List of usage examples for java.lang Character isWhitespace
public static boolean isWhitespace(int codePoint)
From source file:compare.handler.get.CorCode.java
private boolean pairHasText(Pair p) { char[] data = p.getChars(); for (int i = 0; i < data.length; i++) { if (!Character.isWhitespace(data[i])) { return true; }//ww w . j a v a 2 s . c om } return false; }
From source file:net.sf.jabref.importer.TextAnalyzer.java
private static String clean(String s) { boolean found = false; int left = 0; int right = s.length() - 1; while (!found && (left < s.length())) { char c = s.charAt(left); if (Character.isWhitespace(c) || (c == '.') || (c == ',') || (c == '(') || (c == ':') || (c == ')')) { left++;// w ww . ja va2 s .c om } else { found = true; } } found = false; while (!found && (right > left)) { char c = s.charAt(right); if (Character.isWhitespace(c) || (c == '.') || (c == ',') || (c == ')') || (c == ':') || (c == '(')) { right--; } else { found = true; } } //Util.pr(s+"\n"+left+" "+right); return s.substring(left, Math.min(right + 1, s.length())); }
From source file:com.tasktop.internal.hp.qc.core.model.comments.mylyn3_8.HtmlStreamTokenizer_m3_8.java
/** * Parses an HTML tag out of a string of characters. */// ww w.j a v a 2s . co m private static void parseTag(String s, HtmlTag_m3_8 tag, boolean escapeValues) throws ParseException { int i = 0; for (; i < s.length() && Character.isWhitespace(s.charAt(i)); i++) { // just move forward } if (i == s.length()) { throw new ParseException("parse empty tag", 0); //$NON-NLS-1$ } int start = i; for (; i < s.length() && !Character.isWhitespace(s.charAt(i)); i++) { // just move forward } tag.setTagName(s.substring(start, i)); for (; i < s.length() && Character.isWhitespace(s.charAt(i)); i++) { // just move forward } if (i == s.length()) { return; } else { parseAttributes(tag, s, i, escapeValues); return; } }
From source file:de.l3s.boilerpipe.sax.BoilerpipeHTMLContentHandler.java
public void characters(char[] ch, int start, int length) throws SAXException { textElementIdx++;//w ww.jav a2 s . com if (flush) { flushBlock(); flush = false; } if (inIgnorableElement != 0) { return; } char c; boolean startWhitespace = false; boolean endWhitespace = false; if (length == 0) { return; } final int end = start + length; for (int i = start; i < end; i++) { if (Character.isWhitespace(ch[i])) { ch[i] = ' '; } } while (start < end) { c = ch[start]; if (c == ' ') { startWhitespace = true; start++; length--; } else { break; } } while (length > 0) { c = ch[start + length - 1]; if (c == ' ') { endWhitespace = true; length--; } else { break; } } if (length == 0) { if (startWhitespace || endWhitespace) { if (!sbLastWasWhitespace) { textBuffer.append(' '); tokenBuffer.append(' '); } sbLastWasWhitespace = true; } else { sbLastWasWhitespace = false; } lastEvent = Event.WHITESPACE; return; } if (startWhitespace) { if (!sbLastWasWhitespace) { textBuffer.append(' '); tokenBuffer.append(' '); } } if (blockTagLevel == -1) { blockTagLevel = tagLevel; } textBuffer.append(ch, start, length); tokenBuffer.append(ch, start, length); if (endWhitespace) { textBuffer.append(' '); tokenBuffer.append(' '); } sbLastWasWhitespace = endWhitespace; lastEvent = Event.CHARACTERS; currentContainedTextElements.set(textElementIdx); }
From source file:com.opendoorlogistics.core.utils.strings.Strings.java
/** * Standardised version of a string value. * Calculation is optimised as much as possible. * @param s//from w w w . j a v a 2s . co m * @return */ public static String std(String s) { if (s == null) { return ""; } int n = s.length(); StringBuilder b = new StringBuilder(n); // find first non-whitespace int firstNonWS = n; for (int i = 0; i < n; i++) { char c = s.charAt(i); if (!Character.isWhitespace(c)) { firstNonWS = i; break; } } // get last non-whitespace char int lastNonWS = -1; for (int i = n - 1; i >= 0; i--) { char c = s.charAt(i); if (!Character.isWhitespace(c)) { lastNonWS = i; break; } } boolean inWhiteSpace = false; char c; for (int i = firstNonWS; i <= lastNonWS; i++) { c = Character.toLowerCase(s.charAt(i)); if (inWhiteSpace) { if (Character.isWhitespace(c)) { // never add two whitespaces in a row } else { // no longer in whitespace inWhiteSpace = false; b.append(c); } } else { if (Character.isWhitespace(c)) { // always treat whitespace as a space b.append(' '); inWhiteSpace = true; } else { b.append(c); } } } return b.toString(); }
From source file:Base64.java
/** * Decode a Base-64 string into a byte array. * //from ww w .ja va 2s .co m * @param b64 * The Base-64 encoded string. * @return The decoded bytes. * @throws java.io.IOException * If the argument is not a valid Base-64 encoding. */ public static byte[] decode(String b64) throws IOException { ByteArrayOutputStream result = new ByteArrayOutputStream(b64.length() / 3); int state = 0, i; byte temp = 0; for (i = 0; i < b64.length(); i++) { if (Character.isWhitespace(b64.charAt(i))) { continue; } if (b64.charAt(i) == BASE_64_PAD) { break; } int pos = BASE_64.indexOf(b64.charAt(i)); if (pos < 0) { throw new IOException("non-Base64 character " + b64.charAt(i)); } switch (state) { case 0: temp = (byte) (pos - BASE_64.indexOf('A') << 2); state = 1; break; case 1: temp |= (byte) (pos - BASE_64.indexOf('A') >>> 4); result.write(temp); temp = (byte) ((pos - BASE_64.indexOf('A') & 0x0f) << 4); state = 2; break; case 2: temp |= (byte) ((pos - BASE_64.indexOf('A') & 0x7f) >>> 2); result.write(temp); temp = (byte) ((pos - BASE_64.indexOf('A') & 0x03) << 6); state = 3; break; case 3: temp |= (byte) (pos - BASE_64.indexOf('A') & 0xff); result.write(temp); state = 0; break; default: throw new Error("this statement should be unreachable"); } } if (i < b64.length() && b64.charAt(i) == BASE_64_PAD) { switch (state) { case 0: case 1: throw new IOException("malformed Base64 sequence"); case 2: for (; i < b64.length(); i++) { if (!Character.isWhitespace(b64.charAt(i))) { break; } } // We must see a second pad character here. if (b64.charAt(i) != BASE_64_PAD) { throw new IOException("malformed Base64 sequence"); } i++; // Fall-through. case 3: i++; for (; i < b64.length(); i++) { // We should only see whitespace after this. if (!Character.isWhitespace(b64.charAt(i))) { System.out.println(Character.valueOf(b64.charAt(i))); throw new IOException("malformed Base64 sequence"); } } } } else { if (state != 0) { throw new IOException("malformed Base64 sequence"); } } return result.toByteArray(); }
From source file:com.gargoylesoftware.htmlunit.html.DomText.java
/** * Indicates if the provided character can by "typed" in the element. * @param c the character// w ww .j a v a 2s . c o m * @return {@code true} if it is accepted */ protected boolean acceptChar(final char c) { // This range is this is private use area // see http://www.unicode.org/charts/PDF/UE000.pdf return (c < '\uE000' || c > '\uF8FF') && (c == ' ' || !Character.isWhitespace(c)); }
From source file:cloudeventbus.codec.Decoder.java
private int skipWhiteSpace(int messageIndex, String command) { while (messageIndex < command.length() && Character.isWhitespace(command.charAt(messageIndex))) { messageIndex++;//from www. jav a 2s .c o m } return messageIndex; }
From source file:ca.simplegames.micro.utils.StringUtils.java
/** * Trim trailing whitespace from the given String. * * @param str the String to check// w ww.jav a2 s. com * @return the trimmed String * @see java.lang.Character#isWhitespace */ public static String trimTrailingWhitespace(String str) { if (!hasLength(str)) { return str; } StringBuffer buf = new StringBuffer(str); while (buf.length() > 0 && Character.isWhitespace(buf.charAt(buf.length() - 1))) { buf.deleteCharAt(buf.length() - 1); } return buf.toString(); }
From source file:com.xie.javacase.json.XMLTokener.java
/** * Get the next XML Token. These tokens are found inside of angle * brackets. It may be one of these characters: <code>/ > = ! ?</code> or it * may be a string wrapped in single quotes or double quotes, or it may be a * name./* www . j a v a2s . c o m*/ * @return a String or a Character. * @throws org.json.JSONException If the XML is not well formed. */ public Object nextToken() throws JSONException { char c; char q; StringBuffer sb; do { c = next(); } while (Character.isWhitespace(c)); switch (c) { case 0: throw syntaxError("Misshaped element"); case '<': throw syntaxError("Misplaced '<'"); case '>': return XML.GT; case '/': return XML.SLASH; case '=': return XML.EQ; case '!': return XML.BANG; case '?': return XML.QUEST; // Quoted string case '"': case '\'': q = c; sb = new StringBuffer(); for (;;) { c = next(); if (c == 0) { throw syntaxError("Unterminated string"); } if (c == q) { return sb.toString(); } if (c == '&') { sb.append(nextEntity(c)); } else { sb.append(c); } } default: // Name sb = new StringBuffer(); for (;;) { sb.append(c); c = next(); if (Character.isWhitespace(c)) { return sb.toString(); } switch (c) { case 0: return sb.toString(); case '>': case '/': case '=': case '!': case '?': case '[': case ']': back(); return sb.toString(); case '<': case '"': case '\'': throw syntaxError("Bad character in a name"); } } } }