made bs4 and soupsieve standalone in this project

MarkdownLivePreview.py

@@ -149,7 +149,6 @@ class MarkdownLivePreviewListener(sublime_plugin.EventListener):
         if self.file_name is None:
             total_region = sublime.Region(0, markdown_view.size())
             self.content = markdown_view.substr(total_region)
-            markdown_view.erase(edit, total_region)
         else:
             self.content = None
 

lib/bs4/builder/__init__.py

@@ -4,7 +4,7 @@ __license__ = "MIT"
 from collections import defaultdict
 import itertools
 import sys
-from ...bs4.element import (
+from ..element import (
     CharsetMetaAttributeValue,
     ContentMetaAttributeValue,
     Stylesheet,

lib/bs4/builder/_html5lib.py

@@ -7,13 +7,13 @@ __all__ = [
 
 import warnings
 import re
-from ...bs4.builder import (
+from . import (
     PERMISSIVE,
     HTML,
     HTML_5,
     HTMLTreeBuilder,
     )
-from ...bs4.element import (
+from ..element import (
     NamespacedAttribute,
     nonwhitespace_re,
 )
@@ -22,7 +22,7 @@ from html5lib.constants import (
     namespaces,
     prefixes,
     )
-from ...bs4.element import (
+from ..element import (
     Comment,
     Doctype,
     NavigableString,
@@ -120,7 +120,7 @@ class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
         if soup:
             self.soup = soup
         else:
-            from ...bs4 import BeautifulSoup
+            from .. import BeautifulSoup
             # TODO: Why is the parser 'html.parser' here? To avoid an
             # infinite loop?
             self.soup = BeautifulSoup(
@@ -166,7 +166,7 @@ class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
         return TextNode(Comment(data), self.soup)
 
     def fragmentClass(self):
-        from ...bs4 import BeautifulSoup
+        from .. import BeautifulSoup
         # TODO: Why is the parser 'html.parser' here? To avoid an
         # infinite loop?
         self.soup = BeautifulSoup("", "html.parser")
@@ -184,7 +184,7 @@ class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
         return treebuilder_base.TreeBuilder.getFragment(self).element
 
     def testSerializer(self, element):
-        from ...bs4 import BeautifulSoup
+        from .. import BeautifulSoup
         rv = []
         doctype_re = re.compile(r'^(.*?)(?: PUBLIC "(.*?)"(?: "(.*?)")?| SYSTEM "(.*?)")?$')
 

lib/bs4/builder/_htmlparser.py

@@ -34,16 +34,16 @@ CONSTRUCTOR_STRICT_IS_DEPRECATED = major == 3 and minor == 3
 CONSTRUCTOR_TAKES_CONVERT_CHARREFS = major == 3 and minor >= 4
 
 
-from ...bs4.element import (
+from ..element import (
     CData,
     Comment,
     Declaration,
     Doctype,
     ProcessingInstruction,
     )
-from ...bs4.dammit import EntitySubstitution, UnicodeDammit
+from ..dammit import EntitySubstitution, UnicodeDammit
 
-from ...bs4.builder import (
+from . import (
     HTML,
     HTMLTreeBuilder,
     STRICT,

lib/bs4/builder/_lxml.py

@@ -14,14 +14,14 @@ except ImportError as e:
 from io import BytesIO
 from io import StringIO
 from lxml import etree
-from ...bs4.element import (
+from ..element import (
     Comment,
     Doctype,
     NamespacedAttribute,
     ProcessingInstruction,
     XMLProcessingInstruction,
 )
-from ...bs4.builder import (
+from . import (
     FAST,
     HTML,
     HTMLTreeBuilder,
@@ -29,7 +29,7 @@ from ...bs4.builder import (
     ParserRejectedMarkup,
     TreeBuilder,
     XML)
-from ...bs4.dammit import EncodingDetector
+from ..dammit import EncodingDetector
 
 LXML = 'lxml'
 

lib/bs4/diagnose.py

@@ -6,9 +6,9 @@ __license__ = "MIT"
 import cProfile
 from io import StringIO
 from html.parser import HTMLParser
-from ..bs4 import BeautifulSoup as bs4
+from . import BeautifulSoup as bs4
-from ..bs4 import BeautifulSoup, __version__
+from . import BeautifulSoup, __version__
-from ..bs4.builder import builder_registry
+from .builder import builder_registry
 
 import os
 import pstats

lib/bs4/element.py

@@ -16,7 +16,7 @@ except ImportError as e:
         'The soupsieve package is not installed. CSS selectors cannot be used.'
     )
 
-from ..bs4.formatter import (
+from .formatter import (
     Formatter,
     HTMLFormatter,
     XMLFormatter,
@@ -380,7 +380,7 @@ class PageElement(object):
             and not isinstance(new_child, NavigableString)):
             new_child = NavigableString(new_child)
 
-        from ..bs4 import BeautifulSoup
+        from . import BeautifulSoup
         if isinstance(new_child, BeautifulSoup):
             # We don't want to end up with a situation where one BeautifulSoup
             # object contains another. Insert the children one at a time.

lib/bs4/formatter.py

@@ -1,4 +1,4 @@
-from ..bs4.dammit import EntitySubstitution
+from .dammit import EntitySubstitution
 
 class Formatter(EntitySubstitution):
     """Describes a strategy to use when outputting a parse tree to a string.

lib/bs4/testing.py

@@ -9,8 +9,8 @@ import copy
 import functools
 import unittest
 from unittest import TestCase
-from ..bs4 import BeautifulSoup
+from . import BeautifulSoup
-from ..bs4.element import (
+from .element import (
     CharsetMetaAttributeValue,
     Comment,
     ContentMetaAttributeValue,
@@ -22,7 +22,7 @@ from ..bs4.element import (
     Tag
 )
 
-from ..bs4.builder import HTMLParserTreeBuilder
+from .builder import HTMLParserTreeBuilder
 default_builder = HTMLParserTreeBuilder
 
 BAD_DOCUMENT = """A bare string

lib/bs4/tests/test_builder_registry.py

@@ -3,21 +3,21 @@
 import unittest
 import warnings
 
-from ...bs4 import BeautifulSoup
+from .. import BeautifulSoup
-from ...bs4.builder import (
+from ..builder import (
     builder_registry as registry,
     HTMLParserTreeBuilder,
     TreeBuilderRegistry,
 )
 
 try:
-    from ...bs4.builder import HTML5TreeBuilder
+    from ..builder import HTML5TreeBuilder
     HTML5LIB_PRESENT = True
 except ImportError:
     HTML5LIB_PRESENT = False
 
 try:
-    from ...bs4.builder import (
+    from ..builder import (
         LXMLTreeBuilderForXML,
         LXMLTreeBuilder,
         )

lib/bs4/tests/test_html5lib.py

@@ -3,12 +3,12 @@
 import warnings
 
 try:
-    from ...bs4.builder import HTML5TreeBuilder
+    from ..builder import HTML5TreeBuilder
     HTML5LIB_PRESENT = True
 except ImportError as e:
     HTML5LIB_PRESENT = False
-from ...bs4.element import SoupStrainer
+from ..element import SoupStrainer
-from ...bs4.testing import (
+from ..testing import (
     HTML5TreeBuilderSmokeTest,
     SoupTest,
     skipIf,

lib/bs4/tests/test_htmlparser.py

@@ -3,9 +3,9 @@ trees."""
 
 from pdb import set_trace
 import pickle
-from ...bs4.testing import SoupTest, HTMLTreeBuilderSmokeTest
+from ..testing import SoupTest, HTMLTreeBuilderSmokeTest
-from ...bs4.builder import HTMLParserTreeBuilder
+from ..builder import HTMLParserTreeBuilder
-from ...bs4.builder._htmlparser import BeautifulSoupHTMLParser
+from ..builder._htmlparser import BeautifulSoupHTMLParser
 
 class HTMLParserTreeBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest):
 

lib/bs4/tests/test_lxml.py

@@ -12,16 +12,16 @@ except ImportError as e:
     LXML_VERSION = (0,)
 
 if LXML_PRESENT:
-    from ...bs4.builder import LXMLTreeBuilder, LXMLTreeBuilderForXML
+    from ..builder import LXMLTreeBuilder, LXMLTreeBuilderForXML
 
-from ...bs4 import (
+from .. import (
     BeautifulSoup,
     BeautifulStoneSoup,
     )
-from ...bs4.element import Comment, Doctype, SoupStrainer
+from ..element import Comment, Doctype, SoupStrainer
-from ...bs4.testing import skipIf
+from ..testing import skipIf
-from ...bs4.tests import test_htmlparser
+from . import test_htmlparser
-from ...bs4.testing import (
+from ..testing import (
     HTMLTreeBuilderSmokeTest,
     XMLTreeBuilderSmokeTest,
     SoupTest,

lib/bs4/tests/test_soup.py

@@ -7,17 +7,17 @@ import unittest
 import sys
 import tempfile
 
-from ...bs4 import (
+from .. import (
     BeautifulSoup,
     BeautifulStoneSoup,
     GuessedAtParserWarning,
     MarkupResemblesLocatorWarning,
 )
-from ...bs4.builder import (
+from ..builder import (
     TreeBuilder,
     ParserRejectedMarkup,
 )
-from ...bs4.element import (
+from ..element import (
     CharsetMetaAttributeValue,
     Comment,
     ContentMetaAttributeValue,
@@ -27,13 +27,13 @@ from ...bs4.element import (
     NavigableString,
     )
 
-from ...bs4.dammit import *
+from ..dammit import *
-from ...bs4.dammit import (
+from ..dammit import (
     EntitySubstitution,
     UnicodeDammit,
     EncodingDetector,
 )
-from ...bs4.testing import (
+from ..testing import (
     default_builder,
     SoupTest,
     skipIf,
@@ -41,7 +41,7 @@ from ...bs4.testing import (
 import warnings
 
 try:
-    from ...bs4.builder import LXMLTreeBuilder, LXMLTreeBuilderForXML
+    from ..builder import LXMLTreeBuilder, LXMLTreeBuilderForXML
     LXML_PRESENT = True
 except ImportError as e:
     LXML_PRESENT = False
@@ -120,11 +120,10 @@ class TestConstructor(SoupTest):
             def feed(self, *args, **kwargs):
                 raise ParserRejectedMarkup("Nope.")
 
-        def prepare_markup(self, *args, **kwargs):
+            def prepare_markup(self, markup, *args, **kwargs):
                 # We're going to try two different ways of preparing this markup,
                 # but feed() will reject both of them.
                 yield markup, None, None, False
-            yield markup, None, None, False
             
         import re
         self.assertRaisesRegex(
@@ -613,7 +612,7 @@ class TestUnicodeDammit(unittest.TestCase):
         self.assertRaises(UnicodeDecodeError, doc.decode, "utf8")
 
         # Unicode, Dammit thinks the whole document is Windows-1252,
-        # and decodes it into "☃☃☃“Hi, I like Windows!”☃☃☃"
+        # and decodes it into "☃☃☃"Hi, I like Windows!"☃☃☃"
 
         # But if we run it through fix_embedded_windows_1252, it's fixed:
 

lib/bs4/tests/test_tree.py

@@ -14,12 +14,12 @@ import copy
 import pickle
 import re
 import warnings
-from ...bs4 import BeautifulSoup
+from .. import BeautifulSoup
-from ...bs4.builder import (
+from ..builder import (
     builder_registry,
     HTMLParserTreeBuilder,
 )
-from ...bs4.element import (
+from ..element import (
     PY3K,
     CData,
     Comment,
@@ -33,7 +33,7 @@ from ...bs4.element import (
     Tag,
     TemplateString,
 )
-from ...bs4.testing import (
+from ..testing import (
     SoupTest,
     skipIf,
 )

lib/soupsieve/css_match.py

@@ -6,11 +6,13 @@ from .import css_types as ct
 import unicodedata
 from collections.abc import Sequence
 
-from ..bs4 import *
+from ..bs4 import BeautifulSoup
-from ..bs4.element import *
+from ..bs4.element import (
+    Tag, NavigableString, Comment, Declaration, CData, ProcessingInstruction, Doctype
+)
 
 # Empty tag pattern (whitespace okay)
-RE_NOT_EMPTY = re.compile('[^ \t\r\n\f]')
+RE_NOT_EMPTY = re.compile(r'[^ \t\r\n\f]')
 
 RE_NOT_WS = re.compile('[^ \t\r\n\f]+')
 

markdown2html.py

@@ -194,13 +194,19 @@ def get_image_size(fhandle, pathlike):
                 fhandle.seek(size, 1)
                 byte = fhandle.read(1)
                 if byte == b"":
-                    fhandle = end
+                    # Reached end of file unexpectedly, break the loop
-                    byte = fhandle.read(1)
+                    break
-
                 while ord(byte) == 0xFF:
                     byte = fhandle.read(1)
+                    if byte == b"": # Check EOF in inner loop too
+                        break
+                if byte == b"": # Break outer loop if inner loop hit EOF
+                    break
                 ftype = ord(byte)
                 size = struct.unpack(">H", fhandle.read(2))[0] - 2
+            # Check if the loop exited because of a break (EOF) before finding the marker
+            if not (0xC0 <= ftype <= 0xCF):
+                 return "unknown format {!r}".format(format_)
             # We are at a SOFn block
             fhandle.seek(1, 1)  # Skip `precision' byte.
             height, width = struct.unpack(">HH", fhandle.read(4))