diff options
| -rw-r--r-- | NEWS.txt | 4 | ||||
| -rw-r--r-- | bs4/element.py | 16 | ||||
| -rw-r--r-- | bs4/tests/test_tree.py | 9 |
3 files changed, 26 insertions, 3 deletions
@@ -13,6 +13,10 @@ * Fixed yet another bug that caused a disconnected tree when html5lib copied an element from one part of the tree to another. [bug=1270611] +* __repr__ now returns an ASCII bytestring in Python 2, and a Unicode + string in Python 3, instead of a UTF8-encoded bytestring in both + versions. [bug=1420131] + * The select() method now supports selector grouping. Patch by Francisco Canas [bug=1191917] diff --git a/bs4/element.py b/bs4/element.py index 5d895ab..3c32c17 100644 --- a/bs4/element.py +++ b/bs4/element.py @@ -983,15 +983,25 @@ class Tag(PageElement): as defined in __eq__.""" return not self == other - def __repr__(self, encoding=DEFAULT_OUTPUT_ENCODING): + def __repr__(self, encoding="unicode-escape"): """Renders this tag as a string.""" - return self.encode(encoding) + if PY3K: + # "The return value must be a string object", i.e. Unicode + return self.decode() + else: + # "The return value must be a string object", i.e. a bytestring. + # By convention, the return value of __repr__ should also be + # an ASCII string. + return self.encode(encoding) def __unicode__(self): return self.decode() def __str__(self): - return self.encode() + if PY3K: + return self.decode() + else: + return self.encode() if PY3K: __str__ = __repr__ = __unicode__ diff --git a/bs4/tests/test_tree.py b/bs4/tests/test_tree.py index 7c44c48..bab73c6 100644 --- a/bs4/tests/test_tree.py +++ b/bs4/tests/test_tree.py @@ -19,6 +19,7 @@ from bs4.builder import ( HTMLParserTreeBuilder, ) from bs4.element import ( + PY3K, CData, Comment, Doctype, @@ -1490,6 +1491,14 @@ class TestEncoding(SoupTest): self.assertEqual( u"\N{SNOWMAN}".encode("utf8"), soup.b.renderContents()) + def test_repr(self): + html = u"<b>\N{SNOWMAN}</b>" + soup = self.soup(html) + if PY3K: + self.assertEqual(html, repr(soup)) + else: + self.assertEqual(b'<b>\\u2603</b>', repr(soup)) + class TestNavigableStringSubclasses(SoupTest): def test_cdata(self): |