Last active
August 29, 2015 14:27
-
-
Save bheeshmar/6733b384e60336a0d148 to your computer and use it in GitHub Desktop.
Word splitter solution in bash
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 | |
# call with ./splitwords.bash thisisawesome | |
find_substrings() { | |
local remainder=$1 | |
matched=$2 | |
# echo "in find_substrings '${remainder}' (${matched[@]})" | |
if [[ -z $remainder ]]; then | |
echo "Found: ${matched[@]}" | |
exit 0 | |
fi | |
for sub in ${sorted_subwords[@]}; do | |
local subl=$sub | |
local prefix_removed=${remainder#$subl} | |
# echo "sub: '${subl}' prefix_removed: '${prefix_removed}' remainder: '${remainder}'" | |
if [[ $remainder = $prefix_removed ]]; then | |
# echo "${remainder} does not start with ${subl}" | |
: | |
else | |
matched=("${matched[@]}" "${subl}") | |
# echo "calling find_substrings with '${prefix_removed}' (${matched[@]})" | |
find_substrings $prefix_removed $matched | |
fi | |
done | |
} | |
to_split=$1 | |
letter_filter=$(echo ${to_split}| grep -o . | sort -u | paste -s -d '\0' -) | |
grep -w -e "[${letter_filter}]\+" /usr/share/dict/words > /tmp/words_with_matching_letters | |
while read w; do | |
[[ ${to_split} =~ $w ]] && echo ${BASH_REMATCH} | |
done </tmp/words_with_matching_letters >/tmp/possible_subwords | |
subwords=($(</tmp/possible_subwords)) | |
IFS=$'\n' GLOBIGNORE='*' sorted_subwords=($(printf '%s\n' ${subwords[@]} | awk '{ print length($0) " " $0; }' | sort -nr | cut -d ' ' -f 2-)) | |
echo ${sorted_subwords[@]} | |
declare -a matched_words | |
find_substrings ${to_split} $matched_words |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment