diff options
| -rw-r--r-- | generic/tclCompExpr.c | 6 | ||||
| -rw-r--r-- | generic/tclUtf.c | 42 |
2 files changed, 10 insertions, 38 deletions
diff --git a/generic/tclCompExpr.c b/generic/tclCompExpr.c index 4390282..9c7ab8d 100644 --- a/generic/tclCompExpr.c +++ b/generic/tclCompExpr.c @@ -1885,7 +1885,7 @@ ParseLexeme( { const char *end; int scanned; - Tcl_UniChar ch; + Tcl_UniChar ch = 0; Tcl_Obj *literal = NULL; unsigned char byte; @@ -2064,13 +2064,13 @@ ParseLexeme( if (!TclIsBareword(*start) || *start == '_') { if (Tcl_UtfCharComplete(start, numBytes)) { - scanned = Tcl_UtfToUniChar(start, &ch); + scanned = TclUtfToUniChar(start, &ch); } else { char utfBytes[TCL_UTF_MAX]; memcpy(utfBytes, start, (size_t) numBytes); utfBytes[numBytes] = '\0'; - scanned = Tcl_UtfToUniChar(utfBytes, &ch); + scanned = TclUtfToUniChar(utfBytes, &ch); } *lexemePtr = INVALID; Tcl_DecrRefCount(literal); diff --git a/generic/tclUtf.c b/generic/tclUtf.c index ef3fd9e..91a4b89 100644 --- a/generic/tclUtf.c +++ b/generic/tclUtf.c @@ -753,43 +753,15 @@ Tcl_UtfNext( * * Tcl_UtfPrev -- * - * The aim of this routine is to provide a way to move backward - * through a UTF-8 string. The caller is expected to pass non-NULL - * pointer arguments start and src. start points to the beginning - * of a string, and src >= start points to a location within (or just - * past the end) of the string. This routine always returns a - * pointer within the string (>= start). When (src == start), it - * returns start. When (src > start), it returns a pointer (< src) - * and (>= src - TCL_UTF_MAX). Subject to these constraints, the - * routine returns a pointer to the earliest byte in the string that - * starts a character when characters are read starting at start and - * that character might include the byte src[-1]. The routine will - * examine only those bytes in the range that might be returned. - * It will not examine the byte *src, and because of that cannot - * determine for certain in all circumstances whether the character - * that begins with the returned pointer will or will not include - * the byte src[-1]. In the scenario, where src points to the end of - * a buffer being filled, the returned pointer points to either the - * final complete character in the string or to the earliest byte - * that might start an incomplete character waiting for more bytes to - * complete. - * - * Because this routine always returns a value < src until the point - * it is forced to return start, it is useful as a backward iterator - * through a string that will always make progress and always be - * prevented from running past the beginning of the string. - * - * In a string where all characters are complete and properly formed, - * and the value of src points to the first byte of a character, - * repeated Tcl_UtfPrev calls will step to the starting bytes of - * characters, one character at a time. Within those limitations, - * Tcl_UtfPrev and Tcl_UtfNext are inverses. If either condition cannot - * be met, Tcl_UtfPrev and Tcl_UtfNext may not function as inverses and - * the caller will have to take greater care. + * Given a pointer to some current location in a UTF-8 string, move + * backwards one character. This works correctly when the pointer is in + * the middle of a UTF-8 character. * * Results: - * A pointer to the start of a character in the string as described - * above. + * The return value is a pointer to the previous character in the UTF-8 + * string. If the current location was already at the beginning of the + * string, the return value will also be a pointer to the beginning of + * the string. * * Side effects: * None. |