felixm
71b8c80c69
Bucket keys are {Class, ScrubTitle(Title)}, so each animated progress frame a
terminal app cycles into its title (Claude Code's braille and dingbat-star
glyphs) became a distinct bucket — fragmenting one task into dozens of rows and
inflating the switch count, since applyEvent counts a switch per key change.
ScrubTitle now drops any non-ASCII symbol or control rune and collapses leftover
whitespace. This is category-based rather than range-based, so future spinner
sets are covered too, while letters and digits of every script survive and ASCII
symbols (e.g. "C++") are left intact.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
58 lines
2.2 KiB
Go
58 lines
2.2 KiB
Go
// Package evidence is the activity port: a dumb active-window sensor behind a
|
|
// Source interface, plus the value types it emits. It makes no judgment about
|
|
// whether a window is on-task — that is the advisor's job in a later milestone.
|
|
package evidence
|
|
|
|
import (
|
|
"context"
|
|
"regexp"
|
|
"strings"
|
|
"unicode"
|
|
)
|
|
|
|
// EvidenceHealth records whether the sensor could observe the active window.
|
|
type EvidenceHealth struct {
|
|
Available bool // true when a window was observed
|
|
Reason string // empty when Available; populated when not
|
|
}
|
|
|
|
// WindowSnapshot is one observation of the active window.
|
|
type WindowSnapshot struct {
|
|
Title string // full _NET_WM_NAME (raw; used in live view + raw log)
|
|
Class string // WM_CLASS
|
|
Health EvidenceHealth
|
|
}
|
|
|
|
// Source is the activity port. Watch runs until ctx is cancelled, invoking
|
|
// onChange on every active-window change, and once immediately with the
|
|
// current window.
|
|
type Source interface {
|
|
Watch(ctx context.Context, onChange func(WindowSnapshot))
|
|
}
|
|
|
|
// titleNoise matches the legacy clock/ratio/percent runs that pollute bucket
|
|
// keys (e.g. "1:23", "50.5%", "-3.0"). Ported verbatim from the Rust impl.
|
|
var titleNoise = regexp.MustCompile(`-?\d+([:.]\d+)+%?`)
|
|
|
|
// extraSpace collapses the whitespace runs left behind by the scrubs below.
|
|
var extraSpace = regexp.MustCompile(`\s+`)
|
|
|
|
// ScrubTitle normalizes a window title into a stable bucket key. It drops
|
|
// volatile numeric runs (clocks, ratios, percentages) and any non-ASCII symbol
|
|
// or control rune. The latter covers the animated spinner frames terminal apps
|
|
// (e.g. Claude Code) cycle through their title — braille and dingbat glyphs are
|
|
// both Unicode symbol category, so a single task no longer fragments into dozens
|
|
// of buckets. Letters and digits of every script survive, as do ASCII symbols
|
|
// (so "C++" is not mangled). Leftover whitespace is collapsed. The raw event log
|
|
// keeps the unscrubbed title; only bucket keys (and their display) are scrubbed.
|
|
func ScrubTitle(title string) string {
|
|
title = titleNoise.ReplaceAllString(title, "")
|
|
title = strings.Map(func(r rune) rune {
|
|
if unicode.IsControl(r) || (r > unicode.MaxASCII && unicode.IsSymbol(r)) {
|
|
return -1
|
|
}
|
|
return r
|
|
}, title)
|
|
return strings.TrimSpace(extraSpace.ReplaceAllString(title, " "))
|
|
}
|