Merge pull request #57 from pyupio/security/remove-intensive-regex

Removing index server validation

Author: yeisonvargasf

dparse/parser.py

@@ -8,7 +8,7 @@
 from configparser import ConfigParser, NoOptionError
 
 
-from .regex import URL_REGEX, HASH_REGEX
+from .regex import HASH_REGEX
 
 from .dependencies import DependencyFile, Dependency
 from packaging.requirements import Requirement as PackagingRequirement, InvalidRequirement
@@ -175,10 +175,11 @@ def parse_index_server(cls, line):
         :param line:
         :return:
         """
-        matches = URL_REGEX.findall(line)
-        if matches:
-            url = matches[0]
-            return url if url.endswith("/") else url + "/"
+        groups = re.split(pattern="[=\s]+", string=line.strip(), maxsplit=100)
+
+        if len(groups) >= 2:
+            return groups[1] if groups[1].endswith("/") else groups[1] + "/"
+
         return None
 
     @classmethod
@@ -346,6 +347,7 @@ def parse(self):
         except (toml.TomlDecodeError, IndexError) as e:
             pass
 
+
 class PipfileLockParser(Parser):
 
     def parse(self):

dparse/regex.py

@@ -1,39 +1,4 @@
 # -*- coding: utf-8 -*-
 from __future__ import absolute_import, print_function, unicode_literals
 
-import re
-# see https://gist.github.com/dperini/729294
-URL_REGEX = re.compile(
-    # protocol identifier
-    "(?:(?:https?|ftp)://)"
-    # user:pass authentication
-    "(?:\S+(?::\S*)?@)?"
-    "(?:"
-    # IP address exclusion
-    # private & local networks
-    "(?!(?:10|127)(?:\.\d{1,3}){3})"
-    "(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})"
-    "(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})"
-    # IP address dotted notation octets
-    # excludes loopback network 0.0.0.0
-    # excludes reserved space >= 224.0.0.0
-    # excludes network & broadcast addresses
-    # (first & last IP address of each class)
-    "(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])"
-    "(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}"
-    "(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))"
-    "|"
-    # host name
-    "(?:(?:[a-z\u00a1-\uffff0-9]-?)*[a-z\u00a1-\uffff0-9]+)"
-    # domain name
-    "(?:\.(?:[a-z\u00a1-\uffff0-9]-?)*[a-z\u00a1-\uffff0-9]+)*"
-    # TLD identifier
-    "(?:\.(?:[a-z\u00a1-\uffff]{2,}))"
-    ")"
-    # port number
-    "(?::\d{2,5})?"
-    # resource path
-    "(?:/\S*)?",
-    re.UNICODE)
-
-HASH_REGEX = r"--hash[=| ][\w]+:[\w]+"
+HASH_REGEX = r"--hash[=| ]\w+:\w+"