// ingestion/internal/textutil/truncate_test.go
package textutil_test

import (
	"strings"
	"testing"
	"unicode/utf8"

	"github.com/mathiasbq/hyperguild/ingestion/internal/textutil"
)

func TestTruncate_ShortStringsAreUntouched(t *testing.T) {
	for _, s := range []string{"", "kort", "räv", "a — b"} {
		if got := textutil.Truncate(s, 100); got != s {
			t.Errorf("Truncate(%q, 100) = %q, want it unchanged", s, got)
		}
	}
}

func TestTruncate_NeverCutsInsideACharacter(t *testing.T) {
	// The property, not an example: whatever the limit, the result must be
	// valid UTF-8. Byte-slicing Swedish text (å ä ö) or an em dash produces
	// an orphaned lead byte, which is what corrupted wiki/index.md (#93).
	s := strings.Repeat("räv — ål — ökäd ", 20)

	for limit := 0; limit <= len(s)+5; limit++ {
		got := textutil.Truncate(s, limit)
		if !utf8.ValidString(got) {
			t.Fatalf("Truncate(s, %d) produced invalid UTF-8: %q", limit, got)
		}
	}
}

func TestTruncate_CountsCharactersNotBytes(t *testing.T) {
	// "räv" is 4 bytes, 3 runes. A byte-based limit of 3 would cut inside the
	// "ä"; a rune-based one returns it whole.
	if got := textutil.Truncate("räv", 3); got != "räv" {
		t.Errorf("Truncate(\"räv\", 3) = %q, want the whole word", got)
	}

	got := textutil.Truncate("räven springer", 5)
	if utf8.RuneCountInString(got) != 6 { // 5 runes + the ellipsis
		t.Errorf("Truncate(...) = %q, want 5 runes plus the marker", got)
	}
	if !strings.HasSuffix(got, "…") {
		t.Errorf("Truncate(...) = %q, want it marked as truncated", got)
	}
}

func TestTruncate_MarksOnlyWhenSomethingWasDropped(t *testing.T) {
	// An ellipsis on text that was not cut is a lie about the content.
	if got := textutil.Truncate("räv", 10); strings.HasSuffix(got, "…") {
		t.Errorf("Truncate(%q, 10) = %q, want no truncation marker", "räv", got)
	}
	if got := textutil.Truncate("räv", 3); strings.HasSuffix(got, "…") {
		t.Errorf("exact-length input must not be marked: %q", got)
	}
}

func TestTruncate_NonPositiveLimitYieldsNothingRatherThanPanicking(t *testing.T) {
	for _, limit := range []int{0, -1, -100} {
		if got := textutil.Truncate("räven", limit); got != "" {
			t.Errorf("Truncate(_, %d) = %q, want empty", limit, got)
		}
	}
}