From 106103b9adf0df39c06ea8c5fe20fc178738dabd Mon Sep 17 00:00:00 2001 From: Andrzej Stepien Date: Wed, 2 Aug 2023 11:43:25 +0200 Subject: [PATCH] added 'form_of' boolean field --- src/data/scripts/pipeline.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/data/scripts/pipeline.sh b/src/data/scripts/pipeline.sh index 655e0c2..3914187 100755 --- a/src/data/scripts/pipeline.sh +++ b/src/data/scripts/pipeline.sh @@ -1,7 +1,7 @@ #!/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(" ")))}' \ +jq -r '. | select((.pos=="noun") or (.pos=="verb") or (.pos=="adj") or (.pos=="adv")) | select((.word | test("[^a-z]"))|not) | {word: .word, form_of: .senses[].tags | any(. == "form-of"), 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}]}' \