forked from Shiloh/githaven
b8551f8532
* Fix task-list checkbox styling The pandoc renderer will append the class "task-list" to the ul element wrapping a li with one or more check-boxes. This allows us to select for them, removing their list-style-type property. However, goldmark and the gfm spec doesn't specify the "task-list" class name, so we can't use that to fix the issue there. Signed-off-by: Alexander Scheel <alexander.m.scheel@gmail.com> * Update to goldmark v1.1.25 This version adds the missing space after a checkbox. Resolves: #9656 Signed-off-by: Alexander Scheel <alexander.m.scheel@gmail.com> Co-authored-by: zeripath <art27@cantab.net>
125 lines
4.3 KiB
Go
125 lines
4.3 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 classes for anchors
|
|
sanitizer.policy.AllowAttrs("class").Matching(regexp.MustCompile(`ref-issue`)).OnElements("a")
|
|
|
|
// Allow classes for task lists
|
|
sanitizer.policy.AllowAttrs("class").Matching(regexp.MustCompile(`task-list`)).OnElements("ul")
|
|
|
|
// Allow generally safe attributes
|
|
generalSafeAttrs := []string{"abbr", "accept", "accept-charset",
|
|
"accesskey", "action", "align", "alt",
|
|
"aria-describedby", "aria-hidden", "aria-label", "aria-labelledby",
|
|
"axis", "border", "cellpadding", "cellspacing", "char",
|
|
"charoff", "charset", "checked",
|
|
"clear", "cols", "colspan", "color",
|
|
"compact", "coords", "datetime", "dir",
|
|
"disabled", "enctype", "for", "frame",
|
|
"headers", "height", "hreflang",
|
|
"hspace", "ismap", "label", "lang",
|
|
"maxlength", "media", "method",
|
|
"multiple", "name", "nohref", "noshade",
|
|
"nowrap", "open", "prompt", "readonly", "rel", "rev",
|
|
"rows", "rowspan", "rules", "scope",
|
|
"selected", "shape", "size", "span",
|
|
"start", "summary", "tabindex", "target",
|
|
"title", "type", "usemap", "valign", "value",
|
|
"vspace", "width", "itemprop",
|
|
}
|
|
|
|
generalSafeElements := []string{
|
|
"h1", "h2", "h3", "h4", "h5", "h6", "h7", "h8", "br", "b", "i", "strong", "em", "a", "pre", "code", "img", "tt",
|
|
"div", "ins", "del", "sup", "sub", "p", "ol", "ul", "table", "thead", "tbody", "tfoot", "blockquote",
|
|
"dl", "dt", "dd", "kbd", "q", "samp", "var", "hr", "ruby", "rt", "rp", "li", "tr", "td", "th", "s", "strike", "summary",
|
|
"details", "caption", "figure", "figcaption",
|
|
"abbr", "bdo", "cite", "dfn", "mark", "small", "span", "time", "wbr",
|
|
}
|
|
|
|
sanitizer.policy.AllowAttrs(generalSafeAttrs...).OnElements(generalSafeElements...)
|
|
|
|
sanitizer.policy.AllowAttrs("itemscope", "itemtype").OnElements("div")
|
|
|
|
// FIXME: Need to handle longdesc in img but there is no easy way to do it
|
|
|
|
// 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)
|
|
}
|