Files
Maven/cmd/mavend/ruwords.go
T
claude 9e1958e7b0 one weekday matcher, and a stem list stops answering for sredstvo (V-581)
router.WeekdayIndex reads the lexicon and asks the dictionary about the case.
Four private lists go away: the habit declension map, the weekday block of the
day-plan refusal, the weekday and part-of-day entries of the weather guard, and
the stem list in ruwords.go.

The stem list was the real defect. mentionsUnknownDay matched sred, pyatnits
and subbot with strings.Contains, so sredi, sredstvo and sredniy all read as
Wednesday and a question carrying one was answered with onlyNearDaysReply
instead of a date. It matches whole tokens now.

The weather guard was a third copy of three closed sets that already exist.
It kept the rooms of the house, which are its own, and asks the lexicon for the
weekdays, the parts of the day and the words that follow v without naming a
place. Questions phrased v srede, v utra and v obshchem reached the geocoder as
cities before.

Full suite green under -race.
2026-08-06 03:33:01 +04:00

178 lines
6.9 KiB
Go

// Package main — ruwords.go holds Russian language + calendar/time formatting
// helpers used by the voice reply paths (replySystem, the reminder/routine
// phrasing, etc). Pure functions, no receivers: weekday/month name tables,
// plural agreement, clock/date rendering, and the "do I actually know this
// place/day" guards that pick an honest reply over a confidently wrong one.
// Extend this file rather than voice.go for anything in that shape.
//
// Count agreement is not here. It is say.CountWord, because there were four
// copies of the same three-way rule and two of the sites that needed it were
// spelling one form out (Vikunja #521).
package main
import (
"fmt"
"strconv"
"strings"
"time"
"github.com/kami/maven/internal/lexicon"
"github.com/kami/maven/internal/router"
"github.com/kami/maven/internal/say"
)
// Weekday and month names are a closed class — the language has seven and
// twelve — so they live complete in internal/lexicon, where internal/ttsnorm
// reads the same twelve month names instead of keeping a second copy
// (Vikunja #525).
// onlyLocalTimeReply — the honest answer when the user asks the time somewhere
// other than here. She only keeps one clock, and saying so is better than
// naming the wrong city's time.
//
// There used to be a city→time-zone table here. It was removed on purpose: the
// user only ever asks for local time, so the table was a second list of cities
// to keep in step with the weather one for no gain.
const onlyLocalTimeReply = "я знаю только местное время, про другие города пока не скажу."
// notPlaceAfterV — words that follow "в" without naming a place, so
// mentionsUnknownPlace does not mistake them for a city. Closed set, kept
// complete in internal/lexicon.
var notPlaceAfterV = func() map[string]bool {
m := map[string]bool{}
for _, w := range lexicon.NotPlaceAfterV() {
m[w] = true
}
return m
}()
// mentionsUnknownPlace reports whether the question has a "в <слово>" phrase
// that looks like a place we do not know ("который час в киеве"). Used only to
// pick the honest "local time only" reply instead of answering local time as
// if it were the city's.
func mentionsUnknownPlace(u string) bool {
toks := strings.Fields(u)
for i := 0; i+1 < len(toks); i++ {
if toks[i] != "в" && toks[i] != "во" {
continue
}
next := strings.Trim(toks[i+1], ".,?!")
if next == "" || notPlaceAfterV[next] {
continue
}
// A number after "в" is a clock ("в 5 часов"), not a place.
if _, err := strconv.Atoi(strings.SplitN(next, ":", 2)[0]); err == nil {
continue
}
return true
}
return false
}
// onlyNearDaysReply — she can work out today, tomorrow, the day after and
// yesterday, and nothing further. Said out loud instead of answering today's
// date for a day she did not understand.
const onlyNearDaysReply = "я считаю только сегодня, завтра, послезавтра и вчера — про другие дни пока не скажу."
// mentionsUnknownDay reports whether the question names a day the calendar
// parser could not resolve. Mirror of mentionsUnknownPlace: it exists only to
// pick an honest reply over a confidently wrong one.
//
// Only called after ParseCalendarDate has already failed, so "завтра" and the
// other words it does know never reach here.
//
// The weekday half was a list of STEMS matched with strings.Contains until
// V-581 — "сред", "пятниц", "суббот". That is the hand-written Russian pattern
// the sweep of 2026-08-04 took out, and it was wrong in the way such a pattern
// always is: "среди", "средство" and "средний" all contain "сред", so a question
// carrying any of them was answered with onlyNearDaysReply instead of the date.
// Whole tokens now, and the weekday itself is router.WeekdayIndex, which reads
// the lexicon and asks the dictionary about the case.
func mentionsUnknownDay(u string) bool {
for _, tok := range quietTokens(u) {
if tok == "через" {
return true
}
if _, ok := router.WeekdayIndex(tok); ok {
return true
}
}
return false
}
// ruClock renders the clock part of the time reply: "15 часов 4 минуты".
func ruClock(t time.Time) string {
h, m := t.Hour(), t.Minute()
hourWord := say.CountWord(h, "час", "часа", "часов")
if m == 0 {
return fmt.Sprintf("%d %s ровно", h, hourWord)
}
return fmt.Sprintf("%d %s %d %s", h, hourWord, m, say.CountWord(m, "минута", "минуты", "минут"))
}
// dayPrefix names the day relative to now ("завтра", "вчера", …) so the date
// reply opens the way a person would say it.
func dayPrefix(now, day time.Time) string {
base := time.Date(now.Year(), now.Month(), now.Day(), 0, 0, 0, 0, now.Location())
switch int(day.Sub(base).Hours() / 24) {
case -1:
return "вчера"
case 0:
return "сегодня"
case 1:
return "завтра"
case 2:
return "послезавтра"
}
return "это"
}
// hasDurationWords checks whether u is asking about elapsed/remaining time
// rather than the current clock — guards replySystem from replying "сейчас
// X часов" to "сколько времени прошло". Mirrors the stage0.go build filter.
func hasDurationWords(u string) bool {
s := strings.ToLower(strings.TrimSpace(u))
// First-word duration markers (same keywords as timeQueryBuild in stage0).
first := strings.Fields(s)
if len(first) > 0 {
switch first[0] {
case "прошло", "осталось", "пройдет", "минуло", "проходит":
return true
}
}
// Broader duration keywords appearing anywhere in the utterance.
if strings.Contains(s, "прошло") || strings.Contains(s, "осталось") {
return true
}
if strings.Contains(s, " до ") {
return true
}
return false
}
// formatTime returns a human-readable Russian time string for a fact timestamp.
// Used by the query handler when answering "когда я это сделал?"-style questions.
func formatTime(t time.Time) string {
now := time.Now()
if t.After(now.Add(-2*time.Minute)) && t.Before(now.Add(2*time.Minute)) {
return "только что"
}
diff := now.Sub(t)
switch {
case diff < 10*time.Minute:
return "несколько минут назад"
case diff < 60*time.Minute:
n := int(diff.Minutes())
return fmt.Sprintf("%d %s назад", n, say.CountWord(n, "минуту", "минуты", "минут"))
case diff < 2*time.Hour:
return "час назад"
case diff < 24*time.Hour:
n := int(diff.Hours())
return fmt.Sprintf("%d %s назад", n, say.CountWord(n, "час", "часа", "часов"))
default:
// Not t.Format("2 января …"): Go reads that as a literal, so every
// fact older than a day used to read as January (Vikunja #507).
return fmt.Sprintf("%d %s %s", t.Day(), lexicon.MonthGenitive(int(t.Month())), t.Format("15:04"))
}
}