Move a whole bunch of private modules to be underscore prefixed

Author: gsnedders

html5lib/ihatexml.py renamed to html5lib/_ihatexml.py

@@ -11,9 +11,9 @@
 from .constants import tokenTypes, tagTokenTypes
 from .constants import replacementCharacters
 
-from .inputstream import HTMLInputStream
+from ._inputstream import HTMLInputStream
 
-from .trie import Trie
+from ._trie import Trie
 
 entitiesTrie = Trie(entities)
 

html5lib/inputstream.py renamed to html5lib/_inputstream.py

@@ -8,8 +8,8 @@
 except ImportError:
     from ordereddict import OrderedDict
 
-from . import inputstream
-from . import tokenizer
+from . import _inputstream
+from . import _tokenizer
 
 from . import treebuilders
 from .treebuilders.base import Marker
@@ -82,7 +82,7 @@ def _parse(self, stream, innerHTML=False, container="div", scripting=False, **kw
         self.innerHTMLMode = innerHTML
         self.container = container
         self.scripting = scripting
-        self.tokenizer = tokenizer.HTMLTokenizer(stream, parser=self, **kwargs)
+        self.tokenizer = _tokenizer.HTMLTokenizer(stream, parser=self, **kwargs)
         self.reset()
 
         try:
@@ -687,8 +687,8 @@ def startTagMeta(self, token):
                     # the abstract Unicode string, and just use the
                     # ContentAttrParser on that, but using UTF-8 allows all chars
                     # to be encoded and as a ASCII-superset works.
-                    data = inputstream.EncodingBytes(attributes["content"].encode("utf-8"))
-                    parser = inputstream.ContentAttrParser(data)
+                    data = _inputstream.EncodingBytes(attributes["content"].encode("utf-8"))
+                    parser = _inputstream.ContentAttrParser(data)
                     codec = parser.parse()
                     self.parser.tokenizer.stream.changeEncoding(codec)
 

html5lib/tokenizer.py renamed to html5lib/_tokenizer.py

@@ -5,15 +5,15 @@
 import pytest
 
 from .support import get_data_files, test_dir, errorMessage, TestData as _TestData
-from html5lib import HTMLParser, inputstream
+from html5lib import HTMLParser, _inputstream
 
 
 def test_basic_prescan_length():
     data = "<title>Caf\u00E9</title><!--a--><meta charset='utf-8'>".encode('utf-8')
     pad = 1024 - len(data) + 1
     data = data.replace(b"-a-", b"-" + (b"a" * pad) + b"-")
     assert len(data) == 1024  # Sanity
-    stream = inputstream.HTMLBinaryInputStream(data, useChardet=False)
+    stream = _inputstream.HTMLBinaryInputStream(data, useChardet=False)
     assert 'utf-8' == stream.charEncoding[0].name
 
 
@@ -22,7 +22,7 @@ def test_parser_reparse():
     pad = 10240 - len(data) + 1
     data = data.replace(b"-a-", b"-" + (b"a" * pad) + b"-")
     assert len(data) == 10240  # Sanity
-    stream = inputstream.HTMLBinaryInputStream(data, useChardet=False)
+    stream = _inputstream.HTMLBinaryInputStream(data, useChardet=False)
     assert 'windows-1252' == stream.charEncoding[0].name
     p = HTMLParser(namespaceHTMLElements=False)
     doc = p.parse(data, useChardet=False)
@@ -47,7 +47,7 @@ def test_parser_reparse():
     ("windows-1252", b"", {}),
 ])
 def test_parser_args(expected, data, kwargs):
-    stream = inputstream.HTMLBinaryInputStream(data, useChardet=False, **kwargs)
+    stream = _inputstream.HTMLBinaryInputStream(data, useChardet=False, **kwargs)
     assert expected == stream.charEncoding[0].name
     p = HTMLParser()
     p.parse(data, useChardet=False, **kwargs)
@@ -85,7 +85,7 @@ def runParserEncodingTest(data, encoding):
 
 
 def runPreScanEncodingTest(data, encoding):
-    stream = inputstream.HTMLBinaryInputStream(data, useChardet=False)
+    stream = _inputstream.HTMLBinaryInputStream(data, useChardet=False)
     encoding = encoding.lower().decode("ascii")
 
     # Very crude way to ignore irrelevant tests
@@ -111,6 +111,6 @@ def test_encoding():
 else:
     def test_chardet():
         with open(os.path.join(test_dir, "encoding", "chardet", "test_big5.txt"), "rb") as fp:
-            encoding = inputstream.HTMLInputStream(fp.read()).charEncoding
+            encoding = _inputstream.HTMLInputStream(fp.read()).charEncoding
             assert encoding[0].name == "big5"
 # pylint:enable=wrong-import-position

html5lib/trie/__init__.py renamed to html5lib/_trie/__init__.py

@@ -11,8 +11,8 @@
 import six
 from six.moves import http_client, urllib
 
-from html5lib.inputstream import (BufferedStream, HTMLInputStream,
-                                  HTMLUnicodeInputStream, HTMLBinaryInputStream)
+from html5lib._inputstream import (BufferedStream, HTMLInputStream,
+                                   HTMLUnicodeInputStream, HTMLBinaryInputStream)
 from html5lib.utils import supports_lone_surrogates
 
 

html5lib/trie/_base.py renamed to html5lib/_trie/_base.py

@@ -8,7 +8,7 @@
 import pytest
 from six import unichr
 
-from html5lib.tokenizer import HTMLTokenizer
+from html5lib._tokenizer import HTMLTokenizer
 from html5lib import constants, utils
 
 

html5lib/trie/datrie.py renamed to html5lib/_trie/datrie.py

@@ -6,7 +6,7 @@
 import re
 
 from . import base
-from .. import ihatexml
+from .. import _ihatexml
 from .. import constants
 from ..constants import namespaces
 from ..utils import moduleFactoryFactory
@@ -259,7 +259,7 @@ def serializeElement(element, indent=0):
     def tostring(element):  # pylint:disable=unused-variable
         """Serialize an element and its child nodes to a string"""
         rv = []
-        filter = ihatexml.InfosetFilter()
+        filter = _ihatexml.InfosetFilter()
 
         def serializeElement(element):
             if isinstance(element, ElementTree.ElementTree):

html5lib/trie/py.py renamed to html5lib/_trie/py.py

@@ -20,7 +20,7 @@
 from ..constants import DataLossWarning
 from .. import constants
 from . import etree as etree_builders
-from .. import ihatexml
+from .. import _ihatexml
 
 import lxml.etree as etree
 
@@ -54,7 +54,7 @@ def _getChildNodes(self):
 
 def testSerializer(element):
     rv = []
-    infosetFilter = ihatexml.InfosetFilter(preventDoubleDashComments=True)
+    infosetFilter = _ihatexml.InfosetFilter(preventDoubleDashComments=True)
 
     def serializeElement(element, indent=0):
         if not hasattr(element, "tag"):
@@ -182,7 +182,7 @@ class TreeBuilder(base.TreeBuilder):
 
     def __init__(self, namespaceHTMLElements, fullTree=False):
         builder = etree_builders.getETreeModule(etree, fullTree=fullTree)
-        infosetFilter = self.infosetFilter = ihatexml.InfosetFilter(preventDoubleDashComments=True)
+        infosetFilter = self.infosetFilter = _ihatexml.InfosetFilter(preventDoubleDashComments=True)
         self.namespaceHTMLElements = namespaceHTMLElements
 
         class Attributes(dict):

html5lib/html5parser.py

@@ -6,7 +6,7 @@
 
 from . import base
 
-from .. import ihatexml
+from .. import _ihatexml
 
 
 def ensure_str(s):
@@ -132,7 +132,7 @@ def __init__(self, tree):
             self.fragmentChildren = set()
             tree = Root(tree)
         base.NonRecursiveTreeWalker.__init__(self, tree)
-        self.filter = ihatexml.InfosetFilter()
+        self.filter = _ihatexml.InfosetFilter()
 
     def getNodeDetails(self, node):
         if isinstance(node, tuple):  # Text node