Optimize away git_text_gather_stats in diff

GProf shows `git_text_gather_stats` as the most expensive call
in large diffs.  The function calculates a lot of information
that is not actually used and does not do so in a optimal
order.  This introduces a tuned `git_buf_is_binary` function
that executes the same algorithm in a fraction of the time.

3 files changed, 23 insertions, 7 deletions

diff --git a/src/buffer.c b/src/buffer.c
index ef95839f6..29aaf3fec 100644
--- a/src/buffer.c
+++ b/src/buffer.c
@@ -445,3 +445,21 @@ int git_buf_common_prefix(git_buf *buf, const git_strarray *strings)
 
 	return 0;
 }
+
+bool git_buf_is_binary(const git_buf *buf)
+{
+	int i, printable = 0, nonprintable = 0;
+
+	for (i = 0; i < buf->size; i++) {
+		unsigned char c = buf->ptr[i];
+		if (c > 0x1F && c < 0x7f)
+			printable++;
+		else if (c == '\0')
+			return true;
+		else if (!git__isspace(c))
+			nonprintable++;
+	}
+
+	return ((printable >> 7) < nonprintable);
+}
+
diff --git a/src/buffer.h b/src/buffer.h
index af760f901..090b43548 100644
--- a/src/buffer.h
+++ b/src/buffer.h
@@ -125,4 +125,7 @@ int git_buf_cmp(const git_buf *a, const git_buf *b);
 /* Fill buf with the common prefix of a array of strings */
 int git_buf_common_prefix(git_buf *buf, const git_strarray *strings);
 
+/* Check if buffer looks like it contains binary data */
+bool git_buf_is_binary(const git_buf *buf);
+
 #endif
diff --git a/src/diff_output.c b/src/diff_output.c
index 9c8e07972..4ad736e26 100644
--- a/src/diff_output.c
+++ b/src/diff_output.c
@@ -174,15 +174,12 @@ static int file_is_binary_by_content(
 	git_map *new_data)
 {
 	git_buf search;
-	git_text_stats stats;
 
 	if ((delta->old_file.flags & BINARY_DIFF_FLAGS) == 0) {
 		search.ptr  = old_data->data;
 		search.size = min(old_data->len, 4000);
 
-		git_text_gather_stats(&stats, &search);
-
-		if (git_text_is_binary(&stats))
+		if (git_buf_is_binary(&search))
 			delta->old_file.flags |= GIT_DIFF_FILE_BINARY;
 		else
 			delta->old_file.flags |= GIT_DIFF_FILE_NOT_BINARY;
@@ -192,9 +189,7 @@ static int file_is_binary_by_content(
 		search.ptr  = new_data->data;
 		search.size = min(new_data->len, 4000);
 
-		git_text_gather_stats(&stats, &search);
-
-		if (git_text_is_binary(&stats))
+		if (git_buf_is_binary(&search))
 			delta->new_file.flags |= GIT_DIFF_FILE_BINARY;
 		else
 			delta->new_file.flags |= GIT_DIFF_FILE_NOT_BINARY;