Merge pull request #92 from theflyingcodr/element_regex

AllowElements regex support

.gitignore

@@ -0,0 +1,15 @@
+ # Binaries for programs and plugins
+*.exe
+*.exe~
+*.dll
+*.so
+*.dylib
+
+# Test binary, built with `go test -c`
+*.test
+
+# Output of the go coverage tool, specifically when used with LiteIDE
+*.out
+
+# goland idea folder
+*.idea

README.md

@@ -169,12 +169,26 @@ To add elements to a policy either add just the elements:
 p.AllowElements("b", "strong")
 ```
 
+Or using a regex:
+
+_Note: if an element is added by name as shown above, any matching regex will be ignored_
+
+It is also recommended to ensure multiple patterns don't overlap as order of execution is not guaranteed and can result in some rules being missed.
+```go
+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
 p.AllowAttrs("nowrap").OnElements("td", "th")
 ```
 
+Again, this also supports a regex pattern match alternative:
+```go
+p.AllowAttrs("nowrap").OnElementsMatching(regex.MustCompile(`^my-element-`))
+```
+
 Attributes can either be added to all elements:
 ```go
 p.AllowAttrs("dir").Matching(regexp.MustCompile("(?i)rtl|ltr")).Globally()
@@ -226,6 +240,15 @@ p.AllowAttrs("style").OnElements("span", "p")
 // on 'span' elements only
 p.AllowStyles("text-decoration").MatchingEnum("underline", "line-through", "none").OnElements("span")
 ```
+
+Or you can specify elements based on a regex patterm match:
+```go
+p.AllowAttrs("style").OnElementsMatching(regex.MustCompile(`^my-element-`))
+// Allow the 'text-decoration' property to be set to 'underline', 'line-through' or 'none'
+// on 'span' elements only
+p.AllowStyles("text-decoration").MatchingEnum("underline", "line-through", "none").OnElementsMatching(regex.MustCompile(`^my-element-`))
+```
+
 If you need more specific checking, you can create a handler that takes in a string and returns a bool to
 validate the values for a given property. The string parameter has been
 converted to lowercase and unicode code points have been converted.

go.mod

@@ -3,7 +3,7 @@ module github.com/microcosm-cc/bluemonday
 go 1.9
 
 require (
-	github.com/aymerick/douceur v0.2.0
+	github.com/aymerick/douceur v0.2.0 // indirect
 	github.com/chris-ramon/douceur v0.2.0
 	github.com/gorilla/css v1.0.0 // indirect
 	golang.org/x/net v0.0.0-20181220203305-927f97764cc3

policy.go

@@ -86,12 +86,18 @@ type Policy struct {
 	// map[htmlElementName]map[htmlAttributeName]attrPolicy
 	elsAndAttrs map[string]map[string]attrPolicy
 
+	// elsMatchingAndAttrs stores regex based element matches along with attributes
+	elsMatchingAndAttrs map[*regexp.Regexp]map[string]attrPolicy
+
 	// map[htmlAttributeName]attrPolicy
 	globalAttrs map[string]attrPolicy
 
 	// map[htmlElementName]map[cssPropertyName]stylePolicy
 	elsAndStyles map[string]map[string]stylePolicy
 
+	// map[regex]map[cssPropertyName]stylePolicy
+	elsMatchingAndStyles map[*regexp.Regexp]map[string]stylePolicy
+
 	// map[cssPropertyName]stylePolicy
 	globalStyles map[string]stylePolicy
 
@@ -109,6 +115,16 @@ type Policy struct {
 	// be maintained in the output HTML.
 	setOfElementsAllowedWithoutAttrs map[string]struct{}
 
+	// If an element has had all attributes removed as a result of a policy
+	// being applied, then the element would be removed from the output.
+	//
+	// However some elements are valid and have strong layout meaning without
+	// any attributes, i.e. <table>.
+	//
+	// In this case, any element matching a regular expression will be accepted without
+	// attributes added.
+	setOfElementsMatchingAllowedWithoutAttrs []*regexp.Regexp
+
 	setOfElementsToSkipContent map[string]struct{}
 }
 
@@ -156,8 +172,10 @@ type urlPolicy func(url *url.URL) (allowUrl bool)
 func (p *Policy) init() {
 	if !p.initialized {
 		p.elsAndAttrs = make(map[string]map[string]attrPolicy)
+		p.elsMatchingAndAttrs = make(map[*regexp.Regexp]map[string]attrPolicy)
 		p.globalAttrs = make(map[string]attrPolicy)
 		p.elsAndStyles = make(map[string]map[string]stylePolicy)
+		p.elsMatchingAndStyles = make(map[*regexp.Regexp]map[string]stylePolicy)
 		p.globalStyles = make(map[string]stylePolicy)
 		p.allowURLSchemes = make(map[string]urlPolicy)
 		p.setOfElementsAllowedWithoutAttrs = make(map[string]struct{})
@@ -286,6 +304,30 @@ func (abp *attrPolicyBuilder) OnElements(elements ...string) *Policy {
 	return abp.p
 }
 
+// OnElementsMatching will bind an attribute policy to all elements matching a given regex
+// and return the updated policy
+func (abp *attrPolicyBuilder) OnElementsMatching(regex *regexp.Regexp) *Policy {
+	for _, attr := range abp.attrNames {
+		if _, ok := abp.p.elsMatchingAndAttrs[regex]; !ok {
+			abp.p.elsMatchingAndAttrs[regex] = make(map[string]attrPolicy)
+		}
+		ap := attrPolicy{}
+		if abp.regexp != nil {
+			ap.regexp = abp.regexp
+		}
+		abp.p.elsMatchingAndAttrs[regex][attr] = ap
+	}
+
+	if abp.allowEmpty {
+		abp.p.setOfElementsMatchingAllowedWithoutAttrs = append(abp.p.setOfElementsMatchingAllowedWithoutAttrs, regex)
+		if _, ok := abp.p.elsMatchingAndAttrs[regex]; !ok {
+			abp.p.elsMatchingAndAttrs[regex] = make(map[string]attrPolicy)
+		}
+	}
+
+	return abp.p
+}
+
 // Globally will bind an attribute policy to all HTML elements and return the
 // updated policy
 func (abp *attrPolicyBuilder) Globally() *Policy {
@@ -387,6 +429,32 @@ func (spb *stylePolicyBuilder) OnElements(elements ...string) *Policy {
 	return spb.p
 }
 
+// OnElementsMatching will bind a style policy to any HTML elements matching the pattern
+// and return the updated policy
+func (spb *stylePolicyBuilder) OnElementsMatching(regex *regexp.Regexp) *Policy {
+
+		for _, attr := range spb.propertyNames {
+
+			if _, ok := spb.p.elsMatchingAndStyles[regex]; !ok {
+				spb.p.elsMatchingAndStyles[regex] = make(map[string]stylePolicy)
+			}
+
+			sp := stylePolicy{}
+			if spb.handler != nil {
+				sp.handler = spb.handler
+			} else if len(spb.enum) > 0 {
+				sp.enum = spb.enum
+			} else if spb.regexp != nil {
+				sp.regexp = spb.regexp
+			} else {
+				sp.handler = getDefaultHandler(attr)
+			}
+			spb.p.elsMatchingAndStyles[regex][attr] = sp
+		}
+
+	return spb.p
+}
+
 // Globally will bind a style policy to all HTML elements and return the
 // updated policy
 func (spb *stylePolicyBuilder) Globally() *Policy {
@@ -430,6 +498,14 @@ func (p *Policy) AllowElements(names ...string) *Policy {
 	return p
 }
 
+func (p *Policy) AllowElementsMatching(regex *regexp.Regexp) *Policy {
+	p.init()
+	if _, ok := p.elsMatchingAndAttrs[regex]; !ok {
+		p.elsMatchingAndAttrs[regex] = make(map[string]attrPolicy)
+	}
+	return p
+}
+
 // RequireNoFollowOnLinks will result in all a, area, link tags having a
 // rel="nofollow"added to them if one does not already exist
 //