|
|
researchv10 Dan Cross
sed -e 's/<tab>/:/' -e 's/^ //' $1.idx|sort|uniq|awk '
BEGIN {FS=":"}
{ if($1 != laststr){
if(start){
if(range)pages = pages "-" npage
if(global != "")print laststr "," pages " " global
else print laststr "," pages
}
start=1
laststr=$1
global=$3
pages = " " $2
npage = 0 + $2
range=0
}
else {
if($2 == npage+1){
range=1
npage++
next
}
else if(range) pages = pages "-" npage "," $2
else pages = pages "," $2
npage = 0 + $2
range = 0
}
}
END {
if(range)pages = pages "-" npage
if(global != "")print laststr "," pages " " global
else print laststr "," pages
}
' >$1.index
This archive runs on limited infrastructure. Preserving old code on modern bandwidth. Automated agents are requested to crawl responsibly.