claude
96d97e8964
A ZIM title carries a leading capital and the utterance does not: /A/фотосинтез is a 404 and /A/Фотосинтез is a 200. TitleCandidates tries the spoken form first, so a title that begins lowercase on purpose keeps its chance. That takes the measurement from four right to five, and the fifth is the one that mattered. "столица Франции" returned "Список столиц Олимпийских игр" and now returns Париж, through a title redirect the ZIM already held. The 2026-08-05 measurement named that case as the one no lexical signal could reach. Retrieval by title reaches it. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_013ptwopxyo3Z2kwFckHkLvN
68 lines
2.8 KiB
Go
68 lines
2.8 KiB
Go
package kiwix
|
|
|
|
import "testing"
|
|
|
|
// The cases the 2026-08-09 measurement turned on, plus the ones a topic must
|
|
// not damage. Each left column returned a wrong article when it was sent whole.
|
|
func TestTopicKeepsTheThingTheQuestionIsAbout(t *testing.T) {
|
|
cases := []struct{ utterance, want string }{
|
|
{"что такое TCP?", "TCP"},
|
|
{"что такое фотосинтез", "фотосинтез"},
|
|
{"кто такой Линус Торвальдс?", "Линус Торвальдс"},
|
|
{"кто написал Войну и мир", "Войну и мир"},
|
|
{"расскажи про битву при Ватерлоо", "битву при Ватерлоо"},
|
|
{"what is photosynthesis", "photosynthesis"},
|
|
// No question word, so there is nothing to drop. The topic is the
|
|
// whole utterance and the search is what it was before.
|
|
{"столица Франции", "столица Франции"},
|
|
{"почему небо голубое", "небо голубое"},
|
|
}
|
|
for _, c := range cases {
|
|
if got := Topic(c.utterance); got != c.want {
|
|
t.Errorf("Topic(%q) = %q, want %q", c.utterance, got, c.want)
|
|
}
|
|
}
|
|
}
|
|
|
|
// A verb only goes when a question word already went. Otherwise "написал
|
|
// отчёт" loses the verb that names what he means.
|
|
func TestTopicDropsAVerbOnlyBehindAQuestionWord(t *testing.T) {
|
|
if got := Topic("написал отчёт"); got != "написал отчёт" {
|
|
t.Errorf("Topic dropped a leading verb with no question word: %q", got)
|
|
}
|
|
}
|
|
|
|
// Question words alone reduce to nothing, and the caller reads that as "no
|
|
// topic" and searches the sentence rather than searching the empty string.
|
|
func TestTopicIsEmptyWhenNothingIsLeft(t *testing.T) {
|
|
for _, q := range []string{"что такое?", "кто?", "почему", "???"} {
|
|
if got := Topic(q); got != "" {
|
|
t.Errorf("Topic(%q) = %q, want empty", q, got)
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestTitlePathEscapesAndUnderscores(t *testing.T) {
|
|
got := TitlePath("wikipedia_ru_all_maxi_2026-02", "Чёрная дыра")
|
|
want := "/content/wikipedia_ru_all_maxi_2026-02/A/%D0%A7%D1%91%D1%80%D0%BD%D0%B0%D1%8F_%D0%B4%D1%8B%D1%80%D0%B0"
|
|
if got != want {
|
|
t.Errorf("TitlePath = %q, want %q", got, want)
|
|
}
|
|
}
|
|
|
|
// A ZIM title carries a leading capital and the utterance does not. The spoken
|
|
// form is still tried first, so a title that begins lowercase on purpose keeps
|
|
// its chance.
|
|
func TestTitleCandidatesTryTheSpokenFormFirst(t *testing.T) {
|
|
got := TitleCandidates("фотосинтез")
|
|
if len(got) != 2 || got[0] != "фотосинтез" || got[1] != "Фотосинтез" {
|
|
t.Errorf("TitleCandidates = %q", got)
|
|
}
|
|
if got := TitleCandidates("TCP"); len(got) != 1 || got[0] != "TCP" {
|
|
t.Errorf("an already-capital topic was tried twice: %q", got)
|
|
}
|
|
if got := TitleCandidates(""); got != nil {
|
|
t.Errorf("TitleCandidates(\"\") = %q, want nil", got)
|
|
}
|
|
}
|