urlmatch - pypi Package Compare versions

Comparing version 0.0.2 to 1.0.0

urlmatch/__init__.py

+from urlmatch import *

urlmatch/urlmatch.py

+"""
+urlmatch lets you easily check whether urls are on a domain or subdomain
+"""
+import re
+
+
+class BadMatchPattern(Exception):
+    """The Exception that's raised when a match pattern fails"""
+    pass
+
+
+def parse_match_pattern(pattern, path_required=True, fuzzy_scheme=False,
+                        http_auth_allowed=True):
+    """
+    Returns the regular expression for a given match pattern.
+
+    Args:
+        pattern: a `urlmatch` formatted match pattern
+        path_required: a `bool` which dicates whether the match pattern
+            must have path
+        fuzzy_scheme: if this is true, then if the scheme is `*`, `http`,
+            or `https`, it will match both `http` and `https`
+        http_auth_allowed: if this is true, then URLs with http auth on the
+            correct domain and path will be matched
+
+    Returns:
+        a regular expresion for the match pattern
+    """
+    if not isinstance(pattern, basestring):
+        return
+
+    pattern_regex = "(?:^"
+    result = re.search(r'^(\*|https?):\/\/', pattern)
+    if not result:
+        raise BadMatchPattern("Invalid scheme: {}".format(pattern))
+    elif result.group(1) == "*" or fuzzy_scheme:
+        pattern_regex += "https?"
+    else:
+        pattern_regex += result.group(1)
+
+    pattern_regex += "://"
+
+    if http_auth_allowed:
+        # add optional HTTP auth
+        safe_characters = "[^\/:.]"
+        pattern_regex += "(?:{safe}+(?:\:{safe}+)?@)?".format(
+            safe=safe_characters)
+
+    pattern = pattern[len(result.group(0)):]
+
+    domain_and_path_regex = r'^(?:\*|(\*\.)?([^\/*]+))'
+    if path_required:
+        domain_and_path_regex += r'(?=\/)'
+
+    result = re.search(domain_and_path_regex, pattern)
+    if not result:
+        raise BadMatchPattern("Invalid domain or path: {}".format(pattern))
+
+    pattern = pattern[len(result.group(0)):]
+
+    if result.group(0) == "*":
+        pattern_regex += "[^/]+"
+    else:
+        if result.group(1):
+            pattern_regex += "(?:[^/]+\\.)?"
+
+        pattern_regex += re.escape(result.group(2))
+
+    pattern_regex += ".*".join(map(re.escape, pattern.split("*")))
+    pattern_regex += r'(\/.*)?$)'
+
+    return pattern_regex
+
+
+def urlmatch(match_pattern, url, **kwargs):
+    """
+    Returns whether a given match pattern matches a url
+
+    Args:
+        match_pattern: a `urlmatch` formatted match pattern_regex
+        url: a url
+    """
+    if isinstance(match_pattern, basestring):
+        match_pattern = map(str.strip, match_pattern.split(','))
+
+    regex = "({})".format("|".join(map(
+        lambda x: parse_match_pattern(x, **kwargs), match_pattern)))
+
+    return bool(regex and re.search(regex, url))

PKG-INFO

 Metadata-Version: 1.1
 Name: urlmatch
-Version: 0.0.2
+Version: 1.0.0
 Summary: Python library for matching URLs.
@@ -37,3 +37,3 @@ Home-page: https://github.com/jessepollak/urlmatch
         
-        -  ``path_re1uired`` (default is True) - a ``bool`` which dictates
+        -  ``path_required`` (default is True) - a ``bool`` which dictates
            whether the match pattern must have path
@@ -44,3 +44,3 @@ -  ``fuzzy_scheme`` (default is False) - a ``bool`` which dictates
            ``http`` and ``https``
-        -  'http\_auth\_allowed' (default is True) - ``bool`` which dictates
+        -  ``http_auth_allowed`` (default is True) - ``bool`` which dictates
            whether URLs with HTTP Authentication in the URL should be allowed or
@@ -47,0 +47,0 @@ not

README.txt

@@ -29,3 +29,3 @@ urlmatch - fnmatch for the web
 
--  ``path_re1uired`` (default is True) - a ``bool`` which dictates
+-  ``path_required`` (default is True) - a ``bool`` which dictates
    whether the match pattern must have path
@@ -36,3 +36,3 @@ -  ``fuzzy_scheme`` (default is False) - a ``bool`` which dictates
    ``http`` and ``https``
--  'http\_auth\_allowed' (default is True) - ``bool`` which dictates
+-  ``http_auth_allowed`` (default is True) - ``bool`` which dictates
    whether URLs with HTTP Authentication in the URL should be allowed or
@@ -39,0 +39,0 @@ not

setup.py

@@ -15,6 +15,8 @@ try:
     name='urlmatch',
-    version='0.0.2',
+    version='1.0.0',
     author='Jesse Pollak',
     author_email='[e-mail]',
-    packages=[],
+    packages=[
+        'urlmatch'
+    ],
     url='https://github.com/jessepollak/urlmatch',
@@ -30,2 +32,2 @@ description=short_description,
     install_requires=[]
-)
+)

urlmatch.egg-info/PKG-INFO

 Metadata-Version: 1.1
 Name: urlmatch
-Version: 0.0.2
+Version: 1.0.0
 Summary: Python library for matching URLs.
@@ -37,3 +37,3 @@ Home-page: https://github.com/jessepollak/urlmatch
         
-        -  ``path_re1uired`` (default is True) - a ``bool`` which dictates
+        -  ``path_required`` (default is True) - a ``bool`` which dictates
            whether the match pattern must have path
@@ -44,3 +44,3 @@ -  ``fuzzy_scheme`` (default is False) - a ``bool`` which dictates
            ``http`` and ``https``
-        -  'http\_auth\_allowed' (default is True) - ``bool`` which dictates
+        -  ``http_auth_allowed`` (default is True) - ``bool`` which dictates
            whether URLs with HTTP Authentication in the URL should be allowed or
@@ -47,0 +47,0 @@ not

urlmatch.egg-info/SOURCES.txt

 README.txt
 setup.py
+urlmatch/__init__.py
+urlmatch/urlmatch.py
 urlmatch.egg-info/PKG-INFO
@@ -4,0 +6,0 @@ urlmatch.egg-info/SOURCES.txt

urlmatch.egg-info/top_level.txt

@@ -1,1 +0,1 @@
-
+urlmatch

Alert delta unavailable

Currently unable to show alert delta for PyPI packages.

Improved metrics

Total package byte prevSize

16605

19.88%

Number of package files

10

25%

Lines of code

96

269.23%