1
0
Fork 0
mirror of https://codeberg.org/forgejo/forgejo.git synced 2024-11-22 08:42:32 -05:00
forgejo/modules/markup/sanitizer.go
zeripath 27757714d0 Change markdown rendering from blackfriday to goldmark (#9533)
* Move to goldmark

Markdown rendering moved from blackfriday to the goldmark.

Multiple subtle changes required to the goldmark extensions to keep
current rendering and defaults.

Can go further with goldmark linkify and have this work within markdown
rendering making the link processor unnecessary.

Need to think about how to go about allowing extensions - at present it
seems that these would be hard to do without recompilation.

* linter fixes

Co-authored-by: Lauris BH <lauris@nix.lv>
2019-12-31 03:53:28 +02:00

86 lines
2.6 KiB
Go

// Copyright 2017 The Gitea Authors. All rights reserved.
// Copyright 2017 The Gogs Authors. All rights reserved.
// Use of this source code is governed by a MIT-style
// license that can be found in the LICENSE file.
package markup
import (
"bytes"
"io"
"regexp"
"sync"
"code.gitea.io/gitea/modules/setting"
"github.com/microcosm-cc/bluemonday"
)
// Sanitizer is a protection wrapper of *bluemonday.Policy which does not allow
// any modification to the underlying policies once it's been created.
type Sanitizer struct {
policy *bluemonday.Policy
init sync.Once
}
var sanitizer = &Sanitizer{}
// NewSanitizer initializes sanitizer with allowed attributes based on settings.
// Multiple calls to this function will only create one instance of Sanitizer during
// entire application lifecycle.
func NewSanitizer() {
sanitizer.init.Do(func() {
ReplaceSanitizer()
})
}
// ReplaceSanitizer replaces the current sanitizer to account for changes in settings
func ReplaceSanitizer() {
sanitizer.policy = bluemonday.UGCPolicy()
// We only want to allow HighlightJS specific classes for code blocks
sanitizer.policy.AllowAttrs("class").Matching(regexp.MustCompile(`^language-\w+$`)).OnElements("code")
// Checkboxes
sanitizer.policy.AllowAttrs("type").Matching(regexp.MustCompile(`^checkbox$`)).OnElements("input")
sanitizer.policy.AllowAttrs("checked", "disabled").OnElements("input")
// Custom URL-Schemes
sanitizer.policy.AllowURLSchemes(setting.Markdown.CustomURLSchemes...)
// Allow keyword markup
sanitizer.policy.AllowAttrs("class").Matching(regexp.MustCompile(`^` + keywordClass + `$`)).OnElements("span")
// Allow <kbd> tags for keyboard shortcut styling
sanitizer.policy.AllowElements("kbd")
// Custom keyword markup
for _, rule := range setting.ExternalSanitizerRules {
if rule.Regexp != nil {
sanitizer.policy.AllowAttrs(rule.AllowAttr).Matching(rule.Regexp).OnElements(rule.Element)
} else {
sanitizer.policy.AllowAttrs(rule.AllowAttr).OnElements(rule.Element)
}
}
}
// Sanitize takes a string that contains a HTML fragment or document and applies policy whitelist.
func Sanitize(s string) string {
NewSanitizer()
return sanitizer.policy.Sanitize(s)
}
// SanitizeReader sanitizes a Reader
func SanitizeReader(r io.Reader) *bytes.Buffer {
NewSanitizer()
return sanitizer.policy.SanitizeReader(r)
}
// SanitizeBytes takes a []byte slice that contains a HTML fragment or document and applies policy whitelist.
func SanitizeBytes(b []byte) []byte {
if len(b) == 0 {
// nothing to sanitize
return b
}
NewSanitizer()
return sanitizer.policy.SanitizeBytes(b)
}