new pdfreader.asxhtml tests, fixed other regressions

ferenda/pdfreader.py

@@ -1029,17 +1029,19 @@ def as_xhtml(self, uri, parent_uri=None):
         first = True
         prevpart = None
         for subpart in self:
-            if not first and getattr(subpart, 'tag', None) == getattr(prevpart, 'tag', None):
+            if not first and subpart.tag == prevpart.tag:
                 prevpart = prevpart + subpart
             elif prevpart:
-                if not isinstance(prevpart, str):
+                # make sure Textelements w/o a tag doesn't render with
+                # as_xhtml as this adds a meaningless <span>
+                if hasattr(prevpart, 'as_xhtml') and prevpart.tag:
                     prevpart = prevpart.as_xhtml(uri, parent_uri)
                 children.append(prevpart)
                 prevpart = subpart
             else:
                 prevpart = subpart
             first = False
-        if not isinstance(prevpart, str):
+        if hasattr(prevpart, 'as_xhtml') and prevpart.tag:
             prevpart = prevpart.as_xhtml(uri, parent_uri)
         children.append(prevpart)
         element = E("p", {'class': 'textbox'}, *children)
@@ -1082,7 +1084,7 @@ class Textelement(UnicodeElement):
     as a whole is bold (``'b'``) , italic(``'i'`` bold + italic
     (``'bi'``) or regular (``None``).
     """
-
+        
     def _get_tagname(self):
         if self.tag:
             return self.tag

ferenda/sources/legal/se/propositioner.py

@@ -29,11 +29,12 @@
 class PropAnalyzer(PDFAnalyzer):
     def documents(self):
         for page in self.pdf:
-            determine dominant font:
-            if EUAlbertina:
-                currentdoc = 'eudok'
-            else:
-                currentdoc = 'main'
+            pass 
+            # determine dominant font:
+            # if EUAlbertina:
+            #    currentdoc = 'eudok'
+            # else:
+            #     currentdoc = 'main'
 
     def metrics(self, metricspath=None, plotpath=None, startpage=0,
                 pagecount=None, force=False):

ferenda/sources/legal/se/swedishlegalsource.py

@@ -859,7 +859,6 @@ def infer_identifier(self, basefile):
     def postprocess_doc(self, doc):
         """Do any last-minute postprocessing (mainly used to add extra
         metadata from doc.body to doc.head)"""
-        from pudb import set_trace; set_trace()
         pass
 
     def get_url_transform_func(self, repos=None, basedir=None, develurl=None):

ferenda/wsgiapp.py

@@ -236,8 +236,7 @@ def static(self, environ, start_response):
                 fp = open(fullpath, "rb")
                 iterdata = FileWrapper(fp)
             else:
-                msg = """
-<h1>404</h1>
+                msg = """<h1>404</h1>
 
 The path %s not found at %s.
 

test/testPDFAnalyze.py

@@ -25,7 +25,7 @@ def setUp(self):
         self.analyzer = PDFAnalyzer(self.pdf)
 
     def test_documents(self):
-        self.assertEquals([(0,3)], self.analyzer.documents())
+        self.assertEquals([(0,3, 'main')], self.analyzer.documents())
 
     def test_vcounters(self):
         vcounters = self.analyzer.count_vertical_margins(0, 3)

test/testPDFReader.py

@@ -12,12 +12,15 @@
 import shutil
 import tempfile
 
+from lxml import etree
+
 from ferenda.compat import unittest
 from ferenda import errors, util
+from ferenda.testutil import FerendaTestCase
 
 # SUT
 from ferenda import PDFReader
-
+from ferenda.pdfreader import Textbox, Textelement
 
 class Read(unittest.TestCase):
     def setUp(self):
@@ -231,13 +234,47 @@ def test_custom_encoding(self):
 class AsXHTML(unittest.TestCase, FerendaTestCase):
 
     def _test_asxhtml(self, want, body):
-        uri = "http://localhost:8000/res/base/basefile"
-        got = etree.tostring(body.as_xhtml(uri), pretty_print=True)
+        got = etree.tostring(body.as_xhtml(None), pretty_print=True)
         self.assertEqualXML(want, got)
 
     def test_basic(self):
-        body = Textbox([Textelement(["test"])])
+        body = Textbox([Textelement("test", tag=None)],
+                       top=0, left=0, width=100, height=100, fontid=0)
+        want = """
+<p xmlns="http://www.w3.org/1999/xhtml" class="textbox" style="top: 0px, left: 0px, height: 100px, width: 100px">test</p>
+"""
+        self._test_asxhtml(want, body)
+
+    def test_elements_with_tags(self):
+        body = Textbox([Textelement("normal", tag=None),
+                        Textelement("bold", tag="b"),
+                        Textelement("italic", tag="i"),
+                        Textelement("both", tag="bi")
+        ], top=0, left=0, width=100, height=100, fontid=0)
+        want = """
+<p xmlns="http://www.w3.org/1999/xhtml" class="textbox" style="top: 0px, left: 0px, height: 100px, width: 100px">normal<b>bold</b><i>italic</i><b><i>both</i></b></p>
+"""
+        self._test_asxhtml(want, body)
+
+
+    def test_leading_tag(self):
+        body = Textbox([Textelement("bold", tag="b"),
+                        Textelement("normal", tag=None),
+        ], top=0, left=0, width=100, height=100, fontid=0)
+        want = """
+<p xmlns="http://www.w3.org/1999/xhtml" class="textbox" style="top: 0px, left: 0px, height: 100px, width: 100px"><b>bold</b>normal</p>
+"""
+        self._test_asxhtml(want, body)
+
+    def test_tag_merge(self):
+        body = Textbox([Textelement("identical ", tag=None),
+                        Textelement("tags ", tag=None),
+                        Textelement("should ", tag="b"),
+                        Textelement("merge", tag="b"),
+        ], top=0, left=0, width=100, height=100, fontid=0)
         want = """
-<p>Test</p>
+<p xmlns="http://www.w3.org/1999/xhtml" class="textbox" style="top: 0px, left: 0px, height: 100px, width: 100px">identical tags <b>should merge</b></p>
 """
         self._test_asxhtml(want, body)
+
+

test/testWSGI.py

@@ -147,7 +147,7 @@ def test_index_html(self):
     def test_not_found(self):
         self.env['PATH_INFO'] = '/nonexistent'
         status, headers, content = self.call_wsgi(self.env)
-        msg = '<h1>404</h1>The path /nonexistent not found at %s/nonexistent' % self.datadir
+        msg = '<h1>404</h1>\n\nThe path /nonexistent not found at %s/nonexistent.\n\nExamined 1 repos.' % self.datadir
         self.assertResponse("404 Not Found",
                             {'Content-Type': 'text/html'},
                             msg.encode(),