Shell Scripting — Advanced AWK: Fundamentals

# AWK processes input one record (line) at a time
# Each record is split into fields: $1, $2, ... $NF
# $0 = entire record, NR = record number, NF = number of fields
# FS = field separator (default: whitespace)

# ── Structure: [pattern] { action } ──────────────────────
awk '{ print $1 }'                       # action only (runs for every line)
awk '/ERROR/ { print $0 }'              # pattern + action (regex match)
awk 'NR == 1 { print "Header:", $0 }'  # expression pattern
awk '/START/,/END/ { print }'            # range pattern

# ── BEGIN and END blocks ──────────────────────────────────
awk '
BEGIN {
  FS = ","            # set field separator before any input
  print "Processing CSV..."
  count = 0
}
NR > 1 {             # skip header row
  count++
  total += $3        # sum column 3
}
END {
  print "Records:", count
  print "Total:", total
  print "Average:", (count > 0 ? total/count : 0)
}' data.csv

# ── Multiple rules match the same line ───────────────────
awk '
/ERROR/ { errors++ }
/WARN/  { warns++ }
END     { printf "Errors: %d, Warnings: %d\n", errors, warns }
' app.log

# ── Input variables ───────────────────────────────────────
# NR    current record number (total lines read)
# FNR   record number within current file
# NF    number of fields in current record
# $0    full current record
# $1..$NF  individual fields
# FILENAME  current input filename

# ── Separator variables ───────────────────────────────────
# FS    field separator (default: whitespace; set in BEGIN)
# OFS   output field separator (default: space)
# RS    record separator (default: newline)
# ORS   output record separator (default: newline)

# ── Examples ──────────────────────────────────────────────
awk '{ print NR, NF, $1, $NF }' file.txt

# Process CSV — comma separator
awk -F',' '{ print $2 }' data.csv
awk 'BEGIN{FS=","} { print $2 }' data.csv   # same

# Output with custom separator
awk 'BEGIN{FS=":"; OFS="\t"} { print $1, $3, $7 }' /etc/passwd

# Multi-character delimiter
awk -F'  *' '{ print $1 }'             # 2+ spaces as delimiter
awk -F'[,;|]' '{ print $2 }'           # regex delimiter

# Process records separated by blank lines (paragraphs)
awk 'BEGIN{RS=""} { print NR, $0 }' file.txt

# $NF — last field (very useful)
ls -la | awk '{ print $NF }'            # print filename only
df -h   | awk 'NR>1 { print $NF, $5 }' # mount point + use%

# ── String functions ──────────────────────────────────────
awk '{ print length($0) }'                  # line length
awk '{ print length($1) }'                  # field 1 length

awk '{ print toupper($1) }'                 # uppercase
awk '{ print tolower($1) }'                 # lowercase

awk '{ print substr($0, 1, 10) }'           # first 10 chars
awk '{ print substr($1, 5) }'               # from position 5 to end

awk '{ print index($0, "ERROR") }'          # position of substring (0=not found)

awk '{ if (split($0, arr, ":") > 2) print arr[1], arr[3] }'
# split("str", array, sep) → fills array, returns count

# ── sub and gsub — find and replace ──────────────────────
awk '{ sub(/ERROR/, "WARN"); print }'        # replace first match
awk '{ gsub(/ERROR/, "WARN"); print }'       # replace all matches
awk '{ gsub(/ +/, "_"); print }'             # spaces → underscores
awk '{ gsub(/[^0-9]/, ""); print }'          # keep digits only

# ── printf — formatted output ─────────────────────────────
awk '{ printf "%-20s %8.2f\n", $1, $2 }'    # aligned columns
awk '{ printf "%05d %s\n", NR, $0 }'        # zero-padded line numbers

# ── match — regex matching with position ─────────────────
awk '{ if (match($0, /[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+/))
         print substr($0, RSTART, RLENGTH) }'  # extract IP

# ── Arithmetic ────────────────────────────────────────────
awk '{ sum += $1; count++ } END { print sum/count }'
awk 'BEGIN { print 355/113 }'               # pi approximation: 3.14159
awk '{ print int($1 * 1.21) }'              # integer truncation
awk 'BEGIN { print sqrt(2), log(10), sin(3.14) }'

# ── Conditionals ──────────────────────────────────────────
awk '$3 > 80 { print "HIGH:", $0 }'
awk '{ if ($2 == "ERROR") print "error:", $3; else print "ok:", $3 }'
awk '{ status = ($3 > 90) ? "CRITICAL" : ($3 > 70 ? "WARN" : "OK"); print status, $1 }'

# ── Loops ─────────────────────────────────────────────────
awk '{ for (i=1; i<=NF; i++) printf "%s ", $i; print "" }'
awk 'BEGIN { for (i=1; i<=10; i++) print i*i }'
awk '{ i=1; while (i <= NF) { print $i; i++ } }'

# ── next — skip to next record ────────────────────────────
awk '/^#/ { next } { print }'              # skip comment lines
awk 'NF == 0 { next } { print }'           # skip empty lines

# ── exit — stop processing ────────────────────────────────
awk 'NR==5 { exit } { print }'             # print first 4 lines only