entityMap|blocks|key|8clo0|text|让我们假设这就是您的原始脚本正在做的事情，给定您发布的样本输入和您所获得的输出：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|680c|$+cat+tst.awk
BEGIN+{+FS=",";+OFS="\t"+}
{+vals[$1]+=+($1+in+vals+?+vals[$1]+",+"+:+"")+$4+}
END+{
++++print+"column1",+"column2"
++++print+"=======",+"======="

++++for+(key+in+vals)+{
++++++++print+key,+vals[key]
++++}
}

$+awk+-f+tst.awk+file
column1+column2
=======+=======
1+++++++test1
2+++++++test2,+test2,+test2,+test2,+test2,+test2,+test2,+test2,+test2,+test2,+test2,+test2|code-block|syntax|javascript|1s60b|这是你的问题的一个很好的起点，现在你想要包装每一列吗？如果是这样的话，我将利用现有的UNIX工具(如fold或fmt+)为您完成包装，这样您就不必编写自己的代码来处理空格和中间字的拆分，等等：|offset|length|style|CODE|5ph22|$+cat+tst.awk
BEGIN+{+FS=",";+OFS="\t"+}
{+vals[$1]+=+($1+in+vals+?+vals[$1]+",+"+:+"")+$4+}
END+{
++++print+"column1",+"column2"
++++print+"=======",+"======="

++++for+(key+in+vals)+{
++++++++numKeyLines+=+wrap(key,15,keyArr)
++++++++numValLines+=+wrap(vals[key],50,valArr)
++++++++numLines+=+(numKeyLines+>+numValLines+?+numKeyLines+:+numValLines)
++++++++for+(lineNr=1;+lineNr<=numLines;+lineNr%2B%2B)+{
++++++++++++print+keyArr[lineNr],+valArr[lineNr]
++++++++}
++++}
}

function+wrap(inStr,wid,outArr,+++++++++cmd,line,numLines)+{
++++if+(+length(inStr)+>+wid+)+{
++++++++cmd+=+"printf+\047%25s\n\047+\""+inStr+"\"+%7C+fold+-s+-w+"+wid%2B0
++++++++while+(+(cmd+%7C+getline+line)+>+0+)+{
++++++++++++outArr[%2B%2BnumLines]+=+line
++++++++}
++++++++close(cmd)
++++}
++++else+{
++++++++outArr[%2B%2BnumLines]+=+inStr
++++}
++++return+numLines%2B0
}|egiqt|。|8ialq|$+awk+-f+tst.awk+file
column1+column2
=======+=======
1+++++++test1
2+++++++test2,+test2,+test2,+test2,+test2,+test2,+test2,
++++++++test2,+test2,+test2,+test2,+test2|a9et5|如果你有很多字段需要包装，那么它将不会很快，因为每次调用fold都会产生一个子外壳，所以这里是一个all+awk版本，尽可能在空格中拆分，测试它的边缘情况并根据需要进行按摩：|2909k|$+cat+tst.awk
BEGIN+{+FS=",";+OFS="\t"+}
{+vals[$1]+=+($1+in+vals+?+vals[$1]+",+"+:+"")+$4+}
END+{
++++print+"column1",+"column2"
++++print+"=======",+"======="

++++for+(key+in+vals)+{
++++++++numKeyLines+=+wrap(key,15,keyArr)
++++++++numValLines+=+wrap(vals[key],50,valArr)
++++++++numLines+=+(numKeyLines+>+numValLines+?+numKeyLines+:+numValLines)
++++++++for+(lineNr=1;+lineNr<=numLines;+lineNr%2B%2B)+{
++++++++++++print+keyArr[lineNr],+valArr[lineNr]
++++++++}
++++}
}

function+wrap(inStr,wid,outArr,+++++++++lineEnd,numLines)+{
++++while+(+length(inStr)+>+wid+)+{
++++++++lineEnd+=+(+match(substr(inStr,1,wid),/.*[[:space:]]/)+?+RLENGTH+-+1+:+wid+)
++++++++outArr[%2B%2BnumLines]+=+substr(inStr,1,lineEnd)
++++++++inStr+=+substr(inStr,lineEnd%2B1)
++++++++sub(/%5E[[:space:]]%2B/,"",inStr)
++++}
++++outArr[%2B%2BnumLines]+=+inStr
++++return+numLines
}

$+awk+-f+tst.awk+file
column1+column2
=======+=======
1+++++++test1
2+++++++test2,+test2,+test2,+test2,+test2,+test2,+test2,
++++++++test2,+test2,+test2,+test2,+test2|2ctmr^0|0|0|1E|4|1J|3|0|0|0|0|S|4|0|0^^$0|$]|1|@$2|3|4|5|6|7|8|Y|9|@]|A|@]|B|$]]|$2|C|4|D|6|E|8|Z|9|@]|A|@]|B|$F|G]]|$2|H|4|I|6|7|8|10|9|@$J|11|K|12|L|M]|$J|13|K|14|L|M]]|A|@]|B|$]]|$2|N|4|O|6|E|8|15|9|@]|A|@]|B|$F|G]]|$2|P|4|Q|6|7|8|16|9|@]|A|@]|B|$]]|$2|R|4|S|6|E|8|17|9|@]|A|@]|B|$F|G]]|$2|T|4|U|6|7|8|18|9|@$J|19|K|1A|L|M]]|A|@]|B|$]]|$2|V|4|W|6|E|8|1B|9|@]|A|@]|B|$F|G]]|$2|X|4|-4|6|7|8|1C|9|@]|A|@]|B|$]]]]

Let's pretend this is what your original script is doing given your posted sample input and the output you say you get:

<pre><code>$ cat tst.awk
BEGIN { FS=","; OFS="\t" }
{ vals[$1] = ($1 in vals ? vals[$1] ", " : "") $4 }
END {
 print "column1", "column2"
 print "=======", "======="

 for (key in vals) {
 print key, vals[key]
 }
}

$ awk -f tst.awk file
column1 column2
======= =======
1 test1
2 test2, test2, test2, test2, test2, test2, test2, test2, test2, test2, test2, test2
</code></pre>

Would that be a good starting point for your question and now you want to wrap each column? If so then I'd take advantage of an existing UNIX tool like <code>fold</code> or <code>fmt</code> to do the wrapping for you so you don't have to write your own code to handle splitting on spaces vs mid-word, etc.:

<pre><code>$ cat tst.awk
BEGIN { FS=","; OFS="\t" }
{ vals[$1] = ($1 in vals ? vals[$1] ", " : "") $4 }
END {
 print "column1", "column2"
 print "=======", "======="

 for (key in vals) {
 numKeyLines = wrap(key,15,keyArr)
 numValLines = wrap(vals[key],50,valArr)
 numLines = (numKeyLines &gt; numValLines ? numKeyLines : numValLines)
 for (lineNr=1; lineNr&lt;=numLines; lineNr++) {
 print keyArr[lineNr], valArr[lineNr]
 }
 }
}

function wrap(inStr,wid,outArr, cmd,line,numLines) {
 if ( length(inStr) &gt; wid ) {
 cmd = "printf \047%s\n\047 \"" inStr "\" | fold -s -w " wid+0
 while ( (cmd | getline line) &gt; 0 ) {
 outArr[++numLines] = line
 }
 close(cmd)
 }
 else {
 outArr[++numLines] = inStr
 }
 return numLines+0
}
</code></pre>

.

<pre><code>$ awk -f tst.awk file
column1 column2
======= =======
1 test1
2 test2, test2, test2, test2, test2, test2, test2,
 test2, test2, test2, test2, test2
</code></pre>

If you have a lot of fields that need to be wrapped then it won't be fast due to spawning a subshell for each call to <code>fold</code> so here's an all awk version that splits at spaces when possible, test it for edge cases and massage to suit:

<pre><code>$ cat tst.awk
BEGIN { FS=","; OFS="\t" }
{ vals[$1] = ($1 in vals ? vals[$1] ", " : "") $4 }
END {
 print "column1", "column2"
 print "=======", "======="

 for (key in vals) {
 numKeyLines = wrap(key,15,keyArr)
 numValLines = wrap(vals[key],50,valArr)
 numLines = (numKeyLines &gt; numValLines ? numKeyLines : numValLines)
 for (lineNr=1; lineNr&lt;=numLines; lineNr++) {
 print keyArr[lineNr], valArr[lineNr]
 }
 }
}

function wrap(inStr,wid,outArr, lineEnd,numLines) {
 while ( length(inStr) &gt; wid ) {
 lineEnd = ( match(substr(inStr,1,wid),/.*[[:space:]]/) ? RLENGTH - 1 : wid )
 outArr[++numLines] = substr(inStr,1,lineEnd)
 inStr = substr(inStr,lineEnd+1)
 sub(/^[[:space:]]+/,"",inStr)
 }
 outArr[++numLines] = inStr
 return numLines
}

$ awk -f tst.awk file
column1 column2
======= =======
1 test1
2 test2, test2, test2, test2, test2, test2, test2,
 test2, test2, test2, test2, test2
</code></pre>

entityMap|0|type|LINK|mutability|MUTABLE|data|url|https://perldoc.pl/perlform|blocks|key|5mlpl|text|下面是一个使用perl而不是awk的版本：|unstyled|depth|inlineStyleRanges|entityRanges|e7let|#!/usr/bin/env+perl
use+warnings;
use+strict;

my+($col1,+$col4,+@col4data);

print+<<EOF;
COLUMN1+++++COLUMN2
=======+++++=======
EOF

{
++my+$line+=+<>;
++chomp+$line;
++($col1,+$col4data[0])+=+(split+/,/,+$line)[0,3];
}

while+(<>)+{
++chomp;
++my+($c,+$a)+=+(split+/,/)[0,3];
++if+($c+ne+$col1)+{
++++$col4+=+join+",+",+@col4data;
++++write;
++++@col4data+=+();
++++$col1+=+$c;
++}
++push+@col4data,+$a;
}

$col4+=+join+",+",+@col4data;
write;

format+STDOUT+=
@<<<<<<<++++%5E<<<<<<<<<<<<<<<<<<<<<<
$col1,++++++$col4
~~++++++++++%5E<<<<<<<<<<<<<<<<<<<<<<
++++++++++++$col4
.|code-block|syntax|javascript|3j12f|示例：|9cco2|$+perl+columns.pl+input.csv
COLUMN1+++++COLUMN2
=======+++++=======
1+++++++++++test1
2+++++++++++test2,+test2,+test2,
++++++++++++test2,+test2,+test2,
++++++++++++test2,+test2,+test2,
++++++++++++test2,+test2,+test2|13cn4|这里的魔术是使用output+format的填充模式进行换行，通过在format描述中明显的部分添加更多的<来根据需要调整宽度。|offset|length|style|CODE|f7nf0^0|0|0|0|0|Y|6|1H|1|8|D|0|0^^$0|$1|$2|3|4|5|6|$7|8]]]|9|@$A|B|C|D|2|E|F|Y|G|@]|H|@]|6|$]]|$A|I|C|J|2|K|F|Z|G|@]|H|@]|6|$L|M]]|$A|N|C|O|2|E|F|10|G|@]|H|@]|6|$]]|$A|P|C|Q|2|K|F|11|G|@]|H|@]|6|$L|M]]|$A|R|C|S|2|E|F|12|G|@$T|13|U|14|V|W]|$T|15|U|16|V|W]]|H|@$T|17|U|18|A|19]]|6|$]]|$A|X|C|-4|2|E|F|1A|G|@]|H|@]|6|$]]]]

Here's a version that uses perl instead of awk:



<pre><code>#!/usr/bin/env perl
use warnings;
use strict;

my ($col1, $col4, @col4data);

print &lt;&lt;EOF;
COLUMN1 COLUMN2
======= =======
EOF

{
 my $line = &lt;&gt;;
 chomp $line;
 ($col1, $col4data[0]) = (split /,/, $line)[0,3];
}

while (&lt;&gt;) {
 chomp;
 my ($c, $a) = (split /,/)[0,3];
 if ($c ne $col1) {
 $col4 = join ", ", @col4data;
 write;
 @col4data = ();
 $col1 = $c;
 }
 push @col4data, $a;
}

$col4 = join ", ", @col4data;
write;

format STDOUT =
@&lt;&lt;&lt;&lt;&lt;&lt;&lt; ^&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;
$col1, $col4
~~ ^&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;&lt;
 $col4
.
</code></pre>

Example:

<pre><code>$ perl columns.pl input.csv
COLUMN1 COLUMN2
======= =======
1 test1
2 test2, test2, test2,
 test2, test2, test2,
 test2, test2, test2,
 test2, test2, test2
</code></pre>

The magic here is doing the line wrapping using an <a href="https://perldoc.pl/perlform" rel="nofollow noreferrer">output format</a>'s fill mode. Adjust the width as needed by adding more <code>&lt;</code>'s to the obvious parts in the <code>format</code> description.

I have a comma delimited file which I am formatting to create 2 columns using printf. I am using awk to group the contents into similar groups so I can print them into nicely formatted columns. 

The formatting works but the contents of the array wrap onto new lines instead of wrapping within the column itself.

Input file example:

<pre><code>1,test,test1,test1
2,test,test1,test2
2,test,test1,test2
2,test,test1,test2
2,test,test1,test2
2,test,test1,test2
2,test,test1,test2
2,test,test1,test2
2,test,test1,test2
2,test,test1,test2
2,test,test1,test2
2,test,test1,test2
2,test,test1,test2`
</code></pre>

Command used:

<pre><code>awk -F"," 'NR&gt;1 {a[$3]=a[$3] ? a[$3]", "$4" ("$2")" : $4" ("$2")"}
 END {for (i in a) {print i":"a[i]}}' test.dat |
sort |
awk -F":" 'BEGIN { printf "%-15s %-10s\n", "COLUMN1","COLUMN2"; printf "%-15s %-10s\n", "-----------","----------"}
 { printf "%-15s %-10s\n", $1,$2}'
</code></pre>

I am also aware about and have tried using <code>column -t -s","</code> and <code>pr</code>

The outcome is like (simulating example):

<pre><code>COLUMN1 COLUMN2
======== =======
1 test1
2 test2, test2, test2, test2, test2, test2,test2, test2, test2,test2, test2, test2, test2, test2
</code></pre>

How can I wrap the second column (even the first one if it is too long) so that it fits within its frame?

<pre><code>COLUMN1 COLUMN2
======== =======
1 test1
2 test2, test2, test2, test2, test2, test2,test2, test2, 
 test2,test2, test2, test2, test2, test2
</code></pre>

How to wrap lines within columns in Linux

 我有一个逗号分隔的文件，我正在使用printf格式化它以创建2列。我使用awk将内容分组到类似的组中，这样我就可以将它们打印到格式良好的列中。 格式化是有效的，但是数组的内容换行到新行上，而不是在列本身内换行。 输入文件示例： 1,test,test1,test12,test,test1,test22,test,te...

问在Linux中如何在列中换行
EN

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问在Linux中如何在列中换行EN

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问在Linux中如何在列中换行
EN