google · tushuhei · Mar 16, 2023 · Mar 16, 2023 · Mar 16, 2023
diff --git a/budoux/html_processor.py b/budoux/html_processor.py
@@ -63,11 +63,11 @@ def handle_starttag(self, tag: str, attrs: HTMLAttr) -> None:
     attr_pairs = []
     for attr in attrs:
       if attr[1] is None:
-        attr_pairs.append(attr[0])
+        attr_pairs.append(' ' + attr[0])
       else:
-        attr_pairs.append('%s="%s"' % (attr[0], attr[1]))
-    encoded_attrs = ' '.join(attr_pairs)
-    self.output += '<%s %s>' % (tag, encoded_attrs)
+        attr_pairs.append(' %s="%s"' % (attr[0], attr[1]))
+    encoded_attrs = ''.join(attr_pairs)
+    self.output += '<%s%s>' % (tag, encoded_attrs)
     self.to_skip = tag.upper() in SKIP_NODES
 
   def handle_endtag(self, tag: str) -> None:

diff --git a/setup.cfg b/setup.cfg
@@ -26,14 +26,12 @@ test_suite = tests
 dev =
     build
     flake8
-    html5lib
     isort
     numpy
     mypy==0.971
     pytest
     toml
     twine
-    types-html5lib
     types-setuptools
     yapf
 

diff --git a/tests/test_html_processor.py b/tests/test_html_processor.py
@@ -17,8 +17,6 @@
 import sys
 import unittest
 
-from utils import compare_html_string
-
 # module hack
 LIB_PATH = os.path.join(os.path.dirname(__file__), '..')
 sys.path.insert(0, os.path.abspath(LIB_PATH))
@@ -45,9 +43,8 @@ def test_output(self) -> None:
     expected = '<p>ab<b>c<wbr>de</b>f</p>'
     resolver = html_processor.HTMLChunkResolver(['abc', 'def'])
     resolver.feed(input)
-    self.assertTrue(
-        compare_html_string(resolver.output, expected),
-        'WBR tags should be inserted as specified by chunks.')
+    self.assertEqual(resolver.output, expected,
+                     'WBR tags should be inserted as specified by chunks.')
 
 
 class TestResolve(unittest.TestCase):
@@ -57,25 +54,25 @@ def test_with_simple_text_input(self) -> None:
     html = 'abcdef'
     result = html_processor.resolve(chunks, html)
     expected = '<span style="word-break: keep-all; overflow-wrap: break-word;">abc<wbr>def</span>'
-    self.assertTrue(compare_html_string(result, expected))
+    self.assertEqual(result, expected)
 
   def test_with_standard_html_input(self) -> None:
     chunks = ['abc', 'def']
     html = 'ab<a href="http://example.com">cd</a>ef'
     result = html_processor.resolve(chunks, html)
     expected = '<span style="word-break: keep-all; overflow-wrap: break-word;">ab<a href="http://example.com">c<wbr>d</a>ef</span>'
-    self.assertTrue(compare_html_string(result, expected))
+    self.assertEqual(result, expected)
 
   def test_with_nodes_to_skip(self) -> None:
     chunks = ['abc', 'def']
     html = "a<button>bcde</button>f"
     result = html_processor.resolve(chunks, html)
     expected = '<span style="word-break: keep-all; overflow-wrap: break-word;">a<button>bcde</button>f</span>'
-    self.assertTrue(compare_html_string(result, expected))
+    self.assertEqual(result, expected)
 
   def test_with_nothing_to_split(self) -> None:
     chunks = ['abcdef']
     html = 'abcdef'
     result = html_processor.resolve(chunks, html)
     expected = '<span style="word-break: keep-all; overflow-wrap: break-word;">abcdef</span>'
-    self.assertTrue(compare_html_string(result, expected))
+    self.assertEqual(result, expected)
diff --git a/tests/test_main.py b/tests/test_main.py
@@ -131,7 +131,7 @@ def test_cmdargs_single_html(self) -> None:
     self.assertEqual(
         output,
         '<span style="word-break: keep-all; overflow-wrap: break-word;">'
-        '今日は<b ><wbr>とても<wbr>天気</b>です。</span>')
+        '今日は<b><wbr>とても<wbr>天気</b>です。</span>')
 
   def test_cmdargs_multi_html(self) -> None:
     cmdargs = ['-H', '今日は<b>とても天気</b>です。', 'これは<b>テスト</b>です。']
@@ -174,7 +174,7 @@ def test_cmdargs_html_stdin(self) -> None:
     self.assertEqual(
         output,
         '<span style="word-break: keep-all; overflow-wrap: break-word;">'
-        'これは<b ><wbr>テスト</b>です。<wbr>\n'
+        'これは<b><wbr>テスト</b>です。<wbr>\n'
         '</span>')
 
 

diff --git a/tests/test_parser.py b/tests/test_parser.py
@@ -17,8 +17,6 @@
 import sys
 import unittest
 
-from utils import compare_html_string
-
 # module hack
 LIB_PATH = os.path.join(os.path.dirname(__file__), '..')
 sys.path.insert(0, os.path.abspath(LIB_PATH))
@@ -66,8 +64,8 @@ def test_translate_html_string(self) -> None:
         '<span style="word-break: keep-all; overflow-wrap: break-word;">'
         'xyz<wbr>abcd</span>')
     output_html = p.translate_html_string(input_html)
-    self.assertTrue(
-        compare_html_string(output_html, expected_html),
+    self.assertEqual(
+        output_html, expected_html,
         'Should output a html string with a SPAN parent with proper style attributes.'
     )
 
@@ -76,36 +74,31 @@ def test_translate_html_string(self) -> None:
         '<span style="word-break: keep-all; overflow-wrap: break-word;">'
         'xyz<script>alert(1);</script>xyz<wbr>abc</span>')
     output_html = p.translate_html_string(input_html)
-    self.assertTrue(
-        compare_html_string(output_html, expected_html),
-        'Should pass script tags as is.')
+    self.assertEqual(output_html, expected_html,
+                     'Should pass script tags as is.')
 
     input_html = 'xyz<code>abc</code>abc'
     expected_html = (
         '<span style="word-break: keep-all; overflow-wrap: break-word;">'
         'xyz<code>abc</code><wbr>abc</span>')
     output_html = p.translate_html_string(input_html)
-    self.assertTrue(
-        compare_html_string(output_html, expected_html),
-        'Should skip some specific tags.')
+    self.assertEqual(output_html, expected_html,
+                     'Should skip some specific tags.')
 
     input_html = 'xyza<a href="#" hidden>bc</a>abc'
     expected_html = (
         '<span style="word-break: keep-all; overflow-wrap: break-word;">'
         'xyz<wbr>a<a href="#" hidden>bc</a><wbr>abc</span>')
     output_html = p.translate_html_string(input_html)
-    self.assertTrue(
-        compare_html_string(output_html, expected_html),
-        'Should not ruin attributes of child elements.')
+    self.assertEqual(output_html, expected_html,
+                     'Should not ruin attributes of child elements.')
 
     input_html = 'xyza🇯🇵🇵🇹abc'
     expected_html = (
         '<span style="word-break: keep-all; overflow-wrap: break-word;">'
         'xyz<wbr>a🇯🇵🇵🇹<wbr>abc</span>')
     output_html = p.translate_html_string(input_html)
-    self.assertTrue(
-        compare_html_string(output_html, expected_html),
-        'Should work with emojis.')
+    self.assertEqual(output_html, expected_html, 'Should work with emojis.')
 
 
 class TestDefaultParser(unittest.TestCase):

diff --git a/tests/utils.py b/tests/utils.py