Perl: write custom date format to excel spreadsheet - perl

I would like to know how to update cell with custom date format using perl module Spreadsheet::ParseExcel. I am able to get wrong formatted and unformatted value to variable.
For example:
A1 is 11-9-15 23:00 (unformatted 42317.9583333333)
Needed format is 09.11.2015 23:00 (dd.mm.yyyy hh:mm)
$worksheet->AddCell(0, 0, 42317.9583333333, 'dd.mm.yyyy hh:mm');
I need something like command above but it doesn’t work. Cell is 42317.9583333333 not 09.11.2015 23:00.

# INPUT "2015-10-13 23:47" (dd.mm.yyyy hh:mm) -> OUTPUT "42290,9909722222" (excel epoch 1900)
sub dateStringToExcel {
my $date_excel;
my ($date_string) = #_;
if ( $date_string =~ /\d{4}-(0[1-9]|1[0-2])-(0[1-9]|[12]\d|30|31) ([012345][0-9])\:([012345][0-9])/ ) {
print "stringToexcelDate - OK\n";
my ($year, $month, $day, $hour, $min) = ($date_string =~ /(\d+)-(\d+)-(\d+) (\d+):(\d+)/);
$date_excel = LocaltimeExcel( 0, $min, $hour, $day, $month-1, $year-1900 );
} else {
print "stringToexcelDate - FAILED\n";
$date_excel = "Parsing date string ($date_string) failed!";
};
return $date_excel;
};

I did not know about the LocaltimeExcel! function so i did both conversion functions using plain perl.
sub date2excelvalue {
my($day1, $month, $year, $hour, $min, $sec) = #_;
my #cumul_d_in_m = (0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365);
my $doy = $cumul_d_in_m[$month - 1] + $day1;
#
full years + your day
for my $y(1900..$year) {
if ($y == $year) {
if ($month <= 2) {
#
dont add manually extra date
if inJanuary or February
last;
}
if ((($y % 4 == 0) && ($y % 100 != 0)) || ($y % 400 == 0) || ($y == 1900)) {
$doy++;#
leap year
}
} else {#
full years
$doy += 365;
if ((($y % 4 == 0) && ($y % 100 != 0)) || ($y % 400 == 0) || ($y == 1900)) {
$doy++;#
leap year
}
}
}#
end
for y# calculate second parts as a fraction of 86400 seconds
my $excel_decimaltimepart = 0;
my $total_seconds_from_time = ($hour * 60 * 60 + $min * 60 + $sec);
if ($total_seconds_from_time == 86400) {
$doy++;#
just add a day
} else {#
add decimal in excel
$excel_decimaltimepart = $total_seconds_from_time / (86400);
$excel_decimaltimepart = ~s / 0\. //;
}
return "$doy\.$excel_decimaltimepart";
}
sub excelvalue2date {
my($excelvalueintegerpart, $excelvaluedecimalpart) = #_;
my #cumul_d_in_m = (0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365);
my #cumul_d_in_m_leap = (0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366);
my #cumul_d_in_m_selected;
my($day1, $month, $year, $hour, $min, $sec);
$day1 = 0;#
all days all years
my $days_in_year;
my $acumdays_per_month;
my $daysinmonth;
my $day;
#
full years + your day
for my $y(1900. .3000) {
my $leap_year = 0;#
leap year
my $leap_year_mask = 0;#
leap year
if ((($y % 4 == 0) && ($y % 100 != 0)) || ($y % 400 == 0) || ($y == 1900)) {
$leap_year = 1;#
leap year
#cumul_d_in_m_selected = #cumul_d_in_m_leap;
} else {
$leap_year = 0;#
leap year
#cumul_d_in_m_selected = #cumul_d_in_m;
}
if (($day1 + (365 + $leap_year)) > $excelvalueintegerpart) {
#
found this year $y
$year = $y;
print "year $y\n";
$days_in_year = $excelvalueintegerpart - $day1;
$acumdays_per_month = 0;
print "excelvalueintegerpart $excelvalueintegerpart\n";
print "day1 $day1\n";
print "daysinyear $days_in_year\n";
for my $i(0..$# cumul_d_in_m) {
if ($i == $# cumul_d_in_m) {
$month = $i + 1;#
month 12 December
$day = $days_in_year - $cumul_d_in_m_selected[$i];
last;
} else {
if (($days_in_year > ($cumul_d_in_m_selected[$i])) && ($days_in_year <= ($cumul_d_in_m_selected[$i + 1]))) {
$month = $i + 1;
$day = $days_in_year - $cumul_d_in_m_selected[$i];
last;
}
}
}#
end
for $i months
# end year
last;
} else {#
full years
$day1 += (365 + $leap_year);
}
}#
end
for years interger part comparator
my $total_seconds_inaday;
$total_seconds_inaday = "0\.$excelvaluedecimalpart" * 86400;
$sec = $total_seconds_inaday;
$hour = int($sec / (60 * 60));
$sec -= $hour * (60 * 60);
$min = int($sec / 60);
$sec -= $min * (60);
$sec = int($sec);
return ($day, $month, $year, $hour, $min, $sec);
}
my $excelvariable = date2excelvalue(1, 3, 2018, 14, 14, 30);
print "Excel variable: $excelvariable\n";
my($integerpart, $decimalwithoutzero) = ($1, $2) if ($excelvariable = ~m / (\d + )\.(\d + ) / );
my($day1, $month, $year, $hour, $min, $sec) = excelvalue2date($integerpart, $decimalwithoutzero);
print "Excel Date from value: $day1, $month, $year, $hour, $min, $sec\n";
Enjoy it!

Related

Perl : Getting last Friday of the month

I am trying to get the last Friday of the month. I found out the awesome awk script that could to do this job. I try to port it perl but facing some issues. Any insight would be a great help. I can't use any perl modules apart from the inbuilt one, thats why I have to go through building this stuff.
Thanks for your help.
AWK script :
BEGIN {
split("31,28,31,30,31,30,31,31,30,31,30,31",daynum_array,",") # days per month in non leap year
year = ARGV[1]
if (year % 400 == 0 || (year % 4 == 0 && year % 100 != 0)) {
daynum_array[2] = 29
}
y = year - 1
k = 44 + y + int(y/4) + int(6*(y/100)) + int(y/400)
for (m=1; m<=12; m++) {
k += daynum_array[m]
d = daynum_array[m] - (k%7)
printf("%04d-%02d-%02d\n",year,m,d)
}
exit(0)
}
My Perl script :
my #time = localtime;
my ($month, $year) = #time[4, 5];
$year += 1900;
#months = qw( 31 28 31 30 31 30 31 31 30 31 30 31 );
$months[1] = check_leap_year($year) ? 29 : 28;
$y = $year - 1;
$k = 44 + $y + int($y / 4) + int(6 * ($y / 100)) + int($y / 400);
$k += $months[$month];
$d = $months[$month] - ($k % 7);
$month += 1;
printf "%04d-%02d-%02d\n", $year, $month, $d;
sub check_leap_year {
my $year = shift;
return 0 if $year % 4;
return 1 if $year % 100;
return 0 if $year % 400;
return 1;
}
There's a few ways to do this. Using Time::Piece isn't the simplest, it isn't designed for date math, but you don't have to install additional software.
use v5.10;
use strict;
use warnings;
use Time::Piece;
sub get_last_dow_in_month {
my($year, $month, $dow) = #_;
# Get a Time::Piece object at the last day of the month.
my $first_of_the_month = Time::Piece->strptime("$year $month", "%Y %m");
my $last_day = $first_of_the_month->month_last_day;
my $last_of_the_month = Time::Piece->strptime("$year $month $last_day", "%Y %m %d");
# Figure out how many days you need to go back.
my $days_offset = -(($last_of_the_month->day_of_week + (7 - $dow)) % 7);
return $last_of_the_month->mday + $days_offset;
}
say get_last_dow_in_month(2014, 3, 5);
If you need to do more date processing, DateTime is the most comprehensive.
Modules are made to be used. Calc last friday of month on PerlMonks contains some examples.
E.g.
$ perl -MDate::Manip -E 'say UnixDate(ParseDate("last Friday in March 2015"),"Last Friday of the month is %B %E, %Y.")
Last Friday of the month is March 27th, 2015.
Rather than working around the technical limitation, you need to work around the social limitation that is hampering the technical side of your job.
If you are constrained by using core modules only, this is the way to compute it:
use strict;
use warnings;
use Time::Local qw[];
# Computes the last day in the given month which occurs on the given
# day of the week. Returns the day of the month [22, 31].
# 1 <= $month <= 12
# 0 <= $dow <= 6 (0=Sunday)
sub last_dow_in_month {
my ($year, $month, $dow) = #_;
$year += int($month / 12);
$month %= 12;
my $time = Time::Local::timegm(0, 0, 0, 1, $month, $year) - 86400;
my ($mday, $wday) = (gmtime($time))[3,6];
return $mday - ($wday - $dow) % 7;
}
my $year = 2015;
foreach my $month (1..12) {
printf "%.4d-%.2d-%.2d\n",
$year, $month, last_dow_in_month($year, $month, 5);
}
Output:
2015-01-30
2015-02-27
2015-03-27
2015-04-24
2015-05-29
2015-06-26
2015-07-31
2015-08-28
2015-09-25
2015-10-30
2015-11-27
2015-12-25
Using DateTime the code becomes more readable:
use DateTime;
# Computes the last day in the given month which occurs on the given
# day of the week. Returns the day of the month [22, 31].
# 1 <= $month <= 12
# 1 <= $dow <= 7 (1=Monday)
sub last_dow_in_month {
my ($year, $month, $dow) = #_;
my $dt = DateTime->last_day_of_month(year => $year, month => $month);
$dt->subtract(days => ($dt->day_of_week - $dow) % 7);
return $dt->day_of_month;
}
If performance is of essence, Time::Moment can be used to compute it:
use Time::Moment qw[];
# Computes the last day in the given month which occurs on the given
# day of the week. Returns the day of the month [22, 31].
# 1 <= $month <= 12
# 1 <= $dow <= 7 (1=Monday)
sub last_dow_in_month {
my ($year, $month, $dow) = #_;
my $tm = Time::Moment->new(year => $year, month => $month)
->plus_months(1)
->minus_days(1);
return $tm->minus_days(($tm->day_of_week - $dow) % 7)
->day_of_month;
}
A correct implementation of your intended algorithm:
# Computes the last friday in the given month. Returns the day of the
# month [22, 31].
# 1 <= $month <= 12
sub last_friday_in_month {
my ($year, $month) = #_;
my $days = (
[0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365],
[0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366],
)[($year % 4) == 0 && ($year % 100 != 0 || $year % 400 == 0)];
my $y = $year - 1;
my $k = 44 + $y + int($y/4) + int(6 * ($y/100)) + int($y/400);
$k += $days->[$month];
return $days->[$month] - $days->[$month - 1] - ($k % 7);
}
This is just for variety. As #Schwern notes, "cal is a clever hack, but it's a crutch that lets the OP avoid learning to use a good date library. Calendaring is hard, use a library."
Assuming you have cal on your system
#!/usr/bin/env perl
use strict;
use warnings;
local $ENV{LC_ALL} = 'C';
my #cal = `cal`;
my $last_friday;
for (my $i = $#cal; $i >= 0; $i -= 1) {
my #dates = split ' ', $cal[$i];
next unless #dates > 5;
$last_friday = $dates[5];
last;
}
print "$last_friday\n";
Or, more succinctly, but somewhat less efficiently:
#!/usr/bin/env perl
use strict;
use warnings;
local $ENV{LC_ALL} = 'C';
my ($last_friday) = grep defined, map +(split)[5], reverse `cal`;
print "$last_friday\n";
Or, even,
#!/usr/bin/env perl
use strict;
use warnings;
use List::Util qw( first );
local $ENV{LC_ALL} = 'C';
my $last_friday = first { defined } map +(split)[5], reverse `cal`;
print "$last_friday\n";

Convert serial value to date in perl

I am using Spreadsheet::XLSX to convert XLSX into CSV on Linux.
Custom date fields are being converted to numbers. I know that XLSX stores custom dates as serial values. I need to find the way to convert those values into dates/times.
Example:
CSV: 40829
XLSX: 10/13/2011 0:00
So I am trying to figure out how to convert 40829 to 10/13/2011 0:00
I did some research and I was not able to find any (Perl) solution.
I can provide the code if needed.
Please advise.
Thank you,
-Andrey
Excel stores dates and times as a number representing the number of days since 1900-Jan-0, plus a fractional portion of a 24 hour day: ddddd.tttttt.
You could write a function to do the calculations yourself or you could look at some of the modules already posted on cpan for doing this, DateTime::Format::Excel should do what you need and DateTimeX::Format::Excel looks like it would work too.
As per the previous post, this seems like it's the number of days since Jan 1st 1900. By making the 40828'th of January, 1900 (accounting for the off-by-one of being the 1st of January, not the 0th), we get:
use POSIX 'mktime'
my $epoch = mktime 0,0,0, 40829-1,0,0;
print scalar localtime($epoch);
Gives
Thu Oct 13 00:00:00 2011
Or you can use your own functions to convert the dates in EXCEL datevalue and back
sub date2excelvalue {
my($day1, $month, $year, $hour, $min, $sec) = #_;
my #cumul_d_in_m = (0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365);
my $doy = $cumul_d_in_m[$month - 1] + $day1;
#
full years + your day
for my $y(1900..$year) {
if ($y == $year) {
if ($month <= 2) {
#
dont add manually extra date
if inJanuary or February
last;
}
if ((($y % 4 == 0) && ($y % 100 != 0)) || ($y % 400 == 0) || ($y == 1900)) {
$doy++;#
leap year
}
} else {#
full years
$doy += 365;
if ((($y % 4 == 0) && ($y % 100 != 0)) || ($y % 400 == 0) || ($y == 1900)) {
$doy++;#
leap year
}
}
}#
end
for y# calculate second parts as a fraction of 86400 seconds
my $excel_decimaltimepart = 0;
my $total_seconds_from_time = ($hour * 60 * 60 + $min * 60 + $sec);
if ($total_seconds_from_time == 86400) {
$doy++;#
just add a day
} else {#
add decimal in excel
$excel_decimaltimepart = $total_seconds_from_time / (86400);
$excel_decimaltimepart = ~s / 0\. //;
}
return "$doy\.$excel_decimaltimepart";
}
sub excelvalue2date {
my($excelvalueintegerpart, $excelvaluedecimalpart) = #_;
my #cumul_d_in_m = (0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365);
my #cumul_d_in_m_leap = (0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366);
my #cumul_d_in_m_selected;
my($day1, $month, $year, $hour, $min, $sec);
$day1 = 0;#
all days all years
my $days_in_year;
my $acumdays_per_month;
my $daysinmonth;
my $day;
#
full years + your day
for my $y(1900. .3000) {
my $leap_year = 0;#
leap year
my $leap_year_mask = 0;#
leap year
if ((($y % 4 == 0) && ($y % 100 != 0)) || ($y % 400 == 0) || ($y == 1900)) {
$leap_year = 1;#
leap year
#cumul_d_in_m_selected = #cumul_d_in_m_leap;
} else {
$leap_year = 0;#
leap year
#cumul_d_in_m_selected = #cumul_d_in_m;
}
if (($day1 + (365 + $leap_year)) > $excelvalueintegerpart) {
#
found this year $y
$year = $y;
print "year $y\n";
$days_in_year = $excelvalueintegerpart - $day1;
$acumdays_per_month = 0;
print "excelvalueintegerpart $excelvalueintegerpart\n";
print "day1 $day1\n";
print "daysinyear $days_in_year\n";
for my $i(0..$# cumul_d_in_m) {
if ($i == $# cumul_d_in_m) {
$month = $i + 1;#
month 12 December
$day = $days_in_year - $cumul_d_in_m_selected[$i];
last;
} else {
if (($days_in_year > ($cumul_d_in_m_selected[$i])) && ($days_in_year <= ($cumul_d_in_m_selected[$i + 1]))) {
$month = $i + 1;
$day = $days_in_year - $cumul_d_in_m_selected[$i];
last;
}
}
}#
end
for $i months
# end year
last;
} else {#
full years
$day1 += (365 + $leap_year);
}
}#
end
for years interger part comparator
my $total_seconds_inaday;
$total_seconds_inaday = "0\.$excelvaluedecimalpart" * 86400;
$sec = $total_seconds_inaday;
$hour = int($sec / (60 * 60));
$sec -= $hour * (60 * 60);
$min = int($sec / 60);
$sec -= $min * (60);
$sec = int($sec);
return ($day, $month, $year, $hour, $min, $sec);
}
my $excelvariable = date2excelvalue(1, 3, 2018, 14, 14, 30);
print "Excel variable: $excelvariable\n";
my($integerpart, $decimalwithoutzero) = ($1, $2) if ($excelvariable = ~m / (\d + )\.(\d + ) / );
my($day1, $month, $year, $hour, $min, $sec) = excelvalue2date($integerpart, $decimalwithoutzero);
print "Excel Date from value: $day1, $month, $year, $hour, $min, $sec\n";
Enjoy it!

Perl substr error

I have problem with Perl substr function. It is so simple, but anyway... Don't know what is the problem.
sub encode_date
{
$date = $_[0];
$day = substr($date, 0, 2);
$month = substr($date, 2, 2);
$year = substr($date, 6, 4);
return "$year-$month-$day";
}
Sub accept "DD.MM.YYYY" formatted string and have to convert it to "YYYY-MM-DD" format.
Input : 09.09.1993
Output : 0-09-93-19 ???
Can anybody explain what's wrong, please.
p.s.: I wrote another sub for decoding date (from 'yyyy-mm-dd' to 'dd.mm.yyyy') and all work properly.
sub decode_date
{
$date = $_[0];
$year = substr $date, 0, 4;
$month = substr $date, 5, 2;
$day = substr $date, 8, 2;
return $day.".".$month.".".$year;
}
Sure, I tried both substr $date, 0, 2; and substr($date, 0, 2); and different combinations of the return value.
Month starts at index 3, not 2.
sub encode_date
{
my ($date) = #_;
my $day = substr($date, 0, 2);
my $month = substr($date, 3, 2);
my $year = substr($date, 6, 4);
return "$year-$month-$day";
}
Perhaps better way would be splitting string by non-digit(.), reverse numbers, and join them with dash -
sub encode_date
{
my ($date) = #_;
return join "-", reverse split /\D/, $date;
}
Your problem is that your offsets are wrong, because they don't take into account the separators. (For example, the month starts at offset 3, not 2, because it comes after the two-character date plus a period.)
That said, I think the best way to write this function is:
sub encode_date($) {
if ($_[0] =~ /^(\d\d)\.(\d\d)\.(\d{4})$/) {
return "$3-$2-$1";
}
}
sub encode_date
{
$date = $_[0];
$day = substr($date, 0, 2);
$month = substr($date, 3, 2);
$year = substr($date, 6, 4);
return "$year-$month-$day";
}
There were 2 problems. I used encode_date(encode_date($date)); (2 times)Another was $month = substr($date, 2, 2); Correct is $month = substr($date, 3, 2);

Need to convert data as string into an Excel readable format

I have a file with data that includes date strings in this format:
June 11, 2012 3:47:56 PM GMT-07:00
I'm already using a Perl script to manipulate some other data elements from that file then outputting it as a csv for Excel. Rather than fooling about with functions and formulas in Excel to try to translate the date-as-string into something Excel can read, I figure I should be able to do it easier/quicker in Perl.
The purpose / desired end result is a time & date stamp that I can do simple math on in Excel (i.e, get age difference between entries by mathing the time stamps).
To that end, I want to end up with my datestamps looking like this:
6/11/2012 3:47:56 PM
Really I just need to convert the date, the time is perfect, and remove the GMT differential garbage.
I've seen code snippets and references to modules that seem to convert the other way ... i.e., from "6/24/12" to "June 24, 2012", but that's going the wrong direction for me.
I looked up module time::piece in cpan, but don't really understand it. I'm working in a Cygwin exec, so not a real unix system, and don't have much in the way of man pages or perldocs.
You can use module Date::Parse and POSIX functions strftime. There are plenty modules in CPAN, which can parse dates.
Formatting dates with strftime really cool article
use strict;
use Date::Parse;
use POSIX qw/strftime/;
my $time = str2time( 'June 11, 2012 3:47:56 PM GMT-07:00' );
my $date = strftime "%m/%d/%Y %H:%M:%S %p", localtime($time);
print $date;
Good luck!
If you original string is: $timestring, then this should work (not tested):
my %months = (January => '1', February =>'2', March => '3', ...);
...
etc.
$timestring =~ s<^(w+)\x20(\d{1,2}),\x20(\d{4})(\x20\(?:\d{1,2}\:){2}\d{1,2}\x20PM).*$><"$months{$1}/$2/$3$4">eeg
use DateTime;
use DateTime::Format::Strptime;
# YOU MUST ADAPT THIS PATTERN
my $pat = "%b %d, %Y"; #incomplete
my $d = DateTime::Format::Strptime->new( pattern => $pat, on_error => 'croak' );
my $dt = $d->parse_datetime($strdate);
say $dt->mdy("/") . " " . $dt->hms(":") . " " . $dt->am_or_pm;
But note that Excel prefers Datetime types in ISO Format:
say $dt->ymd('-') . 'T' . $dt->hms(':');
For finetuning the pattern $pat, read the module documentation for DateTime::Format::Strptime.
It works best for parsing input data that is very uniform. Encounter the slightest deviation and the module won't parse it (you can work around this, though)
Many people have their favorite time parsing techniques. I like Time::Piece because it comes with Perl (at least any version over 5.10):
my $time_string = "June 11, 2012 3:47:56 PM GMT-7:00";
my $time_string =~ / GMT.*$//; # That "GMT-7:00" messes things up!
say $time_string # June 11, 2012 3:47:56 PM GMT
my $time = Time::Piece->strptime(
$time_string, "%B %d, %Y %l:%M:%S %p" );
say $time->strftime("%D %l:%M:%S %p");
The $foo->bar is object oriented coding style which is becoming the way of the future in Perl, so you better get use to it.
It's not really all that complex. Basically, you create an container that holds all your data. Sort of the way a hash can hold various pieces of information.
When I do this:
my $time = Time::Piece->strptime( "$time_string", "$time_format" );
I'm creating a Time::Piece object (nee container) called $time which stores the time.
When you say $time->Weekday, you are actually executing a subroutine called Weekday that takes your $time container, extracts the information from it, parses the time, and return the weekday.
The strptime (STRing Parse TIME) constructor (which is the function that creates your container) is taking your time string (the first argument), and the format it is in (the second argument) and creating that $time object. The various %M and %d specify particular time fields. These can be found in the strptime manpage.
You can play around with these formats with the Unix date command:
$ date "+%m/%d/%y"
08/23/13
$ date "+%m/%d/%Y"
08/23/2013
$ date "%Y-%m-%d"
2013-08-23
That might make you feel more comfortable with them.
The strftime (STRing Format TIME) method (nee subroutine) is the opposite of strptime. This takes the time (which is in $time and returns the time in the format you specified.
If you have problems installing new extra packages you can do that using plain per. Once you have the excel date serial value e.g 61,59340278 you can use Excel to format the appearance of that number in a custom date.
For example:
61,59340278 is displayed in Excel using custom date format
CUSTOM Cell format: TT.MM.JJJJ hh:mm:ss
as> 01.03.1900 14:14:30
Below the functions
sub date2excelvalue {
my($day1, $month, $year, $hour, $min, $sec) = #_;
my #cumul_d_in_m = (0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365);
my $doy = $cumul_d_in_m[$month - 1] + $day1;
#
full years + your day
for my $y(1900..$year) {
if ($y == $year) {
if ($month <= 2) {
#
dont add manually extra date
if inJanuary or February
last;
}
if ((($y % 4 == 0) && ($y % 100 != 0)) || ($y % 400 == 0) || ($y == 1900)) {
$doy++;#
leap year
}
} else {#
full years
$doy += 365;
if ((($y % 4 == 0) && ($y % 100 != 0)) || ($y % 400 == 0) || ($y == 1900)) {
$doy++;#
leap year
}
}
}#
end
for y# calculate second parts as a fraction of 86400 seconds
my $excel_decimaltimepart = 0;
my $total_seconds_from_time = ($hour * 60 * 60 + $min * 60 + $sec);
if ($total_seconds_from_time == 86400) {
$doy++;#
just add a day
} else {#
add decimal in excel
$excel_decimaltimepart = $total_seconds_from_time / (86400);
$excel_decimaltimepart = ~s / 0\. //;
}
return "$doy\.$excel_decimaltimepart";
}
sub excelvalue2date {
my($excelvalueintegerpart, $excelvaluedecimalpart) = #_;
my #cumul_d_in_m = (0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365);
my #cumul_d_in_m_leap = (0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366);
my #cumul_d_in_m_selected;
my($day1, $month, $year, $hour, $min, $sec);
$day1 = 0;#
all days all years
my $days_in_year;
my $acumdays_per_month;
my $daysinmonth;
my $day;
#
full years + your day
for my $y(1900. .3000) {
my $leap_year = 0;#
leap year
my $leap_year_mask = 0;#
leap year
if ((($y % 4 == 0) && ($y % 100 != 0)) || ($y % 400 == 0) || ($y == 1900)) {
$leap_year = 1;#
leap year
#cumul_d_in_m_selected = #cumul_d_in_m_leap;
} else {
$leap_year = 0;#
leap year
#cumul_d_in_m_selected = #cumul_d_in_m;
}
if (($day1 + (365 + $leap_year)) > $excelvalueintegerpart) {
#
found this year $y
$year = $y;
print "year $y\n";
$days_in_year = $excelvalueintegerpart - $day1;
$acumdays_per_month = 0;
print "excelvalueintegerpart $excelvalueintegerpart\n";
print "day1 $day1\n";
print "daysinyear $days_in_year\n";
for my $i(0..$# cumul_d_in_m) {
if ($i == $# cumul_d_in_m) {
$month = $i + 1;#
month 12 December
$day = $days_in_year - $cumul_d_in_m_selected[$i];
last;
} else {
if (($days_in_year > ($cumul_d_in_m_selected[$i])) && ($days_in_year <= ($cumul_d_in_m_selected[$i + 1]))) {
$month = $i + 1;
$day = $days_in_year - $cumul_d_in_m_selected[$i];
last;
}
}
}#
end
for $i months
# end year
last;
} else {#
full years
$day1 += (365 + $leap_year);
}
}#
end
for years interger part comparator
my $total_seconds_inaday;
$total_seconds_inaday = "0\.$excelvaluedecimalpart" * 86400;
$sec = $total_seconds_inaday;
$hour = int($sec / (60 * 60));
$sec -= $hour * (60 * 60);
$min = int($sec / 60);
$sec -= $min * (60);
$sec = int($sec);
return ($day, $month, $year, $hour, $min, $sec);
}
my $excelvariable = date2excelvalue(1, 3, 2018, 14, 14, 30);
print "Excel variable: $excelvariable\n";
my($integerpart, $decimalwithoutzero) = ($1, $2) if ($excelvariable = ~m / (\d + )\.(\d + ) / );
my($day1, $month, $year, $hour, $min, $sec) = excelvalue2date($integerpart, $decimalwithoutzero);
print "Excel Date from value: $day1, $month, $year, $hour, $min, $sec\n";
Enjoy it!

How can I sum data over five minute time intervals in Perl?

I have a file in below format.
DATE Time, v1,v2,v3
05:33:25,n1,n2,n3
05:34:25,n4,n5,n5
05:35:24,n6,n7,n8
and so on upto 05:42:25.
I want calculate the values v1, v2 and v3 for every 5 min interval. I have written the below sample code.
while (<STDIN>) {
my ($dateTime, $v1, $v2, $v3) = split /,/, $_;
my ($date, $time) = split / /, $dateTime;
}
I can read all the values but need help to sum all the values for every 5 min interval. Can anyone please suggest me the code to add the time and values for every 5 min.
Required output
05:33 v1(sum 05:33 to 05:37) v2(sum 05:33 to 05:33) v3(sum 05:33 to 05:33)
05:38 v1(sum 05:38 to 05:42) v2(sum 05:38 to 05:42) v3(sum 05:38 to 05:42)
and so on..
The code is a variation the previous answer by Sinan Ünür below, except:
(1) Function timelocal will allow you to read in Day,Month,Year -- so you can sum any five minute gap.
(2) Should deal with case where final time gap is < 5 minutes.
#!/usr/bin/perl -w
use strict;
use warnings;
use Time::Local;
use POSIX qw(strftime);
my ( $start_time, $end_time, $current_time );
my ( $totV1, $totV2, $totV3 ); #totals in time bands
while (<DATA>) {
my ( $hour, $min, $sec, $v1, $v2, $v3 ) =
( $_ =~ /(\d+)\:(\d+)\:(\d+)\,(\d+),(\d+),(\d+)/ );
#convert time to epoch seconds
$current_time =
timelocal( $sec, $min, $hour, (localtime)[ 3, 4, 5 ] ); #sec,min,hr
if ( !$end_time ) {
$start_time = $current_time;
$end_time = $start_time + 5 * 60; #plus 5 min
}
if ( $current_time <= $end_time ) {
$totV1 += $v1;
$totV2 += $v2;
$totV3 += $v3;
}
else {
print strftime( "%H:%M:%S", localtime($start_time) ),
" $totV1,$totV2,$totV3\n";
$start_time = $current_time;
$end_time = $start_time + 5 * 60; #plus 5 min
( $totV1, $totV2, $totV3 ) = ( $v1, $v2, $v3 );
}
}
#Print results of final loop (if required)
if ( $current_time <= $end_time ) {
print strftime( "%H:%M:%S", localtime($start_time) ),
" $totV1,$totV2,$totV3\n";
}
__DATA__
05:33:25,29,74,96
05:34:25,41,69,95
05:35:25,24,38,55
05:36:25,96,63,70
05:37:25,84,65,74
05:38:25,78,58,93
05:39:25,51,38,19
05:40:25,86,40,64
05:41:25,80,68,65
05:42:25,4,93,81
Output:
05:33:25 352,367,483
05:39:25 221,239,229
Obviously, not tested much, for lack of sample data. For parsing the CSV, use either Text::CSV_XS or Text::xSV rather than the naive split below.
Note:
This code does not make sure the output has all consecutive five minute blocks if the input data has gaps.
You will have problems if there are time stamps from multiple days. In fact, if the time stamps are not in 24-hour format, you will have problems even if the data are from a single day.
With those caveats, it should still give you a starting point.
#!/usr/bin/perl
use strict;
use warnings;
my $split_re = qr/ ?, ?/;
my #header = split $split_re, scalar <DATA>;
my #data;
my $time_block = 0;
while ( my $data = <DATA> ) {
last unless $data =~ /\S/;
chomp $data;
my ($ts, #vals) = split $split_re, $data;
my ($hr, $min, $sec) = split /:/, $ts;
my $secs = 3600*$hr + 60*$min + $sec;
if ( $secs > $time_block + 300 ) {
$time_block = $secs;
push #data, [ $time_block ];
}
for my $i (1 .. #vals) {
$data[-1]->[$i] += $vals[$i - 1];
}
}
print join(', ', #header);
for my $row ( #data ) {
my $ts = shift #$row;
print join(', ',
sprintf('%02d:%02d', (localtime($ts))[2,1])
, #$row
), "\n";
}
__DATA__
DATE Time, v1,v2,v3
05:33:25,1,3,5
05:34:25,2,4,6
05:35:24,7,8,9
05:55:24,7,8,9
05:57:24,7,8,9
Output:
DATE Time, v1, v2, v3
05:33, 10, 15, 20
05:55, 14, 16, 18
This is a good problem for Perl to solve. The hardest part is taking the value from the datetime field and identifying which 5 minute bucket it belongs to. The rest is just hashes.
my (%v1,%v2,%v3);
while (<STDIN>) {
my ($datetime,$v1,$v2,$v3) = split /,/, $_;
my ($date,$time) = split / /, $datetime;
my $bucket = &get_bucket_for($time);
$v1{$bucket} += $v1;
$v2{$bucket} += $v2;
$v3{$bucket} += $v3;
}
foreach my $bucket (sort keys %v1) {
print "$bucket $v1{$bucket} $v2{$bucket} $v3{$bucket}\n";
}
Here's one way you could implement &get_bucket_for:
my $first_hhmm;
sub get_bucket_for {
my ($time) = #_;
my ($hh,$mm) = split /:/, $time; # looks like seconds are not important
# buckets are five minutes apart, but not necessarily at multiples of 5 min
# (i.e., buckets could go 05:33,05:38,... instead of 05:30,05:35,...)
# Use the value from the first time this function is called to decide
# what the starting point of the buckets is.
if (!defined $first_hhmm) {
$first_hhmm = $hh * 60 + $mm;
}
my $bucket_index = int(($hh * 60 + $mm - $first_hhmm) / 5);
my $bucket_start = $first_hhmm + 5 * $bucket_index;
return sprintf "%02d:%02d", $bucket_start / 60, $bucket_start % 60;
}
I'm not sure why you would use the times starting from the first time, instead of round 5 minute intervals (00 - 05, 05 - 10, etc), but this is a quick and dirty way to do it your way:
my %output;
my $last_min = -10; # -10 + 5 is less than any positive int.
while (<STDIN>) {
my ($dt, $v1, $v2, $v3) = split(/,/, $_);
my ($h, $m, $s) = split(/:/, $dt);
my $ts = $m + ($h * 60);
if (($last_min + 5) < $ts) {
$last_min = $ts;
}
$output{$last_min}{1} += $v1;
$output{$last_min}{2} += $v2;
$output{$last_min}{3} += $v3;
}
foreach my $ts (sort {$a <=> $b} keys %output) {
my $hour = int($ts / 60);
my $minute = $ts % 60;
printf("%01d:%02d v1(%i) v2(%i) v3(%i)\n", (
$hour,
$minute,
$output{$ts}{1},
$output{$ts}{2},
$output{$ts}{3},
));
}
Not sure why you would do it this way, but there you go in procedural Perl, as example. If you need more on the printf formatting, go here.