From 13417cf9c6eec555b51da49742e47939d2f5715b Mon Sep 17 00:00:00 2001 From: James Moger <james.moger@gitblit.com> Date: Fri, 19 Oct 2012 22:47:33 -0400 Subject: [PATCH] Exclude submodules from zip downloads (issue 151) --- src/com/gitblit/utils/StringUtils.java | 156 +++++++++++++++++++++++++++++++++++++++++++++++++-- 1 files changed, 149 insertions(+), 7 deletions(-) diff --git a/src/com/gitblit/utils/StringUtils.java b/src/com/gitblit/utils/StringUtils.java index 2c35724..d115f89 100644 --- a/src/com/gitblit/utils/StringUtils.java +++ b/src/com/gitblit/utils/StringUtils.java @@ -15,14 +15,27 @@ */ package com.gitblit.utils; +import java.io.ByteArrayOutputStream; 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; /** @@ -66,7 +79,7 @@ * @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) == '&') { @@ -107,7 +120,7 @@ * @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) == '/') { @@ -302,11 +315,16 @@ * @return the relative path */ public static String getRelativePath(String basePath, String fullPath) { - String relativePath = fullPath.substring(basePath.length()).replace('\\', '/'); - if (relativePath.charAt(0) == '/') { - relativePath = relativePath.substring(1); + String bp = basePath.replace('\\', '/').toLowerCase(); + String fp = fullPath.replace('\\', '/').toLowerCase(); + if (fp.startsWith(bp)) { + String relativePath = fullPath.substring(basePath.length()).replace('\\', '/'); + if (relativePath.charAt(0) == '/') { + relativePath = relativePath.substring(1); + } + return relativePath; } - return relativePath; + return fullPath; } /** @@ -354,7 +372,7 @@ * @return the first invalid character found or null if string is acceptable */ public static Character findInvalidCharacter(String name) { - char[] validChars = { '/', '.', '_', '-' }; + char[] validChars = { '/', '.', '_', '-', '~' }; for (char c : name.toCharArray()) { if (!Character.isLetterOrDigit(c)) { boolean ok = false; @@ -550,4 +568,128 @@ // 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; + } + + /** + * Converts a string with \nnn sequences into a UTF-8 encoded string. + * @param input + * @return + */ + public static String convertOctal(String input) { + try { + ByteArrayOutputStream bytes = new ByteArrayOutputStream(); + Pattern p = Pattern.compile("(\\\\\\d{3})"); + Matcher m = p.matcher(input); + int i = 0; + while (m.find()) { + bytes.write(input.substring(i, m.start()).getBytes("UTF-8")); + // replace octal encoded value + // strip leading \ character + String oct = m.group().substring(1); + bytes.write(Integer.parseInt(oct, 8)); + i = m.end(); + } + if (bytes.size() == 0) { + // no octal matches + return input; + } else { + if (i < input.length()) { + // add remainder of string + bytes.write(input.substring(i).getBytes("UTF-8")); + } + } + return bytes.toString("UTF-8"); + } catch (Exception e) { + e.printStackTrace(); + } + return input; + } + + /** + * Returns the first path element of a path string. If no path separator is + * found in the path, an empty string is returned. + * + * @param path + * @return the first element in the path + */ + public static String getFirstPathElement(String path) { + if (path.indexOf('/') > -1) { + return path.substring(0, path.indexOf('/')).trim(); + } + return ""; + } + + /** + * Returns the last path element of a path string + * + * @param path + * @return the last element in the path + */ + public static String getLastPathElement(String path) { + if (path.indexOf('/') > -1) { + return path.substring(path.lastIndexOf('/') + 1); + } + return path; + } } \ No newline at end of file -- Gitblit v1.9.1