summaryrefslogtreecommitdiff
path: root/utf8proc.h
diff options
context:
space:
mode:
authorSteven G. Johnson <stevenj@mit.edu>2018-07-24 13:18:48 -0400
committerGitHub <noreply@github.com>2018-07-24 13:18:48 -0400
commitd4a58cfec5345bbb2bb0db1e85172a8cff278da7 (patch)
tree01a7a3f741550c3a1dbec3b49a70f5d5f2061d6f /utf8proc.h
parent02f4e1890cf8135b609b404c58ac7e8b27136ad6 (diff)
downloadlibutf8proc-d4a58cfec5345bbb2bb0db1e85172a8cff278da7.tar.gz
libutf8proc-d4a58cfec5345bbb2bb0db1e85172a8cff278da7.tar.bz2
update data and algorithms for Unicode 11 (#140)
Diffstat (limited to 'utf8proc.h')
-rw-r--r--utf8proc.h8
1 files changed, 8 insertions, 0 deletions
diff --git a/utf8proc.h b/utf8proc.h
index 20a35a4..4516368 100644
--- a/utf8proc.h
+++ b/utf8proc.h
@@ -382,10 +382,18 @@ typedef enum {
UTF8PROC_BOUNDCLASS_SPACINGMARK = 12, /**< Spacingmark */
UTF8PROC_BOUNDCLASS_PREPEND = 13, /**< Prepend */
UTF8PROC_BOUNDCLASS_ZWJ = 14, /**< Zero Width Joiner */
+
+ /* the following are no longer used in Unicode 11, but we keep
+ the constants here for backward compatibility */
UTF8PROC_BOUNDCLASS_E_BASE = 15, /**< Emoji Base */
UTF8PROC_BOUNDCLASS_E_MODIFIER = 16, /**< Emoji Modifier */
UTF8PROC_BOUNDCLASS_GLUE_AFTER_ZWJ = 17, /**< Glue_After_ZWJ */
UTF8PROC_BOUNDCLASS_E_BASE_GAZ = 18, /**< E_BASE + GLUE_AFTER_ZJW */
+
+ /* the Extended_Pictographic property is used in the Unicode 11
+ grapheme-boundary rules, so we store it in the boundclass field */
+ UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC = 19,
+ UTF8PROC_BOUNDCLASS_E_ZWG = 20, /* UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC + ZWJ */
} utf8proc_boundclass_t;
/**