Merge branch 'rc/histogram-diff' into HEAD

* rc/histogram-diff:
  xdiff/xhistogram: drop need for additional variable
  xdiff/xhistogram: rely on xdl_trim_ends()
  xdiff/xhistogram: rework handling of recursed results
  xdiff: do away with xdl_mmfile_next()
  Make test number unique
  xdiff/xprepare: use a smaller sample size for histogram diff
  xdiff/xprepare: skip classification
  teach --histogram to diff
  t4033-diff-patience: factor out tests
  xdiff/xpatience: factor out fall-back-diff function
  xdiff/xprepare: refactor abort cleanups
  xdiff/xprepare: use memset()

Conflicts:
	xdiff/xprepare.c

Makefile

@@ -1876,7 +1876,7 @@ ifndef NO_CURL
 	GIT_OBJS += http.o http-walker.o remote-curl.o
 endif
 XDIFF_OBJS = xdiff/xdiffi.o xdiff/xprepare.o xdiff/xutils.o xdiff/xemit.o \
-	xdiff/xmerge.o xdiff/xpatience.o
+	xdiff/xmerge.o xdiff/xpatience.o xdiff/xhistogram.o
 VCSSVN_OBJS = vcs-svn/string_pool.o vcs-svn/line_buffer.o \
 	vcs-svn/repo_tree.o vcs-svn/fast_export.o vcs-svn/svndump.o
 VCSSVN_TEST_OBJS = test-obj-pool.o test-string-pool.o \

diff.c

@@ -3393,6 +3393,8 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 		DIFF_XDL_SET(options, IGNORE_WHITESPACE_AT_EOL);
 	else if (!strcmp(arg, "--patience"))
 		DIFF_XDL_SET(options, PATIENCE_DIFF);
+	else if (!strcmp(arg, "--histogram"))
+		DIFF_XDL_SET(options, HISTOGRAM_DIFF);
 
 	/* flags options */
 	else if (!strcmp(arg, "--binary")) {

merge-recursive.c

@@ -1759,6 +1759,8 @@ int parse_merge_opt(struct merge_options *o, const char *s)
 		o->subtree_shift = s + strlen("subtree=");
 	else if (!strcmp(s, "patience"))
 		o->xdl_opts |= XDF_PATIENCE_DIFF;
+	else if (!strcmp(s, "histogram"))
+		o->xdl_opts |= XDF_HISTOGRAM_DIFF;
 	else if (!strcmp(s, "ignore-space-change"))
 		o->xdl_opts |= XDF_IGNORE_WHITESPACE_CHANGE;
 	else if (!strcmp(s, "ignore-all-space"))

t/lib-diff-alternative.sh

@@ -0,0 +1,165 @@
+#!/bin/sh
+
+test_diff_frobnitz() {
+	cat >file1 <<\EOF
+#include <stdio.h>
+
+// Frobs foo heartily
+int frobnitz(int foo)
+{
+    int i;
+    for(i = 0; i < 10; i++)
+    {
+        printf("Your answer is: ");
+        printf("%d\n", foo);
+    }
+}
+
+int fact(int n)
+{
+    if(n > 1)
+    {
+        return fact(n-1) * n;
+    }
+    return 1;
+}
+
+int main(int argc, char **argv)
+{
+    frobnitz(fact(10));
+}
+EOF
+
+	cat >file2 <<\EOF
+#include <stdio.h>
+
+int fib(int n)
+{
+    if(n > 2)
+    {
+        return fib(n-1) + fib(n-2);
+    }
+    return 1;
+}
+
+// Frobs foo heartily
+int frobnitz(int foo)
+{
+    int i;
+    for(i = 0; i < 10; i++)
+    {
+        printf("%d\n", foo);
+    }
+}
+
+int main(int argc, char **argv)
+{
+    frobnitz(fib(10));
+}
+EOF
+
+	cat >expect <<\EOF
+diff --git a/file1 b/file2
+index 6faa5a3..e3af329 100644
+--- a/file1
++++ b/file2
+@@ -1,26 +1,25 @@
+ #include <stdio.h>
+ 
++int fib(int n)
++{
++    if(n > 2)
++    {
++        return fib(n-1) + fib(n-2);
++    }
++    return 1;
++}
++
+ // Frobs foo heartily
+ int frobnitz(int foo)
+ {
+     int i;
+     for(i = 0; i < 10; i++)
+     {
+-        printf("Your answer is: ");
+         printf("%d\n", foo);
+     }
+ }
+ 
+-int fact(int n)
+-{
+-    if(n > 1)
+-    {
+-        return fact(n-1) * n;
+-    }
+-    return 1;
+-}
+-
+ int main(int argc, char **argv)
+ {
+-    frobnitz(fact(10));
++    frobnitz(fib(10));
+ }
+EOF
+
+	STRATEGY=$1
+
+	test_expect_success "$STRATEGY diff" '
+		test_must_fail git diff --no-index "--$STRATEGY" file1 file2 > output &&
+		test_cmp expect output
+	'
+
+	test_expect_success "$STRATEGY diff output is valid" '
+		mv file2 expect &&
+		git apply < output &&
+		test_cmp expect file2
+	'
+}
+
+test_diff_unique() {
+	cat >uniq1 <<\EOF
+1
+2
+3
+4
+5
+6
+EOF
+
+	cat >uniq2 <<\EOF
+a
+b
+c
+d
+e
+f
+EOF
+
+	cat >expect <<\EOF
+diff --git a/uniq1 b/uniq2
+index b414108..0fdf397 100644
+--- a/uniq1
++++ b/uniq2
+@@ -1,6 +1,6 @@
+-1
+-2
+-3
+-4
+-5
+-6
++a
++b
++c
++d
++e
++f
+EOF
+
+	STRATEGY=$1
+
+	test_expect_success 'completely different files' '
+		test_must_fail git diff --no-index "--$STRATEGY" uniq1 uniq2 > output &&
+		test_cmp expect output
+	'
+}
+

t/t4033-diff-patience.sh

@@ -3,166 +3,10 @@
 test_description='patience diff algorithm'
 
 . ./test-lib.sh
+. "$TEST_DIRECTORY"/lib-diff-alternative.sh
 
-cat >file1 <<\EOF
-#include <stdio.h>
+test_diff_frobnitz "patience"
 
-// Frobs foo heartily
-int frobnitz(int foo)
-{
-    int i;
-    for(i = 0; i < 10; i++)
-    {
-        printf("Your answer is: ");
-        printf("%d\n", foo);
-    }
-}
-
-int fact(int n)
-{
-    if(n > 1)
-    {
-        return fact(n-1) * n;
-    }
-    return 1;
-}
-
-int main(int argc, char **argv)
-{
-    frobnitz(fact(10));
-}
-EOF
-
-cat >file2 <<\EOF
-#include <stdio.h>
-
-int fib(int n)
-{
-    if(n > 2)
-    {
-        return fib(n-1) + fib(n-2);
-    }
-    return 1;
-}
-
-// Frobs foo heartily
-int frobnitz(int foo)
-{
-    int i;
-    for(i = 0; i < 10; i++)
-    {
-        printf("%d\n", foo);
-    }
-}
-
-int main(int argc, char **argv)
-{
-    frobnitz(fib(10));
-}
-EOF
-
-cat >expect <<\EOF
-diff --git a/file1 b/file2
-index 6faa5a3..e3af329 100644
---- a/file1
-+++ b/file2
-@@ -1,26 +1,25 @@
- #include <stdio.h>
- 
-+int fib(int n)
-+{
-+    if(n > 2)
-+    {
-+        return fib(n-1) + fib(n-2);
-+    }
-+    return 1;
-+}
-+
- // Frobs foo heartily
- int frobnitz(int foo)
- {
-     int i;
-     for(i = 0; i < 10; i++)
-     {
--        printf("Your answer is: ");
-         printf("%d\n", foo);
-     }
- }
- 
--int fact(int n)
--{
--    if(n > 1)
--    {
--        return fact(n-1) * n;
--    }
--    return 1;
--}
--
- int main(int argc, char **argv)
- {
--    frobnitz(fact(10));
-+    frobnitz(fib(10));
- }
-EOF
-
-test_expect_success 'patience diff' '
-
-	test_must_fail git diff --no-index --patience file1 file2 > output &&
-	test_cmp expect output
-
-'
-
-test_expect_success 'patience diff output is valid' '
-
-	mv file2 expect &&
-	git apply < output &&
-	test_cmp expect file2
-
-'
-
-cat >uniq1 <<\EOF
-1
-2
-3
-4
-5
-6
-EOF
-
-cat >uniq2 <<\EOF
-a
-b
-c
-d
-e
-f
-EOF
-
-cat >expect <<\EOF
-diff --git a/uniq1 b/uniq2
-index b414108..0fdf397 100644
---- a/uniq1
-+++ b/uniq2
-@@ -1,6 +1,6 @@
--1
--2
--3
--4
--5
--6
-+a
-+b
-+c
-+d
-+e
-+f
-EOF
-
-test_expect_success 'completely different files' '
-
-	test_must_fail git diff --no-index --patience uniq1 uniq2 > output &&
-	test_cmp expect output
-
-'
+test_diff_unique "patience"
 
 test_done

t/t4050-diff-histogram.sh

@@ -0,0 +1,12 @@
+#!/bin/sh
+
+test_description='histogram diff algorithm'
+
+. ./test-lib.sh
+. "$TEST_DIRECTORY"/lib-diff-alternative.sh
+
+test_diff_frobnitz "histogram"
+
+test_diff_unique "histogram"
+
+test_done

xdiff/xdiff.h

@@ -33,6 +33,7 @@ extern "C" {
 #define XDF_IGNORE_WHITESPACE_CHANGE (1 << 3)
 #define XDF_IGNORE_WHITESPACE_AT_EOL (1 << 4)
 #define XDF_PATIENCE_DIFF (1 << 5)
+#define XDF_HISTOGRAM_DIFF (1 << 6)
 #define XDF_WHITESPACE_FLAGS (XDF_IGNORE_WHITESPACE | XDF_IGNORE_WHITESPACE_CHANGE | XDF_IGNORE_WHITESPACE_AT_EOL)
 
 #define XDL_PATCH_NORMAL '-'
@@ -105,7 +106,6 @@ typedef struct s_bdiffparam {
 #define xdl_realloc(ptr,x) realloc(ptr,x)
 
 void *xdl_mmfile_first(mmfile_t *mmf, long *size);
-void *xdl_mmfile_next(mmfile_t *mmf, long *size);
 long xdl_mmfile_size(mmfile_t *mmf);
 
 int xdl_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,