1
0
mirror of https://github.com/django/django.git synced 2025-10-26 15:16:09 +00:00

[py3] Ported django.utils.encoding.

* Renamed smart_unicode to smart_text (but kept the old name under
  Python 2 for backwards compatibility).
* Renamed smart_str to smart_bytes.
* Re-introduced smart_str as an alias for smart_text under Python 3
  and smart_bytes under Python 2 (which is backwards compatible).
  Thus smart_str always returns a str objects.
* Used the new smart_str in a few places where both Python 2 and 3
  want a str.
This commit is contained in:
Aymeric Augustin
2012-07-21 10:00:10 +02:00
parent ee191715ea
commit c5ef65bcf3
125 changed files with 629 additions and 583 deletions

View File

@@ -11,7 +11,7 @@ except ImportError: # Python 2
from urlparse import urlsplit, urlunsplit
from django.utils.safestring import SafeData, mark_safe
from django.utils.encoding import smart_str, force_unicode
from django.utils.encoding import smart_bytes, force_text
from django.utils.functional import allow_lazy
from django.utils import six
from django.utils.text import normalize_newlines
@@ -39,7 +39,7 @@ def escape(text):
"""
Returns the given text with ampersands, quotes and angle brackets encoded for use in HTML.
"""
return mark_safe(force_unicode(text).replace('&', '&amp;').replace('<', '&lt;').replace('>', '&gt;').replace('"', '&quot;').replace("'", '&#39;'))
return mark_safe(force_text(text).replace('&', '&amp;').replace('<', '&lt;').replace('>', '&gt;').replace('"', '&quot;').replace("'", '&#39;'))
escape = allow_lazy(escape, six.text_type)
_base_js_escapes = (
@@ -63,7 +63,7 @@ _js_escapes = (_base_js_escapes +
def escapejs(value):
"""Hex encodes characters for use in JavaScript strings."""
for bad, good in _js_escapes:
value = mark_safe(force_unicode(value).replace(bad, good))
value = mark_safe(force_text(value).replace(bad, good))
return value
escapejs = allow_lazy(escapejs, six.text_type)
@@ -120,22 +120,22 @@ linebreaks = allow_lazy(linebreaks, six.text_type)
def strip_tags(value):
"""Returns the given HTML with all tags stripped."""
return re.sub(r'<[^>]*?>', '', force_unicode(value))
return re.sub(r'<[^>]*?>', '', force_text(value))
strip_tags = allow_lazy(strip_tags)
def strip_spaces_between_tags(value):
"""Returns the given HTML with spaces between tags removed."""
return re.sub(r'>\s+<', '><', force_unicode(value))
return re.sub(r'>\s+<', '><', force_text(value))
strip_spaces_between_tags = allow_lazy(strip_spaces_between_tags, six.text_type)
def strip_entities(value):
"""Returns the given HTML with all entities (&something;) stripped."""
return re.sub(r'&(?:\w+|#\d+);', '', force_unicode(value))
return re.sub(r'&(?:\w+|#\d+);', '', force_text(value))
strip_entities = allow_lazy(strip_entities, six.text_type)
def fix_ampersands(value):
"""Returns the given HTML with all unencoded ampersands encoded correctly."""
return unencoded_ampersands_re.sub('&amp;', force_unicode(value))
return unencoded_ampersands_re.sub('&amp;', force_text(value))
fix_ampersands = allow_lazy(fix_ampersands, six.text_type)
def smart_urlquote(url):
@@ -153,9 +153,9 @@ def smart_urlquote(url):
# contains a % not followed by two hexadecimal digits. See #9655.
if '%' not in url or unquoted_percents_re.search(url):
# See http://bugs.python.org/issue2637
url = quote(smart_str(url), safe=b'!*\'();:@&=+$,/?#[]~')
url = quote(smart_bytes(url), safe=b'!*\'();:@&=+$,/?#[]~')
return force_unicode(url)
return force_text(url)
def urlize(text, trim_url_limit=None, nofollow=False, autoescape=False):
"""
@@ -176,7 +176,7 @@ def urlize(text, trim_url_limit=None, nofollow=False, autoescape=False):
"""
trim_url = lambda x, limit=trim_url_limit: limit is not None and (len(x) > limit and ('%s...' % x[:max(0, limit - 3)])) or x
safe_input = isinstance(text, SafeData)
words = word_split_re.split(force_unicode(text))
words = word_split_re.split(force_text(text))
for i, word in enumerate(words):
match = None
if '.' in word or '@' in word or ':' in word:
@@ -245,7 +245,7 @@ def clean_html(text):
bottom of the text.
"""
from django.utils.text import normalize_newlines
text = normalize_newlines(force_unicode(text))
text = normalize_newlines(force_text(text))
text = re.sub(r'<(/?)\s*b\s*>', '<\\1strong>', text)
text = re.sub(r'<(/?)\s*i\s*>', '<\\1em>', text)
text = fix_ampersands(text)