Java tutorial
/* * Copyright (C) 2009 The Android Open Source Project * * 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.lottodroid.widgets.wikiarticle; import java.io.ByteArrayOutputStream; import java.io.IOException; import java.io.InputStream; import java.util.regex.Matcher; import java.util.regex.Pattern; import org.apache.http.HttpEntity; import org.apache.http.HttpResponse; import org.apache.http.StatusLine; import org.apache.http.client.HttpClient; import org.apache.http.client.methods.HttpGet; import org.apache.http.impl.client.DefaultHttpClient; import org.apache.http.params.BasicHttpParams; import org.apache.http.params.HttpConnectionParams; import org.apache.http.params.HttpParams; import org.json.JSONArray; import org.json.JSONException; import org.json.JSONObject; import android.content.Context; import android.content.pm.PackageInfo; import android.content.pm.PackageManager; import android.content.pm.PackageManager.NameNotFoundException; import android.content.res.Resources; import android.net.Uri; import android.text.format.Time; import android.util.Log; /** * Helper methods to simplify talking with and parsing responses from a * Wikipedia API. Before making any requests, you should call * {@link #prepareUserAgent(Context)} to generate a User-Agent string based on * your application package name and version. */ public class WikiarticleHelper { private static final String TAG = "WikiarticleHelper"; /** * Regular expressions that searches the title of the article inside the first * bolded a-tag */ public static final String ARTICLE_OF_DAY_REGEX_1 = "'''\\[\\[([^\\]]*)\\]\\]'''"; /** * Regular expressions that searches the title of the article inside the first * a-tag */ public static final String ARTICLE_OF_DAY_REGEX_2 = "\\('''\\[\\[([^\\]]*)\\]\\]'''\\)"; /** * Partial URL to use when requesting the detailed entry for a specific * Wiktionary page. Use {@link String#format(String, Object...)} to insert * the desired page title after escaping it as needed. */ private static final String WIKIARTICLE_PAGE = "http://en.wikipedia.org/w/api.php?action=query&prop=revisions&titles=%s&" + "rvprop=content&format=json%s"; /** * Partial URL to append to {@link #WIKTIONARY_PAGE} when you want to expand * any templates found on the requested page. This is useful when browsing * full entries, but may use more network bandwidth. */ private static final String WIKIARTICLE_EXPAND_TEMPLATES = "&rvexpandtemplates=true"; /** * {@link StatusLine} HTTP status code when no server error has occurred. */ private static final int HTTP_STATUS_OK = 200; /** Time to wait to the server until the connection is canceled, it is specified in milliseconds */ private static int CONNECT_TIMEOUT = 4 * 1000; // 10 seconds looks like a reasonable amount /** * Shared buffer used by {@link #getUrlContent(String)} when reading results * from an API request. */ private static byte[] sBuffer = new byte[512]; /** * User-agent string to use when making requests. Should be filled using * {@link #prepareUserAgent(Context)} before making any other calls. */ private static String sUserAgent = null; /** * Thrown when there were problems contacting the remote API server, either * because of a network error, or the server returned a bad status code. */ public static class ApiException extends Exception { private static final long serialVersionUID = 8723223636870446004L; public ApiException(String detailMessage, Throwable throwable) { super(detailMessage, throwable); } public ApiException(String detailMessage) { super(detailMessage); } } /** * Thrown when there were problems parsing the response to an API call, * either because the response was empty, or it was malformed. */ public static class ParseException extends Exception { private static final long serialVersionUID = 5554058180484070399L; public ParseException(String detailMessage, Throwable throwable) { super(detailMessage, throwable); } } /** * Parse the content of today featured article looking for the title * * @param pageContent The content of the article * @return The title of the article */ public static String parseAndGetTitleArticle(String pageContent) { // Use a regular expression to parse out the title of the article Pattern pattern = Pattern.compile(WikiarticleHelper.ARTICLE_OF_DAY_REGEX_1); Matcher matcher = pattern.matcher(pageContent); boolean match = false; if (matcher.find()) { match = true; } else { pattern = Pattern.compile(WikiarticleHelper.ARTICLE_OF_DAY_REGEX_2); matcher = pattern.matcher(pageContent); if (matcher.find()) { match = true; } } String title = ""; if (match) { // Sometimes the name is an abbreviation of the link -> Haumea (dwarf planet)|Haumea title = matcher.group(1).trim(); String[] splittedTitle = title.split("\\|"); title = title.substring(0, 1).toUpperCase() + splittedTitle[0].substring(1, splittedTitle[0].length()); } return title; } /** * Build the page title where it is located today's featured article, like * "Wikipedia:Today's_featured_article/March_21,_2009". It uses the actual date * * @param context The context of the application * @return Today's page resource */ public static String buildTodayPageTitle(Context context) { // Pick out month names from resources Resources res = context.getResources(); String[] monthNames = res.getStringArray(R.array.month_names); // Find current month and day Time today = new Time(); today.setToNow(); // Build today's page title, like "Wikipedia:Today's_featured_article/March_21,_2009" String pageName = res.getString(R.string.template_wotd_title, monthNames[today.month], today.monthDay, today.year); return pageName; } /** * Prepare the internal User-Agent string for use. This requires a * {@link Context} to pull the package name and version number for this * application. */ public static void prepareUserAgent(Context context) { try { // Read package name and version number from manifest PackageManager manager = context.getPackageManager(); PackageInfo info = manager.getPackageInfo(context.getPackageName(), 0); sUserAgent = String.format(context.getString(R.string.template_user_agent), info.packageName, info.versionName); } catch (NameNotFoundException e) { Log.e(TAG, "Couldn't find package information in PackageManager", e); } } /** * Read and return the content for a specific Wiktionary page. This makes a * lightweight API call, and trims out just the page content returned. * Because this call blocks until results are available, it should not be * run from a UI thread. * * @param title The exact title of the Wiktionary page requested. * @param expandTemplates If true, expand any wiki templates found. * @return Exact content of page. * @throws ApiException If any connection or server error occurs. * @throws ParseException If there are problems parsing the response. */ public static String getPageContent(String title, boolean expandTemplates) throws ApiException, ParseException { // Encode page title and expand templates if requested String encodedTitle = Uri.encode(title); String expandClause = expandTemplates ? WIKIARTICLE_EXPAND_TEMPLATES : ""; // Query the API for content String content = getUrlContent(String.format(WIKIARTICLE_PAGE, encodedTitle, expandClause)); try { // Drill into the JSON response to find the content body JSONObject response = new JSONObject(content); JSONObject query = response.getJSONObject("query"); JSONObject pages = query.getJSONObject("pages"); JSONObject page = pages.getJSONObject((String) pages.keys().next()); JSONArray revisions = page.getJSONArray("revisions"); JSONObject revision = revisions.getJSONObject(0); return revision.getString("*"); } catch (JSONException e) { throw new ParseException("Problem parsing API response", e); } } /** * Pull the raw text content of the given URL. This call blocks until the * operation has completed, and is synchronized because it uses a shared * buffer {@link #sBuffer}. * * @param url The exact URL to request. * @return The raw content returned by the server. * @throws ApiException If any connection or server error occurs. */ protected static synchronized String getUrlContent(String url) throws ApiException { if (sUserAgent == null) { throw new ApiException("User-Agent string must be prepared"); } Log.i(TAG, "Loading the URL " + url); HttpParams httpParams = new BasicHttpParams(); HttpConnectionParams.setConnectionTimeout(httpParams, CONNECT_TIMEOUT); HttpConnectionParams.setSoTimeout(httpParams, CONNECT_TIMEOUT); // Create client and set our specific user-agent string HttpClient client = new DefaultHttpClient(httpParams); HttpGet request = new HttpGet(url); request.setHeader("User-Agent", sUserAgent); try { HttpResponse response = client.execute(request); // Check if server response is valid StatusLine status = response.getStatusLine(); if (status.getStatusCode() != HTTP_STATUS_OK) { throw new ApiException("Invalid response from server: " + status.toString()); } // Pull content stream from response HttpEntity entity = response.getEntity(); InputStream inputStream = entity.getContent(); ByteArrayOutputStream content = new ByteArrayOutputStream(); // Read response into a buffered stream int readBytes = 0; while ((readBytes = inputStream.read(sBuffer)) != -1) { content.write(sBuffer, 0, readBytes); } // Return result from buffered stream return new String(content.toByteArray()); } catch (IOException e) { throw new ApiException("Problem communicating with API", e); } } }