package be.nikiroo.fanfix.supported;
import java.awt.image.BufferedImage;
+import java.io.BufferedReader;
import java.io.ByteArrayInputStream;
import java.io.File;
import java.io.IOException;
import java.io.InputStream;
+import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import be.nikiroo.fanfix.data.Paragraph.ParagraphType;
import be.nikiroo.fanfix.data.Story;
import be.nikiroo.utils.IOUtils;
+import be.nikiroo.utils.Progress;
import be.nikiroo.utils.StringUtils;
/**
/** Furry website with comics support */
E621,
/** CBZ files */
- CBZ;
+ CBZ,
+ /** HTML files */
+ HTML;
/**
* A description of this support type (more information than the
private InputStream in;
private SupportType type;
- private URL currentReferer; // with on 'r', as in 'HTTP'...
+ private URL currentReferer; // with only one 'r', as in 'HTTP'...
// quote chars
private char openQuote = Instance.getTrans().getChar(
*/
protected Story processMeta(URL url, boolean close, boolean getDesc)
throws IOException {
- in = Instance.getCache().open(url, this, false);
+ in = openInput(url);
if (in == null) {
return null;
}
*
* @param url
* the story resource
+ * @param pg
+ * the optional progress reporter
*
* @return the {@link Story}
*
* @throws IOException
* in case of I/O error
*/
- public Story process(URL url) throws IOException {
+ public Story process(URL url, Progress pg) throws IOException {
+ if (pg == null) {
+ pg = new Progress();
+ } else {
+ pg.setMinMax(0, 100);
+ }
+
setCurrentReferer(url);
+ pg.setProgress(1);
try {
Story story = processMeta(url, false, true);
+ pg.setProgress(10);
if (story == null) {
+ pg.setProgress(100);
return null;
}
story.setChapters(new ArrayList<Chapter>());
List<Entry<String, URL>> chapters = getChapters(url, getInput());
+ pg.setProgress(20);
+
int i = 1;
if (chapters != null) {
+ Progress pgChaps = new Progress(0, chapters.size());
+ pg.addProgress(pgChaps, 80);
+
for (Entry<String, URL> chap : chapters) {
setCurrentReferer(chap.getValue());
InputStream chapIn = Instance.getCache().open(
chapIn.close();
}
- i++;
+ pgChaps.setProgress(i++);
}
+ } else {
+ pg.setProgress(100);
}
return story;
Chapter chap = new Chapter(number, chapterName);
- if (content == null) {
- return chap;
+ if (content != null) {
+ chap.setParagraphs(makeParagraphs(source, content));
}
+ return chap;
+
+ }
+
+ /**
+ * Convert the given content into {@link Paragraph}s.
+ *
+ * @param source
+ * the source URL of the story
+ * @param content
+ * the textual content
+ *
+ * @return the {@link Paragraph}s
+ *
+ * @throws IOException
+ * in case of I/O error
+ */
+ protected List<Paragraph> makeParagraphs(URL source, String content)
+ throws IOException {
if (isHtml()) {
// Special <HR> processing:
content = content.replaceAll("(<hr [^>]*>)|(<hr/>)|(<hr>)",
"\n* * *\n");
}
+ List<Paragraph> paras = new ArrayList<Paragraph>();
InputStream in = new ByteArrayInputStream(content.getBytes("UTF-8"));
try {
- @SuppressWarnings("resource")
- Scanner scan = new Scanner(in, "UTF-8");
- scan.useDelimiter("(\\n|</p>)"); // \n for test, </p> for html
-
- List<Paragraph> paras = new ArrayList<Paragraph>();
- while (scan.hasNext()) {
- String line = scan.next().trim();
- boolean image = false;
- if (line.startsWith("[") && line.endsWith("]")) {
- URL url = getImageUrl(this, source,
- line.substring(1, line.length() - 1).trim());
- if (url != null) {
- paras.add(new Paragraph(url));
- image = true;
- }
+ 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 };
}
- if (!image) {
- paras.add(processPara(line));
+ for (String aline : lines) {
+ String line = aline.trim();
+
+ URL image = null;
+ if (line.startsWith("[") && line.endsWith("]")) {
+ image = getImageUrl(this, source,
+ line.substring(1, line.length() - 1).trim());
+ }
+
+ if (image != null) {
+ paras.add(new Paragraph(image));
+ } else {
+ paras.add(processPara(line));
+ }
}
}
+ } finally {
+ in.close();
+ }
- // 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
- boolean space = false;
- boolean brk = true;
- for (int i = 0; i < paras.size(); i++) {
- Paragraph para = paras.get(i);
- boolean thisSpace = para.getType() == ParagraphType.BLANK;
- boolean thisBrk = para.getType() == ParagraphType.BREAK;
-
- if (space && thisBrk) {
- paras.remove(i - 1);
- i--;
- } else if ((space || brk) && (thisSpace || thisBrk)) {
- paras.remove(i);
- i--;
- }
+ // Check quotes for "bad" format
+ List<Paragraph> newParas = new ArrayList<Paragraph>();
+ for (Paragraph para : paras) {
+ newParas.addAll(requotify(para));
+ }
+ paras = newParas;
- space = thisSpace;
- brk = thisBrk;
- }
+ // Remove double blanks/brks
+ fixBlanksBreaks(paras);
- // Remove blank/brk at start
- if (paras.size() > 0
- && (paras.get(0).getType() == ParagraphType.BLANK || paras
- .get(0).getType() == ParagraphType.BREAK)) {
- paras.remove(0);
- }
+ return paras;
+ }
- // Remove blank/brk at end
- int last = paras.size() - 1;
- if (paras.size() > 0
- && (paras.get(last).getType() == ParagraphType.BLANK || paras
- .get(last).getType() == ParagraphType.BREAK)) {
- paras.remove(last);
+ /**
+ * Fix the {@link ParagraphType#BLANK}s and {@link ParagraphType#BREAK}s of
+ * those {@link Paragraph}s.
+ * <p>
+ * The resulting list will not contain a starting or trailing blank/break
+ * nor 2 blanks or breaks following each other.
+ *
+ * @param paras
+ * the list of {@link Paragraph}s to fix
+ */
+ protected void fixBlanksBreaks(List<Paragraph> paras) {
+ boolean space = false;
+ boolean brk = true;
+ for (int i = 0; i < paras.size(); i++) {
+ Paragraph para = paras.get(i);
+ boolean thisSpace = para.getType() == ParagraphType.BLANK;
+ boolean thisBrk = para.getType() == ParagraphType.BREAK;
+
+ if (i > 0 && space && thisBrk) {
+ paras.remove(i - 1);
+ i--;
+ } else if ((space || brk) && (thisSpace || thisBrk)) {
+ paras.remove(i);
+ i--;
}
- chap.setParagraphs(paras);
+ space = thisSpace;
+ brk = thisBrk;
+ }
- return chap;
- } finally {
- in.close();
+ // Remove blank/brk at start
+ if (paras.size() > 0
+ && (paras.get(0).getType() == ParagraphType.BLANK || paras.get(
+ 0).getType() == ParagraphType.BREAK)) {
+ paras.remove(0);
+ }
+
+ // Remove blank/brk at end
+ int last = paras.size() - 1;
+ if (paras.size() > 0
+ && (paras.get(last).getType() == ParagraphType.BLANK || paras
+ .get(last).getType() == ParagraphType.BREAK)) {
+ paras.remove(last);
}
}
+ /**
+ * Get the default cover related to this subject (see <tt>.info</tt> files).
+ *
+ * @param subject
+ * the subject
+ *
+ * @return the cover if any, or NULL
+ */
static BufferedImage getDefaultCover(String subject) {
if (subject != null && !subject.isEmpty()
&& Instance.getCoverDir() != null) {
return url;
}
+ /**
+ * Open the input file that will be used through the support.
+ *
+ * @param source
+ * the source {@link URL}
+ *
+ * @return the {@link InputStream}
+ *
+ * @throws IOException
+ * in case of I/O error
+ */
+ protected InputStream openInput(URL source) throws IOException {
+ return Instance.getCache().open(source, this, false);
+ }
+
protected InputStream reset(InputStream in) {
try {
in.reset();
*
* @return the correctly (or so we hope) quotified paragraphs
*/
- private List<Paragraph> requotify(Paragraph para) {
+ protected List<Paragraph> requotify(Paragraph para) {
List<Paragraph> newParas = new ArrayList<Paragraph>();
if (para.getType() == ParagraphType.QUOTE
*
* @return the processed {@link Paragraph}
*/
- private Paragraph processPara(String line) {
+ protected Paragraph processPara(String line) {
line = ifUnhtml(line).trim();
boolean space = true;
if (tentativeCloseQuote) {
tentativeCloseQuote = false;
- if ((car >= 'a' && car <= 'z') || (car >= 'A' && car <= 'Z')
- || (car >= '0' && car <= '9')) {
+ if (Character.isLetterOrDigit(car)) {
builder.append("'");
} else {
- builder.append(closeQuote);
+ // handle double-single quotes as double quotes
+ if (prev == car) {
+ builder.append(closeDoubleQuote);
+ continue;
+ } else {
+ builder.append(closeQuote);
+ }
}
}
case '\'':
if (space || (brk && quote)) {
quote = true;
- builder.append(openQuote);
- } else if (prev == ' ') {
- builder.append(openQuote);
+ // handle double-single quotes as double quotes
+ if (prev == car) {
+ builder.deleteCharAt(builder.length() - 1);
+ builder.append(openDoubleQuote);
+ } else {
+ builder.append(openQuote);
+ }
+ } else if (prev == ' ' || prev == car) {
+ // handle double-single quotes as double quotes
+ if (prev == car) {
+ builder.deleteCharAt(builder.length() - 1);
+ builder.append(openDoubleQuote);
+ } else {
+ builder.append(openQuote);
+ }
} else {
// it is a quote ("I'm off") or a 'quote' ("This
// 'good' restaurant"...)
quote = true;
builder.append(openQuote);
} else {
- builder.append(openQuote);
+ // handle double-single quotes as double quotes
+ if (prev == car) {
+ builder.deleteCharAt(builder.length() - 1);
+ builder.append(openDoubleQuote);
+ } else {
+ builder.append(openQuote);
+ }
}
space = false;
brk = false;
case '」':
space = false;
brk = false;
- builder.append(closeQuote);
+ // handle double-single quotes as double quotes
+ if (prev == car) {
+ builder.deleteCharAt(builder.length() - 1);
+ builder.append(closeDoubleQuote);
+ } else {
+ builder.append(closeQuote);
+ }
break;
case '«':
}
}
- for (SupportType type : new SupportType[] { SupportType.TEXT,
- SupportType.INFO_TEXT }) {
+ for (SupportType type : new SupportType[] { SupportType.INFO_TEXT,
+ SupportType.TEXT }) {
BasicSupport support = getSupport(type);
if (support != null && support.supports(url)) {
return support;
return new E621().setType(type);
case CBZ:
return new Cbz().setType(type);
+ case HTML:
+ return new Html().setType(type);
}
return null;