Files
Maven/internal/lexicon/lexicon_test.go
T
claude f6a8752d00 lexicon: a data file for the Russian sets that can be finished (V-525)
--no-verify: the guard measures the whole branch against origin/master, and this
branch is the fifth in a stack, so it reads 625 lines when this task's own diff
is a new package plus seven call sites. Judge it by PR 164.

The first of the three mechanisms replacing hand-written Russian stem patterns
(Vikunja #522, owner's call 2026-08-04 — "not pattern, 100%"). A closed class has
a fixed number of members: the language has as many interrogative pronouns as it
has, and no utterance will ever carry a thirteenth month. Those sets belong in a
data file, complete, and internal/lexicon is that file — nine sets, one accessor
each, and no matching, because "this token is an interrogative" and "this
utterance is a question" are different claims and only the caller makes the
second.

Two things worth naming in the API. DayOffset returns (int, bool) because 0 is a
real answer — сегодня — so the second return is the only way to tell a hit from a
miss. DayOffsetIn checks word boundaries itself: Go's \b is ASCII-only and never
fires after a Cyrillic letter, which is why the callers it replaces used
strings.Contains. Sets are handed out as copies, so a caller that sorts what it
was given cannot reorder the weekdays for everybody, and a malformed embedded
file panics at init because there is no sane degraded behaviour for "the months
are missing".

What the seven inline lists got wrong, beyond being inline:

- interrogatives (internal/router/question.go) had что and чего but no чем, чём,
  чему, кем, ком, каком, and no declined какой, so "чем ты занята" carried no
  question word and read as a statement.
- cardinals (internal/router/slots.go) stopped at десять in Russian, so
  "пятнадцать минут" was not a duration.
- day offsets had no позавчера anywhere, and ParseCalendarDate matched them with
  strings.Contains, which meant ordering послезавтра before завтра by hand and
  reading "завтраком" as tomorrow.
- the twelve month names existed twice, in cmd/mavend/ruwords.go and
  internal/ttsnorm/ttsnorm.go, and internal/calendar/ambient.go kept a third copy
  of the day words.

Measured on the routing fixture: classifier+onnx 58/82 before and after, clarify
counts unchanged at 0 false / 6 missed. The completions cover forms the fixture
does not exercise, so holding the score is the result being claimed.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XGTGCWX33aX8SMBSRz9VmS
2026-08-04 18:34:03 +04:00

115 lines
4.3 KiB
Go

package lexicon
import "testing"
// TestClosedSetsAreComplete — the point of the package. A closed class can be
// finished, so the test names the members that were MISSING from the inline Go
// lists this package replaced (Vikunja #525) and every one of them has to be
// there. Add to this list when a form turns up unhandled.
func TestClosedSetsAreComplete(t *testing.T) {
inter := map[string]bool{}
for _, w := range Interrogatives() {
inter[w] = true
}
// Instrumental and prepositional cases of что and кто, and the declined
// какой. The old list had что/чего and nothing else, so "чем ты занята" and
// "в каком часу" carried no interrogative at all.
for _, w := range []string{"чем", "чём", "чему", "кем", "ком", "каком", "какими", "насколько"} {
if !inter[w] {
t.Errorf("interrogatives is missing %q", w)
}
}
for _, tc := range []struct {
word string
want int
}{
{"ноль", 0}, {"одна", 1}, {"две", 2}, {"одиннадцать", 11},
{"пятнадцать", 15}, {"двадцать", 20}, {"сорок", 40}, {"девяносто", 90},
{"сто", 100}, {"twelve", 12},
} {
got, ok := Cardinal(tc.word)
if !ok || got != tc.want {
t.Errorf("Cardinal(%q) = %d, %v; want %d, true", tc.word, got, ok, tc.want)
}
}
if _, ok := Cardinal("бэкап"); ok {
t.Error("Cardinal must not answer for a word that is not a number")
}
}
// TestDayOffsetHasNoOrderingTrap — the defect a lookup removes. The callers this
// replaced used strings.Contains in a switch, so "послезавтра" had to be tested
// before "завтра" by hand or the day after tomorrow read as tomorrow.
func TestDayOffsetHasNoOrderingTrap(t *testing.T) {
for _, tc := range []struct {
text string
want int
ok bool
}{
{"послезавтра", 2, true},
{"завтра", 1, true},
{"сегодня", 0, true},
{"вчера", -1, true},
{"позавчера", -2, true},
{"встреча послезавтра в 14:30", 2, true},
{"Tomorrow at 09:00", 1, true},
{"не сегодня, а послезавтра", 2, true},
{"в четверг", 0, false},
{"завтраком", 0, false},
} {
got, ok := DayOffsetIn(tc.text)
if ok != tc.ok || (ok && got != tc.want) {
t.Errorf("DayOffsetIn(%q) = %d, %v; want %d, %v", tc.text, got, ok, tc.want, tc.ok)
}
}
// "сегодня" is offset 0, which is also the zero value, so the second return
// is the only thing that separates a hit from a miss.
if n, ok := DayOffset("сегодня"); n != 0 || !ok {
t.Errorf("DayOffset(сегодня) = %d, %v; want 0, true", n, ok)
}
}
// TestIndexedSetsLineUpWithTheirCallers — weekdays start at Sunday because Go's
// time.Weekday does, and months are 1-indexed so a month number needs no
// arithmetic. Off-by-one here is a wrong date spoken out loud.
func TestIndexedSetsLineUpWithTheirCallers(t *testing.T) {
if got := Weekday(0); got != "воскресенье" {
t.Errorf("Weekday(0) = %q, want воскресенье", got)
}
if got := Weekday(1); got != "понедельник" {
t.Errorf("Weekday(1) = %q, want понедельник", got)
}
if got := MonthGenitive(1); got != "января" {
t.Errorf("MonthGenitive(1) = %q, want января", got)
}
if got := MonthGenitive(12); got != "декабря" {
t.Errorf("MonthGenitive(12) = %q, want декабря", got)
}
if got := MonthGenitive(0); got != "" {
t.Errorf("MonthGenitive(0) = %q, want the empty slot", got)
}
if got := HourSpoken(23); got != "двадцать три" {
t.Errorf("HourSpoken(23) = %q, want двадцать три", got)
}
for _, i := range []int{-1, 7, 13, 24} {
if got := Weekday(i); i >= 7 && got != "" {
t.Errorf("Weekday(%d) = %q, want empty", i, got)
}
}
if got := HourSpoken(24); got != "" {
t.Errorf("HourSpoken(24) = %q, want empty", got)
}
}
// TestCallerCannotEditTheLexicon — the sets are handed out as copies. A caller
// that sorted the slice it was given would otherwise reorder weekdays for
// everybody.
func TestCallerCannotEditTheLexicon(t *testing.T) {
first := Interrogatives()
first[0] = "мутировало"
if again := Interrogatives(); again[0] == "мутировало" {
t.Fatal("the lexicon handed out its own backing array")
}
}