diff options
| -rw-r--r-- | docs/cregex_api.md | 7 | ||||
| -rw-r--r-- | include/stc/utf8.h | 6 | ||||
| -rw-r--r-- | misc/examples/regex2.c | 6 | ||||
| -rw-r--r-- | src/cregex.c | 35 | ||||
| -rw-r--r-- | src/utf8code.c | 30 |
5 files changed, 43 insertions, 41 deletions
diff --git a/docs/cregex_api.md b/docs/cregex_api.md index 689fd33d..e528c83b 100644 --- a/docs/cregex_api.md +++ b/docs/cregex_api.md @@ -186,17 +186,16 @@ For reference, **cregex** uses the following files: | \p{XDigit} | Match UTF8 hex number | * | | \p{Nd} or \p{Digit} | Match UTF8 decimal number | * | | \p{Nl} | Match UTF8 numeric letter | * | -| \p{Ll} or \p{Lower} | Match UTF8 lower case letter | * | -| \p{Lu} or \p{Upper} | Match UTF8 upper case letter | * | +| \p{Ll} or \p{Lower} | Match UTF8 lowercase letter | * | +| \p{Lu} or \p{Upper} | Match UTF8 uppercase letter | * | | \p{Lt} | Match UTF8 titlecase letter | * | | \p{L&} or \p{Alpha} | Match UTF8 cased letter | * | | \p{Cc} | Match UTF8 control char | * | | \p{Pc} | Match UTF8 connector punctuation | * | | \p{Pd} | Match UTF8 dash punctuation | * | -| \p{Pf} | Match UTF8 final punctuation | * | | \p{Pi} | Match UTF8 initial punctuation | * | +| \p{Pf} | Match UTF8 final punctuation | * | | \p{Sc} | Match UTF8 currency symbol | * | -| \p{Sk} | Match UTF8 modifier symbol | * | | \p{Zl} | Match UTF8 line separator | * | | \p{Zp} | Match UTF8 paragraph separator | * | | \p{Sz} or \p{Space} | Match UTF8 whitespace separator | * | diff --git a/include/stc/utf8.h b/include/stc/utf8.h index b30b0061..da6643ea 100644 --- a/include/stc/utf8.h +++ b/include/stc/utf8.h @@ -5,7 +5,11 @@ #include "ccommon.h" // utf8 methods defined in src/utf8code.c: - +enum { + U8G_Cc, U8G_Lt, U8G_Nd, U8G_Nl, + U8G_Pc, U8G_Pd, U8G_Pf, U8G_Pi, + U8G_Sc, U8G_Zl, U8G_Zp, U8G_Zs, +}; extern bool utf8_isspace(uint32_t c); extern bool utf8_isdigit(uint32_t c); extern bool utf8_isxdigit(uint32_t c); diff --git a/misc/examples/regex2.c b/misc/examples/regex2.c index 55f8cfc2..abae5695 100644 --- a/misc/examples/regex2.c +++ b/misc/examples/regex2.c @@ -10,7 +10,8 @@ int main() {"(https?://|ftp://|www\\.)([0-9A-Za-z@:%_+~#=-]+\\.)+([a-z][a-z][a-z]?)(/[/0-9A-Za-z\\.@:%_+~#=\\?&-]*)?", "https://en.cppreference.com/w/cpp/regex/regex_search" }, - {"!((abc|123)+)!", "!123abcabc!"} + {"!((abc|123)+)!", "!123abcabc!"}, + {"(\\p{L&}+ )+(\\p{Nd}+)", "Großpackung süßigkeiten 199"}, }; c_AUTO (cregex, re) @@ -21,12 +22,11 @@ int main() printf("error in regex pattern: %d\n", res); continue; } - printf("input: %s\n", s[i].input); + printf("\ninput: %s\n", s[i].input); c_FORMATCH (j, &re, s[i].input) { c_FORRANGE (k, cregex_captures(&re)) printf(" submatch %lld: %.*s\n", k, c_ARGSV(j.match[k])); - puts(""); } } } diff --git a/src/cregex.c b/src/cregex.c index 7b528550..006c2d05 100644 --- a/src/cregex.c +++ b/src/cregex.c @@ -133,22 +133,22 @@ enum { UTF_an , UTF_AN, /* utf8 alphanumeric */ UTF_wr , UTF_WR, /* utf8 word */ UTF_xd , UTF_XD, /* utf8 hex digit */ - U8G_tmp , U8G = U8G_tmp + (U8G_tmp & 1), /* force even */ - UTF_cc = U8G, UTF_CC, /* utf8 control char */ UTF_lc , UTF_LC, /* utf8 letter cased */ UTF_ll , UTF_LL, /* utf8 letter lowercase */ - UTF_lt , UTF_LT, /* utf8 letter titlecase */ UTF_lu , UTF_LU, /* utf8 letter uppercase */ - UTF_nd , UTF_ND, /* utf8 number decimal */ - UTF_nl , UTF_NL, /* utf8 number letter */ - UTF_pc , UTF_PC, /* utf8 punct connector */ - UTF_pd , UTF_PD, /* utf8 punct dash */ - UTF_pf , UTF_PF, /* utf8 punct final */ - UTF_pi , UTF_PI, /* utf8 punct initial */ - UTF_sc , UTF_SC, /* utf8 symbol currency */ - UTF_zl , UTF_ZL, /* utf8 separator line */ - UTF_zp , UTF_ZP, /* utf8 separator paragraph */ - UTF_zs , UTF_ZS, /* utf8 separator space */ + UTF_GRP = 0x8150000, + UTF_cc = UTF_GRP+2*U8G_Cc, UTF_CC, /* utf8 control char */ + UTF_lt = UTF_GRP+2*U8G_Lt, UTF_LT, /* utf8 letter titlecase */ + UTF_nd = UTF_GRP+2*U8G_Nd, UTF_ND, /* utf8 number decimal */ + UTF_nl = UTF_GRP+2*U8G_Nl, UTF_NL, /* utf8 number letter */ + UTF_pc = UTF_GRP+2*U8G_Pc, UTF_PC, /* utf8 punct connector */ + UTF_pd = UTF_GRP+2*U8G_Pd, UTF_PD, /* utf8 punct dash */ + UTF_pf = UTF_GRP+2*U8G_Pf, UTF_PF, /* utf8 punct final */ + UTF_pi = UTF_GRP+2*U8G_Pi, UTF_PI, /* utf8 punct initial */ + UTF_sc = UTF_GRP+2*U8G_Sc, UTF_SC, /* utf8 symbol currency */ + UTF_zl = UTF_GRP+2*U8G_Zl, UTF_ZL, /* utf8 separator line */ + UTF_zp = UTF_GRP+2*U8G_Zp, UTF_ZP, /* utf8 separator paragraph */ + UTF_zs = UTF_GRP+2*U8G_Zs, UTF_ZS, /* utf8 separator space */ TOK_ANY = 0x8200000, /* Any character except newline, . */ TOK_ANYNL , /* Any character including newline, . */ TOK_NOP , /* No operation, internal use only */ @@ -896,7 +896,8 @@ out: static int _runematch(_Rune s, _Rune r) { - int inv = 0, n; + int inv = 0; + uint32_t n; switch (s) { case ASC_D: inv = 1; case ASC_d: return inv ^ (isdigit(r) != 0); case ASC_S: inv = 1; case ASC_s: return inv ^ (isspace(r) != 0); @@ -915,11 +916,11 @@ _runematch(_Rune s, _Rune r) case UTF_AN: inv = 1; case UTF_an: return inv ^ utf8_isalnum(r); case UTF_WR: inv = 1; case UTF_wr: return inv ^ (utf8_isalnum(r) | (r == '_')); case UTF_XD: inv = 1; case UTF_xd: return inv ^ utf8_isxdigit(r); + case UTF_LL: inv = 1; case UTF_ll: return inv ^ utf8_islower(r); + case UTF_LU: inv = 1; case UTF_lu: return inv ^ utf8_isupper(r); case UTF_LC: inv = 1; case UTF_lc: return inv ^ utf8_isalpha(r); case UTF_CC: case UTF_cc: - case UTF_LL: case UTF_ll: case UTF_LT: case UTF_lt: - case UTF_LU: case UTF_lu: case UTF_ND: case UTF_nd: case UTF_NL: case UTF_nl: case UTF_PC: case UTF_pc: @@ -930,7 +931,7 @@ _runematch(_Rune s, _Rune r) case UTF_ZL: case UTF_zl: case UTF_ZP: case UTF_zp: case UTF_ZS: case UTF_zs: - n = s - U8G; + n = s - UTF_GRP; inv = n & 1; return inv ^ utf8_isgroup(n / 2, r); } diff --git a/src/utf8code.c b/src/utf8code.c index 6fe8515e..8f2ce107 100644 --- a/src/utf8code.c +++ b/src/utf8code.c @@ -125,7 +125,6 @@ typedef struct { static const UGroup unicode_groups[]; static const int num_unicode_groups; -static const int Lt_group; bool utf8_isgroup(int group, uint32_t c) { for (int j=0; j<unicode_groups[group].nr16; ++j) { @@ -153,7 +152,7 @@ bool utf8_isalnum(uint32_t c) { bool utf8_isalpha(uint32_t c) { if (c < 128) return isalpha(c) != 0; - return utf8_islower(c) || utf8_isupper(c) || utf8_isgroup(Lt_group, c); + return utf8_islower(c) || utf8_isupper(c) || utf8_isgroup(U8G_Lt, c); } static const URange16 Cc_range16[] = { // Control @@ -321,24 +320,23 @@ static const URange16 Zs_range16[] = { // Space separator }; #define UNI_ENTRY(Code) \ - { #Code, Code##_range16, sizeof(Code##_range16)/2 } + { #Code, Code##_range16, sizeof(Code##_range16)/(2*2) } static const UGroup unicode_groups[] = { - UNI_ENTRY(Cc), - UNI_ENTRY(Lt), - UNI_ENTRY(Nd), - UNI_ENTRY(Nl), - UNI_ENTRY(Pc), - UNI_ENTRY(Pd), - UNI_ENTRY(Pf), - UNI_ENTRY(Pi), - UNI_ENTRY(Sc), - UNI_ENTRY(Zl), - UNI_ENTRY(Zp), - UNI_ENTRY(Zs), + [U8G_Cc] = UNI_ENTRY(Cc), + [U8G_Lt] = UNI_ENTRY(Lt), + [U8G_Nd] = UNI_ENTRY(Nd), + [U8G_Nl] = UNI_ENTRY(Nl), + [U8G_Pc] = UNI_ENTRY(Pc), + [U8G_Pd] = UNI_ENTRY(Pd), + [U8G_Pf] = UNI_ENTRY(Pf), + [U8G_Pi] = UNI_ENTRY(Pi), + [U8G_Sc] = UNI_ENTRY(Sc), + [U8G_Zl] = UNI_ENTRY(Zl), + [U8G_Zp] = UNI_ENTRY(Zp), + [U8G_Zs] = UNI_ENTRY(Zs), }; -static const int Lt_group = 1; static const int num_unicode_groups = sizeof unicode_groups / sizeof unicode_groups[0]; #endif |