All Downloads are FREE. Search and download functionalities are using the official Maven repository.

org.mortbay.util.URIUtil Maven / Gradle / Ivy

There is a newer version: 7.0.0.pre5
Show newest version
// ========================================================================
// Copyright 2004-2005 Mort Bay Consulting Pty. Ltd.
// ------------------------------------------------------------------------
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at 
// http://www.apache.org/licenses/LICENSE-2.0
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
// ========================================================================

package org.mortbay.util;

import java.io.UnsupportedEncodingException;



/* ------------------------------------------------------------ */
/** URI Holder.
 * This class assists with the decoding and encoding or HTTP URI's.
 * It differs from the java.net.URL class as it does not provide
 * communications ability, but it does assist with query string
 * formatting.
 * 

UTF-8 encoding is used by default for % encoded characters. This * may be overridden with the org.mortbay.util.URI.charset system property. * @see UrlEncoded * @author Greg Wilkins (gregw) */ public class URIUtil implements Cloneable { public static final String SLASH="/"; public static final String HTTP="http"; public static final String HTTP_COLON="http:"; public static final String HTTPS="https"; public static final String HTTPS_COLON="https:"; // Use UTF-8 as per http://www.w3.org/TR/html40/appendix/notes.html#non-ascii-chars public static final String __CHARSET=System.getProperty("org.mortbay.util.URI.charset",StringUtil.__UTF8); private URIUtil() {} /* ------------------------------------------------------------ */ /** Encode a URI path. * This is the same encoding offered by URLEncoder, except that * the '/' character is not encoded. * @param path The path the encode * @return The encoded path */ public static String encodePath(String path) { if (path==null || path.length()==0) return path; StringBuffer buf = encodePath(null,path); return buf==null?path:buf.toString(); } /* ------------------------------------------------------------ */ /** Encode a URI path. * @param path The path the encode * @param buf StringBuffer to encode path into (or null) * @return The StringBuffer or null if no substitutions required. */ public static StringBuffer encodePath(StringBuffer buf, String path) { if (buf==null) { loop: for (int i=0;i': case ' ': buf=new StringBuffer(path.length()<<1); break loop; } } if (buf==null) return null; } synchronized(buf) { for (int i=0;i': buf.append("%3E"); continue; case ' ': buf.append("%20"); continue; default: buf.append(c); continue; } } } return buf; } /* ------------------------------------------------------------ */ /** Encode a URI path. * @param path The path the encode * @param buf StringBuffer to encode path into (or null) * @param encode String of characters to encode. % is always encoded. * @return The StringBuffer or null if no substitutions required. */ public static StringBuffer encodeString(StringBuffer buf, String path, String encode) { if (buf==null) { loop: for (int i=0;i=0) { buf=new StringBuffer(path.length()<<1); break loop; } } if (buf==null) return null; } synchronized(buf) { for (int i=0;i=0) { buf.append('%'); StringUtil.append(buf,(byte)(0xff&c),16); } else buf.append(c); } } return buf; } /* ------------------------------------------------------------ */ /* Decode a URI path. * @param path The path the encode * @param buf StringBuffer to encode path into */ public static String decodePath(String path) { if (path==null) return null; char[] chars=null; int n=0; byte[] bytes=null; int b=0; int len=path.length(); for (int i=0;i0) { String s; try { s=new String(bytes,0,b,__CHARSET); } catch (UnsupportedEncodingException e) { s=new String(bytes,0,b); } s.getChars(0,s.length(),chars,n); n+=s.length(); b=0; } chars[n++]=c; } if (chars==null) return path; if (b>0) { String s; try { s=new String(bytes,0,b,__CHARSET); } catch (UnsupportedEncodingException e) { s=new String(bytes,0,b); } s.getChars(0,s.length(),chars,n); n+=s.length(); } return new String(chars,0,n); } /* ------------------------------------------------------------ */ /* Decode a URI path. * @param path The path the encode * @param buf StringBuffer to encode path into */ public static String decodePath(byte[] buf, int offset, int length) { byte[] bytes=null; int n=0; for (int i=0;i=0) return p.substring(0,slash+1); return null; } /* ------------------------------------------------------------ */ /** Strip parameters from a path. * Return path upto any semicolon parameters. */ public static String stripPath(String path) { if (path==null) return null; int semi=path.indexOf(';'); if (semi<0) return path; return path.substring(0,semi); } /* ------------------------------------------------------------ */ /** Convert a path to a cananonical form. * All instances of "." and ".." are factored out. Null is returned * if the path tries to .. above its root. * @param path * @return path or null. */ public static String canonicalPath(String path) { if (path==null || path.length()==0) return path; int end=path.length(); int start = path.lastIndexOf('/', end); search: while (end>0) { switch(end-start) { case 2: // possible single dot if (path.charAt(start+1)!='.') break; break search; case 3: // possible double dot if (path.charAt(start+1)!='.' || path.charAt(start+2)!='.') break; break search; } end=start; start=path.lastIndexOf('/',end-1); } // If we have checked the entire string if (start>=end) return path; StringBuffer buf = new StringBuffer(path); int delStart=-1; int delEnd=-1; int skip=0; while (end>0) { switch(end-start) { case 2: // possible single dot if (buf.charAt(start+1)!='.') { if (skip>0 && --skip==0) { delStart=start>=0?start:0; if(delStart>0 && delEnd==buf.length() && buf.charAt(delEnd-1)=='.') delStart++; } break; } if(start<0 && buf.length()>2 && buf.charAt(1)=='/' && buf.charAt(2)=='/') break; if(delEnd<0) delEnd=end; delStart=start; if (delStart<0 || delStart==0&&buf.charAt(delStart)=='/') { delStart++; if (delEnd=0 && buf.charAt(start)!='/') start--; continue; case 3: // possible double dot if (buf.charAt(start+1)!='.' || buf.charAt(start+2)!='.') { if (skip>0 && --skip==0) { delStart=start>=0?start:0; if(delStart>0 && delEnd==buf.length() && buf.charAt(delEnd-1)=='.') delStart++; } break; } delStart=start; if (delEnd<0) delEnd=end; skip++; end=start--; while (start>=0 && buf.charAt(start)!='/') start--; continue; default: if (skip>0 && --skip==0) { delStart=start>=0?start:0; if(delEnd==buf.length() && buf.charAt(delEnd-1)=='.') delStart++; } } // Do the delete if (skip<=0 && delStart>=0 && delStart>=0) { buf.delete(delStart,delEnd); delStart=delEnd=-1; if (skip>0) delEnd=end; } end=start--; while (start>=0 && buf.charAt(start)!='/') start--; } // Too many .. if (skip>0) return null; // Do the delete if (delEnd>=0) buf.delete(delStart,delEnd); return buf.toString(); } /* ------------------------------------------------------------ */ /** Convert a path to a compact form. * All instances of "//" and "///" etc. are factored out to single "/" * @param path * @return path */ public static String compactPath(String path) { if (path==null || path.length()==0) return path; int state=0; int end=path.length(); int i=0; loop: while (i='a'&&c<='z' || c>='A'&&c<='Z' || (i>0 &&(c>='0'&&c<='9' || c=='.' || c=='+' || c=='-')) )) break; } return false; } }





© 2015 - 2024 Weber Informatics LLC | Privacy Policy