Maven/cmd/mavend/historyq.go

package main

import (
	"context"
	"fmt"
	"log"
	"strings"
	"time"

	"github.com/kami/maven/internal/morph"
)

// Command history — "что я тебе говорил?", "что ты записала сегодня?"
// (Vikunja #456).
//
// Read-only over the facts that already exist. No new mechanism and no new
// storage: everything he tapped in is already a row with a source and a
// timestamp, and this only reads them back.

// A history question needs three things in one utterance: the interrogative,
// whose turn is being asked about, and a verb of saying or recording. Any two of
// them are a different question. "что я говорил про сервер" names a topic and
// the notes pass answers it better; "записал молоко" is a capture.
//
// The verbs are matched by lemma through internal/morph, not by a truncated
// prefix (Vikunja #530). The pairs here used to hold "рассказ" and "записал",
// which is the defect V-528 fixed in complaint.go: "рассказ" is also the noun,
// so "что я рассказал ей" and "что я читал рассказ" were the same string test.
// Aspect pairs are separate lemmas in the dictionary, so both members are listed.
var (
	// historySpokenVerbs — what HE did. "что я тебе говорил".
	historySpokenVerbs = []string{"говорить", "сказать", "рассказать", "рассказывать", "отметить", "отмечать"}

	// historyRecordedVerbs — what SHE did with it. "что ты записала сегодня".
	historyRecordedVerbs = []string{"записать", "запомнить", "отметить", "отмечать"}

	// firstPersonSubjects and secondPersonSubjects — whose turn the question is
	// about. Only the subject forms: "что я тебе говорил" is his turn, and the
	// dative "тебе" in it is not the subject.
	firstPersonSubjects  = []string{"я"}
	secondPersonSubjects = []string{"ты"}
)

// historyMarkersEn — the English pairs, kept as substrings because the
// dictionary is Russian. Each half alone is a different question, the same way
// the Russian test needs all three parts.
var historyMarkersEn = [][2]string{
	{"what did i", "tell"},
	{"what did you", "record"},
}

// historyRecall — the word that turns a history question into a recall
// question. "что я говорил про сервер" names a topic, and the notes pass
// answers a topic far better than a list of the last five facts does.
var historyRecall = []string{" про ", " об ", " о ", " about "}

// historySide — whose turn the question asks about. The rows read are the same
// either way, because a tapped fact is one act seen from two sides, but the
// sentence is not: answering "что ты записала сегодня?" with "ты говорил…"
// hands the question back instead of answering it (Vikunja #456).
type historySide int

const (
	historyAskedHim historySide = iota // "что я тебе говорил"
	historyAskedHer                    // "что ты записала сегодня"
)

// isHistoryQuery reports whether he is asking what he told her.
func isHistoryQuery(u string) bool {
	_, ok := historyAsks(u)
	return ok
}

// historyAsks reports whether this is a history question, and whose turn it is
// about.
func historyAsks(u string) (historySide, bool) {
	s := " " + strings.ToLower(strings.TrimSpace(u)) + " "
	if s == "  " {
		return historyAskedHim, false
	}
	for _, r := range historyRecall {
		if strings.Contains(s, r) {
			return historyAskedHim, false
		}
	}
	for _, pair := range historyMarkersEn {
		if strings.Contains(s, pair[0]) && strings.Contains(s, pair[1]) {
			if strings.Contains(pair[0], "you") {
				return historyAskedHer, true
			}
			return historyAskedHim, true
		}
	}
	toks := historyTokens(s)
	if !hasAny(toks, "что", "чего") {
		return historyAskedHim, false
	}
	// His side is tested first: "отмечать" is on both verb lists, so "что я
	// отметил" must not read as a question about her.
	if hasAny(toks, firstPersonSubjects...) && hasVerbForm(toks, historySpokenVerbs) {
		return historyAskedHim, true
	}
	if hasAny(toks, secondPersonSubjects...) && hasVerbForm(toks, historyRecordedVerbs) {
		return historyAskedHer, true
	}
	return historyAskedHim, false
}

// historyTokens splits an utterance into bare words. The punctuation goes
// because "говорил?" is the same word as "говорил".
func historyTokens(s string) []string {
	toks := strings.Fields(s)
	out := make([]string, 0, len(toks))
	for _, t := range toks {
		if t = strings.Trim(t, ".,!?;:—–-()\"'«»"); t != "" {
			out = append(out, t)
		}
	}
	return out
}

func hasAny(toks []string, want ...string) bool {
	for _, t := range toks {
		for _, w := range want {
			if t == w {
				return true
			}
		}
	}
	return false
}

// hasVerbForm reports whether any token is a form of any of the lemmas. Both
// sides go through the dictionary, so a caller may name the infinitive and he
// may say the past tense.
func hasVerbForm(toks []string, lemmas []string) bool {
	for _, t := range toks {
		for _, l := range lemmas {
			if morph.SameWord(t, l) {
				return true
			}
		}
	}
	return false
}

// historyScan — how many recent facts are read before filtering. Deliberately
// larger than historyReadOut: a poller writing every few minutes would
// otherwise push everything he said out of the window, the same way his own
// notes used to crowd out the feed headlines.
const historyScan = 100

// historyReadOut — how many she says out loud. Five is what fits in one spoken
// breath; the rest are on /history, which is the surface for reading a list.
const historyReadOut = 5

// historyWindow — how far back "recently" reaches. A day, because the question
// is about this conversation and not about the archive.
const historyWindow = 24 * time.Hour

// queryHistory answers what he told her, from the facts he tapped in.
//
// Only "tap:" sources. A fact written by a poller, an inference or the ambient
// relay is a thing she learned, not a thing he said, and reading those back
// under "что я тебе говорил?" would put words in his mouth.
//
// Placed with the other sources that read his own rows and above the recall
// pass: the notes pass would otherwise answer this from whatever note happens
// to be nearest, which reads as an answer and is not one.
func (h *reactiveHandler) queryHistory(ctx context.Context, t *queryTurn) (string, bool) {
	side, ok := historyAsks(t.dec.Utterance)
	if !ok {
		return "", false
	}
	facts, err := h.api.RecentFacts(ctx, historyScan)
	if err != nil {
		log.Printf("voice: history: recent facts: %v", err)
		return "не получилось посмотреть, что ты говорил.", true
	}
	cutoff := h.now().Add(-historyWindow)
	var said []string
	for _, f := range facts {
		if !strings.HasPrefix(f.Source, "tap:") || f.Ts.Before(cutoff) {
			continue
		}
		said = append(said, historyLine(f.Key, f.Value, f.Ts))
		if len(said) == historyReadOut {
			break
		}
	}
	if len(said) == 0 {
		// Claim the turn rather than fall through. "ничего не говорил" is the
		// true answer, and recall would answer it with an old note instead.
		if side == historyAskedHer {
			return "за последние сутки я ничего с твоих слов не записывала.", true
		}
		return "за последние сутки ты мне ничего такого не говорил.", true
	}
	if side == historyAskedHer {
		return "я записала: " + strings.Join(said, "; "), true
	}
	return "ты говорил: " + strings.Join(said, "; "), true
}

// historyLine — one fact as she says it. The hour and minute, because the day
// is already bounded by historyWindow and a date would be noise.
func historyLine(key, value string, ts time.Time) string {
	what := key
	if value != "" {
		what = key + " — " + value
	}
	return fmt.Sprintf("%s (%s)", what, ts.Local().Format("15:04"))
}