uptodownbot/internal/dl/progress.go

package dl

import (
	"bufio"
	"io"
	"log/slog"
	"regexp"
	"strconv"
	"strings"

	"uptodownBot/internal/domain"
)

var progressRE = regexp.MustCompile(`\[\w+\]\s+([\d.]+)%\s+of\s+~?\s*([\d.]+)(\w+)`)
var progressTemplateRE = regexp.MustCompile(`^DLPROG\|\s*([\d.]+)%\|\s*(.*?)\s*\|(.*)$`)

type progressUpdate struct {
	pct   float64
	speed string
	eta   string
}

// parseProgressTemplate parses a DLPROG-prefixed line from yt-dlp's --progress-template.
func parseProgressTemplate(line string) *progressUpdate {
	m := progressTemplateRE.FindStringSubmatch(line)
	if m == nil {
		return nil
	}
	pct, err := strconv.ParseFloat(m[1], 64)
	if err != nil {
		return nil
	}
	u := &progressUpdate{pct: pct}
	speed := strings.TrimSpace(m[2])
	eta := strings.TrimSpace(m[3])
	if speed != "" && !strings.EqualFold(speed, "unknown") && speed != "N/A" {
		u.speed = speed
	}
	if eta != "" && !strings.EqualFold(eta, "unknown") && eta != "N/A" {
		u.eta = eta
	}
	return u
}

// parseProgressLine parses a single yt-dlp stderr progress line.
// Returns nil if the line doesn't contain progress info.
func parseProgressLine(line string) *progressUpdate {
	line = strings.TrimSpace(line)
	if line == "" {
		return nil
	}
	if u := parseProgressTemplate(line); u != nil {
		return u
	}
	if !strings.HasPrefix(line, "[download]") {
		return nil
	}
	m := progressRE.FindStringSubmatch(line)
	if m == nil {
		return nil
	}
	pct, err := strconv.ParseFloat(m[1], 64)
	if err != nil {
		return nil
	}

	u := &progressUpdate{pct: pct}

	rest := line
	if idx := strings.Index(rest, "%"); idx >= 0 {
		rest = rest[idx+1:]
	}
	if atIdx := strings.Index(rest, " at "); atIdx >= 0 {
		afterAt := strings.TrimSpace(rest[atIdx+4:])
		if spaceIdx := strings.Index(afterAt, " "); spaceIdx >= 0 {
			speedVal := afterAt[:spaceIdx]
			if !strings.EqualFold(speedVal, "unknown") && speedVal != "N/A" {
				u.speed = speedVal
			}
			rest = afterAt[spaceIdx:]
		} else {
			if !strings.EqualFold(afterAt, "unknown") && afterAt != "N/A" {
				u.speed = afterAt
			}
			rest = ""
		}
	}
	if etaIdx := strings.Index(rest, "ETA "); etaIdx >= 0 {
		etaStr := strings.TrimSpace(rest[etaIdx+4:])
		if parenPos := strings.Index(etaStr, "("); parenPos > 0 {
			etaStr = strings.TrimSpace(etaStr[:parenPos])
		}
		if !strings.EqualFold(etaStr, "unknown") && etaStr != "N/A" {
			u.eta = etaStr
		}
	}

	return u
}

// readProgress reads yt-dlp stderr and sends progress updates to the channel.
// The caller is responsible for closing the updates channel.
func readProgress(stderr io.ReadCloser, updates chan<- *domain.DownloadJob, job *domain.DownloadJob) {
	var stderrBuf strings.Builder
	scanner := bufio.NewScanner(stderr)
	lineCount := 0
	matchCount := 0
	for scanner.Scan() {
		line := scanner.Text()
		lineCount++

		if stderrBuf.Len() < 4096 {
			stderrBuf.WriteString(line)
			stderrBuf.WriteByte('\n')
		}

		parsed := parseProgressLine(line)
		if parsed == nil {
			continue
		}
		matchCount++
		job.Progress = parsed.pct
		job.Speed = parsed.speed
		job.ETA = parsed.eta
		updates <- job
	}
	job.StderrLog = stderrBuf.String()
	slog.Info("readProgress finished", "url", job.URL, "lines", lineCount, "matches", matchCount, "stderr_len", len(job.StderrLog))
}