diff --git a/approxidate.c b/approxidate.c new file mode 100644 index 0000000..404019c --- /dev/null +++ b/approxidate.c @@ -0,0 +1,926 @@ +/* + * Approxidate, taken from git. + * + * Copyright (C) Linus Torvalds, 2005 + */ + +#include "approxidate.h" + +#include +#include +#include +#include +#include + +/** + * Maintains compatibility with the default struct tm, + * but adds a field for usec. + */ +struct atm { + int tm_sec; + int tm_min; + int tm_hour; + int tm_mday; + int tm_mon; + int tm_year; + int tm_wday; + int tm_yday; + int tm_isdst; + long tm_usec; +}; + +#define GIT_SPACE 0x01 +#define GIT_DIGIT 0x02 +#define GIT_ALPHA 0x04 +#define GIT_GLOB_SPECIAL 0x08 +#define GIT_REGEX_SPECIAL 0x10 +#define GIT_PATHSPEC_MAGIC 0x20 +#define GIT_CNTRL 0x40 +#define GIT_PUNCT 0x80 +#define sane_istest(x,mask) ((sane_ctype[(unsigned char)(x)] & (mask)) != 0) +#define isdigit(x) sane_istest(x,GIT_DIGIT) +#define isalpha(x) sane_istest(x,GIT_ALPHA) +#define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT) +#define toupper(x) sane_case((unsigned char)(x), 0) +#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0])) + +enum { + S = GIT_SPACE, + A = GIT_ALPHA, + D = GIT_DIGIT, + G = GIT_GLOB_SPECIAL, /* *, ?, [, \\ */ + R = GIT_REGEX_SPECIAL, /* $, (, ), +, ., ^, {, | */ + P = GIT_PATHSPEC_MAGIC, /* other non-alnum, except for ] and } */ + X = GIT_CNTRL, + U = GIT_PUNCT, + Z = GIT_CNTRL | GIT_SPACE +}; + +const unsigned char sane_ctype[256] = { + X, X, X, X, X, X, X, X, X, Z, Z, X, X, Z, X, X, /* 0.. 15 */ + X, X, X, X, X, X, X, X, X, X, X, X, X, X, X, X, /* 16.. 31 */ + S, P, P, P, R, P, P, P, R, R, G, R, P, P, R, P, /* 32.. 47 */ + D, D, D, D, D, D, D, D, D, D, P, P, P, P, P, G, /* 48.. 63 */ + P, A, A, A, A, A, A, A, A, A, A, A, A, A, A, A, /* 64.. 79 */ + A, A, A, A, A, A, A, A, A, A, A, G, G, U, R, P, /* 80.. 95 */ + P, A, A, A, A, A, A, A, A, A, A, A, A, A, A, A, /* 96..111 */ + A, A, A, A, A, A, A, A, A, A, A, R, R, U, P, X, /* 112..127 */ + /* Nothing in the 128.. range */ +}; + +static inline int sane_case(int x, int high) +{ + if (sane_istest(x, GIT_ALPHA)) + x = (x & ~0x20) | high; + return x; +} + +/* + * This is like mktime, but without normalization of tm_wday and tm_yday. + */ +static time_t tm_to_time_t(const struct atm *tm) +{ + static const int mdays[] = { + 0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334 + }; + int year = tm->tm_year - 70; + int month = tm->tm_mon; + int day = tm->tm_mday; + + if (year < 0 || year > 129) /* algo only works for 1970-2099 */ + return -1; + if (month < 0 || month > 11) /* array bounds */ + return -1; + if (month < 2 || (year + 2) % 4) + day--; + if (tm->tm_hour < 0 || tm->tm_min < 0 || tm->tm_sec < 0) + return -1; + return (year * 365 + (year + 1) / 4 + mdays[month] + day) * 24*60*60UL + + tm->tm_hour * 60*60 + tm->tm_min * 60 + tm->tm_sec; +} + +static const char *month_names[] = { + "January", "February", "March", "April", "May", "June", + "July", "August", "September", "October", "November", "December" +}; + +static const char *weekday_names[] = { + "Sundays", "Mondays", "Tuesdays", "Wednesdays", "Thursdays", "Fridays", "Saturdays" +}; + +/* + * Check these. And note how it doesn't do the summer-time conversion. + * + * In my world, it's always summer, and things are probably a bit off + * in other ways too. + */ +static const struct { + const char *name; + int offset; + int dst; +} timezone_names[] = { + { "IDLW", -12, 0, }, /* International Date Line West */ + { "NT", -11, 0, }, /* Nome */ + { "CAT", -10, 0, }, /* Central Alaska */ + { "HST", -10, 0, }, /* Hawaii Standard */ + { "HDT", -10, 1, }, /* Hawaii Daylight */ + { "YST", -9, 0, }, /* Yukon Standard */ + { "YDT", -9, 1, }, /* Yukon Daylight */ + { "PST", -8, 0, }, /* Pacific Standard */ + { "PDT", -8, 1, }, /* Pacific Daylight */ + { "MST", -7, 0, }, /* Mountain Standard */ + { "MDT", -7, 1, }, /* Mountain Daylight */ + { "CST", -6, 0, }, /* Central Standard */ + { "CDT", -6, 1, }, /* Central Daylight */ + { "EST", -5, 0, }, /* Eastern Standard */ + { "EDT", -5, 1, }, /* Eastern Daylight */ + { "AST", -3, 0, }, /* Atlantic Standard */ + { "ADT", -3, 1, }, /* Atlantic Daylight */ + { "WAT", -1, 0, }, /* West Africa */ + + { "GMT", 0, 0, }, /* Greenwich Mean */ + { "UTC", 0, 0, }, /* Universal (Coordinated) */ + { "Z", 0, 0, }, /* Zulu, alias for UTC */ + + { "WET", 0, 0, }, /* Western European */ + { "BST", 0, 1, }, /* British Summer */ + { "CET", +1, 0, }, /* Central European */ + { "MET", +1, 0, }, /* Middle European */ + { "MEWT", +1, 0, }, /* Middle European Winter */ + { "MEST", +1, 1, }, /* Middle European Summer */ + { "CEST", +1, 1, }, /* Central European Summer */ + { "MESZ", +1, 1, }, /* Middle European Summer */ + { "FWT", +1, 0, }, /* French Winter */ + { "FST", +1, 1, }, /* French Summer */ + { "EET", +2, 0, }, /* Eastern Europe, USSR Zone 1 */ + { "EEST", +2, 1, }, /* Eastern European Daylight */ + { "WAST", +7, 0, }, /* West Australian Standard */ + { "WADT", +7, 1, }, /* West Australian Daylight */ + { "CCT", +8, 0, }, /* China Coast, USSR Zone 7 */ + { "JST", +9, 0, }, /* Japan Standard, USSR Zone 8 */ + { "EAST", +10, 0, }, /* Eastern Australian Standard */ + { "EADT", +10, 1, }, /* Eastern Australian Daylight */ + { "GST", +10, 0, }, /* Guam Standard, USSR Zone 9 */ + { "NZT", +12, 0, }, /* New Zealand */ + { "NZST", +12, 0, }, /* New Zealand Standard */ + { "NZDT", +12, 1, }, /* New Zealand Daylight */ + { "IDLE", +12, 0, }, /* International Date Line East */ +}; + +static int match_string(const char *date, const char *str) +{ + int i = 0; + + for (i = 0; *date; date++, str++, i++) { + if (*date == *str) + continue; + if (toupper(*date) == toupper(*str)) + continue; + if (!isalnum(*date)) + break; + return 0; + } + return i; +} + +static int skip_alpha(const char *date) +{ + int i = 0; + do { + i++; + } while (isalpha(date[i])); + return i; +} + +/* +* Parse month, weekday, or timezone name +*/ +static int match_alpha(const char *date, struct atm *tm, int *offset) +{ + int i; + + for (i = 0; i < 12; i++) { + int match = match_string(date, month_names[i]); + if (match >= 3) { + tm->tm_mon = i; + return match; + } + } + + for (i = 0; i < 7; i++) { + int match = match_string(date, weekday_names[i]); + if (match >= 3) { + tm->tm_wday = i; + return match; + } + } + + for (i = 0; i < ARRAY_SIZE(timezone_names); i++) { + int match = match_string(date, timezone_names[i].name); + if (match >= 3 || match == strlen(timezone_names[i].name)) { + int off = timezone_names[i].offset; + + /* This is bogus, but we like summer */ + off += timezone_names[i].dst; + + /* Only use the tz name offset if we don't have anything better */ + if (*offset == -1) + *offset = 60*off; + + return match; + } + } + + if (match_string(date, "PM") == 2) { + tm->tm_hour = (tm->tm_hour % 12) + 12; + return 2; + } + + if (match_string(date, "AM") == 2) { + tm->tm_hour = (tm->tm_hour % 12) + 0; + return 2; + } + + /* BAD CRAP */ + return skip_alpha(date); +} + +static int is_date(int year, int month, int day, struct atm *now_tm, time_t now, struct atm *tm) +{ + if (month > 0 && month < 13 && day > 0 && day < 32) { + struct atm check = *tm; + struct atm *r = (now_tm ? &check : tm); + + r->tm_mon = month - 1; + r->tm_mday = day; + if (year == -1) { + if (!now_tm) + return 1; + r->tm_year = now_tm->tm_year; + } + else if (year >= 1970 && year < 2100) + r->tm_year = year - 1900; + else if (year > 70 && year < 100) + r->tm_year = year; + else if (year < 38) + r->tm_year = year + 100; + else + return 0; + if (!now_tm) + return 1; + + tm->tm_mon = r->tm_mon; + tm->tm_mday = r->tm_mday; + if (year != -1) + tm->tm_year = r->tm_year; + return 1; + } + return 0; +} + +static int match_multi_number(unsigned long num, char c, const char *date, + char *end, struct atm *tm, time_t now) +{ + long num2, num3, num4; + + num2 = strtol(end+1, &end, 10); + num3 = -1; + num4 = 0; + if (*end == c && isdigit(end[1])) { + num3 = strtol(end+1, &end, 10); + + if (*end == '.') { + char *start = end+1; + num4 = strtol(end+1, &end, 10); + if ((end - start) < 6) { + num4 *= (long)pow(10, 6 - (end - start)); + } + } + } + + + /* Time? Date? */ + switch (c) { + case ':': + if (num3 < 0) + num3 = 0; + if (num < 25 && num2 >= 0 && num2 < 60 && num3 >= 0 && num3 <= 60) { + tm->tm_hour = num; + tm->tm_min = num2; + tm->tm_sec = num3; + tm->tm_usec = num4; + break; + } + return 0; + + case '-': + case '/': + case '.': + if (!now) + now = time(NULL); + if (num > 70) { + /* yyyy-mm-dd? */ + if (is_date(num, num2, num3, NULL, now, tm)) + break; + /* yyyy-dd-mm? */ + if (is_date(num, num3, num2, NULL, now, tm)) + break; + } + /* Our eastern European friends say dd.mm.yy[yy] + * is the norm there, so giving precedence to + * mm/dd/yy[yy] form only when separator is not '.' + */ + if (c != '.' && + is_date(num3, num, num2, NULL, now, tm)) + break; + /* European dd.mm.yy[yy] or funny US dd/mm/yy[yy] */ + if (is_date(num3, num2, num, NULL, now, tm)) + break; + /* Funny European mm.dd.yy */ + if (c == '.' && + is_date(num3, num, num2, NULL, now, tm)) + break; + return 0; + } + return end - date; +} + +/* + * Have we filled in any part of the time/date yet? + * We just do a binary 'and' to see if the sign bit + * is set in all the values. + */ +static inline int nodate(struct tm *tm) +{ + return (tm->tm_year & + tm->tm_mon & + tm->tm_mday & + tm->tm_hour & + tm->tm_min & + tm->tm_sec) < 0; +} + +/* + * We've seen a digit. Time? Year? Date? + */ +static int match_digit(const char *date, struct atm *tm, int *offset, int *tm_gmt) +{ + int n; + char *end; + unsigned long num; + + num = strtoul(date, &end, 10); + + /* + * Seconds since 1970? We trigger on that for any numbers with + * more than 8 digits. This is because we don't want to rule out + * numbers like 20070606 as a YYYYMMDD date. + */ + if (num >= 100000000 && nodate((struct tm*)tm)) { + time_t time = num; + if (gmtime_r(&time, (struct tm*)tm)) { + *tm_gmt = 1; + return end - date; + } + } + + /* + * Check for special formats: num[-.:/]num[same]num[.secfracs] + */ + switch (*end) { + case ':': + case '.': + case '/': + case '-': + if (isdigit(end[1])) { + int match = match_multi_number(num, *end, date, end, tm, 0); + if (match) + return match; + } + } + + /* + * None of the special formats? Try to guess what + * the number meant. We use the number of digits + * to make a more educated guess.. + */ + n = 0; + do { + n++; + } while (isdigit(date[n])); + + /* Four-digit year or a timezone? */ + if (n == 4) { + if (num <= 1400 && *offset == -1) { + unsigned int minutes = num % 100; + unsigned int hours = num / 100; + *offset = hours*60 + minutes; + } else if (num > 1900 && num < 2100) + tm->tm_year = num - 1900; + return n; + } + + /* + * Ignore lots of numerals. We took care of 4-digit years above. + * Days or months must be one or two digits. + */ + if (n > 2) + return n; + + /* + * NOTE! We will give precedence to day-of-month over month or + * year numbers in the 1-12 range. So 05 is always "mday 5", + * unless we already have a mday.. + * + * IOW, 01 Apr 05 parses as "April 1st, 2005". + */ + if (num > 0 && num < 32 && tm->tm_mday < 0) { + tm->tm_mday = num; + return n; + } + + /* Two-digit year? */ + if (n == 2 && tm->tm_year < 0) { + if (num < 10 && tm->tm_mday >= 0) { + tm->tm_year = num + 100; + return n; + } + if (num >= 70) { + tm->tm_year = num; + return n; + } + } + + if (num > 0 && num < 13 && tm->tm_mon < 0) + tm->tm_mon = num-1; + + return n; +} + +static int match_tz(const char *date, int *offp) +{ + char *end; + int hour = strtoul(date + 1, &end, 10); + int n = end - (date + 1); + int min = 0; + + if (n == 4) { + /* hhmm */ + min = hour % 100; + hour = hour / 100; + } else if (n != 2) { + min = 99; /* random crap */ + } else if (*end == ':') { + /* hh:mm? */ + min = strtoul(end + 1, &end, 10); + if (end - (date + 1) != 5) + min = 99; /* random crap */ + } /* otherwise we parsed "hh" */ + + /* + * Don't accept any random crap. Even though some places have + * offset larger than 12 hours (e.g. Pacific/Kiritimati is at + * UTC+14), there is something wrong if hour part is much + * larger than that. We might also want to check that the + * minutes are divisible by 15 or something too. (Offset of + * Kathmandu, Nepal is UTC+5:45) + */ + if (min < 60 && hour < 24) { + int offset = hour * 60 + min; + if (*date == '-') + offset = -offset; + *offp = offset; + } + return end - date; +} + +/* + * Parse a string like "0 +0000" as ancient timestamp near epoch, but + * only when it appears not as part of any other string. + */ +static int match_object_header_date(const char *date, struct timeval *tv, int *offset) +{ + char *end; + unsigned long stamp; + int ofs; + + if (*date < '0' || '9' < *date) + return -1; + stamp = strtoul(date, &end, 10); + if (*end != ' ' || stamp == ULONG_MAX || (end[1] != '+' && end[1] != '-')) + return -1; + date = end + 2; + ofs = strtol(date, &end, 10); + if ((*end != '\0' && (*end != '\n')) || end != date + 4) + return -1; + ofs = (ofs / 100) * 60 + (ofs % 100); + if (date[-1] == '-') + ofs = -ofs; + tv->tv_sec = stamp; + *offset = ofs; + return 0; +} + +/* Gr. strptime is crap for this; it doesn't have a way to require RFC2822 + (i.e. English) day/month names, and it doesn't work correctly with %z. */ +int parse_date_basic(const char *date, struct timeval *tv, int *offset) +{ + struct atm tm; + int tm_gmt; + int dummy_offset; + + if (!offset) + offset = &dummy_offset; + + memset(&tm, 0, sizeof(tm)); + tm.tm_year = -1; + tm.tm_mon = -1; + tm.tm_mday = -1; + tm.tm_isdst = -1; + tm.tm_hour = -1; + tm.tm_min = -1; + tm.tm_sec = -1; + tm.tm_usec = 0; + *offset = -1; + tm_gmt = 0; + + if (*date == '@' && + !match_object_header_date(date + 1, tv, offset)) + return 0; /* success */ + for (;;) { + int match = 0; + unsigned char c = *date; + + /* Stop at end of string or newline */ + if (!c || c == '\n') + break; + + if (isalpha(c)) + match = match_alpha(date, &tm, offset); + else if (isdigit(c)) + match = match_digit(date, &tm, offset, &tm_gmt); + else if ((c == '-' || c == '+') && isdigit(date[1])) + match = match_tz(date, offset); + + if (!match) { + /* BAD CRAP */ + match = 1; + } + + date += match; + } + + tv->tv_usec = tm.tm_usec; + + /* mktime uses local timezone */ + tv->tv_sec = tm_to_time_t(&tm); + if (*offset == -1) { + time_t temp_time = mktime((struct tm*)&tm); + if (tv->tv_sec > temp_time) { + *offset = (tv->tv_sec - temp_time) / 60; + } else { + *offset = -(int)((temp_time - tv->tv_sec) / 60); + } + } + + if (*offset == -1) + *offset = (((time_t)tv->tv_sec) - mktime((struct tm*)&tm)) / 60; + + if (tv->tv_sec == -1) + return -1; + + if (!tm_gmt) + tv->tv_sec -= *offset * 60; + + return 0; /* success */ +} + +/* + * Relative time update (eg "2 days ago"). If we haven't set the time + * yet, we need to set it from current time. + */ +static unsigned long update_tm(struct atm *tm, struct atm *now, unsigned long sec) +{ + time_t n; + + if (tm->tm_mday < 0) + tm->tm_mday = now->tm_mday; + if (tm->tm_mon < 0) + tm->tm_mon = now->tm_mon; + if (tm->tm_year < 0) { + tm->tm_year = now->tm_year; + if (tm->tm_mon > now->tm_mon) + tm->tm_year--; + } + + n = mktime((struct tm*)tm) - sec; + localtime_r(&n, (struct tm*)tm); + return n; +} + +static void date_now(struct atm *tm, struct atm *now, int *num) +{ + update_tm(tm, now, 0); +} + +static void date_yesterday(struct atm *tm, struct atm *now, int *num) +{ + update_tm(tm, now, 24*60*60); +} + +static void date_time(struct atm *tm, struct atm *now, int hour) +{ + if (tm->tm_hour < hour) + date_yesterday(tm, now, NULL); + tm->tm_hour = hour; + tm->tm_min = 0; + tm->tm_sec = 0; +} + +static void date_midnight(struct atm *tm, struct atm *now, int *num) +{ + date_time(tm, now, 0); +} + +static void date_noon(struct atm *tm, struct atm *now, int *num) +{ + date_time(tm, now, 12); +} + +static void date_tea(struct atm *tm, struct atm *now, int *num) +{ + date_time(tm, now, 17); +} + +static void date_pm(struct atm *tm, struct atm *now, int *num) +{ + int hour, n = *num; + *num = 0; + + hour = tm->tm_hour; + if (n) { + hour = n; + tm->tm_min = 0; + tm->tm_sec = 0; + } + tm->tm_hour = (hour % 12) + 12; +} + +static void date_am(struct atm *tm, struct atm *now, int *num) +{ + int hour, n = *num; + *num = 0; + + hour = tm->tm_hour; + if (n) { + hour = n; + tm->tm_min = 0; + tm->tm_sec = 0; + } + tm->tm_hour = (hour % 12); +} + +static void date_never(struct atm *tm, struct atm *now, int *num) +{ + time_t n = 0; + localtime_r(&n, (struct tm*)tm); +} + +static const struct special { + const char *name; + void (*fn)(struct atm *, struct atm *, int *); +} special[] = { + { "yesterday", date_yesterday }, + { "noon", date_noon }, + { "midnight", date_midnight }, + { "tea", date_tea }, + { "PM", date_pm }, + { "AM", date_am }, + { "never", date_never }, + { "now", date_now }, + { NULL } +}; + +static const char *number_name[] = { + "zero", "one", "two", "three", "four", + "five", "six", "seven", "eight", "nine", "ten", +}; + +static const struct typelen { + const char *type; + int length; +} typelen[] = { + { "seconds", 1 }, + { "minutes", 60 }, + { "hours", 60*60 }, + { "days", 24*60*60 }, + { "weeks", 7*24*60*60 }, + { NULL } +}; + +static const char *approxidate_alpha(const char *date, struct atm *tm, struct atm *now, int *num, int *touched) +{ + const struct typelen *tl; + const struct special *s; + const char *end = date; + int i; + + while (isalpha(*++end)) + ; + + for (i = 0; i < 12; i++) { + int match = match_string(date, month_names[i]); + if (match >= 3) { + tm->tm_mon = i; + *touched = 1; + return end; + } + } + + for (s = special; s->name; s++) { + int len = strlen(s->name); + if (match_string(date, s->name) == len) { + s->fn(tm, now, num); + *touched = 1; + return end; + } + } + + if (!*num) { + for (i = 1; i < 11; i++) { + int len = strlen(number_name[i]); + if (match_string(date, number_name[i]) == len) { + *num = i; + *touched = 1; + return end; + } + } + if (match_string(date, "last") == 4) { + *num = 1; + *touched = 1; + } + return end; + } + + tl = typelen; + while (tl->type) { + int len = strlen(tl->type); + if (match_string(date, tl->type) >= len-1) { + update_tm(tm, now, tl->length * *num); + *num = 0; + *touched = 1; + return end; + } + tl++; + } + + for (i = 0; i < 7; i++) { + int match = match_string(date, weekday_names[i]); + if (match >= 3) { + int diff, n = *num -1; + *num = 0; + + diff = tm->tm_wday - i; + if (diff <= 0) + n++; + diff += 7*n; + + update_tm(tm, now, diff * 24 * 60 * 60); + *touched = 1; + return end; + } + } + + if (match_string(date, "months") >= 5) { + int n; + update_tm(tm, now, 0); /* fill in date fields if needed */ + n = tm->tm_mon - *num; + *num = 0; + while (n < 0) { + n += 12; + tm->tm_year--; + } + tm->tm_mon = n; + *touched = 1; + return end; + } + + if (match_string(date, "years") >= 4) { + update_tm(tm, now, 0); /* fill in date fields if needed */ + tm->tm_year -= *num; + *num = 0; + *touched = 1; + return end; + } + + return end; +} + +static const char *approxidate_digit(const char *date, struct atm *tm, int *num, + time_t now) +{ + char *end; + unsigned long number = strtoul(date, &end, 10); + + switch (*end) { + case ':': + case '.': + case '/': + case '-': + if (isdigit(end[1])) { + int match = match_multi_number(number, *end, date, end, + tm, now); + if (match) + return date + match; + } + } + + /* Accept zero-padding only for small numbers ("Dec 02", never "Dec 0002") */ + if (date[0] != '0' || end - date <= 2) + *num = number; + return end; +} + +/* + * Do we have a pending number at the end, or when + * we see a new one? Let's assume it's a month day, + * as in "Dec 6, 1992" + */ +static void pending_number(struct atm *tm, int *num) +{ + int number = *num; + + if (number) { + *num = 0; + if (tm->tm_mday < 0 && number < 32) + tm->tm_mday = number; + else if (tm->tm_mon < 0 && number < 13) + tm->tm_mon = number-1; + else if (tm->tm_year < 0) { + if (number > 1969 && number < 2100) + tm->tm_year = number - 1900; + else if (number > 69 && number < 100) + tm->tm_year = number; + else if (number < 38) + tm->tm_year = 100 + number; + /* We screw up for number = 00 ? */ + } + } +} + +static int approxidate_str(const char *date, struct timeval *tv) +{ + int number = 0; + int touched = 0; + struct atm tm, now; + time_t time_sec; + + time_sec = tv->tv_sec; + localtime_r(&time_sec, (struct tm*)&tm); + now = tm; + + tm.tm_year = -1; + tm.tm_mon = -1; + tm.tm_mday = -1; + tm.tm_usec = tv->tv_usec; + + for (;;) { + unsigned char c = *date; + if (!c) + break; + date++; + if (isdigit(c)) { + pending_number(&tm, &number); + date = approxidate_digit(date-1, &tm, &number, time_sec); + touched = 1; + continue; + } + if (isalpha(c)) + date = approxidate_alpha(date-1, &tm, &now, &number, &touched); + } + + pending_number(&tm, &number); + if (!touched) + return -1; + + tv->tv_usec = tm.tm_usec; + tv->tv_sec = update_tm(&tm, &now, 0); + + return 0; +} + +int approxidate(const char *date, struct timeval *tv) +{ + int offset; + + if (!parse_date_basic(date, tv, &offset)) { + return 0; + } + + gettimeofday(tv, NULL); + if (!approxidate_str(date, tv)) { + return 0; + } + + return -1; +} diff --git a/approxidate.h b/approxidate.h new file mode 100644 index 0000000..da382bb --- /dev/null +++ b/approxidate.h @@ -0,0 +1,15 @@ +#ifndef APPROXIDATE_H +#define APPROXIDATE_H + +#include + +/** + * @param date The date string + * @param tv Where the time will be placed. + * + * @return 0 on success + * @return 1 on error + */ +int approxidate(const char *date, struct timeval *tv); + +#endif \ No newline at end of file diff --git a/make_gen b/make_gen index 23c2c52..5f9a9fa 100644 --- a/make_gen +++ b/make_gen @@ -12,7 +12,7 @@ OBJ=psi.o buffer.o ruli.o sps.o pimotor.o \ pipiezo.o sanswave.o faverage.o spss7.o\ amorstat.o tasinit.o ptasdrive.o tasutil.o tasscan.o swmotor.o \ - polterwrite.o ecb.o frame.o \ + polterwrite.o ecb.o frame.o sqlitelog.o mongolog.o sicslogquery.o approxidate.o \ el737driv.o sinqhmdriv.o tdchm.o \ sanscook.o itc4driv.o itc4.o\ bruker.o ltc11.o eurodriv.o \ diff --git a/makefile_linux b/makefile_linux index 1a0d19d..7a9b415 100644 --- a/makefile_linux +++ b/makefile_linux @@ -15,6 +15,7 @@ include $(SICSROOT)/sics/sllinux_def CC = gcc CFLAGS = -I$(HDFROOT)/include -I$(HDFROOT)/include/os/Linux -DHDF4 -DHDF5 $(NI) -I$(TCLINC) -Ihardsup \ -I$(SICSROOT)/sics -I.. -I. -MMD -DCYGNUS -DNONINTF $(DBG) \ + -I$(HDFROOT)/include/libbson-1.0 -I$(HDFROOT)/include/libmongoc-1.0 \ $(DFORTIFY) -Wall -Wno-unused -Wunused-value -Wno-comment \ -Wno-switch -Werror diff --git a/mongolog.c b/mongolog.c new file mode 100644 index 0000000..c51b840 --- /dev/null +++ b/mongolog.c @@ -0,0 +1,198 @@ +/* + This is a module which implements output of the log to a mongodb NoSQL database. + The database is much easier for searching the log + + copyright: see file COPYRIGHT + + Mark Koennecke, February 2016 +*/ + +#include +#include +#include +#include +#include +#include +#include "sicslogquery.h" + +static char mongoURL[1024]; +static char inst[132]; + +static mongoc_client_t *client; +static mongoc_collection_t *collection; + +static void MongoCallback(unsigned int severity, const char *timeStamp, + const char *subsystem, + const char *message, void *userData); + +/*-----------------------------------------------------------------------------------*/ +static void MongoClose(void *data) +{ + RemoveLogCallback(MongoCallback); + mongoc_collection_destroy (collection); + mongoc_client_destroy (client); + mongoc_cleanup (); + client = NULL; + collection = NULL; +} +/*---------------------------------------------------------------------------------- + The callback function for entering data into the log + ------------------------------------------------------------------------------------*/ +static void MongoCallback(unsigned int severity, const char *timeStamp, + const char *subsystem, + const char *message, void *userData) +{ + double tVal = DoubleTime(); + int status; + bson_t *doc; + bson_error_t error; + bson_oid_t oid; + + if(client == NULL){ + return; + } + + if(logFilter(severity,subsystem) == 1) { + return; + } + + doc = bson_new (); + bson_oid_init (&oid, NULL); + BSON_APPEND_OID (doc, "_id", &oid); + BSON_APPEND_DOUBLE(doc,"timestamp",tVal); + BSON_APPEND_INT32(doc,"severity",severity); + BSON_APPEND_UTF8(doc,"timetext",timeStamp); + BSON_APPEND_UTF8(doc,"sub",subsystem); + BSON_APPEND_UTF8(doc,"message",message); + + if (!mongoc_collection_insert (collection, MONGOC_INSERT_NONE, doc, NULL, &error)) { + fprintf (stdout, "%s\n", error.message); + MongoClose(NULL); + Log(FATAL,"sys", "Lost connection to mongo server at %s", mongoURL); + } + + bson_destroy (doc); +} +/*------------------------------------------------------------------------------------*/ +static int MongoConfigAction(SConnection * pCon, SicsInterp * pSics, + void *pData, int argc, char *argv[]) +{ + int status; + + if(argc < 2) { + SCWrite(pCon,"ERROR: need keyword", eError); + return 0; + } + + strtolower(argv[1]); + if(strcmp(argv[1],"open") == 0){ + if(argc < 3){ + SCWrite(pCon,"ERROR: need mongourl and instrument parameters for open",eError); + return 0; + } + strncpy(mongoURL,argv[2],sizeof(mongoURL)); + strncpy(inst, argv[3],sizeof(inst)); + mongoc_init(); + client = mongoc_client_new (mongoURL); + if(!client){ + SCWrite(pCon,"ERROR: failed to connect to mongodb, bad URL?", eError); + return 0; + } + collection = mongoc_client_get_collection (client, inst, "log"); + if(!collection){ + SCWrite(pCon,"ERROR: failed to connect link to mongo DB", eError); + return 0; + } + RegisterLogCallback(MongoCallback,NULL); + SCSendOK(pCon); + } else if(strcmp(argv[1],"reopen") == 0) { + mongoc_init(); + client = mongoc_client_new (mongoURL); + if(!client){ + SCWrite(pCon,"ERROR: failed to connect to mongodb, bad URL?", eError); + return 0; + } + collection = mongoc_client_get_collection (client, inst, "log"); + if(!collection){ + SCWrite(pCon,"ERROR: failed to connect link to mongo DB", eError); + return 0; + } + RegisterLogCallback(MongoCallback,NULL); + SCSendOK(pCon); + }else if(strcmp(argv[1],"status") == 0){ + if(client == NULL){ + SCWrite(pCon,"Mongo is disconnected", eValue); + } else { + SCWrite(pCon,"Mongo is connected", eValue); + } + } else if(strcmp(argv[1],"close") == 0) { + MongoClose(NULL); + SCSendOK(pCon); + } else if(strcmp(argv[1],"filename") == 0) { + SCPrintf(pCon,eValue,"mongodb = %s", mongoURL); + } else { + SCPrintf(pCon,eError,"ERROR: keyword %s not recognised", argv[1]); + return 0; + } + return 1; +} +/*----------------------------------------------------------------------------*/ +static void QueryCallback(const bson_t *doc, void *userData) +{ + pDynString result = (pDynString)userData; + bson_iter_t iter; + unsigned int severity; + uint32_t length; + const char *message, *timeText, *sub; + char sevBuf[20]; + + bson_iter_init(&iter,doc); + bson_iter_find(&iter,"timetext"); + timeText = bson_iter_utf8(&iter,&length); + DynStringConcat(result,(char *)timeText); + DynStringConcatChar(result,' '); + bson_iter_init(&iter,doc); + bson_iter_find(&iter,"severity"); + severity = bson_iter_int32(&iter); + formatSeverity(severity,sevBuf,sizeof(sevBuf)); + DynStringConcat(result,(char *)severity); + DynStringConcatChar(result,' '); + bson_iter_find(&iter,"sub"); + sub = bson_iter_utf8(&iter,&length); + DynStringConcat(result,(char *)sub); + DynStringConcatChar(result,' '); + bson_iter_find(&iter,"message"); + message = bson_iter_utf8(&iter,&length); + DynStringConcat(result,(char *)message); + DynStringConcatChar(result,'\n'); +} +/*-----------------------------------------------------------------------------*/ +static int MongoQueryAction(SConnection * pCon, SicsInterp * pSics, + void *pData, int argc, char *argv[]) +{ + pDynString result; + char *error = NULL; + int status; + + sicslogSetup(mongoURL,inst); + result = CreateDynString(132,132); + + status = sicslogQuery(argc,argv,QueryCallback,result); + if(status != 0){ + error = sicslogGetError(); + SCPrintf(pCon,eError,"Error %s querying mongodb", error); + } else { + SCPureSockWrite(pCon,GetCharArray(result),eValue); + } + DeleteDynString(result); + return 1; +} +/*-----------------------------------------------------------------------------*/ +void MongoLogInit(void) +{ + AddCommand(pServ->pSics,"mongoconfig", MongoConfigAction, + MongoClose, NULL); + AddCommand(pServ->pSics,"showlog", MongoQueryAction, + MongoClose, NULL); +} + diff --git a/psi.c b/psi.c index a7d9866..31d742e 100644 --- a/psi.c +++ b/psi.c @@ -54,6 +54,8 @@ void SiteInit(void) INIT(LinaStartup); INIT(HaakeStartup); INIT(AmiStartup); + INIT(SqliteLogInit); + INIT(MongoLogInit); /* * SICS specific Asynchronous I/O protocols diff --git a/sicslogquery.c b/sicslogquery.c new file mode 100644 index 0000000..52e1c3d --- /dev/null +++ b/sicslogquery.c @@ -0,0 +1,206 @@ +/** + * This does the query execution for the new mongodb based sicslog. + * + * COPYRIGHT GPL + * + * Mark Koennecke, February 2016 + */ +#include +#include +#include +#include +#include + +static char lastError[1024]; +static char mongoURL[1024]; +static char inst[132]; + +static mongoc_client_t *client; +static mongoc_collection_t *collection; + +/*--------------------------------------------------------------------------------*/ +char * sicslogGetError(void) +{ + /* + May be change to strdup(lastError); + */ + return lastError; +} +/*--------------------------------------------------------------------------------*/ +int sicslogSetup(char *url, char *instPar) +{ + memset(inst,0,sizeof(inst)); + + if(instPar != NULL){ + strncpy(inst,instPar, sizeof(inst)); + } + strncpy(mongoURL,url,sizeof(mongoURL)); + + mongoc_init(); + client = mongoc_client_new (mongoURL); + if(!client){ + snprintf(lastError,sizeof(lastError),"ERROR: failed to connect to mongodb, bad URL?"); + return 1; + } + return 0; +} +/*--------------------------------------------------------------------------------*/ +static unsigned int sevFromText(const char *txt) +{ + static const char *severityText[] = {"fatal", + "error", + "warn", + "info", + "verbose", + "debug", + NULL + }; + int sev = 0; + while(severityText[sev] != NULL){ + if(strcmp(txt,severityText[sev]) == 0){ + break; + } + sev++; + } + sev++; /* starting at 1 rather then 0 */ + return sev; +} +/*---------------------------------------------------------------------------*/ +int sicslogQuery(int argc, char *argv[], ResultCallback_t func, void *userData) +{ + char c; + time_t to = time(NULL), from = to - 3600; + int severity = INFO, mult = 1, status = 0; + char *sub = NULL; + char *exp = NULL; + char *instLocal = NULL; + char *tmp, *pPtr; + char jsonQuery[2024], subQuery[132]; + struct timeval tv; + mongoc_collection_t *collection = NULL; + bson_t *query; + const bson_t *doc; + mongoc_cursor_t *cursor; + bson_error_t err; + + /* + parse options + */ + while((c = getopt(argc,argv,"s:l:f:t:i:e:c:")) != -1) { + switch (c){ + case 's': + sub = strdup(optarg); + break; + case 'l': + tmp = strdup(optarg); + if((pPtr = strrchr(tmp,(int)'h')) != NULL){ + mult = 60; + *pPtr = '\0'; + } else if((pPtr = strrchr(tmp,(int)'d')) != NULL){ + mult = 24*60; + *pPtr = '\0'; + } + from = to - atoi(tmp)*mult*60; + free(tmp); + break; + case 'f': + if(approxidate(optarg,&tv) == 0){ + from = tv.tv_sec; + } else { + snprintf(lastError,sizeof(lastError),"Failed to parse date from %s", optarg); + return 1; + } + break; + case 't': + if(approxidate(optarg,&tv) == 0){ + to = tv.tv_sec; + } else { + snprintf(lastError,sizeof(lastError),"Failed to parse date from %s", optarg); + return 1; + } + break; + case 'i': + instLocal = strdup(optarg); + break; + case 'e': + exp = strdup(optarg); + break; + case 'c': + severity = sevFromText(optarg); + break; + case '?': + if( optopt == 's' || optopt == 'l' || optopt == 'f' || optopt == 't' + || optopt == 'i' || optopt == 'e' || optopt == 'c') { + snprintf(lastError,sizeof(lastError),"Option %c requires an argument", optopt); + } else { + snprintf(lastError,sizeof(lastError),"Unknown option %c", optopt); + } + return 1; + break; + } + } + + if(instLocal == NULL && strlen(inst) > 1){ + instLocal = strdup(inst); + } + if(instLocal == NULL){ + snprintf(lastError,sizeof(lastError),"Do not know which instrument log to query, specify with -i"); + return 1; + } + + /* + build the query + */ + snprintf(jsonQuery, sizeof(jsonQuery),"{ \"timestamp\" : {\"$gt\": %ld, \"$lt\": %ld}, \"severity\": {\"$lt\": %d}", + from,to,severity-1); + if(sub != NULL){ + snprintf(subQuery,sizeof(subQuery),", \"sub\" : \"%s\"", sub); + strncat(jsonQuery,subQuery,sizeof(jsonQuery)); + } + if(exp != NULL){ + snprintf(subQuery,sizeof(subQuery),", \"message\" : {$regexp : \"/%s/\" }", exp); + strncat(jsonQuery,subQuery,sizeof(jsonQuery)); + } + strncat(jsonQuery,"}",sizeof(jsonQuery)); + + /* + now execute the query + */ + collection = mongoc_client_get_collection(client,instLocal,"log"); + if(collection == NULL){ + snprintf(lastError,sizeof(lastError),"Failed to find log for %s", instLocal); + status = 1; + goto cleanup; + } + fprintf(stdout,"The query: %s\n", jsonQuery); + query = bson_new_from_json((const uint8_t *)jsonQuery,strlen(jsonQuery), &err); + if(query == NULL){ + snprintf(lastError,sizeof(lastError),"Failed to parse query with %s", err.message); + status = 1; + goto cleanup; + } + + cursor = mongoc_collection_find (collection, MONGOC_QUERY_NONE, 0, 0, 0, query, NULL, NULL); + while (mongoc_cursor_next (cursor, &doc)) { + func(doc,userData); + } + + cleanup: + if(sub != NULL){ + free(sub); + } + if(exp != NULL){ + free(exp); + } + if(query != NULL){ + bson_destroy(query); + } + if(cursor != NULL){ + /* mongoc_cursor_destroy(cursor); */ + } + if(collection != NULL){ + mongoc_collection_destroy(collection); + } + + return status; +} diff --git a/sicslogquery.h b/sicslogquery.h new file mode 100644 index 0000000..437f6f2 --- /dev/null +++ b/sicslogquery.h @@ -0,0 +1,35 @@ +/** + * This does the query execution for the new mongodb based sicslog. + * + * COPYRIGHT GPL + * + * Mark Koennecke, February 2016 + */ + +#ifndef __SICSLOGMONGO +#define __SICSLOGMONGO +#include +/* + callback called with result data +*/ +typedef void (*ResultCallback_t)(const bson_t *doc, void *userData); + +/* + setup of the data base connection and the default instrument +*/ +int sicslogSetup(char *url, char *inst); + +/* + do the query. Retruns 0 on success, 1 on failure +*/ +int sicslogQuery(int argc, char *argv[], ResultCallback_t func, void *userData); + +/* + If sicslogQuery returned or sicslogSetup returns an error, retrieve a description + of it. Only valid right after the error inducing call. +*/ +char *sicslogGetError(); + + +#endif + diff --git a/sqlitelog.c b/sqlitelog.c new file mode 100644 index 0000000..216e94d --- /dev/null +++ b/sqlitelog.c @@ -0,0 +1,122 @@ +/* + This is a module which implements output of the log to a sqlite database. + The database is much easier for searching the log + + copyright: see file COPYRIGHT + + Mark Koennecke, February 2016 +*/ + +#include +#include +#include +#include +#include + +static sqlite3 *db; +static char sqliteFile[1024]; +static unsigned int lineCount = 0; +static unsigned int sqlActive = 0; + +/*----------------------------------------------------------------------------------*/ +static void SqlFlush(void) +{ + char *err; + + if(sqlActive == 1){ + sqlite3_exec(db,"END TRANSACTION",NULL,NULL,&err); + lineCount = 0; + } +} +/*---------------------------------------------------------------------------------- + The callback function for entering data into the log + ------------------------------------------------------------------------------------*/ +static void SqliteCallback(unsigned int severity, const char *timeStamp, + const char *subsystem, + const char *message, void *userData) +{ + double tVal = DoubleTime(); + char sql[2024]; + int status; + char *err; + + if(logFilter(severity,subsystem) == 1) { + return; + } + + if(lineCount == 0){ + sqlite3_exec(db,"BEGIN TRANSACTION",NULL,NULL,&err); + } + + sqlite3_snprintf(sizeof(sql),sql,"INSERT into log VALUES(%f,\"%s\",%d,\"%s\",\"%w\")", + tVal,timeStamp,severity,subsystem,message); + status = sqlite3_exec(db,sql,NULL,NULL,&err); + if(status != SQLITE_OK){ + printf("Sqlite logging error: %s from %s\n", err, sql); + sqlite3_free(err); + } + lineCount++; + + if(lineCount >= 1000){ + SqlFlush(); + } +} +/*-----------------------------------------------------------------------------------*/ +static void SqlClose(void *data) +{ + char *err; + + sqlite3_exec(db,"END TRANSACTION",NULL,NULL,&err); + sqlite3_close(db); + RemoveLogCallback(SqliteCallback); + sqlActive = 0; +} +/*------------------------------------------------------------------------------------*/ +static int SQLLogConfigAction(SConnection * pCon, SicsInterp * pSics, + void *pData, int argc, char *argv[]) +{ + int status; + + if(argc < 2) { + SCWrite(pCon,"ERROR: need keyword", eError); + return 0; + } + + strtolower(argv[1]); + if(strcmp(argv[1],"open") == 0){ + if(argc < 3){ + SCWrite(pCon,"ERROR: need dbfilename parameter for open",eError); + return 0; + } + strncpy(sqliteFile,argv[2],sizeof(sqliteFile)); + status = sqlite3_open(sqliteFile,&db); + if(status){ + SCPrintf(pCon,eError,"ERROR: failed to open database %s", argv[2]); + sqlite3_close(db); + return 0; + } else { + RegisterLogCallback(SqliteCallback,NULL); + sqlActive = 1; + SCSendOK(pCon); + } + } else if(strcmp(argv[1],"close") == 0) { + SqlClose(NULL); + SCSendOK(pCon); + } else if(strcmp(argv[1],"flush") == 0) { + SqlFlush(); + SCSendOK(pCon); + } else if(strcmp(argv[1],"filename") == 0) { + SCPrintf(pCon,eValue,"sqlitedb = %s", sqliteFile); + } else { + SCPrintf(pCon,eError,"ERROR: keyword %s not recognised", argv[1]); + return 0; + } + return 1; +} +/*-----------------------------------------------------------------------------*/ +void SqliteLogInit(void) +{ + AddCommand(pServ->pSics,"sqlconfig", SQLLogConfigAction, + SqlClose, NULL); +} + diff --git a/utils/Make.sicslog b/utils/Make.sicslog new file mode 100644 index 0000000..07299c4 --- /dev/null +++ b/utils/Make.sicslog @@ -0,0 +1,17 @@ +.SUFFIXES: +.SUFFIXES: .c .o + +LIBROOT=/afs/psi.ch/project/sinq/sl6 + +OBJ=../sicslogquery.o ../approxidate.o sicslogmain.o +CFLAGS=-I$(LIBROOT)/include/libmongoc-1.0 -I../ -I../../sics -I$(LIBROOT)/include/libbson-1.0 -I. +LIBFLAGS=-L$(LIBROOT)/lib -lmongoc-1.0 -lbson-1.0 + +.c.o: + $(CC) $(CFLAGS) -c -g $*.c + +all:sicslog + +sicslog: $(OBJ) + $(CC) -g -o sicslog $(OBJ) $(LIBFLAGS) + diff --git a/utils/sicslogmain.c b/utils/sicslogmain.c new file mode 100644 index 0000000..70e39f2 --- /dev/null +++ b/utils/sicslogmain.c @@ -0,0 +1,66 @@ +/* + * This is a little utility for querying the SICS mongo DB log. + * + * copyright: GPL + * + * Mark Koennecke, February 2016 + */ +#include +#include +#include + +static void formatSeverity(unsigned int severity, char *buffer, unsigned int bufferLength) +{ + static const char *severityText[] = {"FATAL", + "ERROR", + "WARNING", + "INFO", + "VERBOSE", + "DEBUG", + "INVALID" + }; + + if(severity > DEBUG){ + severity = INVALID; + } + strncpy(buffer,severityText[severity-1],bufferLength); +} +/*----------------------------------------------------------------------------------------*/ +static void ResultPrint(const bson_t *doc, void *userData) +{ + bson_iter_t iter; + unsigned int severity; + int length; + const char *message, *timeText, *sub; + char sevBuf[20]; + + bson_iter_init(&iter,doc); + bson_iter_find(&iter,"timetext"); + timeText = bson_iter_utf8(&iter,&length); + bson_iter_init(&iter,doc); + bson_iter_find(&iter,"severity"); + severity = bson_iter_int32(&iter); + formatSeverity(severity,sevBuf,sizeof(sevBuf)); + bson_iter_find(&iter,"sub"); + sub = bson_iter_utf8(&iter,&length); + bson_iter_find(&iter,"message"); + message = bson_iter_utf8(&iter,&length); + + fprintf(stdout,"%s %s %s %s\n",timeText,sevBuf, sub, message); + +} + +int main(int argc, char *argv[]) +{ + int status; + char *error; + + sicslogSetup("mongodb://logwriter:sinqsics@localhost:27017/?authSource=admin",NULL); + status = sicslogQuery(argc,argv,ResultPrint,NULL); + if(status != 0){ + error = sicslogGetError(); + fprintf(stdout,"%s\n", error); + } + return status; +} +