Files
bookhoard/internal/services/media_scanner_test.go
T
John O'Keefe f2629942e4 fix(scanner): classify .docx as reflowable — was landing format_group unknown
.docx is accepted for ingest but the format-group switch had no case
for it, so every DOCX row stored format_group 'unknown' with
is_reflowable=false. Extract the classification switch into a pure
classifyFormatGroup helper with a table test, and classify .docx
reflowable like the other reflowable text formats (.rtf/.doc stay out
until they are readable client-side). Existing rows: dev alice (DOCX)
reclassified by hand; production rows reclassify on rescan.
2026-10-03 14:17:58 -04:00

153 lines
4.7 KiB
Go

package services
import (
"os"
"path/filepath"
"testing"
"time"
"bookhoard/internal/database"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func setupTestDB(t *testing.T) *database.Queries {
return &database.Queries{}
}
func TestMarkDirectoryDirty(t *testing.T) {
db := setupTestDB(t)
scanner := NewMediaScanner(db)
scanner.folders = []string{"/test/folder"}
scanner.markDirectoryDirty("/test/folder/subdir")
scanner.dirtyDirsMu.RLock()
_, exists := scanner.dirtyDirs["/test/folder/subdir"]
scanner.dirtyDirsMu.RUnlock()
assert.True(t, exists, "Directory should be marked dirty")
}
func TestMarkDirectoryDirty_IgnoresNonWatchedPaths(t *testing.T) {
db := setupTestDB(t)
scanner := NewMediaScanner(db)
scanner.folders = []string{"/test/folder"}
scanner.markDirectoryDirty("/other/folder")
scanner.dirtyDirsMu.RLock()
_, exists := scanner.dirtyDirs["/other/folder"]
scanner.dirtyDirsMu.RUnlock()
assert.False(t, exists, "Non-watched directory should be ignored")
}
func TestMarkDirectoryDirty_SmartEventMerging(t *testing.T) {
db := setupTestDB(t)
scanner := NewMediaScanner(db)
scanner.folders = []string{"/test/folder"}
scanner.markDirectoryDirty("/test/folder/subdir1")
scanner.dirtyDirsMu.RLock()
_, exists1 := scanner.dirtyDirs["/test/folder/subdir1"]
scanner.dirtyDirsMu.RUnlock()
assert.True(t, exists1)
scanner.markDirectoryDirty("/test/folder")
scanner.dirtyDirsMu.RLock()
_, parentExists := scanner.dirtyDirs["/test/folder"]
_, childExists := scanner.dirtyDirs["/test/folder/subdir1"]
scanner.dirtyDirsMu.RUnlock()
assert.True(t, parentExists, "Parent should exist")
assert.False(t, childExists, "Child should be removed (consolidated)")
}
func TestWaitForFileStability_StableFile(t *testing.T) {
db := setupTestDB(t)
scanner := NewMediaScanner(db)
tmpDir := t.TempDir()
filePath := filepath.Join(tmpDir, "stable.epub")
err := os.WriteFile(filePath, []byte("test content"), 0644)
require.NoError(t, err)
assert.True(t, scanner.waitForFileStability(filePath))
}
func TestWaitForFileStability_UnstableFile(t *testing.T) {
db := setupTestDB(t)
scanner := NewMediaScanner(db)
tmpDir := t.TempDir()
filePath := filepath.Join(tmpDir, "unstable.epub")
file, err := os.Create(filePath)
require.NoError(t, err)
defer file.Close()
stableChan := make(chan bool)
go func() {
stableChan <- scanner.waitForFileStability(filePath)
}()
for i := 0; i < 3; i++ {
time.Sleep(100 * time.Millisecond)
file.WriteString("more data\n")
}
file.Close()
select {
case stable := <-stableChan:
assert.True(t, stable)
case <-time.After(7 * time.Second):
t.Fatal("waitForFileStability timeout")
}
}
func TestProcessDirtyDirectories_CollectsReadyDirs(t *testing.T) {
db := setupTestDB(t)
scanner := NewMediaScanner(db)
scanner.folders = []string{"/test/folder"}
scanner.dirtyDirsMu.Lock()
scanner.dirtyDirs["/test/folder/subdir"] = time.Now().Add(-15 * time.Second)
scanner.dirtyDirsMu.Unlock()
scanner.dirtyDirsMu.Lock()
now := time.Now()
readyDirs := make([]string, 0)
for dirPath, lastChange := range scanner.dirtyDirs {
if now.Sub(lastChange) >= 10*time.Second {
readyDirs = append(readyDirs, dirPath)
delete(scanner.dirtyDirs, dirPath)
}
}
scanner.dirtyDirsMu.Unlock()
assert.Equal(t, 1, len(readyDirs), "Should find one ready directory")
assert.Equal(t, "/test/folder/subdir", readyDirs[0])
scanner.dirtyDirsMu.RLock()
count := len(scanner.dirtyDirs)
scanner.dirtyDirsMu.RUnlock()
assert.Equal(t, 0, count, "Ready directory should be removed from dirty list")
}
func TestClassifyFormatGroup(t *testing.T) {
tests := []struct {
name string
ext string
epubFixed bool
group string
reflow bool
fixed bool
}{
{"EPUB reflowable", ".epub", false, "reflowable", true, false},
{"EPUB fixed-layout", ".epub", true, "fixed_layout", false, true},
{"MOBI", ".mobi", false, "reflowable", true, false},
{"FB2", ".fb2", false, "reflowable", true, false},
{"TXT", ".txt", false, "reflowable", true, false},
{"DOCX (was unknown before the fix)", ".docx", false, "reflowable", true, false},
{"PDF", ".pdf", false, "fixed_layout", false, true},
{"DJVU", ".djvu", false, "fixed_layout", false, true},
{"CBZ", ".cbz", false, "comic_archive", false, true},
{"unrecognized extension", ".xyz", false, "unknown", false, false},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
group, reflow, fixed := classifyFormatGroup(tt.ext, tt.epubFixed)
if group != tt.group || reflow != tt.reflow || fixed != tt.fixed {
t.Errorf("classifyFormatGroup(%q, %v) = (%q, %v, %v), want (%q, %v, %v)",
tt.ext, tt.epubFixed, group, reflow, fixed, tt.group, tt.reflow, tt.fixed)
}
})
}
}