lingdocs
/
pashto-grammar
mirror of https://github.com/lingdocs/pashto-grammar.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

cleaner get-words

This commit is contained in:
adueck 2022-11-02 11:08:24 +05:00
parent f249555eac
commit 35a984a2b2
3 changed files with 20 additions and 53 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@ -1,5 +1,7 @@
# See https://help.github.com/articles/ignoring-files/ for more about ignoring files. # See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
/src/words/raw-words.ts
# dependencies # dependencies
/node_modules /node_modules
/.pnp /.pnp

67
scripts/get-words.js
View File

@ -24,60 +24,29 @@ const allAdverbTsS = adverbTsFiles.flatMap(fileName => [
...require(path.join("..", adverbCollectionPath, fileName)) ...require(path.join("..", adverbCollectionPath, fileName))
]).filter((v, i, a) => a.findIndex(x => x === v) === i); ]).filter((v, i, a) => a.findIndex(x => x === v) === i);
const allTs = [...allVerbTsS, ...allAdverbTsS, ...allNounAdjTsS];
console.log("getting words from dictionary..."); console.log("getting words from dictionary...");
fetch(process.env.LINGDOCS_DICTIONARY_URL + ".json").then(res => res.json()).then(data => { fetch("https://account.lingdocs.com/dictionary/entries", {
const { entries } = data; method: "POST",
// MAKE VERBS FILE headers: {
const allWords = [ "Content-Type": "application/json",
...getVerbsFromTsS(entries), },
...getNounsAdjsFromTsS(entries), body: JSON.stringify({ ids: allTs }),
]; }).then(res => res.json()).then(data => {
const content = ` const content = `
// @ts-ignore // @ts-ignore
const words: Word[] = ${JSON.stringify(allWords)}; const words: Word[] = ${JSON.stringify(data.results)};
export default words;`; export default words;`;
fs.writeFileSync(path.join(wordsPath, wordsFile), content); fs.writeFileSync(path.join(wordsPath, wordsFile), content);
const missingEc = data.results.filter(x => "entry" in x && !x.entry.ec);
if (missingEc.length) {
console.log("verbs missing ec");
console.log(missingEc);
}
if (data.notFound.length) {
console.log("entries not found:");
console.log(data.notFound);
}
}); });
function getVerbsFromTsS(entries) {
const missingEc = [];
const toReturn = allVerbTsS.map(ts => {
const entry = entries.find(x => ts === x.ts);
if (!entry) {
console.log("couldn't find ts", ts);
return undefined;
}
if (!entry.ec) {
missingEc.push(entry.ts);
}
if (entry.c && entry.c.includes("comp.")) {
const complement = entries.find(x => entry.l === x.ts);
return {
entry,
complement,
};
}
return { entry };
}).filter(x => x);
if (missingEc.length !== 0) {
console.log("Verbs missing ec:", missingEc);
}
return toReturn;
}
function getNounsAdjsFromTsS(entries) {
const b = [...allNounAdjTsS, ...allAdverbTsS].map(ts => {
const entry = entries.find(x => ts === x.ts);
if (!entry) {
console.log("couldn't find ts", ts);
return undefined;
}
// const firstWord = entry.e.split(",")[0].split(";")[0].split("(")[0].trim();
// console.log(firstWord, entry.f, entry.ts);
// if (firstWord.contains(" ")) console.log("SPACE PRESENT");
return entry;
}).filter(x => x);
return b;
// console.log(b.length, "number of nouns/adjs");
}

4
src/words/raw-words.ts
View File

File diff suppressed because one or more lines are too long