Merge pull request 'reminder_verbs has no alarm verb, so an alarm never routes (V-627)' (#180) from task/627-reminder-verbs-has-no-alarm-verb-so-an-a into master

internal/lexicon/lexicon_ru_v1.json

@@ -173,10 +173,11 @@
       ]
     },
     "reminder_verbs": {
-      "note": "The imperatives that mean \"remind me\", in the forms he speaks. The same kind of set as capture_verbs and decided the same way: it is her vocabulary, not a discovery about Russian (Vikunja #530).",
+      "note": "The imperatives that mean \"remind me\", in the forms he speaks. The same kind of set as capture_verbs and decided the same way: it is her vocabulary, not a discovery about Russian (Vikunja #530). The alarm verbs joined them in V-627. \"разбуди меня в 6:30\" is a reminder that fires at the hour he gets up, and the set knew no form of it, so an alarm reached IntentReminder only by resembling one to the embedder.",
       "words": [
         "напомни", "напомните", "напомнить", "напоминай",
-        "remind"
+        "разбуди", "разбудите", "разбудить", "буди",
+        "remind", "wake"
       ]
     },
     "half_hour": {

internal/router/stage0.go

@@ -2,6 +2,7 @@ package router
 
 import (
 	"regexp"
+	"sort"
 	"strings"
 	"unicode"
 
@@ -94,10 +95,41 @@ func DefaultGrammars(actMatcher ActMatcher) []Grammar {
 // stage-0 decision too (fillMatchedSlots in router.go). Before that it did not,
 // so "напомни в 11:00 позвонить маме" reached the daemon with HasTime false and
 // was asked "Когда?" about an hour he had just said.
+//
+// The verb alternation is built from lexicon.ReminderVerbs rather than written
+// out (V-627). The literal here knew "напомни" and "remind me" and nothing
+// else, so "разбуди меня в 6:30" never reached stage 0 — and it does not reach
+// IntentReminder further down either, where the classifier calls it fact at
+// 0.918. An alarm is a reminder that fires at the hour he gets up, and the
+// verb that names one is her vocabulary, so it belongs in the lexicon with the
+// rest of it.
+//
+// Longest-first ordering matters: Go's regexp alternation is leftmost-first,
+// not longest-match, so "напомнить" listed after "напомни" would never match.
+var reminderVerbPattern = regexp.MustCompile(
+	`(?i)^\s*(?:` + longestFirstAlternation(lexicon.ReminderVerbs()) +
+		`)\s*(?:мне|меня|me)?[\s,:]+(.+)$`)
+
+// longestFirstAlternation joins a word set into a regexp alternation, longest
+// alternative first, with every member escaped.
+func longestFirstAlternation(set []string) string {
+	out := make([]string, 0, len(set))
+	for _, w := range set {
+		out = append(out, regexp.QuoteMeta(w))
+	}
+	sort.Slice(out, func(i, j int) bool {
+		if len(out[i]) != len(out[j]) {
+			return len(out[i]) > len(out[j])
+		}
+		return out[i] < out[j]
+	})
+	return strings.Join(out, "|")
+}
+
 func ReminderGrammar() Grammar {
 	return Grammar{
 		Name:    "reminder-wakeword",
-		Pattern: regexp.MustCompile(`(?i)^\s*(?:напомни|remind me)[\s,:]+(.+)$`),
+		Pattern: reminderVerbPattern,
 		Build: func(m []string) (Decision, bool) {
 			rest := strings.TrimSpace(m[1])
 			if rest == "" {