andrzej
/
micro365
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

added 'form_of' boolean field

This commit is contained in:
Andrzej Stepien 2023-08-02 11:43:25 +02:00
parent 379c1b0b77
commit 106103b9ad
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/data/scripts/pipeline.sh
View File

@ -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}]}' \