database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-11-21 00:42:43 +03:00
Code Activity

pgindent run before PG 9.1 beta 1.

Browse Source
This commit is contained in:
Bruce Momjian
2011-04-10 11:42:00 -04:00
parent 9a8b73147c
commit bf50caf105
446 changed files with 5737 additions and 5258 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/backend/tsearch/spell.c
View File

@@ -74,7 +74,7 @@ NIFinishBuild(IspellDict *Conf)
* doesn't need that. The cpalloc and cpalloc0 macros are just documentation
* to indicate which allocations actually require zeroing.
*/
#define COMPACT_ALLOC_CHUNK 8192 /* must be > aset.c's allocChunkLimit */
#define COMPACT_ALLOC_CHUNK 8192 /* must be > aset.c's allocChunkLimit */
#define COMPACT_MAX_REQ 1024 /* must be < COMPACT_ALLOC_CHUNK */
static void *

11
src/backend/tsearch/ts_locale.c
View File

@@ -28,7 +28,7 @@ t_isdigit(const char *ptr)
{
int clen = pg_mblen(ptr);
wchar_t character[2];
Oid collation = DEFAULT_COLLATION_OID; /*TODO*/
Oid collation = DEFAULT_COLLATION_OID; /* TODO */
if (clen == 1 || lc_ctype_is_c(collation))
return isdigit(TOUCHAR(ptr));
@@ -43,7 +43,7 @@ t_isspace(const char *ptr)
{
int clen = pg_mblen(ptr);
wchar_t character[2];
Oid collation = DEFAULT_COLLATION_OID; /*TODO*/
Oid collation = DEFAULT_COLLATION_OID; /* TODO */
if (clen == 1 || lc_ctype_is_c(collation))
return isspace(TOUCHAR(ptr));
@@ -58,7 +58,7 @@ t_isalpha(const char *ptr)
{
int clen = pg_mblen(ptr);
wchar_t character[2];
Oid collation = DEFAULT_COLLATION_OID; /*TODO*/
Oid collation = DEFAULT_COLLATION_OID; /* TODO */
if (clen == 1 || lc_ctype_is_c(collation))
return isalpha(TOUCHAR(ptr));
@@ -73,7 +73,7 @@ t_isprint(const char *ptr)
{
int clen = pg_mblen(ptr);
wchar_t character[2];
Oid collation = DEFAULT_COLLATION_OID; /*TODO*/
Oid collation = DEFAULT_COLLATION_OID; /* TODO */
if (clen == 1 || lc_ctype_is_c(collation))
return isprint(TOUCHAR(ptr));
@@ -243,8 +243,9 @@ char *
lowerstr_with_len(const char *str, int len)
{
char *out;
#ifdef USE_WIDE_UPPER_LOWER
Oid collation = DEFAULT_COLLATION_OID; /*TODO*/
Oid collation = DEFAULT_COLLATION_OID; /* TODO */
#endif
if (len == 0)

8
src/backend/tsearch/ts_selfuncs.c
View File

@@ -304,9 +304,9 @@ tsquery_opr_selec(QueryItem *item, char *operand,
/*
* Our strategy is to scan through the MCV list and add up the
* frequencies of the ones that match the prefix, thereby
* assuming that the MCVs are representative of the whole lexeme
* population in this respect. Compare histogram_selectivity().
* frequencies of the ones that match the prefix, thereby assuming
* that the MCVs are representative of the whole lexeme population
* in this respect. Compare histogram_selectivity().
*
* This is only a good plan if we have a pretty fair number of
* MCVs available; we set the threshold at 100. If no stats or
@@ -401,7 +401,7 @@ tsquery_opr_selec(QueryItem *item, char *operand,
default:
elog(ERROR, "unrecognized operator: %d", item->qoperator.oper);
selec = 0; /* keep compiler quiet */
selec = 0; /* keep compiler quiet */
break;
}
}

707
src/backend/tsearch/wparser_def.c
View File

@@ -299,16 +299,16 @@ TParserInit(char *str, int len)
*/
if (prs->charmaxlen > 1)
{
Oid collation = DEFAULT_COLLATION_OID; /*TODO*/
Oid collation = DEFAULT_COLLATION_OID; /* TODO */
prs->usewide = true;
if ( lc_ctype_is_c(collation) )
if (lc_ctype_is_c(collation))
{
/*
* char2wchar doesn't work for C-locale and
* sizeof(pg_wchar) could be not equal to sizeof(wchar_t)
* char2wchar doesn't work for C-locale and sizeof(pg_wchar) could
* be not equal to sizeof(wchar_t)
*/
prs->pgwstr = (pg_wchar*) palloc(sizeof(pg_wchar) * (prs->lenstr + 1));
prs->pgwstr = (pg_wchar *) palloc(sizeof(pg_wchar) * (prs->lenstr + 1));
pg_mb2wchar_with_len(prs->str, prs->pgwstr, prs->lenstr);
}
else
@@ -325,10 +325,11 @@ TParserInit(char *str, int len)
prs->state->state = TPS_Base;
#ifdef WPARSER_TRACE
/*
* Use of %.*s here is a bit risky since it can misbehave if the data
* is not in what libc thinks is the prevailing encoding. However,
* since this is just a debugging aid, we choose to live with that.
* Use of %.*s here is a bit risky since it can misbehave if the data is
* not in what libc thinks is the prevailing encoding. However, since
* this is just a debugging aid, we choose to live with that.
*/
fprintf(stderr, "parsing \"%.*s\"\n", len, str);
#endif
@@ -425,11 +426,11 @@ TParserCopyClose(TParser *prs)
/*
* Character-type support functions, equivalent to is* macros, but
* working with any possible encodings and locales. Notes:
* - with multibyte encoding and C-locale isw* function may fail
* or give wrong result.
* - multibyte encoding and C-locale often are used for
* Asian languages.
* - if locale is C the we use pgwstr instead of wstr
* - with multibyte encoding and C-locale isw* function may fail
* or give wrong result.
* - multibyte encoding and C-locale often are used for
* Asian languages.
* - if locale is C the we use pgwstr instead of wstr
*/
#ifdef USE_WIDE_UPPER_LOWER
@@ -447,7 +448,7 @@ p_is##type(TParser *prs) { \
} \
\
return is##type( *(unsigned char*)( prs->str + prs->state->posbyte ) ); \
} \
} \
\
static int \
p_isnot##type(TParser *prs) { \
@@ -719,7 +720,7 @@ p_isignore(TParser *prs)
static int
p_ishost(TParser *prs)
{
TParser *tmpprs = TParserCopyInit(prs);
TParser *tmpprs = TParserCopyInit(prs);
int res = 0;
tmpprs->wanthost = true;
@@ -741,7 +742,7 @@ p_ishost(TParser *prs)
static int
p_isURLPath(TParser *prs)
{
TParser *tmpprs = TParserCopyInit(prs);
TParser *tmpprs = TParserCopyInit(prs);
int res = 0;
tmpprs->state = newTParserPosition(tmpprs->state);
@@ -773,269 +774,269 @@ p_isspecial(TParser *prs)
/*
* pg_dsplen could return -1 which means error or control character
*/
if ( pg_dsplen(prs->str + prs->state->posbyte) == 0 )
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.
* 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 )
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;
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 )
if (prs->pgwstr)
c = *(prs->pgwstr + prs->state->poschar);
else
c = (pg_wchar) *(prs->wstr + prs->state->poschar);
while( StopLow < StopHigh )
while (StopLow < StopHigh)
{
StopMiddle = StopLow + ((StopHigh - StopLow) >> 1);
if ( *StopMiddle == c )
if (*StopMiddle == c)
return 1;
else if ( *StopMiddle < c )
else if (*StopMiddle < c)
StopLow = StopMiddle + 1;
else
StopHigh = StopMiddle;
@@ -1288,7 +1289,7 @@ static const TParserStateActionItem actionTPS_InTagFirst[] = {
static const TParserStateActionItem actionTPS_InXMLBegin[] = {
{p_isEOF, 0, A_POP, TPS_Null, 0, NULL},
/* <?xml ... */
/* XXX do we wants states for the m and l ? Right now this accepts <?xZ */
/* XXX do we wants states for the m and l ? Right now this accepts <?xZ */
{p_iseqC, 'x', A_NEXT, TPS_InTag, 0, NULL},
{NULL, 0, A_POP, TPS_Null, 0, NULL}
};
@@ -2004,10 +2005,10 @@ prsd_end(PG_FUNCTION_ARGS)
#define COMPLEXTOKEN(x) ( (x)==URL_T || (x)==NUMHWORD || (x)==ASCIIHWORD || (x)==HWORD )
#define ENDPUNCTOKEN(x) ( (x)==SPACE )
#define TS_IDIGNORE(x) ( (x)==TAG_T || (x)==PROTOCOL || (x)==SPACE || (x)==XMLENTITY )
#define HLIDREPLACE(x) ( (x)==TAG_T )
#define HLIDSKIP(x) ( (x)==URL_T || (x)==NUMHWORD || (x)==ASCIIHWORD || (x)==HWORD )
#define XMLHLIDSKIP(x) ( (x)==URL_T || (x)==NUMHWORD || (x)==ASCIIHWORD || (x)==HWORD )
#define TS_IDIGNORE(x) ( (x)==TAG_T || (x)==PROTOCOL || (x)==SPACE || (x)==XMLENTITY )
#define HLIDREPLACE(x) ( (x)==TAG_T )
#define HLIDSKIP(x) ( (x)==URL_T || (x)==NUMHWORD || (x)==ASCIIHWORD || (x)==HWORD )
#define XMLHLIDSKIP(x) ( (x)==URL_T || (x)==NUMHWORD || (x)==ASCIIHWORD || (x)==HWORD )
#define NONWORDTOKEN(x) ( (x)==SPACE || HLIDREPLACE(x) || HLIDSKIP(x) )
#define NOENDTOKEN(x) ( NONWORDTOKEN(x) || (x)==SCIENTIFIC || (x)==VERSIONNUMBER || (x)==DECIMAL_T || (x)==SIGNEDINT || (x)==UNSIGNEDINT || TS_IDIGNORE(x) )
@@ -2105,7 +2106,7 @@ hlCover(HeadlineParsedText *prs, TSQuery query, int *p, int *q)
static void
mark_fragment(HeadlineParsedText *prs, int highlight, int startpos, int endpos)
{
int i;
int i;
for (i = startpos; i <= endpos; i++)
{
@@ -2115,7 +2116,7 @@ mark_fragment(HeadlineParsedText *prs, int highlight, int startpos, int endpos)
{
if (HLIDREPLACE(prs->words[i].type))
prs->words[i].replace = 1;
else if ( HLIDSKIP(prs->words[i].type) )
else if (HLIDSKIP(prs->words[i].type))
prs->words[i].skip = 1;
}
else
@@ -2130,27 +2131,29 @@ mark_fragment(HeadlineParsedText *prs, int highlight, int startpos, int endpos)
typedef struct
{
int4 startpos;
int4 endpos;
int4 poslen;
int4 curlen;
int2 in;
int2 excluded;
int4 startpos;
int4 endpos;
int4 poslen;
int4 curlen;
int2 in;
int2 excluded;
} CoverPos;
static void
get_next_fragment(HeadlineParsedText *prs, int *startpos, int *endpos,
int *curlen, int *poslen, int max_words)
int *curlen, int *poslen, int max_words)
{
int i;
/* Objective: Generate a fragment of words between startpos and endpos
* such that it has at most max_words and both ends has query words.
* If the startpos and endpos are the endpoints of the cover and the
* cover has fewer words than max_words, then this function should
* just return the cover
int i;
/*
* Objective: Generate a fragment of words between startpos and endpos
* such that it has at most max_words and both ends has query words. If
* the startpos and endpos are the endpoints of the cover and the cover
* has fewer words than max_words, then this function should just return
* the cover
*/
/* first move startpos to an item */
for(i = *startpos; i <= *endpos; i++)
for (i = *startpos; i <= *endpos; i++)
{
*startpos = i;
if (prs->words[i].item && !prs->words[i].repeated)
@@ -2159,7 +2162,7 @@ get_next_fragment(HeadlineParsedText *prs, int *startpos, int *endpos,
/* cut endpos to have only max_words */
*curlen = 0;
*poslen = 0;
for(i = *startpos; i <= *endpos && *curlen < max_words; i++)
for (i = *startpos; i <= *endpos && *curlen < max_words; i++)
{
if (!NONWORDTOKEN(prs->words[i].type))
*curlen += 1;
@@ -2170,7 +2173,7 @@ get_next_fragment(HeadlineParsedText *prs, int *startpos, int *endpos,
if (*endpos > i)
{
*endpos = i;
for(i = *endpos; i >= *startpos; i --)
for (i = *endpos; i >= *startpos; i--)
{
*endpos = i;
if (prs->words[i].item && !prs->words[i].repeated)
@@ -2183,22 +2186,30 @@ get_next_fragment(HeadlineParsedText *prs, int *startpos, int *endpos,
static void
mark_hl_fragments(HeadlineParsedText *prs, TSQuery query, int highlight,
int shortword, int min_words,
int max_words, int max_fragments)
int shortword, int min_words,
int max_words, int max_fragments)
{
int4 poslen, curlen, i, f, num_f = 0;
int4 stretch, maxstretch, posmarker;
int4 poslen,
curlen,
i,
f,
num_f = 0;
int4 stretch,
maxstretch,
posmarker;
int4 startpos = 0,
endpos = 0,
p = 0,
q = 0;
int4 startpos = 0,
endpos = 0,
p = 0,
q = 0;
int4 numcovers = 0,
maxcovers = 32;
maxcovers = 32;
int4 minI, minwords, maxitems;
CoverPos *covers;
int4 minI,
minwords,
maxitems;
CoverPos *covers;
covers = palloc(maxcovers * sizeof(CoverPos));
@@ -2206,12 +2217,13 @@ mark_hl_fragments(HeadlineParsedText *prs, TSQuery query, int highlight,
while (hlCover(prs, query, &p, &q))
{
startpos = p;
endpos = q;
endpos = q;
/* Break the cover into smaller fragments such that each fragment
* has at most max_words. Also ensure that each end of the fragment
* is a query word. This will allow us to stretch the fragment in
* either direction
/*
* Break the cover into smaller fragments such that each fragment has
* at most max_words. Also ensure that each end of the fragment is a
* query word. This will allow us to stretch the fragment in either
* direction
*/
while (startpos <= endpos)
@@ -2220,17 +2232,17 @@ mark_hl_fragments(HeadlineParsedText *prs, TSQuery query, int highlight,
if (numcovers >= maxcovers)
{
maxcovers *= 2;
covers = repalloc(covers, sizeof(CoverPos) * maxcovers);
covers = repalloc(covers, sizeof(CoverPos) * maxcovers);
}
covers[numcovers].startpos = startpos;
covers[numcovers].endpos = endpos;
covers[numcovers].curlen = curlen;
covers[numcovers].poslen = poslen;
covers[numcovers].in = 0;
covers[numcovers].endpos = endpos;
covers[numcovers].curlen = curlen;
covers[numcovers].poslen = poslen;
covers[numcovers].in = 0;
covers[numcovers].excluded = 0;
numcovers ++;
numcovers++;
startpos = endpos + 1;
endpos = q;
endpos = q;
}
/* move p to generate the next cover */
p++;
@@ -2242,19 +2254,20 @@ mark_hl_fragments(HeadlineParsedText *prs, TSQuery query, int highlight,
maxitems = 0;
minwords = 0x7fffffff;
minI = -1;
/* Choose the cover that contains max items.
* In case of tie choose the one with smaller
* number of words.
/*
* Choose the cover that contains max items. In case of tie choose the
* one with smaller number of words.
*/
for (i = 0; i < numcovers; i ++)
for (i = 0; i < numcovers; i++)
{
if (!covers[i].in && !covers[i].excluded &&
if (!covers[i].in && !covers[i].excluded &&
(maxitems < covers[i].poslen || (maxitems == covers[i].poslen
&& minwords > covers[i].curlen)))
&& minwords > covers[i].curlen)))
{
maxitems = covers[i].poslen;
minwords = covers[i].curlen;
minI = i;
minI = i;
}
}
/* if a cover was found mark it */
@@ -2263,27 +2276,27 @@ mark_hl_fragments(HeadlineParsedText *prs, TSQuery query, int highlight,
covers[minI].in = 1;
/* adjust the size of cover */
startpos = covers[minI].startpos;
endpos = covers[minI].endpos;
curlen = covers[minI].curlen;
endpos = covers[minI].endpos;
curlen = covers[minI].curlen;
/* stretch the cover if cover size is lower than max_words */
if (curlen < max_words)
{
/* divide the stretch on both sides of cover */
maxstretch = (max_words - curlen)/2;
/* first stretch the startpos
* stop stretching if
* 1. we hit the beginning of document
* 2. exceed maxstretch
* 3. we hit an already marked fragment
maxstretch = (max_words - curlen) / 2;
/*
* first stretch the startpos stop stretching if 1. we hit the
* beginning of document 2. exceed maxstretch 3. we hit an
* already marked fragment
*/
stretch = 0;
stretch = 0;
posmarker = startpos;
for (i = startpos - 1; i >= 0 && stretch < maxstretch && !prs->words[i].in; i--)
{
if (!NONWORDTOKEN(prs->words[i].type))
{
curlen ++;
stretch ++;
curlen++;
stretch++;
}
posmarker = i;
}
@@ -2291,35 +2304,35 @@ mark_hl_fragments(HeadlineParsedText *prs, TSQuery query, int highlight,
for (i = posmarker; i < startpos && (NOENDTOKEN(prs->words[i].type) || prs->words[i].len <= shortword); i++)
{
if (!NONWORDTOKEN(prs->words[i].type))
curlen --;
curlen--;
}
startpos = i;
/* now stretch the endpos as much as possible*/
/* now stretch the endpos as much as possible */
posmarker = endpos;
for (i = endpos + 1; i < prs->curwords && curlen < max_words && !prs->words[i].in; i++)
{
if (!NONWORDTOKEN(prs->words[i].type))
curlen ++;
curlen++;
posmarker = i;
}
/* cut back endpos till we find a non-short token */
for ( i = posmarker; i > endpos && (NOENDTOKEN(prs->words[i].type) || prs->words[i].len <= shortword); i--)
for (i = posmarker; i > endpos && (NOENDTOKEN(prs->words[i].type) || prs->words[i].len <= shortword); i--)
{
if (!NONWORDTOKEN(prs->words[i].type))
curlen --;
curlen--;
}
endpos = i;
}
covers[minI].startpos = startpos;
covers[minI].endpos = endpos;
covers[minI].curlen = curlen;
covers[minI].endpos = endpos;
covers[minI].curlen = curlen;
/* Mark the chosen fragments (covers) */
mark_fragment(prs, highlight, startpos, endpos);
num_f ++;
num_f++;
/* exclude overlapping covers */
for (i = 0; i < numcovers; i ++)
for (i = 0; i < numcovers; i++)
{
if (i != minI && ( (covers[i].startpos >= covers[minI].startpos && covers[i].startpos <= covers[minI].endpos) || (covers[i].endpos >= covers[minI].startpos && covers[i].endpos <= covers[minI].endpos)))
if (i != minI && ((covers[i].startpos >= covers[minI].startpos && covers[i].startpos <= covers[minI].endpos) || (covers[i].endpos >= covers[minI].startpos && covers[i].endpos <= covers[minI].endpos)))
covers[i].excluded = 1;
}
}
@@ -2327,7 +2340,7 @@ mark_hl_fragments(HeadlineParsedText *prs, TSQuery query, int highlight,
break;
}
/* show at least min_words we have not marked anything*/
/* show at least min_words we have not marked anything */
if (num_f <= 0)
{
startpos = endpos = curlen = 0;
@@ -2344,7 +2357,7 @@ mark_hl_fragments(HeadlineParsedText *prs, TSQuery query, int highlight,
static void
mark_hl_words(HeadlineParsedText *prs, TSQuery query, int highlight,
int shortword, int min_words, int max_words)
int shortword, int min_words, int max_words)
{
int p = 0,
q = 0;
@@ -2408,7 +2421,7 @@ mark_hl_words(HeadlineParsedText *prs, TSQuery query, int highlight,
curlen++;
if (prs->words[i].item && !prs->words[i].repeated)
poslen++;
if ( curlen >= max_words )
if (curlen >= max_words)
break;
if (NOENDTOKEN(prs->words[i].type) || prs->words[i].len <= shortword)
continue;
@@ -2472,7 +2485,7 @@ mark_hl_words(HeadlineParsedText *prs, TSQuery query, int highlight,
{
if (HLIDREPLACE(prs->words[i].type))
prs->words[i].replace = 1;
else if ( HLIDSKIP(prs->words[i].type) )
else if (HLIDSKIP(prs->words[i].type))
prs->words[i].skip = 1;
}
else
@@ -2494,11 +2507,11 @@ prsd_headline(PG_FUNCTION_ARGS)
TSQuery query = PG_GETARG_TSQUERY(2);
/* from opt + start and and tag */
int min_words = 15;
int max_words = 35;
int shortword = 3;
int min_words = 15;
int max_words = 35;
int shortword = 3;
int max_fragments = 0;
int highlight = 0;
int highlight = 0;
ListCell *l;
/* config */