mirror of
https://github.com/discourse/discourse-ai.git
synced 2025-07-07 06:52:36 +00:00
2b9a4f9232
A more deterministic way of making sure the LLM detects the correct language (instead of relying on prompt to LLM to ignore it) is to take the cooked and remove unwanted elements. In this commit - we remove quotes, image captions, etc. and only take the remaining text, falling back to the unadulterated cooked - and update prompts related to detection and translation - /152465/12
37 lines
1.2 KiB
Ruby
37 lines
1.2 KiB
Ruby
# frozen_string_literal: true
|
|
|
|
describe DiscourseAi::Translation::PostLocaleDetector do
|
|
describe ".detect_locale" do
|
|
fab!(:post) { Fabricate(:post, cooked: "Hello world", locale: nil) }
|
|
|
|
def language_detector_stub(opts)
|
|
mock = instance_double(DiscourseAi::Translation::LanguageDetector)
|
|
allow(DiscourseAi::Translation::LanguageDetector).to receive(:new).with(
|
|
opts[:text],
|
|
post: opts[:post],
|
|
).and_return(mock)
|
|
allow(mock).to receive(:detect).and_return(opts[:locale])
|
|
end
|
|
|
|
it "returns nil if post is blank" do
|
|
expect(described_class.detect_locale(nil)).to eq(nil)
|
|
end
|
|
|
|
it "updates the post locale with the detected locale" do
|
|
language_detector_stub({ text: post.cooked, locale: "zh_CN", post: })
|
|
expect { described_class.detect_locale(post) }.to change { post.reload.locale }.from(nil).to(
|
|
"zh_CN",
|
|
)
|
|
end
|
|
|
|
it "bypasses validations when updating locale" do
|
|
post.update_column(:cooked, "A")
|
|
|
|
language_detector_stub({ text: post.cooked, locale: "zh_CN", post: })
|
|
|
|
described_class.detect_locale(post)
|
|
expect(post.reload.locale).to eq("zh_CN")
|
|
end
|
|
end
|
|
end
|