forgejo/modules/charset/escape.go
zeripath 72524adf3f
Ensure that plain files are rendered correctly even when containing ambiguous characters (#22017) (#22160)
Backport #22017

As recognised in #21841 the rendering of plain text files is somewhat
incorrect when there are ambiguous characters as the html code is double
escaped. In fact there are several more problems here.

We have a residual isRenderedHTML which is actually simply escaping the
file - not rendering it. This is badly named and gives the wrong
impression.

There is also unusual behaviour whether the file is called a Readme or
not and there is no way to get to the source code if the file is called
README.

In reality what should happen is different depending on whether the file
is being rendered a README at the bottom of the directory view or not.

1. If it is rendered as a README on a directory - it should simply be
escaped and rendered as `<pre>` text.
2. If it is rendered as a file then it should be rendered as source
code.

This PR therefore does:
1. Rename IsRenderedHTML to IsPlainText
2. Readme files rendered at the bottom of the directory are rendered
without line numbers
3. Otherwise plain text files are rendered as source code.

Replace #21841

Signed-off-by: Andrew Thornton <art27@cantab.net>
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
2022-12-19 23:51:21 +08:00

88 lines
3.2 KiB
Go

// Copyright 2022 The Gitea Authors. All rights reserved.
// Use of this source code is governed by a MIT-style
// license that can be found in the LICENSE file.
//go:generate go run invisible/generate.go -v -o ./invisible_gen.go
//go:generate go run ambiguous/generate.go -v -o ./ambiguous_gen.go ambiguous/ambiguous.json
package charset
import (
"bufio"
"io"
"strings"
"code.gitea.io/gitea/modules/log"
"code.gitea.io/gitea/modules/translation"
)
// RuneNBSP is the codepoint for NBSP
const RuneNBSP = 0xa0
// EscapeControlHTML escapes the unicode control sequences in a provided html document
func EscapeControlHTML(text string, locale translation.Locale, allowed ...rune) (escaped *EscapeStatus, output string) {
sb := &strings.Builder{}
outputStream := &HTMLStreamerWriter{Writer: sb}
streamer := NewEscapeStreamer(locale, outputStream, allowed...).(*escapeStreamer)
if err := StreamHTML(strings.NewReader(text), streamer); err != nil {
streamer.escaped.HasError = true
log.Error("Error whilst escaping: %v", err)
}
return streamer.escaped, sb.String()
}
// EscapeControlReaders escapes the unicode control sequences in a provided reader of HTML content and writer in a locale and returns the findings as an EscapeStatus and the escaped []byte
func EscapeControlReader(reader io.Reader, writer io.Writer, locale translation.Locale, allowed ...rune) (escaped *EscapeStatus, err error) {
outputStream := &HTMLStreamerWriter{Writer: writer}
streamer := NewEscapeStreamer(locale, outputStream, allowed...).(*escapeStreamer)
if err = StreamHTML(reader, streamer); err != nil {
streamer.escaped.HasError = true
log.Error("Error whilst escaping: %v", err)
}
return streamer.escaped, err
}
// EscapeControlStringReader escapes the unicode control sequences in a provided reader of string content and writer in a locale and returns the findings as an EscapeStatus and the escaped []byte
func EscapeControlStringReader(reader io.Reader, writer io.Writer, locale translation.Locale, allowed ...rune) (escaped *EscapeStatus, err error) {
bufRd := bufio.NewReader(reader)
outputStream := &HTMLStreamerWriter{Writer: writer}
streamer := NewEscapeStreamer(locale, outputStream, allowed...).(*escapeStreamer)
for {
line, rdErr := bufRd.ReadString('\n')
if len(line) > 0 {
if err := streamer.Text(line); err != nil {
streamer.escaped.HasError = true
log.Error("Error whilst escaping: %v", err)
return streamer.escaped, err
}
}
if rdErr != nil {
if rdErr != io.EOF {
err = rdErr
}
break
}
if err := streamer.SelfClosingTag("br"); err != nil {
streamer.escaped.HasError = true
return streamer.escaped, err
}
}
return streamer.escaped, err
}
// EscapeControlString escapes the unicode control sequences in a provided string and returns the findings as an EscapeStatus and the escaped string
func EscapeControlString(text string, locale translation.Locale, allowed ...rune) (escaped *EscapeStatus, output string) {
sb := &strings.Builder{}
outputStream := &HTMLStreamerWriter{Writer: sb}
streamer := NewEscapeStreamer(locale, outputStream, allowed...).(*escapeStreamer)
if err := streamer.Text(text); err != nil {
streamer.escaped.HasError = true
log.Error("Error whilst escaping: %v", err)
}
return streamer.escaped, sb.String()
}