Skip to content

close document for TestPDFText2HTML #396

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
valerybokov wants to merge 1 commit into from
Closed

close document for TestPDFText2HTML #396

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 17 additions & 13 deletions tools/src/test/java/org/apache/pdfbox/tools/TestPDFText2HTML.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,25 +55,29 @@ private PDDocument createDocument(String title, PDFont font, String text) throws
void testEscapeTitle() throws IOException
{
PDFTextStripper stripper = new PDFText2HTML();
PDDocument doc = createDocument("<script>\u3042", new PDType1Font(FontName.HELVETICA),
"<foo>");
String text = stripper.getText(doc);

Matcher m = Pattern.compile("<title>(.*?)</title>").matcher(text);
assertTrue(m.find());
assertEquals("&lt;script&gt;&#12354;", m.group(1));
assertTrue(text.contains("&lt;foo&gt;"));
try(PDDocument doc = createDocument("<script>\u3042", new PDType1Font(FontName.HELVETICA),
"<foo>"))
{
String text = stripper.getText(doc);

Matcher m = Pattern.compile("<title>(.*?)</title>").matcher(text);
assertTrue(m.find());
assertEquals("&lt;script&gt;&#12354;", m.group(1));
assertTrue(text.contains("&lt;foo&gt;"));
}
}

@Test
void testStyle() throws IOException
{
PDFTextStripper stripper = new PDFText2HTML();
PDDocument doc = createDocument("t", new PDType1Font(FontName.HELVETICA_BOLD), "<bold>");
String text = stripper.getText(doc);
try(PDDocument doc = createDocument("t", new PDType1Font(FontName.HELVETICA_BOLD), "<bold>"))
{
String text = stripper.getText(doc);

Matcher bodyMatcher = Pattern.compile("<p>(.*?)</p>").matcher(text);
assertTrue(bodyMatcher.find(), "body p exists");
assertEquals("<b>&lt;bold&gt;</b>", bodyMatcher.group(1), "body p");
Matcher bodyMatcher = Pattern.compile("<p>(.*?)</p>").matcher(text);
assertTrue(bodyMatcher.find(), "body p exists");
assertEquals("<b>&lt;bold&gt;</b>", bodyMatcher.group(1), "body p");
}
}
}