src/be/nikiroo/fanfix/supported/BasicSupport.java

   1 package be.nikiroo.fanfix.supported;
   2
   3 import java.io.IOException;
   4 import java.io.InputStream;
   5 import java.net.URL;
   6 import java.util.ArrayList;
   7 import java.util.Date;
   8 import java.util.HashMap;
   9 import java.util.List;
  10 import java.util.Map;
  11 import java.util.Map.Entry;
  12
  13 import org.jsoup.helper.DataUtil;
  14 import org.jsoup.nodes.Document;
  15 import org.jsoup.nodes.Element;
  16 import org.jsoup.nodes.Node;
  17
  18 import be.nikiroo.fanfix.Instance;
  19 import be.nikiroo.fanfix.bundles.StringId;
  20 import be.nikiroo.fanfix.data.Chapter;
  21 import be.nikiroo.fanfix.data.MetaData;
  22 import be.nikiroo.fanfix.data.Story;
  23 import be.nikiroo.utils.Progress;
  24 import be.nikiroo.utils.StringUtils;
  25
  26 /**
  27  * This class is the base class used by the other support classes. It can be
  28  * used outside of this package, and have static method that you can use to get
  29  * access to the correct support class.
  30  * <p>
  31  * It will be used with 'resources' (usually web pages or files).
  32  *
  33  * @author niki
  34  */
  35 public abstract class BasicSupport {
  36         private Document sourceNode;
  37         private URL source;
  38         private SupportType type;
  39         private URL currentReferer; // with only one 'r', as in 'HTTP'...
  40
  41         /**
  42          * The name of this support class.
  43          *
  44          * @return the name
  45          */
  46         protected abstract String getSourceName();
  47
  48         /**
  49          * Check if the given resource is supported by this {@link BasicSupport}.
  50          *
  51          * @param url
  52          *            the resource to check for
  53          *
  54          * @return TRUE if it is
  55          */
  56         protected abstract boolean supports(URL url);
  57
  58         /**
  59          * Return TRUE if the support will return HTML encoded content values for
  60          * the chapters content.
  61          *
  62          * @return TRUE for HTML
  63          */
  64         protected abstract boolean isHtml();
  65
  66         /**
  67          * Return the {@link MetaData} of this story.
  68          *
  69          * @return the associated {@link MetaData}, never NULL
  70          *
  71          * @throws IOException
  72          *             in case of I/O error
  73          */
  74         protected abstract MetaData getMeta() throws IOException;
  75
  76         /**
  77          * Return the story description.
  78          *
  79          * @return the description
  80          *
  81          * @throws IOException
  82          *             in case of I/O error
  83          */
  84         protected abstract String getDesc() throws IOException;
  85
  86         /**
  87          * Return the list of chapters (name and resource).
  88          * <p>
  89          * Can be NULL if this {@link BasicSupport} do no use chapters.
  90          *
  91          * @param pg
  92          *            the optional progress reporter
  93          *
  94          * @return the chapters or NULL
  95          *
  96          * @throws IOException
  97          *             in case of I/O error
  98          */
  99         protected abstract List<Entry<String, URL>> getChapters(Progress pg)
 100                         throws IOException;
 101
 102         /**
 103          * Return the content of the chapter (possibly HTML encoded, if
 104          * {@link BasicSupport#isHtml()} is TRUE).
 105          *
 106          * @param chapUrl
 107          *            the chapter {@link URL}
 108          * @param number
 109          *            the chapter number
 110          * @param pg
 111          *            the optional progress reporter
 112          *
 113          * @return the content
 114          *
 115          * @throws IOException
 116          *             in case of I/O error
 117          */
 118         protected abstract String getChapterContent(URL chapUrl, int number,
 119                         Progress pg) throws IOException;
 120
 121         /**
 122          * Return the list of cookies (values included) that must be used to
 123          * correctly fetch the resources.
 124          * <p>
 125          * You are expected to call the super method implementation if you override
 126          * it.
 127          *
 128          * @return the cookies
 129          */
 130         public Map<String, String> getCookies() {
 131                 return new HashMap<String, String>();
 132         }
 133
 134         /**
 135          * OAuth authorisation (aka, "bearer XXXXXXX").
 136          *
 137          * @return the OAuth string
 138          */
 139         public String getOAuth() {
 140                 return null;
 141         }
 142
 143         /**
 144          * Return the canonical form of the main {@link URL}.
 145          *
 146          * @param source
 147          *            the source {@link URL}, which can be NULL
 148          *
 149          * @return the canonical form of this {@link URL} or NULL if the source was
 150          *         NULL
 151          */
 152         protected URL getCanonicalUrl(URL source) {
 153                 return source;
 154         }
 155
 156         /**
 157          * The main {@link Node} for this {@link Story}.
 158          *
 159          * @return the node
 160          */
 161         protected Element getSourceNode() {
 162                 return sourceNode;
 163         }
 164
 165         /**
 166          * The main {@link URL} for this {@link Story}.
 167          *
 168          * @return the URL
 169          */
 170         protected URL getSource() {
 171                 return source;
 172         }
 173
 174         /**
 175          * The current referer {@link URL} (only one 'r', as in 'HTML'...), i.e.,
 176          * the current {@link URL} we work on.
 177          *
 178          * @return the referer
 179          */
 180         public URL getCurrentReferer() {
 181                 return currentReferer;
 182         }
 183
 184         /**
 185          * The current referer {@link URL} (only one 'r', as in 'HTML'...), i.e.,
 186          * the current {@link URL} we work on.
 187          *
 188          * @param currentReferer
 189          *            the new referer
 190          */
 191         protected void setCurrentReferer(URL currentReferer) {
 192                 this.currentReferer = currentReferer;
 193         }
 194
 195         /**
 196          * The support type.
 197          *
 198          * @return the type
 199          */
 200         public SupportType getType() {
 201                 return type;
 202         }
 203
 204         /**
 205          * The support type.
 206          *
 207          * @param type
 208          *            the new type
 209          */
 210         protected void setType(SupportType type) {
 211                 this.type = type;
 212         }
 213
 214         /**
 215          * Open an input link that will be used for the support.
 216          * <p>
 217          * Can return NULL, in which case you are supposed to work without a source
 218          * node.
 219          *
 220          * @param source
 221          *            the source {@link URL}
 222          *
 223          * @return the {@link InputStream}
 224          *
 225          * @throws IOException
 226          *             in case of I/O error
 227          */
 228         protected Document loadDocument(URL source) throws IOException {
 229                 String url = getCanonicalUrl(source).toString();
 230                 return DataUtil.load(Instance.getCache().open(source, this, false),
 231                                 "UTF-8", url.toString());
 232         }
 233
 234         /**
 235          * Log into the support (can be a no-op depending upon the support).
 236          *
 237          * @throws IOException
 238          *             in case of I/O error
 239          */
 240         protected void login() throws IOException {
 241         }
 242
 243         /**
 244          * Now that we have processed the {@link Story}, close the resources if any.
 245          */
 246         protected void close() {
 247                 setCurrentReferer(null);
 248         }
 249
 250         /**
 251          * Process the given story resource into a partially filled {@link Story}
 252          * object containing the name and metadata.
 253          *
 254          * @param getDesc
 255          *            retrieve the description of the story, or not
 256          * @param pg
 257          *            the optional progress reporter
 258          *
 259          * @return the {@link Story}, never NULL
 260          *
 261          * @throws IOException
 262          *             in case of I/O error
 263          */
 264         protected Story processMeta(boolean getDesc, Progress pg)
 265                         throws IOException {
 266                 if (pg == null) {
 267                         pg = new Progress();
 268                 } else {
 269                         pg.setMinMax(0, 100);
 270                 }
 271
 272                 pg.setProgress(30);
 273
 274                 Story story = new Story();
 275                 MetaData meta = getMeta();
 276                 if (meta.getCreationDate() == null || meta.getCreationDate().isEmpty()) {
 277                         meta.setCreationDate(StringUtils.fromTime(new Date().getTime()));
 278                 }
 279                 story.setMeta(meta);
 280
 281                 pg.setProgress(50);
 282
 283                 if (meta.getCover() == null) {
 284                         meta.setCover(BasicSupportHelper.getDefaultCover(meta.getSubject()));
 285                 }
 286
 287                 pg.setProgress(60);
 288
 289                 if (getDesc) {
 290                         String descChapterName = Instance.getTrans().getString(
 291                                         StringId.DESCRIPTION);
 292                         story.getMeta().setResume(
 293                                         BasicSupportPara.makeChapter(this, source, 0,
 294                                                         descChapterName, //
 295                                                         getDesc(), isHtml(), null));
 296                 }
 297
 298                 pg.setProgress(100);
 299                 return story;
 300         }
 301
 302         /**
 303          * Process the given story resource into a fully filled {@link Story}
 304          * object.
 305          *
 306          * @param pg
 307          *            the optional progress reporter
 308          *
 309          * @return the {@link Story}, never NULL
 310          *
 311          * @throws IOException
 312          *             in case of I/O error
 313          */
 314         // ADD final when BasicSupport_Deprecated is gone
 315         public Story process(Progress pg) throws IOException {
 316                 setCurrentReferer(source);
 317                 login();
 318                 sourceNode = loadDocument(source);
 319
 320                 try {
 321                         return doProcess(pg);
 322                 } finally {
 323                         close();
 324                 }
 325         }
 326
 327         /**
 328          * Actual processing step, without the calls to other methods.
 329          * <p>
 330          * Will convert the story resource into a fully filled {@link Story} object.
 331          *
 332          * @param pg
 333          *            the optional progress reporter
 334          *
 335          * @return the {@link Story}, never NULL
 336          *
 337          * @throws IOException
 338          *             in case of I/O error
 339          */
 340         protected Story doProcess(Progress pg) throws IOException {
 341                 if (pg == null) {
 342                         pg = new Progress();
 343                 } else {
 344                         pg.setMinMax(0, 100);
 345                 }
 346
 347                 pg.setProgress(1);
 348                 Progress pgMeta = new Progress();
 349                 pg.addProgress(pgMeta, 10);
 350                 Story story = processMeta(true, pgMeta);
 351                 if (!pgMeta.isDone()) {
 352                         pgMeta.setProgress(pgMeta.getMax()); // 10%
 353                 }
 354
 355                 pg.setName("Retrieving " + story.getMeta().getTitle());
 356
 357                 Progress pgGetChapters = new Progress();
 358                 pg.addProgress(pgGetChapters, 10);
 359                 story.setChapters(new ArrayList<Chapter>());
 360                 List<Entry<String, URL>> chapters = getChapters(pgGetChapters);
 361                 if (!pgGetChapters.isDone()) {
 362                         pgGetChapters.setProgress(pgGetChapters.getMax()); // 20%
 363                 }
 364
 365                 if (chapters != null) {
 366                         Progress pgChaps = new Progress("Extracting chapters", 0,
 367                                         chapters.size() * 300);
 368                         pg.addProgress(pgChaps, 80);
 369
 370                         long words = 0;
 371                         int i = 1;
 372                         for (Entry<String, URL> chap : chapters) {
 373                                 pgChaps.setName("Extracting chapter " + i);
 374                                 URL chapUrl = chap.getValue();
 375                                 String chapName = chap.getKey();
 376                                 if (chapUrl != null) {
 377                                         setCurrentReferer(chapUrl);
 378                                 }
 379
 380                                 pgChaps.setProgress(i * 100);
 381                                 Progress pgGetChapterContent = new Progress();
 382                                 Progress pgMakeChapter = new Progress();
 383                                 pgChaps.addProgress(pgGetChapterContent, 100);
 384                                 pgChaps.addProgress(pgMakeChapter, 100);
 385
 386                                 String content = getChapterContent(chapUrl, i,
 387                                                 pgGetChapterContent);
 388                                 if (!pgGetChapterContent.isDone()) {
 389                                         pgGetChapterContent.setProgress(pgGetChapterContent
 390                                                         .getMax());
 391                                 }
 392
 393                                 Chapter cc = BasicSupportPara.makeChapter(this, chapUrl, i,
 394                                                 chapName, content, isHtml(), pgMakeChapter);
 395                                 if (!pgMakeChapter.isDone()) {
 396                                         pgMakeChapter.setProgress(pgMakeChapter.getMax());
 397                                 }
 398
 399                                 words += cc.getWords();
 400                                 story.getChapters().add(cc);
 401                                 story.getMeta().setWords(words);
 402
 403                                 i++;
 404                         }
 405
 406                         pgChaps.setName("Extracting chapters");
 407                 } else {
 408                         pg.setProgress(80);
 409                 }
 410
 411                 return story;
 412         }
 413
 414         /**
 415          * Return a {@link BasicSupport} implementation supporting the given
 416          * resource if possible.
 417          *
 418          * @param url
 419          *            the story resource
 420          *
 421          * @return an implementation that supports it, or NULL
 422          */
 423         public static BasicSupport getSupport(URL url) {
 424                 if (url == null) {
 425                         return null;
 426                 }
 427
 428                 // TEXT and INFO_TEXT always support files (not URLs though)
 429                 for (SupportType type : SupportType.values()) {
 430                         if (type != SupportType.TEXT && type != SupportType.INFO_TEXT) {
 431                                 BasicSupport support = getSupport(type, url);
 432                                 if (support != null && support.supports(url)) {
 433                                         return support;
 434                                 }
 435                         }
 436                 }
 437
 438                 for (SupportType type : new SupportType[] { SupportType.INFO_TEXT,
 439                                 SupportType.TEXT }) {
 440                         BasicSupport support = getSupport(type, url);
 441                         if (support != null && support.supports(url)) {
 442                                 return support;
 443                         }
 444                 }
 445
 446                 return null;
 447         }
 448
 449         /**
 450          * Return a {@link BasicSupport} implementation supporting the given type.
 451          *
 452          * @param type
 453          *            the type
 454          * @param url
 455          *            the {@link URL} to support (can be NULL to get an
 456          *            "abstract support")
 457          *
 458          * @return an implementation that supports it, or NULL
 459          */
 460         public static BasicSupport getSupport(SupportType type, URL url) {
 461                 BasicSupport support = null;
 462
 463                 switch (type) {
 464                 case EPUB:
 465                         support = new Epub();
 466                         break;
 467                 case INFO_TEXT:
 468                         support = new InfoText();
 469                         break;
 470                 case FIMFICTION:
 471                         try {
 472                                 // Can fail if no client key or NO in options
 473                                 support = new FimfictionApi();
 474                         } catch (IOException e) {
 475                                 support = new Fimfiction();
 476                         }
 477                         break;
 478                 case FANFICTION:
 479                         support = new Fanfiction();
 480                         break;
 481                 case TEXT:
 482                         support = new Text();
 483                         break;
 484                 case MANGAFOX:
 485                         support = new MangaFox();
 486                         break;
 487                 case E621:
 488                         support = new E621();
 489                         break;
 490                 case YIFFSTAR:
 491                         support = new YiffStar();
 492                         break;
 493                 case E_HENTAI:
 494                         support = new EHentai();
 495                         break;
 496                 case MANGA_LEL:
 497                         support = new MangaLel();
 498                         break;
 499                 case CBZ:
 500                         support = new Cbz();
 501                         break;
 502                 case HTML:
 503                         support = new Html();
 504                         break;
 505                 }
 506
 507                 if (support != null) {
 508                         support.setType(type);
 509                         support.source = support.getCanonicalUrl(url);
 510                 }
 511
 512                 return support;
 513         }
 514 }