test_data_1              
1  2  90%
4  3  91%
5  4  90%
6  5  90%
9  6  90%

test_data_2              
3  5  92%
5  4  92%
7  3  93%
9  2  92%
1  1  92%
...

test_data_1           test_data_2       ...
1  2  90%             3  5  92%         ...
4  3  91%             5  4  92%         ...
5  4  90%             7  3  93%         ...
6  5  90%             9  2  92%         ...
9  6  90%             1  1  92%         ...

paste file1 file2 file3 ...

test_data_9
2  95%
3  94%
4  91%
5  92%
6  93%
7  90%

#!/bin/sh

# @(#) s1       Demonstrate context splitting, pasting, adjusting columns.

set -o nounset
echo
echo "GNU bash $BASH_VERSION" >&2
csplit --version | head -1 >&2
echo

FILE=${1-data1}
csplit -k -z $FILE /^test_data/ "{*}"

echo
echo " Lines per file:"
wc -l xx*

echo
paste xx* |
column -s"      " -t
# Note: there is a TAB inside -s" ".

exit 0

% ./s1

GNU bash 2.05b.0(1)-release
csplit (coreutils) 5.2.1

76
76
54

 Lines per file:
  6 xx00
  6 xx01
  7 xx02
 19 total

test_data_1                test_data_2                test_data_9
1  2  90%                  3  5  92%                  2  95%
4  3  91%                  5  4  92%                  3  94%
5  4  90%                  7  3  93%                  4  91%
6  5  90%                  9  2  92%                  5  92%
9  6  90%                  1  1  92%                  6  93%
7  90%

#!/bin/sh

# Exit if any variable is not set.
set -o nounset

# Input file:
DATA_FILE=${1}
echo "Data File: "$DATA_FILE

# Dataset Header Prefix.
HEADER_PREFIX=${2}
echo "Header Prefix: "$HEADER_PREFIX

# Make columns from space-delimited file.
# -e indicates a command, several of which can be included in one
# sed call. s indicates the string to search for, which is prefixed
# by '/'. The replacement string is prefixed by the second '/' and
# closed with a final '/'.
# Following the list of commands is the input file.
# ' > $DATA_FILE.temp" directs the output to an output file,
# in this case with '.temp' added to the filename.
# This file is removed when the script finishes. In this
# script, the 's/[[ ]]*/\t/' is finding all spaces and replacing them
# with TAB (\t). The 's/$HEADER_PREFIX\S*/&\t\t/' is finding all strings beginning
# with '$HEADER_PREFIX' and appending two tabs after each occurrence.
# Oh, and the 'g' tells sed to replace all occurrences, not just the first occurrence
# per line, which is the default behavior.
sed -e 's/[[ ]]*/\t/g' -e 's/$HEADER_PREFIX\S*/&\t\t/' $DATA_FILE > $DATA_FILE.temp

# Cut datasets from input file into separate temporary files, named as xx##.
# The '-k' option leaves the temp files in place in the case of an error.
# The '-s' option silences the default byte counts that csplit offers.
# The '-z' option deletes any output files that are empty.
# csplit cuts the data sets based on the search string, in this case:
# whatever you put as the second argument to the script.
csplit -k -s -z $DATA_FILE.temp /^$HEADER_PREFIX/ "{*}"

# Paste temporary files into output, piped through 'column' to create columns.
# NOTE: there is a TAB inside -s" ".
# The 'paste' command pastes multiple files into one, with the contents of all files side by side.
paste xx* | column -s"      " -t > $DATA_FILE.out

#Remove the temporary files.
rm xx*
rm $DATA_FILE.temp

# Exit
exit 0