open-dsi
/
postgres
mirror of https://github.com/postgres/postgres
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Some languages have symbols with zero display's width or/and vowels/signs which

Browse Source 
are not an alphabetic character although they are not word-breakers too.
So, treat them as part of word.

Per off-list discussion with Dibyendra Hyoju <dibyendra@gmail.com> and
and Bal Krishna Bal <balkrishna7bal@gmail.com> about Nepali language and
Devanagari alphabet.
REL8_5_ALPHA1_BRANCH
Teodor Sigaev 17 years ago
parent c394bd331a
commit e43bb5beb7
1 changed files with 299 additions and 1 deletions
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Show Stats Download Patch File Download Diff File
  1. 300
      src/backend/tsearch/wparser_def.c

300
src/backend/tsearch/wparser_def.c
Unescape View File

@ -7,7 +7,7 @@
*
*
* IDENTIFICATION
* $PostgreSQL: pgsql/src/backend/tsearch/wparser_def.c,v 1.22 2009/03/10 17:32:14 teodor Exp $
* $PostgreSQL: pgsql/src/backend/tsearch/wparser_def.c,v 1.23 2009/03/11 16:03:40 teodor Exp $
*
*-------------------------------------------------------------------------
*/
@ -659,6 +659,291 @@ p_isURLPath(TParser *prs)
return res;
}
/*
* returns true if current character has zero display length or
* it's a special sign in several languages. Such characters
* aren't a word-breaker although they aren't an isalpha.
* In beginning of word they aren't a part of it.
*/
static int
p_isspecial(TParser *prs)
{
/*
* pg_dsplen could return -1 which means error or control character
*/
if ( pg_dsplen(prs->str + prs->state->posbyte) == 0 )
return 1;
#ifdef USE_WIDE_UPPER_LOWER
/*
* Unicode Characters in the 'Mark, Spacing Combining' Category
* That characters are not alpha although they are not breakers
* of word too.
* Check that only in utf encoding, because other encodings
* aren't supported by postgres or even exists.
*/
if ( GetDatabaseEncoding() == PG_UTF8 && prs->usewide )
{
static pg_wchar strange_letter[] = {
/*
* use binary search, so elements
* should be ordered
*/
0x0903, /* DEVANAGARI SIGN VISARGA */
0x093E, /* DEVANAGARI VOWEL SIGN AA */
0x093F, /* DEVANAGARI VOWEL SIGN I */
0x0940, /* DEVANAGARI VOWEL SIGN II */
0x0949, /* DEVANAGARI VOWEL SIGN CANDRA O */
0x094A, /* DEVANAGARI VOWEL SIGN SHORT O */
0x094B, /* DEVANAGARI VOWEL SIGN O */
0x094C, /* DEVANAGARI VOWEL SIGN AU */
0x0982, /* BENGALI SIGN ANUSVARA */
0x0983, /* BENGALI SIGN VISARGA */
0x09BE, /* BENGALI VOWEL SIGN AA */
0x09BF, /* BENGALI VOWEL SIGN I */
0x09C0, /* BENGALI VOWEL SIGN II */
0x09C7, /* BENGALI VOWEL SIGN E */
0x09C8, /* BENGALI VOWEL SIGN AI */
0x09CB, /* BENGALI VOWEL SIGN O */
0x09CC, /* BENGALI VOWEL SIGN AU */
0x09D7, /* BENGALI AU LENGTH MARK */
0x0A03, /* GURMUKHI SIGN VISARGA */
0x0A3E, /* GURMUKHI VOWEL SIGN AA */
0x0A3F, /* GURMUKHI VOWEL SIGN I */
0x0A40, /* GURMUKHI VOWEL SIGN II */
0x0A83, /* GUJARATI SIGN VISARGA */
0x0ABE, /* GUJARATI VOWEL SIGN AA */
0x0ABF, /* GUJARATI VOWEL SIGN I */
0x0AC0, /* GUJARATI VOWEL SIGN II */
0x0AC9, /* GUJARATI VOWEL SIGN CANDRA O */
0x0ACB, /* GUJARATI VOWEL SIGN O */
0x0ACC, /* GUJARATI VOWEL SIGN AU */
0x0B02, /* ORIYA SIGN ANUSVARA */
0x0B03, /* ORIYA SIGN VISARGA */
0x0B3E, /* ORIYA VOWEL SIGN AA */
0x0B40, /* ORIYA VOWEL SIGN II */
0x0B47, /* ORIYA VOWEL SIGN E */
0x0B48, /* ORIYA VOWEL SIGN AI */
0x0B4B, /* ORIYA VOWEL SIGN O */
0x0B4C, /* ORIYA VOWEL SIGN AU */
0x0B57, /* ORIYA AU LENGTH MARK */
0x0BBE, /* TAMIL VOWEL SIGN AA */
0x0BBF, /* TAMIL VOWEL SIGN I */
0x0BC1, /* TAMIL VOWEL SIGN U */
0x0BC2, /* TAMIL VOWEL SIGN UU */
0x0BC6, /* TAMIL VOWEL SIGN E */
0x0BC7, /* TAMIL VOWEL SIGN EE */
0x0BC8, /* TAMIL VOWEL SIGN AI */
0x0BCA, /* TAMIL VOWEL SIGN O */
0x0BCB, /* TAMIL VOWEL SIGN OO */
0x0BCC, /* TAMIL VOWEL SIGN AU */
0x0BD7, /* TAMIL AU LENGTH MARK */
0x0C01, /* TELUGU SIGN CANDRABINDU */
0x0C02, /* TELUGU SIGN ANUSVARA */
0x0C03, /* TELUGU SIGN VISARGA */
0x0C41, /* TELUGU VOWEL SIGN U */
0x0C42, /* TELUGU VOWEL SIGN UU */
0x0C43, /* TELUGU VOWEL SIGN VOCALIC R */
0x0C44, /* TELUGU VOWEL SIGN VOCALIC RR */
0x0C82, /* KANNADA SIGN ANUSVARA */
0x0C83, /* KANNADA SIGN VISARGA */
0x0CBE, /* KANNADA VOWEL SIGN AA */
0x0CC0, /* KANNADA VOWEL SIGN II */
0x0CC1, /* KANNADA VOWEL SIGN U */
0x0CC2, /* KANNADA VOWEL SIGN UU */
0x0CC3, /* KANNADA VOWEL SIGN VOCALIC R */
0x0CC4, /* KANNADA VOWEL SIGN VOCALIC RR */
0x0CC7, /* KANNADA VOWEL SIGN EE */
0x0CC8, /* KANNADA VOWEL SIGN AI */
0x0CCA, /* KANNADA VOWEL SIGN O */
0x0CCB, /* KANNADA VOWEL SIGN OO */
0x0CD5, /* KANNADA LENGTH MARK */
0x0CD6, /* KANNADA AI LENGTH MARK */
0x0D02, /* MALAYALAM SIGN ANUSVARA */
0x0D03, /* MALAYALAM SIGN VISARGA */
0x0D3E, /* MALAYALAM VOWEL SIGN AA */
0x0D3F, /* MALAYALAM VOWEL SIGN I */
0x0D40, /* MALAYALAM VOWEL SIGN II */
0x0D46, /* MALAYALAM VOWEL SIGN E */
0x0D47, /* MALAYALAM VOWEL SIGN EE */
0x0D48, /* MALAYALAM VOWEL SIGN AI */
0x0D4A, /* MALAYALAM VOWEL SIGN O */
0x0D4B, /* MALAYALAM VOWEL SIGN OO */
0x0D4C, /* MALAYALAM VOWEL SIGN AU */
0x0D57, /* MALAYALAM AU LENGTH MARK */
0x0D82, /* SINHALA SIGN ANUSVARAYA */
0x0D83, /* SINHALA SIGN VISARGAYA */
0x0DCF, /* SINHALA VOWEL SIGN AELA-PILLA */
0x0DD0, /* SINHALA VOWEL SIGN KETTI AEDA-PILLA */
0x0DD1, /* SINHALA VOWEL SIGN DIGA AEDA-PILLA */
0x0DD8, /* SINHALA VOWEL SIGN GAETTA-PILLA */
0x0DD9, /* SINHALA VOWEL SIGN KOMBUVA */
0x0DDA, /* SINHALA VOWEL SIGN DIGA KOMBUVA */
0x0DDB, /* SINHALA VOWEL SIGN KOMBU DEKA */
0x0DDC, /* SINHALA VOWEL SIGN KOMBUVA HAA AELA-PILLA */
0x0DDD, /* SINHALA VOWEL SIGN KOMBUVA HAA DIGA AELA-PILLA */
0x0DDE, /* SINHALA VOWEL SIGN KOMBUVA HAA GAYANUKITTA */
0x0DDF, /* SINHALA VOWEL SIGN GAYANUKITTA */
0x0DF2, /* SINHALA VOWEL SIGN DIGA GAETTA-PILLA */
0x0DF3, /* SINHALA VOWEL SIGN DIGA GAYANUKITTA */
0x0F3E, /* TIBETAN SIGN YAR TSHES */
0x0F3F, /* TIBETAN SIGN MAR TSHES */
0x0F7F, /* TIBETAN SIGN RNAM BCAD */
0x102B, /* MYANMAR VOWEL SIGN TALL AA */
0x102C, /* MYANMAR VOWEL SIGN AA */
0x1031, /* MYANMAR VOWEL SIGN E */
0x1038, /* MYANMAR SIGN VISARGA */
0x103B, /* MYANMAR CONSONANT SIGN MEDIAL YA */
0x103C, /* MYANMAR CONSONANT SIGN MEDIAL RA */
0x1056, /* MYANMAR VOWEL SIGN VOCALIC R */
0x1057, /* MYANMAR VOWEL SIGN VOCALIC RR */
0x1062, /* MYANMAR VOWEL SIGN SGAW KAREN EU */
0x1063, /* MYANMAR TONE MARK SGAW KAREN HATHI */
0x1064, /* MYANMAR TONE MARK SGAW KAREN KE PHO */
0x1067, /* MYANMAR VOWEL SIGN WESTERN PWO KAREN EU */
0x1068, /* MYANMAR VOWEL SIGN WESTERN PWO KAREN UE */
0x1069, /* MYANMAR SIGN WESTERN PWO KAREN TONE-1 */
0x106A, /* MYANMAR SIGN WESTERN PWO KAREN TONE-2 */
0x106B, /* MYANMAR SIGN WESTERN PWO KAREN TONE-3 */
0x106C, /* MYANMAR SIGN WESTERN PWO KAREN TONE-4 */
0x106D, /* MYANMAR SIGN WESTERN PWO KAREN TONE-5 */
0x1083, /* MYANMAR VOWEL SIGN SHAN AA */
0x1084, /* MYANMAR VOWEL SIGN SHAN E */
0x1087, /* MYANMAR SIGN SHAN TONE-2 */
0x1088, /* MYANMAR SIGN SHAN TONE-3 */
0x1089, /* MYANMAR SIGN SHAN TONE-5 */
0x108A, /* MYANMAR SIGN SHAN TONE-6 */
0x108B, /* MYANMAR SIGN SHAN COUNCIL TONE-2 */
0x108C, /* MYANMAR SIGN SHAN COUNCIL TONE-3 */
0x108F, /* MYANMAR SIGN RUMAI PALAUNG TONE-5 */
0x17B6, /* KHMER VOWEL SIGN AA */
0x17BE, /* KHMER VOWEL SIGN OE */
0x17BF, /* KHMER VOWEL SIGN YA */
0x17C0, /* KHMER VOWEL SIGN IE */
0x17C1, /* KHMER VOWEL SIGN E */
0x17C2, /* KHMER VOWEL SIGN AE */
0x17C3, /* KHMER VOWEL SIGN AI */
0x17C4, /* KHMER VOWEL SIGN OO */
0x17C5, /* KHMER VOWEL SIGN AU */
0x17C7, /* KHMER SIGN REAHMUK */
0x17C8, /* KHMER SIGN YUUKALEAPINTU */
0x1923, /* LIMBU VOWEL SIGN EE */
0x1924, /* LIMBU VOWEL SIGN AI */
0x1925, /* LIMBU VOWEL SIGN OO */
0x1926, /* LIMBU VOWEL SIGN AU */
0x1929, /* LIMBU SUBJOINED LETTER YA */
0x192A, /* LIMBU SUBJOINED LETTER RA */
0x192B, /* LIMBU SUBJOINED LETTER WA */
0x1930, /* LIMBU SMALL LETTER KA */
0x1931, /* LIMBU SMALL LETTER NGA */
0x1933, /* LIMBU SMALL LETTER TA */
0x1934, /* LIMBU SMALL LETTER NA */
0x1935, /* LIMBU SMALL LETTER PA */
0x1936, /* LIMBU SMALL LETTER MA */
0x1937, /* LIMBU SMALL LETTER RA */
0x1938, /* LIMBU SMALL LETTER LA */
0x19B0, /* NEW TAI LUE VOWEL SIGN VOWEL SHORTENER */
0x19B1, /* NEW TAI LUE VOWEL SIGN AA */
0x19B2, /* NEW TAI LUE VOWEL SIGN II */
0x19B3, /* NEW TAI LUE VOWEL SIGN U */
0x19B4, /* NEW TAI LUE VOWEL SIGN UU */
0x19B5, /* NEW TAI LUE VOWEL SIGN E */
0x19B6, /* NEW TAI LUE VOWEL SIGN AE */
0x19B7, /* NEW TAI LUE VOWEL SIGN O */
0x19B8, /* NEW TAI LUE VOWEL SIGN OA */
0x19B9, /* NEW TAI LUE VOWEL SIGN UE */
0x19BA, /* NEW TAI LUE VOWEL SIGN AY */
0x19BB, /* NEW TAI LUE VOWEL SIGN AAY */
0x19BC, /* NEW TAI LUE VOWEL SIGN UY */
0x19BD, /* NEW TAI LUE VOWEL SIGN OY */
0x19BE, /* NEW TAI LUE VOWEL SIGN OAY */
0x19BF, /* NEW TAI LUE VOWEL SIGN UEY */
0x19C0, /* NEW TAI LUE VOWEL SIGN IY */
0x19C8, /* NEW TAI LUE TONE MARK-1 */
0x19C9, /* NEW TAI LUE TONE MARK-2 */
0x1A19, /* BUGINESE VOWEL SIGN E */
0x1A1A, /* BUGINESE VOWEL SIGN O */
0x1A1B, /* BUGINESE VOWEL SIGN AE */
0x1B04, /* BALINESE SIGN BISAH */
0x1B35, /* BALINESE VOWEL SIGN TEDUNG */
0x1B3B, /* BALINESE VOWEL SIGN RA REPA TEDUNG */
0x1B3D, /* BALINESE VOWEL SIGN LA LENGA TEDUNG */
0x1B3E, /* BALINESE VOWEL SIGN TALING */
0x1B3F, /* BALINESE VOWEL SIGN TALING REPA */
0x1B40, /* BALINESE VOWEL SIGN TALING TEDUNG */
0x1B41, /* BALINESE VOWEL SIGN TALING REPA TEDUNG */
0x1B43, /* BALINESE VOWEL SIGN PEPET TEDUNG */
0x1B44, /* BALINESE ADEG ADEG */
0x1B82, /* SUNDANESE SIGN PANGWISAD */
0x1BA1, /* SUNDANESE CONSONANT SIGN PAMINGKAL */
0x1BA6, /* SUNDANESE VOWEL SIGN PANAELAENG */
0x1BA7, /* SUNDANESE VOWEL SIGN PANOLONG */
0x1BAA, /* SUNDANESE SIGN PAMAAEH */
0x1C24, /* LEPCHA SUBJOINED LETTER YA */
0x1C25, /* LEPCHA SUBJOINED LETTER RA */
0x1C26, /* LEPCHA VOWEL SIGN AA */
0x1C27, /* LEPCHA VOWEL SIGN I */
0x1C28, /* LEPCHA VOWEL SIGN O */
0x1C29, /* LEPCHA VOWEL SIGN OO */
0x1C2A, /* LEPCHA VOWEL SIGN U */
0x1C2B, /* LEPCHA VOWEL SIGN UU */
0x1C34, /* LEPCHA CONSONANT SIGN NYIN-DO */
0x1C35, /* LEPCHA CONSONANT SIGN KANG */
0xA823, /* SYLOTI NAGRI VOWEL SIGN A */
0xA824, /* SYLOTI NAGRI VOWEL SIGN I */
0xA827, /* SYLOTI NAGRI VOWEL SIGN OO */
0xA880, /* SAURASHTRA SIGN ANUSVARA */
0xA881, /* SAURASHTRA SIGN VISARGA */
0xA8B4, /* SAURASHTRA CONSONANT SIGN HAARU */
0xA8B5, /* SAURASHTRA VOWEL SIGN AA */
0xA8B6, /* SAURASHTRA VOWEL SIGN I */
0xA8B7, /* SAURASHTRA VOWEL SIGN II */
0xA8B8, /* SAURASHTRA VOWEL SIGN U */
0xA8B9, /* SAURASHTRA VOWEL SIGN UU */
0xA8BA, /* SAURASHTRA VOWEL SIGN VOCALIC R */
0xA8BB, /* SAURASHTRA VOWEL SIGN VOCALIC RR */
0xA8BC, /* SAURASHTRA VOWEL SIGN VOCALIC L */
0xA8BD, /* SAURASHTRA VOWEL SIGN VOCALIC LL */
0xA8BE, /* SAURASHTRA VOWEL SIGN E */
0xA8BF, /* SAURASHTRA VOWEL SIGN EE */
0xA8C0, /* SAURASHTRA VOWEL SIGN AI */
0xA8C1, /* SAURASHTRA VOWEL SIGN O */
0xA8C2, /* SAURASHTRA VOWEL SIGN OO */
0xA8C3, /* SAURASHTRA VOWEL SIGN AU */
0xA952, /* REJANG CONSONANT SIGN H */
0xA953, /* REJANG VIRAMA */
0xAA2F, /* CHAM VOWEL SIGN O */
0xAA30, /* CHAM VOWEL SIGN AI */
0xAA33, /* CHAM CONSONANT SIGN YA */
0xAA34, /* CHAM CONSONANT SIGN RA */
0xAA4D /* CHAM CONSONANT SIGN FINAL H */
};
pg_wchar *StopLow = strange_letter,
*StopHigh = strange_letter + lengthof(strange_letter),
*StopMiddle;
pg_wchar c;
if ( prs->pgwstr )
c = *(prs->pgwstr + prs->state->poschar);
else
c = (pg_wchar) *(prs->wstr + prs->state->poschar);
while( StopLow < StopHigh )
{
StopMiddle = StopLow + ((StopHigh - StopLow) >> 1);
if ( *StopMiddle == c )
return 1;
else if ( *StopMiddle < c )
StopLow = StopMiddle + 1;
else
StopHigh = StopMiddle;
}
}
#endif
return 0;
}
/*
* Table of state/action of parser
*/
@ -683,6 +968,7 @@ static const TParserStateActionItem actionTPS_Base[] = {
static const TParserStateActionItem actionTPS_InNumWord[] = {
{p_isEOF, 0, A_BINGO, TPS_Base, NUMWORD, NULL},
{p_isalnum, 0, A_NEXT, TPS_InNumWord, 0, NULL},
{p_isspecial, 0, A_NEXT, TPS_InNumWord, 0, NULL},
{p_iseqC, '@', A_PUSH, TPS_InEmail, 0, NULL},
{p_iseqC, '/', A_PUSH, TPS_InFileFirst, 0, NULL},
{p_iseqC, '.', A_PUSH, TPS_InFileNext, 0, NULL},
@ -703,12 +989,14 @@ static const TParserStateActionItem actionTPS_InAsciiWord[] = {
{p_isdigit, 0, A_PUSH, TPS_InHost, 0, NULL},
{p_isdigit, 0, A_NEXT, TPS_InNumWord, 0, NULL},
{p_isalpha, 0, A_NEXT, TPS_InWord, 0, NULL},
{p_isspecial, 0, A_NEXT, TPS_InWord, 0, NULL},
{NULL, 0, A_BINGO, TPS_Base, ASCIIWORD, NULL}
};
static const TParserStateActionItem actionTPS_InWord[] = {
{p_isEOF, 0, A_BINGO, TPS_Base, WORD_T, NULL},
{p_isalpha, 0, A_NEXT, TPS_Null, 0, NULL},
{p_isspecial, 0, A_NEXT, TPS_Null, 0, NULL},
{p_isdigit, 0, A_NEXT, TPS_InNumWord, 0, NULL},
{p_iseqC, '-', A_PUSH, TPS_InHyphenWordFirst, 0, NULL},
{NULL, 0, A_BINGO, TPS_Base, WORD_T, NULL}
@ -723,6 +1011,7 @@ static const TParserStateActionItem actionTPS_InUnsignedInt[] = {
{p_iseqC, 'E', A_PUSH, TPS_InMantissaFirst, 0, NULL},
{p_isasclet, 0, A_PUSH, TPS_InHost, 0, NULL},
{p_isalpha, 0, A_NEXT, TPS_InNumWord, 0, NULL},
{p_isspecial, 0, A_NEXT, TPS_InNumWord, 0, NULL},
{p_iseqC, '/', A_PUSH, TPS_InFileFirst, 0, NULL},
{NULL, 0, A_BINGO, TPS_Base, UNSIGNEDINT, NULL}
};
@ -1196,6 +1485,7 @@ static const TParserStateActionItem actionTPS_InHyphenAsciiWord[] = {
{p_isEOF, 0, A_BINGO | A_CLRALL, TPS_InParseHyphen, ASCIIHWORD, SpecialHyphen},
{p_isasclet, 0, A_NEXT, TPS_InHyphenAsciiWord, 0, NULL},
{p_isalpha, 0, A_NEXT, TPS_InHyphenWord, 0, NULL},
{p_isspecial, 0, A_NEXT, TPS_InHyphenWord, 0, NULL},
{p_isdigit, 0, A_NEXT, TPS_InHyphenNumWord, 0, NULL},
{p_iseqC, '-', A_PUSH, TPS_InHyphenAsciiWordFirst, 0, NULL},
{NULL, 0, A_BINGO | A_CLRALL, TPS_InParseHyphen, ASCIIHWORD, SpecialHyphen}
@ -1211,6 +1501,7 @@ static const TParserStateActionItem actionTPS_InHyphenWordFirst[] = {
static const TParserStateActionItem actionTPS_InHyphenWord[] = {
{p_isEOF, 0, A_BINGO | A_CLRALL, TPS_InParseHyphen, HWORD, SpecialHyphen},
{p_isalpha, 0, A_NEXT, TPS_InHyphenWord, 0, NULL},
{p_isspecial, 0, A_NEXT, TPS_InHyphenWord, 0, NULL},
{p_isdigit, 0, A_NEXT, TPS_InHyphenNumWord, 0, NULL},
{p_iseqC, '-', A_PUSH, TPS_InHyphenWordFirst, 0, NULL},
{NULL, 0, A_BINGO | A_CLRALL, TPS_InParseHyphen, HWORD, SpecialHyphen}
@ -1226,6 +1517,7 @@ static const TParserStateActionItem actionTPS_InHyphenNumWordFirst[] = {
static const TParserStateActionItem actionTPS_InHyphenNumWord[] = {
{p_isEOF, 0, A_BINGO | A_CLRALL, TPS_InParseHyphen, NUMHWORD, SpecialHyphen},
{p_isalnum, 0, A_NEXT, TPS_InHyphenNumWord, 0, NULL},
{p_isspecial, 0, A_NEXT, TPS_InHyphenNumWord, 0, NULL},
{p_iseqC, '-', A_PUSH, TPS_InHyphenNumWordFirst, 0, NULL},
{NULL, 0, A_BINGO | A_CLRALL, TPS_InParseHyphen, NUMHWORD, SpecialHyphen}
};
@ -1234,6 +1526,7 @@ static const TParserStateActionItem actionTPS_InHyphenDigitLookahead[] = {
{p_isEOF, 0, A_POP, TPS_Null, 0, NULL},
{p_isdigit, 0, A_NEXT, TPS_InHyphenDigitLookahead, 0, NULL},
{p_isalpha, 0, A_NEXT, TPS_InHyphenNumWord, 0, NULL},
{p_isspecial, 0, A_NEXT, TPS_InHyphenNumWord, 0, NULL},
{NULL, 0, A_POP, TPS_Null, 0, NULL}
};
@ -1249,12 +1542,14 @@ static const TParserStateActionItem actionTPS_InParseHyphen[] = {
static const TParserStateActionItem actionTPS_InParseHyphenHyphen[] = {
{p_isEOF, 0, A_POP, TPS_Null, 0, NULL},
{p_isalnum, 0, A_BINGO | A_CLEAR, TPS_InParseHyphen, SPACE, NULL},
{p_isspecial, 0, A_BINGO | A_CLEAR, TPS_InParseHyphen, SPACE, NULL},
{NULL, 0, A_POP, TPS_Null, 0, NULL}
};
static const TParserStateActionItem actionTPS_InHyphenWordPart[] = {
{p_isEOF, 0, A_BINGO, TPS_Base, PARTHWORD, NULL},
{p_isalpha, 0, A_NEXT, TPS_InHyphenWordPart, 0, NULL},
{p_isspecial, 0, A_NEXT, TPS_InHyphenWordPart, 0, NULL},
{p_isdigit, 0, A_NEXT, TPS_InHyphenNumWordPart, 0, NULL},
{NULL, 0, A_BINGO, TPS_InParseHyphen, PARTHWORD, NULL}
};
@ -1263,6 +1558,7 @@ static const TParserStateActionItem actionTPS_InHyphenAsciiWordPart[] = {
{p_isEOF, 0, A_BINGO, TPS_Base, ASCIIPARTHWORD, NULL},
{p_isasclet, 0, A_NEXT, TPS_InHyphenAsciiWordPart, 0, NULL},
{p_isalpha, 0, A_NEXT, TPS_InHyphenWordPart, 0, NULL},
{p_isspecial, 0, A_NEXT, TPS_InHyphenWordPart, 0, NULL},
{p_isdigit, 0, A_NEXT, TPS_InHyphenNumWordPart, 0, NULL},
{NULL, 0, A_BINGO, TPS_InParseHyphen, ASCIIPARTHWORD, NULL}
};
@ -1270,6 +1566,7 @@ static const TParserStateActionItem actionTPS_InHyphenAsciiWordPart[] = {
static const TParserStateActionItem actionTPS_InHyphenNumWordPart[] = {
{p_isEOF, 0, A_BINGO, TPS_Base, NUMPARTHWORD, NULL},
{p_isalnum, 0, A_NEXT, TPS_InHyphenNumWordPart, 0, NULL},
{p_isspecial, 0, A_NEXT, TPS_InHyphenNumWordPart, 0, NULL},
{NULL, 0, A_BINGO, TPS_InParseHyphen, NUMPARTHWORD, NULL}
};
@ -1277,6 +1574,7 @@ static const TParserStateActionItem actionTPS_InHyphenUnsignedInt[] = {
{p_isEOF, 0, A_POP, TPS_Null, 0, NULL},
{p_isdigit, 0, A_NEXT, TPS_Null, 0, NULL},
{p_isalpha, 0, A_CLEAR, TPS_InHyphenNumWordPart, 0, NULL},
{p_isspecial, 0, A_CLEAR, TPS_InHyphenNumWordPart, 0, NULL},
{NULL, 0, A_POP, TPS_Null, 0, NULL}
};

Write Preview
Loading…
Cancel
Save