| | |
| | | package com.gitblit.utils;
|
| | |
|
| | | import java.io.UnsupportedEncodingException;
|
| | | import java.nio.ByteBuffer;
|
| | | import java.nio.CharBuffer;
|
| | | import java.nio.charset.CharacterCodingException;
|
| | | import java.nio.charset.Charset;
|
| | | import java.nio.charset.CharsetDecoder;
|
| | | import java.nio.charset.IllegalCharsetNameException;
|
| | | import java.nio.charset.UnsupportedCharsetException;
|
| | | import java.security.MessageDigest;
|
| | | import java.security.NoSuchAlgorithmException;
|
| | | import java.util.ArrayList;
|
| | | import java.util.Arrays;
|
| | | import java.util.Collection;
|
| | | import java.util.Collections;
|
| | | import java.util.Comparator;
|
| | | import java.util.LinkedHashSet;
|
| | | import java.util.List;
|
| | | import java.util.Set;
|
| | | import java.util.regex.Matcher;
|
| | | import java.util.regex.Pattern;
|
| | | import java.util.regex.PatternSyntaxException;
|
| | |
|
| | | /**
|
| | |
| | | * @return plain text escaped for html
|
| | | */
|
| | | public static String escapeForHtml(String inStr, boolean changeSpace) {
|
| | | StringBuffer retStr = new StringBuffer();
|
| | | StringBuilder retStr = new StringBuilder();
|
| | | int i = 0;
|
| | | while (i < inStr.length()) {
|
| | | if (inStr.charAt(i) == '&') {
|
| | |
| | | * @return properly escaped url
|
| | | */
|
| | | public static String encodeURL(String inStr) {
|
| | | StringBuffer retStr = new StringBuffer();
|
| | | StringBuilder retStr = new StringBuilder();
|
| | | int i = 0;
|
| | | while (i < inStr.length()) {
|
| | | if (inStr.charAt(i) == '/') {
|
| | |
| | | // remember to append any characters to the right of a match
|
| | | return sb.toString();
|
| | | }
|
| | | |
| | | /**
|
| | | * Decodes a string by trying several charsets until one does not throw a
|
| | | * coding exception. Last resort is to interpret as UTF-8 with illegal
|
| | | * character substitution.
|
| | | * |
| | | * @param content
|
| | | * @param charsets optional
|
| | | * @return a string
|
| | | */
|
| | | public static String decodeString(byte [] content, String... charsets) {
|
| | | Set<String> sets = new LinkedHashSet<String>();
|
| | | if (!ArrayUtils.isEmpty(charsets)) {
|
| | | sets.addAll(Arrays.asList(charsets));
|
| | | }
|
| | | String value = null;
|
| | | sets.addAll(Arrays.asList("UTF-8", "ISO-8859-1", Charset.defaultCharset().name()));
|
| | | for (String charset : sets) {
|
| | | try {
|
| | | Charset cs = Charset.forName(charset);
|
| | | CharsetDecoder decoder = cs.newDecoder();
|
| | | CharBuffer buffer = decoder.decode(ByteBuffer.wrap(content));
|
| | | value = buffer.toString();
|
| | | break;
|
| | | } catch (CharacterCodingException e) {
|
| | | // ignore and advance to the next charset
|
| | | } catch (IllegalCharsetNameException e) {
|
| | | // ignore illegal charset names
|
| | | } catch (UnsupportedCharsetException e) {
|
| | | // ignore unsupported charsets
|
| | | }
|
| | | }
|
| | | if (value.startsWith("\uFEFF")) {
|
| | | // strip UTF-8 BOM
|
| | | return value.substring(1);
|
| | | }
|
| | | return value;
|
| | | }
|
| | | |
| | | /**
|
| | | * Attempt to extract a repository name from a given url using regular
|
| | | * expressions. If no match is made, then return whatever trails after
|
| | | * the final / character.
|
| | | * |
| | | * @param regexUrls
|
| | | * @return a repository path
|
| | | */
|
| | | public static String extractRepositoryPath(String url, String... urlpatterns) {
|
| | | for (String urlPattern : urlpatterns) {
|
| | | Pattern p = Pattern.compile(urlPattern);
|
| | | Matcher m = p.matcher(url);
|
| | | while (m.find()) {
|
| | | String repositoryPath = m.group(1);
|
| | | return repositoryPath;
|
| | | }
|
| | | }
|
| | | // last resort
|
| | | if (url.lastIndexOf('/') > -1) {
|
| | | return url.substring(url.lastIndexOf('/') + 1);
|
| | | }
|
| | | return url;
|
| | | }
|
| | | } |