Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

refactor(utils.py): move language data to JSON file (resolves #52) #54

Merged
merged 1 commit into from
Oct 30, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Empty file.
128 changes: 128 additions & 0 deletions src/scribe_data/resources/language_meta_data.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,128 @@
{
"used by": "Scribe-Data/src/scribe_data/utils.py",
"description": {
"entry": {
"language": "the supported language. All lowercase",
"iso": "the ISO 639 code for 'language'. See https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes . All lowercase",
"qid": "the unique identifier of 'language' on Wikidata. 'Q' followed by one or more digits. See https://www.wikidata.org/wiki/Q43649390",
"remove-words": "words that should not be included as autosuggestions for the given language.",
"ignore-words": "TODO. Case sensitive."
}
},
"languages": [
{
"language": "english",
"iso": "en",
"qid": "Q1860",
"remove-words": [
"of",
"the",
"The",
"and"
],
"ignore-words": []
},
{
"language": "french",
"iso": "fr",
"qid": "Q150",
"remove-words": [
"of",
"the",
"The",
"and"
],
"ignore-words": [
"XXe"
]
},
{
"language": "german",
"iso": "de",
"qid": "Q188",
"remove-words": [
"of",
"the",
"The",
"and",
"NeinJa",
"et",
"redirect"
],
"ignore-words": [
"Gemeinde",
"Familienname"
]
},
{
"language": "italian",
"iso": "it",
"qid": "Q652",
"remove-words": [
"of",
"the",
"The",
"and",
"text",
"from"
],
"ignore-words": [
"The",
"ATP"
]
},
{
"language": "portuguese",
"iso": "pt",
"qid": "Q5146",
"remove-words": [
"of",
"the",
"The",
"and",
"jbutadptflora"
],
"ignore-words": []
},
{
"language": "russian",
"iso": "ru",
"qid": "Q7737",
"remove-words": [
"of",
"the",
"The",
"and"
],
"ignore-words": []
},
{
"language": "spanish",
"iso": "es",
"qid": "Q1321",
"remove-words": [
"of",
"the",
"The",
"and"
],
"ignore-words": []
},
{
"language": "swedish",
"iso": "sv",
"qid": "Q9027",
"remove-words": [
"of",
"the",
"The",
"and",
"Checklist",
"Catalogue"
],
"ignore-words": [
"databasdump"
]
}
]
}
Loading