[PATCH v2] merge-file: add --diff-algorithm option

["Antonin Delpeuch via GitGitGadget" <gitgitgadget@gmail.com>]

From: Antonin Delpeuch <antonin@delpeuch.eu>

This makes it possible to use other diff algorithms than the 'myers'
default algorithm, when using the 'git merge-file' command. This helps
avoid spurious conflicts by selecting a more recent algorithm such as
'histogram', for instance when using 'git merge-file' as part of a custom
merge driver.

Signed-off-by: Antonin Delpeuch <antonin@delpeuch.eu>
Reviewed-by: Phillip Wood <phillip.wood@dunelm.org.uk>
---
    merge-file: add --diff-algorithm option
    
    Changes since v1:
    
     * improve commit message to mention the use case of custom merge
       drivers
     * improve documentation to show available options and recommend
       switching to "histogram"
     * add tests
    
    I have left out:
    
     * switching the default to "histogram", because it should only be done
       in a subsequent release
     * adding a configuration variable to control this option, because I was
       not sure how to call it. Perhaps "merge-file.diffAlgorithm"?

Published-As: https://github.com/gitgitgadget/git/releases/tag/pr-git-1606%2Fwetneb%2Fmerge_file_configurable_diff_algorithm-v2
Fetch-It-Via: git fetch https://github.com/gitgitgadget/git pr-git-1606/wetneb/merge_file_configurable_diff_algorithm-v2
Pull-Request: https://github.com/git/git/pull/1606

Range-diff vs v1:

 1:  4aa453e30be ! 1:  842b5abf33c merge-file: add --diff-algorithm option
     @@ Commit message
          merge-file: add --diff-algorithm option
      
          This makes it possible to use other diff algorithms than the 'myers'
     -    default algorithm, when using the 'git merge-file' command.
     +    default algorithm, when using the 'git merge-file' command. This helps
     +    avoid spurious conflicts by selecting a more recent algorithm such as
     +    'histogram', for instance when using 'git merge-file' as part of a custom
     +    merge driver.
      
          Signed-off-by: Antonin Delpeuch <antonin@delpeuch.eu>
     +    Reviewed-by: Phillip Wood <phillip.wood@dunelm.org.uk>
      
       ## Documentation/git-merge-file.txt ##
      @@ Documentation/git-merge-file.txt: object store and the object ID of its blob is written to standard output.
       	Instead of leaving conflicts in the file, resolve conflicts
       	favouring our (or their or both) side of the lines.
       
     -+--diff-algorithm <algorithm>::
     -+	Use a different diff algorithm while merging, which can help
     ++--diff-algorithm={patience|minimal|histogram|myers}::
     ++	Use a different diff algorithm while merging. The current default is "myers",
     ++	but selecting more recent algorithm such as "histogram" can help
      +	avoid mismerges that occur due to unimportant matching lines
     -+	(such as braces from distinct functions).  See also
     ++	(such as braces from distinct functions). See also
      +	linkgit:git-diff[1] `--diff-algorithm`.
       
       EXAMPLES
     @@ builtin/merge-file.c: int cmd_merge_file(int argc, const char **argv, const char
       		OPT_INTEGER(0, "marker-size", &xmp.marker_size,
       			    N_("for conflicts, use this marker size")),
       		OPT__QUIET(&quiet, N_("do not warn about conflicts")),
     +
     + ## t/t6403-merge-file.sh ##
     +@@ t/t6403-merge-file.sh: test_expect_success 'setup' '
     + 	deduxit me super semitas jusitiae,
     + 	EOF
     + 
     +-	printf "propter nomen suum." >>new4.txt
     ++	printf "propter nomen suum." >>new4.txt &&
     ++
     ++	cat >base.c <<-\EOF &&
     ++	int f(int x, int y)
     ++	{
     ++		if (x == 0)
     ++		{
     ++			return y;
     ++		}
     ++		return x;
     ++	}
     ++
     ++	int g(size_t u)
     ++	{
     ++		while (u < 30)
     ++		{
     ++			u++;
     ++		}
     ++		return u;
     ++	}
     ++	EOF
     ++
     ++	cat >ours.c <<-\EOF &&
     ++	int g(size_t u)
     ++	{
     ++		while (u < 30)
     ++		{
     ++			u++;
     ++		}
     ++		return u;
     ++	}
     ++
     ++	int h(int x, int y, int z)
     ++	{
     ++		if (z == 0)
     ++		{
     ++			return x;
     ++		}
     ++		return y;
     ++	}
     ++	EOF
     ++
     ++	cat >theirs.c <<-\EOF
     ++	int f(int x, int y)
     ++	{
     ++		if (x == 0)
     ++		{
     ++			return y;
     ++		}
     ++		return x;
     ++	}
     ++
     ++	int g(size_t u)
     ++	{
     ++		while (u > 34)
     ++		{
     ++			u--;
     ++		}
     ++		return u;
     ++	}
     ++	EOF
     + '
     + 
     + test_expect_success 'merge with no changes' '
     +@@ t/t6403-merge-file.sh: test_expect_success '--object-id fails without repository' '
     + 	grep "not a git repository" err
     + '
     + 
     ++test_expect_success 'merging C files with "myers" diff algorithm creates some spurious conflicts' '
     ++	cat >expect.c <<-\EOF &&
     ++	int g(size_t u)
     ++	{
     ++		while (u < 30)
     ++		{
     ++			u++;
     ++		}
     ++		return u;
     ++	}
     ++
     ++	int h(int x, int y, int z)
     ++	{
     ++	<<<<<<< ours.c
     ++		if (z == 0)
     ++	||||||| base.c
     ++		while (u < 30)
     ++	=======
     ++		while (u > 34)
     ++	>>>>>>> theirs.c
     ++		{
     ++	<<<<<<< ours.c
     ++			return x;
     ++	||||||| base.c
     ++			u++;
     ++	=======
     ++			u--;
     ++	>>>>>>> theirs.c
     ++		}
     ++		return y;
     ++	}
     ++	EOF
     ++
     ++	test_must_fail git merge-file -p --diff3 --diff-algorithm myers ours.c base.c theirs.c >myers_output.c &&
     ++	test_cmp expect.c myers_output.c
     ++'
     ++
     ++test_expect_success 'merging C files with "histogram" diff algorithm avoids some spurious conflicts' '
     ++	cat >expect.c <<-\EOF &&
     ++	int g(size_t u)
     ++	{
     ++		while (u > 34)
     ++		{
     ++			u--;
     ++		}
     ++		return u;
     ++	}
     ++
     ++	int h(int x, int y, int z)
     ++	{
     ++		if (z == 0)
     ++		{
     ++			return x;
     ++		}
     ++		return y;
     ++	}
     ++	EOF
     ++
     ++	git merge-file -p --diff3 --diff-algorithm histogram ours.c base.c theirs.c >histogram_output.c &&
     ++	test_cmp expect.c histogram_output.c
     ++'
     ++
     + test_done


 Documentation/git-merge-file.txt |   6 ++
 builtin/merge-file.c             |  28 +++++++
 t/t6403-merge-file.sh            | 124 ++++++++++++++++++++++++++++++-
 3 files changed, 157 insertions(+), 1 deletion(-)

diff --git a/Documentation/git-merge-file.txt b/Documentation/git-merge-file.txt
index 6a081eacb72..71915a00fa4 100644
--- a/Documentation/git-merge-file.txt
+++ b/Documentation/git-merge-file.txt
@@ -92,6 +92,12 @@ object store and the object ID of its blob is written to standard output.
 	Instead of leaving conflicts in the file, resolve conflicts
 	favouring our (or their or both) side of the lines.
 
+--diff-algorithm={patience|minimal|histogram|myers}::
+	Use a different diff algorithm while merging. The current default is "myers",
+	but selecting more recent algorithm such as "histogram" can help
+	avoid mismerges that occur due to unimportant matching lines
+	(such as braces from distinct functions). See also
+	linkgit:git-diff[1] `--diff-algorithm`.
 
 EXAMPLES
 --------
diff --git a/builtin/merge-file.c b/builtin/merge-file.c
index 832c93d8d54..1f987334a31 100644
--- a/builtin/merge-file.c
+++ b/builtin/merge-file.c
@@ -1,5 +1,6 @@
 #include "builtin.h"
 #include "abspath.h"
+#include "diff.h"
 #include "hex.h"
 #include "object-name.h"
 #include "object-store.h"
@@ -28,6 +29,30 @@ static int label_cb(const struct option *opt, const char *arg, int unset)
 	return 0;
 }
 
+static int set_diff_algorithm(xpparam_t *xpp,
+			      const char *alg)
+{
+	long diff_algorithm = parse_algorithm_value(alg);
+	if (diff_algorithm < 0)
+		return -1;
+	xpp->flags = (xpp->flags & ~XDF_DIFF_ALGORITHM_MASK) | diff_algorithm;
+	return 0;
+}
+
+static int diff_algorithm_cb(const struct option *opt,
+				const char *arg, int unset)
+{
+	xpparam_t *xpp = opt->value;
+
+	BUG_ON_OPT_NEG(unset);
+
+	if (set_diff_algorithm(xpp, arg))
+		return error(_("option diff-algorithm accepts \"myers\", "
+			       "\"minimal\", \"patience\" and \"histogram\""));
+
+	return 0;
+}
+
 int cmd_merge_file(int argc, const char **argv, const char *prefix)
 {
 	const char *names[3] = { 0 };
@@ -48,6 +73,9 @@ int cmd_merge_file(int argc, const char **argv, const char *prefix)
 			    XDL_MERGE_FAVOR_THEIRS),
 		OPT_SET_INT(0, "union", &xmp.favor, N_("for conflicts, use a union version"),
 			    XDL_MERGE_FAVOR_UNION),
+		OPT_CALLBACK_F(0, "diff-algorithm", &xmp.xpp, N_("<algorithm>"),
+			     N_("choose a diff algorithm"),
+			     PARSE_OPT_NONEG, diff_algorithm_cb),
 		OPT_INTEGER(0, "marker-size", &xmp.marker_size,
 			    N_("for conflicts, use this marker size")),
 		OPT__QUIET(&quiet, N_("do not warn about conflicts")),
diff --git a/t/t6403-merge-file.sh b/t/t6403-merge-file.sh
index 2c92209ecab..fb872c5a113 100755
--- a/t/t6403-merge-file.sh
+++ b/t/t6403-merge-file.sh
@@ -56,7 +56,67 @@ test_expect_success 'setup' '
 	deduxit me super semitas jusitiae,
 	EOF
 
-	printf "propter nomen suum." >>new4.txt
+	printf "propter nomen suum." >>new4.txt &&
+
+	cat >base.c <<-\EOF &&
+	int f(int x, int y)
+	{
+		if (x == 0)
+		{
+			return y;
+		}
+		return x;
+	}
+
+	int g(size_t u)
+	{
+		while (u < 30)
+		{
+			u++;
+		}
+		return u;
+	}
+	EOF
+
+	cat >ours.c <<-\EOF &&
+	int g(size_t u)
+	{
+		while (u < 30)
+		{
+			u++;
+		}
+		return u;
+	}
+
+	int h(int x, int y, int z)
+	{
+		if (z == 0)
+		{
+			return x;
+		}
+		return y;
+	}
+	EOF
+
+	cat >theirs.c <<-\EOF
+	int f(int x, int y)
+	{
+		if (x == 0)
+		{
+			return y;
+		}
+		return x;
+	}
+
+	int g(size_t u)
+	{
+		while (u > 34)
+		{
+			u--;
+		}
+		return u;
+	}
+	EOF
 '
 
 test_expect_success 'merge with no changes' '
@@ -447,4 +507,66 @@ test_expect_success '--object-id fails without repository' '
 	grep "not a git repository" err
 '
 
+test_expect_success 'merging C files with "myers" diff algorithm creates some spurious conflicts' '
+	cat >expect.c <<-\EOF &&
+	int g(size_t u)
+	{
+		while (u < 30)
+		{
+			u++;
+		}
+		return u;
+	}
+
+	int h(int x, int y, int z)
+	{
+	<<<<<<< ours.c
+		if (z == 0)
+	||||||| base.c
+		while (u < 30)
+	=======
+		while (u > 34)
+	>>>>>>> theirs.c
+		{
+	<<<<<<< ours.c
+			return x;
+	||||||| base.c
+			u++;
+	=======
+			u--;
+	>>>>>>> theirs.c
+		}
+		return y;
+	}
+	EOF
+
+	test_must_fail git merge-file -p --diff3 --diff-algorithm myers ours.c base.c theirs.c >myers_output.c &&
+	test_cmp expect.c myers_output.c
+'
+
+test_expect_success 'merging C files with "histogram" diff algorithm avoids some spurious conflicts' '
+	cat >expect.c <<-\EOF &&
+	int g(size_t u)
+	{
+		while (u > 34)
+		{
+			u--;
+		}
+		return u;
+	}
+
+	int h(int x, int y, int z)
+	{
+		if (z == 0)
+		{
+			return x;
+		}
+		return y;
+	}
+	EOF
+
+	git merge-file -p --diff3 --diff-algorithm histogram ours.c base.c theirs.c >histogram_output.c &&
+	test_cmp expect.c histogram_output.c
+'
+
 test_done

base-commit: 98009afd24e2304bf923a64750340423473809ff
-- 
gitgitgadget