Refine pluggable similarity API

This plugs in the three basic similarity strategies for handling
whitespace via internal use of the pluggable API.  In so doing, I
realized that the use of git_buf in the hashsig API was not needed
and actually just made it harder to use, so I tweaked that API as
well.

Note that the similarity metric is still not hooked up in the
find_similarity code - this is just setting out the function that
will be used.

include/git2/diff.h

@@ -387,20 +387,46 @@ typedef enum {
 
 	/** split large rewrites into delete/add pairs (`--break-rewrites=/M`) */
 	GIT_DIFF_FIND_AND_BREAK_REWRITES = (1 << 4),
+
+	/** measure similarity ignoring leading whitespace (default) */
+	GIT_DIFF_FIND_IGNORE_LEADING_WHITESPACE = 0,
+	/** measure similarity ignoring all whitespace */
+	GIT_DIFF_FIND_IGNORE_WHITESPACE = (1 << 6),
+	/** measure similarity including all data */
+	GIT_DIFF_FIND_DONT_IGNORE_WHITESPACE = (1 << 7),
 } git_diff_find_t;
 
 /**
  * Pluggable similarity metric
  */
 typedef struct {
-	int (*calc_signature)(void **out, const git_diff_file *file, void *payload);
+	int (*file_signature)(
+		void **out, const git_diff_file *file,
+		const char *fullpath, void *payload);
+	int (*buffer_signature)(
+		void **out, const git_diff_file *file,
+		const char *buf, size_t buflen, void *payload);
 	void (*free_signature)(void *sig, void *payload);
-	int (*calc_similarity)(int *score, void *siga, void *sigb, void *payload);
+	int (*similarity)(int *score, void *siga, void *sigb, void *payload);
 	void *payload;
 } git_diff_similarity_metric;
 
 /**
  * Control behavior of rename and copy detection
+ *
+ * These options mostly mimic parameters that can be passed to git-diff.
+ *
+ * - `rename_threshold` is the same as the -M option with a value
+ * - `copy_threshold` is the same as the -C option with a value
+ * - `rename_from_rewrite_threshold` matches the top of the -B option
+ * - `break_rewrite_threshold` matches the bottom of the -B option
+ * - `target_limit` matches the -l option
+ *
+ * The `metric` option allows you to plug in a custom similarity metric.
+ * Set it to NULL for the default internal metric which is based on sampling
+ * hashes of ranges of data in the file.  The default metric is a pretty
+ * good similarity approximation that should work fairly well for both text
+ * and binary data, and is pretty fast with fixed memory overhead.
  */
 typedef struct {
 	unsigned int version;

src/diff_tform.c

@@ -169,6 +169,60 @@ int git_diff_merge(
 	return error;
 }
 
+#define FIND_SIMILAR_HASHSIG(NAME,OPT) \
+	static int find_similar__hashsig_for_file ## NAME( \
+		void **out, const git_diff_file *f, const char *path, void *p) { \
+		GIT_UNUSED(f); GIT_UNUSED(p); \
+		return git_hashsig_create_fromfile((git_hashsig **)out, path, OPT); \
+	} \
+	static int find_similar__hashsig_for_buf ## NAME( \
+		void **out, const git_diff_file *f, const char *buf, size_t len, void *p) { \
+		GIT_UNUSED(f); GIT_UNUSED(p); \
+		return git_hashsig_create((git_hashsig **)out, buf, len, OPT); \
+	}
+
+FIND_SIMILAR_HASHSIG(_default, GIT_HASHSIG_SMART_WHITESPACE);
+FIND_SIMILAR_HASHSIG(_ignore_whitespace, GIT_HASHSIG_IGNORE_WHITESPACE);
+FIND_SIMILAR_HASHSIG(_include_whitespace, GIT_HASHSIG_NORMAL);
+
+static void find_similar__hashsig_free(void *sig, void *payload)
+{
+	GIT_UNUSED(payload);
+	git_hashsig_free(sig);
+}
+
+static int find_similar__calc_similarity(
+	int *score, void *siga, void *sigb, void *payload)
+{
+	GIT_UNUSED(payload);
+	*score = git_hashsig_compare(siga, sigb);
+	return 0;
+}
+
+static git_diff_similarity_metric find_similar__internal_metrics[3] = {
+	{
+		find_similar__hashsig_for_file_default,
+		find_similar__hashsig_for_buf_default,
+		find_similar__hashsig_free,
+		find_similar__calc_similarity,
+		NULL
+	},
+	{
+		find_similar__hashsig_for_file_ignore_whitespace,
+		find_similar__hashsig_for_buf_ignore_whitespace,
+		find_similar__hashsig_free,
+		find_similar__calc_similarity,
+		NULL
+	},
+	{
+		find_similar__hashsig_for_file_include_whitespace,
+		find_similar__hashsig_for_buf_include_whitespace,
+		find_similar__hashsig_free,
+		find_similar__calc_similarity,
+		NULL
+	}
+};
+
 #define DEFAULT_THRESHOLD 50
 #define DEFAULT_BREAK_REWRITE_THRESHOLD 60
 #define DEFAULT_TARGET_LIMIT 200
@@ -237,6 +291,16 @@ static int normalize_find_opts(
 			opts->target_limit = limit;
 	}
 
+	/* for now, always assign the same internal metric */
+	if (!opts->metric) {
+		if (opts->flags & GIT_DIFF_FIND_IGNORE_WHITESPACE)
+			opts->metric = &find_similar__internal_metrics[1];
+		else if (opts->flags & GIT_DIFF_FIND_DONT_IGNORE_WHITESPACE)
+			opts->metric = &find_similar__internal_metrics[2];
+		else
+			opts->metric = &find_similar__internal_metrics[0];
+	}
+
 	return 0;
 }
 

src/hashsig.c

@@ -266,7 +266,8 @@ static git_hashsig *hashsig_alloc(git_hashsig_option_t opts)
 
 int git_hashsig_create(
 	git_hashsig **out,
-	const git_buf *buf,
+	const char *buf,
+	size_t buflen,
 	git_hashsig_option_t opts)
 {
 	int error;
@@ -274,7 +275,7 @@ int git_hashsig_create(
 	git_hashsig *sig = hashsig_alloc(opts);
 	GITERR_CHECK_ALLOC(sig);
 
-	error = hashsig_add_hashes(sig, buf->ptr, buf->size, &prog);
+	error = hashsig_add_hashes(sig, buf, buflen, &prog);
 
 	if (!error)
 		error = hashsig_finalize_hashes(sig);

src/hashsig.h

@@ -7,7 +7,7 @@
 #ifndef INCLUDE_hashsig_h__
 #define INCLUDE_hashsig_h__
 
-#include "buffer.h"
+#include "common.h"
 
 /**
  * Similarity signature of line hashes for a buffer
@@ -32,11 +32,13 @@ typedef enum {
  *
  * @param out The array of hashed runs representing the file content
  * @param buf The contents of the file to hash
+ * @param buflen The length of the data at `buf`
  * @param generate_pairwise_hashes Should pairwise runs be hashed
  */
 extern int git_hashsig_create(
 	git_hashsig **out,
-	const git_buf *buf,
+	const char *buf,
+	size_t buflen,
 	git_hashsig_option_t opts);
 
 /**

tests-clar/core/buffer.c

@@ -748,8 +748,8 @@ void test_core_buffer__similarity_metric(void)
 	/* in the first case, we compare data to itself and expect 100% match */
 
 	cl_git_pass(git_buf_sets(&buf, SIMILARITY_TEST_DATA_1));
-	cl_git_pass(git_hashsig_create(&a, &buf, GIT_HASHSIG_NORMAL));
-	cl_git_pass(git_hashsig_create(&b, &buf, GIT_HASHSIG_NORMAL));
+	cl_git_pass(git_hashsig_create(&a, buf.ptr, buf.size, GIT_HASHSIG_NORMAL));
+	cl_git_pass(git_hashsig_create(&b, buf.ptr, buf.size, GIT_HASHSIG_NORMAL));
 
 	cl_assert_equal_i(100, git_hashsig_compare(a, b));
 
@@ -759,13 +759,13 @@ void test_core_buffer__similarity_metric(void)
 	/* if we change just a single byte, how much does that change magnify? */
 
 	cl_git_pass(git_buf_sets(&buf, SIMILARITY_TEST_DATA_1));
-	cl_git_pass(git_hashsig_create(&a, &buf, GIT_HASHSIG_NORMAL));
+	cl_git_pass(git_hashsig_create(&a, buf.ptr, buf.size, GIT_HASHSIG_NORMAL));
 	cl_git_pass(git_buf_sets(&buf,
 		"Test data\nright here\ninline\ntada\nneeds more data\nlots of data\n"
 		"is this enough?\nthere has to be enough data to fill the hash array!\n"
 		"Apparently 191 bytes is the minimum amount of data needed.\nHere goes!\n"
 		 "Let's make sure we've got plenty to go with here.\n   smile   \n"));
-	cl_git_pass(git_hashsig_create(&b, &buf, GIT_HASHSIG_NORMAL));
+	cl_git_pass(git_hashsig_create(&b, buf.ptr, buf.size, GIT_HASHSIG_NORMAL));
 
 	sim = git_hashsig_compare(a, b);
 
@@ -777,10 +777,10 @@ void test_core_buffer__similarity_metric(void)
 	/* let's try comparing data to a superset of itself */
 
 	cl_git_pass(git_buf_sets(&buf, SIMILARITY_TEST_DATA_1));
-	cl_git_pass(git_hashsig_create(&a, &buf, GIT_HASHSIG_NORMAL));
+	cl_git_pass(git_hashsig_create(&a, buf.ptr, buf.size, GIT_HASHSIG_NORMAL));
 	cl_git_pass(git_buf_sets(&buf, SIMILARITY_TEST_DATA_1
 		"and if I add some more, it should still be pretty similar, yes?\n"));
-	cl_git_pass(git_hashsig_create(&b, &buf, GIT_HASHSIG_NORMAL));
+	cl_git_pass(git_hashsig_create(&b, buf.ptr, buf.size, GIT_HASHSIG_NORMAL));
 
 	sim = git_hashsig_compare(a, b);
 
@@ -792,13 +792,13 @@ void test_core_buffer__similarity_metric(void)
 	/* what if we keep about half the original data and add half new */
 
 	cl_git_pass(git_buf_sets(&buf, SIMILARITY_TEST_DATA_1));
-	cl_git_pass(git_hashsig_create(&a, &buf, GIT_HASHSIG_NORMAL));
+	cl_git_pass(git_hashsig_create(&a, buf.ptr, buf.size, GIT_HASHSIG_NORMAL));
 	cl_git_pass(git_buf_sets(&buf,
 		"test data\nright here\ninline\ntada\nneeds more data\nlots of data\n"
 		"is this enough?\nthere has to be enough data to fill the hash array!\n"
 		"okay, that's half the original\nwhat else can we add?\nmore data\n"
 		 "one more line will complete this\nshort\nlines\ndon't\nmatter\n"));
-	cl_git_pass(git_hashsig_create(&b, &buf, GIT_HASHSIG_NORMAL));
+	cl_git_pass(git_hashsig_create(&b, buf.ptr, buf.size, GIT_HASHSIG_NORMAL));
 
 	sim = git_hashsig_compare(a, b);
 
@@ -810,7 +810,7 @@ void test_core_buffer__similarity_metric(void)
 	/* lastly, let's check that we can hash file content as well */
 
 	cl_git_pass(git_buf_sets(&buf, SIMILARITY_TEST_DATA_1));
-	cl_git_pass(git_hashsig_create(&a, &buf, GIT_HASHSIG_NORMAL));
+	cl_git_pass(git_hashsig_create(&a, buf.ptr, buf.size, GIT_HASHSIG_NORMAL));
 
 	cl_git_pass(git_futils_mkdir("scratch", NULL, 0755, GIT_MKDIR_PATH));
 	cl_git_mkfile("scratch/testdata", SIMILARITY_TEST_DATA_1);
@@ -880,10 +880,10 @@ void test_core_buffer__similarity_metric_whitespace(void)
 		for (i = 0; i < 3; ++i) {
 			for (j = 0; j < 3; ++j) {
 				cl_git_pass(git_buf_sets(&buf, text[i]));
-				cl_git_pass(git_hashsig_create(&a, &buf, opt));
+				cl_git_pass(git_hashsig_create(&a, buf.ptr, buf.size, opt));
 
 				cl_git_pass(git_buf_sets(&buf, text[j]));
-				cl_git_pass(git_hashsig_create(&b, &buf, opt));
+				cl_git_pass(git_hashsig_create(&b, buf.ptr, buf.size, opt));
 
 				sim = git_hashsig_compare(a, b);