Add trim selector parsing

internal/trim/selector.go

@@ -0,0 +1,156 @@
+package trim
+
+import (
+	"fmt"
+	"regexp"
+	"sort"
+	"strconv"
+	"strings"
+)
+
+var selectorElementPattern = regexp.MustCompile(`^([+-]?\d+)(?:\s*-\s*([+-]?\d+))?$`)
+
+// Selector represents a normalized union of segment IDs.
+type Selector struct {
+	ranges []idRange
+}
+
+type idRange struct {
+	start int
+	end   int
+}
+
+// ParseSelector parses an inline segment selector expression.
+func ParseSelector(input string) (Selector, error) {
+	if strings.TrimSpace(input) == "" {
+		return Selector{}, fmt.Errorf("selector cannot be empty")
+	}
+
+	parts := strings.Split(input, ",")
+	ranges := make([]idRange, 0, len(parts))
+	for index, raw := range parts {
+		element := strings.TrimSpace(raw)
+		if element == "" {
+			return Selector{}, fmt.Errorf("selector element %d cannot be empty", index+1)
+		}
+
+		rangeValue, err := parseElement(element)
+		if err != nil {
+			return Selector{}, fmt.Errorf("selector element %d %q: %w", index+1, element, err)
+		}
+		ranges = append(ranges, rangeValue)
+	}
+
+	normalized := normalizeRanges(ranges)
+	if len(normalized) == 0 {
+		return Selector{}, fmt.Errorf("selector cannot be empty")
+	}
+	return Selector{ranges: normalized}, nil
+}
+
+// Contains returns true when id is included by this selector.
+func (s Selector) Contains(id int) bool {
+	if id <= 0 {
+		return false
+	}
+	index := sort.Search(len(s.ranges), func(i int) bool {
+		return s.ranges[i].end >= id
+	})
+	if index == len(s.ranges) {
+		return false
+	}
+	rangeValue := s.ranges[index]
+	return id >= rangeValue.start && id <= rangeValue.end
+}
+
+// IDs returns a deterministic ascending list of unique segment IDs.
+func (s Selector) IDs() []int {
+	total := 0
+	for _, rangeValue := range s.ranges {
+		total += rangeValue.end - rangeValue.start + 1
+	}
+
+	ids := make([]int, 0, total)
+	for _, rangeValue := range s.ranges {
+		for id := rangeValue.start; id <= rangeValue.end; id++ {
+			ids = append(ids, id)
+		}
+	}
+	return ids
+}
+
+func parseElement(element string) (idRange, error) {
+	matches := selectorElementPattern.FindStringSubmatch(element)
+	if matches == nil {
+		return idRange{}, fmt.Errorf("malformed element")
+	}
+
+	start, err := parseID(matches[1])
+	if err != nil {
+		return idRange{}, err
+	}
+
+	if matches[2] == "" {
+		return idRange{start: start, end: start}, nil
+	}
+
+	end, err := parseID(matches[2])
+	if err != nil {
+		return idRange{}, fmt.Errorf("invalid range end: %w", err)
+	}
+	if start > end {
+		return idRange{}, fmt.Errorf("descending range %d-%d is invalid", start, end)
+	}
+	return idRange{start: start, end: end}, nil
+}
+
+func parseID(value string) (int, error) {
+	value = strings.TrimSpace(value)
+	if value == "" {
+		return 0, fmt.Errorf("missing segment ID")
+	}
+
+	id, err := strconv.Atoi(value)
+	if err != nil {
+		return 0, fmt.Errorf("segment ID must be an integer")
+	}
+	if id <= 0 {
+		return 0, fmt.Errorf("segment ID must be positive")
+	}
+	return id, nil
+}
+
+func normalizeRanges(in []idRange) []idRange {
+	if len(in) == 0 {
+		return nil
+	}
+
+	sorted := make([]idRange, len(in))
+	copy(sorted, in)
+	sort.Slice(sorted, func(i, j int) bool {
+		if sorted[i].start == sorted[j].start {
+			return sorted[i].end < sorted[j].end
+		}
+		return sorted[i].start < sorted[j].start
+	})
+
+	merged := make([]idRange, 0, len(sorted))
+	for _, next := range sorted {
+		if len(merged) == 0 {
+			merged = append(merged, next)
+			continue
+		}
+
+		last := &merged[len(merged)-1]
+		if next.start <= last.end+1 {
+			if next.end > last.end {
+				last.end = next.end
+			}
+			continue
+		}
+
+		merged = append(merged, next)
+	}
+
+	return merged
+}

internal/trim/selector_test.go

@@ -0,0 +1,127 @@
+package trim
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestParseSelectorSingleID(t *testing.T) {
+	selector, err := ParseSelector("1")
+	if err != nil {
+		t.Fatalf("parse failed: %v", err)
+	}
+	assertIDs(t, selector, []int{1})
+	assertContains(t, selector, map[int]bool{1: true, 2: false, 0: false, -1: false})
+}
+
+func TestParseSelectorInclusiveRange(t *testing.T) {
+	selector, err := ParseSelector("1-3")
+	if err != nil {
+		t.Fatalf("parse failed: %v", err)
+	}
+	assertIDs(t, selector, []int{1, 2, 3})
+}
+
+func TestParseSelectorCommaSeparatedCombination(t *testing.T) {
+	selector, err := ParseSelector("1-3,8,10-12")
+	if err != nil {
+		t.Fatalf("parse failed: %v", err)
+	}
+	assertIDs(t, selector, []int{1, 2, 3, 8, 10, 11, 12})
+}
+
+func TestParseSelectorWhitespaceTolerance(t *testing.T) {
+	selector, err := ParseSelector(" 1 - 3 ,  8 , 10 - 12 ")
+	if err != nil {
+		t.Fatalf("parse failed: %v", err)
+	}
+	assertIDs(t, selector, []int{1, 2, 3, 8, 10, 11, 12})
+}
+
+func TestParseSelectorDuplicatesAndOverlapsNormalizeUnion(t *testing.T) {
+	selector, err := ParseSelector("1-4,2,4,3-6,6")
+	if err != nil {
+		t.Fatalf("parse failed: %v", err)
+	}
+	assertIDs(t, selector, []int{1, 2, 3, 4, 5, 6})
+	assertContains(t, selector, map[int]bool{1: true, 5: true, 6: true, 7: false})
+}
+
+func TestParseSelectorDeterministicNormalizedOutput(t *testing.T) {
+	left, err := ParseSelector("8,1-3,2,10-12")
+	if err != nil {
+		t.Fatalf("parse left failed: %v", err)
+	}
+	right, err := ParseSelector("10-12,3,2,1,8")
+	if err != nil {
+		t.Fatalf("parse right failed: %v", err)
+	}
+
+	leftIDs := left.IDs()
+	rightIDs := right.IDs()
+	if !equalInts(leftIDs, rightIDs) {
+		t.Fatalf("normalized IDs mismatch: %v vs %v", leftIDs, rightIDs)
+	}
+}
+
+func TestParseSelectorFailures(t *testing.T) {
+	tests := []struct {
+		name      string
+		selector  string
+		wantError string
+	}{
+		{name: "empty", selector: "", wantError: "cannot be empty"},
+		{name: "whitespace only", selector: "   ", wantError: "cannot be empty"},
+		{name: "zero", selector: "0", wantError: "must be positive"},
+		{name: "negative", selector: "-1", wantError: "must be positive"},
+		{name: "range includes zero", selector: "0-2", wantError: "must be positive"},
+		{name: "descending range", selector: "10-1", wantError: "descending range"},
+		{name: "empty element", selector: "1,,2", wantError: "cannot be empty"},
+		{name: "trailing comma", selector: "1,", wantError: "cannot be empty"},
+		{name: "malformed alpha", selector: "abc", wantError: "malformed element"},
+		{name: "malformed range", selector: "1-2-3", wantError: "malformed element"},
+		{name: "missing end", selector: "1-", wantError: "malformed element"},
+		{name: "missing start", selector: "-2", wantError: "must be positive"},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			_, err := ParseSelector(test.selector)
+			if err == nil {
+				t.Fatalf("expected error for %q", test.selector)
+			}
+			if !strings.Contains(err.Error(), test.wantError) {
+				t.Fatalf("error = %q, want substring %q", err.Error(), test.wantError)
+			}
+		})
+	}
+}
+
+func assertIDs(t *testing.T, selector Selector, want []int) {
+	t.Helper()
+	got := selector.IDs()
+	if !equalInts(got, want) {
+		t.Fatalf("IDs = %v, want %v", got, want)
+	}
+}
+
+func assertContains(t *testing.T, selector Selector, checks map[int]bool) {
+	t.Helper()
+	for id, want := range checks {
+		if got := selector.Contains(id); got != want {
+			t.Fatalf("Contains(%d) = %t, want %t", id, got, want)
+		}
+	}
+}
+
+func equalInts(left []int, right []int) bool {
+	if len(left) != len(right) {
+		return false
+	}
+	for index := range left {
+		if left[index] != right[index] {
+			return false
+		}
+	}
+	return true
+}