import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
+import java.util.Date;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
E621,
/** Furry website with stories */
YIFFSTAR,
+ /** Comics and images groups, mostly but not only NSFW */
+ E_HENTAI,
/** CBZ files */
CBZ,
/** HTML files */
private URL currentReferer; // with only one 'r', as in 'HTTP'...
// quote chars
- private char openQuote = Instance.getTrans().getChar(
+ private char openQuote = Instance.getTrans().getCharacter(
StringId.OPEN_SINGLE_QUOTE);
- private char closeQuote = Instance.getTrans().getChar(
+ private char closeQuote = Instance.getTrans().getCharacter(
StringId.CLOSE_SINGLE_QUOTE);
- private char openDoubleQuote = Instance.getTrans().getChar(
+ private char openDoubleQuote = Instance.getTrans().getCharacter(
StringId.OPEN_DOUBLE_QUOTE);
- private char closeDoubleQuote = Instance.getTrans().getChar(
+ private char closeDoubleQuote = Instance.getTrans().getCharacter(
StringId.CLOSE_DOUBLE_QUOTE);
/**
* the source of the story
* @param in
* the input (the main resource)
+ * @param pg
+ * the optional progress reporter
*
* @return the chapters
*
* in case of I/O error
*/
protected abstract List<Entry<String, URL>> getChapters(URL source,
- InputStream in) throws IOException;
+ InputStream in, Progress pg) throws IOException;
/**
* Return the content of the chapter (possibly HTML encoded, if
* the input (the main resource)
* @param number
* the chapter number
+ * @param pg
+ * the optional progress reporter
*
* @return the content
*
* in case of I/O error
*/
protected abstract String getChapterContent(URL source, InputStream in,
- int number) throws IOException;
+ int number, Progress pg) throws IOException;
+
+ /**
+ * Log into the support (can be a no-op depending upon the support).
+ *
+ * @throws IOException
+ * in case of I/O error
+ */
+ public void login() throws IOException {
+
+ }
/**
* Return the list of cookies (values included) that must be used to
* it.
*
* @return the cookies
+ *
+ * @throws IOException
+ * in case of I/O error
*/
- public Map<String, String> getCookies() {
+ public Map<String, String> getCookies() throws IOException {
return new HashMap<String, String>();
}
* in case of I/O error
*/
public Story processMeta(URL url) throws IOException {
- return processMeta(url, true, false);
+ return processMeta(url, true, false, null);
}
/**
*
* @param close
* close "this" and "in" when done
+ * @param pg
+ * the optional progress reporter
*
* @return the {@link Story}
*
* @throws IOException
* in case of I/O error
*/
- protected Story processMeta(URL url, boolean close, boolean getDesc)
- throws IOException {
+ protected Story processMeta(URL url, boolean close, boolean getDesc,
+ Progress pg) throws IOException {
+ if (pg == null) {
+ pg = new Progress();
+ } else {
+ pg.setMinMax(0, 100);
+ }
+
+ login();
+ pg.setProgress(10);
+
url = getCanonicalUrl(url);
setCurrentReferer(url);
try {
preprocess(url, getInput());
+ pg.setProgress(30);
Story story = new Story();
MetaData meta = getMeta(url, getInput());
+ if (meta.getCreationDate() == null
+ || meta.getCreationDate().isEmpty()) {
+ meta.setCreationDate(StringUtils.fromTime(new Date().getTime()));
+ }
story.setMeta(meta);
+ pg.setProgress(50);
+
if (meta != null && meta.getCover() == null) {
meta.setCover(getDefaultCover(meta.getSubject()));
}
+ pg.setProgress(60);
+
if (getDesc) {
String descChapterName = Instance.getTrans().getString(
StringId.DESCRIPTION);
story.getMeta().setResume(
makeChapter(url, 0, descChapterName,
- getDesc(url, getInput())));
+ getDesc(url, getInput()), null));
}
+ pg.setProgress(100);
return story;
} finally {
if (close) {
url = getCanonicalUrl(url);
pg.setProgress(1);
try {
- Story story = processMeta(url, false, true);
- pg.setProgress(10);
+ Progress pgMeta = new Progress();
+ pg.addProgress(pgMeta, 10);
+ Story story = processMeta(url, false, true, pgMeta);
+ if (!pgMeta.isDone()) {
+ pgMeta.setProgress(pgMeta.getMax()); // 10%
+ }
+
if (story == null) {
- pg.setProgress(100);
+ pg.setProgress(90);
return null;
}
+ pg.setName("Retrieving " + story.getMeta().getTitle());
+
setCurrentReferer(url);
+ Progress pgGetChapters = new Progress();
+ pg.addProgress(pgGetChapters, 10);
story.setChapters(new ArrayList<Chapter>());
+ List<Entry<String, URL>> chapters = getChapters(url, getInput(),
+ pgGetChapters);
+ if (!pgGetChapters.isDone()) {
+ pgGetChapters.setProgress(pgGetChapters.getMax()); // 20%
+ }
- List<Entry<String, URL>> chapters = getChapters(url, getInput());
- pg.setProgress(20);
-
- int i = 1;
if (chapters != null) {
- Progress pgChaps = new Progress(0, chapters.size());
+ Progress pgChaps = new Progress("Extracting chapters", 0,
+ chapters.size() * 300);
pg.addProgress(pgChaps, 80);
+ long words = 0;
+ int i = 1;
for (Entry<String, URL> chap : chapters) {
+ pgChaps.setName("Extracting chapter " + i);
setCurrentReferer(chap.getValue());
InputStream chapIn = Instance.getCache().open(
chap.getValue(), this, true);
+ pgChaps.setProgress(i * 100);
try {
- story.getChapters().add(
- makeChapter(url, i, chap.getKey(),
- getChapterContent(url, chapIn, i)));
+ Progress pgGetChapterContent = new Progress();
+ Progress pgMakeChapter = new Progress();
+ pgChaps.addProgress(pgGetChapterContent, 100);
+ pgChaps.addProgress(pgMakeChapter, 100);
+
+ String content = getChapterContent(url, chapIn, i,
+ pgGetChapterContent);
+ if (!pgGetChapterContent.isDone()) {
+ pgGetChapterContent.setProgress(pgGetChapterContent
+ .getMax());
+ }
+
+ Chapter cc = makeChapter(url, i, chap.getKey(),
+ content, pgMakeChapter);
+ if (!pgMakeChapter.isDone()) {
+ pgMakeChapter.setProgress(pgMakeChapter.getMax());
+ }
+
+ words += cc.getWords();
+ story.getChapters().add(cc);
+ if (story.getMeta() != null) {
+ story.getMeta().setWords(words);
+ }
} finally {
chapIn.close();
}
- pgChaps.setProgress(i++);
+ i++;
}
+
+ pgChaps.setName("Extracting chapters");
} else {
- pg.setProgress(100);
+ pg.setProgress(80);
}
return story;
* the chapter name
* @param content
* the chapter content
+ * @param pg
+ * the optional progress reporter
*
* @return the {@link Chapter}
*
* in case of I/O error
*/
protected Chapter makeChapter(URL source, int number, String name,
- String content) throws IOException {
+ String content, Progress pg) throws IOException {
// Chapter name: process it correctly, then remove the possible
- // redundant "Chapter x: " in front of it
+ // redundant "Chapter x: " in front of it, or "-" (as in
+ // "Chapter 5: - Fun!" after the ": " was automatically added)
String chapterName = processPara(name).getContent().trim();
for (String lang : Instance.getConfig().getString(Config.CHAPTER)
.split(",")) {
Integer.toString(number).length()).trim();
}
- if (chapterName.startsWith(":")) {
+ while (chapterName.startsWith(":") || chapterName.startsWith("-")) {
chapterName = chapterName.substring(1).trim();
}
//
Chapter chap = new Chapter(number, chapterName);
if (content != null) {
- chap.setParagraphs(makeParagraphs(source, content));
+ List<Paragraph> paras = makeParagraphs(source, content, pg);
+ long words = 0;
+ for (Paragraph para : paras) {
+ words += para.getWords();
+ }
+ chap.setParagraphs(paras);
+ chap.setWords(words);
}
return chap;
* the source URL of the story
* @param content
* the textual content
+ * @param pg
+ * the optional progress reporter
*
* @return the {@link Paragraph}s
*
* @throws IOException
* in case of I/O error
*/
- protected List<Paragraph> makeParagraphs(URL source, String content)
- throws IOException {
+ protected List<Paragraph> makeParagraphs(URL source, String content,
+ Progress pg) throws IOException {
+ if (pg == null) {
+ pg = new Progress();
+ }
+
if (isHtml()) {
// Special <HR> processing:
content = content.replaceAll("(<hr [^>]*>)|(<hr/>)|(<hr>)",
- "\n* * *\n");
+ "<br/>* * *<br/>");
}
List<Paragraph> paras = new ArrayList<Paragraph>();
- InputStream in = new ByteArrayInputStream(content.getBytes("UTF-8"));
- try {
- BufferedReader buff = new BufferedReader(new InputStreamReader(in,
- "UTF-8"));
-
- for (String encodedLine = buff.readLine(); encodedLine != null; encodedLine = buff
- .readLine()) {
- String lines[];
- if (isHtml()) {
- lines = encodedLine.split("(<p>|</p>|<br>|<br/>|\\n)");
- } else {
- lines = new String[] { encodedLine };
- }
-
- for (String aline : lines) {
- String line = aline.trim();
- URL image = null;
+ if (content != null && !content.trim().isEmpty()) {
+ if (isHtml()) {
+ String[] tab = content.split("(<p>|</p>|<br>|<br/>)");
+ pg.setMinMax(0, tab.length);
+ int i = 1;
+ for (String line : tab) {
if (line.startsWith("[") && line.endsWith("]")) {
- image = getImageUrl(this, source,
- line.substring(1, line.length() - 1).trim());
+ pg.setName("Extracting image " + i);
}
+ paras.add(makeParagraph(source, line.trim()));
+ pg.setProgress(i++);
+ }
+ pg.setName(null);
+ } else {
+ List<String> lines = new ArrayList<String>();
+ BufferedReader buff = null;
+ try {
+ buff = new BufferedReader(
+ new InputStreamReader(new ByteArrayInputStream(
+ content.getBytes("UTF-8")), "UTF-8"));
+ for (String line = buff.readLine(); line != null; line = buff
+ .readLine()) {
+ lines.add(line.trim());
+ }
+ } finally {
+ if (buff != null) {
+ buff.close();
+ }
+ }
- if (image != null) {
- paras.add(new Paragraph(image));
- } else {
- paras.add(processPara(line));
+ pg.setMinMax(0, lines.size());
+ int i = 0;
+ for (String line : lines) {
+ if (line.startsWith("[") && line.endsWith("]")) {
+ pg.setName("Extracting image " + i);
}
+ paras.add(makeParagraph(source, line));
+ pg.setProgress(i++);
}
+ pg.setName(null);
}
- } finally {
- in.close();
- }
- // Check quotes for "bad" format
- List<Paragraph> newParas = new ArrayList<Paragraph>();
- for (Paragraph para : paras) {
- newParas.addAll(requotify(para));
- }
- paras = newParas;
+ // Check quotes for "bad" format
+ List<Paragraph> newParas = new ArrayList<Paragraph>();
+ for (Paragraph para : paras) {
+ newParas.addAll(requotify(para));
+ }
+ paras = newParas;
- // Remove double blanks/brks
- fixBlanksBreaks(paras);
+ // Remove double blanks/brks
+ fixBlanksBreaks(paras);
+ }
return paras;
}
+ /**
+ * Convert the given line into a single {@link Paragraph}.
+ *
+ * @param source
+ * the source URL of the story
+ * @param line
+ * the textual content of the paragraph
+ *
+ * @return the {@link Paragraph}
+ */
+ private Paragraph makeParagraph(URL source, String line) {
+ URL image = null;
+ if (line.startsWith("[") && line.endsWith("]")) {
+ image = getImageUrl(this, source,
+ line.substring(1, line.length() - 1).trim());
+ }
+
+ if (image != null) {
+ return new Paragraph(image);
+ } else {
+ return processPara(line);
+ }
+ }
+
/**
* Fix the {@link ParagraphType#BLANK}s and {@link ParagraphType#BREAK}s of
* those {@link Paragraph}s.
if (line != null) {
// try for files
- String path = null;
if (source != null) {
- path = new File(source.getFile()).getParent();
try {
- String basePath = new File(new File(path), line.trim())
- .getAbsolutePath();
+
+ String relPath = null;
+ String absPath = null;
+ try {
+ String path = new File(source.getFile()).getParent();
+ relPath = new File(new File(path), line.trim())
+ .getAbsolutePath();
+ } catch (Exception e) {
+ // Cannot be converted to path (one possibility to take
+ // into account: absolute path on Windows)
+ }
+ try {
+ absPath = new File(line.trim()).getAbsolutePath();
+ } catch (Exception e) {
+ // Cannot be converted to path (at all)
+ }
+
for (String ext : getImageExt(true)) {
- if (new File(basePath + ext).exists()) {
- url = new File(basePath + ext).toURI().toURL();
+ if (absPath != null && new File(absPath + ext).exists()) {
+ url = new File(absPath + ext).toURI().toURL();
+ } else if (relPath != null
+ && new File(relPath + ext).exists()) {
+ url = new File(relPath + ext).toURI().toURL();
}
}
} catch (Exception e) {
- // Nothing to do here
+ // Should not happen since we control the correct arguments
}
}
if (!singleQ && !doubleQ) {
line = openDoubleQuote + line + closeDoubleQuote;
- newParas.add(new Paragraph(ParagraphType.QUOTE, line));
+ newParas.add(new Paragraph(ParagraphType.QUOTE, line, para
+ .getWords()));
} else {
char open = singleQ ? openQuote : openDoubleQuote;
char close = singleQ ? closeQuote : closeDoubleQuote;
if (posDot >= 0) {
String rest = line.substring(posDot + 1).trim();
line = line.substring(0, posDot + 1).trim();
- newParas.add(new Paragraph(ParagraphType.QUOTE, line));
+ long words = 1;
+ for (char car : line.toCharArray()) {
+ if (car == ' ') {
+ words++;
+ }
+ }
+ newParas.add(new Paragraph(ParagraphType.QUOTE, line, words));
if (!rest.isEmpty()) {
newParas.addAll(requotify(processPara(rest)));
}
boolean tentativeCloseQuote = false;
char prev = '\0';
int dashCount = 0;
+ long words = 1;
StringBuilder builder = new StringBuilder();
for (char car : line.toCharArray()) {
case '\t':
case '\n': // just in case
case '\r': // just in case
+ if (builder.length() > 0
+ && builder.charAt(builder.length() - 1) != ' ') {
+ words++;
+ }
builder.append(' ');
break;
type = ParagraphType.QUOTE;
}
- return new Paragraph(type, line);
+ return new Paragraph(type, line, words);
}
/**
return new E621().setType(type);
case YIFFSTAR:
return new YiffStar().setType(type);
+ case E_HENTAI:
+ return new EHentai().setType(type);
case CBZ:
return new Cbz().setType(type);
case HTML:
return rep;
}
+
+ /**
+ * Return the text between the key and the endKey (and optional subKey can
+ * be passed, in this case we will look for the key first, then take the
+ * text between the subKey and the endKey).
+ * <p>
+ * Will only match the first line with the given key if more than one are
+ * possible. Which also means that if the subKey or endKey is not found on
+ * that line, NULL will be returned.
+ *
+ * @param in
+ * the input
+ * @param key
+ * the key to match (also supports "^" at start to say
+ * "only if it starts with" the key)
+ * @param subKey
+ * the sub key or NULL if none
+ * @param endKey
+ * the end key or NULL for "up to the end"
+ * @return the text or NULL if not found
+ */
+ static String getKeyLine(InputStream in, String key, String subKey,
+ String endKey) {
+ String result = null;
+
+ String line = getLine(in, key, 0);
+ if (line != null && line.contains(key)) {
+ line = line.substring(line.indexOf(key) + key.length());
+ if (subKey == null || subKey.isEmpty() || line.contains(subKey)) {
+ if (subKey != null) {
+ line = line.substring(line.indexOf(subKey)
+ + subKey.length());
+ }
+ if (endKey == null || line.contains(endKey)) {
+ if (endKey != null) {
+ line = line.substring(0, line.indexOf(endKey));
+ result = line;
+ }
+ }
+ }
+ }
+
+ return result;
+ }
}