Issue 1347 retrieve HTML title as supplemental info

git-svn-id: https://zxing.googlecode.com/svn/trunk@2397 59b500cc-1b3d-0410-9834-0bbf25fbcc57

android/src/com/google/zxing/client/android/HttpHelper.java

@@ -18,10 +18,9 @@ package com.google.zxing.client.android;
 
 import android.util.Log;
 
-import java.io.ByteArrayOutputStream;
 import java.io.IOException;
-import java.io.InputStream;
-import java.io.UnsupportedEncodingException;
+import java.io.InputStreamReader;
+import java.io.Reader;
 import java.net.HttpURLConnection;
 import java.net.URI;
 import java.net.URISyntaxException;
@@ -56,13 +55,23 @@ public final class HttpHelper {
     TEXT,
   }
 
+  /**
+   * Downloads the entire resource instead of part.
+   *
+   * @see #downloadViaHttp(String, HttpHelper.ContentType, int)
+   */
+  public static CharSequence downloadViaHttp(String uri, ContentType type) throws IOException {
+    return downloadViaHttp(uri, type, Integer.MAX_VALUE);
+  }
+
   /**
    * @param uri URI to retrieve
    * @param type expected text-like MIME type of that content
+   * @param maxChars approximate maximum characters to read from the source
    * @return content as a {@code String}
    * @throws IOException if the content can't be retrieved because of a bad URI, network problem, etc.
    */
-  public static String downloadViaHttp(String uri, ContentType type) throws IOException {
+  public static CharSequence downloadViaHttp(String uri, ContentType type, int maxChars) throws IOException {
     String contentTypes;
     switch (type) {
       case HTML:
@@ -75,10 +84,10 @@ public final class HttpHelper {
       default:
         contentTypes = "text/*,*/*";
     }
-    return downloadViaHttp(uri, contentTypes);
+    return downloadViaHttp(uri, contentTypes, maxChars);
   }
 
-  private static String downloadViaHttp(String uri, String contentTypes) throws IOException {
+  private static CharSequence downloadViaHttp(String uri, String contentTypes, int maxChars) throws IOException {
     Log.i(TAG, "Downloading " + uri);
     URL url = new URL(uri);
     HttpURLConnection connection = (HttpURLConnection) url.openConnection();
@@ -91,7 +100,7 @@ public final class HttpHelper {
         throw new IOException("Bad HTTP response: " + connection.getResponseCode());
       }
       Log.i(TAG, "Consuming " + uri);
-      return consume(connection);
+      return consume(connection, maxChars);
     } finally {
       connection.disconnect();
     }
@@ -108,34 +117,27 @@ public final class HttpHelper {
     return "UTF-8";
   }
 
-  private static String consume(URLConnection connection) throws IOException {
+  private static CharSequence consume(URLConnection connection, int maxChars) throws IOException {
     String encoding = getEncoding(connection);
-    ByteArrayOutputStream out = new ByteArrayOutputStream();
-    InputStream in = connection.getInputStream();
+    StringBuilder out = new StringBuilder();
+    Reader in = null;
     try {
-      in = connection.getInputStream();
-      byte[] buffer = new byte[1024];
-      int bytesRead;
-      while ((bytesRead = in.read(buffer)) > 0) {
-        out.write(buffer, 0, bytesRead);
+      in = new InputStreamReader(connection.getInputStream(), encoding);
+      char[] buffer = new char[1024];
+      int charsRead;
+      while (out.length() < maxChars && (charsRead = in.read(buffer)) > 0) {
+        out.append(buffer, 0, charsRead);
       }
     } finally {
-      try {
-        in.close();
-      } catch (IOException ioe) {
-        // continue
-      }
-    }
-    try {
-      return new String(out.toByteArray(), encoding);
-    } catch (UnsupportedEncodingException uee) {
-      try {
-        return new String(out.toByteArray(), "UTF-8");
-      } catch (UnsupportedEncodingException uee2) {
-        // can't happen
-        throw new IllegalStateException(uee2);
+      if (in != null) {
+        try {
+          in.close();
+        } catch (IOException ioe) {
+          // continue
+        }
       }
     }
+    return out;
   }
 
   public static URI unredirect(URI uri) throws IOException {

android/src/com/google/zxing/client/android/book/SearchBookContentsActivity.java

@@ -187,8 +187,8 @@ public final class SearchBookContentsActivity extends Activity {
         } else {
           uri = "http://www.google.com/books?vid=isbn" + theIsbn + "&jscmd=SearchWithinVolume2&q=" + theQuery;
         }
-        String content = HttpHelper.downloadViaHttp(uri, HttpHelper.ContentType.JSON);
-        return new JSONObject(content);
+        CharSequence content = HttpHelper.downloadViaHttp(uri, HttpHelper.ContentType.JSON);
+        return new JSONObject(content.toString());
       } catch (IOException ioe) {
         Log.w(TAG, "Error accessing book search", ioe);
         return null;

android/src/com/google/zxing/client/android/result/supplement/BookResultInfoRetriever.java

@@ -52,8 +52,8 @@ final class BookResultInfoRetriever extends SupplementalInfoRetriever {
   @Override
   void retrieveSupplementalInfo() throws IOException {
 
-    String contents = HttpHelper.downloadViaHttp("https://www.googleapis.com/books/v1/volumes?q=isbn:" + isbn,
-                                                 HttpHelper.ContentType.JSON);
+    CharSequence contents = HttpHelper.downloadViaHttp("https://www.googleapis.com/books/v1/volumes?q=isbn:" + isbn,
+                                                       HttpHelper.ContentType.JSON);
 
     if (contents.length() == 0) {
       return;
@@ -65,7 +65,7 @@ final class BookResultInfoRetriever extends SupplementalInfoRetriever {
 
     try {
 
-      JSONObject topLevel = (JSONObject) new JSONTokener(contents).nextValue();
+      JSONObject topLevel = (JSONObject) new JSONTokener(contents.toString()).nextValue();
       JSONArray items = topLevel.optJSONArray("items");
       if (items == null || items.isNull(0)) {
         return;

android/src/com/google/zxing/client/android/result/supplement/ProductResultInfoRetriever.java

@@ -53,7 +53,7 @@ final class ProductResultInfoRetriever extends SupplementalInfoRetriever {
     String encodedProductID = URLEncoder.encode(productID, "UTF-8");
     String uri = "http://www.google." + LocaleManager.getProductSearchCountryTLD(context)
             + "/m/products?ie=utf8&oe=utf8&scoring=p&source=zxing&q=" + encodedProductID;
-    String content = HttpHelper.downloadViaHttp(uri, HttpHelper.ContentType.HTML);
+    CharSequence content = HttpHelper.downloadViaHttp(uri, HttpHelper.ContentType.HTML);
 
     for (Pattern p : PRODUCT_NAME_PRICE_PATTERNS) {
       Matcher matcher = p.matcher(content);

android/src/com/google/zxing/client/android/result/supplement/SupplementalInfoRetriever.java

@@ -50,6 +50,7 @@ public abstract class SupplementalInfoRetriever extends AsyncTask<Object,Object,
     AsyncTaskExecInterface taskExec = new AsyncTaskExecManager().build();
     if (result instanceof URIParsedResult) {
       taskExec.execute(new URIResultInfoRetriever(textView, (URIParsedResult) result, historyManager, context));
+      taskExec.execute(new TitleRetriever(textView, (URIParsedResult) result, historyManager));
     } else if (result instanceof ProductParsedResult) {
       String productID = ((ProductParsedResult) result).getProductID();
       taskExec.execute(new ProductResultInfoRetriever(textView, productID, historyManager, context));

android/src/com/google/zxing/client/android/result/supplement/TitleRetriever.java

@@ -0,0 +1,68 @@
+/*
+ * Copyright 2012 ZXing authors
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package com.google.zxing.client.android.result.supplement;
+
+import android.widget.TextView;
+import com.google.zxing.client.android.HttpHelper;
+import com.google.zxing.client.android.history.HistoryManager;
+import com.google.zxing.client.result.URIParsedResult;
+
+import java.io.IOException;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+/**
+ * Retrieves the title of a web page as supplemental info.
+ *
+ * @author Sean Owen
+ */
+final class TitleRetriever extends SupplementalInfoRetriever {
+
+  private static final Pattern TITLE_PATTERN = Pattern.compile("<title>([^<]+)");
+  private static final int MAX_TITLE_LEN = 100;
+
+  private final String httpUrl;
+
+  TitleRetriever(TextView textView, URIParsedResult result, HistoryManager historyManager) {
+    super(textView, historyManager);
+    this.httpUrl = result.getURI();
+  }
+
+  @Override
+  void retrieveSupplementalInfo() {
+    CharSequence contents;
+    try {
+      contents = HttpHelper.downloadViaHttp(httpUrl, HttpHelper.ContentType.HTML, 4096);
+    } catch (IOException ioe) {
+      // ignore this
+      return;
+    }
+    if (contents != null && contents.length() > 0) {
+      Matcher m = TITLE_PATTERN.matcher(contents);
+      if (m.find()) {
+        String title = m.group(1);
+        if (title != null && !title.isEmpty()) {
+          if (title.length() > MAX_TITLE_LEN) {
+            title = title.substring(0, MAX_TITLE_LEN) + "...";
+          }
+          append(httpUrl, null, new String[] {title}, httpUrl);
+        }
+      }
+    }
+  }
+
+}