form_of fixed

This commit is contained in:
Andrzej Stepien 2023-08-02 16:03:57 +02:00
parent 4f1e3228b1
commit 7a0524e56a
1 changed files with 2 additions and 2 deletions

View File

@ -1,10 +1,10 @@
#!/bin/bash #!/bin/bash
cd ../processing 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(" ")))}' \ 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({definition: .glosses|join(" "), form_of: (.form_of!=null)}))}' \
wiktionary.json > wiktionary-p1.json wiktionary.json > wiktionary-p1.json
jq --slurp '. | group_by(.word)[] | {word:.[0].word, pronunciation:.[0].pronunciation, meanings:[.[]|{type:.type, form_of:(try .form_of), definitions:[try .definitions[]]| select(.!=[]) |map({(.):1})|add|keys_unsorted}]}' \ jq --slurp '. | group_by(.word)[] | {word:.[0].word, pronunciation:.[0].pronunciation, meanings:([.[]|{type:.type, definitions:[try .definitions][]}] |group_by(.type)|[{type: .[][0].type, definitions:[.[][].definitions[]] }] )}' \
wiktionary-p1.json > wiktionary-p2.json wiktionary-p1.json > wiktionary-p2.json
jq --slurp '.' wiktionary-p2.json > wiktionary-p3.json jq --slurp '.' wiktionary-p2.json > wiktionary-p3.json