sift/internal/dcache/pdf_test.go

package dcache_test

// P5a task 03: the PDF document cache. One entry per (URL, caller class): how to revalidate it,
// its metadata (opaque JSON here) and the text of every extracted page.

import (
	"path/filepath"
	"strings"
	"testing"
	"time"

	"git.wntrmute.dev/kyle/sift/internal/dcache"
)

func openDB(t *testing.T, maxBytes int64) *dcache.DB {
	t.Helper()
	db, err := dcache.Open(filepath.Join(t.TempDir(), "c.db"), maxBytes, nil)
	if err != nil {
		t.Fatal(err)
	}
	t.Cleanup(func() { _ = db.Close() })
	return db
}

func entry(pages ...string) dcache.PDFEntry {
	return dcache.PDFEntry{
		ContentHash:  "sha256:abc",
		ETag:         `"v1"`,
		LastModified: "Fri, 25 Sep 2026 12:00:00 GMT",
		FetchedAt:    time.Date(2026, 9, 25, 20, 0, 0, 0, time.UTC),
		Meta:         []byte(`{"pages":3,"title":"T","outline":[]}`),
		Pages:        pages,
	}
}

func TestPDFRoundTrip(t *testing.T) {
	db := openDB(t, 0)
	k := dcache.PDFKey("https://example.org/a.pdf", dcache.ClassFleet)
	if _, ok := db.GetPDF(k); ok {
		t.Fatal("hit on an empty cache")
	}
	want := entry("page one", "page two", "", "page four") // an empty page keeps its place
	db.PutPDF(k, want)
	got, ok := db.GetPDF(k)
	if !ok {
		t.Fatal("miss after put")
	}
	if got.ContentHash != want.ContentHash || got.ETag != want.ETag || got.LastModified != want.LastModified ||
		!got.FetchedAt.Equal(want.FetchedAt) || string(got.Meta) != string(want.Meta) {
		t.Errorf("got %+v, want %+v", got, want)
	}
	if len(got.Pages) != 4 || got.Pages[0] != "page one" || got.Pages[2] != "" || got.Pages[3] != "page four" {
		t.Errorf("pages = %q", got.Pages)
	}
	// A second put replaces the whole entry, pages included.
	db.PutPDF(k, entry("only"))
	got, _ = db.GetPDF(k)
	if len(got.Pages) != 1 || got.Pages[0] != "only" {
		t.Errorf("after replace, pages = %q; want [only]", got.Pages)
	}
}

func TestPDFKeyPartitions(t *testing.T) {
	db := openDB(t, 0)
	u := "https://example.org/a.pdf"
	fleet, restricted := dcache.PDFKey(u, dcache.ClassFleet), dcache.PDFKey(u, dcache.ClassRestricted)
	if fleet == restricted {
		t.Fatal("the same key for both caller classes")
	}
	db.PutPDF(restricted, entry("secret page"))
	if _, ok := db.GetPDF(fleet); ok {
		t.Error("a restricted caller's document is visible to the fleet")
	}
	if dcache.PDFKey(u, dcache.ClassFleet) != fleet || dcache.PDFKey("https://example.org/b.pdf", dcache.ClassFleet) == fleet {
		t.Error("PDFKey must be deterministic and differ per URL")
	}
	if strings.Contains(fleet, "example.org") {
		t.Error("the key must not carry the URL in the clear (it is hashed like the other keys)")
	}
}

func TestPDFTouch(t *testing.T) {
	db := openDB(t, 0)
	k := dcache.PDFKey("https://example.org/a.pdf", dcache.ClassFleet)
	db.PutPDF(k, entry("x"))
	later := time.Date(2026, 9, 26, 20, 0, 0, 0, time.UTC)
	db.TouchPDF(k, later) // after a 304: the text is unchanged, only its freshness moves
	got, _ := db.GetPDF(k)
	if !got.FetchedAt.Equal(later) || len(got.Pages) != 1 {
		t.Errorf("after touch: %+v", got)
	}
	db.TouchPDF(dcache.PDFKey("https://nope", dcache.ClassFleet), later) // a miss is a no-op
}

// Documents count toward maxBytes and are evicted whole, oldest use first.
func TestPDFEviction(t *testing.T) {
	db := openDB(t, 300<<10) // 300 KiB
	big := strings.Repeat("z", 50<<10)
	var keys []string
	for i := 0; i < 10; i++ { // 10 × 2 pages × 50 KiB = 1 MiB of text
		k := dcache.PDFKey("https://example.org/"+string(rune('a'+i))+".pdf", dcache.ClassFleet)
		keys = append(keys, k)
		db.PutPDF(k, entry(big, big))
	}
	if db.Size() > 300<<10 {
		t.Errorf("size %d after puts, want ≤ maxBytes %d", db.Size(), 300<<10)
	}
	if _, ok := db.GetPDF(keys[9]); !ok {
		t.Error("the newest document was evicted")
	}
	if _, ok := db.GetPDF(keys[0]); ok {
		t.Error("the oldest document survived; eviction did not reach PDF entries")
	}
	for _, k := range keys {
		if e, ok := db.GetPDF(k); ok && len(e.Pages) != 2 {
			t.Errorf("a partly evicted document: %d pages", len(e.Pages))
		}
	}
}

func TestPDFNilDB(t *testing.T) {
	var db *dcache.DB
	db.PutPDF("k", entry("x"))
	db.TouchPDF("k", time.Now())
	if _, ok := db.GetPDF("k"); ok {
		t.Error("nil DB returned a hit")
	}
}