Add PDF test and fix page number.

linkcheck/plugins/parsepdf.py

@@ -44,6 +44,9 @@ def search_url(obj, url_data, pageno, seen_objs):
     if isinstance(obj, dict):
         for key, value in obj.items():
             if key == 'URI' and isinstance(value, basestring):
+                # URIs should be 7bit ASCII encoded, but be safe and encode
+                # to unicode
+                # XXX this does not use an optional specified base URL
                 url = strformat.unicode_safe(value)
                 url_data.add_url(url, page=pageno)
             else:
@@ -78,7 +81,7 @@ class PdfParser(_ParserPlugin):
         try:
             parser = PDFParser(fp)
             doc = PDFDocument(parser, password=password)
-            for (pageno, page) in enumerate(PDFPage.create_pages(doc)):
+            for (pageno, page) in enumerate(PDFPage.create_pages(doc), start=1):
                 if "Contents" in page.attrs:
                     search_url(page.attrs["Contents"], url_data, pageno, set())
                 if "Annots" in page.attrs:

tests/__init__.py

@@ -249,6 +249,14 @@ def has_word():
 need_word = _need_func(has_word, 'Word')
 
 
+@memoized
+def has_pdflib():
+    from linkcheck.plugins import parsepdf
+    return parsepdf.has_pdflib
+
+need_pdflib = _need_func(has_pdflib, 'pdflib')
+
+
 @contextmanager
 def _limit_time (seconds):
     """Raises LinkCheckerInterrupt if given number of seconds have passed."""

tests/checker/data/file.pdf.result

@@ -0,0 +1,15 @@
+url file://%(curdir)s/%(datadir)s/file.pdf
+cache key file://%(curdir)s/%(datadir)s/file.pdf
+real url file://%(curdir)s/%(datadir)s/file.pdf
+name %(datadir)s/file.pdf
+valid
+
+url http://www.example.com/link1
+cache key http://www.example.com/link1
+real url http://www.example.com/link1
+error
+
+url http://www.example.com/link2
+cache key http://www.example.com/link2
+real url http://www.example.com/link2
+error

tests/checker/test_file.py

@@ -20,7 +20,7 @@ Test file parsing.
 import os
 import sys
 import zipfile
-from tests import need_word
+from tests import need_word, need_pdflib
 from . import LinkCheckTest, get_file
 
 
@@ -65,7 +65,13 @@ class TestFile (LinkCheckTest):
 
     @need_word
     def test_word (self):
-        self.file_test("file.doc")
+        confargs = dict(enabledplugins=["WordParser"])
+        self.file_test("file.doc", confargs=confargs)
+
+    @need_pdflib
+    def test_pdf(self):
+        confargs = dict(enabledplugins=["PdfParser"])
+        self.file_test("file.pdf", confargs=confargs)
 
     def test_urllist (self):
         self.file_test("urllist.txt")