Created
November 30, 2011 10:46
-
-
Save ubermuda/1408635 to your computer and use it in GitHub Desktop.
A small shellscript to slice a file into several smaller files
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/bash | |
INPUT_FILE=$1 | |
LINES_PER_FILE=$2 | |
if [ -z $LINES_PER_FILE ]; then | |
LINES_PER_FILE=1000 | |
fi | |
if [ -z $INPUT_FILE ]; then | |
echo "usage: $0 input_file [lines_per_file=1000]" | |
exit 1 | |
fi | |
if [ ! -f $INPUT_FILE ]; then | |
echo "$INPUT_FILE could not be read" | |
exit 1 | |
fi | |
INPUT_LINES=`wc -l $INPUT_FILE | awk '{print $1}'` | |
if [ $INPUT_LINES -lt $LINES_PER_FILE ]; then | |
echo "input files has less than $LINES_PER_FILE lines" | |
exit 0 | |
fi | |
RESULT_FILES=$((($INPUT_LINES / $LINES_PER_FILE) + 1)) | |
echo "slicing $INPUT_FILE into $RESULT_FILES $LINES_PER_FILE lines files " | |
for i in `seq $RESULT_FILES`; do | |
echo "slicing file #$i" | |
tail -n +$((($i - 1) * $LINES_PER_FILE)) $INPUT_FILE | head -n $LINES_PER_FILE > $INPUT_FILE.$i | |
done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment