Created
August 6, 2015 14:33
-
-
Save jmealo/103411148300ade619b5 to your computer and use it in GitHub Desktop.
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 | |
cd /usr/share/postgresql/9.4/tsearch_data | |
wget https://stop-words.googlecode.com/files/stop-words-collection-2011.11.21.zip | |
unzip stop-words-collection-2011.11.21.zip | |
wget http://src.chromium.org/svn/trunk/deps/third_party/hunspell_dictionaries/en_US.dic | |
wget http://src.chromium.org/svn/trunk/deps/third_party/hunspell_dictionaries/en_US.dic_delta | |
wget http://src.chromium.org/svn/trunk/deps/third_party/hunspell_dictionaries/en_US.aff -O en_us.affix | |
# Remove first line | |
sed -i 1d en_US.dic | |
# Concat the dic and dic_delta, sort alphabetically and remove the leading blank line (leaves the ending newline intact) | |
cat en_US.dic en_US.dic_delta | sort > en_us.dict | |
sed -i 1d en_us.dict | |
cat stop-words/stop-words-english3-google.txt english.stop | sort | uniq -u > english.stop | |
# clean up | |
rm -rf stop-words-collection-2011.11.21.zip stop-words rm project-information.txt en_US* | |
chown -R postgres:postgres * | |
sudo -u postgres psql -c "CREATE TEXT SEARCH DICTIONARY ispell_en_us (template = ispell, dictfile = en_us, afffile = en_us, stopwords = english);" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment