simplified html regex by removing useless named groups capture

daveoncode · daveoncode · commit 93194a277334 · 2015-08-12T15:38:16.000+02:00
diff --git a/string_utils.py b/string_utils.py
@@ -62,7 +62,7 @@
 IP_RE = re.compile(r'^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$')
 WORDS_COUNT_RE = re.compile(r'\W*[^\W_]+\W*', re.IGNORECASE | re.MULTILINE | re.UNICODE)
 HTML_RE = re.compile(
-    r'((?P<open><([a-z]+:)?[a-z]+[^>]*/?>)((?P<content>.*?)(?P<close></([a-z]+:)?[a-z]+>))?|<!--.*-->|<!doctype.*>)',
+    r'((<([a-z]+:)?[a-z]+[^>]*/?>)(.*?(</([a-z]+:)?[a-z]+>))?|<!--.*-->|<!doctype.*>)',
     re.IGNORECASE | re.MULTILINE | re.DOTALL
 )
 HTML_TAG_ONLY_RE = re.compile(

Original file line number	Diff line number	Diff line change
`@@ -62,7 +62,7 @@`
`62`	`62`	`IP_RE = re.compile(r'^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$')`
`63`	`63`	`WORDS_COUNT_RE = re.compile(r'\W[^\W_]+\W', re.IGNORECASE \| re.MULTILINE \| re.UNICODE)`
`64`	`64`	`HTML_RE = re.compile(`
`65`		`- r'((?P<open><([a-z]+:)?[a-z]+[^>]/?>)((?P<content>.?)(?P<close></([a-z]+:)?[a-z]+>))?\|<!--.-->\|<!doctype.>)',`
	`65`	`+ r'((<([a-z]+:)?[a-z]+[^>]/?>)(.?(</([a-z]+:)?[a-z]+>))?\|<!--.-->\|<!doctype.>)',`
`66`	`66`	`re.IGNORECASE \| re.MULTILINE \| re.DOTALL`
`67`	`67`	`)`
`68`	`68`	`HTML_TAG_ONLY_RE = re.compile(`