Updated testing framework to use PyTidyLib rather than uTidyLib for Python 3 support.

2 files changed, 26 insertions, 27 deletions

diff --git a/docs/test_suite.txt b/docs/test_suite.txt
index 44b6c5c..e10e58b 100644
--- a/docs/test_suite.txt
+++ b/docs/test_suite.txt
@@ -26,7 +26,7 @@ the report.
 The test suite contains two kinds of tests: Markdown Syntax Tests and Unit
 Tests.
 
-# Markdown Syntax Tests
+## Markdown Syntax Tests
 
 The Syntax Tests are in the various directories contained within the 'tests'
 directory of the packaged tarball. Each test consists of a matching pair of txt
@@ -105,7 +105,7 @@ Below are each of the config options available and the defaults used when they
 are not explicitly set.
 
 * `normalize`: Switches whitespace normalization of the test output on or off. 
-  Defaults to `0` (off). Note: This requires that [uTidylib] be installed on 
+  Defaults to `0` (off). Note: This requires that [PyTidyLib] be installed on 
   the system. Otherwise the test will be skipped, regardless of any other 
   settings.  
 * `skip`: Switches skipping of the test on and off. Defaults to `0` (off).  
@@ -113,18 +113,18 @@ are not explicitly set.
   from other implementations.
 * `output_ext`: Extension of output file. Defaults to `.html`. Useful for tests
   from other implementations.
-* Any keyword arguement accepted my Markdown. If not set, Markdown's defaults
-  are used. 
+* Any keyword arguement accepted by the Markdown class. If not set, Markdown's 
+  defaults are used. 
 
 ## Unit Tests
 
 Unit Tests are used as regression tests for Python-Markdown's API.
 All Unit Tests shipped with Python-Markdown are standard Python Unit Tests and
-are all contained in `tests/test_apis.py` and `tests/test_extensions`. 
+are all contained in `tests/test_apis.py` and `tests/test_extensions.py`. 
 Standard discovery methods are used to find and run the tests. Therefore, when 
 writing new tests, those standards and naming conventions should be followed.
 
 [Nose]: http://somethingaboutorange.com/mrl/projects/nose/ 
 [Perl]: http://daringfireball.net/projects/markdown/ 
 [PHP]: http://michelf.com/projects/php-markdown/ 
-[uTidylib]: http://utidylib.berlios.de/
+[PyTidyLib]: http://countergram.com/open-source/pytidylib/
diff --git a/tests/__init__.py b/tests/__init__.py
index bb56bd4..a16d0e6 100644
--- a/tests/__init__.py
+++ b/tests/__init__.py
@@ -12,9 +12,9 @@ except ImportError:
 from . import util 
 from .plugins import HtmlOutput, Markdown
 try:
-    import tidy
+    import tidylib
 except ImportError:
-    tidy = None
+    tidylib = None
 
 
 test_dir = os.path.abspath(os.path.dirname(__file__))
@@ -60,20 +60,19 @@ def get_args(file, config):
     return args
 
 def normalize(text):
-    """ Normalize whitespace for a string of html using tidy. """
-    return str(tidy.parseString(text.encode('utf-8', 'xmlcharrefreplace'), 
-                                    drop_empty_paras=0,
-                                    fix_backslash=0,
-                                    fix_bad_comments=0,
-                                    fix_uri=0,
-                                    join_styles=0,
-                                    lower_literals=0,
-                                    merge_divs=0,
-                                    output_xhtml=1,
-                                    quote_ampersand=0,
-                                    show_body_only=1,
-                                    char_encoding='utf8',
-                                    newline='LF')).decode('string-escape')
+    """ Normalize whitespace for a string of html using tidylib. """
+    output, errors = tidylib.tidy_fragment(text, options={
+                                    'drop_empty_paras':0,
+                                    'fix_backslash':0,
+                                    'fix_bad_comments':0,
+                                    'fix_uri':0,
+                                    'join_styles':0,
+                                    'lower_literals':0,
+                                    'merge_divs':0,
+                                    'output_xhtml':1,
+                                    'quote_ampersand':0,
+                                    'newline':'LF'})
+    return output
 
 class CheckSyntax(object):
     def __init__(self, description=None):
@@ -93,13 +92,13 @@ class CheckSyntax(object):
             # Normalize line endings (on windows, git may have altered line endings).
             expected_output = f.read().replace("\r\n", "\n")
         output = markdown.markdown(input, **get_args(file, config))
-        if tidy and config.get(cfg_section, 'normalize'):
-            # Normalize whitespace with Tidy before comparing.
+        if tidylib and config.get(cfg_section, 'normalize'):
+            # Normalize whitespace with tidylib before comparing.
             expected_output = normalize(expected_output)
             output = normalize(output)
         elif config.get(cfg_section, 'normalize'):
-            # Tidy is not available. Skip this test.
-            raise nose.plugins.skip.SkipTest('Test skipped. Tidy not available in system.')
+            # Tidylib is not available. Skip this test.
+            raise nose.plugins.skip.SkipTest('Test skipped. Tidylib not available on system.')
         diff = [l for l in difflib.unified_diff(expected_output.splitlines(True),
                                                 output.splitlines(True), 
                                                 output_file, 
@@ -124,7 +123,7 @@ def TestSyntax():
 def generate(file, config):
     """ Write expected output file for given input. """
     cfg_section = get_section(file, config)
-    if config.get(cfg_section, 'skip'):
+    if config.get(cfg_section, 'skip') or config.get(cfg_section, 'normalize'):
         print('Skipping:', file)
         return None
     input_file = file + config.get(cfg_section, 'input_ext')