csv2delim.awk
# csv2delim.awk converts comma delimited files with optional quotes to delim separated file
# delim can be any character, defaults to tab
# assumes no repl characters in text, any delim in line converts to repl
# repl can be any character, defaults to ~
# changes two consecutive quotes within quotes to '
# usage: gawk -f csv2delim.awk [-v delim=d] [-v repl=`"] input-file > output-file
# -v delim delimiter, defaults to tab
# -v repl replacement char, defaults to ~
# e.g. gawk -v delim=; -v repl=` -f csv2delim.awk test.csv > test.txt
# abe 2-28-7
# abe 8-8-8 1.0 fixed empty fields, added replacement option
# abe 8-27-8 1.1 used split
# abe 8-27-8 1.2 inline rpl and "" = '
# abe 8-27-8 1.3 revert to 1.0 as it is much faster, split most of the time
# abe 8-29-8 1.4 better message if delim present
BEGIN {
if (delim == "") delim = "\t"
if (repl == "") repl = "~"
print "csv2delim.awk v.m 1.4 run at " strftime() > "/dev/stderr" ###########################################
}
{
#if ($0 ~ repl) {
# print "Replacement character " repl " is on line " FNR ":" lineIn ";" > "/dev/stderr"
#}
if ($0 ~ delim) {
print "Temp delimiter character " delim " is on line " FNR ":" lineIn ";" > "/dev/stderr"
print " replaced by " repl > "/dev/stderr"
}
gsub(delim, repl)
$0 = gensub(/([^,])\"\"/, "\\1'", "g")
# $0 = gensub(/\"\"([^,])/, "'\\1", "g") # not needed above covers all cases
out = ""
#for (i = 1; i <= length($0); i++)
n = length($0)
for (i = 1; i <= n; i++)
if ((ch = substr($0, i, 1)) == "\"")
inString = (inString) ? 0 : 1 # toggle inString
else
out = out ((ch == "," && ! inString) ? delim : ch)
print out
}
END {
print NR " records processed from " FILENAME " at " strftime() > "/dev/stderr"
}
test.csv
"first","second","third"
"fir,st","second","third"
"first","sec""ond","third"
" first ",sec ond,"third"
"first" , "second","th ird"
"first","sec;ond","third"
"first","second","th;ird"
1,2,3
,2,3
1,2,
,2,
1,,2
1,"2",3
"1",2,"3"
"1",,"3"
1,"",3
"","",""
"","""aiyn","oh"""
"""","""",""""
11,2~2,3
test.bat
rem test csv2delim
rem default is: -v delim={tab} -v repl=~
gawk -f csv2delim.awk test.csv > test.txt
gawk -v delim=; -f csv2delim.awk test.csv > testd.txt
gawk -v delim=; -v repl=` -f csv2delim.awk test.csv > testdr.txt
gawk -v repl=` -f csv2delim.awk test.csv > testr.txt