Commit a3337f10bb604fce96e185088411feab53ab3d64

nulltoken 2012-12-17T15:15:20

blob: introduce git_blob_is_binary()

diff --git a/include/git2/blob.h b/include/git2/blob.h
index a68c78b..30055b6 100644
--- a/include/git2/blob.h
+++ b/include/git2/blob.h
@@ -183,6 +183,19 @@ GIT_EXTERN(int) git_blob_create_fromchunks(
  */
 GIT_EXTERN(int) git_blob_create_frombuffer(git_oid *oid, git_repository *repo, const void *buffer, size_t len);
 
+/**
+ * Determine if the blob content is most certainly binary or not.
+ *
+ * The heuristic used to guess if a file is binary is taken from core git:
+ * Searching for NUL bytes and looking for a reasonable ratio of printable
+ * to non-printable characters among the first 4000 bytes.
+ *
+ * @param blob The blob which content should be analyzed
+ * @return 1 if the content of the blob is detected
+ * as binary; 0 otherwise.
+ */
+GIT_EXTERN(int) git_blob_is_binary(git_blob *blob);
+
 /** @} */
 GIT_END_DECL
 #endif
diff --git a/src/blob.c b/src/blob.c
index b168df1..811bd85 100644
--- a/src/blob.c
+++ b/src/blob.c
@@ -296,3 +296,15 @@ cleanup:
 	git__free(content);
 	return error;
 }
+
+int git_blob_is_binary(git_blob *blob)
+{
+	git_buf content;
+
+	assert(blob);
+
+	content.ptr = blob->odb_object->raw.data;
+	content.size = min(blob->odb_object->raw.len, 4000);
+
+	return git_buf_text_is_binary(&content);
+}
diff --git a/tests-clar/diff/blob.c b/tests-clar/diff/blob.c
index d7fdba0..8300cb7 100644
--- a/tests-clar/diff/blob.c
+++ b/tests-clar/diff/blob.c
@@ -335,3 +335,15 @@ void test_diff_blob__checks_options_version_too_high(void)
 	err = giterr_last();
 	cl_assert_equal_i(GITERR_INVALID, err->klass);
 }
+
+void test_diff_blob__can_correctly_detect_a_binary_blob_as_binary(void)
+{
+	/* alien.png */
+	cl_assert_equal_i(true, git_blob_is_binary(alien));
+}
+
+void test_diff_blob__can_correctly_detect_a_textual_blob_as_non_binary(void)
+{
+	/* tests/resources/attr/root_test4.txt */
+	cl_assert_equal_i(false, git_blob_is_binary(d));
+}