Phase 1 Week 2: Format detection and progress conversion engine

- Add internal/sync package with format detection - FormatGroup types: reflowable, fixed_layout, comic_archive - DetectFormatGroup() function based on mimetype and file extension - MimeType mappings for common ebook formats - Progress conversion engine with: - ConvertProgress() between format groups - Extract percentage from various progress formats - PageToPercentage / PercentageToPage helpers - CharacterToPercentage / PercentageToCharacter helpers - MergeProgress() with 'max progress wins' strategy - FormatProgressForDisplay() for UI rendering - Add sqlc queries for format detection and progress updates - BulkUpdateFormatGroups query for auto-format detection - GetUniversalProgress query with all location references - UpdateUniversalProgress query with device sync metadata - ReadingHistory queries for session tracking
2026-01-30 16:07:00 -05:00
parent fa4a9c35bb
commit bb3c32c59f
6 changed files with 3101 additions and 0 deletions
@@ -0,0 +1,132 @@
+package sync
+
+import (
+	"path/filepath"
+	"strings"
+)
+
+// FormatGroup represents the three main format categories
+type FormatGroup string
+
+const (
+	FormatGroupReflowable   FormatGroup = "reflowable"
+	FormatGroupFixedLayout  FormatGroup = "fixed_layout"
+	FormatGroupComicArchive FormatGroup = "comic_archive"
+	FormatGroupUnknown      FormatGroup = "unknown"
+)
+
+// MimeType mappings for common ebook formats
+var mimeTypes = map[string]string{
+	".epub": "application/epub+zip",
+	".mobi": "application/x-mobipocket-ebook",
+	".azw":  "application/x-mobipocket-ebook",
+	".azw3": "application/vnd.amazon.mobi8-ebook",
+	".pdf":  "application/pdf",
+	".djvu": "image/vnd.djvu",
+	".cbz":  "application/x-cbz",
+	".cbr":  "application/x-cbr",
+	".cb7":  "application/x-cb7",
+	".cbt":  "application/x-cbt",
+	".fb2":  "application/x-fictionbook+xml",
+	".txt":  "text/plain",
+	".rtf":  "application/rtf",
+	".doc":  "application/msword",
+	".docx": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+	".lit":  "application/x-ms-reader",
+	".pdb":  "application/vnd.palm",
+	".prc":  "application/vnd.palm",
+}
+
+// ReflowableFormats are formats that support text reflow
+var ReflowableFormats = map[string]bool{
+	".epub": true,
+	".mobi": true,
+	".azw":  true,
+	".azw3": true,
+	".fb2":  true,
+	".txt":  true,
+	".rtf":  true,
+	".doc":  true,
+	".docx": true,
+	".lit":  true,
+	".pdb":  true,
+	".prc":  true,
+}
+
+// FixedLayoutFormats are formats with fixed page layouts
+var FixedLayoutFormats = map[string]bool{
+	".pdf":  true,
+	".djvu": true,
+}
+
+// ComicArchiveFormats are comic archive formats
+var ComicArchiveFormats = map[string]bool{
+	".cbz": true,
+	".cbr": true,
+	".cb7": true,
+	".cbt": true,
+}
+
+// DetectFormatGroup determines the format group based on mimetype and file path
+func DetectFormatGroup(mimetype string, filePath string) FormatGroup {
+	ext := strings.ToLower(filepath.Ext(filePath))
+
+	// Check by mimetype first
+	switch mimetype {
+	case "application/epub+zip",
+		"application/x-mobipocket-ebook",
+		"application/vnd.amazon.mobi8-ebook",
+		"application/x-fictionbook+xml",
+		"text/plain":
+		return FormatGroupReflowable
+
+	case "application/pdf",
+		"image/vnd.djvu":
+		return FormatGroupFixedLayout
+
+	case "application/x-cbr",
+		"application/x-cbz",
+		"application/x-cb7",
+		"application/x-cbt":
+		return FormatGroupComicArchive
+	}
+
+	// Fall back to file extension
+	if ReflowableFormats[ext] {
+		return FormatGroupReflowable
+	}
+
+	if FixedLayoutFormats[ext] {
+		return FormatGroupFixedLayout
+	}
+
+	if ComicArchiveFormats[ext] {
+		return FormatGroupComicArchive
+	}
+
+	return FormatGroupUnknown
+}
+
+// GetMimeType returns the mimetype for a given file extension
+func GetMimeType(filePath string) string {
+	ext := strings.ToLower(filepath.Ext(filePath))
+	if mt, ok := mimeTypes[ext]; ok {
+		return mt
+	}
+	return ""
+}
+
+// IsReflowable checks if a format is reflowable
+func IsReflowable(formatGroup FormatGroup) bool {
+	return formatGroup == FormatGroupReflowable
+}
+
+// HasFixedLayout checks if a format has fixed layout
+func HasFixedLayout(formatGroup FormatGroup) bool {
+	return formatGroup == FormatGroupFixedLayout
+}
+
+// IsComicArchive checks if a format is a comic archive
+func IsComicArchive(formatGroup FormatGroup) bool {
+	return formatGroup == FormatGroupComicArchive
+}