1 /*
2 * Copyright (c) 2004, 2019, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package org.xml.sax.ext;
27
28 import java.io.IOException;
29
30 import org.xml.sax.EntityResolver;
31 import org.xml.sax.InputSource;
32 import org.xml.sax.XMLReader;
33 import org.xml.sax.SAXException;
34
35
36 /**
37 * Extended interface for mapping external entity references to input
38 * sources, or providing a missing external subset. The
39 * {@link XMLReader#setEntityResolver XMLReader.setEntityResolver()} method
40 * is used to provide implementations of this interface to parsers.
41 * When a parser uses the methods in this interface, the
42 * {@link EntityResolver2#resolveEntity EntityResolver2.resolveEntity()}
43 * method (in this interface) is used <em>instead of</em> the older (SAX 1.0)
44 * {@link EntityResolver#resolveEntity EntityResolver.resolveEntity()} method.
45 *
46 * <p>If a SAX application requires the customized handling which this
47 * interface defines for external entities, it must ensure that it uses
48 * an XMLReader with the
49 * <em>http://xml.org/sax/features/use-entity-resolver2</em> feature flag
50 * set to <em>true</em> (which is its default value when the feature is
51 * recognized). If that flag is unrecognized, or its value is false,
52 * or the resolver does not implement this interface, then only the
53 * {@link EntityResolver} method will be used.
54 *
55 * <p>That supports three categories of application that modify entity
56 * resolution. <em>Old Style</em> applications won't know about this interface;
57 * they will provide an EntityResolver.
58 * <em>Transitional Mode</em> provide an EntityResolver2 and automatically
59 * get the benefit of its methods in any systems (parsers or other tools)
60 * supporting it, due to polymorphism.
61 * Both <em>Old Style</em> and <em>Transitional Mode</em> applications will
62 * work with any SAX2 parser.
63 * <em>New style</em> applications will fail to run except on SAX2 parsers
64 * that support this particular feature.
65 * They will insist that feature flag have a value of "true", and the
66 * EntityResolver2 implementation they provide might throw an exception
67 * if the original SAX 1.0 style entity resolution method is invoked.
68 *
69 * @see org.xml.sax.XMLReader#setEntityResolver
70 *
71 * @since 1.5, SAX 2.0 (extensions 1.1 alpha)
72 * @author David Brownell
73 */
74 public interface EntityResolver2 extends EntityResolver
75 {
76 /**
77 * Allows applications to provide an external subset for documents
78 * that don't explicitly define one. Documents with DOCTYPE declarations
79 * that omit an external subset can thus augment the declarations
80 * available for validation, entity processing, and attribute processing
81 * (normalization, defaulting, and reporting types including ID).
82 * This augmentation is reported
83 * through the {@link LexicalHandler#startDTD startDTD()} method as if
84 * the document text had originally included the external subset;
85 * this callback is made before any internal subset data or errors
86 * are reported.
87 *
88 * <p>This method can also be used with documents that have no DOCTYPE
89 * declaration. When the root element is encountered,
90 * but no DOCTYPE declaration has been seen, this method is
91 * invoked. If it returns a value for the external subset, that root
92 * element is declared to be the root element, giving the effect of
93 * splicing a DOCTYPE declaration at the end the prolog of a document
94 * that could not otherwise be valid. The sequence of parser callbacks
95 * in that case logically resembles this:
96 *
97 * <pre>
98 * ... comments and PIs from the prolog (as usual)
99 * startDTD ("rootName", source.getPublicId (), source.getSystemId ());
100 * startEntity ("[dtd]");
101 * ... declarations, comments, and PIs from the external subset
102 * endEntity ("[dtd]");
103 * endDTD ();
104 * ... then the rest of the document (as usual)
105 * startElement (..., "rootName", ...);
106 * </pre>
107 *
108 * <p>Note that the InputSource gets no further resolution.
109 * Implementations of this method may wish to invoke
110 * {@link #resolveEntity resolveEntity()} to gain benefits such as use
111 * of local caches of DTD entities. Also, this method will never be
112 * used by a (non-validating) processor that is not including external
113 * parameter entities.
114 *
115 * <p>Uses for this method include facilitating data validation when
116 * interoperating with XML processors that would always require
117 * undesirable network accesses for external entities, or which for
118 * other reasons adopt a "no DTDs" policy.
119 * Non-validation motives include forcing documents to include DTDs so
120 * that attributes are handled consistently.
121 * For example, an XPath processor needs to know which attibutes have
122 * type "ID" before it can process a widely used type of reference.
123 *
124 * <p><strong>Warning:</strong> Returning an external subset modifies
125 * the input document. By providing definitions for general entities,
126 * it can make a malformed document appear to be well formed.
127 *
128 * @param name Identifies the document root element. This name comes
129 * from a DOCTYPE declaration (where available) or from the actual
130 * root element.
131 * @param baseURI The document's base URI, serving as an additional
132 * hint for selecting the external subset. This is always an absolute
133 * URI, unless it is null because the XMLReader was given an InputSource
134 * without one.
135 *
136 * @return An InputSource object describing the new external subset
137 * to be used by the parser, or null to indicate that no external
138 * subset is provided.
139 *
140 * @exception SAXException Any SAX exception, possibly wrapping
141 * another exception.
142 * @exception IOException Probably indicating a failure to create
143 * a new InputStream or Reader, or an illegal URL.
144 */
145 public InputSource getExternalSubset (String name, String baseURI)
146 throws SAXException, IOException;
147
148 /**
149 * Allows applications to map references to external entities into input
150 * sources, or tell the parser it should use conventional URI resolution.
151 * This method is only called for external entities which have been
152 * properly declared.
153 * This method provides more flexibility than the {@link EntityResolver}
154 * interface, supporting implementations of more complex catalogue
155 * schemes such as the one defined by the <a href=
156 * "http://www.oasis-open.org/committees/entity/spec-2001-08-06.html"
157 * >OASIS XML Catalogs</a> specification.
158 *
159 * <p>Parsers configured to use this resolver method will call it
160 * to determine the input source to use for any external entity
161 * being included because of a reference in the XML text.
162 * That excludes the document entity, and any external entity returned
163 * by {@link #getExternalSubset getExternalSubset()}.
164 * When a (non-validating) processor is configured not to include
165 * a class of entities (parameter or general) through use of feature
166 * flags, this method is not invoked for such entities.
167 *
168 * <p>Note that the entity naming scheme used here is the same one
169 * used in the {@link LexicalHandler}, or in the {@link
170 * org.xml.sax.ContentHandler#skippedEntity
171 * ContentHandler.skippedEntity()}
172 * method.
173 *
174 * @param name Identifies the external entity being resolved.
175 * Either "[dtd]" for the external subset, or a name starting
176 * with "%" to indicate a parameter entity, or else the name of
177 * a general entity. This is never null when invoked by a SAX2
178 * parser.
179 * @param publicId The public identifier of the external entity being
180 * referenced (normalized as required by the XML specification), or
181 * null if none was supplied.
182 * @param baseURI The URI with respect to which relative systemIDs
183 * are interpreted. This is always an absolute URI, unless it is
184 * null (likely because the XMLReader was given an InputSource without
185 * one). This URI is defined by the XML specification to be the one
186 * associated with the "{@literal <}" starting the relevant declaration.
187 * @param systemId The system identifier of the external entity
188 * being referenced; either a relative or absolute URI.
189 * This is never null when invoked by a SAX2 parser; only declared
190 * entities, and any external subset, are resolved by such parsers.
191 *
192 * @return An InputSource object describing the new input source to
193 * be used by the parser. Returning null directs the parser to
194 * resolve the system ID against the base URI and open a connection
195 * to resulting URI.
196 *
197 * @exception SAXException Any SAX exception, possibly wrapping
198 * another exception.
199 * @exception IOException Probably indicating a failure to create
200 * a new InputStream or Reader, or an illegal URL.
201 */
202 public InputSource resolveEntity (
203 String name,
204 String publicId,
205 String baseURI,
206 String systemId
207 ) throws SAXException, IOException;
208 }