We now only encode &, < and > in PROPFIND PCDATA

Signed-off-by: Jörn Friedrich Dreyer <[email protected]>

changelog/unreleased/more-efficient-etag-pcdata.md

@@ -0,0 +1,3 @@
+Enhancement: We now only encode &, < and > in PROPFIND PCDATA
+
+https://github.com/cs3org/reva/pull/3240

internal/http/services/owncloud/ocdav/prop/prop.go

@@ -21,6 +21,7 @@ package prop
 import (
 	"bytes"
 	"encoding/xml"
+	"unicode/utf8"
 )
 
 // PropertyXML represents a single DAV resource property as defined in RFC 4918.
@@ -58,13 +59,78 @@ func EscapedNS(namespace string, local string, val string) PropertyXML {
 	}
 }
 
-// Escaped returns a new PropertyXML instance while xml-escaping the value
+var (
+	escAmp  = []byte("&")
+	escLT   = []byte("<")
+	escGT   = []byte(">")
+	escFFFD = []byte("\uFFFD") // Unicode replacement character
+)
+
+// Decide whether the given rune is in the XML Character Range, per
+// the Char production of https://www.xml.com/axml/testaxml.htm,
+// Section 2.2 Characters.
+func isInCharacterRange(r rune) (inrange bool) {
+	return r == 0x09 ||
+		r == 0x0A ||
+		r == 0x0D ||
+		r >= 0x20 && r <= 0xD7FF ||
+		r >= 0xE000 && r <= 0xFFFD ||
+		r >= 0x10000 && r <= 0x10FFFF
+}
+
+// Escaped returns a new PropertyXML instance while replacing only
+// * `&` with `&amp;`
+// * `<` with `&lt;`
+// * `>` with `&gt;`
+// as defined in https://www.w3.org/TR/REC-xml/#syntax:
+//
+// > The ampersand character (&) and the left angle bracket (<) must not appear
+// > in their literal form, except when used as markup delimiters, or within a
+// > comment, a processing instruction, or a CDATA section. If they are needed
+// > elsewhere, they must be escaped using either numeric character references
+// > or the strings " &amp; " and " &lt; " respectively. The right angle
+// > bracket (>) may be represented using the string " &gt; ", and must, for
+// > compatibility, be escaped using either " &gt; " or a character reference
+// > when it appears in the string " ]]> " in content, when that string is not
+// > marking the end of a CDATA section.
+//
+// The code ignores errors as the legacy Escaped() does
 // TODO properly use the space
 func Escaped(key, val string) PropertyXML {
+	w := new(bytes.Buffer)
+	s := []byte(val)
+	var esc []byte
+	last := 0
+	for i := 0; i < len(s); {
+		r, width := utf8.DecodeRune(s[i:])
+		i += width
+		switch r {
+		case '&':
+			esc = escAmp
+		case '<':
+			esc = escLT
+		case '>':
+			esc = escGT
+		default:
+			if !isInCharacterRange(r) || (r == 0xFFFD && width == 1) {
+				esc = escFFFD
+				break
+			}
+			continue
+		}
+		if _, err := w.Write(s[last : i-width]); err != nil {
+			break
+		}
+		if _, err := w.Write(esc); err != nil {
+			break
+		}
+		last = i
+	}
+	_, _ = w.Write(s[last:])
 	return PropertyXML{
 		XMLName:  xml.Name{Space: "", Local: key},
 		Lang:     "",
-		InnerXML: xmlEscaped(val),
+		InnerXML: w.Bytes(),
 	}
 }
 

internal/http/services/owncloud/ocdav/propfind/propfind_test.go

@@ -499,7 +499,7 @@ var _ = Describe("Propfind", func() {
 				Expect(sf.Href).To(Equal("http:/127.0.0.1:3000/foo/Shares/sharedFile"))
 				Expect(string(sf.Propstat[0].Prop[0].InnerXML)).To(ContainSubstring("<d:getcontentlength>2000</d:getcontentlength>"))
 				Expect(string(sf.Propstat[0].Prop[0].InnerXML)).To(ContainSubstring("<d:getlastmodified>Thu, 01 Jan 1970 00:00:01 GMT</d:getlastmodified>"))
-				Expect(string(sf.Propstat[0].Prop[0].InnerXML)).To(ContainSubstring("<d:getetag>&#34;1&#34;</d:getetag>"))
+				Expect(string(sf.Propstat[0].Prop[0].InnerXML)).To(ContainSubstring(`<d:getetag>"1"</d:getetag>`))
 			})
 		})
 
@@ -547,7 +547,7 @@ var _ = Describe("Propfind", func() {
 				Expect(shares.Href).To(Equal("http:/127.0.0.1:3000/foo/Shares/"))
 				Expect(string(shares.Propstat[0].Prop[0].InnerXML)).To(ContainSubstring("<oc:size>6000</oc:size>"))
 				Expect(string(shares.Propstat[0].Prop[0].InnerXML)).To(ContainSubstring("<d:getlastmodified>Thu, 01 Jan 1970 00:00:03 GMT</d:getlastmodified>"))
-				Expect(string(shares.Propstat[0].Prop[0].InnerXML)).To(ContainSubstring("<d:getetag>&#34;3&#34;</d:getetag>"))
+				Expect(string(shares.Propstat[0].Prop[0].InnerXML)).To(ContainSubstring(`<d:getetag>"3"</d:getetag>`))
 			})
 
 			It("stats the embedded space", func() {