1 package be
.nikiroo
.fanfix
.supported
;
3 import java
.io
.IOException
;
4 import java
.io
.InputStream
;
5 import java
.net
.MalformedURLException
;
7 import java
.util
.ArrayList
;
9 import java
.util
.HashMap
;
10 import java
.util
.List
;
12 import java
.util
.Scanner
;
13 import java
.util
.Map
.Entry
;
15 import org
.json
.JSONException
;
16 import org
.json
.JSONObject
;
17 import org
.jsoup
.helper
.DataUtil
;
18 import org
.jsoup
.nodes
.Document
;
19 import org
.jsoup
.nodes
.Element
;
20 import org
.jsoup
.nodes
.Node
;
22 import be
.nikiroo
.fanfix
.Instance
;
23 import be
.nikiroo
.fanfix
.bundles
.StringId
;
24 import be
.nikiroo
.fanfix
.data
.Chapter
;
25 import be
.nikiroo
.fanfix
.data
.MetaData
;
26 import be
.nikiroo
.fanfix
.data
.Story
;
27 import be
.nikiroo
.utils
.Progress
;
28 import be
.nikiroo
.utils
.StringUtils
;
31 * This class is the base class used by the other support classes. It can be
32 * used outside of this package, and have static method that you can use to get
33 * access to the correct support class.
35 * It will be used with 'resources' (usually web pages or files).
39 public abstract class BasicSupport
{
40 private Document sourceNode
;
42 private SupportType type
;
43 private URL currentReferer
; // with only one 'r', as in 'HTTP'...
45 static protected BasicSupportHelper bsHelper
= new BasicSupportHelper();
46 static protected BasicSupportImages bsImages
= new BasicSupportImages();
47 static protected BasicSupportPara bsPara
= new BasicSupportPara(new BasicSupportHelper(), new BasicSupportImages());
50 * Check if the given resource is supported by this {@link BasicSupport}.
53 * the resource to check for
55 * @return TRUE if it is
57 protected abstract boolean supports(URL url
);
60 * Return TRUE if the support will return HTML encoded content values for
61 * the chapters content.
63 * @return TRUE for HTML
65 protected abstract boolean isHtml();
68 * Return the {@link MetaData} of this story.
70 * @return the associated {@link MetaData}, never NULL
73 * in case of I/O error
75 protected abstract MetaData
getMeta() throws IOException
;
78 * Return the story description.
80 * @return the description
83 * in case of I/O error
85 protected abstract String
getDesc() throws IOException
;
88 * Return the list of chapters (name and resource).
90 * Can be NULL if this {@link BasicSupport} do no use chapters.
93 * the optional progress reporter
95 * @return the chapters or NULL
98 * in case of I/O error
100 protected abstract List
<Entry
<String
, URL
>> getChapters(Progress pg
)
104 * Return the content of the chapter (possibly HTML encoded, if
105 * {@link BasicSupport#isHtml()} is TRUE).
108 * the chapter {@link URL}
112 * the optional progress reporter
114 * @return the content
116 * @throws IOException
117 * in case of I/O error
119 protected abstract String
getChapterContent(URL chapUrl
, int number
,
120 Progress pg
) throws IOException
;
123 * Return the list of cookies (values included) that must be used to
124 * correctly fetch the resources.
126 * You are expected to call the super method implementation if you override
129 * @return the cookies
131 public Map
<String
, String
> getCookies() {
132 return new HashMap
<String
, String
>();
136 * OAuth authorisation (aka, "bearer XXXXXXX").
138 * @return the OAuth string
140 public String
getOAuth() {
145 * Return the canonical form of the main {@link URL}.
148 * the source {@link URL}, which can be NULL
150 * @return the canonical form of this {@link URL} or NULL if the source was
153 protected URL
getCanonicalUrl(URL source
) {
158 * The main {@link Node} for this {@link Story}.
162 protected Element
getSourceNode() {
167 * The main {@link URL} for this {@link Story}.
171 protected URL
getSource() {
176 * The current referer {@link URL} (only one 'r', as in 'HTML'...), i.e.,
177 * the current {@link URL} we work on.
179 * @return the referer
181 public URL
getCurrentReferer() {
182 return currentReferer
;
186 * The current referer {@link URL} (only one 'r', as in 'HTML'...), i.e.,
187 * the current {@link URL} we work on.
189 * @param currentReferer
192 protected void setCurrentReferer(URL currentReferer
) {
193 this.currentReferer
= currentReferer
;
201 public SupportType
getType() {
211 protected void setType(SupportType type
) {
216 * Open an input link that will be used for the support.
218 * Can return NULL, in which case you are supposed to work without a source
222 * the source {@link URL}
224 * @return the {@link InputStream}
226 * @throws IOException
227 * in case of I/O error
229 protected Document
loadDocument(URL source
) throws IOException
{
230 String url
= getCanonicalUrl(source
).toString();
231 return DataUtil
.load(Instance
.getInstance().getCache().open(source
, this, false), "UTF-8", url
.toString());
235 * Log into the support (can be a no-op depending upon the support).
237 * @throws IOException
238 * in case of I/O error
240 protected void login() throws IOException
{
244 * Now that we have processed the {@link Story}, close the resources if any.
246 protected void close() {
247 setCurrentReferer(null);
251 * Process the given story resource into a partially filled {@link Story}
252 * object containing the name and metadata.
255 * retrieve the description of the story, or not
257 * the optional progress reporter
259 * @return the {@link Story}, never NULL
261 * @throws IOException
262 * in case of I/O error
264 protected Story
processMeta(boolean getDesc
, Progress pg
)
269 pg
.setMinMax(0, 100);
274 Story story
= new Story();
276 MetaData meta
= getMeta();
277 meta
.setType(getType().toString());
278 meta
.setSource(getType().getSourceName());
279 meta
.setPublisher(getType().getSourceName());
281 if (meta
.getCreationDate() == null
282 || meta
.getCreationDate().trim().isEmpty()) {
283 meta
.setCreationDate(bsHelper
284 .formatDate(StringUtils
.fromTime(new Date().getTime())));
287 pg
.put("meta", meta
);
291 if (meta
.getCover() == null) {
292 meta
.setCover(bsHelper
.getDefaultCover(meta
.getSubject()));
298 String descChapterName
= Instance
.getInstance().getTrans().getString(StringId
.DESCRIPTION
);
299 story
.getMeta().setResume(bsPara
.makeChapter(this, source
, 0, descChapterName
, //
300 getDesc(), isHtml(), null));
308 * Utility method to convert the given URL into a JSON object.
310 * Note that this method expects small JSON files (everything is copied into
311 * memory at least twice).
316 * TRUE for more stable resources, FALSE when they often change
318 * @return the JSON object
320 * @throws IOException
321 * in case of I/O error
323 protected JSONObject
getJson(String url
, boolean stable
)
326 return getJson(new URL(url
), stable
);
327 } catch (MalformedURLException e
) {
328 throw new IOException("Malformed URL: " + url
, e
);
333 * Utility method to convert the given URL into a JSON object.
335 * Note that this method expects small JSON files (everything is copied into
336 * memory at least twice).
341 * TRUE for more stable resources, FALSE when they often change
343 * @return the JSON object
345 * @throws IOException
346 * in case of I/O error
348 protected JSONObject
getJson(URL url
, boolean stable
) throws IOException
{
349 InputStream in
= Instance
.getInstance().getCache().open(url
, null,
352 Scanner scan
= new Scanner(in
);
353 scan
.useDelimiter("\0");
355 return new JSONObject(scan
.next());
356 } catch (JSONException e
) {
357 throw new IOException(e
);
367 * Process the given story resource into a fully filled {@link Story}
371 * the optional progress reporter
373 * @return the {@link Story}, never NULL
375 * @throws IOException
376 * in case of I/O error
378 // TODO: ADD final when BasicSupport_Deprecated is gone
379 public Story
process(Progress pg
) throws IOException
{
380 setCurrentReferer(source
);
382 sourceNode
= loadDocument(source
);
385 Story story
= doProcess(pg
);
387 // Check for "no chapters" stories
388 if (story
.getChapters().isEmpty()
389 && story
.getMeta().getResume() != null
390 && !story
.getMeta().getResume().getParagraphs().isEmpty()) {
391 Chapter resume
= story
.getMeta().getResume();
394 story
.getChapters().add(resume
);
395 story
.getMeta().setWords(resume
.getWords());
397 String descChapterName
= Instance
.getInstance().getTrans()
398 .getString(StringId
.DESCRIPTION
);
399 resume
= new Chapter(0, descChapterName
);
400 story
.getMeta().setResume(resume
);
410 * Actual processing step, without the calls to other methods.
412 * Will convert the story resource into a fully filled {@link Story} object.
415 * the optional progress reporter
417 * @return the {@link Story}, never NULL
419 * @throws IOException
420 * in case of I/O error
422 protected Story
doProcess(Progress pg
) throws IOException
{
426 pg
.setMinMax(0, 100);
429 pg
.setName("Initialising");
432 Progress pgMeta
= new Progress();
433 pg
.addProgress(pgMeta
, 10);
434 Story story
= processMeta(true, pgMeta
);
435 pgMeta
.done(); // 10%
436 pg
.put("meta", story
.getMeta());
438 Progress pgGetChapters
= new Progress();
439 pg
.addProgress(pgGetChapters
, 10);
440 story
.setChapters(new ArrayList
<Chapter
>());
441 List
<Entry
<String
, URL
>> chapters
= getChapters(pgGetChapters
);
442 pgGetChapters
.done(); // 20%
444 if (chapters
!= null) {
445 Progress pgChaps
= new Progress("Extracting chapters", 0,
446 chapters
.size() * 300);
447 pg
.addProgress(pgChaps
, 80);
451 for (Entry
<String
, URL
> chap
: chapters
) {
452 pgChaps
.setName("Extracting chapter " + i
);
453 URL chapUrl
= chap
.getValue();
454 String chapName
= chap
.getKey();
455 if (chapUrl
!= null) {
456 setCurrentReferer(chapUrl
);
459 pgChaps
.setProgress(i
* 100);
460 Progress pgGetChapterContent
= new Progress();
461 Progress pgMakeChapter
= new Progress();
462 pgChaps
.addProgress(pgGetChapterContent
, 100);
463 pgChaps
.addProgress(pgMakeChapter
, 100);
465 String content
= getChapterContent(chapUrl
, i
,
466 pgGetChapterContent
);
467 pgGetChapterContent
.done();
468 Chapter cc
= bsPara
.makeChapter(this, chapUrl
, i
,
469 chapName
, content
, isHtml(), pgMakeChapter
);
470 pgMakeChapter
.done();
472 words
+= cc
.getWords();
473 story
.getChapters().add(cc
);
478 story
.getMeta().setWords(words
);
480 pgChaps
.setName("Extracting chapters");
490 * Create a chapter from the given data.
493 * the source URL for this content, which can be used to try and
494 * find images if images are present in the format [image-url]
496 * the chapter number (0 = description)
500 * the content of the chapter
502 * @return the {@link Chapter}, never NULL
504 * @throws IOException
505 * in case of I/O error
507 public Chapter
makeChapter(URL source
, int number
, String name
,
508 String content
) throws IOException
{
509 return bsPara
.makeChapter(this, source
, number
, name
,
510 content
, isHtml(), null);
514 * Return a {@link BasicSupport} implementation supporting the given
515 * resource if possible.
520 * @return an implementation that supports it, or NULL
522 public static BasicSupport
getSupport(URL url
) {
527 // TEXT and INFO_TEXT always support files (not URLs though)
528 for (SupportType type
: SupportType
.values()) {
529 if (type
!= SupportType
.TEXT
&& type
!= SupportType
.INFO_TEXT
) {
530 BasicSupport support
= getSupport(type
, url
);
531 if (support
!= null && support
.supports(url
)) {
537 for (SupportType type
: new SupportType
[] { SupportType
.INFO_TEXT
,
538 SupportType
.TEXT
}) {
539 BasicSupport support
= getSupport(type
, url
);
540 if (support
!= null && support
.supports(url
)) {
549 * Return a {@link BasicSupport} implementation supporting the given type.
552 * the type, must not be NULL
554 * the {@link URL} to support (can be NULL to get an
555 * "abstract support"; if not NULL, will be used as the source
558 * @return an implementation that supports it, or NULL
560 public static BasicSupport
getSupport(SupportType type
, URL url
) {
561 BasicSupport support
= null;
565 support
= new Epub();
568 support
= new InfoText();
572 // Can fail if no client key or NO in options
573 support
= new FimfictionApi();
574 } catch (IOException e
) {
575 support
= new Fimfiction();
579 support
= new Fanfiction();
582 support
= new Text();
585 support
= new MangaHub();
588 support
= new E621();
591 support
= new YiffStar();
594 support
= new EHentai();
597 support
= new MangaLel();
603 support
= new Html();
607 if (support
!= null) {
608 support
.setType(type
);
609 support
.source
= support
.getCanonicalUrl(url
);