claude
b954e0cea6
The RU voice reads a latin word letter by letter or guesses, so 'netdata' came out as noise and 'homesrv' as nothing. pronounce_ru_v1.json spells the sound in Cyrillic for the service names, hostnames and acronyms she actually says, and Speakable applies it last, after the numbers around it are words. Data, not code: nothing knows any of these names, and adding one is an edit to the JSON. A word the table does not hold is left exactly as it was, so a miss is the current behaviour rather than a guess. A malformed file logs and loads empty, because speech must not stop over a dictionary. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
69 lines
2.1 KiB
Go
69 lines
2.1 KiB
Go
// Package ttsnorm rewrites machine-formatted dates/times/numbers into RU text
|
|
// a TTS voice speaks naturally — so "10.07.2026" is not read as "number dot
|
|
// number dot number". Pure, deterministic; runs on reply/nudge text before synth.
|
|
package ttsnorm
|
|
|
|
import (
|
|
"regexp"
|
|
"strconv"
|
|
"strings"
|
|
|
|
"github.com/kami/maven/internal/lexicon"
|
|
)
|
|
|
|
// The month names are a closed class and live in internal/lexicon, 1-indexed,
|
|
// which is also where the voice reply path reads them. There used to be a second
|
|
// copy of the twelve names in cmd/mavend/ruwords.go (Vikunja #525).
|
|
|
|
var (
|
|
reDateY = regexp.MustCompile(`\b(\d{1,2})\.(\d{1,2})\.(\d{4})\b`)
|
|
reDate = regexp.MustCompile(`\b(\d{1,2})\.(\d{1,2})\b`)
|
|
reTime = regexp.MustCompile(`\b(\d{1,2}):(\d{2})\b`)
|
|
reDots = regexp.MustCompile(`\b\d+(?:\.\d+){2,}\b`)
|
|
)
|
|
|
|
// Speakable rewrites d.m.y, d.m, h:mm, and residual dotted-number runs.
|
|
// Order matters: dates with year first, then times, then multi-dot numbers
|
|
// (3+ parts — never valid dates), then 2-part dates.
|
|
func Speakable(s string) string {
|
|
s = reDateY.ReplaceAllStringFunc(s, func(m string) string {
|
|
p := reDateY.FindStringSubmatch(m)
|
|
return spokenDate(p[1], p[2], p[3])
|
|
})
|
|
s = reTime.ReplaceAllStringFunc(s, func(m string) string {
|
|
p := reTime.FindStringSubmatch(m)
|
|
return p[1] + " часов " + p[2] + " минут"
|
|
})
|
|
s = reDots.ReplaceAllStringFunc(s, func(m string) string {
|
|
return strings.Join(strings.Split(m, "."), " точка ")
|
|
})
|
|
s = reDate.ReplaceAllStringFunc(s, func(m string) string {
|
|
p := reDate.FindStringSubmatch(m)
|
|
return spokenDate(p[1], p[2], "")
|
|
})
|
|
// Last, so a hostname is spelled out after the numbers around it are
|
|
// already words and no rewrite above can see Cyrillic it did not expect.
|
|
return Pronounce(s)
|
|
}
|
|
|
|
func spokenDate(dd, mm, yyyy string) string {
|
|
mi, _ := strconv.Atoi(mm)
|
|
if mi < 1 || mi > 12 {
|
|
return dd + " " + mm + gap(yyyy)
|
|
}
|
|
day := strconv.Itoa(mustInt(dd))
|
|
out := day + " " + lexicon.MonthGenitive(mi)
|
|
if yyyy != "" {
|
|
out += " " + yyyy
|
|
}
|
|
return out
|
|
}
|
|
|
|
func mustInt(s string) int { n, _ := strconv.Atoi(s); return n }
|
|
func gap(y string) string {
|
|
if y == "" {
|
|
return ""
|
|
}
|
|
return " " + y
|
|
}
|