AWK

Version vom 25. Januar 2021, 22:30 Uhr

awk_deutsch.pdf

Cheat Sheet 1 (PDF)

Cheat Sheet 2 (DOCX)

Invoking Awk: 
   awk [-F<ch>] {pgm} | {-f <pgm file>} [<vars>] [-|<data file>]
-- where: 
   ch:          Field-separator character.
   pgm:         Awk command-line program.
   pgm file:    File containing an Awk program.
   vars:        Awk variable initializations.
   data file:   Input data file.

AWK Library

# PATH Variables, each in a new line, headline separated:
path | awk "{str=$0;gsub(\";\",\"\n\",str);sub(\"=\",\"\n\n\",str);print str}"
# gsub: alle Vorkommen von ; durch Zeilenumbruch. sub: erstes Vorkommen von = durch 2 Zeilenumbrüche ersetzen

# Leerzeilen weg
awk "NF>0" 1.txt

# doppelte aufeinanderfolgende Zeilen raus
awk "{if (a!=$0) {print $0};a=$0}" 1.TXT

# Anzahl Zeilen
awk "END { print NR \" lines\" }" 1.TXT

# Anzahl Wörter
awk "{ nw += NF } END { print nw \" words\"}" 1.TXT

# Anzahl Buchstaben
awk "{ nc += length($0) } END { print nc \" chars\" }" 1.TXT

# Anzahlen
awk "{ nw += NF;nc += length($0);if (NF==0) e++;} END { print \"\nFile : \" FILENAME \"\nLines: \" NR \" (empty: \" e+0 \")\nWords: \" nw \"\nChars: \" nc}" 1.TXT

# Erzeuge Copy-Befehl, der den Dateinamen durch den Verzeichnispfad ersetzt
dir /b /s *.bat | awk -v wobinich=%cd:\=/% -F\ "BEGIN {print \"REM Copy Filename to last Directoryname\";a=\"\x22\";bs=\"\x5c\";b=\" \";split(wobinich,ar,\"/\");start=length(ar)}{split($NF,ex,\".\");t=$(start);s=$(start);for (i=start+1;i<NF;i++){t=t bs $i;s=s \"_\" $i};print \"copy \"a $0 a b a t bs s  \".\" ex[length(ex)] a}"

# Hänge allen Files in CSV noch ein Semikolon plus Dateinamen (ohne Extension) an
awk.exe -F; "$1!~/CWID/ {print $0\";\"substr(substr(FILENAME,1,length(FILENAME)-4),5)}" csv\*.csv > All.csv
# der innere substr entfernt die Extension, der äussere das 3stellige Verzeichnis (CSV) vorne

#Nummeriere Textfile, aber nicht die Leerzeilen
NF {c=++a;printf ("%5d: %s\n",c,$0)} NF==0

#Sortieren und doppelte Zeilen raus (Leerzeilen auch)
NF {a[$0]=1} END {for (i=1;i<asorti(a,b);i++)print b[i];printf b[i]}
#ungeordnet (durcheinander!) plus Leerzeile, aber schneller (7MB/12000DS: ~3 min sortiert, <1 sek unsortiert):
NF {a[$0]=1} END {for (w in a) print w}

#nur Zeilen die suchtext enthalten
awk "/suchtext/"

#insert before or after other files
BAT:
@echo off
cls

rem copy koreader.sh.bak koreader.sh
rem copy plugins\statistics.koplugin\main.lua.bak plugins\statistics.koplugin\main.lua

set search="export LC_ALL=\"en_US.UTF-8\""
set insertbefore=
set insertafter="mount -r /dev/mmcblk0p5 /mnt/ws"
copy koreader.sh koreader.sh_backup
awk -v search=%search% -v insertbefore=%insertbefore% -v insertafter=%insertafter% -f patch.awk koreader.sh_backup > koreader.sh
dos2unix -U koreader.sh

set search="    self.pageturn_count = self.pageturn_count + 1"
set insertbefore="os.execute(\"hwclock -s -u\")"
set insertafter=
copy plugins\statistics.koplugin\main.lua plugins\statistics.koplugin\main.lua_backup
awk -v search=%search% -v insertbefore=%insertbefore% -v insertafter=%insertafter% -f patch.awk plugins\statistics.koplugin\main.lua_backup > plugins\statistics.koplugin\main.lua
dos2unix -U plugins\statistics.koplugin\main.lua

AWK:
BEGIN {
	i=0
	foundafter=0
}
#search     : export LC_ALL="en_US.UTF-8"
#insertafter: mount -r /dev/mmcblk0p5 /mnt/ws
{
	n++
	a[n]=$0
	if (foundafter==1){
		if (a[n]!=insertafter) {
			#print "[n]=" a[n]
			#print "[i]=" insertafter
			a[n]=insertafter
			n++
			a[n]=$0
		}
	}
	if (a[n]==search) {
		if (insertafter>"" && foundafter==0) {
			foundafter=1
			#print "[f]=" a[n]
		}
		else foundafter=0
		if (insertbefore>"") {
			if (a[n-1]!=insertbefore) {
				a[n+1]=a[n]
				a[n]=insertbefore
				n++
			}
		}
	}
	else foundafter=0
}
END {
	for (i=1;i<=n;i++)
		print a[i]
} 

@echo off

echo @echo off > backslash2slash.bat
echo awk "{a=$0;sub(/\\/,\"/\",a);print a}" %%1 ^> %%2 >> backslash2slash.bat

echo @echo off > make_Apple_m3us_copy.bat

dir /b /s _all.m3u | awk -v wobinich=%cd:\=/% -F\ "BEGIN {print \"REM Copy Filename to last Directoryname\";a=\"\x22\";bs=\"\x5c\";b=\" \";sl=\"\x2f\";nl=\"\x3e\" \"\x6e\" \"\x75\" \"\x6c\";split(wobinich,ar,\"/\");start=length(ar)+1}{split($NF,ex,\".\");t=$(start);s=$(start);for (i=start+1;i<NF;i++){t=t bs $i;s=s \"_\" $i};quelle=a $0 a;ziel=a t bs s  \".\" ex[length(ex)] a;gsub(/&/,\"and\",t);print \"echo \"t;print \"call backslash2slash.bat \" quelle b ziel}">> make_Apple_m3us_copy.bat

call make_Apple_m3us_copy.bat

del make_Apple_m3us_copy.bat
del backslash2slash.bat

Trim Funktion:

function ltrim(s) { sub(/^[ \t\r\n]+/, "", s); return s }
function rtrim(s) { sub(/[ \t\r\n]+$/, "", s); return s }
function trim(s) { return rtrim(ltrim(s)); }
BEGIN {
# whatever
}
{
# whatever
}
END {
# whatever
} 

CSV:

{
	n=split($0,a,von)
	for (i=1;i<=n;i++) {
		if (substr(a[i],1,1)=="\x22" && substr(a[i],length(a[i]))!="\x22") {
			a[i]=a[i] von a[i+1]
			for (j=i+1;j<n;j++) a[j]=a[j+1]
			a[n]=""
			n=n-1
			i=i-1
		}
	}

	s=""
	for (i=1;i<=n;i++) {
		if (substr(a[i],1,1)=="\x22") a[i]=substr(a[i],2,length(a[i])-2)
		s=s a[i] nach
	}
	print substr(s,1,length(s)-1)
}

Aufruf: awk -v von="," -v nach="|" -f csv.awk datei.csv Todo: Abfangen von Zeilenumbrüchen