#!/bin/bash

export LANG="sv_SE.UTF-8"
export LC_CTYPE="sv_SE.UTF-8"
export LC_NUMERIC="sv_SE.UTF-8"
export LC_TIME="sv_SE.UTF-8"
export LC_COLLATE="sv_SE.UTF-8"
export LC_MONETARY="sv_SE.UTF-8"
export LC_MESSAGES="sv_SE.UTF-8"
export LC_PAPER="sv_SE.UTF-8"
export LC_NAME="sv_SE.UTF-8"
export LC_ADDRESS="sv_SE.UTF-8"
export LC_TELEPHONE="sv_SE.UTF-8"
export LC_MEASUREMENT="sv_SE.UTF-8"
export LC_IDENTIFICATION="sv_SE.UTF-8"
export LC_ALL="sv_SE.UTF-8"


cat SIMPLEv_SE_2009.txt | awk 'BEGIN {FS = "\t"; OFS = "\t"} { $14 = "-"; $15 = "-"; $16 = "vb"; print }' > "simple_processed_verbs.txt"
cat SIMPLEn_SE_2009.txt | awk 'BEGIN {FS = "\t"; OFS = "\t"} { $14 = $10; $15 = $13; $13 = $12; $12 = $11; $10 = "-"; $11 = "-"; $16 = "nn"; print}' > "simple_processed_nouns.txt"
cat SIMPLEadj_SE_2009.txt | awk 'BEGIN {FS = "\t"; OFS = "\t"} { $13 = $10; $10 = "-"; $11 = "-"; $12 = "-"; $14 = "-"; $15 = "-"; $16 = "av"; print}' > "simple_processed_adjs.txt"
cat simple_processed_verbs.txt simple_processed_nouns.txt simple_processed_adjs.txt
# | ./skript/lmf_med_swefn.py simple | tidy -xml -utf8 -i
#cat simple_processed_verbs.txt simple_processed_nouns.txt simple_processed_adjs.txt | ./skript/pid_to_sid.py