List of usage examples for java.lang Character isDigit
public static boolean isDigit(int codePoint)
From source file:com.joliciel.talismane.tokeniser.filters.TokenRegexFilterImpl.java
Pattern getPattern() {
if (pattern == null) {
// we may need to replace WordLists by the list contents
String myRegex = this.regex;
if (LOG.isTraceEnabled()) {
LOG.trace("Regex: " + myRegex);
}//from w ww.jav a 2 s. c om
if (this.autoWordBoundaries) {
Boolean startsWithLetter = null;
for (int i = 0; i < myRegex.length() && startsWithLetter == null; i++) {
char c = myRegex.charAt(i);
if (c == '\\') {
i++;
c = myRegex.charAt(i);
if (c == 'd' || c == 'w') {
startsWithLetter = true;
} else if (c == 's' || c == 'W' || c == 'b' || c == 'B') {
startsWithLetter = false;
} else if (c == 'p') {
i += 2; // skip the open curly brackets
int closeCurlyBrackets = myRegex.indexOf('}', i);
int openParentheses = myRegex.indexOf('(', i);
int endIndex = closeCurlyBrackets;
if (openParentheses > 0 && openParentheses < closeCurlyBrackets)
endIndex = openParentheses;
if (endIndex > 0) {
String specialClass = myRegex.substring(i, endIndex);
if (specialClass.equals("WordList")) {
startsWithLetter = true;
}
}
}
break;
} else if (c == '[' || c == '(') {
// do nothing
} else if (Character.isLetter(c) || Character.isDigit(c)) {
startsWithLetter = true;
} else {
startsWithLetter = false;
}
}
Boolean endsWithLetter = null;
for (int i = myRegex.length() - 1; i >= 0 && endsWithLetter == null; i--) {
char c = myRegex.charAt(i);
char prevC = ' ';
if (i >= 1)
prevC = myRegex.charAt(i - 1);
if (prevC == '\\') {
if (c == 'd' || c == 'w') {
endsWithLetter = true;
} else if (c == 's' || c == 'W' || c == 'b' || c == 'B') {
endsWithLetter = false;
} else if (c == 'p') {
i += 2; // skip the open curly brackets
int closeCurlyBrackets = myRegex.indexOf('}', i);
int openParentheses = myRegex.indexOf('(', i);
int endIndex = closeCurlyBrackets;
if (openParentheses < closeCurlyBrackets)
endIndex = openParentheses;
if (endIndex > 0) {
String specialClass = myRegex.substring(i, endIndex);
if (specialClass.equals("WordList") || specialClass.equals("Alpha")
|| specialClass.equals("Lower") || specialClass.equals("Upper")
|| specialClass.equals("ASCII") || specialClass.equals("Digit")) {
startsWithLetter = true;
}
}
}
break;
} else if (c == ']' || c == ')' || c == '+') {
// do nothing
} else if (c == '}') {
int startIndex = myRegex.lastIndexOf('{') + 1;
int closeCurlyBrackets = myRegex.indexOf('}', startIndex);
int openParentheses = myRegex.indexOf('(', startIndex);
int endIndex = closeCurlyBrackets;
if (openParentheses > 0 && openParentheses < closeCurlyBrackets)
endIndex = openParentheses;
if (endIndex > 0) {
String specialClass = myRegex.substring(startIndex, endIndex);
if (specialClass.equals("WordList") || specialClass.equals("Alpha")
|| specialClass.equals("Lower") || specialClass.equals("Upper")
|| specialClass.equals("ASCII") || specialClass.equals("Digit")) {
endsWithLetter = true;
}
}
break;
} else if (Character.isLetter(c) || Character.isDigit(c)) {
endsWithLetter = true;
} else {
endsWithLetter = false;
}
}
if (startsWithLetter != null && startsWithLetter) {
myRegex = "\\b" + myRegex;
}
if (endsWithLetter != null && endsWithLetter) {
myRegex = myRegex + "\\b";
}
if (LOG.isTraceEnabled()) {
LOG.trace("After autoWordBoundaries: " + myRegex);
}
}
if (!this.caseSensitive || !this.diacriticSensitive) {
StringBuilder regexBuilder = new StringBuilder();
for (int i = 0; i < myRegex.length(); i++) {
char c = myRegex.charAt(i);
if (c == '\\') {
// escape - skip next
regexBuilder.append(c);
i++;
c = myRegex.charAt(i);
regexBuilder.append(c);
} else if (c == '[') {
// character group, don't change it
regexBuilder.append(c);
while (c != ']' && i < myRegex.length()) {
i++;
c = myRegex.charAt(i);
regexBuilder.append(c);
}
} else if (c == '{') {
// command, don't change it
regexBuilder.append(c);
while (c != '}' && i < myRegex.length()) {
i++;
c = myRegex.charAt(i);
regexBuilder.append(c);
}
} else if (Character.isLetter(c)) {
Set<String> chars = new TreeSet<String>();
chars.add("" + c);
char noAccent = diacriticPattern.matcher(Normalizer.normalize("" + c, Form.NFD))
.replaceAll("").charAt(0);
if (!this.caseSensitive) {
chars.add("" + Character.toUpperCase(c));
chars.add("" + Character.toLowerCase(c));
chars.add("" + Character.toUpperCase(noAccent));
}
if (!this.diacriticSensitive) {
chars.add("" + noAccent);
if (!this.caseSensitive) {
chars.add("" + Character.toLowerCase(noAccent));
}
}
if (chars.size() == 1) {
regexBuilder.append(c);
} else {
regexBuilder.append('[');
for (String oneChar : chars) {
regexBuilder.append(oneChar);
}
regexBuilder.append(']');
}
} else {
regexBuilder.append(c);
}
}
myRegex = regexBuilder.toString();
if (LOG.isTraceEnabled()) {
LOG.trace("After caseSensitive: " + myRegex);
}
}
Matcher matcher = wordListPattern.matcher(myRegex);
StringBuilder regexBuilder = new StringBuilder();
int lastIndex = 0;
while (matcher.find()) {
String[] params = matcher.group(1).split(",");
int start = matcher.start();
int end = matcher.end();
regexBuilder.append(myRegex.substring(lastIndex, start));
String wordListName = params[0];
boolean uppercaseOptional = false;
boolean diacriticsOptional = false;
boolean lowercaseOptional = false;
boolean firstParam = true;
for (String param : params) {
if (firstParam) {
/* word list name */ } else if (param.equals("diacriticsOptional"))
diacriticsOptional = true;
else if (param.equals("uppercaseOptional"))
uppercaseOptional = true;
else if (param.equals("lowercaseOptional"))
lowercaseOptional = true;
else
throw new TalismaneException(
"Unknown parameter in word list " + matcher.group(1) + ": " + param);
firstParam = false;
}
ExternalWordList wordList = externalResourceFinder.getExternalWordList(wordListName);
if (wordList == null)
throw new TalismaneException("Unknown word list: " + wordListName);
StringBuilder sb = new StringBuilder();
boolean firstWord = true;
for (String word : wordList.getWordList()) {
if (!firstWord)
sb.append("|");
word = Normalizer.normalize(word, Form.NFC);
if (uppercaseOptional || diacriticsOptional) {
String wordNoDiacritics = Normalizer.normalize(word, Form.NFD)
.replaceAll("\\p{InCombiningDiacriticalMarks}+", "");
String wordLowercase = word.toLowerCase(Locale.ENGLISH);
String wordLowercaseNoDiacritics = Normalizer.normalize(wordLowercase, Form.NFD)
.replaceAll("\\p{InCombiningDiacriticalMarks}+", "");
String wordUppercase = wordNoDiacritics.toUpperCase(Locale.ENGLISH);
boolean needsGrouping = false;
if (uppercaseOptional && !word.equals(wordLowercase))
needsGrouping = true;
if (diacriticsOptional && !word.equals(wordNoDiacritics))
needsGrouping = true;
if (lowercaseOptional && !word.equals(wordUppercase))
needsGrouping = true;
if (needsGrouping) {
for (int i = 0; i < word.length(); i++) {
char c = word.charAt(i);
boolean grouped = false;
if (uppercaseOptional && c != wordLowercase.charAt(i))
grouped = true;
if (diacriticsOptional && c != wordNoDiacritics.charAt(i))
grouped = true;
if (lowercaseOptional && c != wordUppercase.charAt(i))
grouped = true;
if (!grouped)
sb.append(c);
else {
sb.append("[");
String group = "" + c;
if (uppercaseOptional && group.indexOf(wordLowercase.charAt(i)) < 0)
group += (wordLowercase.charAt(i));
if (lowercaseOptional && group.indexOf(wordUppercase.charAt(i)) < 0)
group += (wordUppercase.charAt(i));
if (diacriticsOptional && group.indexOf(wordNoDiacritics.charAt(i)) < 0)
group += (wordNoDiacritics.charAt(i));
if (uppercaseOptional && diacriticsOptional
&& group.indexOf(wordLowercaseNoDiacritics.charAt(i)) < 0)
group += (wordLowercaseNoDiacritics.charAt(i));
sb.append(group);
sb.append("]");
} // does this letter need grouping?
} // next letter
} else {
sb.append(word);
} // any options activated?
} else {
sb.append(word);
}
firstWord = false;
} // next word in list
regexBuilder.append(sb.toString());
lastIndex = end;
} // next match
regexBuilder.append(myRegex.substring(lastIndex));
myRegex = regexBuilder.toString();
this.pattern = Pattern.compile(myRegex, Pattern.UNICODE_CHARACTER_CLASS);
}
return pattern;
}
From source file:Data.Storage.java
/** * adding a data Storage to the collection * @param key index item is stored by//w w w. j ava 2 s . c om * @param value actual data storage data to be stored */ public void put(String key, Storage value) { try { //find out if it is an array or json //if the collection is empty then hashmap boolean isArray = true; for (String storageKey : value.keys()) for (char k : storageKey.toCharArray()) //if there is just one key not a digit then not array if (!Character.isDigit(k)) isArray = false; //if the collection is empty then hashmap if (value.keys().size() > 0 && isArray) { HashMap<String, Object> newJson = new HashMap<>(); newJson.put(key, value.toJsonArray()); addMap(newJson); } else { JSONObject newJson = new JSONObject(); newJson.put(key, value.toJson()); addJson(newJson); } } catch (JSONException e) { Utils.debug("unable to add to Data Storage:\nStorage: " + toString() + "\nAdding: " + value.toString(), "error"); e.printStackTrace(); } }
From source file:com.duowan.common.spring.jdbc.BeanPropertyRowMapper.java
/** * Convert a name in camelCase to an underscored name in lower case. * Any upper case letters are converted to lower case with a preceding underscore. * @param name the string containing original name * @return the converted name// www. j ava 2s . c om */ private String underscoreName(String name) { StringBuilder result = new StringBuilder(); if (name != null && name.length() > 0) { result.append(name.substring(0, 1).toLowerCase()); for (int i = 1; i < name.length(); i++) { char c = name.charAt(i); if (Character.isUpperCase(c) && !Character.isDigit(c)) { result.append("_"); result.append(Character.toLowerCase(c)); } else { result.append(c); } } } return result.toString(); }
From source file:au.org.ala.delta.intkey.directives.IntkeyDirectiveParser.java
@Override protected void processTrailing(StringBuilder data, IntkeyContext context) throws DirectiveException { if (data.length() > 0) { char ch = data.charAt(0); if (Character.isDigit(ch)) { DirectiveSearchResult r = getDirectiveRegistry() .findDirective(new ArrayList<String>(Arrays.asList("use"))); IntkeyDirective useDirective = (IntkeyDirective) r.getMatches().get(0); try { useDirective.parseAndProcess(context, data.toString()); } catch (Exception ex) { handleDirectiveProcessingException(context, useDirective, ex); }//w ww . ja v a2s .c om } else { super.processTrailing(data, context); } } }
From source file:UTFEncodingUtil.java
/** * Decodes the given string using the provided encoding. The encoding must be a valid * Java-encoding.// w w w. j a v a 2 s . com * * @param s the string that should be encoded. * @param encoding the encoding to tranform the bytes into a string. * @return the encoded string. * @throws UnsupportedEncodingException if the specified encoding is not recognized. */ public static String decode(final String s, final String encoding) throws UnsupportedEncodingException { if ("utf-8".equalsIgnoreCase(encoding)) { return decodeUTF(s); } // the resulting string will never be greater than the encoded string final byte[] result = new byte[s.length()]; final char[] chars = s.toCharArray(); int position = 0; for (int i = 0; i < chars.length; i++) { final char ch = chars[i]; final int b; switch (ch) { case '%': final char lch = s.charAt(++i); final int hb = (Character.isDigit(lch) ? lch - '0' : 10 + Character.toLowerCase(lch) - 'a') & 0xF; final char hch = s.charAt(++i); final int lb = (Character.isDigit(hch) ? hch - '0' : 10 + Character.toLowerCase(hch) - 'a') & 0xF; b = (hb << 4) | lb; break; case '+': b = ' '; break; default: b = ch; } result[position] = (byte) b; position += 1; } return new String(result, 0, position, encoding); }
From source file:com.netflix.dyno.contrib.ElasticConnectionPoolConfigurationPublisher.java
int findVersionStartIndex(String nameWithVersion) { if (nameWithVersion != null) { char[] chars = nameWithVersion.toCharArray(); for (int i = 0; i < chars.length; i++) { if (chars[i] == '-') { if (i < chars.length && Character.isDigit(chars[i + 1])) { return i + 1; }//from ww w . j a v a 2s . co m } } } return -1; }
From source file:FormatTest.java
public void replace(FilterBypass fb, int offset, int length, String string, AttributeSet attr) throws BadLocationException { if (string != null) { StringBuilder builder = new StringBuilder(string); for (int i = builder.length() - 1; i >= 0; i--) { int cp = builder.codePointAt(i); if (!Character.isDigit(cp) && cp != '-') { builder.deleteCharAt(i); if (Character.isSupplementaryCodePoint(cp)) { i--;//from ww w . j a va 2s . c o m builder.deleteCharAt(i); } } } string = builder.toString(); } super.replace(fb, offset, length, string, attr); }
From source file:com.flexive.shared.FxFormatUtils.java
/** * Check if a color value is valid./*from w w w . j av a 2 s .com*/ * <p/> * The color may be a RGB value (recognized by a starting '#') or a css class name.<br> * The function returns the default color if value is empty.<br> * If the value defines an invalid RGB value a FxInvalidParameterException is thrown.<br> * * @param paramName the name of the parameter that is used when a FxInvalidParameterException is thrown * @param value the color alue * @return the (corrected) color * @throws FxInvalidParameterException if the color is invalid */ public static String processColorString(String paramName, String value) throws FxInvalidParameterException { if (value == null || value.length() == 0) { return DEFAULT_COLOR; } if (value.charAt(0) == '#') { if (value.length() != 7) { throw new FxInvalidParameterException("Invalid color for property [" + paramName + "]", paramName); } for (int i = 1; i < 7; i++) { char aChar = value.charAt(i); if (!Character.isDigit(aChar) && (aChar != 'A') && (aChar != 'B') && (aChar != 'C') && (aChar != 'D') && (aChar != 'E') && (aChar != 'F')) { throw new FxInvalidParameterException("Invalid color for property [" + paramName + "]", paramName); } } } else if (StringUtils.containsOnly(value.toUpperCase(), "0123456789ABCDEF")) { // prefix with '#' value = "#" + value; } return value; }
From source file:io.techcode.logbulk.pipeline.input.SyslogInput.java
/** * Default implementation returns the date as a String (if present). * * @param reader the reader./*from w ww . j a v a 2s .c o m*/ * @return the timestamp. */ private String getTimestamp(Reader reader) { int c = reader.getc(); if (c == NILVALUE) { return null; } if (!Character.isDigit(c)) { throw new IllegalStateException("Year expected @" + reader.idx); } StringBuilder dateBuilder = new StringBuilder(64); dateBuilder.append((char) c); while ((c = reader.getc()) != SPACE) { dateBuilder.append((char) c); } return dateBuilder.toString(); }
From source file:com.github.tteofili.p2h.Par2HierTest.java
private String asStrings(Map<String, INDArray> pvs, Map<String, INDArray> hvs) { StringBuilder builder = new StringBuilder(); builder.append("doc, depth, Paragraph, PV x, PV y, HV x, HV y\n"); for (Map.Entry<String, INDArray> entry : pvs.entrySet()) { String key = entry.getKey(); String depth = String.valueOf(key.split("\\.").length - 1); String c = String.valueOf(key.charAt(3)); if (Character.isDigit(key.charAt(4))) { c += key.charAt(4);/*from w ww .jav a2 s.c om*/ } String doc = String.valueOf(c); builder.append(doc).append(',').append(depth).append(", ") .append(entry.toString().replace("=[", ",").replace("]", ",")); String s = hvs.get(key).toString(); builder.append(s.replace("[", "").replace("]", "")).append("\n"); } return builder.toString(); }