Multidiff
Multiff est un algorithme permettant d'analyser les différences entre plusieurs sources.
AUTOMATED INSTALL
- Optional define:
export optMultidiff=<dir>
- Execute :
mkdir -p ~/old &&\
curl https://infocepo.com/wiki/index.php/Special:Export/Multidiff 2>/dev/null |tac |sed -r '0,/'"#"'24cc42#/d' |tac |sed -r '0,/'"#"'24cc42#/d' |sed 's/'"&"'amp;/\&/g;s/'"&"'gt;/>/g;s/'"&"'lt;/</g' >~/old/$$ &&\
bash ~/old/$$ $optMultidiff
code dirDiff.sh
#24cc42#
#!/bin/bash
# diff "<directory>"
# APA 20180712
#ynotopec at gmail.com
#https://github.com/ynotopec/diff-multi
[ $# -gt 1 ] &&exit
[ $# -eq 1 ] &&dirDiff=$1
# initialisation des variables
baseDir="$(realpath "$(dirname $0)"/..)"
cacheFile=/tmp/"$(basename $0)"$$
########### commun algo
rm -rf /tmp/analyse*
[ -z "${dirDiff}" ] &&dirDiff=.
filesList="$(ls -1d ${dirDiff}/*)"
# work dirs
mkdir -p /tmp/analyse$$/files /tmp/analyse$$/diff
# cp files and unzip
echo "${filesList}" |while read fileName ;do
cp -p "${fileName}" /tmp/analyse$$/files/.
done
gunzip /tmp/analyse$$/files/*.gz 2>/dev/null
filesList="$(ls -1d /tmp/analyse$$/files/*)"
## find words
# stat words
echo "${filesList}" |while read fileName ;do
cat "${fileName}" \
|tr -c "[:alnum:]_" "[\n*]" |grep -v "^\s*$" |sort -u
done \
>/tmp/analyse$$/statWords
triggerValue=$(($(ls -1d /tmp/analyse$$/files/* |wc -l) / 2))
# keep vars words
#awk 'NR == FNR {count[$0]++; next}; count[$0] <= '"${triggerValue}" /tmp/analyse$$/statWords /tmp/analyse$$/statWords |sort -u >/tmp/analyse$$/statWords.vars
# replace vars
cp -a /tmp/analyse$$/files /tmp/analyse$$/files.cache
cat /tmp/analyse$$/statWords.vars |while read lineMy ;do sed -i "s#\b${lineMy}\b#\${varMy}#g" /tmp/analyse$$/files.cache/* ;done 2>/dev/null
# comm = /tmp/analyse$$/comm
ls -1d /tmp/analyse$$/files.cache/* |while read fileName ;do
cat "${fileName}" \
|awk '!seen[$0]++'
done \
>/tmp/analyse$$/comm
awk 'NR == FNR {count[$0]++; next}; count[$0] > '"${triggerValue}" /tmp/analyse$$/comm /tmp/analyse$$/comm \
|awk '!seen[$0]++' >/tmp/analyse$$/comm2
mv -f /tmp/analyse$$/comm2 /tmp/analyse$$/comm
# diff = /tmp/analyse$$/diff/
ls -1d /tmp/analyse$$/files.cache/* |while read fileName ;do
( echo "== $(basename "${fileName}") =="
cat "${fileName}"
echo "=== missing ==="
cat /tmp/analyse$$/comm
) >/tmp/analyse$$/tmp
awk 'NR == FNR {count[$0]++; next}; count[$0] == 1' /tmp/analyse$$/tmp /tmp/analyse$$/tmp \
|tee /tmp/analyse$$/diff/"$(basename "${fileName}")"
done
# libère cache
rm -f /tmp/"$(basename $0)"$$*
#24cc42#
Example
== a1 == I made this |
== a2 == I made this |
== a3 == I made this |
== a4 == I made this |
== a5 == I made this |
== a6 == I made this |
== b1 == I made this |
== b2 == I made this |
== b3 == I made this |
== b4 == I made this |
== b5 == I made Ihis |
== b6 == I made this |
Result
== a1 == drifY === missing === drift == a2 == orift === missing === drift == a3 == yode to === missing === code to == a4 == codetto === missing === code to == a5 == mbltiple === missing === multiple == a6 == dBift === missing === drift == a7 == code 5o === missing === code to == a8 == I made thiY === missing === I made this == b1 == betqeen === missing === between == b2 == find tXe === missing === find the == b3 == mustiple === missing === multiple == b4 == mulpiple === missing === multiple == b5 == I made Ihis === missing === I made this == b6 == mEltiple === missing === multiple == b7 == betfeen === missing === between == b8 == systemI === missing === systems == c1 == fiZd the === missing === find the == c2 == I mSde this === missing === I made this == c3 == mu5tiple === missing === multiple == c4 == I maAe this === missing === I made this == c5 == cJde to === missing === code to == c6 == Qystems === missing === systems