Tweak Invalid() function: No need for "return 0" twice in the function.

For start bytes F0-F4, case TCL_UTF_MAX=4, Tcl_UtfToUniChar() reads 3 bytes but only advances 1 byte. So Tcl_UtfCharComplete() must make sure 3 bytes are available, not 1. Adapt Tcl_UtfCharComplete() accordingly. No change for TCL_UTF_MAX=[3|6]

2 files changed, 38 insertions, 15 deletions

diff --git a/generic/tclUtf.c b/generic/tclUtf.c
index c0de80a..5e0b2e0 100644
--- a/generic/tclUtf.c
+++ b/generic/tclUtf.c
@@ -81,6 +81,30 @@ static const unsigned char totalBytes[256] = {
     1,1,1,1,1,1,1,1,1,1,1
 };
 
+static const unsigned char complete[256] = {
+    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+#if TCL_UTF_MAX < 4
+    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+#else /* Tcl_UtfCharComplete() might point to 2nd byte of valid 4-byte sequence */
+    3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,
+    3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,
+#endif
+    2,1,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
+    3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,
+#if TCL_UTF_MAX > 4
+    4,4,4,4,4,
+#elif TCL_UTF_MAX < 4
+    1,1,1,1,1,
+#else
+    3,3,3,3,3,
+#endif
+    1,1,1,1,1,1,1,1,1,1,1
+};
+
 /*
  * Functions used only in this module.
  */
@@ -174,14 +198,13 @@ Invalid(
     unsigned char byte = UCHAR(*src);
     int index;
 
-    if ((byte & 0xC3) != 0xC0) {
+    if ((byte & 0xC3) == 0xC0) {
 	/* Only lead bytes 0xC0, 0xE0, 0xF0, 0xF4 need examination */
-	return 0;
-    }
-    index = (byte - 0xC0) >> 1;
-    if (UCHAR(src[1]) < bounds[index] || UCHAR(src[1]) > bounds[index+1]) {
-	/* Out of bounds - report invalid. */
-	return 1;
+	index = (byte - 0xC0) >> 1;
+	if (UCHAR(src[1]) < bounds[index] || UCHAR(src[1]) > bounds[index+1]) {
+	    /* Out of bounds - report invalid. */
+	    return 1;
+	}
     }
     return 0;
 }
@@ -568,7 +591,7 @@ Tcl_UtfCharComplete(
 				 * a complete UTF-8 character. */
     int length)			/* Length of above string in bytes. */
 {
-    return length >= totalBytes[UCHAR(*src)];
+    return length >= complete[UCHAR(*src)];
 }
 
 /*
diff --git a/tests/utf.test b/tests/utf.test
index 1a4b157..8745385 100644
--- a/tests/utf.test
+++ b/tests/utf.test
@@ -570,13 +570,13 @@ test utf-6.108 {Tcl_UtfNext, read limits} {testutfnext testbytestring} {
 test utf-6.109 {Tcl_UtfNext, read limits} {testutfnext testbytestring} {
     testutfnext \u8820[testbytestring \xA0] 3
 } 3
-test utf-6.110.0 {Tcl_UtfNext, read limits} {testutfnext testbytestring ucs2_utf16} {
+test utf-6.110.0 {Tcl_UtfNext, read limits} {testutfnext testbytestring ucs2} {
     testutfnext [testbytestring \xF2\xA0\xA0\xA0]G 1
 } 1
-test utf-6.110.1 {Tcl_UtfNext, read limits} {testutfnext testbytestring ucs4} {
+test utf-6.110.1 {Tcl_UtfNext, read limits} {testutfnext testbytestring fullutf} {
     testutfnext [testbytestring \xF2\xA0\xA0\xA0]G 1
 } 0
-test utf-6.111.0 {Tcl_UtfNext, read limits} {testutfnext testbytestring ucs2_utf16} {
+test utf-6.111.0 {Tcl_UtfNext, read limits} {testutfnext testbytestring ucs2} {
     testutfnext [testbytestring \xF2\xA0\xA0\xA0]G 2
 } 1
 test utf-6.111.1 {Tcl_UtfNext, read limits} {testutfnext testbytestring ucs4} {
@@ -594,16 +594,16 @@ test utf-6.113.0 {Tcl_UtfNext, read limits} {testutfnext testbytestring ucs2_utf
 test utf-6.113.1 {Tcl_UtfNext, read limits} {testutfnext testbytestring ucs4} {
     testutfnext [testbytestring \xF2\xA0\xA0\xA0]G 4
 } 4
-test utf-6.114.0 {Tcl_UtfNext, read limits} {testutfnext testbytestring ucs2_utf16} {
+test utf-6.114.0 {Tcl_UtfNext, read limits} {testutfnext testbytestring ucs2} {
     testutfnext [testbytestring \xF2\xA0\xA0\xA0\xA0] 1
 } 1
-test utf-6.114.1 {Tcl_UtfNext, read limits} {testutfnext testbytestring ucs4} {
+test utf-6.114.1 {Tcl_UtfNext, read limits} {testutfnext testbytestring fullutf} {
     testutfnext [testbytestring \xF2\xA0\xA0\xA0\xA0] 1
 } 0
-test utf-6.115.0 {Tcl_UtfNext, read limits} {testutfnext testbytestring ucs2_utf16} {
+test utf-6.115.0 {Tcl_UtfNext, read limits} {testutfnext testbytestring ucs2} {
     testutfnext [testbytestring \xF2\xA0\xA0\xA0\xA0] 2
 } 1
-test utf-6.115.1 {Tcl_UtfNext, read limits} {testutfnext testbytestring ucs4} {
+test utf-6.115.1 {Tcl_UtfNext, read limits} {testutfnext testbytestring fullutf} {
     testutfnext [testbytestring \xF2\xA0\xA0\xA0\xA0] 2
 } 0
 test utf-6.116.0 {Tcl_UtfNext, read limits} {testutfnext testbytestring ucs2_utf16} {