Merge branch 'jk/diff-convfilter-test-fix'

* jk/diff-convfilter-test-fix:
  Avoid using non-portable `echo -n` in tests.
  add userdiff textconv tests
  document the diff driver textconv feature
  diff: add missing static declaration

Conflicts:
	Documentation/gitattributes.txt

7 files changed, 178 insertions, 20 deletions

diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt
index eb648418ee..a172baf993 100644
--- a/Documentation/gitattributes.txt
+++ b/Documentation/gitattributes.txt
@@ -216,10 +216,12 @@ Generating diff text
 `diff`
 ^^^^^^
 
-The attribute `diff` affects if 'git-diff' generates textual
-patch for the path or just says `Binary files differ`.  It also
-can affect what line is shown on the hunk header `@@ -k,l +n,m @@`
-line.
+The attribute `diff` affects how 'git' generates diffs for particular
+files. It can tell git whether to generate a textual patch for the path
+or to treat the path as a binary file.  It can also affect what line is
+shown on the hunk header `@@ -k,l +n,m @@` line, tell git to use an
+external command to generate the diff, or ask git to convert binary
+files to a text format before generating the diff.
 
 Set::
 
@@ -230,7 +232,8 @@ Set::
 Unset::
 
 	A path to which the `diff` attribute is unset will
-	generate `Binary files differ`.
+	generate `Binary files differ` (or a binary patch, if
+	binary patches are enabled).
 
 Unspecified::
 
@@ -241,21 +244,21 @@ Unspecified::
 
 String::
 
-	Diff is shown using the specified custom diff driver.
-	The driver program is given its input using the same
-	calling convention as used for GIT_EXTERNAL_DIFF
-	program.  This name is also used for custom hunk header
-	selection.
+	Diff is shown using the specified diff driver.  Each driver may
+	specify one or more options, as described in the following
+	section. The options for the diff driver "foo" are defined
+	by the configuration variables in the "diff.foo" section of the
+	git config file.
 
 
-Defining a custom diff driver
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+Defining an external diff driver
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 The definition of a diff driver is done in `gitconfig`, not
 `gitattributes` file, so strictly speaking this manual page is a
 wrong place to talk about it.  However...
 
-To define a custom diff driver `jcdiff`, add a section to your
+To define an external diff driver `jcdiff`, add a section to your
 `$GIT_DIR/config` file (or `$HOME/.gitconfig` file) like this:
 
 ----------------------------------------------------------------
@@ -331,6 +334,43 @@ patterns are available:
 - `tex` suitable for source code for LaTeX documents.
 
 
+Performing text diffs of binary files
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Sometimes it is desirable to see the diff of a text-converted
+version of some binary files. For example, a word processor
+document can be converted to an ASCII text representation, and
+the diff of the text shown. Even though this conversion loses
+some information, the resulting diff is useful for human
+viewing (but cannot be applied directly).
+
+The `textconv` config option is used to define a program for
+performing such a conversion. The program should take a single
+argument, the name of a file to convert, and produce the
+resulting text on stdout.
+
+For example, to show the diff of the exif information of a
+file instead of the binary information (assuming you have the
+exif tool installed):
+
+------------------------
+[diff "jpg"]
+	textconv = exif
+------------------------
+
+NOTE: The text conversion is generally a one-way conversion;
+in this example, we lose the actual image contents and focus
+just on the text data. This means that diffs generated by
+textconv are _not_ suitable for applying. For this reason,
+only `git diff` and the `git log` family of commands (i.e.,
+log, whatchanged, show) will perform text conversion. `git
+format-patch` will never generate this output. If you want to
+send somebody a text-converted diff of a binary file (e.g.,
+because it quickly conveys the changes you have made), you
+should generate it separately and send it as a comment _in
+addition to_ the usual binary diff that you might send.
+
+
 Performing a three-way merge
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
diff --git a/diff.c b/diff.c
index 1918b73d53..3e6c752bb7 100644
--- a/diff.c
+++ b/diff.c
@@ -1283,7 +1283,7 @@ static void emit_binary_diff(FILE *file, mmfile_t *one, mmfile_t *two)
 	emit_binary_diff_body(file, two, one);
 }
 
-void diff_filespec_load_driver(struct diff_filespec *one)
+static void diff_filespec_load_driver(struct diff_filespec *one)
 {
 	if (!one->driver)
 		one->driver = userdiff_find_by_path(one->path);
diff --git a/t/t2005-checkout-index-symlinks.sh b/t/t2005-checkout-index-symlinks.sh
index ed12c4d782..9fa5610474 100755
--- a/t/t2005-checkout-index-symlinks.sh
+++ b/t/t2005-checkout-index-symlinks.sh
@@ -13,7 +13,7 @@ file if core.symlinks is false.'
 test_expect_success \
 'preparation' '
 git config core.symlinks false &&
-l=$(echo -n file | git hash-object -t blob -w --stdin) &&
+l=$(printf file | git hash-object -t blob -w --stdin) &&
 echo "120000 $l	symlink" | git update-index --index-info'
 
 test_expect_success \
diff --git a/t/t2102-update-index-symlinks.sh b/t/t2102-update-index-symlinks.sh
index f195aefe3a..1ed44ee503 100755
--- a/t/t2102-update-index-symlinks.sh
+++ b/t/t2102-update-index-symlinks.sh
@@ -13,12 +13,12 @@ even if a plain file is in the working tree if core.symlinks is false.'
 test_expect_success \
 'preparation' '
 git config core.symlinks false &&
-l=$(echo -n file | git hash-object -t blob -w --stdin) &&
+l=$(printf file | git hash-object -t blob -w --stdin) &&
 echo "120000 $l	symlink" | git update-index --index-info'
 
 test_expect_success \
 'modify the symbolic link' '
-echo -n new-file > symlink &&
+printf new-file > symlink &&
 git update-index symlink'
 
 test_expect_success \
diff --git a/t/t4030-diff-textconv.sh b/t/t4030-diff-textconv.sh
new file mode 100755
index 0000000000..3aed1bbdfe
--- /dev/null
+++ b/t/t4030-diff-textconv.sh
@@ -0,0 +1,118 @@
+#!/bin/sh
+
+test_description='diff.*.textconv tests'
+. ./test-lib.sh
+
+find_diff() {
+	sed '1,/^index /d' | sed '/^-- $/,$d'
+}
+
+cat >expect.binary <<'EOF'
+Binary files a/file and b/file differ
+EOF
+
+cat >expect.text <<'EOF'
+--- a/file
++++ b/file
+@@ -1 +1,2 @@
+ 0
++1
+EOF
+
+cat >hexdump <<'EOF'
+#!/bin/sh
+perl -e '$/ = undef; $_ = <>; s/./ord($&)/ge; print $_' "$1"
+EOF
+chmod +x hexdump
+
+test_expect_success 'setup binary file with history' '
+	printf "\\0\\n" >file &&
+	git add file &&
+	git commit -m one &&
+	printf "\\1\\n" >>file &&
+	git add file &&
+	git commit -m two
+'
+
+test_expect_success 'file is considered binary by porcelain' '
+	git diff HEAD^ HEAD >diff &&
+	find_diff <diff >actual &&
+	test_cmp expect.binary actual
+'
+
+test_expect_success 'file is considered binary by plumbing' '
+	git diff-tree -p HEAD^ HEAD >diff &&
+	find_diff <diff >actual &&
+	test_cmp expect.binary actual
+'
+
+test_expect_success 'setup textconv filters' '
+	echo file diff=foo >.gitattributes &&
+	git config diff.foo.textconv "$PWD"/hexdump &&
+	git config diff.fail.textconv false
+'
+
+test_expect_failure 'diff produces text' '
+	git diff HEAD^ HEAD >diff &&
+	find_diff <diff >actual &&
+	test_cmp expect.text actual
+'
+
+test_expect_success 'diff-tree produces binary' '
+	git diff-tree -p HEAD^ HEAD >diff &&
+	find_diff <diff >actual &&
+	test_cmp expect.binary actual
+'
+
+test_expect_failure 'log produces text' '
+	git log -1 -p >log &&
+	find_diff <log >actual &&
+	test_cmp expect.text actual
+'
+
+test_expect_failure 'format-patch produces binary' '
+	git format-patch --no-binary --stdout HEAD^ >patch &&
+	find_diff <patch >actual &&
+	test_cmp expect.binary actual
+'
+
+cat >expect.stat <<'EOF'
+ file |  Bin 2 -> 4 bytes
+ 1 files changed, 0 insertions(+), 0 deletions(-)
+EOF
+test_expect_failure 'diffstat does not run textconv' '
+	echo file diff=fail >.gitattributes &&
+	git diff --stat HEAD^ HEAD >actual &&
+	test_cmp expect.stat actual
+'
+# restore working setup
+echo file diff=foo >.gitattributes
+
+cat >expect.typechange <<'EOF'
+--- a/file
++++ /dev/null
+@@ -1,2 +0,0 @@
+-0
+-1
+diff --git a/file b/file
+new file mode 120000
+index ad8b3d2..67be421
+--- /dev/null
++++ b/file
+@@ -0,0 +1 @@
++frotz
+\ No newline at end of file
+EOF
+# make a symlink the hard way that works on symlink-challenged file systems
+test_expect_failure 'textconv does not act on symlinks' '
+	printf frotz > file &&
+	git add file &&
+	git ls-files -s | sed -e s/100644/120000/ |
+		git update-index --index-info &&
+	git commit -m typechange &&
+	git show >diff &&
+	find_diff <diff >actual &&
+	test_cmp expect.typechange actual
+'
+
+test_done
diff --git a/t/t6025-merge-symlinks.sh b/t/t6025-merge-symlinks.sh
index 53892a555c..433c4de08f 100755
--- a/t/t6025-merge-symlinks.sh
+++ b/t/t6025-merge-symlinks.sh
@@ -18,11 +18,11 @@ git add file &&
 git commit -m initial &&
 git branch b-symlink &&
 git branch b-file &&
-l=$(echo -n file | git hash-object -t blob -w --stdin) &&
+l=$(printf file | git hash-object -t blob -w --stdin) &&
 echo "120000 $l	symlink" | git update-index --index-info &&
 git commit -m master &&
 git checkout b-symlink &&
-l=$(echo -n file-different | git hash-object -t blob -w --stdin) &&
+l=$(printf file-different | git hash-object -t blob -w --stdin) &&
 echo "120000 $l	symlink" | git update-index --index-info &&
 git commit -m b-symlink &&
 git checkout b-file &&
diff --git a/t/t9400-git-cvsserver-server.sh b/t/t9400-git-cvsserver-server.sh
index c1850d2923..6a37f71d11 100755
--- a/t/t9400-git-cvsserver-server.sh
+++ b/t/t9400-git-cvsserver-server.sh
@@ -424,7 +424,7 @@ cd "$WORKDIR"
 test_expect_success 'cvs update (-p)' '
     touch really-empty &&
     echo Line 1 > no-lf &&
-    echo -n Line 2 >> no-lf &&
+    printf "Line 2" >> no-lf &&
     git add really-empty no-lf &&
     git commit -q -m "Update -p test" &&
     git push gitcvs.git >/dev/null &&