| 1 | package be.nikiroo.fanfix.supported; |
| 2 | |
| 3 | import java.io.File; |
| 4 | import java.io.IOException; |
| 5 | import java.io.InputStream; |
| 6 | import java.net.URISyntaxException; |
| 7 | import java.net.URL; |
| 8 | import java.net.URLDecoder; |
| 9 | import java.util.ArrayList; |
| 10 | import java.util.Arrays; |
| 11 | import java.util.Collections; |
| 12 | import java.util.zip.ZipEntry; |
| 13 | import java.util.zip.ZipInputStream; |
| 14 | |
| 15 | import org.jsoup.nodes.Document; |
| 16 | |
| 17 | import be.nikiroo.fanfix.Instance; |
| 18 | import be.nikiroo.fanfix.data.MetaData; |
| 19 | import be.nikiroo.utils.IOUtils; |
| 20 | import be.nikiroo.utils.Image; |
| 21 | import be.nikiroo.utils.StringUtils; |
| 22 | import be.nikiroo.utils.streams.MarkableFileInputStream; |
| 23 | |
| 24 | /** |
| 25 | * Support class for EPUB files created with this program (as we need some |
| 26 | * metadata available in those we create). |
| 27 | * |
| 28 | * @author niki |
| 29 | */ |
| 30 | class Epub extends InfoText { |
| 31 | private MetaData meta; |
| 32 | private File tmpDir; |
| 33 | private String desc; |
| 34 | |
| 35 | private URL fakeSource; |
| 36 | private InputStream fakeIn; |
| 37 | |
| 38 | public File getSourceFileOriginal() { |
| 39 | return super.getSourceFile(); |
| 40 | } |
| 41 | |
| 42 | @Override |
| 43 | protected File getSourceFile() { |
| 44 | try { |
| 45 | return new File(fakeSource.toURI()); |
| 46 | } catch (URISyntaxException e) { |
| 47 | Instance.getInstance().getTraceHandler().error(new IOException( |
| 48 | "Cannot get the source file from the info-text URL", e)); |
| 49 | } |
| 50 | |
| 51 | return null; |
| 52 | } |
| 53 | |
| 54 | @Override |
| 55 | protected InputStream getInput() { |
| 56 | if (fakeIn != null) { |
| 57 | try { |
| 58 | fakeIn.reset(); |
| 59 | } catch (IOException e) { |
| 60 | Instance.getInstance().getTraceHandler().error(new IOException( |
| 61 | "Cannot reset the Epub Text stream", e)); |
| 62 | } |
| 63 | |
| 64 | return fakeIn; |
| 65 | } |
| 66 | |
| 67 | return null; |
| 68 | } |
| 69 | |
| 70 | @Override |
| 71 | protected boolean supports(URL url) { |
| 72 | return url.getPath().toLowerCase().endsWith(".epub"); |
| 73 | } |
| 74 | |
| 75 | @Override |
| 76 | protected MetaData getMeta() throws IOException { |
| 77 | return meta; |
| 78 | } |
| 79 | |
| 80 | @Override |
| 81 | protected Document loadDocument(URL source) throws IOException { |
| 82 | super.loadDocument(source); // prepares super.getSourceFile() and |
| 83 | // super.getInput() |
| 84 | |
| 85 | InputStream in = super.getInput(); |
| 86 | ZipInputStream zipIn = null; |
| 87 | try { |
| 88 | zipIn = new ZipInputStream(in); |
| 89 | tmpDir = Instance.getInstance().getTempFiles() |
| 90 | .createTempDir("fanfic-reader-parser"); |
| 91 | File tmp = new File(tmpDir, "file.txt"); |
| 92 | File tmpInfo = new File(tmpDir, "file.info"); |
| 93 | |
| 94 | fakeSource = tmp.toURI().toURL(); |
| 95 | Image cover = null; |
| 96 | |
| 97 | String url; |
| 98 | try { |
| 99 | url = getSource().toURI().toURL().toString(); |
| 100 | } catch (URISyntaxException e1) { |
| 101 | url = getSource().toString(); |
| 102 | } |
| 103 | String title = null; |
| 104 | String author = null; |
| 105 | |
| 106 | for (ZipEntry entry = zipIn |
| 107 | .getNextEntry(); entry != null; entry = zipIn |
| 108 | .getNextEntry()) { |
| 109 | if (!entry.isDirectory() |
| 110 | && entry.getName().startsWith(getDataPrefix())) { |
| 111 | String entryLName = entry.getName().toLowerCase(); |
| 112 | entryLName = entryLName.substring(getDataPrefix().length()); |
| 113 | |
| 114 | boolean imageEntry = false; |
| 115 | for (String ext : bsImages.getImageExt(false)) { |
| 116 | if (entryLName.endsWith(ext)) { |
| 117 | imageEntry = true; |
| 118 | } |
| 119 | } |
| 120 | |
| 121 | if (entryLName.equals("version")) { |
| 122 | // Nothing to do for now ("first" |
| 123 | // version is 3.0) |
| 124 | } else if (entryLName.endsWith(".info")) { |
| 125 | // Info file |
| 126 | IOUtils.write(zipIn, tmpInfo); |
| 127 | } else if (imageEntry) { |
| 128 | // Cover |
| 129 | if (getCover() && cover == null) { |
| 130 | try { |
| 131 | Image img = new Image(zipIn); |
| 132 | if (img.getSize() == 0) { |
| 133 | img.close(); |
| 134 | throw new IOException( |
| 135 | "Empty image not accepted"); |
| 136 | } |
| 137 | cover = img; |
| 138 | } catch (Exception e) { |
| 139 | Instance.getInstance().getTraceHandler() |
| 140 | .error(e); |
| 141 | } |
| 142 | } |
| 143 | } else if (entryLName.equals("url")) { |
| 144 | String[] descArray = StringUtils |
| 145 | .unhtml(IOUtils.readSmallStream(zipIn)).trim() |
| 146 | .split("\n"); |
| 147 | if (descArray.length > 0) { |
| 148 | url = descArray[0].trim(); |
| 149 | } |
| 150 | } else if (entryLName.endsWith(".desc")) { |
| 151 | // // For old files |
| 152 | // if (this.desc != null) { |
| 153 | // this.desc = IOUtils.readSmallStream(zipIn).trim(); |
| 154 | // } |
| 155 | } else if (entryLName.equals("summary")) { |
| 156 | String[] descArray = StringUtils |
| 157 | .unhtml(IOUtils.readSmallStream(zipIn)).trim() |
| 158 | .split("\n"); |
| 159 | int skip = 0; |
| 160 | if (descArray.length > 1) { |
| 161 | title = descArray[0].trim(); |
| 162 | skip = 1; |
| 163 | if (descArray.length > 2 |
| 164 | && descArray[1].startsWith("©")) { |
| 165 | author = descArray[1].substring(1).trim(); |
| 166 | skip = 2; |
| 167 | } |
| 168 | } |
| 169 | // this.desc = ""; |
| 170 | // for (int i = skip; i < descArray.length; i++) { |
| 171 | // this.desc += descArray[i].trim() + "\n"; |
| 172 | // } |
| 173 | // |
| 174 | // this.desc = this.desc.trim(); |
| 175 | } else { |
| 176 | // Hopefully the data file |
| 177 | IOUtils.write(zipIn, tmp); |
| 178 | } |
| 179 | } |
| 180 | } |
| 181 | |
| 182 | if (requireInfo() && !tmp.exists()) { |
| 183 | throw new IOException( |
| 184 | "file not supported (maybe not created with this program or corrupt)"); |
| 185 | } |
| 186 | |
| 187 | if (tmp.exists()) { |
| 188 | this.fakeIn = new MarkableFileInputStream(tmp); |
| 189 | } |
| 190 | |
| 191 | if (tmpInfo.exists()) { |
| 192 | meta = InfoReader.readMeta(tmpInfo, true); |
| 193 | tmpInfo.delete(); |
| 194 | } else { |
| 195 | if (title == null || title.isEmpty()) { |
| 196 | title = getSourceFileOriginal().getName(); |
| 197 | String exts[] = new String[] {".epub", ".cbz"}; |
| 198 | for (String ext : exts) { |
| 199 | if (title.toLowerCase().endsWith(ext)) { |
| 200 | title = title.substring(0, |
| 201 | title.length() - ext.length()); |
| 202 | } |
| 203 | } |
| 204 | title = URLDecoder.decode(title, "UTF-8").trim(); |
| 205 | } |
| 206 | |
| 207 | meta = new MetaData(); |
| 208 | meta.setLang("en"); |
| 209 | meta.setTags(Arrays.asList("[no_info]")); |
| 210 | meta.setSource(getType().getSourceName()); |
| 211 | meta.setUuid(url); |
| 212 | meta.setUrl(url); |
| 213 | meta.setTitle(title); |
| 214 | meta.setAuthor(author); |
| 215 | meta.setImageDocument(isImagesDocumentByDefault()); |
| 216 | |
| 217 | InfoReader.completeMeta(tmp, meta); |
| 218 | } |
| 219 | |
| 220 | if (meta.getCover() == null) { |
| 221 | if (cover != null) { |
| 222 | meta.setCover(cover); |
| 223 | } else { |
| 224 | meta.setCover(InfoReader.getCoverByName( |
| 225 | getSourceFileOriginal().toURI().toURL())); |
| 226 | } |
| 227 | } |
| 228 | } finally { |
| 229 | if (zipIn != null) { |
| 230 | zipIn.close(); |
| 231 | } |
| 232 | if (in != null) { |
| 233 | in.close(); |
| 234 | } |
| 235 | } |
| 236 | |
| 237 | return null; |
| 238 | } |
| 239 | |
| 240 | @Override |
| 241 | protected void close() { |
| 242 | if (tmpDir != null) { |
| 243 | IOUtils.deltree(tmpDir); |
| 244 | } |
| 245 | |
| 246 | tmpDir = null; |
| 247 | |
| 248 | super.close(); |
| 249 | } |
| 250 | |
| 251 | protected String getDataPrefix() { |
| 252 | return "DATA/"; |
| 253 | } |
| 254 | |
| 255 | protected boolean requireInfo() { |
| 256 | return true; |
| 257 | } |
| 258 | |
| 259 | protected boolean getCover() { |
| 260 | return true; |
| 261 | } |
| 262 | |
| 263 | protected boolean isImagesDocumentByDefault() { |
| 264 | return false; |
| 265 | } |
| 266 | } |