summaryrefslogtreecommitdiffstats
path: root/generic/tclUtf.c
diff options
context:
space:
mode:
authordgp <dgp@users.sourceforge.net>2017-06-05 17:15:11 (GMT)
committerdgp <dgp@users.sourceforge.net>2017-06-05 17:15:11 (GMT)
commit0b178367ba3b9a10d44f89025c89292a4ea49b20 (patch)
tree853c1526b11c08616068ce931e63175c687bfd8f /generic/tclUtf.c
parent1d537a6b450c04d52d93f2c04bf3135b60711e61 (diff)
parent67fd012128e6e76e3d745ca090075acbcfa9f258 (diff)
downloadtcl-0b178367ba3b9a10d44f89025c89292a4ea49b20.zip
tcl-0b178367ba3b9a10d44f89025c89292a4ea49b20.tar.gz
tcl-0b178367ba3b9a10d44f89025c89292a4ea49b20.tar.bz2
[67aa9a2070] Tcl_UtfToUniChar returns single byte for invalid UTF-8 input as documented.
Diffstat (limited to 'generic/tclUtf.c')
-rw-r--r--generic/tclUtf.c12
1 files changed, 9 insertions, 3 deletions
diff --git a/generic/tclUtf.c b/generic/tclUtf.c
index b33bf6a..eec4068 100644
--- a/generic/tclUtf.c
+++ b/generic/tclUtf.c
@@ -292,7 +292,9 @@ Tcl_UtfToUniChar(
*/
*chPtr = (Tcl_UniChar) (((byte & 0x1F) << 6) | (src[1] & 0x3F));
- return 2;
+ if ((*chPtr == 0) || (*chPtr > 0x7f)) {
+ return 2;
+ }
}
/*
@@ -307,7 +309,9 @@ Tcl_UtfToUniChar(
*chPtr = (Tcl_UniChar) (((byte & 0x0F) << 12)
| ((src[1] & 0x3F) << 6) | (src[2] & 0x3F));
- return 3;
+ if (*chPtr > 0x7ff) {
+ return 3;
+ }
}
/*
@@ -324,7 +328,9 @@ Tcl_UtfToUniChar(
*chPtr = (Tcl_UniChar) (((byte & 0x0E) << 18) | ((src[1] & 0x3F) << 12)
| ((src[2] & 0x3F) << 6) | (src[3] & 0x3F));
- return 4;
+ if ((*chPtr <= 0x10ffff) && (*chPtr > 0xffff)) {
+ return 4;
+ }
}
/*