TheAnachronism/docspell
1
0
Fork 0
mirror of https://github.com/TheAnachronism/docspell.git synced 2025-06-22 02:18:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Simplify MimeType class and parse mimetypes in a more lenient way

Browse Source
This commit is contained in:
eikek
2021-09-23 14:09:39 +02:00
parent 617f931a14
commit 1761526e20
7 changed files with 321 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
modules/files/src/main/scala/docspell/files/TikaMimetype.scala
View File

@ -31,10 +31,10 @@ object TikaMimetype {
private def convert(mt: MediaType): MimeType =
Option(mt) match {
case Some(_) =>
val params = mt.getParameters.asScala.toMap
val cs = mt.getParameters.asScala.toMap.get("charset").getOrElse("unknown")
val primary = mt.getType
val sub = mt.getSubtype
normalize(MimeType(primary, sub, params))
normalize(MimeType(primary, sub, None).withCharsetName(cs))
case None =>
MimeType.octetStream
}
@ -48,8 +48,8 @@ object TikaMimetype {
private def normalize(in: MimeType): MimeType =
in match {
case MimeType(_, sub, p) if sub contains "xhtml" =>
MimeType.html.copy(params = p)
case MimeType(_, sub, cs) if sub contains "xhtml" =>
MimeType.html.copy(charset = cs)
case _ => in
}
@ -86,7 +86,7 @@ object TikaMimetype {
def resolve[F[_]: Sync](dt: DataType, data: Stream[F, Byte]): F[MimeType] =
dt match {
case DataType.Exact(mt) =>
mt.resolveCharset match {
mt.charset match {
case None if mt.primary == "text" =>
detectCharset[F](data, MimeTypeHint.advertised(mt))
.map {