kami
cb3641e7bb
internal/rss parses RSS 2.0 and Atom, and polls each configured feed on its own interval; internal/webfetch is the one door either of them uses to touch the network. The poller writes items as notes with source "rss:<feed>" and nothing else: the answer path reads them back when he asks "что нового в лентах?", and nothing is announced on arrival. A feed that dispatched would be a nag, which is why the plan's breaking-news rule was left out rather than built. webfetch is where the limits live, as code rather than a paragraph: http(s) only, an allowlist (the configured feeds' hosts) and a denylist, a 2 MiB body cap, a 3-redirect cap, one request per host per second, and a refusal to connect to any private address — checked in the dialer's Control hook so it holds for every resolved address and every redirect hop, not just for a literal IP. Off unless configured: no "feeds" block, no poller, no outbound request. How far a feed was read is a config fact (rss:latest:<name>), so a restart does not re-note yesterday's headlines.
110 lines
3.8 KiB
Go
110 lines
3.8 KiB
Go
package router
|
||
|
||
import "strings"
|
||
|
||
// Feed queries — "что нового в лентах?", "что нового по технологиям?"
|
||
// (Vikunja #258).
|
||
//
|
||
// Deterministic matching, like the calendar, plan and habit matchers above it:
|
||
// the LLM router says this is a query, and this decides whether it is a question
|
||
// about the feeds. A model deciding that would occasionally answer "что нового?"
|
||
// out of world knowledge, which is the one thing a feed reader exists to avoid.
|
||
|
||
// FeedQuery — a parsed "what's new" question. Category is the topic he named
|
||
// ("технологии"), empty when he asked about the feeds in general.
|
||
type FeedQuery struct {
|
||
Category string
|
||
}
|
||
|
||
// feedNouns — the words that make a question about the feeds themselves.
|
||
var feedNouns = []string{
|
||
"лента", "ленте", "ленты", "лентах", "лентам",
|
||
"новости", "новостей", "новостях", "новостям",
|
||
"новое", "нового", "новенького",
|
||
"feed", "feeds", "news", "headlines",
|
||
}
|
||
|
||
// newnessMarkers — the "что нового" half. "нового" alone is in feedNouns
|
||
// because it carries the question on its own ("что нового?"); a bare "лента"
|
||
// needs the ask, which is what askMarkers below is for.
|
||
var askMarkers = []string{
|
||
"что", "какие", "какое", "расскажи", "почитай", "прочитай", "покажи",
|
||
"what", "any", "tell", "show", "read",
|
||
}
|
||
|
||
// ParseFeedQuery reports whether an utterance asks what is new in the feeds, and
|
||
// which topic if it names one after "по"/"о"/"про"/"about".
|
||
//
|
||
// Both a feed noun and an ask are required. "у меня новая лента в инстаграме" is
|
||
// a statement and must not be read as a request to recite headlines.
|
||
func ParseFeedQuery(text string) (FeedQuery, bool) {
|
||
toks := planTokens(text)
|
||
noun, ask := false, false
|
||
for _, t := range toks {
|
||
for _, n := range feedNouns {
|
||
if t == n {
|
||
noun = true
|
||
break
|
||
}
|
||
}
|
||
for _, a := range askMarkers {
|
||
if t == a {
|
||
ask = true
|
||
break
|
||
}
|
||
}
|
||
}
|
||
if !noun || !ask {
|
||
return FeedQuery{}, false
|
||
}
|
||
return FeedQuery{Category: feedCategory(toks)}, true
|
||
}
|
||
|
||
// categoryPreps — the prepositions a topic follows. Russian marks the topic with
|
||
// a preposition ("по технологиям", "про политику"), so the word after one is the
|
||
// category; there is no stemming here, and the match against the configured
|
||
// category is a prefix comparison for exactly that reason.
|
||
var categoryPreps = map[string]bool{"по": true, "о": true, "об": true, "про": true, "about": true, "on": true}
|
||
|
||
func feedCategory(toks []string) string {
|
||
for i, t := range toks {
|
||
if categoryPreps[t] && i+1 < len(toks) {
|
||
next := toks[i+1]
|
||
// "по новостям" names no topic, it repeats the noun.
|
||
for _, n := range feedNouns {
|
||
if next == n {
|
||
return ""
|
||
}
|
||
}
|
||
return next
|
||
}
|
||
}
|
||
return ""
|
||
}
|
||
|
||
// CategoryMatches reports whether a note's text plausibly belongs to the
|
||
// category he named. Russian inflects the topic ("технологиям" vs the configured
|
||
// "технологии"), and there is no stemmer in this repo, so the comparison is on a
|
||
// common prefix — long enough that "полит" and "погод" stay apart, short enough
|
||
// to survive a case ending.
|
||
func CategoryMatches(text, category string) bool {
|
||
if category == "" {
|
||
return true
|
||
}
|
||
stem := categoryStem(category)
|
||
if stem == "" {
|
||
return false
|
||
}
|
||
return strings.Contains(strings.ToLower(text), stem)
|
||
}
|
||
|
||
// categoryStem cuts a word down to the part inflection leaves alone. 5 runes is
|
||
// the compromise: shorter words are used whole.
|
||
func categoryStem(word string) string {
|
||
r := []rune(strings.ToLower(strings.TrimSpace(word)))
|
||
if len(r) > 5 {
|
||
r = r[:5]
|
||
}
|
||
return string(r)
|
||
}
|