extra samples

This commit is contained in:
Andrzej Stepien 2023-07-19 15:25:35 +02:00
parent 7281e50aad
commit 379c1b0b77
1 changed files with 7 additions and 6 deletions

View File

@ -1,13 +1,13 @@
#!/bin/bash
cd ../processing
#jq -r '. | select((.pos=="noun") or (.pos=="verb") or (.pos=="adj") or (.pos=="adv")) | select((.word | test("[^a-z]"))|not) | {word: .word, type: .pos, pronunciation: .sounds[0].ipa, definitions: (try .senses|map(.glosses|join(" ")))}' \
#wiktionary.json > wiktionary-p1.json
jq -r '. | select((.pos=="noun") or (.pos=="verb") or (.pos=="adj") or (.pos=="adv")) | select((.word | test("[^a-z]"))|not) | {word: .word, type: .pos, pronunciation: .sounds[0].ipa, definitions: (try .senses|map(.glosses|join(" ")))}' \
wiktionary.json > wiktionary-p1.json
#jq --slurp '. | group_by(.word)[] | {word:.[0].word, pronunciation:.[0].pronunciation, meanings:[.[]|{type:.type, definitions:[try .definitions[]]| select(.!=[]) |map({(.):1})|add|keys_unsorted}]}' \
#wiktionary-p1.json > wiktionary-p2.json
jq --slurp '. | group_by(.word)[] | {word:.[0].word, pronunciation:.[0].pronunciation, meanings:[.[]|{type:.type, definitions:[try .definitions[]]| select(.!=[]) |map({(.):1})|add|keys_unsorted}]}' \
wiktionary-p1.json > wiktionary-p2.json
#jq --slurp '.' wiktionary-p2.json > wiktionary-p3.json
jq --slurp '.' wiktionary-p2.json > wiktionary-p3.json
#extract samples
timestamp=$(date +%s)
@ -16,4 +16,5 @@ jsonl=wiktionary-p2.json
jq '. | select(.word=="write")' $jsonl > ../samples/write-$timestamp.json
jq '. | select(.word=="terrible")' $jsonl > ../samples/terrible-$timestamp.json
jq '. | select(.word=="look")' $jsonl > ../samples/look-$timestamp.json
jq '. | select(.word=="looks")' $jsonl > ../samples/looks-$timestamp.json
jq '. | select(.word=="edges")' $jsonl > ../samples/edges-$timestamp.json