From 2b8f1dacc70c50b8667423512c465799cd2dc1da Mon Sep 17 00:00:00 2001
From: Connor Olding <cloningdonor@gmail.com>
Date: Fri, 4 Sep 2020 16:06:37 +0200
Subject: [PATCH] merge arrays of Checks and partition by failures

---
 respodns/checks.py | 45 +++++++++++++++++++++++++++------------------
 respodns/ui.py     |  4 +---
 2 files changed, 28 insertions(+), 21 deletions(-)

diff --git a/respodns/checks.py b/respodns/checks.py
index 381bffc..60bf912 100644
--- a/respodns/checks.py
+++ b/respodns/checks.py
@@ -7,6 +7,16 @@ def order_by_failures(checks):  # descending
     return sorted(checks, key=lambda check: -check.failures)
 
 
+def partition_checks(checks, n):
+    more, less = [], []
+    for check in checks:
+        if check.failures >= n:
+            more.append(check)
+        else:
+            less.append(check)
+    return more, less
+
+
 first = [
     # checking this first this avoids issues with censorship in China. see:
     # https://www.bortzmeyer.org/sichuan-pepper.html
@@ -16,54 +26,50 @@ first = [
 _sinkhole = "iuqerfsodp9ifjaposdfjhgosurijfaewrwergwea.com"
 _weirdsub = concat_nonsense("javarevisited.blogspot.com")
 
-likely = order_by_failures([
+checks = order_by_failures([
     # these checks are, in practice, the most likely
     # to weed out unwanted DNS servers.
 
+    # Check("common",         "naver.com", 57),
+    # Check("weird",          "archive.is", 0),
     Check("adtrack",        "ad.doubleclick.net", 81),
     Check("adtrack",        "google-analytics.com", 75),
     Check("adtrack",        "media.fastclick.net", 116),
     Check("adware",         rot13("nqf789.pbz"), 168),
     Check("bad",            concat_nonsense("com"), 153),
     Check("badsub",         concat_nonsense("google.com"), 63),
+    Check("common",         "aliexpress.com", 2),
     Check("common",         "archive.org", 98),
     Check("common",         "duckduckgo.com", 78),
+    Check("common",         "ebay.com", 4),
     Check("common",         "en.wikipedia.org", 75),
     Check("common",         "facebook.com", 94),
     Check("common",         "google.com", 69),
-    # Check("common",         "naver.com", 57),
     Check("common",         "paypal.com", 74),
+    Check("common",         "qq.com", 15),
+    Check("common",         "stackoverflow.com", 1),
+    Check("common",         "tmall.com", 8),
     Check("common",         "wikileaks.com", 86),
     Check("common",         "xn--b1aew.xn--p1ai", 85),
     Check("gambling",       "bet365.com", 157),
     Check("gambling",       "betonline.ag", 168),
     Check("gambling",       "unibet.com", 137),
-    Check("infosec",        _sinkhole, 98),
     Check("infosec",        "scan.shadowserver.org", 73),
+    Check("infosec",        _sinkhole, 98),
     Check("news",           "huanqiu.com", 435),
+    Check("news",           "nytimes.com", 6),
+    Check("news",           "scmp.com", 3),
     Check("news",           "telegram.com", 71),
     Check("parking",        "scmp.org", 132),
     Check("piracy",         "thehiddenbay.org", 77),
+    Check("piracy",         "thepiratebay.org", 24),
+    Check("porn",           "chaturbate.com", 18),
     Check("porn",           "pornhub.com", 151),
+    Check("porn",           "xvideos.com", 23),
     Check("shock",          rot13("tbng.pk"), 209),
     Check("uncommon",       "cybre.space", 88),
     Check("uncommon",       "react.uni-saarland.de", 74),
     Check("usercontent",    "4chan.org", 116),
-    # Check("weird",          "archive.is", 0),
-    Check("weirdsub",       _weirdsub, 126),
-])
-
-unlikely = order_by_failures([
-    Check("common",         "aliexpress.com", 2),
-    Check("common",         "ebay.com", 4),
-    Check("common",         "qq.com", 15),
-    Check("common",         "stackoverflow.com", 1),
-    Check("common",         "tmall.com", 8),
-    Check("news",           "nytimes.com", 6),
-    Check("news",           "scmp.com", 3),
-    Check("piracy",         "thepiratebay.org", 24),
-    Check("porn",           "chaturbate.com", 18),
-    Check("porn",           "xvideos.com", 23),
     Check("usercontent",    "facebook.com", 12),
     Check("usercontent",    "flickr.com", 5),
     Check("usercontent",    "github.com", 19),
@@ -78,8 +84,11 @@ unlikely = order_by_failures([
     Check("video",          "netflix.com", 14),
     Check("video",          "twitch.tv", 16),
     Check("video",          "youtube.com", 11),
+    Check("weirdsub",       _weirdsub, 126),
 ])
 
+likely, unlikely = partition_checks(checks, 50)
+
 defunct = [
     "panda.tv",  # imochen.github.io
 ]
diff --git a/respodns/ui.py b/respodns/ui.py
index 1b0de2c..7651f86 100644
--- a/respodns/ui.py
+++ b/respodns/ui.py
@@ -21,9 +21,7 @@ def ui(program, args):
 
     a = parser.parse_args(args)
 
-    checks = []
-    checks += chk.first
-    checks += chk.likely
+    checks = chk.first + chk.likely
 
     opts = Options()
     opts.dry = a.database is None