com.threerings.gwt.util.WikiUtils Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of gwt-utils Show documentation
Show all versions of gwt-utils Show documentation
Utilities for use in developing GWT applications.
The newest version!
//
// $Id$
//
// OOO GWT Utils - utilities for creating GWT applications
// Copyright (C) 2009-2010 Three Rings Design, Inc., All Rights Reserved
// http://code.google.com/p/ooo-gwt-utils/
//
// This library is free software; you can redistribute it and/or modify it
// under the terms of the GNU Lesser General Public License as published
// by the Free Software Foundation; either version 2.1 of the License, or
// (at your option) any later version.
//
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
//
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
package com.threerings.gwt.util;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.Map;
/**
* Used by {@link WikiParser}.
*
* @author Yaroslav Stavnichiy ([email protected])
*/
public class WikiUtils
{
public static boolean isURI (String uri) {
return !uri.matches(".*\\s.*") && uri.matches(URL_REGEX);
}
private final static String URL_REGEX =
"\\w+://" + // pcol://
"([^:@]+(:[^@]+)@)?" + // (username(:password)@)
"[^:/]+(:\\d+)?" + // hostname(:port)
"(/[^/#?]+)*/?" + // (/pathseg(/pathseg))(/)
"(\\?[^#]*)?(#.*)?"; // (?query)(#hash)
public static boolean isAbsoluteURI (String uri) {
// TODO: make this more sophisticated if needed
return uri.matches("\\w+://.*");
}
public static boolean isUrlChar(char c) {
// From MediaWiki: "._\\/~%-+&#?!=()@"
// From http://www.ietf.org/rfc/rfc2396.txt :
// reserved: ";/?:@&=+$,"
// unreserved: "-_.!~*'()"
// delim: "%#"
if (isLatinLetterOrDigit(c)) return true;
return "/?@&=+,-_.!~()%#;:$*".indexOf(c)>=0; // I excluded '\''
}
public static boolean isLatinLetterOrDigit(char c) {
return (c>='a' && c<='z') || (c>='A' && c<='Z') || (c>='0' && c<='9');
}
/**
* Filters text so there are no '\r' chars in it ("\r\n" -> "\n"; then "\r" -> "\n").
* Most importantly makes all blank lines (lines with only spaces) exactly like this: "\n\n".
* WikiParser relies on that.
*/
public static String preprocessWikiText(String text) {
if (text==null) return "";
text=text.trim();
int length=text.length();
char[] chars=new char[length];
text.getChars(0, length, chars, 0);
StringBuilder sb=new StringBuilder();
boolean blankLine=true;
StringBuilder spaces=new StringBuilder();
for (int p=0; p "\n"; then "\r" -> "\n"
if (p+1 unent = getHtmlUnEntities();
for (int ii = 0, ll = s.length(); ii < ll; ii++) {
char ch = s.charAt(ii);
String ent = unent.get(ch);
if (ent != null) {
sb.append("&").append(ent).append(";");
} else {
sb.append(ch);
}
}
return sb.toString();
}
public static String unescapeHTML(String value) {
if (value==null) return null;
if (value.indexOf('&')<0) return value;
Map ent = getHtmlEntities();
StringBuffer sb=new StringBuffer();
final int length=value.length();
for (int i=0; ii && i1-i<=12) {
if (value.charAt(i+1)=='#') {
if (value.charAt(i+2)=='x') {
ce=(char)atoi(value.substring(i+3, i1), 16);
}
else {
ce=(char)atoi(value.substring(i+2, i1));
}
}
else {
synchronized (ent) {
Character ceObj=ent.get(value.substring(i+1, i1));
ce=ceObj==null?0:ceObj.charValue();
}
}
}
if (ce>0) {
sb.append(ce);
i=i1;
}
else sb.append(c);
}
else {
sb.append(c);
}
}
return sb.toString();
}
static public int atoi(String s) {
try {
return Integer.parseInt(s);
}
catch (Throwable ex) {
return 0;
}
}
static public int atoi(String s, int base) {
try {
return Integer.parseInt(s, base);
}
catch (Throwable ex) {
return 0;
}
}
public static String replaceString(String str, String from, String to) {
StringBuffer buf = new StringBuffer();
int flen = from.length();
int i1=0, i2=0;
while ( (i2 = str.indexOf(from,i1)) >= 0 ) {
buf.append(str.substring(i1, i2));
buf.append(to);
i1 = i2 + flen;
}
buf.append(str.substring(i1));
return buf.toString();
}
public static String[] split(String s, char separator) {
// this is meant to be faster than String.split() when separator is not regexp
if (s==null) return null;
ArrayList parts=new ArrayList();
int beginIndex=0, endIndex;
while ((endIndex=s.indexOf(separator, beginIndex))>=0) {
parts.add(s.substring(beginIndex, endIndex));
beginIndex=endIndex+1;
}
parts.add(s.substring(beginIndex));
String[] a=new String[parts.size()];
return parts.toArray(a);
}
/**
* Translates all non-basic-latin-letters characters into latin ones for use in URLs etc.
* Here is the implementation for cyrillic (Russian) alphabet. Unknown characters are omitted.
*
* @param s string to be translated
* @return translated string
*/
public static String translit(String s) {
if (s==null) return "";
StringBuilder sb=new StringBuilder(s.length()+100);
final int length=s.length();
final int translitTableLength=translitTable.length();
for (int i=0; i getHtmlEntities () {
if (_entities == null) {
_entities = new HashMap();
_entities.put("lt", '<');
_entities.put("gt", '>');
_entities.put("amp", '&');
_entities.put("quot", '"');
_entities.put("apos", '\'');
_entities.put("nbsp", '\u00A0');
_entities.put("shy", '\u00AD');
_entities.put("copy", '\u00A9');
_entities.put("reg", '\u00AE');
_entities.put("trade", '\u2122');
_entities.put("mdash", '\u2014');
_entities.put("ndash", '\u2013');
_entities.put("ldquo", '\u201C');
_entities.put("rdquo", '\u201D');
_entities.put("euro", '\u20AC');
_entities.put("middot", '\u00B7');
_entities.put("bull", '\u2022');
_entities.put("laquo", '\u00AB');
_entities.put("raquo", '\u00BB');
}
return _entities;
}
private static synchronized Map getHtmlUnEntities () {
if (_unentities == null) {
_unentities = new HashMap();
for (Map.Entry entry : getHtmlEntities().entrySet()) {
_unentities.put(entry.getValue(), entry.getKey());
}
}
return _unentities;
}
private static Map _entities;
private static Map _unentities;
private static final String translitTable =
"\ufffda\ufffdb\ufffdv\ufffdg\ufffdd\ufffde\ufffde\ufffdzh\ufffdz\ufffdi\ufffdy\ufffdk" +
"\ufffdl\ufffdm\ufffdn\ufffdo\ufffdp\ufffdr\ufffds\ufffdt\ufffdu\ufffdf\ufffdh\ufffdts" +
"\ufffdch\ufffdsh\ufffdsch\ufffd\ufffdy\ufffd\ufffde\ufffdyu\ufffdya\ufffdA\ufffdB\ufffdV" +
"\ufffdG\ufffdD\ufffdE\ufffdE\ufffdZH\ufffdZ\ufffdI\ufffdY\ufffdK\ufffdL\ufffdM\ufffdN" +
"\ufffdO\ufffdP\ufffdR\ufffdS\ufffdT\ufffdU\ufffdF\ufffdH\ufffdTS\ufffdCH\ufffdSH" +
"\ufffdSCH\ufffd\ufffdY\ufffd\ufffdE\ufffdYU\ufffdYA";
}
© 2015 - 2025 Weber Informatics LLC | Privacy Policy