Merge pull request #20 from jaysonsantos/speed-improvements

Make the code faster by compiling regex on global context and reusing named collection.

Author: retr0h

giturlparse/parser.py

@@ -23,6 +23,43 @@
 import collections
 import re
 
+Parsed = collections.namedtuple('Parsed', [
+    'pathname',
+    'protocols',
+    'protocol',
+    'href',
+    'resource',
+    'user',
+    'port',
+    'name',
+    'owner',
+])
+
+POSSIBLE_REGEXES = (
+    re.compile(r'^(?P<protocol>https?|git|ssh|rsync)\://'
+               r'(?:(?P<user>.+)@)*'
+               r'(?P<resource>[a-z0-9_.-]*)'
+               r'[:/]*'
+               r'(?P<port>[\d]+){0,1}'
+               r'(?P<pathname>\/(?P<owner>.+)/(?P<name>.+).git)'),
+    re.compile(r'(git\+)?'
+               r'((?P<protocol>\w+)://)'
+               r'((?P<user>\w+)@)?'
+               r'((?P<resource>[\w\.\-]+))'
+               r'(:(?P<port>\d+))?'
+               r'(?P<pathname>(\/(?P<owner>\w+)/)?'
+               r'(\/?(?P<name>[\w\-]+)(\.git)?)?)'),
+    re.compile(r'^(?:(?P<user>.+)@)*'
+               r'(?P<resource>[a-z0-9_.-]*)[:/]*'
+               r'(?P<port>[\d]+){0,1}'
+               r'[:](?P<pathname>\/?(?P<owner>.+)/(?P<name>.+).git)'),
+    re.compile(r'((?P<user>\w+)@)?'
+               r'((?P<resource>[\w\.\-]+))'
+               r'[\:\/]{1,2}'
+               r'(?P<pathname>((?P<owner>\w+)/)?'
+               r'((?P<name>[\w\-]+)(\.git)?)?)'),
+)
+
 
 class ParserError(Exception):
     """ Error raised when a URL can't be parsed. """
@@ -37,19 +74,6 @@ class Parser(object):
     def __init__(self, url):
         self._url = url
 
-    def get_parsed(self):
-        return collections.namedtuple('Parsed', [
-            'pathname',
-            'protocols',
-            'protocol',
-            'href',
-            'resource',
-            'user',
-            'port',
-            'name',
-            'owner',
-        ])
-
     def parse(self):
         """
         Parses a GIT URL and returns an object.  Raises an exception on invalid
@@ -69,47 +93,21 @@ def parse(self):
             'name': None,
             'owner': None,
         }
-        regexes = [
-            (r'^(?P<protocol>https?|git|ssh|rsync)\://'
-             r'(?:(?P<user>.+)@)*'
-             r'(?P<resource>[a-z0-9_.-]*)'
-             r'[:/]*'
-             r'(?P<port>[\d]+){0,1}'
-             r'(?P<pathname>\/(?P<owner>.+)/(?P<name>.+).git)'),
-            (r'(git\+)?'
-             r'((?P<protocol>\w+)://)'
-             r'((?P<user>\w+)@)?'
-             r'((?P<resource>[\w\.\-]+))'
-             r'(:(?P<port>\d+))?'
-             r'(?P<pathname>(\/(?P<owner>\w+)/)?'
-             r'(\/?(?P<name>[\w\-]+)(\.git)?)?)'),
-            (r'^(?:(?P<user>.+)@)*'
-             r'(?P<resource>[a-z0-9_.-]*)[:/]*'
-             r'(?P<port>[\d]+){0,1}'
-             r'[:](?P<pathname>\/?(?P<owner>.+)/(?P<name>.+).git)'),
-            (r'((?P<user>\w+)@)?'
-             r'((?P<resource>[\w\.\-]+))'
-             r'[\:\/]{1,2}'
-             r'(?P<pathname>((?P<owner>\w+)/)?'
-             r'((?P<name>[\w\-]+)(\.git)?)?)'),
-        ]
-        for regex in regexes:
-            if re.search(regex, self._url):
-                m = re.search(regex, self._url)
-                d.update(m.groupdict())
+        for regex in POSSIBLE_REGEXES:
+            match = regex.search(self._url)
+            if match:
+                d.update(match.groupdict())
                 break
         else:
             msg = "Invalid URL '{}'".format(self._url)
             raise ParserError(msg)
 
-        p = self.get_parsed()
-
-        return p(**d)
+        return Parsed(**d)
 
     def _get_protocols(self):
         try:
             index = self._url.index('://')
-
-            return self._url[0:index].split('+')
         except ValueError:
             return []
+
+        return self._url[:index].split('+')