awk

Print specific columns from a file

awk '{print $1, $3}' filename

Extract and print specific fields from csv

awk -F',' '{print "Name: " $1, "Salary: " $3}' data.csv

Print lines between two patterns

awk '/start_pattern/,/end_pattern/' filename

Reverse the order of columns, use comma (,) as the field separator

awk -F',' '{for(i=NF;i>=1;i--) printf $i" "; print ""}' filename

Convert spaces to tabs in a file

awk '{gsub(/    /,"\t"); print}' input.txt > output.txt

Display lines with more than 3 fields

awk 'NF > 3' filename

Calculate and print total size of files in a directory

ls -l /path/to/directory | awk '{total += $5} END {print "Total Size: ", total/1024, "KB"}'

Print lines where the 3rd column is greater than 50

awk '$3 > 50 {print $0}' filename

Print lines where the 4th column is blank

 awk -F',' '$4 == ""' filename

Count the number of lines where the 4th column is blank

awk -F',' '$4 == ""' filename | wc -l

Print lines that are duplicates based on the 4th column in a CSV

awk -F ',' '{if (++seen[$4] == 2) print}' filename 

Count lines that are duplicates based on the 4th column in a CSV

awk -F ',' '{if (++seen[$4] == 2) print}' filename | wc -l

Count the number of rows in a file

awk 'END {print NR}' filename

Print lines matching a pattern

awk '/pattern/ {print $0}' filename

Print unique values in a column

awk '{print $1}' filename | sort | uniq

Show unique lines (without duplicates)

awk '!seen[$0]++' filename.csv

Identify duplicate lines

awk 'seen[$0]++' filename.csv

Replace text in a file

awk '{gsub(/old_text/, "new_text"); print}' filename

Format output

ps aux | awk '{printf "%-10s %-10s %-20s\n", $1, $2, $11}'

Extract information based on delimiter

cat /etc/passwd | awk -F: '{print "Username: " $1, "UID: " $3, "Shell: " $NF}'

Extract and sum numeric values in a column

awk '{if ($2 ~ /^[0-9]+$/) sum += $2} END {print "Sum: ", sum}' filename

Process files in some_directory, get first column, remove double quotes, sort, get unique, save to clean.csv

awk -F',' '{gsub(/"/, "", $1); print $1}' some_directory/* | sort | uniq > clean.csv

Identify unique lines in one file not present in another

awk 'FNR==NR {seen[$0]=1; next} !seen[$0]' product_test.csv ledger_test.csv > not_found_test.txt

Identify common lines in two files

awk 'FNR==NR {seen[$0]=1; next} seen[$0]' product_test.csv ledger_test.csv > found_test.txt

Count empty or whitespace lines in csv

awk -F',' '$4 ~ /^ *$/ {count++} END {print count}' "test.csv"

Extract and sort fourth column, save to new file

awk -F',' '{print $4}' filename.csv | sort > new_file.txt

Extract, sort, and get unique values from fourth column

awk -F',' '{print $4}' filename.csv | sort | uniq > uniques.txt

Extract, sort, and get duplicate values from fourth column

awk -F',' '{print $4}' filename.csv | sort | uniq -d> duplicates.txt

Count blank values in the fourth column

awk -F',' '$4 ~ /^ *$/ {count++} END {print count}' filename.csv

Sum of the nth column

awk '{ sum += $n } END { print sum }' data.txt

Maximum value of the nth column

awk 'NR == 1 { max = $n } { if ($n > max) max = $n } END { print max }' data.txt

Minimum value of the nth column

awk 'NR == 1 { min = $n } { if ($n < min) min = $n } END { print min }' data.txt

Average of the nth column

awk '{ sum += $n } END { print sum / NR }' data.txt