bench-forgejo/modules/setting/markup.go
Alexander Scheel ee7df7ba8c Markdown: Sanitizier Configuration (#9075)
* Support custom sanitization policy

Allowing the gitea administrator to configure sanitization policy allows
them to couple external renders and custom templates to support more
markup. In particular, the `pandoc` renderer allows generating KaTeX
annotations, wrapping them in `<span>` elements with class `math` and
either `inline` or `display` (depending on whether or not inline or
block mode was requested).

This iteration gives the administrator whitelisting powers; carefully
crafted regexes will thus let through only the desired attributes
necessary to support their custom markup.

Resolves: #9054

Signed-off-by: Alexander Scheel <alexander.m.scheel@gmail.com>

* Document new sanitization configuration

 - Adds basic documentation to app.ini.sample,
 - Adds an example to the Configuration Cheat Sheet, and
 - Adds extended information to External Renderers section.

Signed-off-by: Alexander Scheel <alexander.m.scheel@gmail.com>

* Drop extraneous length check in newMarkupSanitizer(...)

Signed-off-by: Alexander Scheel <alexander.m.scheel@gmail.com>

* Fix plural ELEMENT and ALLOW_ATTR in docs

These were left over from their initial names. Make them singular to
conform with the current expectations.

Signed-off-by: Alexander Scheel <alexander.m.scheel@gmail.com>
2019-12-07 14:49:04 -05:00

141 lines
3.8 KiB
Go

// Copyright 2019 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.
package setting
import (
"regexp"
"strings"
"code.gitea.io/gitea/modules/log"
"gopkg.in/ini.v1"
)
// ExternalMarkupParsers represents the external markup parsers
var (
ExternalMarkupParsers []MarkupParser
ExternalSanitizerRules []MarkupSanitizerRule
)
// MarkupParser defines the external parser configured in ini
type MarkupParser struct {
Enabled bool
MarkupName string
Command string
FileExtensions []string
IsInputFile bool
}
// MarkupSanitizerRule defines the policy for whitelisting attributes on
// certain elements.
type MarkupSanitizerRule struct {
Element string
AllowAttr string
Regexp *regexp.Regexp
}
func newMarkup() {
for _, sec := range Cfg.Section("markup").ChildSections() {
name := strings.TrimPrefix(sec.Name(), "markup.")
if name == "" {
log.Warn("name is empty, markup " + sec.Name() + "ignored")
continue
}
if name == "sanitizer" {
newMarkupSanitizer(name, sec)
} else {
newMarkupRenderer(name, sec)
}
}
}
func newMarkupSanitizer(name string, sec *ini.Section) {
haveElement := sec.HasKey("ELEMENT")
haveAttr := sec.HasKey("ALLOW_ATTR")
haveRegexp := sec.HasKey("REGEXP")
if !haveElement && !haveAttr && !haveRegexp {
log.Warn("Skipping empty section: markup.%s.", name)
return
}
if !haveElement || !haveAttr || !haveRegexp {
log.Error("Missing required keys from markup.%s. Must have all three of ELEMENT, ALLOW_ATTR, and REGEXP defined!", name)
return
}
elements := sec.Key("ELEMENT").ValueWithShadows()
allowAttrs := sec.Key("ALLOW_ATTR").ValueWithShadows()
regexps := sec.Key("REGEXP").ValueWithShadows()
if len(elements) != len(allowAttrs) ||
len(elements) != len(regexps) {
log.Error("All three keys in markup.%s (ELEMENT, ALLOW_ATTR, REGEXP) must be defined the same number of times! Got %d, %d, and %d respectively.", name, len(elements), len(allowAttrs), len(regexps))
return
}
ExternalSanitizerRules = make([]MarkupSanitizerRule, 0, len(elements))
for index, pattern := range regexps {
if pattern == "" {
rule := MarkupSanitizerRule{
Element: elements[index],
AllowAttr: allowAttrs[index],
Regexp: nil,
}
ExternalSanitizerRules = append(ExternalSanitizerRules, rule)
continue
}
// Validate when parsing the config that this is a valid regular
// expression. Then we can use regexp.MustCompile(...) later.
compiled, err := regexp.Compile(pattern)
if err != nil {
log.Error("In module.%s: REGEXP at definition %d failed to compile: %v", name, index+1, err)
continue
}
rule := MarkupSanitizerRule{
Element: elements[index],
AllowAttr: allowAttrs[index],
Regexp: compiled,
}
ExternalSanitizerRules = append(ExternalSanitizerRules, rule)
}
}
func newMarkupRenderer(name string, sec *ini.Section) {
extensionReg := regexp.MustCompile(`\.\w`)
extensions := sec.Key("FILE_EXTENSIONS").Strings(",")
var exts = make([]string, 0, len(extensions))
for _, extension := range extensions {
if !extensionReg.MatchString(extension) {
log.Warn(sec.Name() + " file extension " + extension + " is invalid. Extension ignored")
} else {
exts = append(exts, extension)
}
}
if len(exts) == 0 {
log.Warn(sec.Name() + " file extension is empty, markup " + name + " ignored")
return
}
command := sec.Key("RENDER_COMMAND").MustString("")
if command == "" {
log.Warn(" RENDER_COMMAND is empty, markup " + name + " ignored")
return
}
ExternalMarkupParsers = append(ExternalMarkupParsers, MarkupParser{
Enabled: sec.Key("ENABLED").MustBool(false),
MarkupName: name,
FileExtensions: exts,
Command: command,
IsInputFile: sec.Key("IS_INPUT_FILE").MustBool(false),
})
}