say, persona, ttsnorm: the clock is spoken and the months have one copy (V-581)

A clock time read aloud now inflects its nouns and drops its leading zeros.
The old rewrite said "часов" for every hour and "минут" for every minute, so
21:00 came out as "21 часов" and 14:00 as "14 часов 00 минут". Russian
inflects a noun after a numeral and internal/say already owns that rule, so
spokenTime calls say.CountWord for both halves and omits the minutes when
there are none. 21:00 is "21 час", 22:02 is "22 часа 2 минуты", 14:00 is
"14 часов".

internal/persona held its own copies of the twelve months and the seven
weekdays. Both are closed classes and both already live in internal/lexicon,
which is where cmd/mavend/ruwords.go sent its copy. The block now reads
lexicon.Weekday and lexicon.MonthGenitive and carries no word list of its own.

LoadSummaries asserted that stall_sitting keeps its two counts and not the two
count words beside them. A variant dropping {word} or {dayword} would have
loaded and spoken a bare number. Both are required now.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
2026-08-06 03:20:10 +04:00
parent 69270f4cfb
commit 8c36e7ef84
4 changed files with 30 additions and 11 deletions
+7 -7
View File
@@ -17,6 +17,8 @@ import (
"fmt"
"strings"
"time"
"github.com/kami/maven/internal/lexicon"
)
// Facts — the optional, deployment-specific half of the block. All fields may
@@ -34,12 +36,10 @@ type Facts struct {
Tools bool // at least one shell act is on the allowlist
}
var ruWeekdays = [...]string{"воскресенье", "понедельник", "вторник", "среда", "четверг", "пятница", "суббота"}
var ruMonths = [...]string{
"января", "февраля", "марта", "апреля", "мая", "июня",
"июля", "августа", "сентября", "октября", "ноября", "декабря",
}
// The weekday and month names are closed classes and live in internal/lexicon,
// which indexes weekdays from Sunday the way time.Weekday does and months from
// one. This file used to carry its own copies, making four copies of the twelve
// months in the tree after cmd/mavend/ruwords.go gave up its own (Vikunja #525).
// Block renders the context block for one turn. Russian even in front of the
// English prompts: the rules it states are Russian grammar (ты/тебя, feminine
@@ -61,7 +61,7 @@ func (f Facts) Block(now time.Time) string {
}
b.WriteString(fmt.Sprintf("Сейчас: %s, %d %s %d, %02d:%02d (местное время).\n",
ruWeekdays[int(now.Weekday())], now.Day(), ruMonths[int(now.Month())-1], now.Year(),
lexicon.Weekday(int(now.Weekday())), now.Day(), lexicon.MonthGenitive(int(now.Month())), now.Year(),
now.Hour(), now.Minute()))
b.WriteString("Умеешь: " + strings.Join(f.can(), "; ") +
+2 -1
View File
@@ -141,7 +141,8 @@ func LoadSummaries(src rand.Source) (*Summaries, error) {
{PlanUncertain, "{line}"},
{TasksFirst, "{items}"}, {TasksCandidates, "{items}"},
{StallOverdue, "{n}"}, {StallOverdue, "{word}"},
{StallSitting, "{n}"}, {StallSitting, "{days}"},
{StallSitting, "{n}"}, {StallSitting, "{word}"},
{StallSitting, "{days}"}, {StallSitting, "{dayword}"},
{StallUnconfirmed, "{n}"}, {StallUnconfirmed, "{word}"},
{ReasonOverdueDays, "{n}"}, {ReasonOverdueDays, "{word}"},
{ReasonInDays, "{n}"}, {ReasonInDays, "{word}"},
+16 -1
View File
@@ -9,6 +9,7 @@ import (
"strings"
"github.com/kami/maven/internal/lexicon"
"github.com/kami/maven/internal/say"
)
// The month names are a closed class and live in internal/lexicon, 1-indexed,
@@ -32,7 +33,7 @@ func Speakable(s string) string {
})
s = reTime.ReplaceAllStringFunc(s, func(m string) string {
p := reTime.FindStringSubmatch(m)
return p[1] + " часов " + p[2] + " минут"
return spokenTime(mustInt(p[1]), mustInt(p[2]))
})
s = reDots.ReplaceAllStringFunc(s, func(m string) string {
return strings.Join(strings.Split(m, "."), " точка ")
@@ -46,6 +47,20 @@ func Speakable(s string) string {
return Pronounce(s)
}
// spokenTime reads a clock time the way it is said rather than the way it is
// written. Two things the written form gets wrong out loud. The noun after a
// numeral inflects, so 21:00 is "час" and 22:00 is "часа", where the old
// rewrite said "часов" for every hour and "минут" for every minute. And a
// leading zero is punctuation, not a word: 14:00 is "14 часов" and 9:05 is
// "9 часов 5 минут", never "00 минут" or "05 минут".
func spokenTime(h, m int) string {
out := strconv.Itoa(h) + " " + say.CountWord(h, "час", "часа", "часов")
if m == 0 {
return out
}
return out + " " + strconv.Itoa(m) + " " + say.CountWord(m, "минута", "минуты", "минут")
}
func spokenDate(dd, mm, yyyy string) string {
mi, _ := strconv.Atoi(mm)
if mi < 1 || mi > 12 {
+5 -2
View File
@@ -6,8 +6,11 @@ func TestSpeakable(t *testing.T) {
cases := []struct{ in, want string }{
{"напомню 10.07.2026", "напомню 10 июля 2026"},
{"срок 01.01", "срок 1 января"},
{"встреча в 14:00", "встреча в 14 часов 00 минут"},
{"в 9:05 подъём", "в 9 часов 05 минут подъём"},
{"встреча в 14:00", "встреча в 14 часов"},
{"в 9:05 подъём", "в 9 часов 5 минут подъём"},
{"в 21:00 отбой", "в 21 час отбой"},
{"в 22:02 отбой", "в 22 часа 2 минуты отбой"},
{"в 1:01 проснулся", "в 1 час 1 минута проснулся"},
{"это 3.2.1 версия", "это 3 точка 2 точка 1 версия"},
{"без чисел", "без чисел"},
}