|
1
16 package org.outerj.daisy.books.publisher.impl.publicationprocess;
17
18 import org.outerj.daisy.books.publisher.impl.BookInstanceLayout;
19 import org.outerj.daisy.books.publisher.impl.util.AbstractContentHandler;
20 import org.outerj.daisy.books.store.BookInstance;
21 import org.outerj.daisy.xmlutil.XmlSerializer;
22 import org.xml.sax.InputSource  ;
23 import org.xml.sax.Attributes ;
24 import org.xml.sax.SAXException ;
25 import org.xml.sax.ContentHandler ;
26 import org.xml.sax.helpers.DefaultHandler ;
27 import org.xml.sax.helpers.AttributesImpl ;
28
29 import javax.xml.parsers.SAXParserFactory ;
30 import javax.xml.parsers.SAXParser ;
31 import java.io.InputStream ;
32 import java.io.OutputStream ;
33 import java.io.PrintWriter ;
34 import java.util.HashSet ;
35 import java.util.regex.Pattern ;
36 import java.util.regex.Matcher ;
37
38 public class VerifyIdsAndLinksTask implements PublicationProcessTask {
39 private final String input;
40 private final String output;
41 private static final Pattern headerPattern = Pattern.compile("h([0-9]+)");
42
43 public VerifyIdsAndLinksTask(String input, String output) {
44 this.input = input;
45 this.output = output;
46 }
47
48 public void run(PublicationContext context) throws Exception {
49 context.getPublicationLog().info("Running verify IDs and links task.");
50 LinkLog linkLog = new LinkLog(context.getBookInstance());
51
52 try {
53 verifyIdsAndLinks(context, linkLog);
54 } finally {
55 linkLog.dispose();
56 }
57 }
58
59 private void verifyIdsAndLinks(PublicationContext context, LinkLog linkLog) throws Exception {
60 String publicationOutputPath = BookInstanceLayout.getPublicationOutputPath(context.getPublicationOutputName());
61 String inputXmlPath = publicationOutputPath + input;
62 String outputXmlPath = publicationOutputPath + output;
63 BookInstance bookInstance = context.getBookInstance();
64
65 SAXParserFactory parserFactory = SAXParserFactory.newInstance();
66 parserFactory.setNamespaceAware(true);
67 SAXParser parser = parserFactory.newSAXParser();
68
69 IdGatherer idGatherer = new IdGatherer(linkLog);
70 parser.getXMLReader().setContentHandler(idGatherer);
71
72 InputStream is = bookInstance.getResource(inputXmlPath);
73 try {
74 InputSource inputSource = new InputSource (is);
75 parser.getXMLReader().parse(inputSource);
76 } finally {
77 is.close();
78 }
79
80 OutputStream os = null;
81 is = null;
82 try {
83 os = bookInstance.getResourceOutputStream(outputXmlPath);
84 XmlSerializer xmlSerializer = new XmlSerializer(os);
85 IdAssigner idAssigner = new IdAssigner(xmlSerializer, idGatherer.getIds());
86 LinkCheckerHandler linkCheckerHandler = new LinkCheckerHandler(idAssigner, idGatherer.getIds(), linkLog);
87 parser.getXMLReader().setContentHandler(linkCheckerHandler);
88 is = bookInstance.getResource(inputXmlPath);
89 InputSource inputSource = new InputSource (is);
90 parser.getXMLReader().parse(inputSource);
91 } finally {
92 if (os != null)
93 os.close();
94 if (is != null)
95 is.close();
96 }
97 }
98
99 private static class IdGatherer extends DefaultHandler {
100 private HashSet ids = new HashSet ();
101 private LinkLog linkLog;
102
103 public IdGatherer(LinkLog linkLog) {
104 this.linkLog = linkLog;
105 }
106
107 public HashSet getIds() {
108 return ids;
109 }
110
111 public void startElement(String namespaceURI, String localName, String qName, Attributes atts) throws SAXException {
112 if (namespaceURI.equals("")) {
113 String id = atts.getValue("id");
114 if (id != null) {
115 if (ids.contains(id)) {
116 linkLog.error("Duplicate ID encountered: " + id);
117 }
118 ids.add(id);
119 }
120 }
121 }
122 }
123
124 private static class LinkCheckerHandler extends AbstractContentHandler {
125 private HashSet ids;
126 private LinkLog linkLog;
127 private String currentDocument;
128 private String currentBranch;
129 private String currentLanguage;
130
131 public LinkCheckerHandler(ContentHandler consumer, HashSet ids, LinkLog linkLog) {
132 super(consumer);
133 this.ids = ids;
134 this.linkLog = linkLog;
135 }
136
137 public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
138 if (uri.length() == 0) {
139 if (headerPattern.matcher(localName).matches()) {
140 String document = attributes.getValue("daisyDocument");
141 if (document != null) {
142 this.currentDocument = document;
143 this.currentBranch = attributes.getValue("daisyBranch");
144 this.currentLanguage = attributes.getValue("daisyLanguage");
145 }
146 } else if (localName.equals("a")) {
147 String href = attributes.getValue("href");
148 if (href != null && href.startsWith("#")) {
149 if (!ids.contains(href.substring(1))) {
150 linkLog.error("Link pointing to non-defined ID: " + href + getContext());
151 }
152 }
153 } else if (localName.equals("span") && "crossreference".equals(attributes.getValue("class"))) {
154 String crossRefBookTarget = attributes.getValue("crossRefBookTarget");
155 if (crossRefBookTarget != null && crossRefBookTarget.length() > 1) {
156 if (!ids.contains(crossRefBookTarget.substring(1))) {
157 linkLog.error("Cross reference pointing to non-defined ID: " + crossRefBookTarget + getContext());
158 }
159 }
160 } else if (localName.equals("img")) {
161 String src = attributes.getValue("src");
164 if (src != null && src.startsWith("file:")) {
165 linkLog.error("Image refering to a file: " + src + getContext());
166 }
167 }
168 }
169 super.startElement(uri, localName, qName, attributes);
170 }
171
172 private String getContext() {
173 return " (source document: " + currentDocument + ", branch: " + currentBranch + ", language: " + currentLanguage + ")";
174 }
175 }
176
177
180 private static class IdAssigner extends AbstractContentHandler {
181 private HashSet existingIds;
182 private int sectionCounter = 0;
183 private int figureCounter = 0;
184 private int tableCounter = 0;
185
186 public IdAssigner(ContentHandler consumer, HashSet existingIds) {
187 super(consumer);
188 this.existingIds = existingIds;
189 }
190
191 public void startElement(String namespaceURI, String localName, String qName, Attributes atts) throws SAXException {
192 if (namespaceURI.equals("")) {
193 Matcher matcher = headerPattern.matcher(localName);
194 String newId = null;
195 if (atts.getValue("id") == null) {
196 if (matcher.matches()) {
197 newId = generateSectionId();
198 } else if (localName.equals("img") && atts.getValue("daisy-caption") != null) {
199 newId = generateFigureId();
200 } else if (localName.equals("table") && atts.getValue("daisy-caption") != null) {
201 newId = generateTableId();
202 }
203 }
204
205 if (newId != null) {
206 AttributesImpl newAttrs = new AttributesImpl (atts);
207 newAttrs.addAttribute("", "id", "id", "CDATA", newId);
208 atts = newAttrs;
209 }
210 }
211 super.startElement(namespaceURI, localName, qName, atts);
212 }
213
214 private String generateSectionId() {
215 String result = "s" + ++sectionCounter;
216 while (existingIds.contains(result)) {
217 result = "s" + ++sectionCounter;
218 }
219 return result;
220 }
221
222 private String generateFigureId() {
223 String result = "dsy_fig_" + ++figureCounter;
224 while (existingIds.contains(result)) {
225 result = "dsy_fig_" + ++figureCounter;
226 }
227 return result;
228 }
229
230 private String generateTableId() {
231 String result = "dsy_tbl_" + ++tableCounter;
232 while (existingIds.contains(result)) {
233 result = "dsy_tbl_" + ++tableCounter;
234 }
235 return result;
236 }
237 }
238
239 static class LinkLog {
240 private PrintWriter pw;
241
242 public LinkLog(BookInstance bookInstance) throws Exception {
243 OutputStream os = bookInstance.getResourceOutputStream(BookInstanceLayout.getLinkLogPath());
244 pw = new PrintWriter (os);
245 pw.println("If this file is empty, then no link errors were detected.");
246 }
247
248 public void dispose() {
249 if (pw != null)
250 pw.close();
251 }
252
253 public void error(String message) {
254 pw.println(message);
255 pw.flush();
256 }
257 }
258 }
259 |
Popular Tags |
Java API By Example, From Geeks To Geeks.