Java 类org.jdom.Verifier 实例源码

public static Map<String, String> convertStringToActionProperties(String text) {
    PropertySplitter split = new PropertySplitter(text);
    String tok = split.nextPair();
    Map<String,String> props = new LinkedHashMap<String,String>();
    while (tok != null) {
        String[] prp = StringUtils.split(tok, "=", 2); //NOI18N
        if (prp.length >= 1 ) {
            String key = prp[0];
            //in case the user adds -D by mistake, remove it to get a parsable xml file.
            if (key.startsWith("-D")) { //NOI18N
                key = key.substring("-D".length()); //NOI18N
            }
            if (key.startsWith("-")) { //NOI18N
                key = key.substring(1);
            }
            if (key.endsWith("=")) {
                key = key.substring(0, key.length() - 1);
            }
            if (key.trim().length() > 0 && Verifier.checkElementName(key.trim()) == null) {
                props.put(key.trim(), prp.length > 1 ? prp[1] : "");
            }
        }
        tok = split.nextPair();
    }
    return props;
}

@Nullable
public static String filterXMLCharacters(String value) {
  if (value != null) {
    StringBuilder builder = null;
    for (int i=0; i<value.length();i++) {
      char c = value.charAt(i);
      if (Verifier.isXMLCharacter(c)) {
        if (builder != null) {
          builder.append(c);
        }
      }
      else {
        if (builder == null) {
          builder = new StringBuilder(value.length()+5);
          builder.append(value, 0, i);
        }
      }
    }
    if (builder != null) {
      value = builder.toString();
    }
  }
  return value;
}

@Nullable
public static String filterXMLCharacters(String value) {
  if (value != null) {
    StringBuilder builder = null;
    for (int i=0; i<value.length();i++) {
      char c = value.charAt(i);
      if (Verifier.isXMLCharacter(c)) {
        if (builder != null) {
          builder.append(c);
        }
      }
      else {
        if (builder == null) {
          builder = new StringBuilder(value.length()+5);
          builder.append(value, 0, i);
        }
      }
    }
    if (builder != null) {
      value = builder.toString();
    }
  }
  return value;
}

static private void addSanitizedContent(
        final Element e,
        final String val ) {
    try {
        e.addContent(val);
    }
    catch (final IllegalDataException ide) {
        LOGGER.warn(
                "Unable to add content",
                ide);
        // Unless a better idea can be found, we need to replace all
        // unparseable characters with a space as a placeholder
        final StringBuffer newVal = new StringBuffer();
        for (int i = 0, len = val.length(); i < len; i++) {
            if (Verifier.isXMLCharacter(val.charAt(i))) {
                newVal.append(val.charAt(i));
            }
            else {
                newVal.append(' ');
            }
        }
        e.addContent(newVal.toString());
    }
}

@Nullable
public static String filterXMLCharacters(String value) {
  if (value != null) {
    StringBuilder builder = null;
    for (int i=0; i<value.length();i++) {
      char c = value.charAt(i);
      if (Verifier.isXMLCharacter(c)) {
        if (builder != null) {
          builder.append(c);
        }
      }
      else {
        if (builder == null) {
          builder = new StringBuilder(value.length()+5);
          builder.append(value, 0, i);
        }
      }
    }
    if (builder != null) {
      value = builder.toString();
    }
  }
  return value;
}

/**
 * Some characters are illegal in XML even as numerical character references. This method performs escaping of them
 * in a custom format, which is supposed to be unescaped on retrieving from XML using {@link #unescapeIllegalXmlChars(String)}.
 * Resulting text can be part of XML version 1.0 document.
 *
 * @see <a href="https://www.w3.org/International/questions/qa-controls">https://www.w3.org/International/questions/qa-controls</a>
 * @see Verifier#isXMLCharacter(int)
 */
@Nonnull
public static String escapeIllegalXmlChars(@Nonnull String text) {
  StringBuilder b = null;
  int lastPos = 0;
  for (int i = 0; i < text.length(); i++) {
    int c = text.codePointAt(i);
    if (Character.isSupplementaryCodePoint(c)) {
      //noinspection AssignmentToForLoopParameter
      i++;
    }
    if (c == '#' || !Verifier.isXMLCharacter(c)) {
      if (b == null) b = new StringBuilder(text.length() + 5); // assuming there's one 'large' char (e.g. 0xFFFF) to escape numerically
      b.append(text, lastPos, i).append('#');
      if (c != '#') b.append(Integer.toHexString(c));
      b.append('#');
      lastPos = i + 1;
    }
  }
  return b == null ? text : b.append(text, lastPos, text.length()).toString();
}

/**
 * XML1.0で使用が禁止されている文字を取り除く.
 * @param str 対象の文字列
 * @return 結果文字列
 */
public static String removeInvalidChars(String str) {
    StringBuilder result = new StringBuilder();
    for (char c : str.toCharArray()) {
        if (Verifier.isXMLCharacter(c)
            || Verifier.isXMLWhitespace(c)) {
            result.append(c);
        }
    }
    return result.toString();
}

public boolean shouldEscape(char ch) {
    if (bits == 16) {
        if (Verifier.isHighSurrogate(ch))
            return true;  // Safer this way per http://unicode.org/faq/utf_bom.html#utf8-4
        else
            return false;
    }
    if (bits == 8) {
        if ((int) ch > 255)
            return true;
        else
            return false;
    }
    if (bits == 7) {
        if ((int) ch > 127)
            return true;
        else
            return false;
    }
    else {
        if (Verifier.isHighSurrogate(ch))
            return true;  // Safer this way per http://unicode.org/faq/utf_bom.html#utf8-4

        if (canEncode != null && encoder != null) {
            try {
                Boolean val = (Boolean) canEncode.invoke(encoder, new Object[]{new Character(ch)});
                return !val.booleanValue();
            }
            catch (Exception ignored) {
            }
        }
        // Return false if we don't know.  This risks not escaping
        // things which should be escaped, but also means people won't
        // start getting loads of unnecessary escapes.
        return false;
    }
}

public static boolean isIdentifier(String name) {
  //return isTokenOfType(manager, name, RncTokenTypes.IDENTIFIER_OR_KEYWORD);
  if (name == null) {
    return false;
  }
  return Verifier.checkXMLName(name) == null ||
         name.length() >= 2 && name.charAt(0) == '\\' && Verifier.checkXMLName(name.substring(1)) == null;
}

public static String getValidXMLString(String source){
    StringBuilder ret = new StringBuilder();
    for (int i = 0, len = source.length(); i < len; i++) {
        // skip non valid XML characters
        if (Verifier.isXMLCharacter(source.charAt(i))) {
            ret.append(source.charAt(i));
        }
    }
    return ret.toString();
}

public static String getValidXMLString(String source){
    StringBuilder ret = new StringBuilder();
    for (int i = 0, len = source.length(); i < len; i++) {
        // skip non valid XML characters
        if (Verifier.isXMLCharacter(source.charAt(i))) {
            ret.append(source.charAt(i));
        }
    }
    return ret.toString();
}

@Override
public void split(@Nullable String text, @NotNull TextRange range, Consumer<TextRange> consumer) {
  if (text == null || StringUtil.isEmpty(text)) {
    return;
  }
  String substring = range.substring(text);
  if (Verifier.checkCharacterData(substring) != null) {
    return;
  }
  //for(int i = 0; i < text.length(); ++i) {
  //  final char ch = text.charAt(i);
  //  if (ch >= '\u3040' && ch <= '\u309f' || // Hiragana
  //      ch >= '\u30A0' && ch <= '\u30ff' || // Katakana
  //      ch >= '\u4E00' && ch <= '\u9FFF' || // CJK Unified ideographs
  //      ch >= '\uF900' && ch <= '\uFAFF' || // CJK Compatibility Ideographs
  //      ch >= '\uFF00' && ch <= '\uFFEF' //Halfwidth and Fullwidth Forms of Katakana & Fullwidth ASCII variants
  //     ) {
  //    return;
  //  }
  //}

  final TextSplitter ws = TextSplitter.getInstance();
  int from = range.getStartOffset();
  int till;
  Matcher matcher = SPLIT_PATTERN.matcher(range.substring(text));
  while (true) {
    checkCancelled();
    List<TextRange> toCheck;
    TextRange wRange;
    String word;
    if(matcher.find()) {
      TextRange found = matcherRange(range, matcher);
      till = found.getStartOffset();
      if (badSize(from, till)) {
        continue;
      }
      wRange = new TextRange(from, till);
      word = wRange.substring(text);
      from = found.getEndOffset();
    } else { // end hit or zero matches
      wRange = new TextRange(from, range.getEndOffset());
      word = wRange.substring(text);
    }
    if (word.contains("@")) {
      toCheck = excludeByPattern(text, wRange, MAIL, 0);
    }
    else
    if (word.contains("://")) {
      toCheck = excludeByPattern(text, wRange, URL, 0);
    }
    else {
      toCheck = Collections.singletonList(wRange);
    }
    for (TextRange r : toCheck) {
      ws.split(text, r, consumer);
    }
    if(matcher.hitEnd()) break;
  }
}