- changed tessil map to robbin hood library

- fix: the library was changing the original domain when it included
  upper cased chars
- updated public suffix list

Author: Gal Ben David

README.md

@@ -39,7 +39,7 @@ PyDomainExtractor is a library intended for parsing domain names into their part
 ### Built With
 
 * [GNU libidn2](https://www.gnu.org/software/libidn/#libidn2)
-* [Tessil/robin-map](https://github.com/Tessil/robin-map)
+* [robin-hood-hashing](https://github.com/martinus/robin-hood-hashing)
 * [Public Suffix List](https://publicsuffix.org/)
 
 

setup.py

@@ -5,7 +5,7 @@
 
 setuptools.setup(
     name='PyDomainExtractor',
-    version='0.8.4',
+    version='0.8.5',
     author='Gal Ben David',
     author_email='[email protected]',
     url='https://github.com/Intsights/PyDomainExtractor',

src/public_suffix_list.h

@@ -1157,7 +1157,7 @@ gov.gr
 // gs : https://en.wikipedia.org/wiki/.gs
 gs
 
-// gt : http://www.gt/politicas_de_registro.html
+// gt : https://www.gt/sitio/registration_policy.php?lang=en
 gt
 com.gt
 edu.gt
@@ -7115,7 +7115,7 @@ org.zw
 
 // newGTLDs
 
-// List of new gTLDs imported from https://www.icann.org/resources/registries/gtlds/v2/gtlds.json on 2020-10-08T17:45:32Z
+// List of new gTLDs imported from https://www.icann.org/resources/registries/gtlds/v2/gtlds.json on 2020-10-28T17:55:28Z
 // This list is auto-generated, don't edit it manually.
 // aaa : 2015-02-26 American Automobile Association, Inc.
 aaa
@@ -7333,7 +7333,7 @@ author
 // auto : 2014-11-13 XYZ.COM LLC
 auto
 
-// autos : 2014-01-09 DERAutos, LLC
+// autos : 2014-01-09 XYZ.COM LLC
 autos
 
 // avianca : 2015-01-08 Avianca Holdings S.A.
@@ -7483,7 +7483,7 @@ bmw
 // bnpparibas : 2014-05-29 BNP Paribas
 bnpparibas
 
-// boats : 2014-12-04 DERBoats, LLC
+// boats : 2014-12-04 XYZ.COM LLC
 boats
 
 // boehringer : 2015-07-09 Boehringer Ingelheim International GmbH
@@ -7522,7 +7522,7 @@ bot
 // boutique : 2013-11-14 Binky Moon, LLC
 boutique
 
-// box : 2015-11-12 .BOX INC.
+// box : 2015-11-12 Intercap Registry Inc.
 box
 
 // bradesco : 2014-12-18 Banco Bradesco S.A.
@@ -8506,7 +8506,7 @@ homedepot
 // homegoods : 2015-07-16 The TJX Companies, Inc.
 homegoods
 
-// homes : 2014-01-09 DERHomes, LLC
+// homes : 2014-01-09 XYZ.COM LLC
 homes
 
 // homesense : 2015-07-16 The TJX Companies, Inc.
@@ -9082,7 +9082,7 @@ moscow
 // moto : 2015-06-04 Motorola Trademark Holdings, LLC
 moto
 
-// motorcycles : 2014-01-09 DERMotorcycles, LLC
+// motorcycles : 2014-01-09 XYZ.COM LLC
 motorcycles
 
 // mov : 2014-01-30 Charleston Road Registry Inc.
@@ -9247,7 +9247,7 @@ one
 // ong : 2014-03-06 Public Interest Registry
 ong
 
-// onl : 2013-09-16 I-Registry Ltd.
+// onl : 2013-09-16 iRegistry GmbH
 onl
 
 // online : 2015-01-15 DotOnline Inc.
@@ -9544,7 +9544,7 @@ reviews
 // rexroth : 2015-06-18 Robert Bosch GMBH
 rexroth
 
-// rich : 2013-11-21 I-Registry Ltd.
+// rich : 2013-11-21 iRegistry GmbH
 rich
 
 // richardli : 2015-05-14 Pacific Century Asset Management (HK) Limited
@@ -10600,7 +10600,7 @@ vermögensberatung
 // xyz : 2013-12-05 XYZ.COM LLC
 xyz
 
-// yachts : 2014-01-09 DERYachts, LLC
+// yachts : 2014-01-09 XYZ.COM LLC
 yachts
 
 // yahoo : 2015-04-02 Yahoo! Domain Services Inc.
@@ -10685,12 +10685,6 @@ barsy.ca
 // Submitted by Werner Kaltofen <[email protected]>
 kasserver.com
 
-// Algorithmia, Inc. : algorithmia.com
-// Submitted by Eli Perelman <[email protected]>
-*.algorithmia.com
-!teams.algorithmia.com
-!test.algorithmia.com
-
 // Altervista: https://www.altervista.org
 // Submitted by Carlo Cannas <[email protected]>
 altervista.org
@@ -11807,6 +11801,10 @@ ukco.me
 // submitted by Koen Van Isterdael <[email protected]>
 mydobiss.com
 
+// FH Muenster : https://www.fh-muenster.de
+// Submitted by Robin Naundorf <[email protected]>
+fh-muenster.io
+
 // Filegear Inc. : https://www.filegear.com
 // Submitted by Jason Zhu <[email protected]>
 filegear.me
@@ -11877,6 +11875,7 @@ usercontent.jp
 gentapps.com
 gentlentapis.com
 lab.ms
+cdn-edges.net
 
 // GitHub, Inc.
 // Submitted by Patrick Toomey <[email protected]>
@@ -11936,9 +11935,10 @@ pagespeedmobilizer.com
 publishproxy.com
 withgoogle.com
 withyoutube.com
-cloudfunctions.net
+*.gateway.dev
 cloud.goog
 translate.goog
+cloudfunctions.net
 
 blogspot.ae
 blogspot.al
@@ -12451,11 +12451,17 @@ eu.meteorapp.com
 co.pl
 
 // Microsoft Corporation : http://microsoft.com
-// Submitted by Mostafa Elzeiny <moelzein@microsoft.com>
+// Submitted by Mitch Webster <miwebst@microsoft.com>
 *.azurecontainer.io
 azurewebsites.net
 azure-mobile.net
 cloudapp.net
+azurestaticapps.net
+centralus.azurestaticapps.net
+eastasia.azurestaticapps.net
+eastus2.azurestaticapps.net
+westeurope.azurestaticapps.net
+westus2.azurestaticapps.net
 
 // minion.systems : http://minion.systems
 // Submitted by Robert Böttinger <[email protected]>
@@ -12890,6 +12896,10 @@ byen.site
 // Submitted by Kor Nielsen <[email protected]>
 pubtls.org
 
+// QOTO, Org.
+// Submitted by Jeffrey Phillips Freeman <[email protected]>
+qoto.io
+
 // Qualifio : https://qualifio.com/
 // Submitted by Xavier De Cock <[email protected]>
 qualifioapp.com

src/pydomainextractor.cpp

@@ -10,8 +10,8 @@
 #include <codecvt>
 #include <memory>
 #include <idn2.h>
-#include <tsl/robin_set.h>
 
+#include "robin_hood.h"
 #include "public_suffix_list.h"
 
 
@@ -262,12 +262,12 @@ class DomainExtractor {
             return true;
         }
 
-        tsl::robin_set<std::string> known_tlds;
-        tsl::robin_set<std::string> blacklisted_tlds;
-        tsl::robin_set<std::string> wildcard_tlds;
-        tsl::robin_set<std::string_view> known_tlds_views;
-        tsl::robin_set<std::string_view> blacklisted_tlds_views;
-        tsl::robin_set<std::string_view> wildcard_tlds_views;
+        robin_hood::unordered_set<std::string> known_tlds;
+        robin_hood::unordered_set<std::string> blacklisted_tlds;
+        robin_hood::unordered_set<std::string> wildcard_tlds;
+        robin_hood::unordered_set<std::string_view> known_tlds_views;
+        robin_hood::unordered_set<std::string_view> blacklisted_tlds_views;
+        robin_hood::unordered_set<std::string_view> wildcard_tlds_views;
 };
 
 
@@ -326,7 +326,7 @@ static PyObject * DomainExtractor_extract(
     DomainExtractorObject * self,
     PyObject * arg
 ) {
-    const char * input = PyUnicode_AsUTF8(arg);
+    std::string input(PyUnicode_AsUTF8(arg));
 
     try {
         auto extracted_domain = self->domain_extractor->extract(input);
@@ -382,7 +382,7 @@ static PyObject * DomainExtractor_extract_from_url(
     DomainExtractorObject * self,
     PyObject * arg
 ) {
-    const char * input = PyUnicode_AsUTF8(arg);
+    std::string input(PyUnicode_AsUTF8(arg));
     std::string_view url(input);
 
     std::size_t scheme_separator_position = url.find("//");
@@ -463,7 +463,7 @@ static PyObject * DomainExtractor_is_valid_domain(
     DomainExtractorObject * self,
     PyObject * arg
 ) {
-    const char * input = PyUnicode_AsUTF8(arg);
+    std::string input(PyUnicode_AsUTF8(arg));
 
     auto valid_domain = self->domain_extractor->is_valid_domain(std::string(input));
     if (valid_domain == true) {