utils.txt

# Some spot checks to make sure only publicly available data go through the database pipeline.
select * from sessions where corpus not in ("Indonesian", "Japanese_Miyata", "Japanese_MiiPro", "Sesotho")
select * from utterances where corpus not in ("Indonesian", "Japanese_Miyata", "Japanese_MiiPro", "Sesotho")
select * from words where corpus not in ("Indonesian", "Japanese_Miyata", "Japanese_MiiPro", "Sesotho")
select * from morphemes where corpus not in ("Indonesian", "Japanese_Miyata", "Japanese_MiiPro", "Sesotho")
select * from speakers where corpus not in ("Indonesian", "Japanese_Miyata", "Japanese_MiiPro", "Sesotho")
select * from uniquespeakers where corpus not in ("Indonesian", "Japanese_Miyata", "Japanese_MiiPro", "Sesotho")

# Double check csv/ files
grep "Cree" *
grep "Chintang" *
grep "Inuktitut" *
grep "Russian" *
grep "Turkish" *
grep "Yucatec" *

# CSV tables too large for GitHub; split em
split -b 100m words.csv
mv xaa words1.csv
mv xab words2.csv
mv xac words3.csv
mv xad words4.csv

split -b 100m morphemes.csv
mv xaa morphemes1.csv
mv xab morphemes2.csv
mv xac morphemes3.csv
mv xad morphemes4.csv
mv xae morphemes5.csv

split -b 100m utterances.csv
mv xaa utterances1.csv
mv xab utterances2.csv
mv xac utterances3.csv
mv xad utterances4.csv