add Proxy and UIUtils in Test to include the class files
[nikiroo-utils.git] / src / be / nikiroo / utils / StringUtils.java
CommitLineData
ec1f3444
NR
1package be.nikiroo.utils;
2
a6a73de3
NR
3import java.io.ByteArrayInputStream;
4import java.io.ByteArrayOutputStream;
ec1f3444 5import java.io.IOException;
a359464f
NR
6import java.io.InputStream;
7import java.io.OutputStream;
3f8349b7 8import java.io.UnsupportedEncodingException;
ec1f3444
NR
9import java.security.MessageDigest;
10import java.security.NoSuchAlgorithmException;
11import java.text.Normalizer;
12import java.text.Normalizer.Form;
13import java.text.ParseException;
14import java.text.SimpleDateFormat;
dc22eb95
NR
15import java.util.AbstractMap;
16import java.util.ArrayList;
5221cf7f 17import java.util.Arrays;
ec1f3444 18import java.util.Date;
cc3e7291 19import java.util.List;
dc22eb95 20import java.util.Map.Entry;
ec1f3444 21import java.util.regex.Pattern;
a6a73de3
NR
22import java.util.zip.GZIPInputStream;
23import java.util.zip.GZIPOutputStream;
ec1f3444 24
ec1f3444
NR
25import org.unbescape.html.HtmlEscape;
26import org.unbescape.html.HtmlEscapeLevel;
27import org.unbescape.html.HtmlEscapeType;
28
f28a134e 29import be.nikiroo.utils.streams.Base64InputStream;
5221cf7f 30import be.nikiroo.utils.streams.Base64OutputStream;
f28a134e 31
ec1f3444
NR
32/**
33 * This class offer some utilities based around {@link String}s.
34 *
35 * @author niki
36 */
37public class StringUtils {
38 /**
39 * This enum type will decide the alignment of a {@link String} when padding
cc3e7291
NR
40 * or justification is applied (if there is enough horizontal space for it
41 * to be aligned).
ec1f3444
NR
42 */
43 public enum Alignment {
44 /** Aligned at left. */
cc3e7291 45 LEFT,
ec1f3444 46 /** Centered. */
cc3e7291 47 CENTER,
ec1f3444 48 /** Aligned at right. */
cc3e7291
NR
49 RIGHT,
50 /** Full justified (to both left and right). */
51 JUSTIFY,
52
53 // Old Deprecated values:
54
55 /** DEPRECATED: please use LEFT. */
56 @Deprecated
57 Beginning,
58 /** DEPRECATED: please use CENTER. */
59 @Deprecated
60 Center,
61 /** DEPRECATED: please use RIGHT. */
62 @Deprecated
63 End;
64
65 /**
66 * Return the non-deprecated version of this enum if needed (or return
67 * self if not).
68 *
69 * @return the non-deprecated value
70 */
71 Alignment undeprecate() {
72 if (this == Beginning)
73 return LEFT;
74 if (this == Center)
75 return CENTER;
76 if (this == End)
77 return RIGHT;
78 return this;
79 }
ec1f3444
NR
80 }
81
e8aa5bf9 82 static private Pattern marks = getMarks();
ec1f3444
NR
83
84 /**
85 * Fix the size of the given {@link String} either with space-padding or by
86 * shortening it.
87 *
88 * @param text
89 * the {@link String} to fix
90 * @param width
91 * the size of the resulting {@link String} or -1 for a noop
92 *
93 * @return the resulting {@link String} of size <i>size</i>
94 */
95 static public String padString(String text, int width) {
451f434b 96 return padString(text, width, true, null);
ec1f3444
NR
97 }
98
99 /**
100 * Fix the size of the given {@link String} either with space-padding or by
101 * optionally shortening it.
102 *
103 * @param text
104 * the {@link String} to fix
105 * @param width
106 * the size of the resulting {@link String} if the text fits or
107 * if cut is TRUE or -1 for a noop
108 * @param cut
109 * cut the {@link String} shorter if needed
110 * @param align
111 * align the {@link String} in this position if we have enough
451f434b 112 * space (default is Alignment.Beginning)
ec1f3444
NR
113 *
114 * @return the resulting {@link String} of size <i>size</i> minimum
115 */
116 static public String padString(String text, int width, boolean cut,
117 Alignment align) {
118
451f434b 119 if (align == null) {
cc3e7291 120 align = Alignment.LEFT;
451f434b
NR
121 }
122
cc3e7291
NR
123 align = align.undeprecate();
124
ec1f3444
NR
125 if (width >= 0) {
126 if (text == null)
127 text = "";
128
129 int diff = width - text.length();
130
131 if (diff < 0) {
132 if (cut)
133 text = text.substring(0, width);
134 } else if (diff > 0) {
cc3e7291
NR
135 if (diff < 2 && align != Alignment.RIGHT)
136 align = Alignment.LEFT;
ec1f3444
NR
137
138 switch (align) {
cc3e7291 139 case RIGHT:
ec1f3444
NR
140 text = new String(new char[diff]).replace('\0', ' ') + text;
141 break;
cc3e7291 142 case CENTER:
ec1f3444
NR
143 int pad1 = (diff) / 2;
144 int pad2 = (diff + 1) / 2;
145 text = new String(new char[pad1]).replace('\0', ' ') + text
146 + new String(new char[pad2]).replace('\0', ' ');
147 break;
cc3e7291
NR
148 case LEFT:
149 default:
150 text = text + new String(new char[diff]).replace('\0', ' ');
151 break;
ec1f3444
NR
152 }
153 }
154 }
155
156 return text;
157 }
158
cc3e7291
NR
159 /**
160 * Justify a text into width-sized (at the maximum) lines.
161 *
162 * @param text
163 * the {@link String} to justify
164 * @param width
165 * the maximum size of the resulting lines
166 *
167 * @return a list of justified text lines
168 */
169 static public List<String> justifyText(String text, int width) {
170 return justifyText(text, width, null);
171 }
172
173 /**
174 * Justify a text into width-sized (at the maximum) lines.
175 *
176 * @param text
177 * the {@link String} to justify
178 * @param width
179 * the maximum size of the resulting lines
180 * @param align
181 * align the lines in this position (default is
182 * Alignment.Beginning)
183 *
184 * @return a list of justified text lines
185 */
186 static public List<String> justifyText(String text, int width,
187 Alignment align) {
188 if (align == null) {
189 align = Alignment.LEFT;
190 }
191
192 align = align.undeprecate();
193
194 switch (align) {
195 case CENTER:
196 return StringJustifier.center(text, width);
197 case RIGHT:
198 return StringJustifier.right(text, width);
199 case JUSTIFY:
200 return StringJustifier.full(text, width);
201 case LEFT:
202 default:
203 return StringJustifier.left(text, width);
204 }
205 }
206
dc22eb95
NR
207 /**
208 * Justify a text into width-sized (at the maximum) lines.
209 *
210 * @param text
211 * the {@link String} to justify
212 * @param width
213 * the maximum size of the resulting lines
214 *
215 * @return a list of justified text lines
216 */
217 static public List<String> justifyText(List<String> text, int width) {
218 return justifyText(text, width, null);
219 }
220
221 /**
222 * Justify a text into width-sized (at the maximum) lines.
223 *
224 * @param text
225 * the {@link String} to justify
226 * @param width
227 * the maximum size of the resulting lines
228 * @param align
229 * align the lines in this position (default is
230 * Alignment.Beginning)
231 *
232 * @return a list of justified text lines
233 */
234 static public List<String> justifyText(List<String> text, int width,
235 Alignment align) {
236 List<String> result = new ArrayList<String>();
237
238 // Content <-> Bullet spacing (null = no spacing)
239 List<Entry<String, String>> lines = new ArrayList<Entry<String, String>>();
240 StringBuilder previous = null;
241 StringBuilder tmp = new StringBuilder();
242 String previousItemBulletSpacing = null;
243 String itemBulletSpacing = null;
244 for (String inputLine : text) {
245 boolean previousLineComplete = true;
246
247 String current = inputLine.replace("\t", " ");
248 itemBulletSpacing = getItemSpacing(current);
249 boolean bullet = isItemLine(current);
250 if ((previousItemBulletSpacing == null || itemBulletSpacing
251 .length() <= previousItemBulletSpacing.length()) && !bullet) {
252 itemBulletSpacing = null;
253 }
254
255 if (itemBulletSpacing != null) {
256 current = current.trim();
257 if (!current.isEmpty() && bullet) {
258 current = current.substring(1);
259 }
260 current = current.trim();
261 previousLineComplete = bullet;
262 } else {
263 tmp.setLength(0);
264 for (String word : current.split(" ")) {
265 if (word.isEmpty()) {
266 continue;
267 }
268
269 if (tmp.length() > 0) {
270 tmp.append(' ');
271 }
272 tmp.append(word.trim());
273 }
274 current = tmp.toString();
275
276 previousLineComplete = current.isEmpty()
277 || previousItemBulletSpacing != null
c0c091af
NR
278 || (previous != null && isFullLine(previous))
279 || isHrLine(current) || isHrLine(previous);
dc22eb95
NR
280 }
281
282 if (previous == null) {
283 previous = new StringBuilder();
284 } else {
285 if (previousLineComplete) {
286 lines.add(new AbstractMap.SimpleEntry<String, String>(
287 previous.toString(), previousItemBulletSpacing));
288 previous.setLength(0);
289 previousItemBulletSpacing = itemBulletSpacing;
290 } else {
291 previous.append(' ');
292 }
293 }
294
295 previous.append(current);
296
297 }
298
299 if (previous != null) {
300 lines.add(new AbstractMap.SimpleEntry<String, String>(previous
301 .toString(), previousItemBulletSpacing));
302 }
303
304 for (Entry<String, String> line : lines) {
305 String content = line.getKey();
306 String spacing = line.getValue();
307
308 String bullet = "- ";
309 if (spacing == null) {
310 bullet = "";
311 spacing = "";
312 }
313
314 if (spacing.length() > width + 3) {
315 spacing = "";
316 }
317
318 for (String subline : StringUtils.justifyText(content, width
319 - (spacing.length() + bullet.length()), align)) {
320 result.add(spacing + bullet + subline);
321 if (!bullet.isEmpty()) {
322 bullet = " ";
323 }
324 }
325 }
326
327 return result;
328 }
329
ec1f3444
NR
330 /**
331 * Sanitise the given input to make it more Terminal-friendly by removing
332 * combining characters.
333 *
334 * @param input
335 * the input to sanitise
336 * @param allowUnicode
337 * allow Unicode or only allow ASCII Latin characters
338 *
339 * @return the sanitised {@link String}
340 */
341 static public String sanitize(String input, boolean allowUnicode) {
342 return sanitize(input, allowUnicode, !allowUnicode);
343 }
344
345 /**
346 * Sanitise the given input to make it more Terminal-friendly by removing
347 * combining characters.
348 *
349 * @param input
350 * the input to sanitise
351 * @param allowUnicode
352 * allow Unicode or only allow ASCII Latin characters
353 * @param removeAllAccents
354 * TRUE to replace all accentuated characters by their non
355 * accentuated counter-parts
356 *
357 * @return the sanitised {@link String}
358 */
359 static public String sanitize(String input, boolean allowUnicode,
360 boolean removeAllAccents) {
361
362 if (removeAllAccents) {
363 input = Normalizer.normalize(input, Form.NFKD);
e8aa5bf9
NR
364 if (marks != null) {
365 input = marks.matcher(input).replaceAll("");
366 }
ec1f3444
NR
367 }
368
369 input = Normalizer.normalize(input, Form.NFKC);
370
371 if (!allowUnicode) {
372 StringBuilder builder = new StringBuilder();
373 for (int index = 0; index < input.length(); index++) {
374 char car = input.charAt(index);
375 // displayable chars in ASCII are in the range 32<->255,
376 // except DEL (127)
377 if (car >= 32 && car <= 255 && car != 127) {
378 builder.append(car);
379 }
380 }
381 input = builder.toString();
382 }
383
384 return input;
385 }
386
387 /**
451f434b
NR
388 * Convert between the time in milliseconds to a {@link String} in a "fixed"
389 * way (to exchange data over the wire, for instance).
390 * <p>
391 * Precise to the second.
ec1f3444
NR
392 *
393 * @param time
451f434b
NR
394 * the specified number of milliseconds since the standard base
395 * time known as "the epoch", namely January 1, 1970, 00:00:00
396 * GMT
ec1f3444
NR
397 *
398 * @return the time as a {@link String}
399 */
400 static public String fromTime(long time) {
401 SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
402 return sdf.format(new Date(time));
403 }
404
405 /**
451f434b 406 * Convert between the time as a {@link String} to milliseconds in a "fixed"
ec1f3444 407 * way (to exchange data over the wire, for instance).
451f434b
NR
408 * <p>
409 * Precise to the second.
ec1f3444 410 *
db31c358 411 * @param displayTime
ec1f3444
NR
412 * the time as a {@link String}
413 *
451f434b 414 * @return the number of milliseconds since the standard base time known as
e8aa5bf9
NR
415 * "the epoch", namely January 1, 1970, 00:00:00 GMT, or -1 in case
416 * of error
417 *
418 * @throws ParseException
419 * in case of parse error
ec1f3444 420 */
e8aa5bf9 421 static public long toTime(String displayTime) throws ParseException {
ec1f3444 422 SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
e8aa5bf9 423 return sdf.parse(displayTime).getTime();
ec1f3444
NR
424 }
425
ec1f3444
NR
426 /**
427 * Return a hash of the given {@link String}.
428 *
429 * @param input
430 * the input data
431 *
432 * @return the hash
433 */
b771aed5 434 static public String getMd5Hash(String input) {
ec1f3444
NR
435 try {
436 MessageDigest md = MessageDigest.getInstance("MD5");
f8147a0e 437 md.update(getBytes(input));
ec1f3444
NR
438 byte byteData[] = md.digest();
439
440 StringBuffer hexString = new StringBuffer();
441 for (int i = 0; i < byteData.length; i++) {
442 String hex = Integer.toHexString(0xff & byteData[i]);
443 if (hex.length() == 1)
444 hexString.append('0');
445 hexString.append(hex);
446 }
447
448 return hexString.toString();
449 } catch (NoSuchAlgorithmException e) {
450 return input;
451 }
452 }
453
ec1f3444
NR
454 /**
455 * Remove the HTML content from the given input, and un-html-ize the rest.
456 *
457 * @param html
458 * the HTML-encoded content
459 *
460 * @return the HTML-free equivalent content
461 */
462 public static String unhtml(String html) {
463 StringBuilder builder = new StringBuilder();
464
465 int inTag = 0;
466 for (char car : html.toCharArray()) {
467 if (car == '<') {
468 inTag++;
469 } else if (car == '>') {
470 inTag--;
471 } else if (inTag <= 0) {
472 builder.append(car);
473 }
474 }
475
7ee9568b
NR
476 char nbsp = ' '; // non-breakable space (a special char)
477 char space = ' ';
478 return HtmlEscape.unescapeHtml(builder.toString()).replace(nbsp, space);
ec1f3444
NR
479 }
480
481 /**
482 * Escape the given {@link String} so it can be used in XML, as content.
483 *
484 * @param input
485 * the input {@link String}
486 *
487 * @return the escaped {@link String}
488 */
489 public static String xmlEscape(String input) {
490 if (input == null) {
491 return "";
492 }
493
494 return HtmlEscape.escapeHtml(input,
495 HtmlEscapeType.HTML4_NAMED_REFERENCES_DEFAULT_TO_HEXA,
496 HtmlEscapeLevel.LEVEL_1_ONLY_MARKUP_SIGNIFICANT);
497 }
498
499 /**
500 * Escape the given {@link String} so it can be used in XML, as text content
501 * inside double-quotes.
502 *
503 * @param input
504 * the input {@link String}
505 *
506 * @return the escaped {@link String}
507 */
508 public static String xmlEscapeQuote(String input) {
509 if (input == null) {
510 return "";
511 }
512
513 return HtmlEscape.escapeHtml(input,
514 HtmlEscapeType.HTML4_NAMED_REFERENCES_DEFAULT_TO_HEXA,
515 HtmlEscapeLevel.LEVEL_1_ONLY_MARKUP_SIGNIFICANT);
516 }
db31c358 517
80500544
NR
518 /**
519 * Zip the data and then encode it into Base64.
520 *
521 * @param data
522 * the data
523 *
524 * @return the Base64 zipped version
a6a73de3
NR
525 *
526 * @throws IOException
527 * in case of I/O error
80500544 528 */
5221cf7f 529 public static String zip64(String data) throws IOException {
db31c358 530 try {
f8147a0e 531 return zip64(getBytes(data));
a6a73de3
NR
532 } catch (UnsupportedEncodingException e) {
533 // All conforming JVM are required to support UTF-8
db31c358
NR
534 e.printStackTrace();
535 return null;
536 }
537 }
538
80500544 539 /**
a6a73de3 540 * Zip the data and then encode it into Base64.
bb60bd13 541 *
80500544 542 * @param data
a6a73de3 543 * the data
80500544 544 *
a6a73de3 545 * @return the Base64 zipped version
80500544
NR
546 *
547 * @throws IOException
548 * in case of I/O error
549 */
a6a73de3
NR
550 public static String zip64(byte[] data) throws IOException {
551 // 1. compress
552 ByteArrayOutputStream bout = new ByteArrayOutputStream();
553 try {
554 OutputStream out = new GZIPOutputStream(bout);
555 try {
556 out.write(data);
557 } finally {
558 out.close();
559 }
560 } finally {
561 data = bout.toByteArray();
562 bout.close();
563 }
564
565 // 2. base64
566 InputStream in = new ByteArrayInputStream(data);
567 try {
568 in = new Base64InputStream(in, true);
569 return new String(IOUtils.toByteArray(in), "UTF-8");
570 } finally {
571 in.close();
572 }
db31c358 573 }
e8aa5bf9 574
a359464f 575 /**
a6a73de3
NR
576 * Unconvert from Base64 then unzip the content, which is assumed to be a
577 * String.
a359464f
NR
578 *
579 * @param data
a6a73de3 580 * the data in Base64 format
a359464f 581 *
a6a73de3 582 * @return the raw data
a359464f
NR
583 *
584 * @throws IOException
a6a73de3 585 * in case of I/O error
a359464f 586 */
a6a73de3
NR
587 public static String unzip64s(String data) throws IOException {
588 return new String(unzip64(data), "UTF-8");
a359464f
NR
589 }
590
bb60bd13 591 /**
a6a73de3 592 * Unconvert from Base64 then unzip the content.
bb60bd13
NR
593 *
594 * @param data
a6a73de3 595 * the data in Base64 format
bb60bd13 596 *
a6a73de3 597 * @return the raw data
bb60bd13
NR
598 *
599 * @throws IOException
a6a73de3 600 * in case of I/O error
bb60bd13 601 */
a6a73de3
NR
602 public static byte[] unzip64(String data) throws IOException {
603 InputStream in = new Base64InputStream(new ByteArrayInputStream(
f8147a0e 604 getBytes(data)), false);
a6a73de3
NR
605 try {
606 in = new GZIPInputStream(in);
607 return IOUtils.toByteArray(in);
608 } finally {
609 in.close();
610 }
bb60bd13
NR
611 }
612
613 /**
a359464f
NR
614 * Convert the given data to Base64 format.
615 *
616 * @param data
617 * the data to convert
a359464f
NR
618 *
619 * @return the Base64 {@link String} representation of the data
620 *
621 * @throws IOException
622 * in case of I/O errors
623 */
a6a73de3 624 public static String base64(String data) throws IOException {
f8147a0e 625 return base64(getBytes(data));
a359464f
NR
626 }
627
628 /**
629 * Convert the given data to Base64 format.
630 *
631 * @param data
632 * the data to convert
a359464f
NR
633 *
634 * @return the Base64 {@link String} representation of the data
635 *
636 * @throws IOException
637 * in case of I/O errors
638 */
a6a73de3
NR
639 public static String base64(byte[] data) throws IOException {
640 Base64InputStream in = new Base64InputStream(new ByteArrayInputStream(
641 data), true);
642 try {
643 return new String(IOUtils.toByteArray(in), "UTF-8");
644 } finally {
645 in.close();
a359464f 646 }
a359464f
NR
647 }
648
649 /**
650 * Unconvert the given data from Base64 format back to a raw array of bytes.
bb60bd13
NR
651 *
652 * @param data
653 * the data to unconvert
bb60bd13
NR
654 *
655 * @return the raw data represented by the given Base64 {@link String},
bb60bd13
NR
656 *
657 * @throws IOException
658 * in case of I/O errors
659 */
a6a73de3
NR
660 public static byte[] unbase64(String data) throws IOException {
661 Base64InputStream in = new Base64InputStream(new ByteArrayInputStream(
f8147a0e 662 getBytes(data)), false);
a6a73de3
NR
663 try {
664 return IOUtils.toByteArray(in);
665 } finally {
666 in.close();
a359464f 667 }
a359464f
NR
668 }
669
bb60bd13
NR
670 /**
671 * Unonvert the given data from Base64 format back to a {@link String}.
672 *
673 * @param data
674 * the data to unconvert
bb60bd13
NR
675 *
676 * @return the {@link String} represented by the given Base64 {@link String}
bb60bd13
NR
677 *
678 * @throws IOException
679 * in case of I/O errors
680 */
a6a73de3
NR
681 public static String unbase64s(String data) throws IOException {
682 return new String(unbase64(data), "UTF-8");
bb60bd13
NR
683 }
684
d1e63903
NR
685 /**
686 * Return a display {@link String} for the given value, which can be
687 * suffixed with "k" or "M" depending upon the number, if it is big enough.
688 * <p>
79961c53
NR
689 * <p>
690 * Examples:
d1e63903 691 * <ul>
79961c53
NR
692 * <li><tt>8 765</tt> becomes "8k"</li>
693 * <li><tt>998 765</tt> becomes "998k"</li>
694 * <li><tt>12 987 364</tt> becomes "12M"</li>
695 * <li><tt>5 534 333 221</tt> becomes "5G"</li>
d1e63903
NR
696 * </ul>
697 *
698 * @param value
699 * the value to convert
700 *
701 * @return the display value
702 */
703 public static String formatNumber(long value) {
5b46737c 704 return formatNumber(value, 0);
d1e63903
NR
705 }
706
707 /**
708 * Return a display {@link String} for the given value, which can be
709 * suffixed with "k" or "M" depending upon the number, if it is big enough.
710 * <p>
79961c53 711 * Examples (assuming decimalPositions = 1):
d1e63903 712 * <ul>
79961c53
NR
713 * <li><tt>8 765</tt> becomes "8.7k"</li>
714 * <li><tt>998 765</tt> becomes "998.7k"</li>
715 * <li><tt>12 987 364</tt> becomes "12.9M"</li>
716 * <li><tt>5 534 333 221</tt> becomes "5.5G"</li>
d1e63903
NR
717 * </ul>
718 *
719 * @param value
720 * the value to convert
5b46737c
NR
721 * @param decimalPositions
722 * the number of decimal positions to keep
d1e63903
NR
723 *
724 * @return the display value
725 */
5b46737c 726 public static String formatNumber(long value, int decimalPositions) {
79961c53 727 long userValue = value;
5b46737c 728 String suffix = "";
79961c53 729 long mult = 1;
5b46737c 730
8758aebb 731 if (value >= 1000000000l) {
79961c53
NR
732 mult = 1000000000l;
733 userValue = value / 1000000000l;
39d16a80 734 suffix = " G";
8758aebb 735 } else if (value >= 1000000l) {
79961c53
NR
736 mult = 1000000l;
737 userValue = value / 1000000l;
39d16a80 738 suffix = " M";
5b46737c 739 } else if (value >= 1000l) {
79961c53
NR
740 mult = 1000l;
741 userValue = value / 1000l;
39d16a80 742 suffix = " k";
d1e63903
NR
743 }
744
79961c53 745 String deci = "";
5b46737c 746 if (decimalPositions > 0) {
79961c53
NR
747 deci = Long.toString(value % mult);
748 int size = Long.toString(mult).length() - 1;
749 while (deci.length() < size) {
750 deci = "0" + deci;
751 }
752
5b46737c
NR
753 deci = deci.substring(0, Math.min(decimalPositions, deci.length()));
754 while (deci.length() < decimalPositions) {
755 deci += "0";
756 }
79961c53 757
5b46737c 758 deci = "." + deci;
d1e63903
NR
759 }
760
79961c53 761 return Long.toString(userValue) + deci + suffix;
d1e63903
NR
762 }
763
60033478
NR
764 /**
765 * The reverse operation to {@link StringUtils#formatNumber(long)}: it will
766 * read a "display" number that can contain a "M" or "k" suffix and return
767 * the full value.
768 * <p>
769 * Of course, the conversion to and from display form is lossy (example:
5b46737c 770 * <tt>6870</tt> to "6.5k" to <tt>6500</tt>).
60033478
NR
771 *
772 * @param value
773 * the value in display form with possible "M" and "k" suffixes,
774 * can be NULL
775 *
776 * @return the value as a number, or 0 if not possible to convert
777 */
778 public static long toNumber(String value) {
779 return toNumber(value, 0l);
780 }
781
782 /**
783 * The reverse operation to {@link StringUtils#formatNumber(long)}: it will
784 * read a "display" number that can contain a "M" or "k" suffix and return
785 * the full value.
786 * <p>
787 * Of course, the conversion to and from display form is lossy (example:
5b46737c 788 * <tt>6870</tt> to "6.5k" to <tt>6500</tt>).
60033478
NR
789 *
790 * @param value
791 * the value in display form with possible "M" and "k" suffixes,
792 * can be NULL
793 * @param def
794 * the default value if it is not possible to convert the given
795 * value to a number
796 *
797 * @return the value as a number, or 0 if not possible to convert
798 */
799 public static long toNumber(String value, long def) {
800 long count = def;
801 if (value != null) {
5b46737c 802 value = value.trim().toLowerCase();
60033478 803 try {
79961c53
NR
804 long mult = 1;
805 if (value.endsWith("g")) {
806 value = value.substring(0, value.length() - 1).trim();
807 mult = 1000000000;
808 } else if (value.endsWith("m")) {
5b46737c
NR
809 value = value.substring(0, value.length() - 1).trim();
810 mult = 1000000;
811 } else if (value.endsWith("k")) {
812 value = value.substring(0, value.length() - 1).trim();
813 mult = 1000;
814 }
815
816 long deci = 0;
817 if (value.contains(".")) {
818 String[] tab = value.split("\\.");
819 if (tab.length != 2) {
820 throw new NumberFormatException(value);
821 }
822 double decimal = Double.parseDouble("0."
823 + tab[tab.length - 1]);
824 deci = ((long) (mult * decimal));
825 value = tab[0];
60033478 826 }
5b46737c
NR
827 count = mult * Long.parseLong(value) + deci;
828 } catch (Exception e) {
60033478
NR
829 }
830 }
831
832 return count;
833 }
834
f8147a0e
NR
835 /**
836 * Return the bytes array representation of the given {@link String} in
837 * UTF-8.
838 *
839 * @param str
840 * the {@link String} to transform into bytes
841 * @return the content in bytes
842 */
843 static public byte[] getBytes(String str) {
844 try {
845 return str.getBytes("UTF-8");
846 } catch (UnsupportedEncodingException e) {
847 // All conforming JVM must support UTF-8
848 e.printStackTrace();
849 return null;
850 }
851 }
852
e8aa5bf9
NR
853 /**
854 * The "remove accents" pattern.
855 *
856 * @return the pattern, or NULL if a problem happens
857 */
858 private static Pattern getMarks() {
859 try {
860 return Pattern
861 .compile("[\\p{InCombiningDiacriticalMarks}\\p{IsLm}\\p{IsSk}]+");
862 } catch (Exception e) {
863 // Can fail on Android...
864 return null;
865 }
866 }
dc22eb95 867
bb60bd13 868 //
dc22eb95 869 // justify List<String> related:
bb60bd13 870 //
dc22eb95 871
bb60bd13
NR
872 /**
873 * Check if this line ends as a complete line (ends with a "." or similar).
874 * <p>
875 * Note that we consider an empty line as full, and a line ending with
876 * spaces as not complete.
877 *
878 * @param line
879 * the line to check
880 *
881 * @return TRUE if it does
882 */
dc22eb95 883 static private boolean isFullLine(StringBuilder line) {
bb60bd13
NR
884 if (line.length() == 0) {
885 return true;
886 }
887
888 char lastCar = line.charAt(line.length() - 1);
889 switch (lastCar) {
890 case '.': // points
891 case '?':
892 case '!':
893
894 case '\'': // quotes
895 case '‘':
896 case '’':
897
898 case '"': // double quotes
899 case '”':
900 case '“':
901 case '»':
902 case '«':
903 return true;
904 default:
905 return false;
906 }
dc22eb95
NR
907 }
908
bb60bd13
NR
909 /**
910 * Check if this line represent an item in a list or description (i.e.,
911 * check that the first non-space char is "-").
912 *
913 * @param line
914 * the line to check
915 *
916 * @return TRUE if it is
917 */
dc22eb95
NR
918 static private boolean isItemLine(String line) {
919 String spacing = getItemSpacing(line);
c0c091af
NR
920 return spacing != null && !spacing.isEmpty()
921 && line.charAt(spacing.length()) == '-';
dc22eb95
NR
922 }
923
bb60bd13
NR
924 /**
925 * Return all the spaces that start this line (or Empty if none).
926 *
927 * @param line
928 * the line to get the starting spaces from
929 *
930 * @return the left spacing
931 */
dc22eb95
NR
932 static private String getItemSpacing(String line) {
933 int i;
934 for (i = 0; i < line.length(); i++) {
935 if (line.charAt(i) != ' ') {
936 return line.substring(0, i);
937 }
938 }
939
940 return "";
941 }
c0c091af 942
bb60bd13
NR
943 /**
944 * This line is an horizontal spacer line.
945 *
946 * @param line
947 * the line to test
948 *
949 * @return TRUE if it is
950 */
c0c091af
NR
951 static private boolean isHrLine(CharSequence line) {
952 int count = 0;
953 if (line != null) {
954 for (int i = 0; i < line.length(); i++) {
955 char car = line.charAt(i);
956 if (car == ' ' || car == '\t' || car == '*' || car == '-'
957 || car == '_' || car == '~' || car == '=' || car == '/'
958 || car == '\\') {
959 count++;
960 } else {
961 return false;
962 }
963 }
964 }
965
966 return count > 2;
967 }
5221cf7f
NR
968
969 // Deprecated functions, please do not use //
970
971 /**
972 * @deprecated please use {@link StringUtils#zip64(byte[])} or
973 * {@link StringUtils#base64(byte[])} instead.
974 *
975 * @param data
976 * the data to encode
977 * @param zip
978 * TRUE to zip it before Base64 encoding it, FALSE for Base64
979 * encoding only
980 *
981 * @return the encoded data
982 *
983 * @throws IOException
984 * in case of I/O error
985 */
986 @Deprecated
987 public static String base64(String data, boolean zip) throws IOException {
988 return base64(getBytes(data), zip);
989 }
990
991 /**
992 * @deprecated please use {@link StringUtils#zip64(String)} or
993 * {@link StringUtils#base64(String)} instead.
994 *
995 * @param data
996 * the data to encode
997 * @param zip
998 * TRUE to zip it before Base64 encoding it, FALSE for Base64
999 * encoding only
1000 *
1001 * @return the encoded data
1002 *
1003 * @throws IOException
1004 * in case of I/O error
1005 */
1006 @Deprecated
1007 public static String base64(byte[] data, boolean zip) throws IOException {
1008 if (zip) {
1009 return zip64(data);
1010 }
1011
1012 Base64InputStream b64 = new Base64InputStream(new ByteArrayInputStream(
1013 data), true);
1014 try {
1015 return IOUtils.readSmallStream(b64);
1016 } finally {
1017 b64.close();
1018 }
1019 }
1020
1021 /**
1022 * @deprecated please use {@link Base64OutputStream} and
1023 * {@link GZIPOutputStream} instead.
1024 *
1025 * @param breakLines
1026 * NOT USED ANYMORE, it is always considered FALSE now
1027 */
1028 @Deprecated
1029 public static OutputStream base64(OutputStream data, boolean zip,
1030 boolean breakLines) throws IOException {
1031 OutputStream out = new Base64OutputStream(data);
1032 if (zip) {
1033 out = new java.util.zip.GZIPOutputStream(out);
1034 }
1035
1036 return out;
1037 }
1038
1039 /**
1040 * Unconvert the given data from Base64 format back to a raw array of bytes.
1041 * <p>
1042 * Will automatically detect zipped data and also uncompress it before
1043 * returning, unless ZIP is false.
1044 *
1045 * @deprecated DO NOT USE ANYMORE (bad perf, will be dropped)
1046 *
1047 * @param data
1048 * the data to unconvert
1049 * @param zip
1050 * TRUE to also uncompress the data from a GZIP format
1051 * automatically; if set to FALSE, zipped data can be returned
1052 *
1053 * @return the raw data represented by the given Base64 {@link String},
1054 * optionally compressed with GZIP
1055 *
1056 * @throws IOException
1057 * in case of I/O errors
1058 */
1059 @Deprecated
1060 public static byte[] unbase64(String data, boolean zip) throws IOException {
1061 byte[] buffer = unbase64(data);
1062 if (!zip) {
1063 return buffer;
1064 }
1065
1066 try {
1067 GZIPInputStream zipped = new GZIPInputStream(
1068 new ByteArrayInputStream(buffer));
1069 try {
1070 ByteArrayOutputStream out = new ByteArrayOutputStream();
1071 try {
1072 IOUtils.write(zipped, out);
1073 return out.toByteArray();
1074 } finally {
1075 out.close();
1076 }
1077 } finally {
1078 zipped.close();
1079 }
1080 } catch (Exception e) {
1081 return buffer;
1082 }
1083 }
1084
1085 /**
1086 * Unconvert the given data from Base64 format back to a raw array of bytes.
1087 * <p>
1088 * Will automatically detect zipped data and also uncompress it before
1089 * returning, unless ZIP is false.
1090 *
1091 * @deprecated DO NOT USE ANYMORE (bad perf, will be dropped)
1092 *
1093 * @param data
1094 * the data to unconvert
1095 * @param zip
1096 * TRUE to also uncompress the data from a GZIP format
1097 * automatically; if set to FALSE, zipped data can be returned
1098 *
1099 * @return the raw data represented by the given Base64 {@link String},
1100 * optionally compressed with GZIP
1101 *
1102 * @throws IOException
1103 * in case of I/O errors
1104 */
1105 @Deprecated
1106 public static InputStream unbase64(InputStream data, boolean zip)
1107 throws IOException {
1108 return new ByteArrayInputStream(unbase64(IOUtils.readSmallStream(data),
1109 zip));
1110 }
1111
1112 /**
1113 * @deprecated DO NOT USE ANYMORE (bad perf, will be dropped)
1114 */
1115 @Deprecated
1116 public static byte[] unbase64(byte[] data, int offset, int count,
1117 boolean zip) throws IOException {
1118 byte[] dataPart = Arrays.copyOfRange(data, offset, offset + count);
1119 return unbase64(new String(dataPart, "UTF-8"), zip);
1120 }
1121
1122 /**
1123 * @deprecated DO NOT USE ANYMORE (bad perf, will be dropped)
1124 */
1125 @Deprecated
1126 public static String unbase64s(String data, boolean zip) throws IOException {
1127 return new String(unbase64(data, zip), "UTF-8");
1128 }
1129
1130 /**
1131 * @deprecated DO NOT USE ANYMORE (bad perf, will be dropped)
1132 */
1133 @Deprecated
1134 public static String unbase64s(byte[] data, int offset, int count,
1135 boolean zip) throws IOException {
1136 return new String(unbase64(data, offset, count, zip), "UTF-8");
1137 }
ec1f3444 1138}