Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

speed sort up by using 50 % of ram, ice tea 33 #4

Merged
merged 2 commits into from
Oct 23, 2017
Merged

speed sort up by using 50 % of ram, ice tea 33 #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4ff9339
speed sort up by using 50 % of ram, ice tea 33
joernhees Oct 22, 2017
7630925
also add 50 % memory to sort in danker.sh
joernhees Oct 23, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions danker.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,15 +24,15 @@ if [ "$1" == "ALL" ]; then
filename='all.links'
for i in `./lib/getLanguages.sh`; do ./lib/createLinks.sh "$i" >> all-link-files.txt; done
for i in `cat all-link-files.txt`; do cat "$i" >> "$filename"; done
sort --field-separator=$'\t' --key=1 --temporary-directory=. -no "$filename" "$filename"
sort -S 50% --field-separator=$'\t' --key=1 --temporary-directory=. -no "$filename" "$filename"
else
filename=`./lib/createLinks.sh "$1"`
fi
if [ "$2" == "BIGMEM" ]; then
./lib/dankerBigMem.py "$filename" $damping_factor $iterations $start_value | sed "s/\(.*\)/Q\1/" > "$filename".rank
else
sort --field-separator=$'\t' --key=2 --temporary-directory=. -no "$filename"".right" "$filename"
sort -S 50% --field-separator=$'\t' --key=2 --temporary-directory=. -no "$filename"".right" "$filename"
./lib/danker.py "$filename" "$filename"".right" $damping_factor $iterations $start_value | sed "s/\(.*\)/Q\1/" > "$filename".rank
rm "$filename"".right"
fi
sort -nro "$filename"".rank" --field-separator=$'\t' --key=2 "$filename"".rank"
sort -S 50% -nro "$filename"".rank" --field-separator=$'\t' --key=2 "$filename"".rank"
20 changes: 10 additions & 10 deletions lib/createLinks.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ rss="https://dumps.wikimedia.org/""$1""wiki/latest/"

###################### DOWNLOAD AND UNZIP
wget -q "$rss""$1""wiki-latest-pagelinks.sql.gz-rss.xml" "$rss""$1""wiki-latest-page_props.sql.gz-rss.xml" "$rss""$1""wiki-latest-page.sql.gz-rss.xml" "$rss""$1""wiki-latest-redirect.sql.gz-rss.xml"
dump_date=`cat *.xml | sed -n "s#^ <link>$download\(.*\)</link>#\1#p" | sort -u | head -n 1`
dump_date=`cat *.xml | sed -n "s#^ <link>$download\(.*\)</link>#\1#p" | sort -S 50% -u | head -n 1`
rm *.xml
pagelinks="$1""wiki-""$dump_date""-pagelinks.sql"
pageprops="$1""wiki-""$dump_date""-page_props.sql"
Expand All @@ -46,15 +46,15 @@ fi
rm "$1"*.sql
###################### JOINS
export LC_ALL=C
sort --field-separator=$'\t' --key=2 -o "$1""page.lines" "$1""page.lines"
sort --field-separator=$'\t' --key=2 -o "$1""pagelinks.lines" "$1""pagelinks.lines"
sort -S 50% --field-separator=$'\t' --key=2 -o "$1""page.lines" "$1""page.lines"
sort -S 50% --field-separator=$'\t' --key=2 -o "$1""pagelinks.lines" "$1""pagelinks.lines"
join -j 2 "$1""pagelinks.lines" "$1""page.lines" -o 1.1,2.1 -t $'\t' > "$1""pagelinks2.lines"
sort --field-separator=$'\t' --key=2 -o "$1""pagelinks2.lines" "$1""pagelinks2.lines"
sort -S 50% --field-separator=$'\t' --key=2 -o "$1""pagelinks2.lines" "$1""pagelinks2.lines"

# take care of redirects (note: 'double redirects' are fixed by bots --> https://en.wikipedia.org/wiki/Wikipedia:Double_redirects)
sort --field-separator=$'\t' --key=2 -o "$1""redirects.lines" "$1""redirects.lines"
sort -S 50% --field-separator=$'\t' --key=2 -o "$1""redirects.lines" "$1""redirects.lines"
join -j 2 "$1""redirects.lines" "$1""page.lines" -o 2.1,1.1 -t $'\t' > "$1""redirects2.lines"
sort --field-separator=$'\t' --key=2 -o "$1""redirects2.lines" "$1""redirects2.lines"
sort -S 50% --field-separator=$'\t' --key=2 -o "$1""redirects2.lines" "$1""redirects2.lines"
join -j 2 "$1""pagelinks2.lines" "$1""redirects2.lines" -o 1.1,2.1 -t $'\t' > "$1""pagelinks22.lines"

# we can write this back to our page links set (potentially duplicating links)
Expand All @@ -63,11 +63,11 @@ cat "$1""pagelinks22.lines" >> "$1""pagelinks2.lines"
# end redirects

###################### GET Q-IDs
sort --field-separator=$'\t' --key=2 -o "$1""pagelinks2.lines" "$1""pagelinks2.lines"
sort --field-separator=$'\t' --key=2 -o "$1""pageprops.lines" "$1""pageprops.lines"
sort -S 50% --field-separator=$'\t' --key=2 -o "$1""pagelinks2.lines" "$1""pagelinks2.lines"
sort -S 50% --field-separator=$'\t' --key=2 -o "$1""pageprops.lines" "$1""pageprops.lines"
join -j 2 "$1""pagelinks2.lines" "$1""pageprops.lines" -o 2.1,1.1 -t $'\t' > "$1""pagelinks.lines"
sort --field-separator=$'\t' --key=2 -o "$1""pagelinks.lines" "$1""pagelinks.lines"
sort -S 50% --field-separator=$'\t' --key=2 -o "$1""pagelinks.lines" "$1""pagelinks.lines"
join -j 2 "$1""pagelinks.lines" "$1""pageprops.lines" -o 2.1,1.1 -t $'\t' | sed "s/\(Q\|q\)\(.*\)\t\(Q\|q\)\(.*\)/\2\t\4/" > "$1""pagelinks2.lines"
sort "$1""pagelinks2.lines" | uniq > "$1"-"$dump_date"".links"
sort -S 50% -u "$1""pagelinks2.lines" > "$1"-"$dump_date"".links"
rm "$1"*.lines
echo "$1"-"$dump_date"".links"