* oracle_compat.c
* Oracle compatible functions.
*
- * Copyright (c) 1996-2001, PostgreSQL Global Development Group
+ * Copyright (c) 1996-2003, PostgreSQL Global Development Group
*
* Author: Edmund Mergl <E.Mergl@bawue.de>
* Multibyte enhancement: Tatsuo Ishii <ishii@postgresql.org>
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/utils/adt/oracle_compat.c,v 1.43 2002/09/04 20:31:28 momjian Exp $
+ * $Header: /cvsroot/pgsql/src/backend/utils/adt/oracle_compat.c,v 1.44 2003/05/23 22:33:20 tgl Exp $
*
*-------------------------------------------------------------------------
*/
-
#include "postgres.h"
#include <ctype.h>
#include "utils/builtins.h"
-
#include "mb/pg_wchar.h"
+
+static text *dotrim(const char *string, int stringlen,
+ const char *set, int setlen,
+ bool doltrim, bool dortrim);
+
+
/********************************************************************
*
* lower
text *string = PG_GETARG_TEXT_P(0);
text *set = PG_GETARG_TEXT_P(1);
text *ret;
- char *ptr,
- *end,
- *ptr2,
- *end2;
- int m;
- char **mp;
- int mplen;
- char *p;
- int mblen;
- int len;
+ ret = dotrim(VARDATA(string), VARSIZE(string) - VARHDRSZ,
+ VARDATA(set), VARSIZE(set) - VARHDRSZ,
+ true, true);
- if ((m = VARSIZE(string) - VARHDRSZ) <= 0 ||
- (VARSIZE(set) - VARHDRSZ) <= 0)
- PG_RETURN_TEXT_P(string);
+ PG_RETURN_TEXT_P(ret);
+}
- ptr = VARDATA(string);
+/********************************************************************
+ *
+ * btrim1 --- btrim with set fixed as ' '
+ *
+ ********************************************************************/
- len = m;
- mp = (char **) palloc(len * sizeof(char *));
- p = ptr;
- mplen = 0;
+Datum
+btrim1(PG_FUNCTION_ARGS)
+{
+ text *string = PG_GETARG_TEXT_P(0);
+ text *ret;
- /* build the mb pointer array */
- while (len > 0)
- {
- mp[mplen++] = p;
- mblen = pg_mblen(p);
- p += mblen;
- len -= mblen;
- }
- mplen--;
- end2 = VARDATA(set) + VARSIZE(set) - VARHDRSZ - 1;
+ ret = dotrim(VARDATA(string), VARSIZE(string) - VARHDRSZ,
+ " ", 1,
+ true, true);
- while (m > 0)
- {
- int str_len = pg_mblen(ptr);
+ PG_RETURN_TEXT_P(ret);
+}
- ptr2 = VARDATA(set);
- while (ptr2 <= end2)
+/*
+ * Common implementation for btrim, ltrim, rtrim
+ */
+static text *
+dotrim(const char *string, int stringlen,
+ const char *set, int setlen,
+ bool doltrim, bool dortrim)
+{
+ text *result;
+ int i;
+
+ /* Nothing to do if either string or set is empty */
+ if (stringlen > 0 && setlen > 0)
+ {
+ if (pg_database_encoding_max_length() > 1)
{
- int set_len = pg_mblen(ptr2);
+ /*
+ * In the multibyte-encoding case, build arrays of pointers to
+ * character starts, so that we can avoid inefficient checks in
+ * the inner loops.
+ */
+ const char **stringchars;
+ const char **setchars;
+ int *stringmblen;
+ int *setmblen;
+ int stringnchars;
+ int setnchars;
+ int resultndx;
+ int resultnchars;
+ const char *p;
+ int len;
+ int mblen;
+ const char *str_pos;
+ int str_len;
+
+ stringchars = (const char **) palloc(stringlen * sizeof(char *));
+ stringmblen = (int *) palloc(stringlen * sizeof(int));
+ stringnchars = 0;
+ p = string;
+ len = stringlen;
+ while (len > 0)
+ {
+ stringchars[stringnchars] = p;
+ stringmblen[stringnchars] = mblen = pg_mblen(p);
+ stringnchars++;
+ p += mblen;
+ len -= mblen;
+ }
- if (str_len == set_len &&
- memcmp(ptr, ptr2, str_len) == 0)
- break;
- ptr2 += set_len;
- }
- if (ptr2 > end2)
- break;
- ptr += str_len;
- m -= str_len;
- }
+ setchars = (const char **) palloc(setlen * sizeof(char *));
+ setmblen = (int *) palloc(setlen * sizeof(int));
+ setnchars = 0;
+ p = set;
+ len = setlen;
+ while (len > 0)
+ {
+ setchars[setnchars] = p;
+ setmblen[setnchars] = mblen = pg_mblen(p);
+ setnchars++;
+ p += mblen;
+ len -= mblen;
+ }
- while (m > 0)
- {
- int str_len;
+ resultndx = 0; /* index in stringchars[] */
+ resultnchars = stringnchars;
- end = mp[mplen--];
- str_len = pg_mblen(end);
- ptr2 = VARDATA(set);
- while (ptr2 <= end2)
+ if (doltrim)
+ {
+ while (resultnchars > 0)
+ {
+ str_pos = stringchars[resultndx];
+ str_len = stringmblen[resultndx];
+ for (i = 0; i < setnchars; i++)
+ {
+ if (str_len == setmblen[i] &&
+ memcmp(str_pos, setchars[i], str_len) == 0)
+ break;
+ }
+ if (i >= setnchars)
+ break; /* no match here */
+ string += str_len;
+ stringlen -= str_len;
+ resultndx++;
+ resultnchars--;
+ }
+ }
+
+ if (dortrim)
+ {
+ while (resultnchars > 0)
+ {
+ str_pos = stringchars[resultndx + resultnchars - 1];
+ str_len = stringmblen[resultndx + resultnchars - 1];
+ for (i = 0; i < setnchars; i++)
+ {
+ if (str_len == setmblen[i] &&
+ memcmp(str_pos, setchars[i], str_len) == 0)
+ break;
+ }
+ if (i >= setnchars)
+ break; /* no match here */
+ stringlen -= str_len;
+ resultnchars--;
+ }
+ }
+
+ pfree(stringchars);
+ pfree(stringmblen);
+ pfree(setchars);
+ pfree(setmblen);
+ }
+ else
{
- int set_len = pg_mblen(ptr2);
+ /*
+ * In the single-byte-encoding case, we don't need such overhead.
+ */
+ if (doltrim)
+ {
+ while (stringlen > 0)
+ {
+ char str_ch = *string;
+
+ for (i = 0; i < setlen; i++)
+ {
+ if (str_ch == set[i])
+ break;
+ }
+ if (i >= setlen)
+ break; /* no match here */
+ string++;
+ stringlen--;
+ }
+ }
- if (str_len == set_len &&
- memcmp(end, ptr2, str_len) == 0)
- break;
- ptr2 += set_len;
+ if (dortrim)
+ {
+ while (stringlen > 0)
+ {
+ char str_ch = string[stringlen - 1];
+
+ for (i = 0; i < setlen; i++)
+ {
+ if (str_ch == set[i])
+ break;
+ }
+ if (i >= setlen)
+ break; /* no match here */
+ stringlen--;
+ }
+ }
}
- if (ptr2 > end2)
- break;
- m -= str_len;
}
- pfree(mp);
- ret = (text *) palloc(VARHDRSZ + m);
- VARATT_SIZEP(ret) = VARHDRSZ + m;
- memcpy(VARDATA(ret), ptr, m);
- PG_RETURN_TEXT_P(ret);
+ /* Return selected portion of string */
+ result = (text *) palloc(VARHDRSZ + stringlen);
+ VARATT_SIZEP(result) = VARHDRSZ + stringlen;
+ memcpy(VARDATA(result), string, stringlen);
+
+ return result;
}
/********************************************************************
text *string = PG_GETARG_TEXT_P(0);
text *set = PG_GETARG_TEXT_P(1);
text *ret;
- char *ptr,
- *ptr2,
- *end2;
- int m;
- if ((m = VARSIZE(string) - VARHDRSZ) <= 0 ||
- (VARSIZE(set) - VARHDRSZ) <= 0)
- PG_RETURN_TEXT_P(string);
+ ret = dotrim(VARDATA(string), VARSIZE(string) - VARHDRSZ,
+ VARDATA(set), VARSIZE(set) - VARHDRSZ,
+ true, false);
- ptr = VARDATA(string);
- end2 = VARDATA(set) + VARSIZE(set) - VARHDRSZ - 1;
+ PG_RETURN_TEXT_P(ret);
+}
- while (m > 0)
- {
- int str_len = pg_mblen(ptr);
+/********************************************************************
+ *
+ * ltrim1 --- ltrim with set fixed as ' '
+ *
+ ********************************************************************/
- ptr2 = VARDATA(set);
- while (ptr2 <= end2)
- {
- int set_len = pg_mblen(ptr2);
+Datum
+ltrim1(PG_FUNCTION_ARGS)
+{
+ text *string = PG_GETARG_TEXT_P(0);
+ text *ret;
- if (str_len == set_len &&
- memcmp(ptr, ptr2, str_len) == 0)
- break;
- ptr2 += set_len;
- }
- if (ptr2 > end2)
- break;
- ptr += str_len;
- m -= str_len;
- }
- ret = (text *) palloc(VARHDRSZ + m);
- VARATT_SIZEP(ret) = VARHDRSZ + m;
- memcpy(VARDATA(ret), ptr, m);
+ ret = dotrim(VARDATA(string), VARSIZE(string) - VARHDRSZ,
+ " ", 1,
+ true, false);
PG_RETURN_TEXT_P(ret);
}
-
/********************************************************************
*
* rtrim
text *set = PG_GETARG_TEXT_P(1);
text *ret;
- char *ptr,
- *end,
- *ptr2,
- *end2;
- int m;
-
- char **mp;
- int mplen;
- char *p;
- int mblen;
- int len;
-
- if ((m = VARSIZE(string) - VARHDRSZ) <= 0 ||
- (VARSIZE(set) - VARHDRSZ) <= 0)
- PG_RETURN_TEXT_P(string);
-
- ptr = VARDATA(string);
+ ret = dotrim(VARDATA(string), VARSIZE(string) - VARHDRSZ,
+ VARDATA(set), VARSIZE(set) - VARHDRSZ,
+ false, true);
- len = m;
- mp = (char **) palloc(len * sizeof(char *));
- p = ptr;
- mplen = 0;
-
- /* build the mb pointer array */
- while (len > 0)
- {
- mp[mplen++] = p;
- mblen = pg_mblen(p);
- p += mblen;
- len -= mblen;
- }
- mplen--;
- end2 = VARDATA(set) + VARSIZE(set) - VARHDRSZ - 1;
+ PG_RETURN_TEXT_P(ret);
+}
- while (m > 0)
- {
- int str_len;
+/********************************************************************
+ *
+ * rtrim1 --- rtrim with set fixed as ' '
+ *
+ ********************************************************************/
- end = mp[mplen--];
- str_len = pg_mblen(end);
- ptr2 = VARDATA(set);
- while (ptr2 <= end2)
- {
- int set_len = pg_mblen(ptr2);
+Datum
+rtrim1(PG_FUNCTION_ARGS)
+{
+ text *string = PG_GETARG_TEXT_P(0);
+ text *ret;
- if (str_len == set_len &&
- memcmp(end, ptr2, str_len) == 0)
- break;
- ptr2 += set_len;
- }
- if (ptr2 > end2)
- break;
- m -= str_len;
- }
- pfree(mp);
- ret = (text *) palloc(VARHDRSZ + m);
- VARATT_SIZEP(ret) = VARHDRSZ + m;
- memcpy(VARDATA(ret), ptr, m);
+ ret = dotrim(VARDATA(string), VARSIZE(string) - VARHDRSZ,
+ " ", 1,
+ false, true);
PG_RETURN_TEXT_P(ret);
}
* Portions Copyright (c) 1996-2002, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: pg_proc.h,v 1.300 2003/05/15 15:50:19 petere Exp $
+ * $Id: pg_proc.h,v 1.301 2003/05/23 22:33:22 tgl Exp $
*
* NOTES
* The script catalog/genbki.sh reads this file and generates .bki
DATA(insert OID = 874 ( rpad PGNSP PGUID 12 f f t f i 3 25 "25 23 25" rpad - _null_ ));
DESCR("right-pad string to length");
DATA(insert OID = 875 ( ltrim PGNSP PGUID 12 f f t f i 2 25 "25 25" ltrim - _null_ ));
-DESCR("left-pad string to length");
+DESCR("trim selected characters from left end of string");
DATA(insert OID = 876 ( rtrim PGNSP PGUID 12 f f t f i 2 25 "25 25" rtrim - _null_ ));
-DESCR("right-pad string to length");
+DESCR("trim selected characters from right end of string");
DATA(insert OID = 877 ( substr PGNSP PGUID 12 f f t f i 3 25 "25 23 23" text_substr - _null_ ));
DESCR("return portion of string");
DATA(insert OID = 878 ( translate PGNSP PGUID 12 f f t f i 3 25 "25 25 25" translate - _null_ ));
DESCR("left-pad string to length");
DATA(insert OID = 880 ( rpad PGNSP PGUID 14 f f t f i 2 25 "25 23" "select rpad($1, $2, \' \')" - _null_ ));
DESCR("right-pad string to length");
-DATA(insert OID = 881 ( ltrim PGNSP PGUID 14 f f t f i 1 25 "25" "select ltrim($1, \' \')" - _null_ ));
-DESCR("remove initial characters from string");
-DATA(insert OID = 882 ( rtrim PGNSP PGUID 14 f f t f i 1 25 "25" "select rtrim($1, \' \')" - _null_ ));
-DESCR("remove trailing characters from string");
+DATA(insert OID = 881 ( ltrim PGNSP PGUID 12 f f t f i 1 25 "25" ltrim1 - _null_ ));
+DESCR("trim spaces from left end of string");
+DATA(insert OID = 882 ( rtrim PGNSP PGUID 12 f f t f i 1 25 "25" rtrim1 - _null_ ));
+DESCR("trim spaces from right end of string");
DATA(insert OID = 883 ( substr PGNSP PGUID 12 f f t f i 2 25 "25 23" text_substr_no_len - _null_ ));
DESCR("return portion of string");
DATA(insert OID = 884 ( btrim PGNSP PGUID 12 f f t f i 2 25 "25 25" btrim - _null_ ));
-DESCR("trim both ends of string");
-DATA(insert OID = 885 ( btrim PGNSP PGUID 14 f f t f i 1 25 "25" "select btrim($1, \' \')" - _null_ ));
-DESCR("trim both ends of string");
+DESCR("trim selected characters from both ends of string");
+DATA(insert OID = 885 ( btrim PGNSP PGUID 12 f f t f i 1 25 "25" btrim1 - _null_ ));
+DESCR("trim spaces from both ends of string");
DATA(insert OID = 936 ( substring PGNSP PGUID 12 f f t f i 3 25 "25 23 23" text_substr - _null_ ));
DESCR("return portion of string");
projects / postgresql.git / commitdiff