/test/edu/ucsb/nceas/metacattest/NonAsciiCharacterTest.java - Diff - Metacat - Ecoinformatics Redmine

« Previous | Next »

Revision 5752

Added by ben leinfelder over 13 years ago

use detected XML encoding when reading/writing files
use UTF-8 as default when performing queries in the DB (assume DB is using UTF-8)
remove as many PrintWriters (uses system default character encoding only) as possible and construct OutputStreamWriters where explicit encoding can be given.
http://bugzilla.ecoinformatics.org/show_bug.cgi?id=2495

     import edu.ucsb.nceas.metacat.client.MetacatFactory;
     import edu.ucsb.nceas.metacat.client.MetacatInaccessibleException;
     import edu.ucsb.nceas.metacat.properties.PropertyService;
     import edu.ucsb.nceas.utilities.FileUtil;
     import edu.ucsb.nceas.utilities.IOUtil;
     import edu.ucsb.nceas.utilities.PropertyNotFoundException;
     import junit.framework.Test;
-...
         /**
          * Returns an xml squery that searches for the doc id in the
          * title of documents. This function is for eml-2.0.1 only. For
          * title of documents. This function is for eml-2.0.1+ only. For
          * other eml versions, this function might have to modified.
          */
         private String getTestEmlQuery(String docid, String emlVersion) {
         private String getTestEmlQuery(String titlePart, String emlVersion) {
         	String docType;
         	if (emlVersion.equals(EML2_0_1)) {
-...
             		"<returndoctype>" + docType + "</returndoctype>" +
             		"<querygroup operator=\"UNION\">" +
             			"<queryterm casesensitive=\"false\" searchmode=\"contains\">" +
             				"<value>" + docid + "</value>" +
             				"<value>" + titlePart + "</value>" +
             				"<pathexpr>dataset/title</pathexpr>" +
             			"</queryterm>" +
             		"</querygroup>" +
-...
             suite.addTest(new NonAsciiCharacterTest("quote210Test"));
             suite.addTest(new NonAsciiCharacterTest("numericCharacterReferenceFormat201Test"));
             suite.addTest(new NonAsciiCharacterTest("numericCharacterReferenceFormat210Test"));*/
             suite.addTest(new NonAsciiCharacterTest("nonLatinUnicodeCharacter201Test"));
             //suite.addTest(new NonAsciiCharacterTest("nonLatinUnicodeCharacter201Test"));
             //suite.addTest(new NonAsciiCharacterTest("nonLatinUnicodeCharacter210Test"));
             suite.addTest(new NonAsciiCharacterTest("unicodeCharacterTest"));
             return suite;
+        }
-...
          * Test inserting and reading an EML 2.0.1 document with the code representation
          * of a micro sign (&#181). Read should succeed since the same document should be
          * read back from disk that was submitted.  Query should succeed because we look
          * for the converted character (¬µ).
          * for the converted character (µ).
          */
         public void numericCharacterReferenceFormat201Test() {
         	debug("\nRunning: numericCharacterReferenceFormat201Test");
-...
                 m.login(username, password);
                 String testTitle = "Checking &#181; in doc: " + newdocid  + ".1";
                 String convertedTestTitle = "Checking ¬µ in doc: " + newdocid  + ".1";
                 String convertedTestTitle = "Checking µ in doc: " + newdocid  + ".1";
                 testdocument = getTestEmlDoc(testTitle, EML2_0_1);
                 insertDocid(newdocid + ".1", testdocument, SUCCESS, true);
-...
          * Test inserting and reading an EML 2.1.0 document with the code representation
          * of a micro sign (&#181). Read should succeed since the same document should be
          * read back from disk that was submitted.  Query should succeed because we look
          * for the converted character (¬µ).
          * for the converted character (µ).
          */
         public void numericCharacterReferenceFormat210Test() {
         	debug("\nRunning: numericCharacterReferenceFormat210Test");
-...
                 m.login(username, password);
                 String testTitle = "Checking &#181; in doc: " + newdocid  + ".1";
                 String convertedTestTitle = "Checking ¬µ in doc: " + newdocid  + ".1";
                 String convertedTestTitle = "Checking µ in doc: " + newdocid  + ".1";
                 testdocument = getTestEmlDoc(testTitle, EML2_1_0);
                 insertDocid(newdocid + ".1", testdocument, SUCCESS, true);
-...
+        }
         /**
          * Test inserting and reading an EML 2.0.1 document with the micro sign (¬µ).
          * Test inserting and reading an EML 2.0.1 document with the micro sign (µ).
          * Read should succeed since the same document should be read back from disk
          * that was submitted.  Query should succeed because we look for the same
          * character (¬µ).
          * character (µ).
          */
         public void nonLatinUnicodeCharacter201Test() {
         	debug("\nRunning: nonLatinUnicodeCharacter201Test");
-...
                 String testTitle = "Checking characters like µ in doc: " + newdocid  + ".1";
                 testdocument = getTestEmlDoc(testTitle, EML2_0_1);
                 debug("original test document:	" + testdocument);
                 insertDocid(newdocid + ".1", testdocument, SUCCESS, false);
                 // this tests reading the document back from disk
-...
                 String newdocid = generateDocid();
                 m.login(username, password);
                 String testTitle = "Checking characters like ¬µ in doc: " + newdocid  + ".1";
                 String testTitle = "Checking characters like µ in doc: " + newdocid  + ".1";
                 testdocument = getTestEmlDoc(testTitle, EML2_1_0);
                 insertDocid(newdocid + ".1", testdocument, SUCCESS, false);
-...
                 fail("General exception:\n" + e.getMessage());
+            }
+        }
         /**
          * Test inserting and reading an EML 2.1.0 with Chinese
          */
         public void unicodeCharacterTest() {
         	debug("\nRunning: unicodeCharacterTest");
             try {
             	String filePath = "test/clienttestfiles/unicodeEML.xml";
                 String testTitle = "測試中的數據包 (Test Chinese data package) _DOCID_";
                 String newdocid = generateDocid() + ".1";
                 testdocument = FileUtil.readFileToString(filePath, "UTF-8");
                 // include the docid
                 testdocument = testdocument.replaceAll("_DOCID_", newdocid);
                 testTitle = testTitle.replaceAll("_DOCID_", newdocid);
                 // login
                 m.login(username, password);
                 // insert
                 insertDocid(newdocid, testdocument, SUCCESS, false);
                 // this tests reading the document back from disk
                 readDocidWhichEqualsDoc(newdocid, testdocument, SUCCESS, true);
                 // this tests searching for the document in the database
                 Thread.sleep(3000);
                 queryDocWhichHasTitle(testTitle, testTitle, EML2_1_0, SUCCESS);
                 // clean up
                 //deleteDocid(newdocid, SUCCESS, false);
                 m.logout();
+            }
             catch (MetacatAuthException mae) {
                 fail("Authorization failed:\n" + mae.getMessage());
+            }
             catch (MetacatInaccessibleException mie) {
                 fail("Metacat Inaccessible:\n" + mie.getMessage());
+            }
             catch (Exception e) {
                 fail("General exception:\n" + e.getMessage());
+            }
+        }
         /**
          * Insert a document into metacat. The expected result is passed as result
          */
-...
                                    boolean expectMetacatException) {
             String response = null;
             try {
             	debug("doctext: " + docText);
                 response = m.insert(docid,
                                     new StringReader(docText), null);
                 System.err.println(response);
-...
+        }
         /**
          * Query a document by looking for it's doc id in the title element.
          * Query a document by looking for a part of the title in the title element.
          * Then check if the testTitle exists in the doc.
          * @param docId the id of the doc to look for
          * @param titlePart the part of the title of the doc to look for
          * @param testTitle the title containing special characters
          * @param result are we expecting SUCCESS or FAILURE
          * @param expextedKarmaFailure
          */
         private void queryDocWhichHasTitle(String docId, String testTitle,
         private void queryDocWhichHasTitle(String titlePart, String testTitle,
                                              String emlVersion, boolean result) {
             try {
                 String sQuery = getTestEmlQuery(docId, emlVersion);
                 String sQuery = getTestEmlQuery(titlePart, emlVersion);
             	Reader queryReader = new StringReader(sQuery);
                 Reader resultReader = m.query(queryReader);
                 String queryResult = IOUtil.getAsString(resultReader, true);

Also available in: Unified diff

Project

General

Profile

Metacat

Revision 5752

Added by ben leinfelder over 13 years ago