING
+COPYING.1
+EOF
+
+test_expect_success \
+    'validate output from rename/copy detection (#2)' \
+    'compare_diff_raw current expected'
+
+# make sure diff-helper can grok it.
+mv current diff-raw
+GIT_DIFF_OPTS=--unified=0 git-diff-helper -z <diff-raw >current
+cat >expected <<\EOF
+diff --git a/COPYING b/COPYING
+--- a/COPYING
++++ b/COPYING
+@@ -2 +2 @@
+- Note that the only valid version of the GPL as far as this project
++ Note that the only valid version of the G.P.L as far as this project
+@@ -6 +6 @@
+- HOWEVER, in order to allow a migration to GPLv3 if that seems like
++ HOWEVER, in order to allow a migration to G.P.Lv3 if that seems like
+@@ -12 +12 @@
+-	This file is licensed under the GPL v2, or a later version
++	This file is licensed under the G.P.L v2, or a later version
+diff --git a/COPYING b/COPYING.1
+copy from COPYING
+copy to COPYING.1
+--- a/COPYING
++++ b/COPYING.1
+@@ -6 +6 @@
+- HOWEVER, in order to allow a migration to GPLv3 if that seems like
++ However, in order to allow a migration to GPLv3 if that seems like
+EOF
+
+test_expect_success \
+    'validate output from diff-helper (#2)' \
+    'compare_diff_patch current expected'
+
+################################################################
+
+# tree has COPYING and rezrov.  work tree has the same COPYING and
+# copy-edited COPYING.1, and unchanged rezrov.  We should not say
+# anything about rezrov nor COPYING, since the revised again diff-raw
+# nows how to say Copy.
+
+test_expect_success \
+    'prepare work tree once again' \
+    'cat ../../COPYING >COPYING &&
+     git-update-cache --add --remove COPYING COPYING.1'
+
+git-diff-cache -z -C $tree >current
+cat >expected <<\EOF
+:100644 100644 6ff87c4664981e4397625791c8ea3bbb5f2279a3 0603b3238a076dc6c8022aedc6648fa523a17178 C1234
+COPYING
+COPYING.1
+EOF
+
+test_expect_success \
+    'validate output from rename/copy detection (#3)' \
+    'compare_diff_raw current expected'
+
+# make sure diff-helper can grok it.
+mv current diff-raw
+GIT_DIFF_OPTS=--unified=0 git-diff-helper -z <diff-raw >current
+cat >expected <<\EOF
+diff --git a/COPYING b/COPYING.1
+copy from COPYING
+copy to COPYING.1
+--- a/COPYING
++++ b/COPYING.1
+@@ -6 +6 @@
+- HOWEVER, in order to allow a migration to GPLv3 if that seems like
++ However, in order to allow a migration to GPLv3 if that seems like
+EOF
+
+test_expect_success \
+    'validate output from diff-helper (#3)' \
+    'compare_diff_patch current expected'
+
+test_done