From f375b39df7306c52ed2d3092ea6989e59725b5e8 Mon Sep 17 00:00:00 2001
From: M66B <M66B@users.noreply.github.com>
Date: Fri, 21 Feb 2020 08:55:24 +0100
Subject: [PATCH] Filter Jsoup stream

---
 .../main/java/eu/faircode/email/JsoupEx.java  | 58 +++++++++++++++----
 1 file changed, 47 insertions(+), 11 deletions(-)

diff --git a/app/src/main/java/eu/faircode/email/JsoupEx.java b/app/src/main/java/eu/faircode/email/JsoupEx.java
index c36b9e3e76..e34232bc5a 100644
--- a/app/src/main/java/eu/faircode/email/JsoupEx.java
+++ b/app/src/main/java/eu/faircode/email/JsoupEx.java
@@ -24,23 +24,25 @@ import org.jsoup.nodes.Document;
 import org.jsoup.nodes.Element;
 
 import java.io.File;
+import java.io.FileInputStream;
+import java.io.FilterInputStream;
 import java.io.IOException;
+import java.io.InputStream;
 import java.nio.charset.StandardCharsets;
 
 public class JsoupEx {
     static Document parse(String html) {
-
+        try {
 /*
-org.jsoup.UncheckedIOException: java.io.IOException: Input is binary and unsupported
-        at org.jsoup.parser.CharacterReader.<init>(SourceFile:38)
-        at org.jsoup.parser.CharacterReader.<init>(SourceFile:43)
-        at org.jsoup.parser.TreeBuilder.initialiseParse(SourceFile:38)
-        at org.jsoup.parser.HtmlTreeBuilder.initialiseParse(SourceFile:65)
-        at org.jsoup.parser.TreeBuilder.parse(SourceFile:46)
-        at org.jsoup.parser.Parser.parse(SourceFile:107)
-        at org.jsoup.Jsoup.parse(SourceFile:58)
+        org.jsoup.UncheckedIOException: java.io.IOException: Input is binary and unsupported
+                at org.jsoup.parser.CharacterReader.<init>(SourceFile:38)
+                at org.jsoup.parser.CharacterReader.<init>(SourceFile:43)
+                at org.jsoup.parser.TreeBuilder.initialiseParse(SourceFile:38)
+                at org.jsoup.parser.HtmlTreeBuilder.initialiseParse(SourceFile:65)
+                at org.jsoup.parser.TreeBuilder.parse(SourceFile:46)
+                at org.jsoup.parser.Parser.parse(SourceFile:107)
+                at org.jsoup.Jsoup.parse(SourceFile:58)
 */
-        try {
             return Jsoup.parse(html.replace("\0", ""));
         } catch (OutOfMemoryError ex) {
             Log.e(ex);
@@ -53,6 +55,40 @@ org.jsoup.UncheckedIOException: java.io.IOException: Input is binary and unsuppo
     }
 
     static Document parse(File in) throws IOException {
-        return Jsoup.parse(in, StandardCharsets.UTF_8.name());
+        try (InputStream is = new FileInputStream(in)) {
+            return Jsoup.parse(new FilteredStream(is), StandardCharsets.UTF_8.name(), "");
+        }
+    }
+
+    private static class FilteredStream extends FilterInputStream {
+        protected FilteredStream(InputStream in) {
+            super(in);
+        }
+
+        @Override
+        public int read() throws IOException {
+            int b = super.read();
+            while (b == 0)
+                b = super.read();
+            return b;
+        }
+
+        @Override
+        public int read(byte[] buffer) throws IOException {
+            return read(buffer, 0, buffer.length);
+        }
+
+        @Override
+        public int read(byte[] buffer, int off, int len) throws IOException {
+            int b;
+            int c = 0;
+            while (c < len) {
+                b = read();
+                if (b < 0)
+                    return (c == 0 ? -1 : c);
+                buffer[off + c++] = (byte) b;
+            }
+            return c;
+        }
     }
 }