diff options
| author | luccioman <luccioman@users.noreply.github.com> | 2017-11-06 09:14:03 +0100 |
|---|---|---|
| committer | luccioman <luccioman@users.noreply.github.com> | 2017-11-06 09:14:03 +0100 |
| commit | 73977ec0fe40cd92a741f38b95e78292b9fdf10b (patch) | |
| tree | 1f5fd32b3396e3f561d8e8110895a9365f9e41dc /test | |
| parent | d14c47d4d35dc2469cf2033ba619b77e318ab688 (diff) | |
Added a html parser charset detection unit test
Diffstat (limited to 'test')
| -rw-r--r-- | test/java/net/yacy/document/parser/htmlParserTest.java | 39 |
1 files changed, 37 insertions, 2 deletions
diff --git a/test/java/net/yacy/document/parser/htmlParserTest.java b/test/java/net/yacy/document/parser/htmlParserTest.java index 8d0f1a4f9..e6b67bd35 100644 --- a/test/java/net/yacy/document/parser/htmlParserTest.java +++ b/test/java/net/yacy/document/parser/htmlParserTest.java @@ -98,11 +98,46 @@ public class htmlParserTest extends TestCase { inStream.close(); } } - - } } + /** + * Test the htmlParser.parse() method, with no charset information, neither + * provided by HTTP header nor by meta tags or attributes. + * + * @throws Exception + * when an unexpected error occurred + */ + @Test + public void testParseHtmlWithoutCharset() throws Exception { + final AnchorURL url = new AnchorURL("http://localhost/test.html"); + final String mimetype = "text/html"; + final StringBuilder testHtml = new StringBuilder("<!DOCTYPE html><html><body><p>"); + /* + * Include some non ASCII characters : once encoded they should make the charset + * detector to detect the exact encoding + */ + testHtml.append("In München steht ein Hofbräuhaus.\n" + "Dort gibt es Bier aus Maßkrügen.<br>"); + testHtml.append("<a href=\"http://localhost/doc1.html\">First link</a>"); + testHtml.append("<a href=\"http://localhost/doc2.html\">Second link</a>"); + testHtml.append("<a href=\"http://localhost/doc3.html\">Third link</a>"); + testHtml.append("</p></body></html>"); + + final htmlParser parser = new htmlParser(); + + final Charset[] charsets = new Charset[] { StandardCharsets.UTF_8, StandardCharsets.ISO_8859_1 }; + + for (final Charset charset : charsets) { + try (InputStream sourceStream = new ByteArrayInputStream(testHtml.toString().getBytes(charset));) { + final Document[] docs = parser.parse(url, mimetype, null, new VocabularyScraper(), 0, sourceStream); + final Document doc = docs[0]; + assertEquals(3, doc.getAnchors().size()); + assertTrue(doc.getTextString().contains("Maßkrügen")); + assertEquals(charset.toString(), doc.getCharset()); + } + } + } + /** * Test the htmlParser.parseWithLimits() method with test content within bounds. * @throws Exception when an unexpected error occurred |