scriptoriumadmin/zotero
1
0
Fork 0
mirror of https://github.com/zotero/zotero.git synced 2026-08-28 05:25:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

lexical test fix
Some checks are pending
CI / Test (shard 1) (push) Waiting to run
Details
CI / Test (shard 2) (push) Waiting to run
Details
CI / Test (shard 3) (push) Waiting to run
Details
CI / Test (shard 4) (push) Waiting to run
Details
CI / Utilities Tests (push) Waiting to run
Details
CI / Build, Upload (push) Waiting to run
Details

Browse source
This commit is contained in:
Bogdan Abaev 2026-08-19 09:55:26 -07:00
parent 4f782d83bc
commit 3f79ce4cd3
1 changed files with 19 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
test/tests/lexicalTest.js
View file

@ -238,19 +238,30 @@ describe("Zotero.Lexical", function () {
});
it("should count CJK units against the 2-gram index", async function () {
await addDoc(4, "lexchinese document", '疫情 情控 控制');
let df = unit => Zotero.Lexical.getDocumentFrequency(unit);
assert.equal(await df(
{ type: 'cjk', text: '疫情控制', bigrams: '疫情 情控 控制' }
), 1);
assert.equal(await df({ type: 'cjk', text: '疫情', bigrams: '疫情' }), 1);
let units = {
run: { type: 'cjk', text: '疫情控制', bigrams: '疫情 情控 控制' },
pair: { type: 'cjk', text: '疫情', bigrams: '疫情' },
reversed: { type: 'cjk', text: '控疫', bigrams: '控疫' },
starting: { type: 'cjk', text: '疫', bigrams: null },
ending: { type: 'cjk', text: '制', bigrams: null }
};
// Counts cover every indexed document, so measure what this one
// adds rather than assuming it's the library's only Chinese text
let before = {};
for (let [name, unit] of Object.entries(units)) {
before[name] = await df(unit);
}
await addDoc(4, "lexchinese document", '疫情 情控 控制');
assert.equal(await df(units.run), before.run + 1);
assert.equal(await df(units.pair), before.pair + 1);
// Not adjacent in the document
assert.equal(await df({ type: 'cjk', text: '控疫', bigrams: '控疫' }), 0);
assert.equal(await df(units.reversed), before.reversed);
// A single character approximates by the bigrams it starts...
assert.equal(await df({ type: 'cjk', text: '疫', bigrams: null }), 1);
assert.equal(await df(units.starting), before.starting + 1);
// ...so one that only ever ends a run undercounts -- the
// documented blind spot of the approximation
assert.equal(await df({ type: 'cjk', text: '制', bigrams: null }), 0);
assert.equal(await df(units.ending), before.ending);
});
it("should measure corpus size from the index state", async function () {