Add a test for HTMLParser(debug=True)

gsnedders · gsnedders · commit 761f3ab25110 · 2016-05-22T02:53:16.000+01:00
diff --git a/html5lib/tests/test_parser2.py b/html5lib/tests/test_parser2.py
@@ -1,11 +1,13 @@
 from __future__ import absolute_import, division, unicode_literals
 
+from six import PY2, text_type
+
 import io
 
 from . import support  # noqa
 
 from html5lib.constants import namespaces
-from html5lib import parse
+from html5lib import parse, HTMLParser
 
 
 # tests that aren't autogenerated from text files
@@ -56,3 +58,33 @@ def test_duplicate_attribute():
     doc = parse('<p class=a class=b>')
     el = doc[1][0]
     assert el.get("class") == "a"
+
+
+def test_debug_log():
+    parser = HTMLParser(debug=True)
+    parser.parse("<!doctype html><title>a</title><p>b<script>c</script>d</p>e")
+
+    expected = [('dataState', 'InitialPhase', 'InitialPhase', 'processDoctype', {'type': 'Doctype'}),
+                ('dataState', 'BeforeHtmlPhase', 'BeforeHtmlPhase', 'processStartTag', {'name': 'title', 'type': 'StartTag'}),
+                ('dataState', 'BeforeHeadPhase', 'BeforeHeadPhase', 'processStartTag', {'name': 'title', 'type': 'StartTag'}),
+                ('dataState', 'InHeadPhase', 'InHeadPhase', 'processStartTag', {'name': 'title', 'type': 'StartTag'}),
+                ('rcdataState', 'TextPhase', 'TextPhase', 'processCharacters', {'type': 'Characters'}),
+                ('dataState', 'TextPhase', 'TextPhase', 'processEndTag', {'name': 'title', 'type': 'EndTag'}),
+                ('dataState', 'InHeadPhase', 'InHeadPhase', 'processStartTag', {'name': 'p', 'type': 'StartTag'}),
+                ('dataState', 'AfterHeadPhase', 'AfterHeadPhase', 'processStartTag', {'name': 'p', 'type': 'StartTag'}),
+                ('dataState', 'InBodyPhase', 'InBodyPhase', 'processStartTag', {'name': 'p', 'type': 'StartTag'}),
+                ('dataState', 'InBodyPhase', 'InBodyPhase', 'processCharacters', {'type': 'Characters'}),
+                ('dataState', 'InBodyPhase', 'InBodyPhase', 'processStartTag', {'name': 'script', 'type': 'StartTag'}),
+                ('dataState', 'InBodyPhase', 'InHeadPhase', 'processStartTag', {'name': 'script', 'type': 'StartTag'}),
+                ('scriptDataState', 'TextPhase', 'TextPhase', 'processCharacters', {'type': 'Characters'}),
+                ('dataState', 'TextPhase', 'TextPhase', 'processEndTag', {'name': 'script', 'type': 'EndTag'}),
+                ('dataState', 'InBodyPhase', 'InBodyPhase', 'processCharacters', {'type': 'Characters'}),
+                ('dataState', 'InBodyPhase', 'InBodyPhase', 'processEndTag', {'name': 'p', 'type': 'EndTag'}),
+                ('dataState', 'InBodyPhase', 'InBodyPhase', 'processCharacters', {'type': 'Characters'})]
+
+    if PY2:
+        for i, log in enumerate(expected):
+            log = [x.encode("ascii") if isinstance(x, text_type) else x for x in log]
+            expected[i] = tuple(log)
+
+    assert parser.log == expected
