在Bash中转置文件的有效方法

#1 楼

awk '
{ 
    for (i=1; i<=NF; i++)  {
        a[NR,i] = $i
    }
}
NF>p { p = NF }
END {    
    for(j=1; j<=p; j++) {
        str=a[1,j]
        for(i=2; i<=NR; i++){
            str=str" "a[i,j];
        }
        print str
    }
}' file

$ more file
0 1 2
3 4 5
6 7 8
9 10 11

$ ./shell.sh
0 3 6 9
1 4 7 10
2 5 8 11

$ head -5 file
1 0 1 2
2 3 4 5
3 6 7 8
4 9 10 11
1 0 1 2

$  wc -l < file
10000

$ time perl test.pl file >/dev/null

real    0m0.480s
user    0m0.442s
sys     0m0.026s

$ time awk -f test.awk file >/dev/null

real    0m0.382s
user    0m0.367s
sys     0m0.011s

$ time perl test.pl file >/dev/null

real    0m0.481s
user    0m0.431s
sys     0m0.022s

$ time awk -f test.awk file >/dev/null

real    0m0.390s
user    0m0.370s
sys     0m0.010s

$ cat tst.awk
BEGIN { FS=OFS="\t" }
{
    for (rowNr=1;rowNr<=NF;rowNr++) {
        cell[rowNr,NR] = $rowNr
    }
    maxRows = (NF > maxRows ? NF : maxRows)
    maxCols = NR
}
END {
    for (rowNr=1;rowNr<=maxRows;rowNr++) {
        for (colNr=1;colNr<=maxCols;colNr++) {
            printf "%s%s", cell[rowNr,colNr], (colNr < maxCols ? OFS : ORS)
        }
    }
}

$ awk -f tst.awk file
X       row1    row2    row3    row4
column1 0       3       6       9
column2 1       4       7       10
column3 2       5       8       11

#2 楼

 rs -T
 

 rs -c -C -T
 

 rs -c, -C, -T
 

 $ seq 4|paste -d, - -|rs -c, -C, -T
1,3,
2,4,
$ seq 4|paste -d, - -|rs -c, -C, -T|sed 's/.$//'
1,3
2,4
 

 $ rs -C, -c, -T<<<$'1,\n3,4'
1,3,4,
 

 split 

 $ ruby -e'p"a,,".split(",")'
["a"]
$ ruby -e'p"a,,".split(",",-1)'
["a", "", ""]
 

 $ tp(){ ruby -e'puts STDIN.read.split("\n").map{|x|x.split(ARGV[0],-1)}.transpose.map{|x|x*ARGV[0]}' -- "${1-$'\t'}";}
$ seq 4|paste - -|tp|sed -n l
1\t3$
2\t4$
  
jq -R .|jq -sr 'map(./"\t")|transpose|map(join("\t"))[]'
将每条输入行打印为JSON字符串文字，jq -R .（-s）在将每一行解析为JSON之后为输入行创建一个数组，而--slurp（-r）输出字符串的内容而不是JSON字符串文字。 --raw-output运算符已重载以分割字符串。
函数形式：
 
 / 
 

评论
我对rs不熟悉-感谢您的指导！ （链接指向Debian；上游似乎是mirbsd.org/MirOS/dist/mir/rs）



 –tripleee

 2015年11月26日13:00



 
@lalebarde至少在OS X附带的rs的实现中，-c单独将输入列分隔符设置为选项卡。



 – nisetama

 16 Mar 5 '16 at 12:20 
@lalebarde，尝试使用bash的ANSI-C引号获取制表符：$'\ t'



 –格伦·杰克曼

 16年4月10日在11:51 
这是一个极端的情况，但是对于具有很多行（如TTC TTA TTC TTC TTC TTT）的非常大的文件，运行rs -c''-C''-T  cols.seq会得到rs：没有内存：无法分配记忆。这是一个运行FreeBSD 11.0-RELEASE且系统内存为32 GB的系统。因此，我的猜测是rs将所有内容都放入RAM，这对于提高速度很有好处，但对大数据却不利。



 – jrm

 17年7月6日在9:35



 
jq在766MB的文件上使用了21Gb的ram。 40分钟后我将其杀死，但没有任何输出。



 –Glubbdrubb

 18年3月20日在9:50 

#3 楼

python -c "import sys; print('\n'.join(' '.join(c) for c in zip(*(l.split() for l in sys.stdin.readlines() if l.strip()))))" < input > output

#4 楼

gcc transpose.c -o transpose
./transpose -t input > output #works with stdin, too.

#5 楼

#6 楼

declare -a array=( )                      # we build a 1-D-array

read -a line < ""                       # read the headline

COLS=${#line[@]}                          # save number of columns

index=0
while read -a line ; do
    for (( COUNTER=0; COUNTER<${#line[@]}; COUNTER++ )); do
        array[$index]=${line[$COUNTER]}
        ((index++))
    done
done < ""

for (( ROW = 0; ROW < COLS; ROW++ )); do
  for (( COUNTER = ROW; COUNTER < ${#array[@]}; COUNTER += COLS )); do
    printf "%s\t" ${array[$COUNTER]}
  done
  printf "\n" 
done

#7 楼

#8 楼

#9 楼

apt install datamash  

datamash transpose < yourfile

#10 楼

psc -r < inputfile | sc -W% - > outputfile

#11 楼

#12 楼

#13 楼

#14 楼

#15 楼

for f in 1 2 3 4 ; do cut -d ' ' -f $f foo | xargs echo ; done

n=$(head -n 1 foo | wc -w)
for f in $(seq 1 $n) ; do cut -d ' ' -f $f foo | xargs echo ; done

{ timeout '.01' xargs --show-limits ; } 2>&1 | grep Max

for f in 1 2 3 4; do cut -d ' ' -f $f foo | tr '\n\ ' ' ; echo; done

n=$(head -n 1 foo | wc -w)
for f in $(seq 1 $n); do 
    cut -d ' ' -f $f foo | tr '\n' ' ' ; echo
done

#16 楼

#17 楼

#!/bin/bash 
declare -a array=( )                      # we build a 1-D-array
declare -a ncols=( )                      # we build a 1-D-array containing number of elements of each row

SEPARATOR="\t";
PADDING="";
MAXROWS=0;
index=0
indexCol=0
while read -a line; do
    ncols[$indexCol]=${#line[@]};
((indexCol++))
if [ ${#line[@]} -gt ${MAXROWS} ]
    then
         MAXROWS=${#line[@]}
    fi    
    for (( COUNTER=0; COUNTER<${#line[@]}; COUNTER++ )); do
        array[$index]=${line[$COUNTER]}
        ((index++))

    done
done < ""

for (( ROW = 0; ROW < MAXROWS; ROW++ )); do
  COUNTER=$ROW;
  for (( indexCol=0; indexCol < ${#ncols[@]}; indexCol++ )); do
if [ $ROW -ge ${ncols[indexCol]} ]
    then
      printf $PADDING
    else
  printf "%s" ${array[$COUNTER]}
fi
if [ $((indexCol+1)) -lt ${#ncols[@]} ]
then
  printf $SEPARATOR
    fi
    COUNTER=$(( COUNTER + ncols[indexCol] ))
  done
  printf "\n" 
done

#18 楼

Row2Trans=number1
Col2Trans=number2

for ((i=1; $i <= Line2Trans; i++));do
    for ((j=1; $j <=Col2Trans ; j++));do
        awk -v var1="$i" -v var2="$j" 'BEGIN { FS = "," }  ; NR==var1 {print $((var2)) }' $ARCHIVO >> Column_$i
    done
done

paste -d',' `ls -mv Column_* | sed 's/,//g'` >> $ARCHIVO

#19 楼

#20 楼

#21 楼

awk '{ for (i=1; i<=NF; i++) RtoC[i]= (RtoC[i]? RtoC[i] FS $i: $i) }
    END{ for (i in RtoC) print RtoC[i] }' infile

#22 楼

#!/bin/bash

aline="$(head -n 1 file.txt)"
set -- $aline
colNum=$#

#set -x
while read line; do
  set -- $line
  for i in $(seq $colNum); do
    eval col$i="\"$col$i $$i\""
  done
done < file.txt

for i in $(seq $colNum); do
  eval echo ${col$i}
done

#23 楼

$ cat file 
XXXX    col1    col2    col3
row1    0       1       2
row2    3       4       5
row3    6       7       8
row4    9       10      11

#!/bin/bash

I=0
while read line; do
    i=0
    for item in $line; { printf -v A$I[$i] $item; ((i++)); }
    ((I++))
done < file
indexes=$(seq 0 $i)

for i in $indexes; {
    J=0
    while ((J<I)); do
        arr="A$J[$i]"
        printf "${!arr}\t"
        ((J++))
    done
    echo
}

$ ./test 
XXXX    row1    row2    row3    row4    
col1    0       3       6       9   
col2    1       4       7       10  
col3    2       5       8       11

#24 楼

transpose :: [[a]] -> [[a]]
transpose = foldr (zipWith (:)) (repeat [])

main :: IO ()
main = interact $ unlines . map unwords . transpose . map words . lines

#25 楼

    awk '
#!/bin/bash
maxf="$(awk '{if (mf<NF); mf=NF}; END{print mf}' infile)"
rowcount=maxf
for (( i=1; i<=rowcount; i++ )); do
    awk -v i="$i" -F " " '{printf("%s\t ", $i)}' infile
    echo
done
!~/^$/{    i++;
                  split(q4312078q,arr,FS);
                  for (j in arr) {
                      out[i,j]=arr[j];
                      if (maxr<j){ maxr=j}     # max number of output rows.
                  }
            }
    END {
        maxc=i                 # max number of output columns.
        for     (j=1; j<=maxr; j++) {
            for (i=1; i<=maxc; i++) {
                printf( "%s:", out[i,j])
            }
            printf( "%s\n","" )
        }
    }' infile

#26 楼

echo '' > tmp1;  \
cat m.txt | while read l ; \
            do    paste tmp1 <(echo $l | tr -s ' ' \n) > tmp2; \
                  cp tmp2 tmp1; \
            done; \
cat tmp1

0 1 2
4 5 6
7 8 9
10 11 12

#27 楼

#28 楼

awk '
{
    for (i = 1; i <= NF; i++) {
        s[i] = s[i]?s[i] FS $i:$i
    }
}
END {
    for (i in s) {
        print s[i]
    }
}' file.txt

declare -a arr

while IFS= read -r line
do
    i=0
    for word in $line
    do
        [[ ${arr[$i]} ]] && arr[$i]="${arr[$i]} $word" || arr[$i]=$word
        ((i++))
    done
done < file.txt

for ((i=0; i < ${#arr[@]}; i++))
do
    echo ${arr[i]}
done

#29 楼

col="$(head -1 file.txt | wc -w)"
for i in $(seq 1 $col); do
    awk '{ print $'$i' }' file.txt | paste -s -d "\t"
done