Merge pull request #252 from gsnedders/drop_charade

gsnedders · gsnedders · commit 143b0d418d48 · 2016-05-22T02:38:06.000+01:00
Drop charade, cleanup setup.py; r=nobody!
diff --git a/CHANGES.rst b/CHANGES.rst
@@ -44,6 +44,8 @@ Released on XXX
   (instead of the tokenizer); as such, this will require amending all
   callers of it to use it via the treewalker API.**
 
+* **Drop support of charade, now that chardet is supported once more.**
+
 
 0.9999999/1.0b8
 ~~~~~~~~~~~~~~~
diff --git a/README.rst b/README.rst
@@ -113,9 +113,8 @@ functionality:
 
 - ``genshi`` has a treewalker (but not builder); and
 
-- ``charade`` can be used as a fallback when character encoding cannot
-  be determined; ``chardet``, from which it was forked, can also be used
-  on Python 2.
+- ``chardet`` can be used as a fallback when character encoding cannot
+  be determined.
 
 - ``ordereddict`` can be used under Python 2.6
   (``collections.OrderedDict`` is used instead on later versions) to
diff --git a/debug-info.py b/debug-info.py
@@ -12,7 +12,7 @@
     "maxsize": sys.maxsize
 }
 
-search_modules = ["charade", "chardet", "datrie", "genshi", "html5lib", "lxml", "six"]
+search_modules = ["chardet", "datrie", "genshi", "html5lib", "lxml", "six"]
 found_modules = []
 
 for m in search_modules:
diff --git a/html5lib/inputstream.py b/html5lib/inputstream.py
@@ -468,10 +468,7 @@ def detectEncoding(self, parseMeta=True, chardet=True):
         if encoding is None and chardet:
             confidence = "tentative"
             try:
-                try:
-                    from charade.universaldetector import UniversalDetector
-                except ImportError:
-                    from chardet.universaldetector import UniversalDetector
+                from chardet.universaldetector import UniversalDetector
                 buffers = []
                 detector = UniversalDetector()
                 while not detector.done:
diff --git a/html5lib/tests/test_encoding.py b/html5lib/tests/test_encoding.py
@@ -57,12 +57,9 @@ def test_encoding():
 
 # pylint:disable=wrong-import-position
 try:
-    try:
-        import charade  # noqa
-    except ImportError:
-        import chardet  # noqa
+    import chardet  # noqa
 except ImportError:
-    print("charade/chardet not found, skipping chardet tests")
+    print("chardet not found, skipping chardet tests")
 else:
     def test_chardet():
         with open(os.path.join(test_dir, "encoding", "chardet", "test_big5.txt"), "rb") as fp:
diff --git a/requirements-optional.txt b/requirements-optional.txt
@@ -4,9 +4,9 @@
 # streams.
 genshi
 
-# charade can be used as a fallback in case we are unable to determine
+# chardet can be used as a fallback in case we are unable to determine
 # the encoding of a document.
-charade
+chardet>=2.2
 
 # lxml is supported with its own treebuilder ("lxml") and otherwise
 # uses the standard ElementTree support
diff --git a/setup.py b/setup.py
@@ -1,8 +1,8 @@
 import ast
-import os
 import codecs
 
-from setuptools import setup
+from os.path import join, dirname
+from setuptools import setup, find_packages
 
 
 classifiers = [
@@ -22,18 +22,13 @@
     'Topic :: Text Processing :: Markup :: HTML'
 ]
 
-packages = ['html5lib'] + ['html5lib.' + name
-                           for name in os.listdir(os.path.join('html5lib'))
-                           if os.path.isdir(os.path.join('html5lib', name)) and
-                           not name.startswith('.') and name != 'tests']
-
-current_dir = os.path.dirname(__file__)
-with codecs.open(os.path.join(current_dir, 'README.rst'), 'r', 'utf8') as readme_file:
-    with codecs.open(os.path.join(current_dir, 'CHANGES.rst'), 'r', 'utf8') as changes_file:
+here = dirname(__file__)
+with codecs.open(join(here, 'README.rst'), 'r', 'utf8') as readme_file:
+    with codecs.open(join(here, 'CHANGES.rst'), 'r', 'utf8') as changes_file:
         long_description = readme_file.read() + '\n' + changes_file.read()
 
 version = None
-with open(os.path.join("html5lib", "__init__.py"), "rb") as init_file:
+with open(join("html5lib", "__init__.py"), "rb") as init_file:
     t = ast.parse(init_file.read(), filename="__init__.py", mode="exec")
     assert isinstance(t, ast.Module)
     assignments = filter(lambda x: isinstance(x, ast.Assign), t.body)
@@ -53,7 +48,7 @@
       classifiers=classifiers,
       maintainer='James Graham',
       maintainer_email='james@hoppipolla.co.uk',
-      packages=packages,
+      packages=find_packages(exclude=["*.tests", "*.tests.*", "tests.*", "tests"]),
       install_requires=[
           'six',
           'webencodings',
@@ -70,13 +65,13 @@
 
           # Standard extras, will be installed when the extra is requested.
           "genshi": ["genshi"],
-          "charade": ["charade"],
+          "chardet": ["chardet>=2.2"],
 
           # The all extra combines a standard extra which will be used anytime
           # the all extra is requested, and it extends it with a conditional
           # extra that will be installed whenever the condition matches and the
           # all extra is requested.
-          "all": ["genshi", "charade"],
+          "all": ["genshi", "chardet>=2.2"],
           "all:platform.python_implementation == 'CPython'": ["datrie", "lxml"],
       },
       )

Original file line number	Diff line number	Diff line change
`@@ -12,7 +12,7 @@`
`12`	`12`	`"maxsize": sys.maxsize`
`13`	`13`	`}`
`14`	`14`
`15`		`-search_modules = ["charade", "chardet", "datrie", "genshi", "html5lib", "lxml", "six"]`
	`15`	`+search_modules = ["chardet", "datrie", "genshi", "html5lib", "lxml", "six"]`
`16`	`16`	`found_modules = []`
`17`	`17`
`18`	`18`	`for m in search_modules:`