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>

4 files changed, 41 insertions, 23 deletions

diff --git a/modules/charset/escape.go b/modules/charset/escape.go
index b264a569ff..e600998937 100644
--- a/modules/charset/escape.go
+++ b/modules/charset/escape.go
@@ -9,6 +9,7 @@
 package charset
 
 import (
+	"bufio"
 	"io"
 	"strings"
 
@@ -32,7 +33,7 @@ func EscapeControlHTML(text string, locale translation.Locale, allowed ...rune)
 	return streamer.escaped, sb.String()
 }
 
-// EscapeControlReaders escapes the unicode control sequences in a provider reader and writer in a locale and returns the findings as an EscapeStatus and the escaped []byte
+// 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)
@@ -44,6 +45,35 @@ func EscapeControlReader(reader io.Reader, writer io.Writer, locale translation.
 	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{}
diff --git a/routers/web/repo/view.go b/routers/web/repo/view.go
index d35ec48df0..293a957266 100644
--- a/routers/web/repo/view.go
+++ b/routers/web/repo/view.go
@@ -10,7 +10,6 @@ import (
 	gocontext "context"
 	"encoding/base64"
 	"fmt"
-	gotemplate "html/template"
 	"io"
 	"net/http"
 	"net/url"
@@ -342,15 +341,13 @@ func renderReadmeFile(ctx *context.Context, readmeFile *namedBlob, readmeTreelin
 		if err != nil {
 			log.Error("Render failed for %s in %-v: %v Falling back to rendering source", readmeFile.name, ctx.Repo.Repository, err)
 			buf := &bytes.Buffer{}
-			ctx.Data["EscapeStatus"], _ = charset.EscapeControlReader(rd, buf, ctx.Locale)
-			ctx.Data["FileContent"] = strings.ReplaceAll(
-				gotemplate.HTMLEscapeString(buf.String()), "\n", `<br>`,
-			)
+			ctx.Data["EscapeStatus"], _ = charset.EscapeControlStringReader(rd, buf, ctx.Locale)
+			ctx.Data["FileContent"] = buf.String()
 		}
 	} else {
-		ctx.Data["IsRenderedHTML"] = true
+		ctx.Data["IsPlainText"] = true
 		buf := &bytes.Buffer{}
-		ctx.Data["EscapeStatus"], err = charset.EscapeControlReader(rd, &charset.BreakWriter{Writer: buf}, ctx.Locale, charset.RuneNBSP)
+		ctx.Data["EscapeStatus"], err = charset.EscapeControlStringReader(rd, buf, ctx.Locale)
 		if err != nil {
 			log.Error("Read failed: %v", err)
 		}
@@ -522,15 +519,6 @@ func renderFile(ctx *context.Context, entry *git.TreeEntry, treeLink, rawLink st
 			}
 			// to prevent iframe load third-party url
 			ctx.Resp.Header().Add("Content-Security-Policy", "frame-src 'self'")
-		} else if readmeExist && !shouldRenderSource {
-			buf := &bytes.Buffer{}
-			ctx.Data["IsRenderedHTML"] = true
-
-			ctx.Data["EscapeStatus"], _ = charset.EscapeControlReader(rd, buf, ctx.Locale)
-
-			ctx.Data["FileContent"] = strings.ReplaceAll(
-				gotemplate.HTMLEscapeString(buf.String()), "\n", `<br>`,
-			)
 		} else {
 			buf, _ := io.ReadAll(rd)
 
diff --git a/templates/repo/settings/lfs_file.tmpl b/templates/repo/settings/lfs_file.tmpl
index ce3c39eac2..6d20aaddef 100644
--- a/templates/repo/settings/lfs_file.tmpl
+++ b/templates/repo/settings/lfs_file.tmpl
@@ -17,11 +17,11 @@
 			</h4>
 			<div class="ui attached table unstackable segment">
 				{{template "repo/unicode_escape_prompt" dict "EscapeStatus" .EscapeStatus "root" $}}
-				<div class="file-view{{if .IsMarkup}} markup {{.MarkupType}}{{else if .IsRenderedHTML}} plain-text{{else if .IsTextFile}} code-view{{end}}">
+				<div class="file-view{{if .IsMarkup}} markup {{.MarkupType}}{{else if .IsPlainText}} plain-text{{else if .IsTextFile}} code-view{{end}}">
 					{{if .IsMarkup}}
 						{{if .FileContent}}{{.FileContent | Safe}}{{end}}
-					{{else if .IsRenderedHTML}}
-						<pre>{{if .FileContent}}{{.FileContent | Str2html}}{{end}}</pre>
+					{{else if .IsPlainText}}
+						<pre>{{if .FileContent}}{{.FileContent | Safe}}{{end}}</pre>
 					{{else if not .IsTextFile}}
 						<div class="view-raw ui center">
 							{{if .IsImageFile}}
diff --git a/templates/repo/view_file.tmpl b/templates/repo/view_file.tmpl
index ed2162a414..14031cec45 100644
--- a/templates/repo/view_file.tmpl
+++ b/templates/repo/view_file.tmpl
@@ -82,11 +82,11 @@
 		{{if not (or .IsMarkup .IsRenderedHTML)}}
 			{{template "repo/unicode_escape_prompt" dict "EscapeStatus" .EscapeStatus "root" $}}
 		{{end}}
-		<div class="file-view{{if .IsMarkup}} markup {{.MarkupType}}{{else if .IsRenderedHTML}} plain-text{{else if .IsTextSource}} code-view{{end}}">
+		<div class="file-view{{if .IsMarkup}} markup {{.MarkupType}}{{else if .IsPlainText}} plain-text{{else if .IsTextSource}} code-view{{end}}">
 			{{if .IsMarkup}}
 				{{if .FileContent}}{{.FileContent | Safe}}{{end}}
-			{{else if .IsRenderedHTML}}
-				<pre>{{if .FileContent}}{{.FileContent | Str2html}}{{end}}</pre>
+			{{else if .IsPlainText}}
+				<pre>{{if .FileContent}}{{.FileContent | Safe}}{{end}}</pre>
 			{{else if not .IsTextSource}}
 				<div class="view-raw ui center">
 					{{if .IsImageFile}}