Extract historic leap seconds from tzdata

Question

Is there a way to extract the moment of historic leap seconds from the time-zone database that is distributed on most linux distributions? I am looking for a solution in pyt

Answer 1

PyEphem has a delta_t function which returns the difference between Terrestrial Time and Universal Time (seconds). You can subtract 32.184 from it to get Leap Seconds (ref).

import ephem, datetime
ephem.delta_t(datetime.datetime.now()) - 32.184
Out[2]: 35.01972996360122

Answer 2

I just did man 5 tzfile and computed an offset that would find the leap seconds info, then read the leap seconds info.

You can uncomment the "DEBUG:" print statements to see more of what it finds in the file.

EDIT: program updated to now be correct. It now uses the file /usr/share/zoneinfo/right/UTC and it now finds leap-seconds to print.

The original program wasn't skipping the timezeone abbreviation characters, which are documented in the man page but sort of hidden ("...and tt_abbrind serves as an index into the array of timezone abbreviation characters that follow the ttinfo structure(s) in the file.").

import datetime
import struct

TZFILE_MAGIC = 'TZif'.encode('US-ASCII')

def leap_seconds(f):
    """
    Return a list of tuples of this format: (timestamp, number_of_seconds)
        timestamp: a 32-bit timestamp, seconds since the UNIX epoch
        number_of_seconds: how many leap-seconds occur at timestamp

    """
    fmt = ">4s c 15x 6l"
    size = struct.calcsize(fmt)
    (tzfile_magic, tzfile_format, ttisgmtcnt, ttisstdcnt, leapcnt, timecnt,
        typecnt, charcnt) =  struct.unpack(fmt, f.read(size))
    #print("DEBUG: tzfile_magic: {} tzfile_format: {} ttisgmtcnt: {} ttisstdcnt: {} leapcnt: {} timecnt: {} typecnt: {} charcnt: {}".format(tzfile_magic, tzfile_format, ttisgmtcnt, ttisstdcnt, leapcnt, timecnt, typecnt, charcnt))

    # Make sure it is a tzfile(5) file
    assert tzfile_magic == TZFILE_MAGIC, (
            "Not a tzfile; file magic was: '{}'".format(tzfile_magic))

    # comments below show struct codes such as "l" for 32-bit long integer
    offset = (timecnt*4  # transition times, each "l"
        + timecnt*1  # indices tying transition time to ttinfo values, each "B"
        + typecnt*6  # ttinfo structs, each stored as "lBB"
        + charcnt*1)  # timezone abbreviation chars, each "c"

    f.seek(offset, 1) # seek offset bytes from current position

    fmt = '>{}l'.format(leapcnt*2)
    #print("DEBUG: leapcnt: {}  fmt: '{}'".format(leapcnt, fmt))
    size = struct.calcsize(fmt)
    data = struct.unpack(fmt, f.read(size))

    lst = [(data[i], data[i+1]) for i in range(0, len(data), 2)]
    assert all(lst[i][0] < lst[i+1][0] for i in range(len(lst)-1))
    assert all(lst[i][1] == lst[i+1][1]-1 for i in range(len(lst)-1))

    return lst

def print_leaps(leap_lst):
    # leap_lst is tuples: (timestamp, num_leap_seconds)
    for ts, num_secs in leap_lst:
        print(datetime.datetime.utcfromtimestamp(ts - num_secs+1))

if __name__ == '__main__':
    import os
    zoneinfo_fname = '/usr/share/zoneinfo/right/UTC'
    with open(zoneinfo_fname, 'rb') as f:
        leap_lst = leap_seconds(f)
    print_leaps(leap_lst)