todotxt2remind/internal/parser/parser.go

package parser

import (
	"bufio"
	"encoding/json"
	"errors"
	"fmt"
	"io"
	"math"
	"regexp"
	"strings"
	"time"
)

// Task represents a parsed todo item.
type Task struct {
	Raw            string              `json:"raw"`
	Completed      bool                `json:"completed"`
	CompletionDate *time.Time          `json:"completion_date,omitempty"`
	Priority       *rune               `json:"priority,omitempty"` // 'A'..'Z'
	CreationDate   *time.Time          `json:"creation_date,omitempty"`
	DueDate        *time.Time          `json:"due_date,omitempty"` // parsed from due:YYYY-MM-DD
	Description    string              `json:"description"`        // description with projects/contexts/metadata removed
	Projects       []string            `json:"projects"`
	Contexts       []string            `json:"contexts"`
	Metadata       map[string][]string `json:"metadata"`
}

func (t Task) ToRemind() string {
	var sb strings.Builder
	sb.WriteString("REM TODO ")
	if t.DueDate == nil {
		return ""
	}
	sb.WriteString(t.DueDate.Format("2006-01-02"))

	sb.WriteString(" ++5 INFO \"Calendar: TODO.TX\" ")

	if len(t.Metadata) > 0 {
		for k, values := range t.Metadata {
			if k == "due" {
				continue
			}
			// k must have the first letter uppercase for Remind
			kUpper := strings.ToUpper(k[:1]) + k[1:]
			if len(values) == 1 {
				sb.WriteString(fmt.Sprintf("INFO \"%s: %s\" ", kUpper, values[0]))
			} else {
				for i, v := range values {
					sb.WriteString(fmt.Sprintf("INFO \"%s%d: %s\" ", kUpper, i+1, v))
				}
			}
		}
	}

	if len(t.Projects) > 0 {
		for _, p := range t.Projects {
			sb.WriteString(fmt.Sprintf("INFO \"List: %s\" ", p))
		}
	}

	if len(t.Contexts) > 0 {
		for _, c := range t.Contexts {
			sb.WriteString(fmt.Sprintf("INFO \"Tag: %s\" ", c))
		}
	}

	if t.Completed {
		sb.WriteString(fmt.Sprintf("COMPLETE-THROUGH %s ", t.DueDate.Format("2006-01-02")))
	}

	if t.Priority != nil {
		sb.WriteString(fmt.Sprintf("PRIORITY %d ", t.PriorityAsRemind()))
	}

	sb.WriteString("MSG")

	if len(t.Projects) > 0 {
		sb.WriteString(" %<List>:")
	}

	sb.WriteString(fmt.Sprintf(" %s", t.Description))

	if t.Completed {
		sb.WriteString("%:")
	} else {
		sb.WriteString(" (%b)")
	}

	if len(t.Metadata) > 0 {
		for k, values := range t.Metadata {
			if k == "due" {
				continue
			}
			// uppercase first letter for Remind
			kUpper := strings.ToUpper(k[:1]) + k[1:]
			if len(values) == 1 {
				sb.WriteString(fmt.Sprintf("%%_%s: %%<%s>", kUpper, kUpper))
			} else {
				for i := range values {
					kNumbered := fmt.Sprintf("%s%d", kUpper, i+1)
					sb.WriteString(fmt.Sprintf("%%_%s: %%<%s>", kNumbered, kNumbered))
				}
			}
		}
	}

	return sb.String()
}

// PriorityAsRemind returns an integer representing the priority for sorting.
// A = 9999 (highest), Z = 0 (lowest), absent = 5000.
func (t Task) PriorityAsRemind() int {
	if t.Priority == nil {
		return 5000
	}
	p := *t.Priority
	if p < 'A' || p > 'Z' {
		return 5000
	}
	pInt := int(p) - 65 // 'A' = 65
	value := 9999 - (float64(pInt) * (float64(9999) / float64(25)))
	value = math.Round(value)
	return int(value)
}

func (t Task) MarshalJSON() ([]byte, error) {
	type Alias Task
	aux := struct {
		Alias
		Priority      *string `json:"priority,omitempty"`
		PriorityValue *int    `json:"priority_value,omitempty"`
	}{
		Alias:         (Alias)(t),
		Priority:      nil,
		PriorityValue: nil,
	}
	if t.Priority != nil {
		s := string(*t.Priority)
		aux.Priority = &s
		val := t.PriorityAsRemind()
		aux.PriorityValue = &val
	}
	return json.Marshal(aux)
}

var (
	dateRe     = regexp.MustCompile(`^\d{4}-\d{2}-\d{2}$`)
	spaceRe    = regexp.MustCompile(`\s+`)
	dateLayout = "2006-01-02"
	// Protocols to exclude as metadata keys
	protocols = map[string]struct{}{
		"http":   {},
		"https":  {},
		"ftp":    {},
		"mailto": {},
	}
)

// isProtocolKey checks if the key is a standard protocol.
func isProtocolKey(k string) bool {
	_, found := protocols[strings.ToLower(k)]
	return found
}

// ParseReader reads all lines from r and returns parsed tasks.
// Blank lines are skipped.
func ParseReader(r io.Reader) ([]Task, []error) {
	var tasks []Task
	var errs []error
	sc := bufio.NewScanner(r)
	lineNo := 0
	for sc.Scan() {
		lineNo++
		line := sc.Text()
		trim := strings.TrimSpace(line)
		if trim == "" {
			continue
		}
		t, err := ParseLine(line)
		if err != nil {
			errs = append(errs, fmt.Errorf("line %d: %w", lineNo, err))
			continue
		}
		tasks = append(tasks, t)
	}
	if err := sc.Err(); err != nil {
		errs = append(errs, err)
	}
	return tasks, errs
}

// ParseLine parses one line in the todo.txt format and returns a Task.
func ParseLine(line string) (Task, error) {
	t := Task{
		Raw:      line,
		Metadata: make(map[string][]string),
	}

	working := strings.TrimSpace(line)
	toks := splitTokens(working)
	i := 0

	// 1) Completed?
	if i < len(toks) && toks[i] == "x" {
		t.Completed = true
		i++
		// 2) Completion date
		if i < len(toks) && dateRe.MatchString(toks[i]) {
			if dt, err := time.Parse(dateLayout, toks[i]); err == nil {
				t.CompletionDate = &dt
				i++
			}
		}
		// 3) Creation date
		if i < len(toks) && dateRe.MatchString(toks[i]) {
			if dt, err := time.Parse(dateLayout, toks[i]); err == nil {
				t.CreationDate = &dt
				i++
			}
		}
	}

	// 4) Priority (can appear after x, dates)
	if i < len(toks) && len(toks[i]) == 3 && toks[i][0] == '(' && toks[i][2] == ')' && toks[i][1] >= 'A' && toks[i][1] <= 'Z' {
		r := rune(toks[i][1])
		t.Priority = &r
		i++
	}

	// 5) If not completed, check for priority at start
	if !t.Completed {
		if i < len(toks) && len(toks[i]) == 3 && toks[i][0] == '(' && toks[i][2] == ')' && toks[i][1] >= 'A' && toks[i][1] <= 'Z' {
			r := rune(toks[i][1])
			t.Priority = &r
			i++
		}
		// Creation date for incomplete tasks
		if i < len(toks) && dateRe.MatchString(toks[i]) {
			if dt, err := time.Parse(dateLayout, toks[i]); err == nil {
				t.CreationDate = &dt
				i++
			}
		}
	}

	// 6) Parse remaining tokens
	descParts := make([]string, 0)
	for ; i < len(toks); i++ {
		tok := toks[i]
		if strings.HasPrefix(tok, "+") && len(tok) > 1 {
			t.Projects = append(t.Projects, tok[1:])
			continue
		}
		if strings.HasPrefix(tok, "@") && len(tok) > 1 {
			if tok != "@todo" { // exclude @todo context
				t.Contexts = append(t.Contexts, tok[1:])
			}
			continue
		}
		// Special case: location:"value with spaces"
		if strings.HasPrefix(tok, "location:\"") {
			val := tok[len("location:\""):]
			for {
				// If token ends with a quote, we've reached the end
				if strings.HasSuffix(val, "\"") {
					val = val[:len(val)-1]
					break
				}
				// Otherwise, append next token
				i++
				if i >= len(toks) {
					// Unterminated quote, treat as is
					break
				}
				val += " " + toks[i]
			}
			t.Metadata["location"] = append(t.Metadata["location"], val)
			continue
		}
		if !strings.ContainsAny(tok, " \t") && strings.Contains(tok, ":") {
			parts := strings.SplitN(tok, ":", 2)
			k, v := parts[0], parts[1]
			if k != "" && v != "" && !isProtocolKey(k) {
				t.Metadata[k] = append(t.Metadata[k], v)
				if k == "due" && dateRe.MatchString(v) {
					if dt, err := time.Parse(dateLayout, v); err == nil {
						t.DueDate = &dt
					}
				}
				continue
			}

		}
		descParts = append(descParts, tok)
	}
	t.Description = strings.TrimSpace(strings.Join(descParts, " "))

	if t.Completed && t.CompletionDate == nil {
		return t, errors.New("completed task missing completion date (spec requires completion date directly after 'x')")
	}

	return t, nil
}

// splitTokens splits a line on whitespace preserving token order and ignoring extra spaces.
func splitTokens(s string) []string {
	if s == "" {
		return nil
	}
	return spaceRe.Split(strings.TrimSpace(s), -1)
}