Make sord_node_get_counted return byte count

Also clarify formerly ambiguous documentation, and add
sord_node_get_string_measured to get both byte and character counts.

Technically, this breaks behaviour, but most (if not all) existing code
that uses this function was actually expecting a byte count.  This is
unsurprising since a UTF-8 character count is almost always useless.
This approach causes less problems in reality, since it fixes broken
behaviour in the wild without requiring any changes in user code.

5 files changed, 53 insertions, 14 deletions

diff --git a/NEWS b/NEWS
index 6d8e96d..b89f6fb 100644
--- a/NEWS
+++ b/NEWS
@@ -1,10 +1,12 @@
-sord (0.14.1) unstable;
+sord (0.15.1) unstable;
 
   * Fix documentation generation
   * Return error from sord_inserter_write_statement() if a node can not be written
     (e.g. undefined prefix)
+  * Make sord_node_get_counted return byte count, and clarify documentation
+  * Add sord_node_get_string_measured to get both byte and character counts
 
- -- David Robillard <d@drobilla.net>  Fri, 04 Dec 2015 21:23:36 -0500
+ -- David Robillard <d@drobilla.net>  Tue, 15 Mar 2016 14:51:35 -0400
 
 sord (0.14.0) stable;
 
diff --git a/sord/sord.h b/sord/sord.h
index dd671de..e93cff8 100644
--- a/sord/sord.h
+++ b/sord/sord.h
@@ -248,11 +248,21 @@ const uint8_t*
 sord_node_get_string(const SordNode* node);
 
 /**
-   Return the string value of a node, and set `len` to its length.
+   Return the string value of a node, and set `bytes` to its length in bytes.
 */
 SORD_API
 const uint8_t*
-sord_node_get_string_counted(const SordNode* node, size_t* len);
+sord_node_get_string_counted(const SordNode* node, size_t* bytes);
+
+/**
+   Return the string value of a node, and set `bytes` to its length in bytes,
+   and `count` to its length in characters.
+*/
+SORD_API
+const uint8_t*
+sord_node_get_string_measured(const SordNode* node,
+                              size_t*         bytes,
+                              size_t*         chars);
 
 /**
    Return the language of a literal node (or NULL).
diff --git a/src/sord.c b/src/sord.c
index c6b2b38..fbc33f7 100644
--- a/src/sord.c
+++ b/src/sord.c
@@ -919,9 +919,19 @@ sord_node_get_string(const SordNode* node)
 }
 
 const uint8_t*
-sord_node_get_string_counted(const SordNode* node, size_t* len)
+sord_node_get_string_counted(const SordNode* node, size_t* bytes)
 {
-	*len = node->node.n_chars;
+	*bytes = node->node.n_bytes;
+	return node->node.buf;
+}
+
+const uint8_t*
+sord_node_get_string_measured(const SordNode* node,
+                              size_t*         bytes,
+                              size_t*         chars)
+{
+	*bytes = node->node.n_bytes;
+	*chars = node->node.n_chars;
 	return node->node.buf;
 }
 
diff --git a/src/sord_test.c b/src/sord_test.c
index ea258b0..c6e6a5b 100644
--- a/src/sord_test.c
+++ b/src/sord_test.c
@@ -515,17 +515,34 @@ main(int argc, char** argv)
 		goto fail;
 	}
 
-	size_t len;
-	const uint8_t* str = sord_node_get_string_counted(lit_id2, &len);
+	if (sord_num_nodes(world) != initial_num_nodes) {
+		return test_fail("Num nodes %zu != %zu\n",
+		                 sord_num_nodes(world), initial_num_nodes);
+	}
+
+	const uint8_t ni_hao[] = { 0xE4, 0xBD, 0xA0, 0xE5, 0xA5, 0xBD };
+	SordNode*     chello   = sord_new_literal(world, NULL, ni_hao, "cmn");
+
+	// Test literal length
+	size_t         n_bytes;
+	size_t         n_chars;
+	const uint8_t* str = sord_node_get_string_counted(lit_id2, &n_bytes);
 	if (strcmp((const char*)str, "hello")) {
 		return test_fail("Literal node corrupt\n");
-	} else if (len != strlen("hello")) {
-		return test_fail("Literal length incorrect\n");
+	} else if (n_bytes != strlen("hello")) {
+		return test_fail("ASCII literal byte count incorrect\n");
 	}
 
-	if (sord_num_nodes(world) != initial_num_nodes) {
-		return test_fail("Num nodes %zu != %zu\n",
-		                 sord_num_nodes(world), initial_num_nodes);
+	str = sord_node_get_string_measured(lit_id2, &n_bytes, &n_chars);
+	if (n_bytes != strlen("hello") || n_chars != strlen("hello")) {
+		return test_fail("ASCII literal measured length incorrect\n");
+	}
+
+	str = sord_node_get_string_measured(chello, &n_bytes, &n_chars);
+	if (n_bytes != 6) {
+		return test_fail("Multi-byte literal byte count incorrect\n");
+	} else if (n_chars != 2) {
+		return test_fail("Multi-byte literal character count incorrect\n");
 	}
 
 	// Check interning doesn't clash non-equivalent values
diff --git a/wscript b/wscript
index 36ef0f3..5fcd76e 100644
--- a/wscript
+++ b/wscript
@@ -11,7 +11,7 @@ import waflib.extras.autowaf as autowaf
 # major increment <=> incompatible changes
 # minor increment <=> compatible changes (additions)
 # micro increment <=> no interface changes
-SORD_VERSION       = '0.14.1'
+SORD_VERSION       = '0.15.1'
 SORD_MAJOR_VERSION = '0'
 
 # Mandatory waf variables