summaryrefslogtreecommitdiffstats
path: root/generic/tclEncoding.c
diff options
context:
space:
mode:
Diffstat (limited to 'generic/tclEncoding.c')
-rw-r--r--generic/tclEncoding.c61
1 files changed, 35 insertions, 26 deletions
diff --git a/generic/tclEncoding.c b/generic/tclEncoding.c
index f332585..e366904 100644
--- a/generic/tclEncoding.c
+++ b/generic/tclEncoding.c
@@ -38,7 +38,7 @@ typedef struct {
* is used to determine the source string
* length when the srcLen argument is
* negative. This number can be 1, 2, or 4. */
- ClientData clientData; /* Arbitrary value associated with encoding
+ void *clientData; /* Arbitrary value associated with encoding
* type. Passed to conversion functions. */
LengthProc *lengthProc; /* Function to compute length of
* null-terminated strings in this encoding.
@@ -2222,9 +2222,11 @@ BinaryProc(
*-------------------------------------------------------------------------
*/
+#define STOPONERROR ((flags & TCL_ENCODING_STRICT) != TCL_ENCODING_NOCOMPLAIN)
+
static int
UtfToUtfProc(
- ClientData clientData, /* additional flags, e.g. TCL_ENCODING_MODIFIED */
+ void *clientData, /* additional flags, e.g. TCL_ENCODING_MODIFIED */
const char *src, /* Source string in UTF-8. */
int srcLen, /* Source string length in bytes. */
int flags, /* Conversion control flags. */
@@ -2288,11 +2290,18 @@ UtfToUtfProc(
*dst++ = *src++;
} else if ((UCHAR(*src) == 0xC0) && (src + 1 < srcEnd)
- && (UCHAR(src[1]) == 0x80) && !(flags & TCL_ENCODING_MODIFIED)) {
+ && (UCHAR(src[1]) == 0x80) && (!(flags & TCL_ENCODING_MODIFIED) || ((flags & TCL_ENCODING_STRICT) == TCL_ENCODING_STRICT))) {
/*
- * Convert 0xC080 to real nulls when we are in output mode.
+ * If in input mode, and -strict is specified: This is an error.
*/
+ if (flags & TCL_ENCODING_MODIFIED) {
+ result = TCL_CONVERT_UNKNOWN;
+ break;
+ }
+ /*
+ * Convert 0xC080 to real nulls when we are in output mode, with or without '-strict'.
+ */
*dst++ = 0;
src += 2;
} else if (!Tcl_UtfCharComplete(src, srcEnd - src)) {
@@ -2304,7 +2313,7 @@ UtfToUtfProc(
*/
if (flags & TCL_ENCODING_MODIFIED) {
- if (!(flags & TCL_ENCODING_NOCOMPLAIN) && (flags & TCL_ENCODING_CHAR_LIMIT)) {
+ if ((STOPONERROR) && (flags & TCL_ENCODING_CHAR_LIMIT)) {
result = TCL_CONVERT_MULTIBYTE;
break;
}
@@ -2318,7 +2327,7 @@ UtfToUtfProc(
} else {
const char *saveSrc = src;
size_t len = TclUtfToUCS4(src, &ch);
- if ((len < 2) && (ch != 0) && !(flags & TCL_ENCODING_NOCOMPLAIN)
+ if ((len < 2) && (ch != 0) && STOPONERROR
&& (flags & TCL_ENCODING_MODIFIED)) {
result = TCL_CONVERT_SYNTAX;
break;
@@ -2351,7 +2360,7 @@ UtfToUtfProc(
if (((low & ~0x3FF) != 0xDC00) || (ch & 0x400)) {
- if (!(flags & TCL_ENCODING_NOCOMPLAIN)) {
+ if (STOPONERROR) {
result = TCL_CONVERT_UNKNOWN;
src = saveSrc;
break;
@@ -2363,7 +2372,7 @@ UtfToUtfProc(
ch = low;
#endif
} else if (!Tcl_UniCharIsUnicode(ch)) {
- if (!(flags & TCL_ENCODING_NOCOMPLAIN)) {
+ if (STOPONERROR) {
result = TCL_CONVERT_UNKNOWN;
src = saveSrc;
break;
@@ -2400,7 +2409,7 @@ UtfToUtfProc(
static int
Utf32ToUtfProc(
- ClientData clientData, /* additional flags, e.g. TCL_ENCODING_LE */
+ void *clientData, /* additional flags, e.g. TCL_ENCODING_LE */
const char *src, /* Source string in Unicode. */
int srcLen, /* Source string length in bytes. */
int flags, /* Conversion control flags. */
@@ -2496,7 +2505,7 @@ Utf32ToUtfProc(
static int
UtfToUtf32Proc(
- ClientData clientData, /* additional flags, e.g. TCL_ENCODING_LE */
+ void *clientData, /* additional flags, e.g. TCL_ENCODING_LE */
const char *src, /* Source string in UTF-8. */
int srcLen, /* Source string length in bytes. */
int flags, /* Conversion control flags. */
@@ -2549,7 +2558,7 @@ UtfToUtf32Proc(
}
len = TclUtfToUCS4(src, &ch);
if (!Tcl_UniCharIsUnicode(ch)) {
- if (!(flags & TCL_ENCODING_NOCOMPLAIN)) {
+ if (STOPONERROR) {
result = TCL_CONVERT_UNKNOWN;
break;
}
@@ -2593,7 +2602,7 @@ UtfToUtf32Proc(
static int
Utf16ToUtfProc(
- ClientData clientData, /* additional flags, e.g. TCL_ENCODING_LE */
+ void *clientData, /* additional flags, e.g. TCL_ENCODING_LE */
const char *src, /* Source string in Unicode. */
int srcLen, /* Source string length in bytes. */
int flags, /* Conversion control flags. */
@@ -2699,7 +2708,7 @@ Utf16ToUtfProc(
static int
UtfToUtf16Proc(
- ClientData clientData, /* additional flags, e.g. TCL_ENCODING_LE */
+ void *clientData, /* additional flags, e.g. TCL_ENCODING_LE */
const char *src, /* Source string in UTF-8. */
int srcLen, /* Source string length in bytes. */
int flags, /* Conversion control flags. */
@@ -2752,7 +2761,7 @@ UtfToUtf16Proc(
}
len = TclUtfToUCS4(src, &ch);
if (!Tcl_UniCharIsUnicode(ch)) {
- if (!(flags & TCL_ENCODING_NOCOMPLAIN)) {
+ if (STOPONERROR) {
result = TCL_CONVERT_UNKNOWN;
break;
}
@@ -2805,7 +2814,7 @@ UtfToUtf16Proc(
static int
UtfToUcs2Proc(
- ClientData clientData, /* additional flags, e.g. TCL_ENCODING_LE */
+ void *clientData, /* additional flags, e.g. TCL_ENCODING_LE */
const char *src, /* Source string in UTF-8. */
int srcLen, /* Source string length in bytes. */
int flags, /* Conversion control flags. */
@@ -2910,7 +2919,7 @@ UtfToUcs2Proc(
static int
TableToUtfProc(
- ClientData clientData, /* TableEncodingData that specifies
+ void *clientData, /* TableEncodingData that specifies
* encoding. */
const char *src, /* Source string in specified encoding. */
int srcLen, /* Source string length in bytes. */
@@ -2972,7 +2981,7 @@ TableToUtfProc(
ch = pageZero[byte];
}
if ((ch == 0) && (byte != 0)) {
- if (!(flags & TCL_ENCODING_NOCOMPLAIN)) {
+ if (STOPONERROR) {
result = TCL_CONVERT_SYNTAX;
break;
}
@@ -3019,7 +3028,7 @@ TableToUtfProc(
static int
TableFromUtfProc(
- ClientData clientData, /* TableEncodingData that specifies
+ void *clientData, /* TableEncodingData that specifies
* encoding. */
const char *src, /* Source string in UTF-8. */
int srcLen, /* Source string length in bytes. */
@@ -3088,7 +3097,7 @@ TableFromUtfProc(
word = fromUnicode[(ch >> 8)][ch & 0xFF];
if ((word == 0) && (ch != 0)) {
- if (!(flags & TCL_ENCODING_NOCOMPLAIN) && (flags & TCL_ENCODING_CHAR_LIMIT)) {
+ if ((STOPONERROR) && (flags & TCL_ENCODING_CHAR_LIMIT)) {
result = TCL_CONVERT_UNKNOWN;
break;
}
@@ -3276,7 +3285,7 @@ Iso88591FromUtfProc(
|| ((ch >= 0xD800) && (len < 3))
#endif
) {
- if (!(flags & TCL_ENCODING_NOCOMPLAIN)) {
+ if (STOPONERROR) {
result = TCL_CONVERT_UNKNOWN;
break;
}
@@ -3325,7 +3334,7 @@ Iso88591FromUtfProc(
static void
TableFreeProc(
- ClientData clientData) /* TableEncodingData that specifies
+ void *clientData) /* TableEncodingData that specifies
* encoding. */
{
TableEncodingData *dataPtr = (TableEncodingData *)clientData;
@@ -3360,7 +3369,7 @@ TableFreeProc(
static int
EscapeToUtfProc(
- ClientData clientData, /* EscapeEncodingData that specifies
+ void *clientData, /* EscapeEncodingData that specifies
* encoding. */
const char *src, /* Source string in specified encoding. */
int srcLen, /* Source string length in bytes. */
@@ -3503,7 +3512,7 @@ EscapeToUtfProc(
if ((checked == dataPtr->numSubTables + 2)
|| (flags & TCL_ENCODING_END)) {
- if (!!(flags & TCL_ENCODING_NOCOMPLAIN)) {
+ if (!STOPONERROR) {
/*
* Skip the unknown escape sequence.
*/
@@ -3574,7 +3583,7 @@ EscapeToUtfProc(
static int
EscapeFromUtfProc(
- ClientData clientData, /* EscapeEncodingData that specifies
+ void *clientData, /* EscapeEncodingData that specifies
* encoding. */
const char *src, /* Source string in UTF-8. */
int srcLen, /* Source string length in bytes. */
@@ -3678,7 +3687,7 @@ EscapeFromUtfProc(
if (word == 0) {
state = oldState;
- if (!(flags & TCL_ENCODING_NOCOMPLAIN)) {
+ if (STOPONERROR) {
result = TCL_CONVERT_UNKNOWN;
break;
}
@@ -3785,7 +3794,7 @@ EscapeFromUtfProc(
static void
EscapeFreeProc(
- ClientData clientData) /* EscapeEncodingData that specifies
+ void *clientData) /* EscapeEncodingData that specifies
* encoding. */
{
EscapeEncodingData *dataPtr = (EscapeEncodingData *)clientData;
generated by cgit v0.12 at 2024-10-23 02:19:40 (GMT)