From 035301443ee6084c504756ded6d4e104443fcd6a Mon Sep 17 00:00:00 2001
From: Brian Carrier <carrier@sleuthkit.org>
Date: Thu, 22 Sep 2011 19:58:49 +0000
Subject: [PATCH] Replace invalid UTF-16 with ^ when converting - patch by
Anthony Lawrence
---
tsk3/base/tsk_unicode.c | 52 +++++++++++++++++++++++++++++------------
1 file changed, 37 insertions(+), 15 deletions(-)
diff --git a/tsk3/base/tsk_unicode.c b/tsk3/base/tsk_unicode.c
index 4c04a1662..391078ed4 100644
--- a/tsk3/base/tsk_unicode.c
+++ b/tsk3/base/tsk_unicode.c
@@ -170,10 +170,16 @@ tsk_UTF16toUTF8(TSK_ENDIAN_ENUM endian, const UTF16 ** sourceStart,
+ (ch2 - UNI_SUR_LOW_START) + halfBase;
++source;
}
- else if (flags == TSKstrictConversion) { /* it's an unpaired high surrogate */
- --source; /* return to the illegal value itself */
- result = TSKsourceIllegal;
- break;
+ else {
+ if (flags == TSKstrictConversion) { /* it's an unpaired high surrogate */
+ --source; /* return to the illegal value itself */
+ result = TSKsourceIllegal;
+ break;
+ }
+ // replace with another character
+ else {
+ ch = '^';
+ }
}
}
else { /* We don't have the 16 bits following the high surrogate. */
@@ -182,14 +188,19 @@ tsk_UTF16toUTF8(TSK_ENDIAN_ENUM endian, const UTF16 ** sourceStart,
break;
}
}
- else if (flags == TSKstrictConversion) {
- /* UTF-16 surrogate values are illegal in UTF-32 */
- if (ch >= UNI_SUR_LOW_START && ch <= UNI_SUR_LOW_END) {
+ /* UTF-16 surrogate values are illegal in UTF-32 */
+ else if (ch >= UNI_SUR_LOW_START && ch <= UNI_SUR_LOW_END) {
+ if (flags == TSKstrictConversion) {
--source; /* return to the illegal value itself */
result = TSKsourceIllegal;
break;
}
+ // replace with another character
+ else {
+ ch = '^';
+ }
}
+
/* Figure out how many bytes the result will require */
if (ch < (UTF32) 0x80) {
bytesToWrite = 1;
@@ -273,10 +284,16 @@ tsk_UTF16toUTF8_lclorder(const UTF16 ** sourceStart,
+ (ch2 - UNI_SUR_LOW_START) + halfBase;
++source;
}
- else if (flags == TSKstrictConversion) { /* it's an unpaired high surrogate */
- --source; /* return to the illegal value itself */
- result = TSKsourceIllegal;
- break;
+ else {
+ if (flags == TSKstrictConversion) { /* it's an unpaired high surrogate */
+ --source; /* return to the illegal value itself */
+ result = TSKsourceIllegal;
+ break;
+ }
+ // replace with another character
+ else {
+ ch = '^';
+ }
}
}
else { /* We don't have the 16 bits following the high surrogate. */
@@ -285,15 +302,20 @@ tsk_UTF16toUTF8_lclorder(const UTF16 ** sourceStart,
break;
}
}
- else if (flags == TSKstrictConversion) {
- /* UTF-16 surrogate values are illegal in UTF-32 */
- if (ch >= UNI_SUR_LOW_START && ch <= UNI_SUR_LOW_END) {
+ /* UTF-16 surrogate values are illegal in UTF-32 */
+ else if (ch >= UNI_SUR_LOW_START && ch <= UNI_SUR_LOW_END) {
+ if (flags == TSKstrictConversion) {
--source; /* return to the illegal value itself */
result = TSKsourceIllegal;
break;
}
+ // replace with another character
+ else {
+ ch = '^';
+ }
}
-/* Figure out how many bytes the result will require */
+
+ /* Figure out how many bytes the result will require */
if (ch < (UTF32) 0x80) {
bytesToWrite = 1;
}
--
GitLab