Upgrade Bluemonday to v1.0.16 (#17372)

Upgrade Bluemonday to latest version

Signed-off-by: Andrew Thornton <art27@cantab.net>

Co-authored-by: 6543 <6543@obermui.de>

go.mod

@@ -82,7 +82,7 @@ require (
 	github.com/mattn/go-runewidth v0.0.13 // indirect
 	github.com/mattn/go-sqlite3 v1.14.8
 	github.com/mholt/archiver/v3 v3.5.0
-	github.com/microcosm-cc/bluemonday v1.0.15
+	github.com/microcosm-cc/bluemonday v1.0.16
 	github.com/miekg/dns v1.1.43 // indirect
 	github.com/minio/md5-simd v1.1.2 // indirect
 	github.com/minio/minio-go/v7 v7.0.12

go.sum

@@ -869,8 +869,8 @@ github.com/mholt/acmez v0.1.3 h1:J7MmNIk4Qf9b8mAGqAh4XkNeowv3f1zW816yf4zt7Qk=
 github.com/mholt/acmez v0.1.3/go.mod h1:8qnn8QA/Ewx8E3ZSsmscqsIjhhpxuy9vqdgbX2ceceM=
 github.com/mholt/archiver/v3 v3.5.0 h1:nE8gZIrw66cu4osS/U7UW7YDuGMHssxKutU8IfWxwWE=
 github.com/mholt/archiver/v3 v3.5.0/go.mod h1:qqTTPUK/HZPFgFQ/TJ3BzvTpF/dPtFVJXdQbCmeMxwc=
-github.com/microcosm-cc/bluemonday v1.0.15 h1:J4uN+qPng9rvkBZBoBb8YGR+ijuklIMpSOZZLjYpbeY=
+github.com/microcosm-cc/bluemonday v1.0.16 h1:kHmAq2t7WPWLjiGvzKa5o3HzSfahUKiOq7fAPUiMNIc=
-github.com/microcosm-cc/bluemonday v1.0.15/go.mod h1:ZLvAzeakRwrGnzQEvstVzVt3ZpqOF2+sdFr0Om+ce30=
+github.com/microcosm-cc/bluemonday v1.0.16/go.mod h1:Z0r70sCuXHig8YpBzCc5eGHAap2K7e/u082ZUpDRRqM=
 github.com/miekg/dns v1.0.14/go.mod h1:W1PPwlIAgtquWBMBEV9nkV9Cazfe8ScdGz/Lj7v3Nrg=
 github.com/miekg/dns v1.1.42/go.mod h1:+evo5L0630/F6ca/Z9+GAqzhjGyn8/c+TBaOyfEl0V4=
 github.com/miekg/dns v1.1.43 h1:JKfpVSCB84vrAmHzyrsxB5NAr5kLoMXZArPSw7Qlgyg=

vendor/github.com/microcosm-cc/bluemonday/.editorconfig

@@ -0,0 +1,4 @@
+root = true
+
+[*]
+end_of_line = lf

vendor/github.com/microcosm-cc/bluemonday/.gitattributes

@@ -0,0 +1 @@
+* text=auto eol=lf

vendor/github.com/microcosm-cc/bluemonday/CREDITS.md

@@ -4,4 +4,5 @@
 1. Andrew Krasichkov @buglloc https://github.com/buglloc
 1. Mike Samuel mikesamuel@gmail.com
 1. Dmitri Shuralyov shurcooL@gmail.com
-1. https://github.com/opennota
+1. opennota https://github.com/opennota https://gitlab.com/opennota
+1. Tom Anthony https://www.tomanthony.co.uk/

vendor/github.com/microcosm-cc/bluemonday/Makefile

@@ -3,6 +3,7 @@
 #   all:          Builds the code locally after testing
 #
 #   fmt:          Formats the source files
+#   fmt-check:    Check if the source files are formated
 #   build:        Builds the code locally
 #   vet:          Vets the code
 #   lint:         Runs lint over the code (you do not need to fix everything)
@@ -11,6 +12,8 @@
 #
 #   install:      Builds, tests and installs the code locally
 
+GOFILES_NOVENDOR = $(shell find . -type f -name '*.go' -not -path "./vendor/*" -not -path "./.git/*")
+
 .PHONY: all fmt build vet lint test cover install
 
 # The first target is always the default action if `make` is called without
@@ -19,7 +22,10 @@
 all: fmt vet test install
 
 fmt:
-	@gofmt -s -w ./$*
+	@gofmt -s -w ${GOFILES_NOVENDOR}
+
+fmt-check:
+	@([ -z "$(shell gofmt -d $(GOFILES_NOVENDOR) | head)" ]) || (echo "Source is unformatted"; exit 1)
 
 build:
 	@go build

vendor/github.com/microcosm-cc/bluemonday/README.md

@@ -180,7 +180,7 @@ p.AllowElementsMatching(regex.MustCompile(`^my-element-`))
 
 Or add elements as a virtue of adding an attribute:
 ```go
-// Not the recommended pattern, see the recommendation on using .Matching() below
+// Note the recommended pattern, see the recommendation on using .Matching() below
 p.AllowAttrs("nowrap").OnElements("td", "th")
 ```
 
@@ -222,7 +222,7 @@ p.AllowElements("fieldset", "select", "option")
 
 Although it's possible to handle inline CSS using `AllowAttrs` with a `Matching` rule, writing a single monolithic regular expression to safely process all inline CSS which you wish to allow is not a trivial task.  Instead of attempting to do so, you can allow the `style` attribute on whichever element(s) you desire and use style policies to control and sanitize inline styles.
 
-It is suggested that you use `Matching` (with a suitable regular expression)
+It is strongly recommended that you use `Matching` (with a suitable regular expression)
 `MatchingEnum`, or `MatchingHandler` to ensure each style matches your needs,
 but default handlers are supplied for most widely used styles.
 
@@ -379,6 +379,8 @@ Both examples exhibit the same issue, they declare attributes but do not then sp
 
 We are not yet including any tools to help allow and sanitize CSS. Which means that unless you wish to do the heavy lifting in a single regular expression (inadvisable), **you should not allow the "style" attribute anywhere**.
 
+In the same theme, both `<script>` and `<style>` are considered harmful. These elements (and their content) will not be rendered by default, and require you to explicitly set `p.AllowUnsafe(true)`. You should be aware that allowing these elements defeats the purpose of using a HTML sanitizer as you would be explicitly allowing either JavaScript (and any plainly written XSS) and CSS (which can modify a DOM to insert JS), and additionally but limitations in this library mean it is not aware of whether HTML is validly structured and that can allow these elements to bypass some of the safety mechanisms built into the [WhatWG HTML parser standard](https://html.spec.whatwg.org/multipage/parsing.html#parsing-main-inselect).
+
 It is not the job of bluemonday to fix your bad HTML, it is merely the job of bluemonday to prevent malicious HTML getting through. If you have mismatched HTML elements, or non-conforming nesting of elements, those will remain. But if you have well-structured HTML bluemonday will not break it.
 
 ## TODO

vendor/github.com/microcosm-cc/bluemonday/go.mod

@@ -3,7 +3,6 @@ module github.com/microcosm-cc/bluemonday
 go 1.16
 
 require (
-	github.com/asaskevich/govalidator v0.0.0-20210307081110-f21760c49a8d
 	github.com/aymerick/douceur v0.2.0
 	github.com/gorilla/css v1.0.0 // indirect
 	golang.org/x/net v0.0.0-20210614182718-04defd469f4e

vendor/github.com/microcosm-cc/bluemonday/go.sum

@@ -1,17 +1,10 @@
-github.com/asaskevich/govalidator v0.0.0-20210307081110-f21760c49a8d h1:Byv0BzEl3/e6D5CLfI0j/7hiIEtvGVFPCZ7Ei2oq8iQ=
-github.com/asaskevich/govalidator v0.0.0-20210307081110-f21760c49a8d/go.mod h1:WaHUgvxTVq04UNunO+XhnAqY/wQc+bxr74GqbsZ/Jqw=
 github.com/aymerick/douceur v0.2.0 h1:Mv+mAeH1Q+n9Fr+oyamOlAkUNPWPlA8PPGR0QAaYuPk=
 github.com/aymerick/douceur v0.2.0/go.mod h1:wlT5vV2O3h55X9m7iVYN0TBM0NH/MmbLnd30/FjWUq4=
 github.com/gorilla/css v1.0.0 h1:BQqNyPTi50JCFMTw/b67hByjMVXZRwGha6wxVGkeihY=
 github.com/gorilla/css v1.0.0/go.mod h1:Dn721qIggHpt4+EFCcTLTU/vk5ySda2ReITrtgBl60c=
-golang.org/x/net v0.0.0-20210421230115-4e50805a0758 h1:aEpZnXcAmXkd6AvLb2OPt+EN1Zu/8Ne3pCqPjja5PXY=
-golang.org/x/net v0.0.0-20210421230115-4e50805a0758/go.mod h1:72T/g9IO56b78aLF+1Kcs5dz7/ng1VjMUvfKvpfy+jM=
-golang.org/x/net v0.0.0-20210610132358-84b48f89b13b h1:k+E048sYJHyVnsr1GDrRZWQ32D2C7lWs9JRc0bel53A=
-golang.org/x/net v0.0.0-20210610132358-84b48f89b13b/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
 golang.org/x/net v0.0.0-20210614182718-04defd469f4e h1:XpT3nA5TvE525Ne3hInMh6+GETgn27Zfm9dxsThnX2Q=
 golang.org/x/net v0.0.0-20210614182718-04defd469f4e/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20210420072515-93ed5bcd2bfe/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=

vendor/github.com/microcosm-cc/bluemonday/policy.go

@@ -134,6 +134,19 @@ type Policy struct {
 	setOfElementsMatchingAllowedWithoutAttrs []*regexp.Regexp
 
 	setOfElementsToSkipContent map[string]struct{}
+
+	// Permits fundamentally unsafe elements.
+	//
+	// If false (default) then elements such as `style` and `script` will not be
+	// permitted even if declared in a policy. These elements when combined with
+	// untrusted input cannot be safely handled by bluemonday at this point in
+	// time.
+	//
+	// If true then `style` and `script` would be permitted by bluemonday if a
+	// policy declares them. However this is not recommended under any circumstance
+	// and can lead to XSS being rendered thus defeating the purpose of using a
+	// HTML sanitizer.
+	allowUnsafe bool
 }
 
 type attrPolicy struct {
@@ -714,6 +727,23 @@ func (p *Policy) AllowElementsContent(names ...string) *Policy {
 	return p
 }
 
+// AllowUnsafe permits fundamentally unsafe elements.
+//
+// If false (default) then elements such as `style` and `script` will not be
+// permitted even if declared in a policy. These elements when combined with
+// untrusted input cannot be safely handled by bluemonday at this point in
+// time.
+//
+// If true then `style` and `script` would be permitted by bluemonday if a
+// policy declares them. However this is not recommended under any circumstance
+// and can lead to XSS being rendered thus defeating the purpose of using a
+// HTML sanitizer.
+func (p *Policy) AllowUnsafe(allowUnsafe bool) *Policy {
+	p.init()
+	p.allowUnsafe = allowUnsafe
+	return p
+}
+
 // addDefaultElementsWithoutAttrs adds the HTML elements that we know are valid
 // without any attributes to an internal map.
 // i.e. we know that <table> is valid, but <bdo> isn't valid as the "dir" attr

vendor/github.com/microcosm-cc/bluemonday/sanitize.go

@@ -130,7 +130,7 @@ func escapeUrlComponent(w stringWriterWriter, val string) error {
 	return err
 }
 
-// Query represents a single part of the query string, a query param 
+// Query represents a single part of the query string, a query param
 type Query struct {
 	Key      string
 	Value    string
@@ -293,6 +293,17 @@ func (p *Policy) sanitize(r io.Reader, w io.Writer) error {
 
 			mostRecentlyStartedToken = normaliseElementName(token.Data)
 
+			switch normaliseElementName(token.Data) {
+			case `script`:
+				if !p.allowUnsafe {
+					continue
+				}
+			case `style`:
+				if !p.allowUnsafe {
+					continue
+				}
+			}
+
 			aps, ok := p.elsAndAttrs[token.Data]
 			if !ok {
 				aa, matched := p.matchRegex(token.Data)
@@ -341,6 +352,17 @@ func (p *Policy) sanitize(r io.Reader, w io.Writer) error {
 				mostRecentlyStartedToken = ""
 			}
 
+			switch normaliseElementName(token.Data) {
+			case `script`:
+				if !p.allowUnsafe {
+					continue
+				}
+			case `style`:
+				if !p.allowUnsafe {
+					continue
+				}
+			}
+
 			if skipClosingTag && closingTagToSkipStack[len(closingTagToSkipStack)-1] == token.Data {
 				closingTagToSkipStack = closingTagToSkipStack[:len(closingTagToSkipStack)-1]
 				if len(closingTagToSkipStack) == 0 {
@@ -386,6 +408,17 @@ func (p *Policy) sanitize(r io.Reader, w io.Writer) error {
 
 		case html.SelfClosingTagToken:
 
+			switch normaliseElementName(token.Data) {
+			case `script`:
+				if !p.allowUnsafe {
+					continue
+				}
+			case `style`:
+				if !p.allowUnsafe {
+					continue
+				}
+			}
+
 			aps, ok := p.elsAndAttrs[token.Data]
 			if !ok {
 				aa, matched := p.matchRegex(token.Data)
@@ -425,14 +458,22 @@ func (p *Policy) sanitize(r io.Reader, w io.Writer) error {
 				case `script`:
 					// not encouraged, but if a policy allows JavaScript we
 					// should not HTML escape it as that would break the output
-					if _, err := buff.WriteString(token.Data); err != nil {
+					//
-						return err
+					// requires p.AllowUnsafe()
+					if p.allowUnsafe {
+						if _, err := buff.WriteString(token.Data); err != nil {
+							return err
+						}
 					}
 				case "style":
 					// not encouraged, but if a policy allows CSS styles we
 					// should not HTML escape it as that would break the output
-					if _, err := buff.WriteString(token.Data); err != nil {
+					//
-						return err
+					// requires p.AllowUnsafe()
+					if p.allowUnsafe {
+						if _, err := buff.WriteString(token.Data); err != nil {
+							return err
+						}
 					}
 				default:
 					// HTML escape the text
@@ -524,11 +565,11 @@ attrsLoop:
 			for _, ap := range apl {
 				if ap.regexp != nil {
 					if ap.regexp.MatchString(htmlAttr.Val) {
-				htmlAttr.Val = escapeAttribute(htmlAttr.Val)
+						htmlAttr.Val = escapeAttribute(htmlAttr.Val)
 						cleanAttrs = append(cleanAttrs, htmlAttr)
 					}
 				} else {
-				htmlAttr.Val = escapeAttribute(htmlAttr.Val)
+					htmlAttr.Val = escapeAttribute(htmlAttr.Val)
 					cleanAttrs = append(cleanAttrs, htmlAttr)
 				}
 			}
@@ -1058,4 +1099,4 @@ func escapeAttribute(val string) string {
 	val = strings.Replace(val, string([]rune{'\u00A0'}), ` `, -1)
 	val = strings.Replace(val, `"`, `"`, -1)
 	return val
-}
+}

vendor/github.com/microcosm-cc/bluemonday/stringwriterwriter_go1.12.go

@@ -1,3 +1,4 @@
+//go:build go1.12
 // +build go1.12
 
 package bluemonday

vendor/github.com/microcosm-cc/bluemonday/stringwriterwriter_ltgo1.12.go

@@ -1,3 +1,4 @@
+//go:build go1.1 && !go1.12
 // +build go1.1,!go1.12
 
 package bluemonday

vendor/modules.txt

@@ -625,7 +625,7 @@ github.com/mholt/acmez/acme
 # github.com/mholt/archiver/v3 v3.5.0
 ## explicit
 github.com/mholt/archiver/v3
-# github.com/microcosm-cc/bluemonday v1.0.15
+# github.com/microcosm-cc/bluemonday v1.0.16
 ## explicit
 github.com/microcosm-cc/bluemonday
 github.com/microcosm-cc/bluemonday/css