util, utf8: make ellipsize take multi-byte characters into account

rename old versions to ascii_*

Do not take into account zerowidth characters, but do consider double-wide characters.
Import needed utf8 helper code from glib.

v3: rebase ontop of utf8 restructuring work

[zj: tweak the algorithm a bit, move new code to separate file]

1 files changed, 28 insertions, 0 deletions

diff --git a/src/shared/gunicode.h b/src/shared/gunicode.h
new file mode 100644
index 0000000000..a4b2934a4b
--- /dev/null
+++ b/src/shared/gunicode.h
@@ -0,0 +1,28 @@
+/* gunicode.h - Unicode manipulation functions
+ *
+ *  Copyright (C) 1999, 2000 Tom Tromey
+ *  Copyright 2000, 2005 Red Hat, Inc.
+ */
+
+#include <stdint.h>
+#include <stdbool.h>
+#include <stdlib.h>
+
+char *utf8_prev_char (const char *p);
+
+extern const char utf8_skip_data[256];
+
+/**
+ * g_utf8_next_char:
+ * @p: Pointer to the start of a valid UTF-8 character
+ *
+ * Skips to the next character in a UTF-8 string. The string must be
+ * valid; this macro is as fast as possible, and has no error-checking.
+ * You would use this macro to iterate over a string character by
+ * character. The macro returns the start of the next UTF-8 character.
+ * Before using this macro, use g_utf8_validate() to validate strings
+ * that may contain invalid UTF-8.
+ */
+#define utf8_next_char(p) (char *)((p) + utf8_skip_data[*(const unsigned char *)(p)])
+
+bool unichar_iswide (uint32_t c);