awk의 레코드, 필드 및 사용자 지정 구분자

awk에서 레코드와 필드란 무엇인가요

#!/usr/bin/env bash
# Show how awk sees records and fields
echo 'alice 30 engineer' | awk '{ print "Name:", $1, "Age:", $2, "Role:", $3 }'

# $NF is always the last field — regardless of how many there are
echo 'one two three four five' | awk '{ print "Last field:", $NF }'

입력 필드 구분자: FS

#!/usr/bin/env bash
# Parse /etc/passwd using ':' as the field separator
# Field 1 = username, field 3 = UID, field 7 = shell
echo 'root:x:0:0:root:/root:/bin/bash
daemon:x:1:1:daemon:/usr/sbin:/usr/sbin/nologin
nobody:x:65534:65534:nobody:/nonexistent:/usr/sbin/nologin' \
  | awk -F':' '{ print $1, "UID="$3, "shell="$7 }'

BEGIN 블록에서 FS 설정하기

#!/usr/bin/env bash
# awk script using BEGIN to set FS for TSV input
printf 'alice\t30\tengineer\nbob\t25\tdesigner\ncarol\t35\tmanager\n' \
  | awk 'BEGIN { FS = "\t" } { printf "%-10s age=%-3s role=%s\n", $1, $2, $3 }'

awk로 CSV 파일 분석하기

#!/usr/bin/env bash
# Simple CSV: extract name and salary columns, filter salary > 50000
data='name,department,salary
alice,engineering,95000
bob,marketing,48000
carol,engineering,112000
dave,hr,45000'

echo "$data" | awk -F',' '
  NR == 1 { next }          # skip header row
  $3 > 50000 { print $1, "earns", $3 }
'

여러 문자 및 정규식 필드 구분자

#!/usr/bin/env bash
# Log lines with mixed delimiters: split on " | " or "::" or ","
# Here we split on one or more spaces or pipe characters
printf '2024-01-15 | ERROR | disk full | /dev/sda1\n2024-01-15 | INFO  | startup ok | main\n' \
  | awk -F' \\| ' '{ printf "date=%-12s level=%-6s msg=%s\n", $1, $2, $3 }'

# Split on multiple possible delimiters using character class
echo 'alpha,beta;gamma,delta;epsilon' \
  | awk -F'[,;]' '{ for(i=1; i<=NF; i++) print i": "$i }'

출력 필드 구분자: OFS

#!/usr/bin/env bash
# Convert CSV to TSV using FS and OFS
data='alice,30,engineer
bob,25,designer
carol,35,manager'

echo "$data" | awk 'BEGIN { FS=","; OFS="\t" } { print $1, $2, $3 }'

echo '---'

# OFS also applies when you modify a field — awk rebuilds $0 with OFS
echo 'alice,30,engineer' | awk 'BEGIN { FS=","; OFS=" | " } { $1=$1; print $0 }'

OFS로 awk가 $0을 다시 만들도록 하기

#!/usr/bin/env bash
# Reformat a pipe-delimited file to comma-separated WITHOUT listing every field
printf 'alice|30|engineer|london\nbob|25|designer|paris\ncarol|35|manager|berlin\n' \
  | awk 'BEGIN { FS="|"; OFS="," } { $1=$1; print $0 }'

# Useful when you don't know how many fields there are:
printf 'a|b|c|d|e|f|g\n1|2|3|4|5|6|7\n' \
  | awk 'BEGIN { FS="|"; OFS="\t" } { $1=$1; print $0 }'

레코드 구분자: RS

#!/usr/bin/env bash
# Paragraph mode: each blank-line-separated block is one record
# Useful for processing structured text blocks (e.g., stanzas, config sections)
data='Name: Alice
Role: Engineer
City: London

Name: Bob
Role: Designer
City: Paris'

echo "$data" | awk 'BEGIN { RS=""; FS="\n" } {
  print "Record", NR":"
  for (i=1; i<=NF; i++) print "  ", $i
  print ""
}'

출력 레코드 구분자: ORS

#!/usr/bin/env bash
# Join all matching lines onto one line by setting ORS to a space
printf 'apple\nbanana\ncherry\ndate\n' | awk '{ ORS=" " } { print $0 }'
echo  # final newline

# Add a blank line after every output record for readability
printf 'alice 30 engineer\nbob 25 designer\ncarol 35 manager\n' \
  | awk 'BEGIN { ORS="\n\n" } { print $1, "is a", $3 }'

실전 예제: Apache 액세스 로그 구문 분석

#!/usr/bin/env bash
# Parse a simulated Apache Combined Log Format line
# Extract: IP, status code, bytes, and request path
logs='192.168.1.10 - alice [15/Jan/2024:10:23:45 +0000] "GET /api/users HTTP/1.1" 200 1523
10.0.0.5 - - [15/Jan/2024:10:23:46 +0000] "POST /login HTTP/1.1" 401 89
172.16.0.3 - bob [15/Jan/2024:10:23:47 +0000] "GET /dashboard HTTP/1.1" 200 8741'

echo "$logs" | awk '{
  ip     = $1
  status = $9
  bytes  = $10
  # Extract the request path from the quoted string in field 7
  split($7, parts, "/")
  path = "/" parts[2]
  printf "ip=%-15s status=%s bytes=%-6s endpoint=%s\n", ip, status, bytes, path
}'

파이프라인에서 FS, OFS, RS, ORS 결합하기

#!/usr/bin/env bash
# Full pipeline: read a colon-delimited file,
# filter rows where field 3 (UID) >= 1000 (real users),
# then output as tab-separated: username, UID, home dir
echo 'root:x:0:0:root:/root:/bin/bash
daemon:x:1:1:daemon:/usr/sbin:/usr/sbin/nologin
alice:x:1001:1001:Alice:/home/alice:/bin/bash
bob:x:1002:1002:Bob:/home/bob:/bin/zsh
www-data:x:33:33:www-data:/var/www:/usr/sbin/nologin' \
  | awk 'BEGIN { FS=":"; OFS="\t" } $3 >= 1000 { print $1, $3, $6 }'

지식 확인: OFS와 필드 다시 구성

단원 요약: 레코드, 필드, 구분자