001/*
002 * Copyright (c) 2004 World Wide Web Consortium,
003 *
004 * (Massachusetts Institute of Technology, European Research Consortium for
005 * Informatics and Mathematics, Keio University). All Rights Reserved. This
006 * work is distributed under the W3C(r) Software License [1] in the hope that
007 * it will be useful, but WITHOUT ANY WARRANTY; without even the implied
008 * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
009 *
010 * [1] http://www.w3.org/Consortium/Legal/2002/copyright-software-20021231
011 */
012
013package org.w3c.dom.ls;
014
015/**
016 *  This interface represents an input source for data.
017 * <p> This interface allows an application to encapsulate information about
018 * an input source in a single object, which may include a public
019 * identifier, a system identifier, a byte stream (possibly with a specified
020 * encoding), a base URI, and/or a character stream.
021 * <p> The exact definitions of a byte stream and a character stream are
022 * binding dependent.
023 * <p> The application is expected to provide objects that implement this
024 * interface whenever such objects are needed. The application can either
025 * provide its own objects that implement this interface, or it can use the
026 * generic factory method <code>DOMImplementationLS.createLSInput()</code>
027 * to create objects that implement this interface.
028 * <p> The <code>LSParser</code> will use the <code>LSInput</code> object to
029 * determine how to read data. The <code>LSParser</code> will look at the
030 * different inputs specified in the <code>LSInput</code> in the following
031 * order to know which one to read from, the first one that is not null and
032 * not an empty string will be used:
033 * <ol>
034 * <li> <code>LSInput.characterStream</code>
035 * </li>
036 * <li>
037 * <code>LSInput.byteStream</code>
038 * </li>
039 * <li> <code>LSInput.stringData</code>
040 * </li>
041 * <li>
042 * <code>LSInput.systemId</code>
043 * </li>
044 * <li> <code>LSInput.publicId</code>
045 * </li>
046 * </ol>
047 * <p> If all inputs are null, the <code>LSParser</code> will report a
048 * <code>DOMError</code> with its <code>DOMError.type</code> set to
049 * <code>"no-input-specified"</code> and its <code>DOMError.severity</code>
050 * set to <code>DOMError.SEVERITY_FATAL_ERROR</code>.
051 * <p> <code>LSInput</code> objects belong to the application. The DOM
052 * implementation will never modify them (though it may make copies and
053 * modify the copies, if necessary).
054 * <p>See also the <a href='http://www.w3.org/TR/2004/REC-DOM-Level-3-LS-20040407'>Document Object Model (DOM) Level 3 Load
055and Save Specification</a>.
056 */
057public interface LSInput {
058    /**
059     *  An attribute of a language and binding dependent type that represents
060     * a stream of 16-bit units. The application must encode the stream
061     * using UTF-16 (defined in [Unicode] and in [ISO/IEC 10646]). It is not a requirement to have an XML declaration when
062     * using character streams. If an XML declaration is present, the value
063     * of the encoding attribute will be ignored.
064     */
065    public java.io.Reader getCharacterStream();
066    /**
067     *  An attribute of a language and binding dependent type that represents
068     * a stream of 16-bit units. The application must encode the stream
069     * using UTF-16 (defined in [Unicode] and in [ISO/IEC 10646]). It is not a requirement to have an XML declaration when
070     * using character streams. If an XML declaration is present, the value
071     * of the encoding attribute will be ignored.
072     */
073    public void setCharacterStream(java.io.Reader characterStream);
074
075    /**
076     *  An attribute of a language and binding dependent type that represents
077     * a stream of bytes.
078     * <br> If the application knows the character encoding of the byte
079     * stream, it should set the encoding attribute. Setting the encoding in
080     * this way will override any encoding specified in an XML declaration
081     * in the data.
082     */
083    public java.io.InputStream getByteStream();
084    /**
085     *  An attribute of a language and binding dependent type that represents
086     * a stream of bytes.
087     * <br> If the application knows the character encoding of the byte
088     * stream, it should set the encoding attribute. Setting the encoding in
089     * this way will override any encoding specified in an XML declaration
090     * in the data.
091     */
092    public void setByteStream(java.io.InputStream byteStream);
093
094    /**
095     *  String data to parse. If provided, this will always be treated as a
096     * sequence of 16-bit units (UTF-16 encoded characters). It is not a
097     * requirement to have an XML declaration when using
098     * <code>stringData</code>. If an XML declaration is present, the value
099     * of the encoding attribute will be ignored.
100     */
101    public String getStringData();
102    /**
103     *  String data to parse. If provided, this will always be treated as a
104     * sequence of 16-bit units (UTF-16 encoded characters). It is not a
105     * requirement to have an XML declaration when using
106     * <code>stringData</code>. If an XML declaration is present, the value
107     * of the encoding attribute will be ignored.
108     */
109    public void setStringData(String stringData);
110
111    /**
112     *  The system identifier, a URI reference [<a href='http://www.ietf.org/rfc/rfc2396.txt'>IETF RFC 2396</a>], for this
113     * input source. The system identifier is optional if there is a byte
114     * stream, a character stream, or string data. It is still useful to
115     * provide one, since the application will use it to resolve any
116     * relative URIs and can include it in error messages and warnings. (The
117     * LSParser will only attempt to fetch the resource identified by the
118     * URI reference if there is no other input available in the input
119     * source.)
120     * <br> If the application knows the character encoding of the object
121     * pointed to by the system identifier, it can set the encoding using
122     * the <code>encoding</code> attribute.
123     * <br> If the specified system ID is a relative URI reference (see
124     * section 5 in [<a href='http://www.ietf.org/rfc/rfc2396.txt'>IETF RFC 2396</a>]), the DOM
125     * implementation will attempt to resolve the relative URI with the
126     * <code>baseURI</code> as the base, if that fails, the behavior is
127     * implementation dependent.
128     */
129    public String getSystemId();
130    /**
131     *  The system identifier, a URI reference [<a href='http://www.ietf.org/rfc/rfc2396.txt'>IETF RFC 2396</a>], for this
132     * input source. The system identifier is optional if there is a byte
133     * stream, a character stream, or string data. It is still useful to
134     * provide one, since the application will use it to resolve any
135     * relative URIs and can include it in error messages and warnings. (The
136     * LSParser will only attempt to fetch the resource identified by the
137     * URI reference if there is no other input available in the input
138     * source.)
139     * <br> If the application knows the character encoding of the object
140     * pointed to by the system identifier, it can set the encoding using
141     * the <code>encoding</code> attribute.
142     * <br> If the specified system ID is a relative URI reference (see
143     * section 5 in [<a href='http://www.ietf.org/rfc/rfc2396.txt'>IETF RFC 2396</a>]), the DOM
144     * implementation will attempt to resolve the relative URI with the
145     * <code>baseURI</code> as the base, if that fails, the behavior is
146     * implementation dependent.
147     */
148    public void setSystemId(String systemId);
149
150    /**
151     *  The public identifier for this input source. This may be mapped to an
152     * input source using an implementation dependent mechanism (such as
153     * catalogues or other mappings). The public identifier, if specified,
154     * may also be reported as part of the location information when errors
155     * are reported.
156     */
157    public String getPublicId();
158    /**
159     *  The public identifier for this input source. This may be mapped to an
160     * input source using an implementation dependent mechanism (such as
161     * catalogues or other mappings). The public identifier, if specified,
162     * may also be reported as part of the location information when errors
163     * are reported.
164     */
165    public void setPublicId(String publicId);
166
167    /**
168     *  The base URI to be used (see section 5.1.4 in [<a href='http://www.ietf.org/rfc/rfc2396.txt'>IETF RFC 2396</a>]) for
169     * resolving a relative <code>systemId</code> to an absolute URI.
170     * <br> If, when used, the base URI is itself a relative URI, an empty
171     * string, or null, the behavior is implementation dependent.
172     */
173    public String getBaseURI();
174    /**
175     *  The base URI to be used (see section 5.1.4 in [<a href='http://www.ietf.org/rfc/rfc2396.txt'>IETF RFC 2396</a>]) for
176     * resolving a relative <code>systemId</code> to an absolute URI.
177     * <br> If, when used, the base URI is itself a relative URI, an empty
178     * string, or null, the behavior is implementation dependent.
179     */
180    public void setBaseURI(String baseURI);
181
182    /**
183     *  The character encoding, if known. The encoding must be a string
184     * acceptable for an XML encoding declaration ([<a href='http://www.w3.org/TR/2004/REC-xml-20040204'>XML 1.0</a>] section
185     * 4.3.3 "Character Encoding in Entities").
186     * <br> This attribute has no effect when the application provides a
187     * character stream or string data. For other sources of input, an
188     * encoding specified by means of this attribute will override any
189     * encoding specified in the XML declaration or the Text declaration, or
190     * an encoding obtained from a higher level protocol, such as HTTP [<a href='http://www.ietf.org/rfc/rfc2616.txt'>IETF RFC 2616</a>].
191     */
192    public String getEncoding();
193    /**
194     *  The character encoding, if known. The encoding must be a string
195     * acceptable for an XML encoding declaration ([<a href='http://www.w3.org/TR/2004/REC-xml-20040204'>XML 1.0</a>] section
196     * 4.3.3 "Character Encoding in Entities").
197     * <br> This attribute has no effect when the application provides a
198     * character stream or string data. For other sources of input, an
199     * encoding specified by means of this attribute will override any
200     * encoding specified in the XML declaration or the Text declaration, or
201     * an encoding obtained from a higher level protocol, such as HTTP [<a href='http://www.ietf.org/rfc/rfc2616.txt'>IETF RFC 2616</a>].
202     */
203    public void setEncoding(String encoding);
204
205    /**
206     *  If set to true, assume that the input is certified (see section 2.13
207     * in [<a href='http://www.w3.org/TR/2004/REC-xml11-20040204/'>XML 1.1</a>]) when
208     * parsing [<a href='http://www.w3.org/TR/2004/REC-xml11-20040204/'>XML 1.1</a>].
209     */
210    public boolean getCertifiedText();
211    /**
212     *  If set to true, assume that the input is certified (see section 2.13
213     * in [<a href='http://www.w3.org/TR/2004/REC-xml11-20040204/'>XML 1.1</a>]) when
214     * parsing [<a href='http://www.w3.org/TR/2004/REC-xml11-20040204/'>XML 1.1</a>].
215     */
216    public void setCertifiedText(boolean certifiedText);
217
218}