stringhelper.java

CRM源码This file describes some issues that should be implemented in future and how it should be imple

            }
            if( i < max ) {
                sb.append( delim );
            }
        }
        return sb.toString();
    }

    /**
     * Escapes the string.
     *
     * <p>
     * Changes the entity characters (currently &lt;,&gt;, &quot;,&amp; and &apos;)
     * with the XML entities. Empty strings are returned unchanged.
     * </p>
     *
     * @param s the string to escape
     * @return XML-safe string
     */
    public static String escape( String s ) {

        if( isEmpty( s ) ) {
            return s;
        }

        StringBuffer sb = new StringBuffer();
        int size = s.length();
        for( int i = 0; i < size; i++ ) {
            char c = s.charAt( i );
            switch( c ) {
            case '<':
                sb.append( "&lt;" );
                break;
            case '>':
                sb.append( "&gt;" );
                break;
            case '"':
                sb.append( "&quot;" );
                break;
            case '\'':
                sb.append( "&apos;" );
                break;
            case '&':
                sb.append( "&amp;" );
                break;
            default:
                if( c != 0 ) {
                    sb.append( ( char ) c );
                }
            }
        }

        return sb.toString();

    }

    /**
     * Unescapes the string.
     *
     * <p>
     * Changes the XML entities (currently &lt;, &gt;, &quot;,&amp; and &apos;)
     * with the entity characters. Empty strings are returned unchanged.
     * </p>
     *
     * @param s the string to unescape
     * @return XML-unsafe string
     */
    public static String unEscape( String s ) {

        if( isEmpty( s ) ) {
            return s;
        }

        int len = s.length();
        StringBuffer sb = new StringBuffer();
        int i = 0;
        while( i < s.length() ) {
            char c = s.charAt( i );
            if( c == '&' ) {
                if( len >= ( i + 4 ) && s.substring( i, i + 4 ).equalsIgnoreCase( "&lt;" ) ) {
                    sb.append( '<' );
                    i += 4;
                } else if( len >= ( i + 4 ) && s.substring( i, i + 4 ).equalsIgnoreCase( "&gt;" ) ) {
                    sb.append( '>' );
                    i += 4;
                } else if( len >= ( i + 6 ) && s.substring( i, i + 6 ).equalsIgnoreCase( "&quot;" ) ) {
                    sb.append( '"' );
                    i += 6;
                } else if( len >= ( i + 6 ) && s.substring( i, i + 6 ).equalsIgnoreCase( "&apos;" ) ) {
                    i += 6;
                    sb.append( '\\' );
                } else if( len >= ( i + 5 ) && s.substring( i, i + 5 ).equalsIgnoreCase( "&amp;" ) ) {
                    sb.append( '&' );
                    i += 5;
                } else {
                    sb.append( c );
                    i++;
                }

            } else if( c != 0 ) {
                sb.append( c );
                i++;
            }
        }

        return sb.toString();

    }

    /**
     * Unescapes the string with Unicode characters entities (%uXXXX;)
     * Empty strings are returned unchanged.
     *
     * @param s the string to unescape
     * @return Unicode string
     */
    public static String unEscapeUnicode( String s ) {

        if( isEmpty( s ) ) {
            return s;
        }

        int len = s.length();
        StringBuffer sb = new StringBuffer();
        int i = 0;
        while( i < s.length() ) {
            char c = s.charAt( i );
            if( len >= ( i + 6 ) && s.substring( i, i + 2 ).equalsIgnoreCase( "%u" ) ) {
                String hex = s.substring( i + 2, i + 6 );
                try {
                    int _c = Integer.parseInt( hex, 16 );
                    sb.append( ( char ) _c );
                    i += 6;
                } catch( NumberFormatException ex ) {
                    sb.append( c );
                    i++;
                }
            } else if( c != 0 ) {
                sb.append( c );
                i++;
            }
        }

        return sb.toString();

    }

    /**
     * Converts the string from HTML to plain text.
     *
     * @param s the string to convert
     * @return plain-text string
     */
    public static String html2text( String s ) {

        if( isEmpty( s ) ) {
            return s;
        }

        String result = s;
        try {

            // Clear HTML.
            result = clearHtml( result );

            // Platform-dependent linefeeds.
            RE re = new RE( "\\r\\n|\\r|\\n", RE.REPLACE_ALL );
            result = re.subst( result, "" );

            // <BR> -> linefeeds.
            re = new RE( "<br.*?[\\/]??>", RE.MATCH_CASEINDEPENDENT + RE.REPLACE_ALL );
            result = re.subst( result, "\n" );

            // <P> -> double linefeeds.
            re = new RE( "<p.*?[\\/]??>", RE.MATCH_CASEINDEPENDENT + RE.REPLACE_ALL );
            result = re.subst( result, "\n\n" );

            // Removes all other tags.
            re = new RE( "<[^>]+>", RE.MATCH_CASEINDEPENDENT + RE.REPLACE_ALL );
            result = re.subst( result, "" );

            // Removes all XML entities.
            result = replaceXMLEntities( result );

        } catch( RESyntaxException rex ) {
            throw new GenericSystemException( "Regexp exception: " + rex.getMessage(), rex );
        }

        return result;

    }

    /**
     * Converts the string from XML to plain text.
     *
     * @param s the string to convert
     * @return plain-text string
     */
    public static String xml2text( String s ) {

        if( isEmpty( s ) ) {
            return s;
        }

        String result = s;
        try {

            // Clear XML.
            result = clearXml( result );

            // Removes all tags.
            RE re = new RE( "<[^>]+>", RE.MATCH_CASEINDEPENDENT + RE.REPLACE_ALL );
            result = re.subst( result, "" );

            // Removes all XML entities.
            result = replaceXMLEntities( result );

        } catch( RESyntaxException rex ) {
            throw new GenericSystemException( "Regexp exception: " + rex.getMessage(), rex );
        }

        return result;

    }

    /**
     * Converts the string from plain text to HTML.
     *
     * @param s the string to convert
     * @return HTML string
     */
    public static String text2html( String s ) {
        String result = s;
        if( !isEmpty( result ) ) {
            try {
                RE re = new RE( "\\r\\n|\\r|\\n", RE.REPLACE_ALL );
                result = re.subst( result, "<br>" );
            } catch( RESyntaxException rex ) {
                throw new GenericSystemException( "Regexp exception: " + rex.getMessage(), rex );
            }
        }
        return "<html><body>" + result + "</body></html>";
    }

    /**
     * Converts the string from plain text to HTML.
     *
     * @param s the string to convert
     * @return HTML string
     */
    public static String text2htmlNoTag( String s ) {
        String result = s;
        if( !isEmpty( result ) ) {
            try {
                RE re = new RE( "\\r\\n|\\r|\\n", RE.REPLACE_ALL );
                result = re.subst( result, "<br>" );
            } catch( RESyntaxException rex ) {
                throw new GenericSystemException( "Regexp exception: " + rex.getMessage(), rex );
            }
        }
        return result;
    }

    /**
     * Removes "bad" characters from XML.
     * Valid symbols: #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD]
     * (| [#x10000-#x10FFFF])???
     * @param s the string to convert
     * @return cleared XML
     */
    public static String clear( String s ) {

        // [ALB] don't use StringHelper#isEmpty here!
        if( s == null ) {
            return s;
        }

        StringBuffer sb = null;
        String result = s;
        int length = result.length();

        for( int i = 0; i < length; i++ ) {
            char c = result.charAt( i );

            if( ( c >= '\u0020' && c <= '\ud7ff' )
                || ( c == 9 )
                || ( c == 10 )
                || ( c == 13 )
                || ( c >= '\ue000' && c <= '\ufffd' ) ) {

                // Symbol is valid
                if( sb != null ) {
                    // StringBuffer is created - just append valid symbol...
                    sb.append( c );
                }

            } else {
                // Symbol is not valid
                if( sb == null ) {
                    // first occurance - create new StringBuffer
                    sb = new StringBuffer( result.substring( 0, i ) );
                }
            }
        }

        if( sb != null ) {
            // if StringBuffer is created - take value from it
            result = sb.toString();
        }

        return result;
    }

    /**
     * Removes system XML tag <?xml .. ?>, XMS schema and DTD references from XML.
     * @param s the string to convert
     * @return cleared XML
     */
    public static String clearXml( String s ) {
        return clearXml( s, true );
    }

    /**
     * Removes system XML tag <?xml .. ?>, XMS schema and DTD references from XML.
     * @param s the string to convert
     * @param clearText clear bad characters
     * @return cleared XML
     */
    public static String clearXml( String s, boolean clearText ) {

        if( isEmpty( s ) ) {
            return s;
        }

        // Remove special xml tag.
        String result = s;
        int pos = s.indexOf( "?>" );
        if( pos > 0 ) {
            result = s.substring( pos + 2 ).trim();
        }

        if( clearText ) {
            // Removes "bad" characters.
            return clear( result );