| 1 | package be.nikiroo.utils; |
| 2 | |
| 3 | import java.io.ByteArrayInputStream; |
| 4 | import java.io.IOException; |
| 5 | import java.io.UnsupportedEncodingException; |
| 6 | import java.security.MessageDigest; |
| 7 | import java.security.NoSuchAlgorithmException; |
| 8 | import java.text.Normalizer; |
| 9 | import java.text.Normalizer.Form; |
| 10 | import java.text.ParseException; |
| 11 | import java.text.SimpleDateFormat; |
| 12 | import java.util.Date; |
| 13 | import java.util.Scanner; |
| 14 | import java.util.regex.Pattern; |
| 15 | |
| 16 | import org.unbescape.html.HtmlEscape; |
| 17 | import org.unbescape.html.HtmlEscapeLevel; |
| 18 | import org.unbescape.html.HtmlEscapeType; |
| 19 | |
| 20 | /** |
| 21 | * This class offer some utilities based around {@link String}s. |
| 22 | * |
| 23 | * @author niki |
| 24 | */ |
| 25 | public class StringUtils { |
| 26 | /** |
| 27 | * This enum type will decide the alignment of a {@link String} when padding |
| 28 | * is applied or if there is enough horizontal space for it to be aligned. |
| 29 | */ |
| 30 | public enum Alignment { |
| 31 | /** Aligned at left. */ |
| 32 | Beginning, |
| 33 | /** Centered. */ |
| 34 | Center, |
| 35 | /** Aligned at right. */ |
| 36 | End |
| 37 | } |
| 38 | |
| 39 | static private Pattern marks = Pattern |
| 40 | .compile("[\\p{InCombiningDiacriticalMarks}\\p{IsLm}\\p{IsSk}]+"); |
| 41 | |
| 42 | /** |
| 43 | * Fix the size of the given {@link String} either with space-padding or by |
| 44 | * shortening it. |
| 45 | * |
| 46 | * @param text |
| 47 | * the {@link String} to fix |
| 48 | * @param width |
| 49 | * the size of the resulting {@link String} or -1 for a noop |
| 50 | * |
| 51 | * @return the resulting {@link String} of size <i>size</i> |
| 52 | */ |
| 53 | static public String padString(String text, int width) { |
| 54 | return padString(text, width, true, null); |
| 55 | } |
| 56 | |
| 57 | /** |
| 58 | * Fix the size of the given {@link String} either with space-padding or by |
| 59 | * optionally shortening it. |
| 60 | * |
| 61 | * @param text |
| 62 | * the {@link String} to fix |
| 63 | * @param width |
| 64 | * the size of the resulting {@link String} if the text fits or |
| 65 | * if cut is TRUE or -1 for a noop |
| 66 | * @param cut |
| 67 | * cut the {@link String} shorter if needed |
| 68 | * @param align |
| 69 | * align the {@link String} in this position if we have enough |
| 70 | * space (default is Alignment.Beginning) |
| 71 | * |
| 72 | * @return the resulting {@link String} of size <i>size</i> minimum |
| 73 | */ |
| 74 | static public String padString(String text, int width, boolean cut, |
| 75 | Alignment align) { |
| 76 | |
| 77 | if (align == null) { |
| 78 | align = Alignment.Beginning; |
| 79 | } |
| 80 | |
| 81 | if (width >= 0) { |
| 82 | if (text == null) |
| 83 | text = ""; |
| 84 | |
| 85 | int diff = width - text.length(); |
| 86 | |
| 87 | if (diff < 0) { |
| 88 | if (cut) |
| 89 | text = text.substring(0, width); |
| 90 | } else if (diff > 0) { |
| 91 | if (diff < 2 && align != Alignment.End) |
| 92 | align = Alignment.Beginning; |
| 93 | |
| 94 | switch (align) { |
| 95 | case Beginning: |
| 96 | text = text + new String(new char[diff]).replace('\0', ' '); |
| 97 | break; |
| 98 | case End: |
| 99 | text = new String(new char[diff]).replace('\0', ' ') + text; |
| 100 | break; |
| 101 | case Center: |
| 102 | default: |
| 103 | int pad1 = (diff) / 2; |
| 104 | int pad2 = (diff + 1) / 2; |
| 105 | text = new String(new char[pad1]).replace('\0', ' ') + text |
| 106 | + new String(new char[pad2]).replace('\0', ' '); |
| 107 | break; |
| 108 | } |
| 109 | } |
| 110 | } |
| 111 | |
| 112 | return text; |
| 113 | } |
| 114 | |
| 115 | /** |
| 116 | * Sanitise the given input to make it more Terminal-friendly by removing |
| 117 | * combining characters. |
| 118 | * |
| 119 | * @param input |
| 120 | * the input to sanitise |
| 121 | * @param allowUnicode |
| 122 | * allow Unicode or only allow ASCII Latin characters |
| 123 | * |
| 124 | * @return the sanitised {@link String} |
| 125 | */ |
| 126 | static public String sanitize(String input, boolean allowUnicode) { |
| 127 | return sanitize(input, allowUnicode, !allowUnicode); |
| 128 | } |
| 129 | |
| 130 | /** |
| 131 | * Sanitise the given input to make it more Terminal-friendly by removing |
| 132 | * combining characters. |
| 133 | * |
| 134 | * @param input |
| 135 | * the input to sanitise |
| 136 | * @param allowUnicode |
| 137 | * allow Unicode or only allow ASCII Latin characters |
| 138 | * @param removeAllAccents |
| 139 | * TRUE to replace all accentuated characters by their non |
| 140 | * accentuated counter-parts |
| 141 | * |
| 142 | * @return the sanitised {@link String} |
| 143 | */ |
| 144 | static public String sanitize(String input, boolean allowUnicode, |
| 145 | boolean removeAllAccents) { |
| 146 | |
| 147 | if (removeAllAccents) { |
| 148 | input = Normalizer.normalize(input, Form.NFKD); |
| 149 | input = marks.matcher(input).replaceAll(""); |
| 150 | } |
| 151 | |
| 152 | input = Normalizer.normalize(input, Form.NFKC); |
| 153 | |
| 154 | if (!allowUnicode) { |
| 155 | StringBuilder builder = new StringBuilder(); |
| 156 | for (int index = 0; index < input.length(); index++) { |
| 157 | char car = input.charAt(index); |
| 158 | // displayable chars in ASCII are in the range 32<->255, |
| 159 | // except DEL (127) |
| 160 | if (car >= 32 && car <= 255 && car != 127) { |
| 161 | builder.append(car); |
| 162 | } |
| 163 | } |
| 164 | input = builder.toString(); |
| 165 | } |
| 166 | |
| 167 | return input; |
| 168 | } |
| 169 | |
| 170 | /** |
| 171 | * Convert between the time in milliseconds to a {@link String} in a "fixed" |
| 172 | * way (to exchange data over the wire, for instance). |
| 173 | * <p> |
| 174 | * Precise to the second. |
| 175 | * |
| 176 | * @param time |
| 177 | * the specified number of milliseconds since the standard base |
| 178 | * time known as "the epoch", namely January 1, 1970, 00:00:00 |
| 179 | * GMT |
| 180 | * |
| 181 | * @return the time as a {@link String} |
| 182 | */ |
| 183 | static public String fromTime(long time) { |
| 184 | SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); |
| 185 | return sdf.format(new Date(time)); |
| 186 | } |
| 187 | |
| 188 | /** |
| 189 | * Convert between the time as a {@link String} to milliseconds in a "fixed" |
| 190 | * way (to exchange data over the wire, for instance). |
| 191 | * <p> |
| 192 | * Precise to the second. |
| 193 | * |
| 194 | * @param displayTime |
| 195 | * the time as a {@link String} |
| 196 | * |
| 197 | * @return the number of milliseconds since the standard base time known as |
| 198 | * "the epoch", namely January 1, 1970, 00:00:00 GMT |
| 199 | */ |
| 200 | static public long toTime(String displayTime) { |
| 201 | SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); |
| 202 | try { |
| 203 | return sdf.parse(displayTime).getTime(); |
| 204 | } catch (ParseException e) { |
| 205 | return -1; |
| 206 | } |
| 207 | } |
| 208 | |
| 209 | /** |
| 210 | * Return a hash of the given {@link String}. |
| 211 | * |
| 212 | * @param input |
| 213 | * the input data |
| 214 | * |
| 215 | * @return the hash |
| 216 | */ |
| 217 | static public String getMd5Hash(String input) { |
| 218 | try { |
| 219 | MessageDigest md = MessageDigest.getInstance("MD5"); |
| 220 | md.update(input.getBytes("UTF-8")); |
| 221 | byte byteData[] = md.digest(); |
| 222 | |
| 223 | StringBuffer hexString = new StringBuffer(); |
| 224 | for (int i = 0; i < byteData.length; i++) { |
| 225 | String hex = Integer.toHexString(0xff & byteData[i]); |
| 226 | if (hex.length() == 1) |
| 227 | hexString.append('0'); |
| 228 | hexString.append(hex); |
| 229 | } |
| 230 | |
| 231 | return hexString.toString(); |
| 232 | } catch (NoSuchAlgorithmException e) { |
| 233 | return input; |
| 234 | } catch (UnsupportedEncodingException e) { |
| 235 | return input; |
| 236 | } |
| 237 | } |
| 238 | |
| 239 | /** |
| 240 | * Remove the HTML content from the given input, and un-html-ize the rest. |
| 241 | * |
| 242 | * @param html |
| 243 | * the HTML-encoded content |
| 244 | * |
| 245 | * @return the HTML-free equivalent content |
| 246 | */ |
| 247 | public static String unhtml(String html) { |
| 248 | StringBuilder builder = new StringBuilder(); |
| 249 | |
| 250 | int inTag = 0; |
| 251 | for (char car : html.toCharArray()) { |
| 252 | if (car == '<') { |
| 253 | inTag++; |
| 254 | } else if (car == '>') { |
| 255 | inTag--; |
| 256 | } else if (inTag <= 0) { |
| 257 | builder.append(car); |
| 258 | } |
| 259 | } |
| 260 | |
| 261 | char nbsp = ' '; // non-breakable space (a special char) |
| 262 | char space = ' '; |
| 263 | return HtmlEscape.unescapeHtml(builder.toString()).replace(nbsp, space); |
| 264 | } |
| 265 | |
| 266 | /** |
| 267 | * Escape the given {@link String} so it can be used in XML, as content. |
| 268 | * |
| 269 | * @param input |
| 270 | * the input {@link String} |
| 271 | * |
| 272 | * @return the escaped {@link String} |
| 273 | */ |
| 274 | public static String xmlEscape(String input) { |
| 275 | if (input == null) { |
| 276 | return ""; |
| 277 | } |
| 278 | |
| 279 | return HtmlEscape.escapeHtml(input, |
| 280 | HtmlEscapeType.HTML4_NAMED_REFERENCES_DEFAULT_TO_HEXA, |
| 281 | HtmlEscapeLevel.LEVEL_1_ONLY_MARKUP_SIGNIFICANT); |
| 282 | } |
| 283 | |
| 284 | /** |
| 285 | * Escape the given {@link String} so it can be used in XML, as text content |
| 286 | * inside double-quotes. |
| 287 | * |
| 288 | * @param input |
| 289 | * the input {@link String} |
| 290 | * |
| 291 | * @return the escaped {@link String} |
| 292 | */ |
| 293 | public static String xmlEscapeQuote(String input) { |
| 294 | if (input == null) { |
| 295 | return ""; |
| 296 | } |
| 297 | |
| 298 | return HtmlEscape.escapeHtml(input, |
| 299 | HtmlEscapeType.HTML4_NAMED_REFERENCES_DEFAULT_TO_HEXA, |
| 300 | HtmlEscapeLevel.LEVEL_1_ONLY_MARKUP_SIGNIFICANT); |
| 301 | } |
| 302 | |
| 303 | /** |
| 304 | * Zip the data and then encode it into Base64. |
| 305 | * |
| 306 | * @param data |
| 307 | * the data |
| 308 | * |
| 309 | * @return the Base64 zipped version |
| 310 | */ |
| 311 | public static String zip64(String data) { |
| 312 | try { |
| 313 | return Base64.encodeBytes(data.getBytes(), Base64.GZIP); |
| 314 | } catch (IOException e) { |
| 315 | e.printStackTrace(); |
| 316 | return null; |
| 317 | } |
| 318 | } |
| 319 | |
| 320 | /** |
| 321 | * Unconvert from Base64 then unzip the content. |
| 322 | * |
| 323 | * @param data |
| 324 | * the data in Base64 format |
| 325 | * |
| 326 | * @return the raw data |
| 327 | * |
| 328 | * @throws IOException |
| 329 | * in case of I/O error |
| 330 | */ |
| 331 | public static String unzip64(String data) throws IOException { |
| 332 | ByteArrayInputStream in = new ByteArrayInputStream(Base64.decode(data, |
| 333 | Base64.GZIP)); |
| 334 | |
| 335 | Scanner scan = new Scanner(in); |
| 336 | scan.useDelimiter("\\A"); |
| 337 | try { |
| 338 | return scan.next(); |
| 339 | } finally { |
| 340 | scan.close(); |
| 341 | } |
| 342 | } |
| 343 | } |