Make preprocessing of input stream handle supplementary characters

Fixes #383

When performing preprocessing of the input stream as specified in
https://drafts.csswg.org/css-syntax/#input-preprocessing, this change
makes our implementation handle non-BMP supplementary characters as
expected — by only replacing surrogates with U+FFFD if they are lone
(unpaired) surrogates, but not replacing surrogates that are part of
surrogate pairs (a high surrogate followed by a low surrogate).

Otherwise, without this change, a parse error will occur when our
implementation encounters supplementary characters in the input stream.

Author: sideshowbarker

org/w3c/css/css/StyleSheetParser.java

@@ -299,13 +299,7 @@ public void parseStyleElement(ApplContext ac, Reader reader,
 
 //	    if (cssFouffa == null) {
             String charset = ac.getCharsetForURL(url);
-            if (ac.getCssVersion().compareTo(CssVersion.CSS2) >=0
-                    && !isPreprocessed) {
-                cssFouffa = new CssFouffa(ac, new UnescapeFilterReader(new BufferedReader(reader)), url, lineno);
-            } else {
-                cssFouffa = new CssFouffa(ac, reader, url, lineno);
-
-            }
+            cssFouffa = new CssFouffa(ac, reader, url, lineno);
             cssFouffa.addListener(this);
 //	    } else {
 //		cssFouffa.ReInit(ac, input, url, lineno);

org/w3c/css/parser/CssFouffa.java

@@ -26,12 +26,14 @@
 import org.w3c.css.util.CssVersion;
 import org.w3c.css.util.HTTPURL;
 import org.w3c.css.util.InvalidParamException;
+import org.w3c.css.util.UnescapeFilterReader;
 import org.w3c.css.util.Util;
 import org.w3c.css.util.WarningParamException;
 import org.w3c.css.util.Warnings;
 import org.w3c.css.values.CssExpression;
 import org.w3c.css.values.CssValue;
 
+import java.io.BufferedReader;
 import java.io.FileNotFoundException;
 import java.io.IOException;
 import java.io.InputStream;
@@ -88,7 +90,7 @@ public final class CssFouffa extends CssParser {
      */
     public CssFouffa(ApplContext ac, Reader reader, URL file, int beginLine)
             throws IOException {
-        super(reader);
+        super(new UnescapeFilterReader(new BufferedReader(reader)));
         if (ac.getOrigin() == -1) {
             setOrigin(StyleSheetOrigin.AUTHOR); // default is user
         } else {

org/w3c/css/util/UnescapeFilterReader.java

@@ -3,6 +3,7 @@
 import java.io.FilterReader;
 import java.io.IOException;
 import java.io.Reader;
+import java.lang.Character;
 
 public class UnescapeFilterReader extends FilterReader {
 
@@ -32,7 +33,14 @@ public int read()
             return 0xfffd; // U+FFFD REPLACEMENT CHARACTER
         }
         if (c >= 0xd800 && c <= 0xdfff) { // surrogate
-            return 0xfffd;
+            if (!Character.isHighSurrogate((char) c)) {
+                return 0xfffd;
+            }
+            mark(1);
+            if (!Character.isLowSurrogate((char) in.read())) {
+                return 0xfffd;
+            }
+            reset();
         }
 
         // now specific case of CSS unicode escape for ascii values [A-Za-z0-9].
@@ -109,7 +117,15 @@ public int read(char[] cbuf, int off, int len) throws IOException {
             } else if (chars[i] == 0) {
                 chars[j++] = 0xfffd;
             } else if (chars[i] >= 0xd800 && chars[i] <= 0xdfff) {
-                chars[j++] = 0xfffd;
+                if (i + 1 >= l) {
+                    chars[j++] = 0xfffd;
+                } else if (!Character.isHighSurrogate((char) chars[i])) {
+                    chars[j++] = 0xfffd;
+                } else if (!Character.isLowSurrogate((char) chars[i + 1])) {
+                    chars[j++] = 0xfffd;
+                }
+                i++;
+                j++;
             }
             // escaping