datetime.c

来自「postgresql8.3.4源码,开源数据库」· C语言 代码 · 共 2,681 行 · 第 1/5 页

/*-------------------------------------------------------------------------
 *
 * datetime.c
 *	  Support functions for date/time types.
 *
 * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  $PostgreSQL: pgsql/src/backend/utils/adt/datetime.c,v 1.184.2.2 2008/06/09 19:34:09 tgl Exp $
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include <ctype.h>
#include <float.h>
#include <limits.h>
#include <math.h>

#include "access/heapam.h"
#include "access/xact.h"
#include "catalog/pg_type.h"
#include "funcapi.h"
#include "miscadmin.h"
#include "utils/builtins.h"
#include "utils/datetime.h"
#include "utils/memutils.h"
#include "utils/tzparser.h"


static int DecodeNumber(int flen, char *field, bool haveTextMonth,
			 int fmask, int *tmask,
			 struct pg_tm * tm, fsec_t *fsec, bool *is2digits);
static int DecodeNumberField(int len, char *str,
				  int fmask, int *tmask,
				  struct pg_tm * tm, fsec_t *fsec, bool *is2digits);
static int DecodeTime(char *str, int fmask, int *tmask,
		   struct pg_tm * tm, fsec_t *fsec);
static int	DecodeTimezone(char *str, int *tzp);
static const datetkn *datebsearch(const char *key, const datetkn *base, int nel);
static int	DecodeDate(char *str, int fmask, int *tmask, bool *is2digits,
					   struct pg_tm * tm);
static int	ValidateDate(int fmask, bool is2digits, bool bc,
						 struct pg_tm * tm);
static void TrimTrailingZeros(char *str);


const int	day_tab[2][13] =
{
	{31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31, 0},
	{31, 29, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31, 0}
};

char	   *months[] = {"Jan", "Feb", "Mar", "Apr", "May", "Jun",
"Jul", "Aug", "Sep", "Oct", "Nov", "Dec", NULL};

char	   *days[] = {"Sunday", "Monday", "Tuesday", "Wednesday",
"Thursday", "Friday", "Saturday", NULL};


/*****************************************************************************
 *	 PRIVATE ROUTINES														 *
 *****************************************************************************/

/*
 * Definitions for squeezing values into "value"
 * We set aside a high bit for a sign, and scale the timezone offsets
 * in minutes by a factor of 15 (so can represent quarter-hour increments).
 */
#define ABS_SIGNBIT		((char) 0200)
#define VALMASK			((char) 0177)
#define POS(n)			(n)
#define NEG(n)			((n)|ABS_SIGNBIT)
#define SIGNEDCHAR(c)	((c)&ABS_SIGNBIT? -((c)&VALMASK): (c))
#define FROMVAL(tp)		(-SIGNEDCHAR((tp)->value) * 15) /* uncompress */
#define TOVAL(tp, v)	((tp)->value = ((v) < 0? NEG((-(v))/15): POS(v)/15))

/*
 * datetktbl holds date/time keywords.
 *
 * Note that this table must be strictly alphabetically ordered to allow an
 * O(ln(N)) search algorithm to be used.
 *
 * The text field is NOT guaranteed to be NULL-terminated.
 *
 * To keep this table reasonably small, we divide the lexval for TZ and DTZ
 * entries by 15 (so they are on 15 minute boundaries) and truncate the text
 * field at TOKMAXLEN characters.
 * Formerly, we divided by 10 rather than 15 but there are a few time zones
 * which are 30 or 45 minutes away from an even hour, most are on an hour
 * boundary, and none on other boundaries.
 *
 * The static table contains no TZ or DTZ entries, rather those are loaded
 * from configuration files and stored in timezonetktbl, which has the same
 * format as the static datetktbl.
 */
static datetkn *timezonetktbl = NULL;

static int	sztimezonetktbl = 0;

static const datetkn datetktbl[] = {
/*	text, token, lexval */
	{EARLY, RESERV, DTK_EARLY}, /* "-infinity" reserved for "early time" */
	{"abstime", IGNORE_DTF, 0}, /* for pre-v6.1 "Invalid Abstime" */
	{DA_D, ADBC, AD},			/* "ad" for years > 0 */
	{"allballs", RESERV, DTK_ZULU},		/* 00:00:00 */
	{"am", AMPM, AM},
	{"apr", MONTH, 4},
	{"april", MONTH, 4},
	{"at", IGNORE_DTF, 0},		/* "at" (throwaway) */
	{"aug", MONTH, 8},
	{"august", MONTH, 8},
	{DB_C, ADBC, BC},			/* "bc" for years <= 0 */
	{DCURRENT, RESERV, DTK_CURRENT},	/* "current" is always now */
	{"d", UNITS, DTK_DAY},		/* "day of month" for ISO input */
	{"dec", MONTH, 12},
	{"december", MONTH, 12},
	{"dow", RESERV, DTK_DOW},	/* day of week */
	{"doy", RESERV, DTK_DOY},	/* day of year */
	{"dst", DTZMOD, 6},
	{EPOCH, RESERV, DTK_EPOCH}, /* "epoch" reserved for system epoch time */
	{"feb", MONTH, 2},
	{"february", MONTH, 2},
	{"fri", DOW, 5},
	{"friday", DOW, 5},
	{"h", UNITS, DTK_HOUR},		/* "hour" */
	{LATE, RESERV, DTK_LATE},	/* "infinity" reserved for "late time" */
	{INVALID, RESERV, DTK_INVALID},		/* "invalid" reserved for bad time */
	{"isodow", RESERV, DTK_ISODOW},		/* ISO day of week, Sunday == 7 */
	{"isoyear", UNITS, DTK_ISOYEAR},	/* year in terms of the ISO week date */
	{"j", UNITS, DTK_JULIAN},
	{"jan", MONTH, 1},
	{"january", MONTH, 1},
	{"jd", UNITS, DTK_JULIAN},
	{"jul", MONTH, 7},
	{"julian", UNITS, DTK_JULIAN},
	{"july", MONTH, 7},
	{"jun", MONTH, 6},
	{"june", MONTH, 6},
	{"m", UNITS, DTK_MONTH},	/* "month" for ISO input */
	{"mar", MONTH, 3},
	{"march", MONTH, 3},
	{"may", MONTH, 5},
	{"mm", UNITS, DTK_MINUTE},	/* "minute" for ISO input */
	{"mon", DOW, 1},
	{"monday", DOW, 1},
	{"nov", MONTH, 11},
	{"november", MONTH, 11},
	{NOW, RESERV, DTK_NOW},		/* current transaction time */
	{"oct", MONTH, 10},
	{"october", MONTH, 10},
	{"on", IGNORE_DTF, 0},		/* "on" (throwaway) */
	{"pm", AMPM, PM},
	{"s", UNITS, DTK_SECOND},	/* "seconds" for ISO input */
	{"sat", DOW, 6},
	{"saturday", DOW, 6},
	{"sep", MONTH, 9},
	{"sept", MONTH, 9},
	{"september", MONTH, 9},
	{"sun", DOW, 0},
	{"sunday", DOW, 0},
	{"t", ISOTIME, DTK_TIME},	/* Filler for ISO time fields */
	{"thu", DOW, 4},
	{"thur", DOW, 4},
	{"thurs", DOW, 4},
	{"thursday", DOW, 4},
	{TODAY, RESERV, DTK_TODAY}, /* midnight */
	{TOMORROW, RESERV, DTK_TOMORROW},	/* tomorrow midnight */
	{"tue", DOW, 2},
	{"tues", DOW, 2},
	{"tuesday", DOW, 2},
	{"undefined", RESERV, DTK_INVALID}, /* pre-v6.1 invalid time */
	{"wed", DOW, 3},
	{"wednesday", DOW, 3},
	{"weds", DOW, 3},
	{"y", UNITS, DTK_YEAR},		/* "year" for ISO input */
	{YESTERDAY, RESERV, DTK_YESTERDAY}	/* yesterday midnight */
};

static int	szdatetktbl = sizeof datetktbl / sizeof datetktbl[0];

static datetkn deltatktbl[] = {
	/* text, token, lexval */
	{"@", IGNORE_DTF, 0},		/* postgres relative prefix */
	{DAGO, AGO, 0},				/* "ago" indicates negative time offset */
	{"c", UNITS, DTK_CENTURY},	/* "century" relative */
	{"cent", UNITS, DTK_CENTURY},		/* "century" relative */
	{"centuries", UNITS, DTK_CENTURY},	/* "centuries" relative */
	{DCENTURY, UNITS, DTK_CENTURY},		/* "century" relative */
	{"d", UNITS, DTK_DAY},		/* "day" relative */
	{DDAY, UNITS, DTK_DAY},		/* "day" relative */
	{"days", UNITS, DTK_DAY},	/* "days" relative */
	{"dec", UNITS, DTK_DECADE}, /* "decade" relative */
	{DDECADE, UNITS, DTK_DECADE},		/* "decade" relative */
	{"decades", UNITS, DTK_DECADE},		/* "decades" relative */
	{"decs", UNITS, DTK_DECADE},	/* "decades" relative */
	{"h", UNITS, DTK_HOUR},		/* "hour" relative */
	{DHOUR, UNITS, DTK_HOUR},	/* "hour" relative */
	{"hours", UNITS, DTK_HOUR}, /* "hours" relative */
	{"hr", UNITS, DTK_HOUR},	/* "hour" relative */
	{"hrs", UNITS, DTK_HOUR},	/* "hours" relative */
	{INVALID, RESERV, DTK_INVALID},		/* reserved for invalid time */
	{"m", UNITS, DTK_MINUTE},	/* "minute" relative */
	{"microsecon", UNITS, DTK_MICROSEC},		/* "microsecond" relative */
	{"mil", UNITS, DTK_MILLENNIUM},		/* "millennium" relative */
	{"millennia", UNITS, DTK_MILLENNIUM},		/* "millennia" relative */
	{DMILLENNIUM, UNITS, DTK_MILLENNIUM},		/* "millennium" relative */
	{"millisecon", UNITS, DTK_MILLISEC},		/* relative */
	{"mils", UNITS, DTK_MILLENNIUM},	/* "millennia" relative */
	{"min", UNITS, DTK_MINUTE}, /* "minute" relative */
	{"mins", UNITS, DTK_MINUTE},	/* "minutes" relative */
	{DMINUTE, UNITS, DTK_MINUTE},		/* "minute" relative */
	{"minutes", UNITS, DTK_MINUTE},		/* "minutes" relative */
	{"mon", UNITS, DTK_MONTH},	/* "months" relative */
	{"mons", UNITS, DTK_MONTH}, /* "months" relative */
	{DMONTH, UNITS, DTK_MONTH}, /* "month" relative */
	{"months", UNITS, DTK_MONTH},
	{"ms", UNITS, DTK_MILLISEC},
	{"msec", UNITS, DTK_MILLISEC},
	{DMILLISEC, UNITS, DTK_MILLISEC},
	{"mseconds", UNITS, DTK_MILLISEC},
	{"msecs", UNITS, DTK_MILLISEC},
	{"qtr", UNITS, DTK_QUARTER},	/* "quarter" relative */
	{DQUARTER, UNITS, DTK_QUARTER},		/* "quarter" relative */
	{"reltime", IGNORE_DTF, 0}, /* pre-v6.1 "Undefined Reltime" */
	{"s", UNITS, DTK_SECOND},
	{"sec", UNITS, DTK_SECOND},
	{DSECOND, UNITS, DTK_SECOND},
	{"seconds", UNITS, DTK_SECOND},
	{"secs", UNITS, DTK_SECOND},
	{DTIMEZONE, UNITS, DTK_TZ}, /* "timezone" time offset */
	{"timezone_h", UNITS, DTK_TZ_HOUR}, /* timezone hour units */
	{"timezone_m", UNITS, DTK_TZ_MINUTE},		/* timezone minutes units */
	{"undefined", RESERV, DTK_INVALID}, /* pre-v6.1 invalid time */
	{"us", UNITS, DTK_MICROSEC},	/* "microsecond" relative */
	{"usec", UNITS, DTK_MICROSEC},		/* "microsecond" relative */
	{DMICROSEC, UNITS, DTK_MICROSEC},	/* "microsecond" relative */
	{"useconds", UNITS, DTK_MICROSEC},	/* "microseconds" relative */
	{"usecs", UNITS, DTK_MICROSEC},		/* "microseconds" relative */
	{"w", UNITS, DTK_WEEK},		/* "week" relative */
	{DWEEK, UNITS, DTK_WEEK},	/* "week" relative */
	{"weeks", UNITS, DTK_WEEK}, /* "weeks" relative */
	{"y", UNITS, DTK_YEAR},		/* "year" relative */
	{DYEAR, UNITS, DTK_YEAR},	/* "year" relative */
	{"years", UNITS, DTK_YEAR}, /* "years" relative */
	{"yr", UNITS, DTK_YEAR},	/* "year" relative */
	{"yrs", UNITS, DTK_YEAR}	/* "years" relative */
};

static int	szdeltatktbl = sizeof deltatktbl / sizeof deltatktbl[0];

static const datetkn *datecache[MAXDATEFIELDS] = {NULL};

static const datetkn *deltacache[MAXDATEFIELDS] = {NULL};


/*
 * strtoi --- just like strtol, but returns int not long
 */
static int
strtoi(const char *nptr, char **endptr, int base)
{
	long	val;

	val = strtol(nptr, endptr, base);
#ifdef HAVE_LONG_INT_64
	if (val != (long) ((int32) val))
		errno = ERANGE;
#endif
	return (int) val;
}


/*
 * Calendar time to Julian date conversions.
 * Julian date is commonly used in astronomical applications,
 *	since it is numerically accurate and computationally simple.
 * The algorithms here will accurately convert between Julian day
 *	and calendar date for all non-negative Julian days
 *	(i.e. from Nov 24, -4713 on).
 *
 * These routines will be used by other date/time packages
 * - thomas 97/02/25
 *
 * Rewritten to eliminate overflow problems. This now allows the
 * routines to work correctly for all Julian day counts from
 * 0 to 2147483647	(Nov 24, -4713 to Jun 3, 5874898) assuming
 * a 32-bit integer. Longer types should also work to the limits
 * of their precision.
 */

int
date2j(int y, int m, int d)
{
	int			julian;
	int			century;

	if (m > 2)
	{
		m += 1;
		y += 4800;
	}
	else
	{
		m += 13;
		y += 4799;
	}

	century = y / 100;
	julian = y * 365 - 32167;
	julian += y / 4 - century + century / 4;
	julian += 7834 * m / 256 + d;

	return julian;
}	/* date2j() */

void
j2date(int jd, int *year, int *month, int *day)
{
	unsigned int julian;
	unsigned int quad;
	unsigned int extra;
	int			y;

	julian = jd;
	julian += 32044;
	quad = julian / 146097;
	extra = (julian - quad * 146097) * 4 + 3;
	julian += 60 + quad * 3 + extra / 146097;
	quad = julian / 1461;
	julian -= quad * 1461;
	y = julian * 4 / 1461;
	julian = ((y != 0) ? ((julian + 305) % 365) : ((julian + 306) % 366))
		+ 123;
	y += quad * 4;
	*year = y - 4800;
	quad = julian * 2141 / 65536;
	*day = julian - 7834 * quad / 256;
	*month = (quad + 10) % 12 + 1;

	return;
}	/* j2date() */


/*
 * j2day - convert Julian date to day-of-week (0..6 == Sun..Sat)
 *
 * Note: various places use the locution j2day(date - 1) to produce a
 * result according to the convention 0..6 = Mon..Sun.	This is a bit of
 * a crock, but will work as long as the computation here is just a modulo.
 */
int
j2day(int date)
{
	unsigned int day;

	day = date;

	day += 1;
	day %= 7;

	return (int) day;
}	/* j2day() */


/*
 * GetCurrentDateTime()
 *
 * Get the transaction start time ("now()") broken down as a struct pg_tm.
 */
void
GetCurrentDateTime(struct pg_tm * tm)
{
	int			tz;
	fsec_t		fsec;

	timestamp2tm(GetCurrentTransactionStartTimestamp(), &tz, tm, &fsec,
				 NULL, NULL);
	/* Note: don't pass NULL tzp to timestamp2tm; affects behavior */
}

/*
 * GetCurrentTimeUsec()
 *
 * Get the transaction start time ("now()") broken down as a struct pg_tm,
 * including fractional seconds and timezone offset.
 */
void
GetCurrentTimeUsec(struct pg_tm * tm, fsec_t *fsec, int *tzp)
{
	int			tz;

	timestamp2tm(GetCurrentTransactionStartTimestamp(), &tz, tm, fsec,
				 NULL, NULL);
	/* Note: don't pass NULL tzp to timestamp2tm; affects behavior */
	if (tzp != NULL)
		*tzp = tz;
}


/* TrimTrailingZeros()
 * ... resulting from printing numbers with full precision.
 */
static void
TrimTrailingZeros(char *str)
{
	int			len = strlen(str);

#if 0
	/* chop off trailing one to cope with interval rounding */
	if (strcmp(str + len - 4, "0001") == 0)
	{
		len -= 4;
		*(str + len) = '\0';
	}
#endif

	/* chop off trailing zeros... but leave at least 2 fractional digits */
	while (*(str + len - 1) == '0' && *(str + len - 3) != '.')
	{
		len--;
		*(str + len) = '\0';
	}
}

/* ParseDateTime()
 *	Break string into tokens based on a date/time context.
 *	Returns 0 if successful, DTERR code if bogus input detected.
 *
 * timestr - the input string
 * workbuf - workspace for field string storage. This must be
 *	 larger than the largest legal input for this datetime type --
 *	 some additional space will be needed to NUL terminate fields.
 * buflen - the size of workbuf
 * field[] - pointers to field strings are returned in this array
 * ftype[] - field type indicators are returned in this array
 * maxfields - dimensions of the above two arrays
 * *numfields - set to the actual number of fields detected
 *
 * The fields extracted from the input are stored as separate,
 * null-terminated strings in the workspace at workbuf. Any text is
 * converted to lower case.
 *
 * Several field types are assigned:
 *	DTK_NUMBER - digits and (possibly) a decimal point
 *	DTK_DATE - digits and two delimiters, or digits and text
 *	DTK_TIME - digits, colon delimiters, and possibly a decimal point
 *	DTK_STRING - text (no digits or punctuation)
 *	DTK_SPECIAL - leading "+" or "-" followed by text
 *	DTK_TZ - leading "+" or "-" followed by digits (also eats ':' or '.')
 *
 * Note that some field types can hold unexpected items:
 *	DTK_NUMBER can hold date fields (yy.ddd)
 *	DTK_STRING can hold months (January) and time zones (PST)
 *	DTK_DATE can hold time zone names (America/New_York, GMT-8)
 */
int
ParseDateTime(const char *timestr, char *workbuf, size_t buflen,
			  char **field, int *ftype, int maxfields, int *numfields)
{
	int			nf = 0;
	const char *cp = timestr;
	char	   *bufp = workbuf;
	const char *bufend = workbuf + buflen;

	/*
	 * Set the character pointed-to by "bufptr" to "newchar", and increment
	 * "bufptr". "end" gives the end of the buffer -- we return an error if
	 * there is no space left to append a character to the buffer. Note that
	 * "bufptr" is evaluated twice.
	 */
#define APPEND_CHAR(bufptr, end, newchar)		\
	do											\
	{											\
		if (((bufptr) + 1) >= (end))			\
			return DTERR_BAD_FORMAT;			\
		*(bufptr)++ = newchar;					\
	} while (0)

	/* outer loop through fields */
	while (*cp != '\0')
	{
		/* Ignore spaces between fields */
		if (isspace((unsigned char) *cp))
		{
			cp++;
			continue;
		}

		/* Record start of current field */
		if (nf >= maxfields)
			return DTERR_BAD_FORMAT;
		field[nf] = bufp;

		/* leading digit? then date or time */
		if (isdigit((unsigned char) *cp))
		{
			APPEND_CHAR(bufp, bufend, *cp++);
			while (isdigit((unsigned char) *cp))
				APPEND_CHAR(bufp, bufend, *cp++);

			/* time field? */
			if (*cp == ':')
			{
				ftype[nf] = DTK_TIME;
				APPEND_CHAR(bufp, bufend, *cp++);
				while (isdigit((unsigned char) *cp) ||
					   (*cp == ':') || (*cp == '.'))
					APPEND_CHAR(bufp, bufend, *cp++);
			}
			/* date field? allow embedded text month */
			else if (*cp == '-' || *cp == '/' || *cp == '.')
			{
				/* save delimiting character to use later */
				char		delim = *cp;

				APPEND_CHAR(bufp, bufend, *cp++);
				/* second field is all digits? then no embedded text month */
				if (isdigit((unsigned char) *cp))
				{
					ftype[nf] = ((delim == '.') ? DTK_NUMBER : DTK_DATE);
					while (isdigit((unsigned char) *cp))
						APPEND_CHAR(bufp, bufend, *cp++);

					/*
					 * insist that the delimiters match to get a three-field
					 * date.
					 */
					if (*cp == delim)
					{
						ftype[nf] = DTK_DATE;
						APPEND_CHAR(bufp, bufend, *cp++);
						while (isdigit((unsigned char) *cp) || *cp == delim)
							APPEND_CHAR(bufp, bufend, *cp++);
					}