From e0289735068ffcd6042b1ccebd6903b96341afbf Mon Sep 17 00:00:00 2001 From: Andrzej Stepien Date: Wed, 2 Aug 2023 16:25:34 +0200 Subject: [PATCH] preserve order of wordtypes --- 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 a5d8446..2ebac2f 100755 --- a/src/data/scripts/pipeline.sh +++ b/src/data/scripts/pipeline.sh @@ -4,7 +4,7 @@ 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({definition: .glosses|join(" "), form_of: (.form_of!=null)}))}' \ wiktionary.json > wiktionary-p1.json -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[]] }] )}' \ +jq --slurp '. | group_by(.word)[] | {word:.[0].word, pronunciation:.[0].pronunciation, meanings:([.[]|{type:.type, definitions:[try .definitions][]}] )}' \ wiktionary-p1.json > wiktionary-p2.json jq --slurp '.' wiktionary-p2.json > wiktionary-p3.json