X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/5e3d7cf5b1cf51f4fbbb385e2877c7a903bb778f..508f7cfaca1a9a559de9b56ba489e1f4ec3519a7:/utf8.c diff --git a/utf8.c b/utf8.c index 7bf2e15..371db53 100644 --- a/utf8.c +++ b/utf8.c @@ -139,7 +139,7 @@ Perl_uvuni_to_utf8_flags(pTHX_ U8 *d, UV uv, UV flags) if (ckWARN_d(WARN_UTF8)) { if (UNICODE_IS_SURROGATE(uv)) { if (flags & UNICODE_WARN_SURROGATE) { - Perl_warner(aTHX_ packWARN(WARN_UTF8), + Perl_ck_warner_d(aTHX_ packWARN(WARN_SURROGATE), "UTF-16 surrogate U+%04"UVXf, uv); } if (flags & UNICODE_DISALLOW_SURROGATE) { @@ -150,7 +150,7 @@ Perl_uvuni_to_utf8_flags(pTHX_ U8 *d, UV uv, UV flags) if (flags & UNICODE_WARN_SUPER || (UNICODE_IS_FE_FF(uv) && (flags & UNICODE_WARN_FE_FF))) { - Perl_warner(aTHX_ packWARN(WARN_UTF8), + Perl_ck_warner_d(aTHX_ packWARN(WARN_NON_UNICODE), "Code point 0x%04"UVXf" is not Unicode, may not be portable", uv); } if (flags & UNICODE_DISALLOW_SUPER @@ -161,7 +161,7 @@ Perl_uvuni_to_utf8_flags(pTHX_ U8 *d, UV uv, UV flags) } else if (UNICODE_IS_NONCHAR(uv)) { if (flags & UNICODE_WARN_NONCHAR) { - Perl_warner(aTHX_ packWARN(WARN_UTF8), + Perl_ck_warner_d(aTHX_ packWARN(WARN_NONCHAR), "Unicode non-character U+%04"UVXf" is illegal for open interchange", uv); } @@ -547,9 +547,9 @@ Perl_utf8n_to_uvuni(pTHX_ const U8 *s, STRLEN curlen, STRLEN *retlen, U32 flags) #define UTF8_WARN_EMPTY 1 #define UTF8_WARN_CONTINUATION 2 #define UTF8_WARN_NON_CONTINUATION 3 -#define UTF8_WARN_SHORT 5 -#define UTF8_WARN_OVERFLOW 6 -#define UTF8_WARN_LONG 8 +#define UTF8_WARN_SHORT 4 +#define UTF8_WARN_OVERFLOW 5 +#define UTF8_WARN_LONG 6 if (curlen == 0 && !(flags & UTF8_ALLOW_EMPTY)) { @@ -580,7 +580,7 @@ Perl_utf8n_to_uvuni(pTHX_ const U8 *s, STRLEN curlen, STRLEN *retlen, U32 flags) #else if (uv == 0xfe || uv == 0xff) { if (flags & (UTF8_WARN_SUPER|UTF8_WARN_FE_FF)) { - sv = sv_2mortal(newSVpvf_nocontext("Code point beginning with byte 0x%02"UVXf" is not Unicode, and not portable", uv)); + sv = sv_2mortal(Perl_newSVpvf(aTHX_ "Code point beginning with byte 0x%02"UVXf" is not Unicode, and not portable", uv)); flags &= ~UTF8_WARN_SUPER; /* Only warn once on this problem */ } if (flags & (UTF8_DISALLOW_SUPER|UTF8_DISALLOW_FE_FF)) { @@ -651,7 +651,7 @@ Perl_utf8n_to_uvuni(pTHX_ const U8 *s, STRLEN curlen, STRLEN *retlen, U32 flags) } else if (flags & (UTF8_DISALLOW_ILLEGAL_INTERCHANGE|UTF8_WARN_ILLEGAL_INTERCHANGE)) { if (UNICODE_IS_SURROGATE(uv)) { if ((flags & (UTF8_WARN_SURROGATE|UTF8_CHECK_ONLY)) == UTF8_WARN_SURROGATE) { - sv = sv_2mortal(newSVpvf_nocontext("UTF-16 surrogate U+%04"UVXf"", uv)); + sv = sv_2mortal(Perl_newSVpvf(aTHX_ "UTF-16 surrogate U+%04"UVXf"", uv)); } if (flags & UTF8_DISALLOW_SURROGATE) { goto disallowed; @@ -659,7 +659,7 @@ Perl_utf8n_to_uvuni(pTHX_ const U8 *s, STRLEN curlen, STRLEN *retlen, U32 flags) } else if (UNICODE_IS_NONCHAR(uv)) { if ((flags & (UTF8_WARN_NONCHAR|UTF8_CHECK_ONLY)) == UTF8_WARN_NONCHAR ) { - sv = sv_2mortal(newSVpvf_nocontext("Unicode non-character U+%04"UVXf" is illegal for open interchange", uv)); + sv = sv_2mortal(Perl_newSVpvf(aTHX_ "Unicode non-character U+%04"UVXf" is illegal for open interchange", uv)); } if (flags & UTF8_DISALLOW_NONCHAR) { goto disallowed; @@ -667,7 +667,7 @@ Perl_utf8n_to_uvuni(pTHX_ const U8 *s, STRLEN curlen, STRLEN *retlen, U32 flags) } else if ((uv > PERL_UNICODE_MAX)) { if ((flags & (UTF8_WARN_SUPER|UTF8_CHECK_ONLY)) == UTF8_WARN_SUPER) { - sv = sv_2mortal(newSVpvf_nocontext("Code point 0x%04"UVXf" is not Unicode, may not be portable", uv)); + sv = sv_2mortal(Perl_newSVpvf(aTHX_ "Code point 0x%04"UVXf" is not Unicode, may not be portable", uv)); } if (flags & UTF8_DISALLOW_SUPER) { goto disallowed; @@ -766,13 +766,14 @@ returned and retlen is set, if possible, to -1. =cut */ + UV Perl_utf8_to_uvchr(pTHX_ const U8 *s, STRLEN *retlen) { PERL_ARGS_ASSERT_UTF8_TO_UVCHR; return utf8n_to_uvchr(s, UTF8_MAXBYTES, retlen, - ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY); + ckWARN_d(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY); } /* @@ -798,7 +799,7 @@ Perl_utf8_to_uvuni(pTHX_ const U8 *s, STRLEN *retlen) /* Call the low level routine asking for checks */ return Perl_utf8n_to_uvuni(aTHX_ s, UTF8_MAXBYTES, retlen, - ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY); + ckWARN_d(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY); } /* @@ -840,7 +841,7 @@ Perl_utf8_length(pTHX_ const U8 *s, const U8 *e) Perl_ck_warner_d(aTHX_ packWARN(WARN_UTF8), "%s in %s", unees, OP_DESC(PL_op)); else - Perl_ck_warner_d(aTHX_ packWARN(WARN_UTF8), unees); + Perl_ck_warner_d(aTHX_ packWARN(WARN_UTF8), "%s", unees); } return len; @@ -952,7 +953,7 @@ Perl_bytes_cmp_utf8(pTHX_ const U8 *b, STRLEN blen, const U8 *u, STRLEN ulen) Perl_ck_warner_d(aTHX_ packWARN(WARN_UTF8), "%s in %s", unees, OP_DESC(PL_op)); else - Perl_ck_warner_d(aTHX_ packWARN(WARN_UTF8), unees); + Perl_ck_warner_d(aTHX_ packWARN(WARN_UTF8), "%s", unees); return -2; /* Really want to return undef :-) */ } } else { @@ -1340,12 +1341,12 @@ Perl_to_uni_lower(pTHX_ UV c, U8* p, STRLEN *lenp) } UV -Perl_to_uni_fold(pTHX_ UV c, U8* p, STRLEN *lenp) +Perl__to_uni_fold_flags(pTHX_ UV c, U8* p, STRLEN *lenp, U8 flags) { - PERL_ARGS_ASSERT_TO_UNI_FOLD; + PERL_ARGS_ASSERT__TO_UNI_FOLD_FLAGS; uvchr_to_utf8(p, c); - return to_utf8_fold(p, p, lenp); + return _to_utf8_fold_flags(p, p, lenp, flags); } /* for now these all assume no locale info available for Unicode > 255 */ @@ -1500,6 +1501,19 @@ Perl_is_utf8_idfirst(pTHX_ const U8 *p) /* The naming is historical. */ } bool +Perl_is_utf8_xidfirst(pTHX_ const U8 *p) /* The naming is historical. */ +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_XIDFIRST; + + if (*p == '_') + return TRUE; + /* is_utf8_idstart would be more logical. */ + return is_utf8_common(p, &PL_utf8_xidstart, "XIdStart"); +} + +bool Perl_is_utf8_idcont(pTHX_ const U8 *p) { dVAR; @@ -1512,6 +1526,18 @@ Perl_is_utf8_idcont(pTHX_ const U8 *p) } bool +Perl_is_utf8_xidcont(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_XIDCONT; + + if (*p == '_') + return TRUE; + return is_utf8_common(p, &PL_utf8_idcont, "XIdContinue"); +} + +bool Perl_is_utf8_alpha(pTHX_ const U8 *p) { dVAR; @@ -1773,7 +1799,7 @@ of the result. The "swashp" is a pointer to the swash to use. -Both the special and normal mappings are stored lib/unicore/To/Foo.pl, +Both the special and normal mappings are stored in lib/unicore/To/Foo.pl, and loaded by SWASHNEW, using lib/utf8_heavy.pl. The special (usually, but not always, a multicharacter mapping), is tried first. @@ -1801,6 +1827,28 @@ Perl_to_utf8_case(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp, PERL_ARGS_ASSERT_TO_UTF8_CASE; + /* Note that swash_fetch() doesn't output warnings for these because it + * assumes we will */ + if (uv1 >= UNICODE_SURROGATE_FIRST) { + if (uv1 <= UNICODE_SURROGATE_LAST) { + if (ckWARN_d(WARN_SURROGATE)) { + const char* desc = (PL_op) ? OP_DESC(PL_op) : normal; + Perl_warner(aTHX_ packWARN(WARN_SURROGATE), + "Operation \"%s\" returns its argument for UTF-16 surrogate U+%04"UVXf"", desc, uv1); + } + } + else if (UNICODE_IS_SUPER(uv1)) { + if (ckWARN_d(WARN_NON_UNICODE)) { + const char* desc = (PL_op) ? OP_DESC(PL_op) : normal; + Perl_warner(aTHX_ packWARN(WARN_NON_UNICODE), + "Operation \"%s\" returns its argument for non-Unicode code point 0x%04"UVXf"", desc, uv1); + } + } + + /* Note that non-characters are perfectly legal, so no warning should + * be given */ + } + uvuni_to_utf8(tmpbuf, uv1); if (!*swashp) /* load on-demand */ @@ -1978,15 +2026,20 @@ The first character of the foldcased version is returned =cut */ +/* Not currently externally documented is 'flags', which currently is non-zero + * if full case folds are to be used; otherwise simple folds */ + UV -Perl_to_utf8_fold(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp) +Perl__to_utf8_fold_flags(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp, U8 flags) { + const char *specials = (flags) ? "utf8::ToSpecFold" : NULL; + dVAR; - PERL_ARGS_ASSERT_TO_UTF8_FOLD; + PERL_ARGS_ASSERT__TO_UTF8_FOLD_FLAGS; return Perl_to_utf8_case(aTHX_ p, ustrp, lenp, - &PL_utf8_tofold, "ToFold", "utf8::ToSpecFold"); + &PL_utf8_tofold, "ToFold", specials); } /* Note: @@ -2121,6 +2174,18 @@ Perl_swash_fetch(pTHX_ SV *swash, const U8 *ptr, bool do_utf8) /* If char is encoded then swatch is for the prefix */ needents = (1 << UTF_ACCUMULATION_SHIFT); off = NATIVE_TO_UTF(ptr[klen]) & UTF_CONTINUATION_MASK; + if (UTF8_IS_SUPER(ptr) && ckWARN_d(WARN_NON_UNICODE)) { + const UV code_point = utf8n_to_uvuni(ptr, UTF8_MAXBYTES, 0, 0); + + /* This outputs warnings for binary properties only, assuming that + * to_utf8_case() will output any. Also, surrogates aren't checked + * for, as that would warn on things like /\p{Gc=Cs}/ */ + SV** const bitssvp = hv_fetchs(hv, "BITS", FALSE); + if (SvUV(*bitssvp) == 1) { + Perl_warner(aTHX_ packWARN(WARN_NON_UNICODE), + "Code point 0x%04"UVXf" is not Unicode, no properties match it; all inverse properties do", code_point); + } + } } /* @@ -2551,7 +2616,7 @@ S_swash_get(pTHX_ SV* swash, UV start, UV span) } HV* -Perl__swash_inversion_hash(pTHX_ SV* swash) +Perl__swash_inversion_hash(pTHX_ SV* const swash) { /* Subject to change or removal. For use only in one place in regexec.c @@ -2626,10 +2691,6 @@ Perl__swash_inversion_hash(pTHX_ SV* swash) char* key_end = (char *) uvuni_to_utf8((U8*) key, val); STRLEN key_len = key_end - key; - /* And the value is what the forward mapping is from. */ - char utf8_inverse[UTF8_MAXBYTES+1]; - char *utf8_inverse_end = (char *) uvuni_to_utf8((U8*) utf8_inverse, inverse); - /* Get the list for the map */ if ((listp = hv_fetch(ret, key, key_len, FALSE))) { list = (AV*) *listp; @@ -2641,29 +2702,28 @@ Perl__swash_inversion_hash(pTHX_ SV* swash) } } - for (i = 0; i < av_len(list); i++) { + for (i = 0; i <= av_len(list); i++) { SV** entryp = av_fetch(list, i, FALSE); SV* entry; if (entryp == NULL) { Perl_croak(aTHX_ "panic: av_fetch() unexpectedly failed"); } entry = *entryp; - if (SvCUR(entry) != key_len) { - continue; - } - if (memEQ(key, SvPVX(entry), key_len)) { + if (SvUV(entry) == val) { found_key = TRUE; break; } } + + /* Make sure there is a mapping to itself on the list */ if (! found_key) { - element = newSVpvn_flags(key, key_len, SVf_UTF8); + element = newSVuv(val); av_push(list, element); } /* Simply add the value to the list */ - element = newSVpvn_flags(utf8_inverse, utf8_inverse_end - utf8_inverse, SVf_UTF8); + element = newSVuv(inverse); av_push(list, element); /* swash_get() increments the value of val for each element in the @@ -2682,6 +2742,81 @@ Perl__swash_inversion_hash(pTHX_ SV* swash) return ret; } +HV* +Perl__swash_to_invlist(pTHX_ SV* const swash) +{ + + /* Subject to change or removal. For use only in one place in regcomp.c */ + + U8 *l, *lend; + char *loc; + STRLEN lcur; + HV *const hv = MUTABLE_HV(SvRV(swash)); + UV elements = 0; /* Number of elements in the inversion list */ + U8 empty[] = ""; + + /* The string containing the main body of the table */ + SV** const listsvp = hv_fetchs(hv, "LIST", FALSE); + SV** const typesvp = hv_fetchs(hv, "TYPE", FALSE); + SV** const bitssvp = hv_fetchs(hv, "BITS", FALSE); + + const U8* const typestr = (U8*)SvPV_nolen(*typesvp); + const STRLEN bits = SvUV(*bitssvp); + const STRLEN octets = bits >> 3; /* if bits == 1, then octets == 0 */ + + HV* invlist; + + PERL_ARGS_ASSERT__SWASH_TO_INVLIST; + + /* read $swash->{LIST} */ + if (SvPOK(*listsvp)) { + l = (U8*)SvPV(*listsvp, lcur); + } + else { + /* LIST legitimately doesn't contain a string during compilation phases + * of Perl itself, before the Unicode tables are generated. In this + * case, just fake things up by creating an empty list */ + l = empty; + lcur = 0; + } + loc = (char *) l; + lend = l + lcur; + + /* Scan the input to count the number of lines to preallocate array size + * based on worst possible case, which is each line in the input creates 2 + * elements in the inversion list: 1) the beginning of a range in the list; + * 2) the beginning of a range not in the list. */ + while ((loc = (strchr(loc, '\n'))) != NULL) { + elements += 2; + loc++; + } + + /* If the ending is somehow corrupt and isn't a new line, add another + * element for the final range that isn't in the inversion list */ + if (! (*lend == '\n' || (*lend == '\0' && *(lend - 1) == '\n'))) { + elements++; + } + + invlist = _new_invlist(elements); + + /* Now go through the input again, adding each range to the list */ + while (l < lend) { + UV start, end; + UV val; /* Not used by this function */ + + l = S_swash_scan_list_line(aTHX_ l, lend, &start, &end, &val, + cBOOL(octets), typestr); + + if (l > lend) { + break; + } + + _append_range_to_invlist(invlist, start, end); + } + + return invlist; +} + /* =for apidoc uvchr_to_utf8 @@ -2766,22 +2901,27 @@ Perl_check_utf8_print(pTHX_ register const U8* s, const STRLEN len) if (*s >= UTF8_FIRST_PROBLEMATIC_CODE_POINT_FIRST_BYTE) { STRLEN char_len; if (UTF8_IS_SUPER(s)) { - UV uv = utf8_to_uvchr(s, &char_len); - Perl_warner(aTHX_ packWARN(WARN_UTF8), - "Code point 0x%04"UVXf" is not Unicode, may not be portable", uv); - ok = FALSE; + if (ckWARN_d(WARN_NON_UNICODE)) { + UV uv = utf8_to_uvchr(s, &char_len); + Perl_warner(aTHX_ packWARN(WARN_NON_UNICODE), + "Code point 0x%04"UVXf" is not Unicode, may not be portable", uv); + ok = FALSE; + } } else if (UTF8_IS_SURROGATE(s)) { - UV uv = utf8_to_uvchr(s, &char_len); - Perl_warner(aTHX_ packWARN(WARN_UTF8), - "Unicode surrogate U+%04"UVXf" is illegal in UTF-8", uv); - ok = FALSE; + if (ckWARN_d(WARN_SURROGATE)) { + UV uv = utf8_to_uvchr(s, &char_len); + Perl_warner(aTHX_ packWARN(WARN_SURROGATE), + "Unicode surrogate U+%04"UVXf" is illegal in UTF-8", uv); + ok = FALSE; + } } else if - (UTF8_IS_NONCHAR_GIVEN_THAT_NON_SUPER_AND_GE_PROBLEMATIC(s)) + ((UTF8_IS_NONCHAR_GIVEN_THAT_NON_SUPER_AND_GE_PROBLEMATIC(s)) + && (ckWARN_d(WARN_NONCHAR))) { UV uv = utf8_to_uvchr(s, &char_len); - Perl_warner(aTHX_ packWARN(WARN_UTF8), + Perl_warner(aTHX_ packWARN(WARN_NONCHAR), "Unicode non-character U+%04"UVXf" is illegal for open interchange", uv); ok = FALSE; } @@ -2932,8 +3072,19 @@ instead of upper/lowercasing both the characters, see http://www.unicode.org/unicode/reports/tr21/ (Case Mappings). =cut */ + +/* A flags parameter has been added which may change, and hence isn't + * externally documented. Currently it is: + * 0 for as-documented above + * FOLDEQ_UTF8_NOMIX_ASCII meaning that if a non-ASCII character folds to an + ASCII one, to not match + * FOLDEQ_UTF8_LOCALE meaning that locale rules are to be used for code + * points below 256; unicode rules for above 255; and + * folds that cross those boundaries are disallowed, + * like the NOMIX_ASCII option + */ I32 -Perl_foldEQ_utf8(pTHX_ const char *s1, char **pe1, register UV l1, bool u1, const char *s2, char **pe2, register UV l2, bool u2) +Perl_foldEQ_utf8_flags(pTHX_ const char *s1, char **pe1, register UV l1, bool u1, const char *s2, char **pe2, register UV l2, bool u2, U32 flags) { dVAR; register const U8 *p1 = (const U8*)s1; /* Point to current char */ @@ -2950,7 +3101,7 @@ Perl_foldEQ_utf8(pTHX_ const char *s1, char **pe1, register UV l1, bool u1, cons U8 natbuf[2]; /* Holds native 8-bit char converted to utf8; these always fit in 2 bytes */ - PERL_ARGS_ASSERT_FOLDEQ_UTF8; + PERL_ARGS_ASSERT_FOLDEQ_UTF8_FLAGS; if (pe1) { e1 = *(U8**)pe1; @@ -2997,9 +3148,45 @@ Perl_foldEQ_utf8(pTHX_ const char *s1, char **pe1, register UV l1, bool u1, cons while (p1 < e1 && p2 < e2) { /* If at the beginning of a new character in s1, get its fold to use - * and the length of the fold */ + * and the length of the fold. (exception: locale rules just get the + * character to a single byte) */ if (n1 == 0) { - if (u1) { + + /* If in locale matching, we use two sets of rules, depending on if + * the code point is above or below 255. Here, we test for and + * handle locale rules */ + if ((flags & FOLDEQ_UTF8_LOCALE) + && (! u1 || UTF8_IS_INVARIANT(*p1) || UTF8_IS_DOWNGRADEABLE_START(*p1))) + { + /* There is no mixing of code points above and below 255. */ + if (u2 && (! UTF8_IS_INVARIANT(*p2) + && ! UTF8_IS_DOWNGRADEABLE_START(*p2))) + { + return 0; + } + + /* We handle locale rules by converting, if necessary, the code + * point to a single byte. */ + if (! u1 || UTF8_IS_INVARIANT(*p1)) { + *foldbuf1 = *p1; + } + else { + *foldbuf1 = TWO_BYTE_UTF8_TO_UNI(*p1, *(p1 + 1)); + } + n1 = 1; + } + else if (isASCII(*p1)) { /* Note, that here won't be both ASCII + and using locale rules */ + + /* If trying to mix non- with ASCII, and not supposed to, fail */ + if ((flags & FOLDEQ_UTF8_NOMIX_ASCII) && ! isASCII(*p2)) { + return 0; + } + n1 = 1; + *foldbuf1 = toLOWER(*p1); /* Folds in the ASCII range are + just lowercased */ + } + else if (u1) { to_utf8_fold(p1, foldbuf1, &n1); } else { /* Not utf8, convert to it first and then get fold */ @@ -3010,7 +3197,38 @@ Perl_foldEQ_utf8(pTHX_ const char *s1, char **pe1, register UV l1, bool u1, cons } if (n2 == 0) { /* Same for s2 */ - if (u2) { + if ((flags & FOLDEQ_UTF8_LOCALE) + && (! u2 || UTF8_IS_INVARIANT(*p2) || UTF8_IS_DOWNGRADEABLE_START(*p2))) + { + /* Here, the next char in s2 is < 256. We've already worked on + * s1, and if it isn't also < 256, can't match */ + if (u1 && (! UTF8_IS_INVARIANT(*p1) + && ! UTF8_IS_DOWNGRADEABLE_START(*p1))) + { + return 0; + } + if (! u2 || UTF8_IS_INVARIANT(*p2)) { + *foldbuf2 = *p2; + } + else { + *foldbuf2 = TWO_BYTE_UTF8_TO_UNI(*p2, *(p2 + 1)); + } + + /* Use another function to handle locale rules. We've made + * sure that both characters to compare are single bytes */ + if (! foldEQ_locale((char *) f1, (char *) foldbuf2, 1)) { + return 0; + } + n1 = n2 = 0; + } + else if (isASCII(*p2)) { + if (flags && ! isASCII(*p1)) { + return 0; + } + n2 = 1; + *foldbuf2 = toLOWER(*p2); + } + else if (u2) { to_utf8_fold(p2, foldbuf2, &n2); } else { @@ -3020,6 +3238,10 @@ Perl_foldEQ_utf8(pTHX_ const char *s1, char **pe1, register UV l1, bool u1, cons f2 = foldbuf2; } + /* Here f1 and f2 point to the beginning of the strings to compare. + * These strings are the folds of the input characters, stored in utf8. + */ + /* While there is more to look for in both folds, see if they * continue to match */ while (n1 && n2) {