1
|
/**
|
2
|
* '$RCSfile$'
|
3
|
* Purpose: A Class that transforms an XML text document
|
4
|
* into a another type using XSL
|
5
|
* Copyright: 2000 Regents of the University of California and the
|
6
|
* National Center for Ecological Analysis and Synthesis
|
7
|
* Authors: Matt Jones
|
8
|
*
|
9
|
* '$Author: leinfelder $'
|
10
|
* '$Date: 2010-12-21 14:26:06 -0800 (Tue, 21 Dec 2010) $'
|
11
|
* '$Revision: 5752 $'
|
12
|
*
|
13
|
* This program is free software; you can redistribute it and/or modify
|
14
|
* it under the terms of the GNU General Public License as published by
|
15
|
* the Free Software Foundation; either version 2 of the License, or
|
16
|
* (at your option) any later version.
|
17
|
*
|
18
|
* This program is distributed in the hope that it will be useful,
|
19
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
20
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
21
|
* GNU General Public License for more details.
|
22
|
*
|
23
|
* You should have received a copy of the GNU General Public License
|
24
|
* along with this program; if not, write to the Free Software
|
25
|
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
26
|
*/
|
27
|
|
28
|
package edu.ucsb.nceas.metacat;
|
29
|
|
30
|
import java.io.File;
|
31
|
import java.io.FileInputStream;
|
32
|
import java.io.FileNotFoundException;
|
33
|
import java.io.IOException;
|
34
|
import java.io.OutputStreamWriter;
|
35
|
import java.io.StringReader;
|
36
|
import java.io.StringWriter;
|
37
|
import java.io.Writer;
|
38
|
import java.sql.SQLException;
|
39
|
import java.util.Enumeration;
|
40
|
import java.util.Hashtable;
|
41
|
import java.util.Iterator;
|
42
|
import java.util.Map;
|
43
|
|
44
|
import javax.xml.transform.TransformerFactory;
|
45
|
import javax.xml.transform.Transformer;
|
46
|
import javax.xml.transform.stream.StreamSource;
|
47
|
import javax.xml.transform.stream.StreamResult;
|
48
|
|
49
|
import org.apache.log4j.Logger;
|
50
|
import org.apache.xerces.parsers.DOMParser;
|
51
|
import org.w3c.dom.NamedNodeMap;
|
52
|
import org.w3c.dom.NodeList;
|
53
|
import org.w3c.dom.Document;
|
54
|
import org.w3c.dom.Node;
|
55
|
import org.xml.sax.InputSource;
|
56
|
import org.apache.xpath.XPathAPI;
|
57
|
|
58
|
import edu.ucsb.nceas.metacat.properties.PropertyService;
|
59
|
import edu.ucsb.nceas.metacat.properties.SkinPropertyService;
|
60
|
import edu.ucsb.nceas.metacat.util.SystemUtil;
|
61
|
import edu.ucsb.nceas.utilities.PropertyNotFoundException;
|
62
|
import edu.ucsb.nceas.utilities.SortedProperties;
|
63
|
|
64
|
/**
|
65
|
* A Class that transforms XML documents utitlizing XSL style sheets
|
66
|
*/
|
67
|
public class DBTransform {
|
68
|
|
69
|
// private Connection conn = null;
|
70
|
// private MetacatUtil util = null;
|
71
|
private String configDir = null;
|
72
|
private String defaultStyle = null;
|
73
|
private Logger logMetacat = Logger.getLogger(DBTransform.class);
|
74
|
private String httpServer = null;
|
75
|
private String contextURL = null;
|
76
|
private String servletURL = null;
|
77
|
|
78
|
/**
|
79
|
* construct a DBTransform instance.
|
80
|
*
|
81
|
* Generally, one calls transformXMLDocument() after constructing the instance
|
82
|
*
|
83
|
* @param conn the database connection from which to lookup the public ids
|
84
|
*/
|
85
|
public DBTransform()
|
86
|
throws IOException,
|
87
|
SQLException,
|
88
|
ClassNotFoundException,
|
89
|
PropertyNotFoundException
|
90
|
{
|
91
|
configDir = SystemUtil.getStyleSkinsDir();
|
92
|
defaultStyle = PropertyService.getProperty("application.default-style");
|
93
|
httpServer = SystemUtil.getServerURL();
|
94
|
contextURL = SystemUtil.getContextURL();
|
95
|
servletURL = SystemUtil.getServletURL();
|
96
|
}
|
97
|
|
98
|
/**
|
99
|
* Transform an XML document using the stylesheet reference from the db
|
100
|
*
|
101
|
* @param doc the document to be transformed
|
102
|
* @param sourcetype the document type of the source
|
103
|
* @param targettype the target document type
|
104
|
* @param qformat the name of the style set to use
|
105
|
* @param pw the PrintWriter to which output is printed
|
106
|
* @param params some parameters for eml2 transformation
|
107
|
*/
|
108
|
public void transformXMLDocument(String doc, String sourceType,
|
109
|
String targetType, String qformat,
|
110
|
Writer w, Hashtable<String, String[]> param,
|
111
|
String sessionid)
|
112
|
{
|
113
|
|
114
|
String xslSystemId = getStyleSystemId(qformat, sourceType, targetType);
|
115
|
try {
|
116
|
// Look up the stylesheet for this type combination
|
117
|
if (xslSystemId != null) {
|
118
|
// Create a stylesheet from the system id that was found
|
119
|
doc = removeDOCTYPE(doc);
|
120
|
StringReader xml = new StringReader(doc);
|
121
|
StreamResult result = new StreamResult(w);
|
122
|
doTransform(xml, result, xslSystemId, param, qformat, sessionid);
|
123
|
}
|
124
|
else {
|
125
|
// No stylesheet registered form this document type, so just return the
|
126
|
// XML stream we were passed
|
127
|
w.write(doc);
|
128
|
}
|
129
|
}
|
130
|
catch (Exception e)
|
131
|
{
|
132
|
try {
|
133
|
w.write(xslSystemId + ": Error transforming document in " +
|
134
|
"DBTransform.transformXMLDocument: " +
|
135
|
e.getMessage());
|
136
|
} catch (IOException e1) {
|
137
|
logMetacat.error(e1.getMessage(), e1);
|
138
|
}
|
139
|
|
140
|
}
|
141
|
|
142
|
}
|
143
|
|
144
|
/**
|
145
|
* Transform an XML document to StringWriter using the stylesheet reference
|
146
|
* from the db
|
147
|
* @param doc the document to be transformed
|
148
|
* @param sourceType the document type of the source
|
149
|
* @param targetType the target document type
|
150
|
* @param qFormat the name of the style set to use
|
151
|
* @param pw the StringWriter to which output will be stored
|
152
|
*/
|
153
|
public void transformXMLDocument(String doc, String sourceType,
|
154
|
String targetType, String qFormat, StringWriter pw,
|
155
|
Hashtable<String, String[]> param, String sessionid)
|
156
|
{
|
157
|
|
158
|
// Look up the stylesheet for this type combination
|
159
|
String xslSystemId = getStyleSystemId(qFormat, sourceType, targetType);
|
160
|
if (xslSystemId != null)
|
161
|
{
|
162
|
// Create a stylesheet from the system id that was found
|
163
|
try
|
164
|
{
|
165
|
doc = removeDOCTYPE(doc);
|
166
|
StringReader xml = new StringReader(doc);
|
167
|
StreamResult result = new StreamResult(pw);
|
168
|
doTransform(xml, result, xslSystemId, param, qFormat, sessionid);
|
169
|
}
|
170
|
catch (Exception e)
|
171
|
{
|
172
|
logMetacat.error("DBTransform.transformXMLDocument - " + xslSystemId + ": Error transforming document in " +
|
173
|
"DBTransform.transformXMLDocument: " +
|
174
|
e.getMessage());
|
175
|
|
176
|
}
|
177
|
}
|
178
|
else
|
179
|
{
|
180
|
// No stylesheet registered form this document type, so just return the
|
181
|
// XML stream we were passed
|
182
|
pw.write(doc);
|
183
|
}
|
184
|
}
|
185
|
|
186
|
|
187
|
/**
|
188
|
* Reads skin's config file if it exists, and populates Transformer paramaters
|
189
|
* with its contents.
|
190
|
* It then adds the parameters passed to it via Hashtable param to the Transformer.
|
191
|
* It then calls the Transformer.transform method.
|
192
|
*/
|
193
|
private void doTransform(StringReader docContent,
|
194
|
StreamResult resultOutput,
|
195
|
String xslSystemId,
|
196
|
Hashtable<String, String[]> param,
|
197
|
String qformat,
|
198
|
String sessionid)
|
199
|
throws Exception {
|
200
|
|
201
|
SortedProperties skinOptions;
|
202
|
TransformerFactory tFactory;
|
203
|
Transformer transformer;
|
204
|
String key, value;
|
205
|
StreamSource xml;
|
206
|
Enumeration<String> en;
|
207
|
Iterator<Map.Entry<String, String>> iterIt;
|
208
|
Map.Entry<String, String> entry;
|
209
|
|
210
|
if (xslSystemId != null) {
|
211
|
tFactory = TransformerFactory.newInstance();
|
212
|
transformer = tFactory.newTransformer(new StreamSource(xslSystemId));
|
213
|
|
214
|
transformer.setParameter("qformat", qformat);
|
215
|
logMetacat.info("DBTransform.doTransform - qformat: " + qformat);
|
216
|
|
217
|
skinOptions = SkinPropertyService.getProperties(qformat);
|
218
|
if (skinOptions != null) {
|
219
|
iterIt = skinOptions.getProperties().entrySet().iterator();
|
220
|
while (iterIt.hasNext()) {
|
221
|
entry = iterIt.next();
|
222
|
key = entry.getKey();
|
223
|
value = entry.getValue();
|
224
|
//only include the plain properties
|
225
|
if (key.indexOf('.') == -1) {
|
226
|
transformer.setParameter(key, value);
|
227
|
}
|
228
|
}
|
229
|
}
|
230
|
|
231
|
if (sessionid != null && !sessionid.equals("null")) {
|
232
|
transformer.setParameter("sessid", sessionid);
|
233
|
}
|
234
|
|
235
|
//set up the default params (can be overridden by the passed in params)
|
236
|
String cgiPrefix = SystemUtil.getCGI_URL();
|
237
|
logMetacat.debug("DBTransform.doTransform - cgi-prefix: " + cgiPrefix);
|
238
|
logMetacat.debug("DBTransform.doTransform - httpServer: " + httpServer);
|
239
|
logMetacat.debug("DBTransform.doTransform - contextURL: " + contextURL);
|
240
|
logMetacat.debug("DBTransform.doTransform - serletURL: " + servletURL);
|
241
|
transformer.setParameter("cgi-prefix", cgiPrefix);
|
242
|
transformer.setParameter("httpServer", httpServer);
|
243
|
transformer.setParameter("contextURL", contextURL);
|
244
|
transformer.setParameter("servletURL", servletURL);
|
245
|
|
246
|
// Set up parameter for transformation
|
247
|
if ( param != null) {
|
248
|
en = param.keys();
|
249
|
while (en.hasMoreElements()) {
|
250
|
key = en.nextElement();
|
251
|
value = (param.get(key))[0];
|
252
|
logMetacat.info("DBTransform.doTransform - param: " + key + " -- " + value);
|
253
|
transformer.setParameter(key, value);
|
254
|
}
|
255
|
}
|
256
|
xml = new StreamSource(docContent);
|
257
|
transformer.transform(xml,resultOutput);
|
258
|
}
|
259
|
}//doTransform
|
260
|
|
261
|
|
262
|
/**
|
263
|
* gets the content of a tag in a given xml file with the given path
|
264
|
* @param f the file to parse
|
265
|
* @param path the path to get the content from
|
266
|
*/
|
267
|
public static NodeList getPathContent(File f, String path)
|
268
|
{
|
269
|
if(f == null)
|
270
|
{
|
271
|
return null;
|
272
|
}
|
273
|
|
274
|
DOMParser parser = new DOMParser();
|
275
|
InputSource in;
|
276
|
FileInputStream fs;
|
277
|
|
278
|
try
|
279
|
{
|
280
|
fs = new FileInputStream(f);
|
281
|
in = new InputSource(fs);
|
282
|
}
|
283
|
catch(FileNotFoundException fnf)
|
284
|
{
|
285
|
fnf.printStackTrace();
|
286
|
return null;
|
287
|
}
|
288
|
|
289
|
try
|
290
|
{
|
291
|
parser.parse(in);
|
292
|
fs.close();
|
293
|
}
|
294
|
catch(Exception e1)
|
295
|
{
|
296
|
System.err.println("File: " + f.getPath() + " : parse threw: " +
|
297
|
e1.toString());
|
298
|
return null;
|
299
|
}
|
300
|
|
301
|
Document doc = parser.getDocument();
|
302
|
|
303
|
try
|
304
|
{
|
305
|
NodeList docNodeList = XPathAPI.selectNodeList(doc, path);
|
306
|
return docNodeList;
|
307
|
}
|
308
|
catch(Exception se)
|
309
|
{
|
310
|
System.err.println("file: " + f.getPath() + " : parse threw: " +
|
311
|
se.toString());
|
312
|
return null;
|
313
|
}
|
314
|
}
|
315
|
|
316
|
/**
|
317
|
* Lookup a stylesheet reference from the db catalog
|
318
|
*
|
319
|
* @param qformat the named style-set format
|
320
|
* @param sourcetype the document type of the source
|
321
|
* @param targettype the document type of the target
|
322
|
*/
|
323
|
public String getStyleSystemId(String qformat, String sourcetype,
|
324
|
String targettype) {
|
325
|
String systemId = null;
|
326
|
|
327
|
if ((qformat == null) || (qformat.equals("html"))) {
|
328
|
qformat = defaultStyle;
|
329
|
}
|
330
|
|
331
|
// Load the style-set map for this qformat into a DOM
|
332
|
try {
|
333
|
boolean breakflag = false;
|
334
|
String filename = configDir + "/" + qformat + "/" + qformat + ".xml";
|
335
|
logMetacat.info("DBTransform.getStyleSystemId - Trying style-set file: " + filename);
|
336
|
File f = new File(filename);
|
337
|
NodeList nlDoctype = getPathContent(f, "/style-set/doctype");
|
338
|
NodeList nlDefault = getPathContent(f, "/style-set/default-style");
|
339
|
Node nDefault = nlDefault.item(0);
|
340
|
systemId = nDefault.getFirstChild().getNodeValue(); //set the default
|
341
|
|
342
|
for(int i=0; i<nlDoctype.getLength(); i++)
|
343
|
{ //look for the right sourcetype
|
344
|
Node nDoctype = nlDoctype.item(i);
|
345
|
NamedNodeMap atts = nDoctype.getAttributes();
|
346
|
Node nAtt = atts.getNamedItem("publicid");
|
347
|
String doctype = nAtt.getFirstChild().getNodeValue();
|
348
|
if(doctype.equals(sourcetype))
|
349
|
{ //found the right sourcetype now we need to get the target type
|
350
|
NodeList nlChildren = nDoctype.getChildNodes();
|
351
|
for(int j=0; j<nlChildren.getLength(); j++)
|
352
|
{
|
353
|
Node nChild = nlChildren.item(j);
|
354
|
String childName = nChild.getNodeName();
|
355
|
if(childName.equals("target"))
|
356
|
{
|
357
|
NamedNodeMap childAtts = nChild.getAttributes();
|
358
|
Node nTargetPublicId = childAtts.getNamedItem("publicid");
|
359
|
String target = nTargetPublicId.getFirstChild().getNodeValue();
|
360
|
if(target.equals(targettype))
|
361
|
{ //we found the right target type
|
362
|
NodeList nlTarget = nChild.getChildNodes();
|
363
|
for(int k=0; k<nlTarget.getLength(); k++)
|
364
|
{
|
365
|
Node nChildText = nlTarget.item(k);
|
366
|
if(nChildText.getNodeType() == Node.TEXT_NODE)
|
367
|
{ //get the text from the target node
|
368
|
systemId = nChildText.getNodeValue();
|
369
|
breakflag = true;
|
370
|
break;
|
371
|
}
|
372
|
}
|
373
|
}
|
374
|
}
|
375
|
|
376
|
if(breakflag)
|
377
|
{
|
378
|
break;
|
379
|
}
|
380
|
}
|
381
|
}
|
382
|
|
383
|
if(breakflag)
|
384
|
{
|
385
|
break;
|
386
|
}
|
387
|
}
|
388
|
}
|
389
|
catch(Exception e)
|
390
|
{
|
391
|
System.out.println("Error parsing style-set file: " + e.getMessage());
|
392
|
e.printStackTrace();
|
393
|
}
|
394
|
|
395
|
//Check if the systemId is relative path, add a postfix - the contextULR to systemID.
|
396
|
if (systemId != null && systemId.indexOf("http://" ) == -1)
|
397
|
{
|
398
|
systemId = contextURL+systemId;
|
399
|
}
|
400
|
// Return the system ID for this particular source document type
|
401
|
logMetacat.info("DBTransform.getStyleSystemId - style system id is: " + systemId);
|
402
|
return systemId;
|
403
|
}
|
404
|
|
405
|
// /* Method to modified the system id of xml input -- make sure it
|
406
|
// points to system id in xml_catalog table
|
407
|
// */
|
408
|
// private void modifiedXmlStreamSource(StreamSource xml, String publicId)
|
409
|
// throws Exception
|
410
|
// {
|
411
|
// // make sure the xml is not null
|
412
|
// if (xml == null || publicId == null)
|
413
|
// {
|
414
|
// return;
|
415
|
// }
|
416
|
// logMetacat.info("public id of input stream is " +publicId);
|
417
|
// // Get system id from xml_catalog table
|
418
|
// String systemId = DBEntityResolver.getDTDSystemID(publicId);
|
419
|
// logMetacat.info("system id of input stream from xml_catalog"
|
420
|
// +"table is " +systemId);
|
421
|
// //set system id to input stream
|
422
|
// xml.setSystemId(systemId);
|
423
|
// }
|
424
|
|
425
|
/*
|
426
|
* removes the DOCTYPE element and its contents from a Sting
|
427
|
* used to avoid problems with incorrect SystemIDs
|
428
|
*/
|
429
|
private String removeDOCTYPE(String in) {
|
430
|
String ret = "";
|
431
|
int startpos = in.indexOf("<!DOCTYPE");
|
432
|
if (startpos>-1) {
|
433
|
int stoppos = in.indexOf(">", startpos + 8);
|
434
|
ret = in.substring(0,startpos) + in.substring(stoppos+1,in.length());
|
435
|
} else {
|
436
|
return in;
|
437
|
}
|
438
|
return ret;
|
439
|
}
|
440
|
|
441
|
/**
|
442
|
* the main routine used to test the transform utility.
|
443
|
*
|
444
|
* Usage: java DBTransform
|
445
|
*/
|
446
|
static public void main(String[] args) {
|
447
|
|
448
|
if (args.length > 0)
|
449
|
{
|
450
|
System.err.println("Wrong number of arguments!!!");
|
451
|
System.err.println("USAGE: java DBTransform");
|
452
|
return;
|
453
|
} else {
|
454
|
try {
|
455
|
|
456
|
// Create a test document
|
457
|
StringBuffer testdoc = new StringBuffer();
|
458
|
String encoding = "UTF-8";
|
459
|
testdoc.append("<?xml version=\"1.0\" encoding=\"" + encoding + "\"?>");
|
460
|
testdoc.append("<eml-dataset><metafile_id>NCEAS-0001</metafile_id>");
|
461
|
testdoc.append("<dataset_id>DS001</dataset_id>");
|
462
|
testdoc.append("<title>My test doc</title></eml-dataset>");
|
463
|
|
464
|
// Transform the document to the new doctype
|
465
|
Writer w = new OutputStreamWriter(System.out, encoding);
|
466
|
DBTransform dbt = new DBTransform();
|
467
|
dbt.transformXMLDocument(testdoc.toString(),
|
468
|
"-//NCEAS//eml-dataset//EN",
|
469
|
"-//W3C//HTML//EN",
|
470
|
"knb",
|
471
|
w, null, null);
|
472
|
|
473
|
} catch (Exception e) {
|
474
|
System.err.println("EXCEPTION HANDLING REQUIRED");
|
475
|
System.err.println(e.getMessage());
|
476
|
e.printStackTrace(System.err);
|
477
|
}
|
478
|
}
|
479
|
}
|
480
|
|
481
|
// private void dbg(int position) {
|
482
|
// System.err.println("Debug flag: " + position);
|
483
|
// }
|
484
|
|
485
|
}
|