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;
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);
if (meta != null && meta.getCover() == null) {
return null;
}
+ pg.setName("Retrieving " + story.getMeta().getTitle());
+
setCurrentReferer(url);
story.setChapters(new ArrayList<Chapter>());
Progress pgChaps = new Progress(0, chapters.size());
pg.addProgress(pgChaps, 80);
+ long words = 0;
for (Entry<String, URL> chap : chapters) {
setCurrentReferer(chap.getValue());
InputStream chapIn = Instance.getCache().open(
chap.getValue(), this, true);
try {
- story.getChapters().add(
- makeChapter(url, i, chap.getKey(),
- getChapterContent(url, chapIn, i)));
+ Chapter cc = makeChapter(url, i, chap.getKey(),
+ getChapterContent(url, chapIn, i));
+ words += cc.getWords();
+ story.getChapters().add(cc);
+ if (story.getMeta() != null) {
+ story.getMeta().setWords(words);
+ }
} finally {
chapIn.close();
}
Chapter chap = new Chapter(number, chapterName);
if (content != null) {
- chap.setParagraphs(makeParagraphs(source, content));
+ List<Paragraph> paras = makeParagraphs(source, content);
+ long words = 0;
+ for (Paragraph para : paras) {
+ words += para.getWords();
+ }
+ chap.setParagraphs(paras);
+ chap.setWords(words);
}
return chap;
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 (line.startsWith("[") && line.endsWith("]")) {
- image = getImageUrl(this, source,
- line.substring(1, line.length() - 1).trim());
+ if (content != null && !content.trim().isEmpty()) {
+ if (isHtml()) {
+ for (String line : content.split("(<p>|</p>|<br>|<br/>)")) {
+ paras.add(makeParagraph(source, line.trim()));
+ }
+ } else {
+ 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()) {
+ paras.add(makeParagraph(source, line.trim()));
}
-
- if (image != null) {
- paras.add(new Paragraph(image));
- } else {
- paras.add(processPara(line));
+ } finally {
+ if (buff != null) {
+ buff.close();
}
}
}
- } 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 (!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);
}
/**
git://git.nikiroo.be / fanfix.git / blobdiff