Fix false positive extraction of the adblock decoder.

This patch fix #13.

Reverse:
  * Of the last patch for the way we check for URL.

Introduction:
  * Of new test cases.
  * Of the force update for all version which are older than `0.94.3`.
    * Because of this patch.

Review:
  * Of the way we extract domain and URL from the given adblock file.

Deprecation:
  * Of all version which are equal or older than `0.109.0`.

Thanks:
  * To @dnmTX
  * @adblockplus for their documentation
    * cf: https://adblockplus.org/filter-cheatsheet

PyFunceble/__init__.py

@@ -79,7 +79,7 @@
 # We set our project name.
 NAME = "PyFunceble"
 # We set out project version.
-VERSION = "0.109.0.dev-beta (Sarcoline Puku / Mosquito)"
+VERSION = "0.110.0.dev-beta (Sarcoline Puku / Mosquito)"
 
 if "PYFUNCEBLE_OUTPUT_DIR" in environ:  # pragma: no cover
     # We handle the case that the `PYFUNCEBLE_OUTPUT_DIR` environnement variable is set.

PyFunceble/check.py

@@ -122,7 +122,7 @@ def is_url_valid(self, url=None, return_formated=False):
 
             try:
                 # We initiate a regex which will match the domain or the url base.
-                regex = r"(^([a-z]+:\/\/)(.+?(?=\/)|.+?$))"
+                regex = r"(^(http:\/\/|https:\/\/)(.+?(?=\/)|.+?$))"
 
                 # We extract the url base with the help of the initiated regex.
                 formated_base = Regex(

PyFunceble/core.py

@@ -637,6 +637,13 @@ def _format_adblock_decoded(cls, to_format, result=None):
             if data:
                 # The currently read line is not empty.
 
+                if "^" in data:
+                    # There is an accent in the currently read line.
+
+                    # We recall this method but with the current result state
+                    # and splited data.
+                    return cls._format_adblock_decoded(data.split("^"), result)
+
                 if "#" in data:
                     # There is a dash in the currently read line.
 
@@ -651,13 +658,6 @@ def _format_adblock_decoded(cls, to_format, result=None):
                     # and splited data.
                     return cls._format_adblock_decoded(data.split(","), result)
 
-                if "~" in data:
-                    # There is a tilde in the currently read line.
-
-                    # We recall this method but with the current result state
-                    # and splited data.
-                    return cls._format_adblock_decoded(data.split("~"), result)
-
                 if "!" in data:
                     # There is an exclamation mark in the currently read line.
 
@@ -719,28 +719,38 @@ def _adblock_decode(self, list_to_test):
         # the element to format.
         regex = r"^(?:.*\|\|)([^\/\$\^]{1,}).*$"
 
-        # We initiate the second regex we are going to use to get
+        # We initiate the third regex we are going to use to get
         # the element to format.
-        regex_v2 = r"((.*\..*)(?:#{1,}.*))"
+        regex_v3 = (
+            r"(?:#+(?:[a-z]+?)?\[[a-z]+(?:\^|\*)\=(?:\'|\"))(.*\..*)(?:(?:\'|\")\])"
+        )
 
-        # We initiate the third regex we are going to use to get
+        # We initiate the fourth regex we are going to use to get
         # the element to format.
-        regex_v3 = r"(?:#+(?:[a-z]+?)?\[[a-z]+\^\=(?:\'|\"))(.*\..*)(?:(?:\'|\")\])"
+        regex_v4 = r"^\|(.*\..*)\|$"
 
         for line in list_to_test:
             # We loop through the different line.
 
-            if line.startswith("!"):
+            if (
+                line.startswith("!")
+                or line.startswith("@@")
+                or line.startswith("/")
+                or line.startswith("[")
+            ):
                 continue
 
             # We extract the different group from our first regex.
             rematch = Regex(
                 line, regex, return_data=True, rematch=True, group=0
             ).match()
 
-            # We extract the different group from our second regex.
-            rematch_v2 = Regex(
-                line, regex_v2, return_data=True, rematch=True, group=0
+            # We extract the different group from our fourth regex.
+            #
+            # Note: We execute the following in second because it is more
+            # specific that others.
+            rematch_v4 = Regex(
+                line, regex_v4, return_data=True, rematch=True, group=0
             ).match()
 
             # We extract the different group from our third regex.
@@ -754,11 +764,11 @@ def _adblock_decode(self, list_to_test):
                 # We extend the result with the extracted elements.
                 result.extend(rematch)
 
-            if rematch_v2:
-                # The second extraction was successfull.
+            if rematch_v4:
+                # The fourth extraction was successfull.
 
                 # We extend the formated elements from the extracted elements.
-                result.extend(List(self._format_adblock_decoded(rematch_v2)).format())
+                result.extend(List(self._format_adblock_decoded(rematch_v4)).format())
 
             if rematch_v3:
                 # The second extraction was successfull.

tests/test_core.py

@@ -353,45 +353,38 @@ def setUp(self):
 
         load_config(True)
         self.lines = [
-            "||google.com$script,image",
-            "||twitter.com^",
+            "||funilrys.github.io$script,image",
+            "||google.com^$script,image",
+            "||twitter.com^helloworld.com",
             "||api.google.com/papi/action$popup",
             "facebook.com###player-above-2",
             "~github.com,hello.world##.wrapper",
             "@@||cnn.com/*ad.xml",
             "!||world.hello/*ad.xml",
             "bing.com,bingo.com#@##adBanner",
             "!@@||funceble.world/js",
-            "yahoo.com,msn.com,api.hello.world#@#awesomeWorld",
+            "yahoo.com,~msn.com,api.hello.world#@#awesomeWorld",
             "!funilrys.com##body",
             "hello#@#badads",
             "hubgit.com|oohay.com|ipa.elloh.dlorw#@#awesomeWorld",
             '##[href^="https://funceble.funilrys.com/"]',
+            "[AdBlock Plus 2.0]",
             '##div[href^="http://funilrys.com/"]',
-            '##[href^="ftp://funceble.funilrys.com/"]',
+            'com##[href^="ftp://funceble.funilrys-funceble.com/"]',
+            "/banner/*/img^" "|github.io|",
+            "|github.io|",
+            "||api.funilrys.com/widget/$",
         ]
 
         self.expected = [
+            "funilrys.github.io",
             "google.com",
             "twitter.com",
             "api.google.com",
-            "facebook.com",
-            "github.com",
-            "hello.world",
-            "cnn.com",
-            "world.hello",
-            "bing.com",
-            "bingo.com",
-            "funceble.world",
-            "api.hello.world",
-            "msn.com",
-            "yahoo.com",
-            "funilrys.com",
-            "hubgit.com",
-            "ipa.elloh.dlorw",
-            "oohay.com",
             "funceble.funilrys.com",
             "funilrys.com",
+            "github.io",
+            "api.funilrys.com",
         ]
 
     def test_adblock_decode(self):

version.yaml

@@ -1,9 +1,9 @@
-current_version: 0.109.0.dev-beta (Sarcoline Puku / Mosquito)
+current_version: 0.110.0.dev-beta (Sarcoline Puku / Mosquito)
 deprecated: [0.0.0, 0.0.1, 0.65.0, 0.67.1, 0.68.0, 0.69.3, 0.69.5, 0.70.4, 0.71.2,
     0.72.7, 0.73.1, 0.74.5, 0.75.1, 0.76.2, 0.77.0, 0.78.0, 0.79.1, 0.80.9, 0.81.8,
     0.82.4, 0.83.2, 0.84.5, 0.85.0, 0.86.0, 0.87.1, 0.88.3, 0.89.3, 0.90.2, 0.91.1,
     0.92.0, 0.93.0, 0.94.6, 0.95.1, 0.96.2, 0.97.1, 0.98.0, 0.99.4, 0.100.0, 0.101.23,
-    0.102.0, 0.103.3, 0.104.4, 0.105.1, 0.106.2, 0.107.1, 0.108.1]
+    0.102.0, 0.103.3, 0.104.4, 0.105.1, 0.106.2, 0.107.1, 0.108.1, 0.109.0]
 force_update:
-    minimal_version: [0.0.0, 0.0.1, 0.82.5, 0.89.2]
+    minimal_version: [0.0.0, 0.0.1, 0.82.5, 0.89.2, 0.94.3]
     status: true