(old)Puppy Linux Discussion Forum

Code: Select all

03:50|Artist - Title|001 /path/Artist_Title.mp3
04:16|Bartist - Title|002 /path/Bartist_Title.mp3
03:32|Cartist - Title|003 /path/Cartist_Title.mp3

Code: Select all

002 /path/Bartist_Title.mp3
001 /path/Artist_Title.mp3
003 /path/Cartist_Title.mp3

Code: Select all

#!/bin/bash

for i in `awk '{print $1}' file2`; do
  awk 'NR=='$i'' file1
done

Code: Select all

echo -e "1 hello\n2 world\n256 last" |awk '{printf "%5s %s\n",$1, $2}'

Code: Select all

#!/bin/awk -f
#FILENAME (name of current file) $FILENAME (contents of current file)
#NF number of fields, $NF last field
#NR line number in all files		#FNR line number in current file
#ORS (default is "\n")				#RS  (default is "\n")
#OFS (default is " ")				#FS (default is [ \t]*)
#system(command) run a command		#close(filename) close(command)
#ARGC, ARGV similar to C, but skips some stuff
#IGNORECASE (default is 0) set to non-0 or use toupper() or tolower()
#ENVIRON array of env vars ex. ENVIRON["SHELL"] (equivalent of $SHELL)
#getline var < file ... close file or command | getline var
#index(haystack, needle) find needle in haystack
#length(string)
#match(string, regexp) returns where the regex starts, or 0
#RLENGTH length of /match/ substring or -1
#RSTART position where the /match/ substring starts, or 0
#split(string, array, fieldsep) split string into an array separated by fieldsep
#printf(format, expression1,...) print format-ted replacing %* with expressions
#%{c,d/i,e,f,g,o,s,x,X,%} char, decimal int, exp notation, float, shortest of 
#	exp/float, octal, string, hex int, capitalized hex int, a '%' character
#sprintf(format, expression1,...) store printf in a variable
#sub(regexp, replacement, target) replace first regex with replacement in target
#gsub(regexp, replacement, target) like gsub but for all regex in target
#substr(string, start, length)get substring of string from start to start+length
#print > /dev/stdin, /dev/stdout, /dev/stderr, /dev/fd/# or filename
#output can be piped like print $0 | command
#comparisons <,>,<=,>=,==,!=,~,!~,in use && for AND, || for OR, ! for NOT
#	(~ is for regexp and "in" looks for subscript in array)
#/word/{...} like if match(...) {...} equivalent of grep
#(condition) ? if-true-exp : if-false-exp or use if (condition){}
#math +,-,*,/,%,**,log(x),exp(x),,sqrt(x),cos(x),sin(x),atan2(y,x),
#rand(),srand(x),time(),ctime()
#
#function name (parameter-list) {
#     body-of-function
#}

BEGIN {
#actions that happen before any files are read in
}
#
{
#actions to do on files
}
#
END {
#actions to do after all files are done
}

Code: Select all

#!/bin/bash

#Utility
function endl()
{
	cat
	echo
}

#Our own private directory
tmp="/tmp/sort2"
mkdir -p "$tmp"

#Index file2
i=0
ifsbak="$IFS"
IFS=""
while read line; do
	echo "$i|$line"
	i=$(( $i+1 ))
done < "./file2" > "$tmp/file2_indexed"

#Sort both files alphabetically
sort -t '|' -k 3 -o "$tmp/file1_sorted" "./file1"
sort -t '|' -k 2 -o "$tmp/file2_sorted" "$tmp/file2_indexed"

#Load 'sorted' indices into array
IFS='|'
cut -d '|' -f 1 "$tmp/file2_sorted" | tr '
' '|' | endl | while read -a indices; do
	IFS='
'
	#Don't know why read -a doesn't work outside the loop
	
	#Attach indices to file1_sorted
	IFS=""
	i=0
	while read line; do
		echo "${indices[$i]}|$line"
		i=$(( $i+1 ))
	done < "$tmp/file1_sorted" > "$tmp/file1_indexed"
	#Sort it by attached index
	sort -t '|' -k 1 -n -o "$tmp/file1_sorted_final" "$tmp/file1_indexed"
	#Final output
	cut -d '|' -f 2- "$tmp/file1_sorted_final"
	break
done

Code: Select all

# time ./zigsort file1 file2
04:16|Bartist - Title|002 /path/Bartist_Title.mp3
03:50|Artist - Title|001 /path/Artist_Title.mp3
03:32|Cartist - Title|003 /path/Cartist_Title.mp3

real	0m0.001s
user	0m0.000s
sys	0m0.000s

Code: Select all

#!/bin/awk -f
BEGIN{FS="|"}{if($3){d[$3]=$0;}else{print d[$1]}}

Code: Select all

awk 'BEGIN{FS="|"}{if($3){d[$3]=$0;}else{print d[$1]}}' unsorted_file sorted_file

Code: Select all

# time ./zigsort file1 file2 > file3

real	0m0.031s
user	0m0.008s
sys	0m0.020s

# time ./technosort file1 file2 > file3

real	0m0.039s
user	0m0.036s
sys	0m0.000s
# 

Code: Select all

# time ./zigsort file1 file2 > file3

real	0m0.011s
user	0m0.004s
sys	0m0.004s

Code: Select all

#!/bin/ash

ENTRIES=10000
FILE1=/tmp/file1
FILE2=/tmp/file2
OUTFILE=/tmp/outfile

generate_file1() {
	for a in $(seq 1 $ENTRIES); do
		printf "03:50|Artist - Title|%.3d /path/Artist_Title.mp3\n" $a
	done > $FILE1
}

generate_file2() {
	for a in $(seq 1 $ENTRIES); do
		printf "%.3d /path/Artist_Title.mp3\n" $a
	done | sort -R > $FILE2
}

# generate fake data for testing
generate_file1
generate_file2

time -p -- awk -F"|" '
NR > FNR {
	# sort	
	FS=" "
	print file1[$1]
	next
}
{
	# scan
	line=$0
	sub(/ .*/,"",$3)
	file1[$3]=line
}
' $FILE1 $FILE2 > $OUTFILE