This is an automated email from the ASF dual-hosted git repository. nick pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/tika.git
commit 90720aed2836da7114f6495d61e12fd9af01d4fc Author: Nick Burch <[email protected]> AuthorDate: Thu May 3 18:58:14 2018 +0100 SAS7BDAT html tests --- .../org/apache/tika/parser/sas/SAS7BDATParser.java | 5 ++++- .../org/apache/tika/parser/sas/SAS7BDATParserTest.java | 18 +++++++++++++++++- 2 files changed, 21 insertions(+), 2 deletions(-) diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/sas/SAS7BDATParser.java b/tika-parsers/src/main/java/org/apache/tika/parser/sas/SAS7BDATParser.java index 56260ca..121d958 100644 --- a/tika-parsers/src/main/java/org/apache/tika/parser/sas/SAS7BDATParser.java +++ b/tika-parsers/src/main/java/org/apache/tika/parser/sas/SAS7BDATParser.java @@ -119,8 +119,11 @@ public class SAS7BDATParser extends AbstractParser { // Do the column headings xhtml.startElement("tr"); for (Column c : sas.getColumns()) { + String label = c.getLabel(); + if (label == null || label.isEmpty()) label = c.getName(); + xhtml.startElement("th", "title", c.getName()); - xhtml.characters(c.getLabel()); + xhtml.characters(label); xhtml.endElement("th"); } xhtml.endElement("tr"); diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/sas/SAS7BDATParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/sas/SAS7BDATParserTest.java index c2a74a7..37be73b 100644 --- a/tika-parsers/src/test/java/org/apache/tika/parser/sas/SAS7BDATParserTest.java +++ b/tika-parsers/src/test/java/org/apache/tika/parser/sas/SAS7BDATParserTest.java @@ -118,6 +118,22 @@ public class SAS7BDATParserTest extends TikaTest { assertContains("\t08Feb1904\t", content); } - // TODO HTML contents unit test + @Test + public void testHTML() throws Exception { + XMLResult result = getXML("testSAS.sas7bdat"); + String xml = result.xml; + + // Check the title came through + assertContains("<h1>TESTING</h1>", xml); + // Check the headings + assertContains("<th title=\"recnum\">recnum</th>", xml); + assertContains("<th title=\"label\">label</th>", xml); + // Check some rows + assertContains("<td>3</td>", xml); + assertContains("<td>This is row", xml); + assertContains("10</td>", xml); + } + // TODO Column names vs labels, with a different test file + // TODO Columnar consistency test } -- To stop receiving notification emails like this one, please contact [email protected].
