diff options
author | jan.nijtmans <nijtmans@users.sourceforge.net> | 2020-04-25 22:50:39 (GMT) |
---|---|---|
committer | jan.nijtmans <nijtmans@users.sourceforge.net> | 2020-04-25 22:50:39 (GMT) |
commit | 0f01f464deacd837c381b9e4c571a1976d553334 (patch) | |
tree | 2459e6cc99474974b16d413e885d34cbbb47f614 /generic | |
parent | 5fe38b57ea738f0b1910e0d02cbdc7e7d3d5e86e (diff) | |
parent | ff3cf2ae397658af620c85dafae887a07774fab7 (diff) | |
download | tcl-0f01f464deacd837c381b9e4c571a1976d553334.zip tcl-0f01f464deacd837c381b9e4c571a1976d553334.tar.gz tcl-0f01f464deacd837c381b9e4c571a1976d553334.tar.bz2 |
Merge 8.7
Diffstat (limited to 'generic')
-rw-r--r-- | generic/regc_lex.c | 10 | ||||
-rw-r--r-- | generic/tclUtf.c | 42 |
2 files changed, 9 insertions, 43 deletions
diff --git a/generic/regc_lex.c b/generic/regc_lex.c index 6ef0a83..a303ec6 100644 --- a/generic/regc_lex.c +++ b/generic/regc_lex.c @@ -843,18 +843,12 @@ lexescape( if (ISERR()) { FAILW(REG_EESCAPE); } -#if CHRBITS > 16 - if ((unsigned)i > 0x10FFFF) { - i = 0xFFFD; - } -#else - if ((unsigned)i & ~0xFFFF) { + if (i > 0xFFFF) { /* TODO: output a Surrogate pair */ i = 0xFFFD; } -#endif - RETV(PLAIN, (uchr)i); + RETV(PLAIN, (uchr) i); break; case CHR('v'): RETV(PLAIN, CHR('\v')); diff --git a/generic/tclUtf.c b/generic/tclUtf.c index d5560fc..d050daf 100644 --- a/generic/tclUtf.c +++ b/generic/tclUtf.c @@ -967,43 +967,15 @@ 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. |