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.
This commit is contained in:
John O'Keefe
2026-10-03 14:17:58 -04:00
parent ad1ad11fb5
commit f2629942e4
2 changed files with 57 additions and 22 deletions
+26 -22
View File
@@ -974,30 +974,12 @@ func (s *MediaScanner) processMediaFile(ctx context.Context, path string) (bool,
// Set format group, total characters, and chapter count
mimeType := s.getMimeType(path)
ext := strings.ToLower(filepath.Ext(path))
var formatGroup string
var isReflowable, hasFixedLayout bool
switch ext {
case ".epub":
var epubIsFixedLayout bool
if ext == ".epub" {
isFixed, fixedErr := s.DetectFixedLayoutEPUB(path)
if fixedErr == nil && isFixed {
formatGroup = "fixed_layout"
hasFixedLayout = true
} else {
formatGroup = "reflowable"
isReflowable = true
}
case ".mobi", ".azw", ".azw3", ".fb2", ".txt":
formatGroup = "reflowable"
isReflowable = true
case ".pdf", ".djvu":
formatGroup = "fixed_layout"
hasFixedLayout = true
case ".cbz", ".cbr", ".cb7", ".cbt":
formatGroup = "comic_archive"
hasFixedLayout = true
default:
formatGroup = "unknown"
epubIsFixedLayout = fixedErr == nil && isFixed
}
formatGroup, isReflowable, hasFixedLayout := classifyFormatGroup(ext, epubIsFixedLayout)
err = s.db.UpdateMediaItemFormatGroup(ctx, database.UpdateMediaItemFormatGroupParams{
ID: createdItem.ID,
FormatGroup: formatGroup,
@@ -3880,6 +3862,28 @@ func (s *MediaScanner) detectFormatType(filePath string) string {
}
}
// classifyFormatGroup maps a lowercased file extension to the format
// group and layout flags stored on the media item. `.epub` is passed in
// with its detected fixed-layout flag because that check needs the file
// itself.
func classifyFormatGroup(ext string, epubIsFixedLayout bool) (formatGroup string, isReflowable, hasFixedLayout bool) {
switch ext {
case ".epub":
if epubIsFixedLayout {
return "fixed_layout", false, true
}
return "reflowable", true, false
case ".mobi", ".azw", ".azw3", ".fb2", ".txt", ".docx":
return "reflowable", true, false
case ".pdf", ".djvu":
return "fixed_layout", false, true
case ".cbz", ".cbr", ".cb7", ".cbt":
return "comic_archive", false, true
default:
return "unknown", false, false
}
}
// extractHashInfo calculates hash and extracts OPF identifiers for a file
func (s *MediaScanner) extractHashInfo(filePath string) (*HashInfo, *FormatInfo, error) {
// Calculate SHA-256