Commit b3aaafd9 authored by Samarth Joshi's avatar Samarth Joshi
parents 86df5826 8fa5cde1
...@@ -2,9 +2,9 @@ ...@@ -2,9 +2,9 @@
#converting whitespaces to new line in temp file #converting whitespaces to new line in temp file
sed -e 's/[\t ]\+/\n/g' -e 's/https/\nhttps/g' $1 >temp sed -e 's/[\t ]\+/\n/g' -e 's/https/\nhttps/g' $1 >temp
#saving all urls #saving all urls
sed -n '/https\:\/\/www\.cse\.iitb\.ac\.in[/][~][^ ]\+/p' temp >url sed -n '/http[s]\:\/\/www\.cse\.iitb\.ac\.in[/][~][a-z]\{5,15\}/p' temp >url
#removing all urls from inputfile
sed -i -e 's/http[s]\?\:\/\/[^ ]\+/ /g' -e 's/[^ ]\+[.]\(com\|in\|org\|net\|co\|us\|edu\|gov\)[^ ]\?/ /g' $1
sed -i -e 's/[\t ]\+/ /g' $1
rm temp rm temp
#trimming $1
\ No newline at end of file sed -i -e 's/'
sed -i -e 's/[\t ]\+/ /g' -e 's/[)]\{1\}/ )/g' -e 's/http[s]\?\:\/\/[^ ]\+/ /g' -e 's/[ ][^ ^@]\+[.]\{1\}\(com\|in\|org\|net\|co\|us\|edu\|gov\)\{1\}[/]\{0,1\}[^ ^@]\+[ ]\+/ /g' -e 's/[ ]\{1\}[)]\{1\}/)/g' $1
sed -i -e 's/[\t ]\+/ /g' $1
\ No newline at end of file
This diff is collapsed.
This diff is collapsed.
sed 's/\([^ ]\) /\1 \n /g' $1 | awk '/\s*[A-Za-z]+-[0-9]{3}-[0-9]{8}\s*$/' | awk 'NR==FNR{a[$1]=$2", "$3} NR!=FNR{print $1" "$2"-"$3" "a[$2]}' FS=" ?\t+" STD_Codes_list FS="-" - | awk '!/00000000/' -
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment