Library scanning much quicker
[nikiroo-utils.git] / src / be / nikiroo / fanfix / supported / Text.java
1 package be.nikiroo.fanfix.supported;
2
3 import java.awt.image.BufferedImage;
4 import java.io.File;
5 import java.io.IOException;
6 import java.io.InputStream;
7 import java.net.URISyntaxException;
8 import java.net.URL;
9 import java.util.ArrayList;
10 import java.util.List;
11 import java.util.Map.Entry;
12 import java.util.Scanner;
13
14 import be.nikiroo.fanfix.Instance;
15 import be.nikiroo.fanfix.bundles.Config;
16 import be.nikiroo.fanfix.data.MetaData;
17
18 /**
19 * Support class for local stories encoded in textual format, with a few rules:
20 * <ul>
21 * <li>The title must be on the first line</li>
22 * <li>The author (preceded by nothing, "by " or "©") must be on the second
23 * line, possibly with the publication date in parenthesis (i.e., "
24 * <tt>By Unknown (3rd October 1998)</tt>")</li>
25 * <li>Chapters must be declared with "<tt>Chapter x</tt>" or "
26 * <tt>Chapter x: NAME OF THE CHAPTER</tt>", where "<tt>x</tt>" is the chapter
27 * number</li>
28 * <li>A description of the story must be given as chapter number 0</li>
29 * <li>A cover may be present, with the same filename but a PNG, JPEG or JPG
30 * extension</li<
31 * </ul>
32 *
33 * @author niki
34 */
35 class Text extends BasicSupport {
36 @Override
37 protected boolean isHtml() {
38 return false;
39 }
40
41 @Override
42 public String getSourceName() {
43 return "text";
44 }
45
46 @Override
47 protected MetaData getMeta(URL source, InputStream in) throws IOException {
48 MetaData meta = new MetaData();
49
50 meta.setTitle(getTitle(reset(in)));
51 meta.setAuthor(getAuthor(reset(in)));
52 meta.setDate(getDate(reset(in)));
53 meta.setTags(new ArrayList<String>());
54 meta.setSource(getSourceName());
55 meta.setPublisher(""); // often sourceName
56 meta.setUuid(source.toString());
57 meta.setLuid("");
58 meta.setLang(getLang(source, reset(in))); // default is EN
59 meta.setSubject(getSubject(source));
60 meta.setType(getType().toString());
61 meta.setImageDocument(false);
62 meta.setCover(getCover(source));
63
64 return meta;
65 }
66
67 private String getSubject(URL source) throws IOException {
68 try {
69 File file = new File(source.toURI());
70 return file.getParentFile().getName();
71 } catch (URISyntaxException e) {
72 throw new IOException("Cannot parse the URL to File: "
73 + source.toString(), e);
74 }
75
76 }
77
78 private String getLang(URL source, InputStream in) throws IOException {
79 @SuppressWarnings("resource")
80 Scanner scan = new Scanner(in, "UTF-8");
81 scan.useDelimiter("\\n");
82 scan.next(); // Title
83 scan.next(); // Author (Date)
84 String chapter0 = scan.next(); // empty or Chapter 0
85 while (chapter0.isEmpty()) {
86 chapter0 = scan.next();
87 }
88
89 String lang = detectChapter(chapter0);
90 if (lang == null) {
91 lang = "EN";
92 } else {
93 lang = lang.toUpperCase();
94 }
95
96 return lang;
97 }
98
99 private String getTitle(InputStream in) throws IOException {
100 @SuppressWarnings("resource")
101 Scanner scan = new Scanner(in, "UTF-8");
102 scan.useDelimiter("\\n");
103 return scan.next();
104 }
105
106 private String getAuthor(InputStream in) throws IOException {
107 @SuppressWarnings("resource")
108 Scanner scan = new Scanner(in, "UTF-8");
109 scan.useDelimiter("\\n");
110 scan.next();
111 String authorDate = scan.next();
112
113 String author = authorDate;
114 int pos = authorDate.indexOf('(');
115 if (pos >= 0) {
116 author = authorDate.substring(0, pos);
117 }
118
119 return fixAuthor(author);
120 }
121
122 private String getDate(InputStream in) throws IOException {
123 @SuppressWarnings("resource")
124 Scanner scan = new Scanner(in, "UTF-8");
125 scan.useDelimiter("\\n");
126 scan.next();
127 String authorDate = scan.next();
128
129 String date = "";
130 int pos = authorDate.indexOf('(');
131 if (pos >= 0) {
132 date = authorDate.substring(pos + 1).trim();
133 pos = date.lastIndexOf(')');
134 if (pos >= 0) {
135 date = date.substring(0, pos).trim();
136 }
137 }
138
139 return date;
140 }
141
142 @Override
143 protected String getDesc(URL source, InputStream in) throws IOException {
144 return getChapterContent(source, in, 0);
145 }
146
147 private BufferedImage getCover(URL source) throws IOException {
148 String path;
149 try {
150 path = new File(source.toURI()).getPath();
151 } catch (URISyntaxException e) {
152 Instance.syserr(e);
153 path = null;
154 }
155
156 for (String ext : new String[] { ".txt", ".text", ".story" }) {
157 if (path.endsWith(ext)) {
158 path = path.substring(0, path.length() - ext.length());
159 }
160 }
161
162 return getImage(source, path);
163 }
164
165 @Override
166 protected List<Entry<String, URL>> getChapters(URL source, InputStream in)
167 throws IOException {
168 List<Entry<String, URL>> chaps = new ArrayList<Entry<String, URL>>();
169 @SuppressWarnings("resource")
170 Scanner scan = new Scanner(in, "UTF-8");
171 scan.useDelimiter("\\n");
172 boolean descSkipped = false;
173 boolean prevLineEmpty = false;
174 while (scan.hasNext()) {
175 String line = scan.next();
176 if (prevLineEmpty && detectChapter(line) != null) {
177 if (descSkipped) {
178 String chapName = Integer.toString(chaps.size());
179 int pos = line.indexOf(':');
180 if (pos >= 0 && pos + 1 < line.length()) {
181 chapName = line.substring(pos + 1).trim();
182 }
183 final URL value = source;
184 final String key = chapName;
185 chaps.add(new Entry<String, URL>() {
186 public URL setValue(URL value) {
187 return null;
188 }
189
190 public URL getValue() {
191 return value;
192 }
193
194 public String getKey() {
195 return key;
196 }
197 });
198 } else {
199 descSkipped = true;
200 }
201 }
202
203 prevLineEmpty = line.trim().isEmpty();
204 }
205
206 return chaps;
207 }
208
209 @Override
210 protected String getChapterContent(URL source, InputStream in, int number)
211 throws IOException {
212 StringBuilder builder = new StringBuilder();
213 @SuppressWarnings("resource")
214 Scanner scan = new Scanner(in, "UTF-8");
215 scan.useDelimiter("\\n");
216 boolean inChap = false;
217 while (scan.hasNext()) {
218 String line = scan.next();
219 if (detectChapter(line, number) != null) {
220 inChap = true;
221 } else if (inChap && detectChapter(line) != null) {
222 break;
223 } else if (inChap) {
224 builder.append(line);
225 builder.append("\n");
226 }
227 }
228
229 return builder.toString();
230 }
231
232 @Override
233 protected boolean supports(URL url) {
234 if ("file".equals(url.getProtocol())) {
235 File file;
236 try {
237 file = new File(url.toURI());
238 file = new File(file.getPath() + ".info");
239 } catch (URISyntaxException e) {
240 Instance.syserr(e);
241 file = null;
242 }
243
244 return file == null || !file.exists();
245 }
246
247 return false;
248 }
249
250 /**
251 * Check if the given line looks like a starting chapter in a supported
252 * language, and return the language if it does (or NULL if not).
253 *
254 * @param line
255 * the line to check
256 *
257 * @return the language or NULL
258 */
259 private String detectChapter(String line) {
260 return detectChapter(line, null);
261 }
262
263 /**
264 * Check if the given line looks like the given starting chapter in a
265 * supported language, and return the language if it does (or NULL if not).
266 *
267 * @param line
268 * the line to check
269 *
270 * @return the language or NULL
271 */
272 private String detectChapter(String line, Integer number) {
273 line = line.toUpperCase();
274 for (String lang : Instance.getConfig().getString(Config.CHAPTER)
275 .split(",")) {
276 String chapter = Instance.getConfig().getStringX(Config.CHAPTER,
277 lang);
278 if (chapter != null && !chapter.isEmpty()) {
279 chapter = chapter.toUpperCase() + " ";
280 if (line.startsWith(chapter)) {
281 if (number != null) {
282 // We want "[CHAPTER] [number]: [name]", with ": [name]"
283 // optional
284 String test = line.substring(chapter.length()).trim();
285 if (test.startsWith(Integer.toString(number))) {
286 test = test.substring(
287 Integer.toString(number).length()).trim();
288 if (test.isEmpty() || test.startsWith(":")) {
289 return lang;
290 }
291 }
292 } else {
293 return lang;
294 }
295 }
296 }
297 }
298
299 return null;
300 }
301 }