utf8proc

commit 8239639e3fe1192c8b0c3f45ed7eb5be02853476
parent df2997a300792b8efd6a1ea9281c14dfe986d6f9
Author: Steven G. Johnson <stevenj@alum.mit.edu>
Date:   Tue, 15 Dec 2020 15:26:56 -0500

fix NULL args in grapheme_break_stateful

Diffstat:
M
NEWS.md
 | 
7
+++++++
M
test/graphemetest.c
 | 
3
+++
M
utf8proc.c
 | 
18
+++++++++++-------

3 files changed, 21 insertions(+), 7 deletions(-)
diff --git a/NEWS.md b/NEWS.md
@@ -1,5 +1,12 @@
 # utf8proc release history #
 
+## Version 2.6.1 ##
+
+2020-12-15
+
+ - Bugfix in `utf8proc_grapheme_break_stateful` for `NULL` state argument, which
+   also broke `utf8proc_grapheme_break`.
+
 ## Version 2.6 ##
 
 2020-11-23
diff --git a/test/graphemetest.c b/test/graphemetest.c
@@ -118,6 +118,9 @@ int main(int argc, char **argv)
     checkline("/ 1f926 1f3fc 200d 2642 fe0f /", true); /* facepalm + pale skin + zwj + male sign + FE0F */
     checkline("/ 1f468 1f3fb 200d 1f91d 200d 1f468 1f3fd /", true); /* man face + pale skin + zwj + hand holding + zwj + man face + dark skin */
 
+    check(utf8proc_grapheme_break(0x03b1, 0x03b2), "failed 03b1 / 03b2 test");
+    check(!utf8proc_grapheme_break(0x03b1, 0x0302), "failed 03b1 0302 test");
+
     printf("Passed regression tests!\n");
 
     return 0;
diff --git a/utf8proc.c b/utf8proc.c
@@ -290,13 +290,14 @@ static utf8proc_bool grapheme_break_simple(int lbc, int tbc) {
 
 static utf8proc_bool grapheme_break_extended(int lbc, int tbc, utf8proc_int32_t *state)
 {
-  int lbc_override;
-  if (*state == UTF8PROC_BOUNDCLASS_START)
-    *state = lbc_override = lbc; 
-  else
-    lbc_override = *state;
-  utf8proc_bool break_permitted = grapheme_break_simple(lbc_override, tbc);
   if (state) {
+    int lbc_override;
+    if (*state == UTF8PROC_BOUNDCLASS_START)
+      *state = lbc_override = lbc;
+    else
+      lbc_override = *state;
+    utf8proc_bool break_permitted = grapheme_break_simple(lbc_override, tbc);
+
     // Special support for GB 12/13 made possible by GB999. After two RI
     // class codepoints we want to force a break. Do this by resetting the
     // second RI's bound class to UTF8PROC_BOUNDCLASS_OTHER, to force a break
@@ -315,8 +316,11 @@ static utf8proc_bool grapheme_break_extended(int lbc, int tbc, utf8proc_int32_t 
     }
     else
       *state = tbc;
+
+    return break_permitted;
   }
-  return break_permitted;
+  else
+    return grapheme_break_simple(lbc, tbc);
 }
 
 UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break_stateful(