Detect charset and convert non UTF-8 files for display (#4950)
* Detect charset and convert non UTF-8 files for display * Refactor and move function to correct module * Revert unrelated changes * More unrelated changes * Duplicate content for small text to have better encoding detection * Check if original content is valid before duplicating it
This commit is contained in:
parent
6780661192
commit
81702e6ec9
3 changed files with 44 additions and 4 deletions
|
@ -59,7 +59,22 @@ func DetectEncoding(content []byte) (string, error) {
|
|||
return "UTF-8", nil
|
||||
}
|
||||
|
||||
result, err := chardet.NewTextDetector().DetectBest(content)
|
||||
textDetector := chardet.NewTextDetector()
|
||||
var detectContent []byte
|
||||
if len(content) < 1024 {
|
||||
// Check if original content is valid
|
||||
if _, err := textDetector.DetectBest(content); err != nil {
|
||||
return "", err
|
||||
}
|
||||
times := 1024 / len(content)
|
||||
detectContent = make([]byte, 0, times*len(content))
|
||||
for i := 0; i < times; i++ {
|
||||
detectContent = append(detectContent, content...)
|
||||
}
|
||||
} else {
|
||||
detectContent = content
|
||||
}
|
||||
result, err := textDetector.DetectBest(detectContent)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue