139 lines
3.0 KiB
Awk
Executable File
139 lines
3.0 KiB
Awk
Executable File
#!/usr/bin/awk -f
|
|
#
|
|
# Performs interpolation for columns in a CSV and outputs the result
|
|
#
|
|
# Copyright (C) 2014-2020 Ryan Specialty Group, LLC.
|
|
#
|
|
# This program is free software: you can redistribute it and/or modify
|
|
# it under the terms of the GNU General Public License as published by
|
|
# the Free Software Foundation, either version 3 of the License, or
|
|
# (at your option) any later version.
|
|
#
|
|
# This program is distributed in the hope that it will be useful,
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
# GNU General Public License for more details.
|
|
#
|
|
# You should have received a copy of the GNU General Public License
|
|
# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
#
|
|
# Configurable values (use -vname=value from command line):
|
|
# step - use predeterminated step instead of calculating from first two rows
|
|
##
|
|
|
|
function storeline()
|
|
{
|
|
for ( i = 1; i <= hlen; i++ ) {
|
|
prev[i] = $i
|
|
}
|
|
}
|
|
|
|
function clearline()
|
|
{
|
|
for ( i = 1; i <= hlen; i++ ) {
|
|
prev[i] = 0
|
|
}
|
|
}
|
|
|
|
function getprev()
|
|
{
|
|
for ( i = 1; i <= hlen; i++ ) {
|
|
$i = prev[i]
|
|
}
|
|
}
|
|
|
|
|
|
function interpolate()
|
|
{
|
|
lastval = prev[1]
|
|
|
|
curval = $1
|
|
diff = curval - lastval
|
|
|
|
# does this value fall in line with the requested step?
|
|
if ( diff == step )
|
|
{
|
|
storeline()
|
|
|
|
# we're good; continue
|
|
print
|
|
next
|
|
}
|
|
|
|
# if we do not yet have a value large enough to reach our step, then continue
|
|
# until we do (do not store this line)
|
|
n = int( diff / step )
|
|
if ( n <= 0 ) {
|
|
next
|
|
}
|
|
|
|
# determine interpolation values
|
|
for ( i = 2; i <= hlen; i++ ) {
|
|
ival[i] = ( ( $i - prev[i] ) / n )
|
|
}
|
|
|
|
getprev()
|
|
|
|
# let us interpolate values that are divisible by the step
|
|
do
|
|
{
|
|
# increase the last value by our step
|
|
$1 += step
|
|
|
|
# interpolate each column value (notice that we skip the first column, which
|
|
# was handled directly above)
|
|
for ( i = 2; i <= hlen; i++ ) {
|
|
$i += ival[i]
|
|
}
|
|
|
|
# print the new line
|
|
print
|
|
} while ( ( diff -= step ) > 0 )
|
|
|
|
# anything remaining does not fit into our step and will be ignored; we'll
|
|
# continue with our next step at the next line
|
|
|
|
# consider this to be our last line
|
|
storeline()
|
|
}
|
|
|
|
|
|
BEGIN {
|
|
# the first row of the CSV is the header representing the column identifiers
|
|
getline
|
|
hlen = split( $0, header, /,/ )
|
|
|
|
# output the header
|
|
print $0
|
|
|
|
# delimit fields by commas (the field separator for CSVs); note that this
|
|
# won't work properly if strings contain commas
|
|
FS = OFS = ","
|
|
|
|
clearline()
|
|
getline
|
|
|
|
# if no step was provided, then calculate one based on the first two rows
|
|
if ( step == 0 ) {
|
|
# output the first row, which does not need to be interpolated
|
|
print
|
|
|
|
# compute the step
|
|
vala = $1
|
|
getline
|
|
valb = $1
|
|
step = valb - vala
|
|
|
|
# since the second line is used to determine the step, then it must match the
|
|
# step and therefore is good to output
|
|
print
|
|
|
|
# begin.
|
|
storeline()
|
|
}
|
|
}
|
|
|
|
|
|
# for each row
|
|
{ interpolate() }
|