diff --git a/devtools/adj_minip.sh b/devtools/adj_minip.sh index 20d5cc001..bb375e0cb 100755 --- a/devtools/adj_minip.sh +++ b/devtools/adj_minip.sh @@ -15,7 +15,7 @@ GTLANGS=$(echo $GTLANGS) PATTERN=$1 L_FILE="in.txt" -cut -d '!' -f1 src/fst/stems/adjectives.lexc | egrep $PATTERN | sed 's/% /%/g' | tr ' +' ':' | cut -d ':' -f1 | sed 's/%/% /g' | tr -d '%'>$L_FILE +cut -d '!' -f1 src/fst/morphology/stems/adjectives.lexc | egrep $PATTERN | sed 's/% /%/g' | tr ' +' ':' | cut -d ':' -f1 | sed 's/%/% /g' | tr -d '%'>$L_FILE P_FILE="test/data/testadjparadigm.txt" diff --git a/devtools/check-missing.sh b/devtools/check-missing.sh index 0348712ed..2225c74ef 100755 --- a/devtools/check-missing.sh +++ b/devtools/check-missing.sh @@ -25,8 +25,8 @@ cat $MISSING | awk '{print ("^" $1 ":")}' > $FILTER echo "" echo '#### STEMS:' -egrep --color -f $FILTER src/fst/stems/${TYPE}.lexc +egrep --color -f $FILTER src/fst/morphology/stems/${TYPE}.lexc echo "" echo '#### CONTINUATION LEXICA:' -egrep -f $FILTER src/fst/stems/${TYPE}.lexc | awk '{print $2}' | sort | uniq -c | sort -nr --key=1,1 +egrep -f $FILTER src/fst/morphology/stems/${TYPE}.lexc | awk '{print $2}' | sort | uniq -c | sort -nr --key=1,1 diff --git a/devtools/noun_minip.sh b/devtools/noun_minip.sh index 2a48607c9..b088c296c 100755 --- a/devtools/noun_minip.sh +++ b/devtools/noun_minip.sh @@ -17,7 +17,7 @@ GTLANGS=$(echo $GTLANGS) PATTERN=$1 L_FILE="in.txt" -cut -d '!' -f1 src/fst/stems/nouns.lexc | egrep $PATTERN | sed 's/% /%/g' | tr ' +' ':' | cut -d ':' -f1 | sed 's/%/% /g' | tr -d '%'>$L_FILE +cut -d '!' -f1 src/fst/morphology/stems/nouns.lexc | egrep $PATTERN | sed 's/% /%/g' | tr ' +' ':' | cut -d ':' -f1 | sed 's/%/% /g' | tr -d '%'>$L_FILE P_FILE="test/data/testnounpradigm.txt" diff --git a/devtools/numerals_minip.sh b/devtools/numerals_minip.sh index fc54741dc..dfca50c3e 100755 --- a/devtools/numerals_minip.sh +++ b/devtools/numerals_minip.sh @@ -17,7 +17,7 @@ GTLANGS=$(echo $GTLANGS) PATTERN=$1 L_FILE="in.txt" -cut -d '!' -f1 src/fst/stems/numerals.lexc | egrep $PATTERN | sed 's/% /%/g' | tr ' +' ':' | cut -d ':' -f1 | sed 's/%/% /g' | tr -d '%'>$L_FILE +cut -d '!' -f1 src/fst/morphology/stems/numerals.lexc | egrep $PATTERN | sed 's/% /%/g' | tr ' +' ':' | cut -d ':' -f1 | sed 's/%/% /g' | tr -d '%'>$L_FILE P_FILE="test/data/testnumeralpradigm.txt" diff --git a/devtools/ord_minip.sh b/devtools/ord_minip.sh index a18fab52d..e713ffe88 100755 --- a/devtools/ord_minip.sh +++ b/devtools/ord_minip.sh @@ -15,7 +15,7 @@ GTLANGS=$(echo $GTLANGS) PATTERN=$1 L_FILE="in.txt" -cut -d '!' -f1 src/fst/stems/numerals.lexc | egrep $PATTERN | sed 's/% /%/g' | tr ' +' ':' | cut -d ':' -f1 | sed 's/%/% /g' | tr -d '%'>$L_FILE +cut -d '!' -f1 src/fst/morphology/stems/numerals.lexc | egrep $PATTERN | sed 's/% /%/g' | tr ' +' ':' | cut -d ':' -f1 | sed 's/%/% /g' | tr -d '%'>$L_FILE P_FILE="test/data/testordparadigm.txt" diff --git a/devtools/prop_minip.sh b/devtools/prop_minip.sh index 476eb4f25..88ac4f70a 100755 --- a/devtools/prop_minip.sh +++ b/devtools/prop_minip.sh @@ -10,7 +10,7 @@ PATTERN=$1 L_FILE="in.txt" -cut -d '!' -f1 src/fst/stems/propernouns.lexc | grep $PATTERN | sed 's/% /%/g' | tr ' +' ':' | cut -d ':' -f1 | sed 's/%/% /g' | tr -d '%'>$L_FILE +cut -d '!' -f1 src/fst/morphology/stems/propernouns.lexc | grep $PATTERN | sed 's/% /%/g' | tr ' +' ':' | cut -d ':' -f1 | sed 's/%/% /g' | tr -d '%'>$L_FILE P_FILE="test/data/testpropparadigm.txt" diff --git a/devtools/qu_minip.sh b/devtools/qu_minip.sh index ac0caf4af..0ed7c3166 100644 --- a/devtools/qu_minip.sh +++ b/devtools/qu_minip.sh @@ -10,7 +10,7 @@ PATTERN=$1 L_FILE="in.txt" -cut -d '!' -f1 src/fst/stems/pronouns.lexc | grep $PATTERN | sed 's/% /%/g' | tr ' +' ':' | cut -d ':' -f1 | sed 's/%/% /g' | tr -d '%'>$L_FILE +cut -d '!' -f1 src/fst/morphology/stems/pronouns.lexc | grep $PATTERN | sed 's/% /%/g' | tr ' +' ':' | cut -d ':' -f1 | sed 's/%/% /g' | tr -d '%'>$L_FILE P_FILE="test/data/testquparadigm.txt" diff --git a/devtools/tag_test.sh b/devtools/tag_test.sh index b1821053d..d9610b25b 100755 --- a/devtools/tag_test.sh +++ b/devtools/tag_test.sh @@ -1,7 +1,7 @@ #shell script to see if there are tags which are not declared in root.lexc or if tags are misspelled echo 'Are there tags not declared in root.lexc or misspelled?' -cat src/fst/clitics.lexc src/fst/compounding.lexc src/fst/affixes/*lexc src/fst/stems/*lexc ../shared-smi/src/fst/stems/*lexc |cut -d '!' -f1 |grep ' ;' | cut -d ':' -f1 |rev |cut -d ' ' -f1 |rev |sed 's/+/¢+/g' |sed 's/@/¢@/g'|tr '¢' '\n' | tr '#"' '\n'| egrep '(\+|@)' |sort -u | egrep -v '^(\+|\+%|\+\/\-|\+Cmp\-|\+Cmp%\-|\@0|\@%)$' > lexctags +cat src/fst/clitics.lexc src/fst/compounding.lexc src/fst/morphology/affixes/*lexc src/fst/morphology/stems/*lexc ../shared-smi/src/fst/morphology/stems/*lexc |cut -d '!' -f1 |grep ' ;' | cut -d ':' -f1 |rev |cut -d ' ' -f1 |rev |sed 's/+/¢+/g' |sed 's/@/¢@/g'|tr '¢' '\n' | tr '#"' '\n'| egrep '(\+|@)' |sort -u | egrep -v '^(\+|\+%|\+\/\-|\+Cmp\-|\+Cmp%\-|\@0|\@%)$' > lexctags cat src/fst/root.lexc |cut -d '!' -f1 |cut -d ':' -f1 |sed 's/+/¢+/g'|sed 's/@/¢@/g' |tr '¢' '\n' | egrep '(\+|@)' |tr -d ' ' | tr -d '\t'|sort -u > roottags @@ -10,13 +10,13 @@ echo 'Have a look at these:' comm -23 lexctags roottags echo 'Checking for double semicolon in stem files:' -cat src/fst/stems/*lexc |cut -d '!' -f1 |grep ';.*;' +cat src/fst/morphology/stems/*lexc |cut -d '!' -f1 |grep ';.*;' echo 'Checking for missing Der-tags:' -cat src/fst/stems/*lexc |cut -d '!' -f1 |grep '\+Der/.*;' |egrep -v 'Der([1234]|\+)' +cat src/fst/morphology/stems/*lexc |cut -d '!' -f1 |grep '\+Der/.*;' |egrep -v 'Der([1234]|\+)' echo 'Checking for double Sem-tags:' -cat src/fst/stems/*lexc |cut -d '!' -f1 |grep '+Sem.*+Sem' +cat src/fst/morphology/stems/*lexc |cut -d '!' -f1 |grep '+Sem.*+Sem' echo 'checked' #rm lexctags roottags diff --git a/devtools/verb_minip.sh b/devtools/verb_minip.sh index fdd44ac34..f1957cf1c 100755 --- a/devtools/verb_minip.sh +++ b/devtools/verb_minip.sh @@ -13,7 +13,7 @@ GTLANGS=$(echo $GTLANGS) PATTERN=$1 L_FILE="in.txt" -cut -d '!' -f1 src/fst/stems/verbs.lexc | egrep $PATTERN | sed 's/% /%/g' | tr ' +' ':' | cut -d ':' -f1 | sed 's/%/% /g' | tr -d '%'>$L_FILE +cut -d '!' -f1 src/fst/morphology/stems/verbs.lexc | egrep $PATTERN | sed 's/% /%/g' | tr ' +' ':' | cut -d ':' -f1 | sed 's/%/% /g' | tr -d '%'>$L_FILE P_FILE="test/data/testverbparadigm.txt"