parse_date.re

PHP v6.0 For Linux 运行环境：Win9X/ WinME/ WinNT/ Win2K/ WinXP

/*
   +----------------------------------------------------------------------+
   | PHP Version 5                                                        |
   +----------------------------------------------------------------------+
   | Copyright (c) 1997-2006 The PHP Group                                |
   +----------------------------------------------------------------------+
   | This source file is subject to version 3.01 of the PHP license,      |
   | that is bundled with this package in the file LICENSE, and is        |
   | available through the world-wide-web at the following url:           |
   | http://www.php.net/license/3_01.txt                                  |
   | If you did not receive a copy of the PHP license and are unable to   |
   | obtain it through the world-wide-web, please send a note to          |
   | [e-mail] so we can mail you a copy immediately.               |
   +----------------------------------------------------------------------+
   | Authors: Derick Rethans <[e-mail]>                    |
   +----------------------------------------------------------------------+
 */

/* $Id: parse_date.re,v 1.59 2006/07/27 13:01:10 iliaa Exp $ */

#include "timelib.h"

#include <stdio.h>
#include <ctype.h>

#ifdef HAVE_STDLIB_H
#include <stdlib.h>
#endif
#ifdef HAVE_STRING_H
#include <string.h>
#else
#include <strings.h>
#endif

#if defined(_MSC_VER)
# define strtoll(s, f, b) _atoi64(s)
#elif !defined(HAVE_STRTOLL)
# if defined(HAVE_ATOLL)
#  define strtoll(s, f, b) atoll(s)
# else
#  define strtoll(s, f, b) strtol(s, f, b)
# endif
#endif

#define TIMELIB_SECOND  1
#define TIMELIB_MINUTE  2
#define TIMELIB_HOUR    3
#define TIMELIB_DAY     4
#define TIMELIB_MONTH   5
#define TIMELIB_YEAR    6
#define TIMELIB_WEEKDAY 7
#define TIMELIB_SPECIAL 8

#define EOI      257
#define TIME     258
#define DATE     259

#define TIMELIB_XMLRPC_SOAP    260
#define TIMELIB_TIME12         261
#define TIMELIB_TIME24         262
#define TIMELIB_GNU_NOCOLON    263
#define TIMELIB_GNU_NOCOLON_TZ 264
#define TIMELIB_ISO_NOCOLON    265

#define TIMELIB_AMERICAN       266
#define TIMELIB_ISO_DATE       267
#define TIMELIB_DATE_FULL      268
#define TIMELIB_DATE_TEXT      269
#define TIMELIB_DATE_NOCOLON   270
#define TIMELIB_PG_YEARDAY     271
#define TIMELIB_PG_TEXT        272
#define TIMELIB_PG_REVERSE     273
#define TIMELIB_CLF            274
#define TIMELIB_DATE_NO_DAY    275
#define TIMELIB_SHORTDATE_WITH_TIME 276
#define TIMELIB_DATE_FULL_POINTED 277
#define TIMELIB_TIME24_WITH_ZONE 278
#define TIMELIB_ISO_WEEK       279

#define TIMELIB_TIMEZONE       300
#define TIMELIB_AGO            301

#define TIMELIB_RELATIVE       310

#define TIMELIB_ERROR          999

typedef unsigned char uchar;

#define   BSIZE	   8192

#define   YYCTYPE      uchar
#define   YYCURSOR     cursor
#define   YYLIMIT      s->lim
#define   YYMARKER     s->ptr
#define   YYFILL(n)    return EOI;

#define   RET(i)       {s->cur = cursor; return i;}

#define timelib_string_free free

#define TIMELIB_HAVE_TIME() { if (s->time->have_time) { add_error(s, "Double time specification"); timelib_string_free(str); return TIMELIB_ERROR; } else { s->time->have_time = 1; s->time->h = 0; s->time->i = 0; s->time->s = 0; s->time->f = 0; } }
#define TIMELIB_UNHAVE_TIME() { s->time->have_time = 0; s->time->h = 0; s->time->i = 0; s->time->s = 0; s->time->f = 0; }
#define TIMELIB_HAVE_DATE() { if (s->time->have_date) { add_error(s, "Double date specification"); timelib_string_free(str); return TIMELIB_ERROR; } else { s->time->have_date = 1; } }
#define TIMELIB_UNHAVE_DATE() { s->time->have_date = 0; s->time->d = 0; s->time->m = 0; s->time->y = 0; }
#define TIMELIB_HAVE_RELATIVE() { s->time->have_relative = 1; s->time->relative.weekday_behavior = 1; }
#define TIMELIB_HAVE_WEEKDAY_RELATIVE() { s->time->have_weekday_relative = 1; }
#define TIMELIB_HAVE_SPECIAL_RELATIVE() { s->time->have_special_relative = 1; }
#define TIMELIB_HAVE_TZ() { s->cur = cursor; if (s->time->have_zone) { add_warning(s, "Double timezone specification"); timelib_string_free(str); return TIMELIB_ERROR; } else { s->time->have_zone = 1; } }

#define TIMELIB_INIT  s->cur = cursor; str = timelib_string(s); ptr = str
#define TIMELIB_DEINIT timelib_string_free(str)
#define TIMELIB_ADJUST_RELATIVE_WEEKDAY() if (in->time.have_weekday_relative && (in.rel.d > 0)) { in.rel.d -= 7; }

#define TIMELIB_PROCESS_YEAR(x) { \
	if ((x) == -1) {         \
	/*	(x) = 0; */          \
	} else if ((x) < 100) {  \
		if ((x) < 70) {      \
			(x) += 2000;     \
		} else {             \
			(x) += 1900;     \
		}                    \
	}                        \
}

#ifdef DEBUG_PARSER
#define DEBUG_OUTPUT(s) printf("%s\n", s);
#define YYDEBUG(s,c) { if (s != -1) { printf("state: %d ", s); printf("[%c]\n", c); } }
#else
#define DEBUG_OUTPUT(s)
#define YYDEBUG(s,c)
#endif

#include "timelib_structs.h"

typedef struct timelib_elems {
	unsigned int   c; /* Number of elements */
	char         **v; /* Values */
} timelib_elems;

typedef struct Scanner {
	int           fd;
	uchar        *lim, *str, *ptr, *cur, *tok, *pos;
	unsigned int  line, len;
	struct timelib_error_container *errors;

	struct timelib_time *time;
	const timelib_tzdb  *tzdb;
} Scanner;

typedef struct _timelib_lookup_table {
    const char *name;
    int         type;
    int         value;
} timelib_lookup_table;

typedef struct _timelib_relunit {
	const char *name;
	int         unit;
	int         multiplier;
} timelib_relunit;

#define HOUR(a) (int)(a * 60)

/* The timezone table. */
const static timelib_tz_lookup_table timelib_timezone_lookup[] = {
#include "timezonemap.h"
	{ NULL, 0, 0, NULL },
};

const static timelib_tz_lookup_table timelib_timezone_fallbackmap[] = {
#include "fallbackmap.h"
	{ NULL, 0, 0, NULL },
};

const static timelib_tz_lookup_table timelib_timezone_utc[] = {
	{ "utc", 0, 0, "UTC" },
};

static timelib_relunit const timelib_relunit_lookup[] = {
	{ "sec",         TIMELIB_SECOND,  1 },
	{ "secs",        TIMELIB_SECOND,  1 },
	{ "second",      TIMELIB_SECOND,  1 },
	{ "seconds",     TIMELIB_SECOND,  1 },
	{ "min",         TIMELIB_MINUTE,  1 },
	{ "mins",        TIMELIB_MINUTE,  1 },
	{ "minute",      TIMELIB_MINUTE,  1 },
	{ "minutes",     TIMELIB_MINUTE,  1 },
	{ "hour",        TIMELIB_HOUR,    1 },
	{ "hours",       TIMELIB_HOUR,    1 },
	{ "day",         TIMELIB_DAY,     1 },
	{ "days",        TIMELIB_DAY,     1 },
	{ "week",        TIMELIB_DAY,     7 },
	{ "weeks",       TIMELIB_DAY,     7 },
	{ "fortnight",   TIMELIB_DAY,    14 },
	{ "fortnights",  TIMELIB_DAY,    14 },
	{ "forthnight",  TIMELIB_DAY,    14 },
	{ "forthnights", TIMELIB_DAY,    14 },
	{ "month",       TIMELIB_MONTH,   1 },
	{ "months",      TIMELIB_MONTH,   1 },
	{ "year",        TIMELIB_YEAR,    1 },
	{ "years",       TIMELIB_YEAR,    1 },

	{ "monday",      TIMELIB_WEEKDAY, 1 },
	{ "mon",         TIMELIB_WEEKDAY, 1 },
	{ "tuesday",     TIMELIB_WEEKDAY, 2 },
	{ "tue",         TIMELIB_WEEKDAY, 2 },
	{ "wednesday",   TIMELIB_WEEKDAY, 3 },
	{ "wed",         TIMELIB_WEEKDAY, 3 },
	{ "thursday",    TIMELIB_WEEKDAY, 4 },
	{ "thu",         TIMELIB_WEEKDAY, 4 },
	{ "friday",      TIMELIB_WEEKDAY, 5 },
	{ "fri",         TIMELIB_WEEKDAY, 5 },
	{ "saturday",    TIMELIB_WEEKDAY, 6 },
	{ "sat",         TIMELIB_WEEKDAY, 6 },
	{ "sunday",      TIMELIB_WEEKDAY, 0 },
	{ "sun",         TIMELIB_WEEKDAY, 0 },

	{ "weekday",     TIMELIB_SPECIAL, TIMELIB_SPECIAL_WEEKDAY },
	{ "weekdays",    TIMELIB_SPECIAL, TIMELIB_SPECIAL_WEEKDAY },
	{ NULL,          0,          0 }
};

/* The relative text table. */
static timelib_lookup_table const timelib_reltext_lookup[] = {
	{ "first",    0,  1 },
	{ "next",     0,  1 },
	{ "second",   0,  2 },
	{ "third",    0,  3 },
	{ "fourth",   0,  4 },
	{ "fifth",    0,  5 },
	{ "sixth",    0,  6 },
	{ "seventh",  0,  7 },
	{ "eight",    0,  8 },
	{ "ninth",    0,  9 },
	{ "tenth",    0, 10 },
	{ "eleventh", 0, 11 },
	{ "twelfth",  0, 12 },
	{ "last",     0, -1 },
	{ "previous", 0, -1 },
	{ "this",     1,  0 },
	{ NULL,       1,  0 }
};

/* The month table. */
static timelib_lookup_table const timelib_month_lookup[] = {
	{ "jan",  0,  1 },
	{ "feb",  0,  2 },
	{ "mar",  0,  3 },
	{ "apr",  0,  4 },
	{ "may",  0,  5 },
	{ "jun",  0,  6 },
	{ "jul",  0,  7 },
	{ "aug",  0,  8 },
	{ "sep",  0,  9 },
	{ "sept", 0,  9 },
	{ "oct",  0, 10 },
	{ "nov",  0, 11 },
	{ "dec",  0, 12 },
	{ "i",    0,  1 },
	{ "ii",   0,  2 },
	{ "iii",  0,  3 },
	{ "iv",   0,  4 },
	{ "v",    0,  5 },
	{ "vi",   0,  6 },
	{ "vii",  0,  7 },
	{ "viii", 0,  8 },
	{ "ix",   0,  9 },
	{ "x",    0, 10 },
	{ "xi",   0, 11 },
	{ "xii",  0, 12 },

	{ "january",   0,  1 },
	{ "february",  0,  2 },
	{ "march",     0,  3 },
	{ "april",     0,  4 },
	{ "may",       0,  5 },
	{ "june",      0,  6 },
	{ "july",      0,  7 },
	{ "august",    0,  8 },
	{ "september", 0,  9 },
	{ "october",   0, 10 },
	{ "november",  0, 11 },
	{ "december",  0, 12 },
	{  NULL,       0,  0 }
};

#if 0
static char* timelib_ltrim(char *s)
{
	char *ptr = s;
	while (ptr[0] == ' ' || ptr[0] == '\t') {
		ptr++;
	}
	return ptr;
}
#endif

#if 0
uchar *fill(Scanner *s, uchar *cursor){
	if(!s->eof){
		unsigned int cnt = s->tok - s->bot;
		if(cnt){
			memcpy(s->bot, s->tok, s->lim - s->tok);
			s->tok = s->bot;
			s->ptr -= cnt;
			cursor -= cnt;
			s->pos -= cnt;
			s->lim -= cnt;
		}
		if((s->top - s->lim) < BSIZE){
			uchar *buf = (uchar*) malloc(((s->lim - s->bot) + BSIZE)*sizeof(uchar));
			memcpy(buf, s->tok, s->lim - s->tok);
			s->tok = buf;
			s->ptr = &buf[s->ptr - s->bot];
			cursor = &buf[cursor - s->bot];
			s->pos = &buf[s->pos - s->bot];
			s->lim = &buf[s->lim - s->bot];
			s->top = &s->lim[BSIZE];
			free(s->bot);
			s->bot = buf;
		}
		if((cnt = read(s->fd, (char*) s->lim, BSIZE)) != BSIZE){
			s->eof = &s->lim[cnt]; *(s->eof)++ = '\n';
		}
		s->lim += cnt;
	}
	return cursor;
}
#endif

static void add_warning(Scanner *s, char *error)
{
	s->errors->warning_count++;
	s->errors->warning_messages = realloc(s->errors->warning_messages, s->errors->warning_count * sizeof(timelib_error_message));
	s->errors->warning_messages[s->errors->warning_count - 1].position = s->tok ? s->tok - s->str : 0;
	s->errors->warning_messages[s->errors->warning_count - 1].character = s->tok ? *s->tok : 0;
	s->errors->warning_messages[s->errors->warning_count - 1].message = strdup(error);
}

static void add_error(Scanner *s, char *error)
{
	s->errors->error_count++;
	s->errors->error_messages = realloc(s->errors->error_messages, s->errors->error_count * sizeof(timelib_error_message));
	s->errors->error_messages[s->errors->error_count - 1].position = s->tok ? s->tok - s->str : 0;
	s->errors->error_messages[s->errors->error_count - 1].character = s->tok ? *s->tok : 0;
	s->errors->error_messages[s->errors->error_count - 1].message = strdup(error);
}

static timelib_sll timelib_meridian(char **ptr, timelib_sll h)
{
	timelib_sll retval = 0;

	while (!strchr("AaPp", **ptr)) {
		++*ptr;
	}
	if (**ptr == 'a' || **ptr == 'A') {
		if (h == 12) {
			retval = -12;
		}
	} else if (h != 12) {
		retval = 12;
	}
	++*ptr;
	if (**ptr == '.') {
		*ptr += 3;
	} else {
		++*ptr;
	}
	return retval;
}

static char *timelib_string(Scanner *s)
{
	char *tmp = calloc(1, s->cur - s->tok + 1);
	memcpy(tmp, s->tok, s->cur - s->tok);

	return tmp;
}

static timelib_sll timelib_get_nr(char **ptr, int max_length)
{
	char *begin, *end, *str;
	timelib_sll tmp_nr = -1;
	int len = 0;

	while ((**ptr < '0') || (**ptr > '9')) {
		if (**ptr == '\0') {
			return -1;
		}
		++*ptr;
	}
	begin = *ptr;
	while ((**ptr >= '0') && (**ptr <= '9') && len < max_length) {
		++*ptr;
		++len;
	}
	end = *ptr;
	str = calloc(1, end - begin + 1);
	memcpy(str, begin, end - begin);
	tmp_nr = strtoll(str, NULL, 10);
	free(str);
	return tmp_nr;
}

static void timelib_skip_day_suffix(char **ptr)
{
	if (isspace(**ptr)) {
		return;
	}
	if (!strncasecmp(*ptr, "nd", 2) || !strncasecmp(*ptr, "rd", 2) ||!strncasecmp(*ptr, "st", 2) || !strncasecmp(*ptr, "th", 2)) {
		*ptr += 2;
	}
}

static double timelib_get_frac_nr(char **ptr, int max_length)
{
	char *begin, *end, *str;
	double tmp_nr = -1;
	int len = 0;

	while ((**ptr != '.') && ((**ptr < '0') || (**ptr > '9'))) {
		if (**ptr == '\0') {
			return -1;
		}
		++*ptr;
	}
	begin = *ptr;
	while (((**ptr == '.') || ((**ptr >= '0') && (**ptr <= '9'))) && len < max_length) {
		++*ptr;
		++len;
	}
	end = *ptr;
	str = calloc(1, end - begin + 1);
	memcpy(str, begin, end - begin);
	tmp_nr = strtod(str, NULL);
	free(str);
	return tmp_nr;
}

static timelib_ull timelib_get_unsigned_nr(char **ptr, int max_length)
{
	timelib_ull dir = 1;

	while (((**ptr < '0') || (**ptr > '9')) && (**ptr != '+') && (**ptr != '-')) {
		if (**ptr == '\0') {
			return -1;
		}
		++*ptr;
	}
	if (**ptr == '+') {
		++*ptr;
	} else if (**ptr == '-') {
		dir = -1;
		++*ptr;
	}
	return dir * timelib_get_nr(ptr, max_length);
}

static long timelib_parse_tz_cor(char **ptr)
{
	char *begin = *ptr, *end;
	long  tmp;

	while (**ptr != '\0') {
		++*ptr;
	}
	end = *ptr;
	switch (end - begin) {
		case 1:
		case 2:
			return HOUR(strtol(begin, NULL, 10));
			break;
		case 3:
		case 4:
			if (begin[1] == ':') {
				tmp = HOUR(strtol(begin, NULL, 10)) + strtol(begin + 2, NULL, 10);
				return tmp;
			} else if (begin[2] == ':') {
				tmp = HOUR(strtol(begin, NULL, 10)) + strtol(begin + 3, NULL, 10);
				return tmp;
			} else {
				tmp = strtol(begin, NULL, 10);
				return HOUR(tmp / 100) + tmp % 100;
			}
		case 5:
			tmp = HOUR(strtol(begin, NULL, 10)) + strtol(begin + 3, NULL, 10);
			return tmp;
	}
	return 0;
}

static timelib_sll timelib_lookup_relative_text(char **ptr, int *behavior)
{
	char *word;
	char *begin = *ptr, *end;
	timelib_sll  value = 0;
	const timelib_lookup_table *tp;

	while ((**ptr >= 'A' && **ptr <= 'Z') || (**ptr >= 'a' && **ptr <= 'z')) {
		++*ptr;
	}
	end = *ptr;
	word = calloc(1, end - begin + 1);
	memcpy(word, begin, end - begin);

	for (tp = timelib_reltext_lookup; tp->name; tp++) {
		if (strcasecmp(word, tp->name) == 0) {
			value = tp->value;
			*behavior = tp->type;
		}
	}

	free(word);
	return value;
}

static timelib_sll timelib_get_relative_text(char **ptr, int *behavior)
{
	while (**ptr == ' ' || **ptr == '\t' || **ptr == '-' || **ptr == '/') {
		++*ptr;
	}
	return timelib_lookup_relative_text(ptr, behavior);
}

static long timelib_lookup_month(char **ptr)
{
	char *word;
	char *begin = *ptr, *end;
	long  value = 0;
	const timelib_lookup_table *tp;

	while ((**ptr >= 'A' && **ptr <= 'Z') || (**ptr >= 'a' && **ptr <= 'z')) {
		++*ptr;
	}
	end = *ptr;
	word = calloc(1, end - begin + 1);
	memcpy(word, begin, end - begin);

	for (tp = timelib_month_lookup; tp->name; tp++) {
		if (strcasecmp(word, tp->name) == 0) {
			value = tp->value;
		}
	}

	free(word);
	return value;
}

static long timelib_get_month(char **ptr)
{
	while (**ptr == ' ' || **ptr == '\t' || **ptr == '-' || **ptr == '.' || **ptr == '/') {