| 1 | package be.nikiroo.utils; |
| 2 | |
| 3 | import java.io.ByteArrayInputStream; |
| 4 | import java.io.IOException; |
| 5 | import java.io.InputStream; |
| 6 | import java.io.OutputStream; |
| 7 | import java.io.UnsupportedEncodingException; |
| 8 | import java.security.MessageDigest; |
| 9 | import java.security.NoSuchAlgorithmException; |
| 10 | import java.text.Normalizer; |
| 11 | import java.text.Normalizer.Form; |
| 12 | import java.text.ParseException; |
| 13 | import java.text.SimpleDateFormat; |
| 14 | import java.util.AbstractMap; |
| 15 | import java.util.ArrayList; |
| 16 | import java.util.Date; |
| 17 | import java.util.List; |
| 18 | import java.util.Map.Entry; |
| 19 | import java.util.Scanner; |
| 20 | import java.util.regex.Pattern; |
| 21 | |
| 22 | import org.unbescape.html.HtmlEscape; |
| 23 | import org.unbescape.html.HtmlEscapeLevel; |
| 24 | import org.unbescape.html.HtmlEscapeType; |
| 25 | |
| 26 | /** |
| 27 | * This class offer some utilities based around {@link String}s. |
| 28 | * |
| 29 | * @author niki |
| 30 | */ |
| 31 | public class StringUtils { |
| 32 | /** |
| 33 | * This enum type will decide the alignment of a {@link String} when padding |
| 34 | * or justification is applied (if there is enough horizontal space for it |
| 35 | * to be aligned). |
| 36 | */ |
| 37 | public enum Alignment { |
| 38 | /** Aligned at left. */ |
| 39 | LEFT, |
| 40 | /** Centered. */ |
| 41 | CENTER, |
| 42 | /** Aligned at right. */ |
| 43 | RIGHT, |
| 44 | /** Full justified (to both left and right). */ |
| 45 | JUSTIFY, |
| 46 | |
| 47 | // Old Deprecated values: |
| 48 | |
| 49 | /** DEPRECATED: please use LEFT. */ |
| 50 | @Deprecated |
| 51 | Beginning, |
| 52 | /** DEPRECATED: please use CENTER. */ |
| 53 | @Deprecated |
| 54 | Center, |
| 55 | /** DEPRECATED: please use RIGHT. */ |
| 56 | @Deprecated |
| 57 | End; |
| 58 | |
| 59 | /** |
| 60 | * Return the non-deprecated version of this enum if needed (or return |
| 61 | * self if not). |
| 62 | * |
| 63 | * @return the non-deprecated value |
| 64 | */ |
| 65 | Alignment undeprecate() { |
| 66 | if (this == Beginning) |
| 67 | return LEFT; |
| 68 | if (this == Center) |
| 69 | return CENTER; |
| 70 | if (this == End) |
| 71 | return RIGHT; |
| 72 | return this; |
| 73 | } |
| 74 | } |
| 75 | |
| 76 | static private Pattern marks = getMarks(); |
| 77 | |
| 78 | /** |
| 79 | * Fix the size of the given {@link String} either with space-padding or by |
| 80 | * shortening it. |
| 81 | * |
| 82 | * @param text |
| 83 | * the {@link String} to fix |
| 84 | * @param width |
| 85 | * the size of the resulting {@link String} or -1 for a noop |
| 86 | * |
| 87 | * @return the resulting {@link String} of size <i>size</i> |
| 88 | */ |
| 89 | static public String padString(String text, int width) { |
| 90 | return padString(text, width, true, null); |
| 91 | } |
| 92 | |
| 93 | /** |
| 94 | * Fix the size of the given {@link String} either with space-padding or by |
| 95 | * optionally shortening it. |
| 96 | * |
| 97 | * @param text |
| 98 | * the {@link String} to fix |
| 99 | * @param width |
| 100 | * the size of the resulting {@link String} if the text fits or |
| 101 | * if cut is TRUE or -1 for a noop |
| 102 | * @param cut |
| 103 | * cut the {@link String} shorter if needed |
| 104 | * @param align |
| 105 | * align the {@link String} in this position if we have enough |
| 106 | * space (default is Alignment.Beginning) |
| 107 | * |
| 108 | * @return the resulting {@link String} of size <i>size</i> minimum |
| 109 | */ |
| 110 | static public String padString(String text, int width, boolean cut, |
| 111 | Alignment align) { |
| 112 | |
| 113 | if (align == null) { |
| 114 | align = Alignment.LEFT; |
| 115 | } |
| 116 | |
| 117 | align = align.undeprecate(); |
| 118 | |
| 119 | if (width >= 0) { |
| 120 | if (text == null) |
| 121 | text = ""; |
| 122 | |
| 123 | int diff = width - text.length(); |
| 124 | |
| 125 | if (diff < 0) { |
| 126 | if (cut) |
| 127 | text = text.substring(0, width); |
| 128 | } else if (diff > 0) { |
| 129 | if (diff < 2 && align != Alignment.RIGHT) |
| 130 | align = Alignment.LEFT; |
| 131 | |
| 132 | switch (align) { |
| 133 | case RIGHT: |
| 134 | text = new String(new char[diff]).replace('\0', ' ') + text; |
| 135 | break; |
| 136 | case CENTER: |
| 137 | int pad1 = (diff) / 2; |
| 138 | int pad2 = (diff + 1) / 2; |
| 139 | text = new String(new char[pad1]).replace('\0', ' ') + text |
| 140 | + new String(new char[pad2]).replace('\0', ' '); |
| 141 | break; |
| 142 | case LEFT: |
| 143 | default: |
| 144 | text = text + new String(new char[diff]).replace('\0', ' '); |
| 145 | break; |
| 146 | } |
| 147 | } |
| 148 | } |
| 149 | |
| 150 | return text; |
| 151 | } |
| 152 | |
| 153 | /** |
| 154 | * Justify a text into width-sized (at the maximum) lines. |
| 155 | * |
| 156 | * @param text |
| 157 | * the {@link String} to justify |
| 158 | * @param width |
| 159 | * the maximum size of the resulting lines |
| 160 | * |
| 161 | * @return a list of justified text lines |
| 162 | */ |
| 163 | static public List<String> justifyText(String text, int width) { |
| 164 | return justifyText(text, width, null); |
| 165 | } |
| 166 | |
| 167 | /** |
| 168 | * Justify a text into width-sized (at the maximum) lines. |
| 169 | * |
| 170 | * @param text |
| 171 | * the {@link String} to justify |
| 172 | * @param width |
| 173 | * the maximum size of the resulting lines |
| 174 | * @param align |
| 175 | * align the lines in this position (default is |
| 176 | * Alignment.Beginning) |
| 177 | * |
| 178 | * @return a list of justified text lines |
| 179 | */ |
| 180 | static public List<String> justifyText(String text, int width, |
| 181 | Alignment align) { |
| 182 | if (align == null) { |
| 183 | align = Alignment.LEFT; |
| 184 | } |
| 185 | |
| 186 | align = align.undeprecate(); |
| 187 | |
| 188 | switch (align) { |
| 189 | case CENTER: |
| 190 | return StringJustifier.center(text, width); |
| 191 | case RIGHT: |
| 192 | return StringJustifier.right(text, width); |
| 193 | case JUSTIFY: |
| 194 | return StringJustifier.full(text, width); |
| 195 | case LEFT: |
| 196 | default: |
| 197 | return StringJustifier.left(text, width); |
| 198 | } |
| 199 | } |
| 200 | |
| 201 | /** |
| 202 | * Justify a text into width-sized (at the maximum) lines. |
| 203 | * |
| 204 | * @param text |
| 205 | * the {@link String} to justify |
| 206 | * @param width |
| 207 | * the maximum size of the resulting lines |
| 208 | * |
| 209 | * @return a list of justified text lines |
| 210 | */ |
| 211 | static public List<String> justifyText(List<String> text, int width) { |
| 212 | return justifyText(text, width, null); |
| 213 | } |
| 214 | |
| 215 | /** |
| 216 | * Justify a text into width-sized (at the maximum) lines. |
| 217 | * |
| 218 | * @param text |
| 219 | * the {@link String} to justify |
| 220 | * @param width |
| 221 | * the maximum size of the resulting lines |
| 222 | * @param align |
| 223 | * align the lines in this position (default is |
| 224 | * Alignment.Beginning) |
| 225 | * |
| 226 | * @return a list of justified text lines |
| 227 | */ |
| 228 | static public List<String> justifyText(List<String> text, int width, |
| 229 | Alignment align) { |
| 230 | List<String> result = new ArrayList<String>(); |
| 231 | |
| 232 | // Content <-> Bullet spacing (null = no spacing) |
| 233 | List<Entry<String, String>> lines = new ArrayList<Entry<String, String>>(); |
| 234 | StringBuilder previous = null; |
| 235 | StringBuilder tmp = new StringBuilder(); |
| 236 | String previousItemBulletSpacing = null; |
| 237 | String itemBulletSpacing = null; |
| 238 | for (String inputLine : text) { |
| 239 | boolean previousLineComplete = true; |
| 240 | |
| 241 | String current = inputLine.replace("\t", " "); |
| 242 | itemBulletSpacing = getItemSpacing(current); |
| 243 | boolean bullet = isItemLine(current); |
| 244 | if ((previousItemBulletSpacing == null || itemBulletSpacing |
| 245 | .length() <= previousItemBulletSpacing.length()) && !bullet) { |
| 246 | itemBulletSpacing = null; |
| 247 | } |
| 248 | |
| 249 | if (itemBulletSpacing != null) { |
| 250 | current = current.trim(); |
| 251 | if (!current.isEmpty() && bullet) { |
| 252 | current = current.substring(1); |
| 253 | } |
| 254 | current = current.trim(); |
| 255 | previousLineComplete = bullet; |
| 256 | } else { |
| 257 | tmp.setLength(0); |
| 258 | for (String word : current.split(" ")) { |
| 259 | if (word.isEmpty()) { |
| 260 | continue; |
| 261 | } |
| 262 | |
| 263 | if (tmp.length() > 0) { |
| 264 | tmp.append(' '); |
| 265 | } |
| 266 | tmp.append(word.trim()); |
| 267 | } |
| 268 | current = tmp.toString(); |
| 269 | |
| 270 | previousLineComplete = current.isEmpty() |
| 271 | || previousItemBulletSpacing != null |
| 272 | || (previous != null && isFullLine(previous)) |
| 273 | || isHrLine(current) || isHrLine(previous); |
| 274 | } |
| 275 | |
| 276 | if (previous == null) { |
| 277 | previous = new StringBuilder(); |
| 278 | } else { |
| 279 | if (previousLineComplete) { |
| 280 | lines.add(new AbstractMap.SimpleEntry<String, String>( |
| 281 | previous.toString(), previousItemBulletSpacing)); |
| 282 | previous.setLength(0); |
| 283 | previousItemBulletSpacing = itemBulletSpacing; |
| 284 | } else { |
| 285 | previous.append(' '); |
| 286 | } |
| 287 | } |
| 288 | |
| 289 | previous.append(current); |
| 290 | |
| 291 | } |
| 292 | |
| 293 | if (previous != null) { |
| 294 | lines.add(new AbstractMap.SimpleEntry<String, String>(previous |
| 295 | .toString(), previousItemBulletSpacing)); |
| 296 | } |
| 297 | |
| 298 | for (Entry<String, String> line : lines) { |
| 299 | String content = line.getKey(); |
| 300 | String spacing = line.getValue(); |
| 301 | |
| 302 | String bullet = "- "; |
| 303 | if (spacing == null) { |
| 304 | bullet = ""; |
| 305 | spacing = ""; |
| 306 | } |
| 307 | |
| 308 | if (spacing.length() > width + 3) { |
| 309 | spacing = ""; |
| 310 | } |
| 311 | |
| 312 | for (String subline : StringUtils.justifyText(content, width |
| 313 | - (spacing.length() + bullet.length()), align)) { |
| 314 | result.add(spacing + bullet + subline); |
| 315 | if (!bullet.isEmpty()) { |
| 316 | bullet = " "; |
| 317 | } |
| 318 | } |
| 319 | } |
| 320 | |
| 321 | return result; |
| 322 | } |
| 323 | |
| 324 | /** |
| 325 | * Sanitise the given input to make it more Terminal-friendly by removing |
| 326 | * combining characters. |
| 327 | * |
| 328 | * @param input |
| 329 | * the input to sanitise |
| 330 | * @param allowUnicode |
| 331 | * allow Unicode or only allow ASCII Latin characters |
| 332 | * |
| 333 | * @return the sanitised {@link String} |
| 334 | */ |
| 335 | static public String sanitize(String input, boolean allowUnicode) { |
| 336 | return sanitize(input, allowUnicode, !allowUnicode); |
| 337 | } |
| 338 | |
| 339 | /** |
| 340 | * Sanitise the given input to make it more Terminal-friendly by removing |
| 341 | * combining characters. |
| 342 | * |
| 343 | * @param input |
| 344 | * the input to sanitise |
| 345 | * @param allowUnicode |
| 346 | * allow Unicode or only allow ASCII Latin characters |
| 347 | * @param removeAllAccents |
| 348 | * TRUE to replace all accentuated characters by their non |
| 349 | * accentuated counter-parts |
| 350 | * |
| 351 | * @return the sanitised {@link String} |
| 352 | */ |
| 353 | static public String sanitize(String input, boolean allowUnicode, |
| 354 | boolean removeAllAccents) { |
| 355 | |
| 356 | if (removeAllAccents) { |
| 357 | input = Normalizer.normalize(input, Form.NFKD); |
| 358 | if (marks != null) { |
| 359 | input = marks.matcher(input).replaceAll(""); |
| 360 | } |
| 361 | } |
| 362 | |
| 363 | input = Normalizer.normalize(input, Form.NFKC); |
| 364 | |
| 365 | if (!allowUnicode) { |
| 366 | StringBuilder builder = new StringBuilder(); |
| 367 | for (int index = 0; index < input.length(); index++) { |
| 368 | char car = input.charAt(index); |
| 369 | // displayable chars in ASCII are in the range 32<->255, |
| 370 | // except DEL (127) |
| 371 | if (car >= 32 && car <= 255 && car != 127) { |
| 372 | builder.append(car); |
| 373 | } |
| 374 | } |
| 375 | input = builder.toString(); |
| 376 | } |
| 377 | |
| 378 | return input; |
| 379 | } |
| 380 | |
| 381 | /** |
| 382 | * Convert between the time in milliseconds to a {@link String} in a "fixed" |
| 383 | * way (to exchange data over the wire, for instance). |
| 384 | * <p> |
| 385 | * Precise to the second. |
| 386 | * |
| 387 | * @param time |
| 388 | * the specified number of milliseconds since the standard base |
| 389 | * time known as "the epoch", namely January 1, 1970, 00:00:00 |
| 390 | * GMT |
| 391 | * |
| 392 | * @return the time as a {@link String} |
| 393 | */ |
| 394 | static public String fromTime(long time) { |
| 395 | SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); |
| 396 | return sdf.format(new Date(time)); |
| 397 | } |
| 398 | |
| 399 | /** |
| 400 | * Convert between the time as a {@link String} to milliseconds in a "fixed" |
| 401 | * way (to exchange data over the wire, for instance). |
| 402 | * <p> |
| 403 | * Precise to the second. |
| 404 | * |
| 405 | * @param displayTime |
| 406 | * the time as a {@link String} |
| 407 | * |
| 408 | * @return the number of milliseconds since the standard base time known as |
| 409 | * "the epoch", namely January 1, 1970, 00:00:00 GMT, or -1 in case |
| 410 | * of error |
| 411 | * |
| 412 | * @throws ParseException |
| 413 | * in case of parse error |
| 414 | */ |
| 415 | static public long toTime(String displayTime) throws ParseException { |
| 416 | SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); |
| 417 | return sdf.parse(displayTime).getTime(); |
| 418 | } |
| 419 | |
| 420 | /** |
| 421 | * Return a hash of the given {@link String}. |
| 422 | * |
| 423 | * @param input |
| 424 | * the input data |
| 425 | * |
| 426 | * @return the hash |
| 427 | */ |
| 428 | static public String getMd5Hash(String input) { |
| 429 | try { |
| 430 | MessageDigest md = MessageDigest.getInstance("MD5"); |
| 431 | md.update(input.getBytes("UTF-8")); |
| 432 | byte byteData[] = md.digest(); |
| 433 | |
| 434 | StringBuffer hexString = new StringBuffer(); |
| 435 | for (int i = 0; i < byteData.length; i++) { |
| 436 | String hex = Integer.toHexString(0xff & byteData[i]); |
| 437 | if (hex.length() == 1) |
| 438 | hexString.append('0'); |
| 439 | hexString.append(hex); |
| 440 | } |
| 441 | |
| 442 | return hexString.toString(); |
| 443 | } catch (NoSuchAlgorithmException e) { |
| 444 | return input; |
| 445 | } catch (UnsupportedEncodingException e) { |
| 446 | return input; |
| 447 | } |
| 448 | } |
| 449 | |
| 450 | /** |
| 451 | * Remove the HTML content from the given input, and un-html-ize the rest. |
| 452 | * |
| 453 | * @param html |
| 454 | * the HTML-encoded content |
| 455 | * |
| 456 | * @return the HTML-free equivalent content |
| 457 | */ |
| 458 | public static String unhtml(String html) { |
| 459 | StringBuilder builder = new StringBuilder(); |
| 460 | |
| 461 | int inTag = 0; |
| 462 | for (char car : html.toCharArray()) { |
| 463 | if (car == '<') { |
| 464 | inTag++; |
| 465 | } else if (car == '>') { |
| 466 | inTag--; |
| 467 | } else if (inTag <= 0) { |
| 468 | builder.append(car); |
| 469 | } |
| 470 | } |
| 471 | |
| 472 | char nbsp = ' '; // non-breakable space (a special char) |
| 473 | char space = ' '; |
| 474 | return HtmlEscape.unescapeHtml(builder.toString()).replace(nbsp, space); |
| 475 | } |
| 476 | |
| 477 | /** |
| 478 | * Escape the given {@link String} so it can be used in XML, as content. |
| 479 | * |
| 480 | * @param input |
| 481 | * the input {@link String} |
| 482 | * |
| 483 | * @return the escaped {@link String} |
| 484 | */ |
| 485 | public static String xmlEscape(String input) { |
| 486 | if (input == null) { |
| 487 | return ""; |
| 488 | } |
| 489 | |
| 490 | return HtmlEscape.escapeHtml(input, |
| 491 | HtmlEscapeType.HTML4_NAMED_REFERENCES_DEFAULT_TO_HEXA, |
| 492 | HtmlEscapeLevel.LEVEL_1_ONLY_MARKUP_SIGNIFICANT); |
| 493 | } |
| 494 | |
| 495 | /** |
| 496 | * Escape the given {@link String} so it can be used in XML, as text content |
| 497 | * inside double-quotes. |
| 498 | * |
| 499 | * @param input |
| 500 | * the input {@link String} |
| 501 | * |
| 502 | * @return the escaped {@link String} |
| 503 | */ |
| 504 | public static String xmlEscapeQuote(String input) { |
| 505 | if (input == null) { |
| 506 | return ""; |
| 507 | } |
| 508 | |
| 509 | return HtmlEscape.escapeHtml(input, |
| 510 | HtmlEscapeType.HTML4_NAMED_REFERENCES_DEFAULT_TO_HEXA, |
| 511 | HtmlEscapeLevel.LEVEL_1_ONLY_MARKUP_SIGNIFICANT); |
| 512 | } |
| 513 | |
| 514 | /** |
| 515 | * Zip the data and then encode it into Base64. |
| 516 | * |
| 517 | * @deprecated use {@link StringUtils#base64(byte[], boolean)} with the |
| 518 | * correct parameter instead |
| 519 | * |
| 520 | * @param data |
| 521 | * the data |
| 522 | * |
| 523 | * @return the Base64 zipped version |
| 524 | */ |
| 525 | @Deprecated |
| 526 | public static String zip64(String data) { |
| 527 | try { |
| 528 | return Base64.encodeBytes(data.getBytes("UTF-8"), Base64.GZIP); |
| 529 | } catch (IOException e) { |
| 530 | e.printStackTrace(); |
| 531 | return null; |
| 532 | } |
| 533 | } |
| 534 | |
| 535 | /** |
| 536 | * Unconvert from Base64 then unzip the content. |
| 537 | * |
| 538 | * @deprecated use {@link StringUtils#unbase64s(String, boolean)} with the |
| 539 | * correct parameter instead |
| 540 | * |
| 541 | * @param data |
| 542 | * the data in Base64 format |
| 543 | * |
| 544 | * @return the raw data |
| 545 | * |
| 546 | * @throws IOException |
| 547 | * in case of I/O error |
| 548 | */ |
| 549 | @Deprecated |
| 550 | public static String unzip64(String data) throws IOException { |
| 551 | ByteArrayInputStream in = new ByteArrayInputStream(Base64.decode(data, |
| 552 | Base64.GZIP)); |
| 553 | |
| 554 | Scanner scan = new Scanner(in); |
| 555 | scan.useDelimiter("\\A"); |
| 556 | try { |
| 557 | return scan.next(); |
| 558 | } finally { |
| 559 | scan.close(); |
| 560 | } |
| 561 | } |
| 562 | |
| 563 | /** |
| 564 | * Convert the given data to Base64 format. |
| 565 | * |
| 566 | * @param data |
| 567 | * the data to convert |
| 568 | * @param zip |
| 569 | * TRUE to also compress the data in GZIP format; remember that |
| 570 | * compressed and not-compressed content are different; you need |
| 571 | * to know which is which when decoding |
| 572 | * |
| 573 | * @return the Base64 {@link String} representation of the data |
| 574 | * |
| 575 | * @throws IOException |
| 576 | * in case of I/O errors |
| 577 | */ |
| 578 | public static String base64(String data, boolean zip) throws IOException { |
| 579 | return base64(data.getBytes("UTF-8"), zip); |
| 580 | } |
| 581 | |
| 582 | /** |
| 583 | * Convert the given data to Base64 format. |
| 584 | * |
| 585 | * @param data |
| 586 | * the data to convert |
| 587 | * @param zip |
| 588 | * TRUE to also compress the data in GZIP format; remember that |
| 589 | * compressed and not-compressed content are different; you need |
| 590 | * to know which is which when decoding |
| 591 | * |
| 592 | * @return the Base64 {@link String} representation of the data |
| 593 | * |
| 594 | * @throws IOException |
| 595 | * in case of I/O errors |
| 596 | */ |
| 597 | public static String base64(byte[] data, boolean zip) throws IOException { |
| 598 | return Base64.encodeBytes(data, zip ? Base64.GZIP : Base64.NO_OPTIONS); |
| 599 | } |
| 600 | |
| 601 | /** |
| 602 | * Convert the given data to Base64 format. |
| 603 | * |
| 604 | * @param data |
| 605 | * the data to convert |
| 606 | * @param zip |
| 607 | * TRUE to also uncompress the data from a GZIP format; take care |
| 608 | * about this flag, as it could easily cause errors in the |
| 609 | * returned content or an {@link IOException} |
| 610 | * @param breakLines |
| 611 | * TRUE to break lines on every 76th character |
| 612 | * |
| 613 | * @return the Base64 {@link String} representation of the data |
| 614 | * |
| 615 | * @throws IOException |
| 616 | * in case of I/O errors |
| 617 | */ |
| 618 | public static OutputStream base64(OutputStream data, boolean zip, |
| 619 | boolean breakLines) throws IOException { |
| 620 | OutputStream out = new Base64.OutputStream(data, |
| 621 | breakLines ? Base64.DO_BREAK_LINES & Base64.ENCODE |
| 622 | : Base64.ENCODE); |
| 623 | |
| 624 | if (zip) { |
| 625 | out = new java.util.zip.GZIPOutputStream(out); |
| 626 | } |
| 627 | |
| 628 | return out; |
| 629 | } |
| 630 | |
| 631 | /** |
| 632 | * Convert the given data to Base64 format. |
| 633 | * |
| 634 | * @param data |
| 635 | * the data to convert |
| 636 | * @param zip |
| 637 | * TRUE to also uncompress the data from a GZIP format; take care |
| 638 | * about this flag, as it could easily cause errors in the |
| 639 | * returned content or an {@link IOException} |
| 640 | * @param breakLines |
| 641 | * TRUE to break lines on every 76th character |
| 642 | * |
| 643 | * @return the Base64 {@link String} representation of the data |
| 644 | * |
| 645 | * @throws IOException |
| 646 | * in case of I/O errors |
| 647 | */ |
| 648 | public static InputStream base64(InputStream data, boolean zip, |
| 649 | boolean breakLines) throws IOException { |
| 650 | if (zip) { |
| 651 | data = new java.util.zip.GZIPInputStream(data); |
| 652 | } |
| 653 | |
| 654 | return new Base64.InputStream(data, breakLines ? Base64.DO_BREAK_LINES |
| 655 | & Base64.ENCODE : Base64.ENCODE); |
| 656 | } |
| 657 | |
| 658 | /** |
| 659 | * Unconvert the given data from Base64 format back to a raw array of bytes. |
| 660 | * |
| 661 | * @param data |
| 662 | * the data to unconvert |
| 663 | * @param zip |
| 664 | * TRUE to also uncompress the data from a GZIP format; take care |
| 665 | * about this flag, as it could easily cause errors in the |
| 666 | * returned content or an {@link IOException} |
| 667 | * |
| 668 | * @return the raw data represented by the given Base64 {@link String}, |
| 669 | * optionally compressed with GZIP |
| 670 | * |
| 671 | * @throws IOException |
| 672 | * in case of I/O errors |
| 673 | */ |
| 674 | public static byte[] unbase64(String data, boolean zip) throws IOException { |
| 675 | return Base64.decode(data, zip ? Base64.GZIP : Base64.NO_OPTIONS); |
| 676 | } |
| 677 | |
| 678 | /** |
| 679 | * Unconvert the given data from Base64 format back to a raw array of bytes. |
| 680 | * |
| 681 | * @param data |
| 682 | * the data to unconvert |
| 683 | * @param zip |
| 684 | * TRUE to also uncompress the data from a GZIP format; take care |
| 685 | * about this flag, as it could easily cause errors in the |
| 686 | * returned content or an {@link IOException} |
| 687 | * @param breakLines |
| 688 | * TRUE to break lines on every 76th character |
| 689 | * |
| 690 | * @return the raw data represented by the given Base64 {@link String} |
| 691 | * |
| 692 | * @throws IOException |
| 693 | * in case of I/O errors |
| 694 | */ |
| 695 | public static OutputStream unbase64(OutputStream data, boolean zip, |
| 696 | boolean breakLines) throws IOException { |
| 697 | OutputStream out = new Base64.OutputStream(data, |
| 698 | breakLines ? Base64.DO_BREAK_LINES & Base64.ENCODE |
| 699 | : Base64.ENCODE); |
| 700 | |
| 701 | if (zip) { |
| 702 | out = new java.util.zip.GZIPOutputStream(out); |
| 703 | } |
| 704 | |
| 705 | return out; |
| 706 | } |
| 707 | |
| 708 | /** |
| 709 | * Unconvert the given data from Base64 format back to a raw array of bytes. |
| 710 | * |
| 711 | * @param data |
| 712 | * the data to unconvert |
| 713 | * @param zip |
| 714 | * TRUE to also uncompress the data from a GZIP format; take care |
| 715 | * about this flag, as it could easily cause errors in the |
| 716 | * returned content or an {@link IOException} |
| 717 | * @param breakLines |
| 718 | * TRUE to break lines on every 76th character |
| 719 | * |
| 720 | * @return the raw data represented by the given Base64 {@link String} |
| 721 | * |
| 722 | * @throws IOException |
| 723 | * in case of I/O errors |
| 724 | */ |
| 725 | public static InputStream unbase64(InputStream data, boolean zip, |
| 726 | boolean breakLines) throws IOException { |
| 727 | if (zip) { |
| 728 | data = new java.util.zip.GZIPInputStream(data); |
| 729 | } |
| 730 | |
| 731 | return new Base64.InputStream(data, breakLines ? Base64.DO_BREAK_LINES |
| 732 | & Base64.ENCODE : Base64.ENCODE); |
| 733 | } |
| 734 | |
| 735 | /** |
| 736 | * Unonvert the given data from Base64 format back to a {@link String}. |
| 737 | * |
| 738 | * @param data |
| 739 | * the data to unconvert |
| 740 | * @param zip |
| 741 | * TRUE to also uncompress the data from a GZIP format; take care |
| 742 | * about this flag, as it could easily cause errors in the |
| 743 | * returned content or an {@link IOException} |
| 744 | * |
| 745 | * @return the {@link String} represented by the given Base64 {@link String} |
| 746 | * , optionally compressed with GZIP |
| 747 | * |
| 748 | * @throws IOException |
| 749 | * in case of I/O errors |
| 750 | */ |
| 751 | public static String unbase64s(String data, boolean zip) throws IOException { |
| 752 | ByteArrayInputStream in = new ByteArrayInputStream(unbase64(data, zip)); |
| 753 | |
| 754 | Scanner scan = new Scanner(in, "UTF-8"); |
| 755 | scan.useDelimiter("\\A"); |
| 756 | try { |
| 757 | return scan.next(); |
| 758 | } finally { |
| 759 | scan.close(); |
| 760 | } |
| 761 | } |
| 762 | |
| 763 | /** |
| 764 | * The "remove accents" pattern. |
| 765 | * |
| 766 | * @return the pattern, or NULL if a problem happens |
| 767 | */ |
| 768 | private static Pattern getMarks() { |
| 769 | try { |
| 770 | return Pattern |
| 771 | .compile("[\\p{InCombiningDiacriticalMarks}\\p{IsLm}\\p{IsSk}]+"); |
| 772 | } catch (Exception e) { |
| 773 | // Can fail on Android... |
| 774 | return null; |
| 775 | } |
| 776 | } |
| 777 | |
| 778 | // |
| 779 | // justify List<String> related: |
| 780 | // |
| 781 | |
| 782 | /** |
| 783 | * Check if this line ends as a complete line (ends with a "." or similar). |
| 784 | * <p> |
| 785 | * Note that we consider an empty line as full, and a line ending with |
| 786 | * spaces as not complete. |
| 787 | * |
| 788 | * @param line |
| 789 | * the line to check |
| 790 | * |
| 791 | * @return TRUE if it does |
| 792 | */ |
| 793 | static private boolean isFullLine(StringBuilder line) { |
| 794 | if (line.length() == 0) { |
| 795 | return true; |
| 796 | } |
| 797 | |
| 798 | char lastCar = line.charAt(line.length() - 1); |
| 799 | switch (lastCar) { |
| 800 | case '.': // points |
| 801 | case '?': |
| 802 | case '!': |
| 803 | |
| 804 | case '\'': // quotes |
| 805 | case '‘': |
| 806 | case '’': |
| 807 | |
| 808 | case '"': // double quotes |
| 809 | case '”': |
| 810 | case '“': |
| 811 | case '»': |
| 812 | case '«': |
| 813 | return true; |
| 814 | default: |
| 815 | return false; |
| 816 | } |
| 817 | } |
| 818 | |
| 819 | /** |
| 820 | * Check if this line represent an item in a list or description (i.e., |
| 821 | * check that the first non-space char is "-"). |
| 822 | * |
| 823 | * @param line |
| 824 | * the line to check |
| 825 | * |
| 826 | * @return TRUE if it is |
| 827 | */ |
| 828 | static private boolean isItemLine(String line) { |
| 829 | String spacing = getItemSpacing(line); |
| 830 | return spacing != null && !spacing.isEmpty() |
| 831 | && line.charAt(spacing.length()) == '-'; |
| 832 | } |
| 833 | |
| 834 | /** |
| 835 | * Return all the spaces that start this line (or Empty if none). |
| 836 | * |
| 837 | * @param line |
| 838 | * the line to get the starting spaces from |
| 839 | * |
| 840 | * @return the left spacing |
| 841 | */ |
| 842 | static private String getItemSpacing(String line) { |
| 843 | int i; |
| 844 | for (i = 0; i < line.length(); i++) { |
| 845 | if (line.charAt(i) != ' ') { |
| 846 | return line.substring(0, i); |
| 847 | } |
| 848 | } |
| 849 | |
| 850 | return ""; |
| 851 | } |
| 852 | |
| 853 | /** |
| 854 | * This line is an horizontal spacer line. |
| 855 | * |
| 856 | * @param line |
| 857 | * the line to test |
| 858 | * |
| 859 | * @return TRUE if it is |
| 860 | */ |
| 861 | static private boolean isHrLine(CharSequence line) { |
| 862 | int count = 0; |
| 863 | if (line != null) { |
| 864 | for (int i = 0; i < line.length(); i++) { |
| 865 | char car = line.charAt(i); |
| 866 | if (car == ' ' || car == '\t' || car == '*' || car == '-' |
| 867 | || car == '_' || car == '~' || car == '=' || car == '/' |
| 868 | || car == '\\') { |
| 869 | count++; |
| 870 | } else { |
| 871 | return false; |
| 872 | } |
| 873 | } |
| 874 | } |
| 875 | |
| 876 | return count > 2; |
| 877 | } |
| 878 | } |