forked from forgejo/forgejo
Backport #28935 by @silverwind
The `ToUTF8*` functions were stripping BOM, while BOM is actually valid
in UTF8, so the stripping must be optional depending on use case. This
does:
- Add a options struct to all `ToUTF8*` functions, that by default will
strip BOM to preserve existing behaviour
- Remove `ToUTF8` function, it was dead code
- Rename `ToUTF8WithErr` to `ToUTF8`
- Preserve BOM in Monaco Editor
- Remove a unnecessary newline in the textarea value. Browsers did
ignore it, it seems but it's better not to rely on this behaviour.
Fixes: https://github.com/go-gitea/gitea/issues/28743
Related: https://github.com/go-gitea/gitea/issues/6716 which seems to
have once introduced a mechanism that strips and re-adds the BOM, but
from what I can tell, this mechanism was removed at some point after
that PR.
Co-authored-by: silverwind <me@silverwind.io>
(cherry picked from commit b8e6cffd31
)
This commit is contained in:
parent
afdce6bd45
commit
b272224918
13 changed files with 69 additions and 134 deletions
|
@ -43,7 +43,7 @@ func RenderFile(ctx *context.Context) {
|
|||
st := typesniffer.DetectContentType(buf)
|
||||
isTextFile := st.IsText()
|
||||
|
||||
rd := charset.ToUTF8WithFallbackReader(io.MultiReader(bytes.NewReader(buf), dataRc))
|
||||
rd := charset.ToUTF8WithFallbackReader(io.MultiReader(bytes.NewReader(buf), dataRc), charset.ConvertOpts{})
|
||||
|
||||
if markupType := markup.Type(blob.Name()); markupType == "" {
|
||||
if isTextFile {
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue