diff options
| author | Stefan Behnel <stefan_ml@behnel.de> | 2013-08-01 06:18:47 +0200 |
|---|---|---|
| committer | Stefan Behnel <stefan_ml@behnel.de> | 2013-08-01 06:18:47 +0200 |
| commit | ef52eb5cff33d61b8a4195bfadb01b2fb034daf9 (patch) | |
| tree | 92a9a2c03baa6230ac964f51b0c34060214c5628 /src/lxml/html/diff.py | |
| parent | 2988c135dba40054b0022a98473cead02edc2d8c (diff) | |
| download | python-lxml-ef52eb5cff33d61b8a4195bfadb01b2fb034daf9.tar.gz | |
use Unicode whitespace in regex
Diffstat (limited to 'src/lxml/html/diff.py')
| -rw-r--r-- | src/lxml/html/diff.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/src/lxml/html/diff.py b/src/lxml/html/diff.py index 79eb4112..c6a62c67 100644 --- a/src/lxml/html/diff.py +++ b/src/lxml/html/diff.py @@ -705,7 +705,7 @@ def flatten_el(el, include_hrefs, skip_tag=False): for word in end_words: yield html_escape(word) -split_words_re = re.compile(r'\S+(?:\s+|$)') +split_words_re = re.compile(r'\S+(?:\s+|$)', re.U) def split_words(text): """ Splits some text into words. Includes trailing whitespace |