swehockey/output.go

package main

import (
	"bytes"
	"encoding/csv"
	"encoding/json"
	"fmt"
	"os"
	"strconv"
	"strings"
)

// render turns a schedule into bytes. Both encoders are pure functions of the
// data: no timestamps, no maps, fixed column order, LF line endings. Running
// the crawler twice on the same page produces identical bytes, which is what
// makes -check and diff-based review meaningful.
func render(format string, s *Schedule) ([]byte, error) {
	switch format {
	case "json":
		var buf bytes.Buffer
		enc := json.NewEncoder(&buf)
		enc.SetEscapeHTML(false) // keep team names readable
		enc.SetIndent("", "  ")
		if err := enc.Encode(s); err != nil {
			return nil, err
		}
		return buf.Bytes(), nil
	case "csv":
		return renderCSV(s)
	default:
		return nil, fmt.Errorf("unknown format %q: want json, csv or ndjson", format)
	}
}

func renderNDJSON(s *Schedule) ([]byte, error) {
	var buf bytes.Buffer
	if err := jsonEncoder(&buf).Encode(s); err != nil {
		return nil, err
	}
	return buf.Bytes(), nil
}

// jsonEncoder keeps "ä" readable instead of \u00e4, which matters for diffs
// of team names.
func jsonEncoder(buf *bytes.Buffer) *json.Encoder {
	enc := json.NewEncoder(buf)
	enc.SetEscapeHTML(false)
	return enc
}

var csvHeader = []string{
	"season_id", "game_id", "event_id", "date", "time", "home", "away",
	"home_goals", "away_goals", "periods", "spectators", "venue",
}

func renderCSV(s *Schedule) ([]byte, error) {
	var buf bytes.Buffer
	w := csv.NewWriter(&buf) // LF, not CRLF
	if err := w.Write(csvHeader); err != nil {
		return nil, err
	}
	for _, g := range s.Games {
		periods := make([]string, 0, len(g.Periods))
		for _, p := range g.Periods {
			periods = append(periods, fmt.Sprintf("%s:%d-%d", p.Label, p.Home, p.Away))
		}
		row := []string{
			strconv.Itoa(s.SeasonID),
			g.GameID,
			g.EventID,
			g.Date,
			g.Time,
			g.Home,
			g.Away,
			optInt(g.HomeGoals),
			optInt(g.AwayGoals),
			strings.Join(periods, " "),
			optInt(g.Spectators),
			g.Venue,
		}
		if err := w.Write(row); err != nil {
			return nil, err
		}
	}
	w.Flush()
	return buf.Bytes(), w.Error()
}

func optInt(p *int) string {
	if p == nil {
		return ""
	}
	return strconv.Itoa(*p)
}

// emit writes the bytes to -out or stdout and, when -check is set, compares
// them with a committed golden file. A mismatch exits 3 so CI turns an upstream
// change into a reviewable diff instead of a silent data change.
func emit(out, check string, b []byte) error {
	if check != "" {
		golden, err := os.ReadFile(check)
		switch {
		case err == nil && bytes.Equal(golden, b):
		case err != nil:
			return fmt.Errorf("golden file %s: %w", check, err)
		default:
			return &DriftError{Msg: fmt.Sprintf("output no longer matches %s: %s", check, firstDiff(golden, b))}
		}
	}
	if out == "" {
		_, err := os.Stdout.Write(b)
		return err
	}
	return os.WriteFile(out, b, 0o644)
}

// firstDiff describes the first differing line, for a readable failure.
func firstDiff(a, b []byte) string {
	al, bl := strings.Split(string(a), "\n"), strings.Split(string(b), "\n")
	for i := 0; i < len(al) || i < len(bl); i++ {
		var x, y string
		if i < len(al) {
			x = al[i]
		}
		if i < len(bl) {
			y = bl[i]
		}
		if x != y {
			return fmt.Sprintf("line %d: %q != %q", i+1, trim(x), trim(y))
		}
	}
	return "documents differ only in length"
}

func trim(s string) string {
	if len(s) > 80 {
		return s[:80] + "..."
	}
	return s
}