Initial working library

11 files changed, 683 insertions, 0 deletions

diff --git a/COPYING b/COPYING
new file mode 100644
index 0000000..d448ee3
--- /dev/null
+++ b/COPYING
@@ -0,0 +1,19 @@
+Copyright 2016 Vincent Sanders <vince@netsurf-browser.org>
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+  * The above copyright notice and this permission notice shall be included in
+    all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
diff --git a/Makefile b/Makefile
new file mode 100644
index 0000000..1a9c1ed
--- /dev/null
+++ b/Makefile
@@ -0,0 +1,48 @@
+#!/bin/make
+#
+# Makefile for libnspsl
+#
+# Copyright 2016 Vincent Sanders <vince@netsurf-browser.org>
+
+# Component settings
+COMPONENT := nspsl
+COMPONENT_VERSION := 0.0.1
+# Default to a static library
+COMPONENT_TYPE ?= lib-static
+
+# Setup the tooling
+PREFIX ?= /opt/netsurf
+NSSHARED ?= $(PREFIX)/share/netsurf-buildsystem
+include $(NSSHARED)/makefiles/Makefile.tools
+
+# Reevaluate when used, as BUILDDIR won't be defined yet
+TESTRUNNER = test/runtest.sh $(BUILDDIR) $(EXEEXT)
+
+# Toolchain flags
+WARNFLAGS := -Wall -W -Wundef -Wpointer-arith -Wcast-align \
+	-Wwrite-strings -Wstrict-prototypes -Wmissing-prototypes \
+	-Wmissing-declarations -Wnested-externs
+
+CFLAGS := -D_GNU_SOURCE -D_DEFAULT_SOURCE \
+	-I$(CURDIR)/include/ -I$(CURDIR)/src \
+	$(WARNFLAGS) $(CFLAGS)
+ifneq ($(GCCVER),2)
+  CFLAGS := $(CFLAGS) -std=c99
+else
+  # __inline__ is a GCCism
+  CFLAGS := $(CFLAGS) -Dinline="__inline__"
+endif
+CFLAGS := $(CFLAGS) -D_POSIX_C_SOURCE=200809L
+
+REQUIRED_LIBS := nspsl
+
+TESTCFLAGS := -g -O2
+TESTLDFLAGS := -l$(COMPONENT) $(TESTLDFLAGS)
+
+include $(NSBUILD)/Makefile.top
+
+# Extra installation rules
+I := /$(INCLUDEDIR)
+INSTALL_ITEMS := $(INSTALL_ITEMS) $(I):include/nspsl.h
+INSTALL_ITEMS := $(INSTALL_ITEMS) /$(LIBDIR)/pkgconfig:lib$(COMPONENT).pc.in
+INSTALL_ITEMS := $(INSTALL_ITEMS) /$(LIBDIR):$(OUTPUT)
diff --git a/README b/README
new file mode 100644
index 0000000..792e62e
--- /dev/null
+++ b/README
@@ -0,0 +1,4 @@
+library to generate static code representation of the Public suffix list
+
+https://publicsuffix.org
+
diff --git a/include/nspsl.h b/include/nspsl.h
new file mode 100644
index 0000000..2358167
--- /dev/null
+++ b/include/nspsl.h
@@ -0,0 +1,10 @@
+/*
+ * Copyright 2016 Vincent Sanders <vince@netsurf-browser.org>
+ *
+ * This file is part of libnspsl
+ *
+ * Licensed under the MIT License,
+ *                http://www.opensource.org/licenses/mit-license.php
+ */
+
+const char *nspsl_getpublicsuffix(const char *hostname);
diff --git a/libnspsl.pc.in b/libnspsl.pc.in
new file mode 100644
index 0000000..91aff99
--- /dev/null
+++ b/libnspsl.pc.in
@@ -0,0 +1,10 @@
+prefix=PREFIX
+exec_prefix=${prefix}
+libdir=${exec_prefix}/LIBDIR
+includedir=${prefix}/INCLUDEDIR
+
+Name: libnspsl
+Description: NetSurf Public Suffix List
+Version: VERSION
+Libs: -L${libdir} LIBRARIES
+Cflags: -I${includedir}
diff --git a/src/Makefile b/src/Makefile
new file mode 100644
index 0000000..1121639
--- /dev/null
+++ b/src/Makefile
@@ -0,0 +1,13 @@
+CFLAGS := $(CFLAGS) -I$(BUILDDIR)
+
+DIR_SOURCES := nspsl.c
+
+src/nspsl.c:$(BUILDDIR)/psl.inc
+
+$(BUILDDIR)/psl.inc:$(BUILDDIR)/public_suffix_list.dat
+	perl src/genpubsuffix.pl $< > $@
+
+$(BUILDDIR)/public_suffix_list.dat:
+	wget -O $@ https://publicsuffix.org/list/public_suffix_list.dat
+
+include $(NSBUILD)/Makefile.subdir
diff --git a/src/genpubsuffix.pl b/src/genpubsuffix.pl
new file mode 100644
index 0000000..7323645
--- /dev/null
+++ b/src/genpubsuffix.pl
@@ -0,0 +1,298 @@
+#
+# Public suffix C include generator
+#
+# Copyright 2016 Vincent Sanders <vince@kyllikki.og>
+#
+# Permission to use, copy, modify, and/or distribute this software for
+# any purpose with or without fee is hereby granted, provided that the
+# above copyright notice and this permission notice appear in all
+# copies.
+#
+# THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL
+# WARRANTIES WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED
+# WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE
+# AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL
+# DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA
+# OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
+# TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
+# PERFORMANCE OF THIS SOFTWARE.
+
+
+# This program converts the public suffix list data [1] into a C
+#  program with static data representation and acessor function.
+#
+# The actual data list [2] should be placed in a file effective_tld_names.dat
+#
+# The C program is written to stdout, the typical 160K input file
+#  generates 500K of program and compiles down to a 100K object file
+#
+# There is a single exported function
+#
+# const char *getpublicsuffix(const char *hostname)
+# 
+# This returns the public suffix of the passed hostname or NULL if
+#  there was an error processing the hostname. The returned pointer is
+#  within the passed hostname so if the returned pointer is the same as
+#  hostname the whole hostname is a public suffix otherwise the passed
+#  hostname has a private part.
+#
+# The resulting C file is mearly a conversion of the input data (the
+#  added c code is from this source and licenced under the same terms)
+#  and imposes no additional copyright above that of the source data
+#  file.
+#
+# Note: The pnode structure is built assuming there will never be more
+#  label nodes than can fit in an unsigned 16 bit value (65535) but as
+#  there are currently around 8000 nodes there is space for another
+#  58,000 before this becomes an issue.
+#
+# [1] https://publicsuffix.org/
+# [2] https://publicsuffix.org/list/effective_tld_names.dat
+
+
+# debian package for ordered hashes: libtie-ixhash-perl
+# debian package for punycode encode: libidna-punycode-perl
+
+use strict;
+use warnings;
+use utf8;
+use Tie::IxHash;
+use IDNA::Punycode;
+
+sub treesubdom
+{
+    my ($tldtree_ref, $nodeidx_ref, $strtab_ref, $stridx_ref, $parts_ref) = @_;
+
+    my $domelem = pop @{$parts_ref}; # Doamin element
+    my $isexception = 0;
+    tie my %node, 'Tie::IxHash'; # this nodes hash
+
+    # deal with explicit domain exceptions 
+    $isexception = ($domelem =~ s/\A!//);
+    if ($isexception != 0) {
+	$node{"!"} = {};
+	$$nodeidx_ref += 1;
+    }
+    my $domelem_puny = encode_punycode($domelem);
+
+    # Update string table
+    if (! exists $strtab_ref->{$domelem_puny}) {
+	# add to string table
+	$strtab_ref->{$domelem_puny} = $$stridx_ref;
+	{
+	    use bytes;
+	    # update the character count index
+	    $$stridx_ref += length($domelem_puny);
+	}
+	
+    }
+
+    # link new node list into tree
+    if (! exists $tldtree_ref->{$domelem_puny}) {
+	$tldtree_ref->{$domelem_puny} = \%node;
+	$$nodeidx_ref += 1;
+    }
+    
+    # recurse down if there are more parts to the domain
+    if (($isexception == 0) && (scalar(@{$parts_ref}) > 0)) {
+	treesubdom($tldtree_ref->{$domelem_puny}, $nodeidx_ref, $strtab_ref, $stridx_ref, $parts_ref);
+    }
+}
+
+# output string table
+#
+# array of characters the node table below directly indexes entries.
+sub generate_string_table
+{
+    my ($tldtree_ref, $nodeidx_ref, $strtab_ref, $stridx_ref) = @_;
+
+    my @tmp_array;
+
+    foreach my $keys (keys %$strtab_ref) {
+	push(@tmp_array, $keys);
+    }
+
+    my @domelem_array = sort { length($b) <=> length($a) } @tmp_array;
+    
+    print "static const char stab[" . $$stridx_ref . "] = {\n";
+    while ( my ($key, $value) = each(%$strtab_ref) ) {
+    #for (@domelem_array) {
+#	my $key = $_;
+#	my $value = $strtab_ref->{$key};
+	print "    " . phexstr($key) . "/* " . $key . " " . $value . " */\n";
+    }
+    print "};\n\n";
+}
+
+sub phexstr
+{
+    use bytes;
+
+    my ($str) = @_;
+    my $ret;
+
+    my @bytes = unpack('C*', $str);
+
+    #$ret = $ret . sprintf("0x%02x, ", scalar(@bytes));
+
+    foreach (@bytes) {
+	$ret = $ret . sprintf("0x%02x, ", $_);
+    }
+
+    return $ret;
+}
+
+# Output the length of the string
+sub pstr_len
+{
+    use bytes;
+
+    my ($str) = @_;
+    my $ret;
+
+    my @bytes = unpack('C*', $str);
+
+    $ret = $ret . sprintf("%d", scalar(@bytes));
+
+    return $ret;
+}
+
+# generate all the children of a parent node and recurse into each of
+#  those updating optidx to point to the next free node
+sub calc_pnode 
+{
+    my ($parent_ref, $strtab_ref, $opidx_ref) = @_;
+    my $our_dat;
+    my $child_dat = "";
+    my $startidx = $$opidx_ref;
+    my $lineidx = -1;
+
+    # update the output index to after this node
+    $$opidx_ref += scalar keys %$parent_ref;
+
+    # entry block 
+    if ($startidx == ($$opidx_ref - 1)) {
+	$our_dat = "\n    /* entry " . $startidx . " */\n    ";
+    } else {
+	$our_dat = "\n    /* entries " . $startidx . " to " . ($$opidx_ref - 1) . " */\n    ";
+    }
+
+    # iterate over each child element domain/ref pair
+    while ( my ($cdom, $cref) = each(%$parent_ref) ) {
+        # make array look pretty by limiting entries per line
+	if ($lineidx == 3) {
+	    $our_dat .= "\n    ";
+	    $lineidx = 0;
+	} elsif ($lineidx == -1) {
+	    $lineidx = 1;
+	} else {
+	    $our_dat .= " ";
+	    $lineidx += 1;
+	}
+
+	$our_dat .= "{ ";
+	$our_dat .= $strtab_ref->{$cdom} . ", ";
+	my $child_count = scalar keys (%$cref);
+	$our_dat .= $child_count . ", ";
+	if ($child_count != 0) {
+	    $our_dat .= $$opidx_ref . ", ";
+	    $child_dat .= calc_pnode($cref, $strtab_ref, $opidx_ref);
+	} else {
+	    $our_dat .= 0 . ", ";
+	}
+	$our_dat .= pstr_len($cdom) ;
+	$our_dat .= " },";
+
+    }
+
+    return $our_dat . $child_dat;
+}
+
+# main
+binmode(STDOUT, ":utf8");
+
+my ($filename) = @ARGV;
+
+if (not defined $filename) {
+    die "need filename\n";
+}
+
+open(my $fh, '<:encoding(UTF-8)', $filename)
+    or die "Could not open file '$filename' $!";
+
+tie my %tldtree, 'Tie::IxHash'; # node tree
+my $nodeidx = 1; # count of nodes allowing for the root node
+
+tie my %strtab, 'Tie::IxHash'; # string table
+my $stridx = 0;
+
+# put the wildcard match at 0 in the string table
+$strtab{'*'} = $stridx;
+$stridx += 1;
+
+# put the invert match at 1 in the string table
+$strtab{'!'} = $stridx;
+$stridx += 1;
+
+# read each line from prefix data and inject into hash tree
+while (my $line = <$fh>) {
+    chomp $line;
+
+    if (($line ne "") && ($line !~ /\/\/.*$/)) {
+
+	# print "$line\n";
+	my @parts=split("\\.", $line);
+
+	# recusrsive call to build tree from root
+
+	treesubdom(\%tldtree, \$nodeidx, \%strtab, \$stridx, \@parts);
+    }
+}
+
+# C program header
+print <<EOF;
+/*
+ * Generated with the genpubsuffix tool from effective_tld_names.dat
+ */
+
+EOF
+
+generate_string_table(\%tldtree, \$nodeidx, \%strtab, \$stridx);
+
+print "enum stab_entities {\n";
+print "    STAB_WILDCARD = 0,\n";
+print "    STAB_EXCEPTION = 1\n";
+print "};\n\n";
+
+
+# output static node array
+#
+# The constructed array of nodes has all siblings sequentialy and an
+# index/count to its children. This yeilds a very compact data
+# structure easily traversable.
+#
+# Additional flags for * (match all) and ! (exception) are omitted as
+# they can be infered by having a node with a label of 0 (*) or 1 (!)
+# as the string table has those values explicitly created.
+#
+# As labels cannot be more than 63 characters a byte length is more
+# than sufficient.
+
+print "struct pnode {\n";
+print "    uint16_t label; /**< index of domain element in string table */\n";
+print "    uint16_t child_count; /* number of children of this node */\n";
+print "    uint16_t child_index; /**< index of first child node */\n";
+print "    uint8_t label_len; /**< length of domain element in string table */\n";
+print "};\n\n";
+
+my $opidx = 1; # output index of node
+
+print "static const struct pnode pnodes[" . $nodeidx . "] = {\n";
+
+# root node
+print "    /* root entry */\n"; 
+print "    { 0, " . scalar keys(%tldtree) . ", " . $opidx . ", 0 },"; 
+
+# all subsequent nodes
+print calc_pnode(\%tldtree, \%strtab, \$opidx);
+print "\n};\n\n";
diff --git a/src/nspsl.c b/src/nspsl.c
new file mode 100644
index 0000000..2e6e4dd
--- /dev/null
+++ b/src/nspsl.c
@@ -0,0 +1,128 @@
+/*
+ * Copyright 2016 Vincent Sanders <vince@netsurf-browser.org>
+ *
+ * This file is part of libnspsl
+ *
+ * Licensed under the MIT License,
+ *                http://www.opensource.org/licenses/mit-license.php
+ */
+
+#include <stdint.h>
+#include <string.h>
+
+#include "nspsl.h"
+
+#include "psl.inc"
+
+#define DOMSEP '.'
+
+static int matchlabel(int parent, const char *start, int len)
+{
+	int clast = pnodes[parent].child_index + pnodes[parent].child_count;
+	int cidx; /*child node index */
+	int ridx = -1; /* index of match or -1 */
+
+	if (pnodes[parent].child_count != 0) {
+		/* there are child nodes present to scan */
+
+		for (cidx = pnodes[parent].child_index; cidx < clast; cidx++) {
+			if (pnodes[cidx].label == STAB_WILDCARD) {
+				/* wildcard match */
+				ridx = cidx;
+			} else {
+				if ((pnodes[cidx].label_len == len) &&
+				    (strncasecmp(&stab[pnodes[cidx].label],
+						 start,
+						 len) == 0)) {
+
+					if ((pnodes[cidx].child_count == 1) &&
+					    (pnodes[pnodes[cidx].child_index].label == STAB_EXCEPTION)) {
+						/* exception to previous */
+						ridx = -1;
+					} else {
+						ridx = cidx;
+					}
+					break;
+				}
+			}
+		}
+	}
+	return ridx;
+}
+
+/*
+ * Exported public API 
+ */
+const char *nspsl_getpublicsuffix(const char *hostname)
+{
+	int treeidx = 0; /* index to current tree node */
+	const char *elem_start;
+	const char *elem_end;
+	int lab_count = 0;
+
+	/* deal with obviously bad hostname */
+	if ((hostname == NULL) ||
+	    (hostname[0]) == 0 ||
+	    (hostname[0] == DOMSEP)) {
+		return NULL;
+	}
+
+	/* hostnames are ass backwards and we need to consider elemets
+	 * from the end first.
+	 */
+	 elem_end = hostname + strlen(hostname);
+	 /* fqdn have a separator on the end */
+	 if (elem_end[-1] == DOMSEP) {
+		 elem_end--;
+	 }
+	 elem_start = elem_end;
+
+	 /* extract the element and check for a match in our tree */
+	 for(;;) {
+		 /* find the start of the element */
+		 while ((elem_start > hostname) && (*elem_start != DOMSEP)) {
+			 elem_start--;
+		 }
+		 if (*elem_start == DOMSEP) {
+			 elem_start++;
+		 }
+
+		 lab_count++;
+
+		 /* search child nodes for label */
+		 treeidx = matchlabel(treeidx, elem_start, elem_end - elem_start);
+		 if (treeidx == -1) {
+			 break;
+		 }
+
+		 if (elem_start == hostname) {
+			 /* not valid */
+			 return NULL;
+		 }
+
+		 elem_end = elem_start - 1;
+		 elem_start = elem_end - 1;
+	 }
+
+	 /* The public suffix algorithm says: "the domain must match
+	  * the public suffix plus one additional label." This
+	  * requires there to be at least two labels so we need to
+	  * check
+	  */
+	 if (lab_count == 1) {
+		 if (elem_start == hostname) {
+			 elem_start = NULL;
+		 } else {
+			 /* strip the non matching part */
+			 elem_start -= 2;
+			 while (elem_start > hostname && *elem_start != DOMSEP) {
+				 elem_start--;
+			 }
+			 if (*elem_start == DOMSEP)
+				 elem_start++;
+		 }
+	 }
+
+
+	 return elem_start;
+}
diff --git a/test/Makefile b/test/Makefile
new file mode 100644
index 0000000..369b078
--- /dev/null
+++ b/test/Makefile
@@ -0,0 +1,3 @@
+DIR_TEST_ITEMS := nspsl:nspsl.c
+
+include $(NSBUILD)/Makefile.subdir
diff --git a/test/nspsl.c b/test/nspsl.c
new file mode 100644
index 0000000..88b41c7
--- /dev/null
+++ b/test/nspsl.c
@@ -0,0 +1,44 @@
+/*
+ * Copyright 2016 Vincent Sanders <vince@netsurf-browser.org>
+ *
+ * This file is part of libnspsl
+ *
+ * Licensed under the MIT License,
+ *                http://www.opensource.org/licenses/mit-license.php
+ */
+
+/**
+ * \file
+ *
+ * psl test program. first argument is checked against being a public suffix.
+ */
+
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <nspsl.h>
+
+int main(int argc, char**argv)
+{
+    const char *output;
+    size_t output_len;
+
+
+    if (argc == 2) {
+        output = nspsl_getpublicsuffix(argv[1]);
+    } else {
+        fprintf(stderr, "Usage: %s data", argv[0]);
+        return 1;
+    }
+    
+    if (output != NULL) {
+        output_len = strlen(output);
+        printf("%.*s\n", (int)output_len, output);
+    } else {
+        printf("null\n");
+    }
+
+    return 0;
+}
diff --git a/test/runtest.sh b/test/runtest.sh
new file mode 100755
index 0000000..8520232
--- /dev/null
+++ b/test/runtest.sh
@@ -0,0 +1,106 @@
+#!/bin/sh 
+TEST_PATH=$1
+
+#set -x
+
+checkPublicSuffix()
+{
+    ENC=$(${TEST_PATH}/test_nspsl "${1}")
+    if [ "${ENC}" != "${2}" ];then
+        echo "psl error ${ENC} != ${2}"
+	exit 2
+    fi 
+}
+
+## test list derived from mozilla test data
+##
+## https://hg.mozilla.org/mozilla-central/raw-file/82d0a583a9a39bf0b0000bccbf6d5c9ec2596bcc/netwerk/test/unit/data/test_psl.txt
+##
+## Any copyright is dedicated to the Public Domain.
+## http://creativecommons.org/publicdomain/zero/1.0/
+
+## null input.
+#checkPublicSuffix(null, null);
+## Mixed case.
+checkPublicSuffix 'COM' null
+#checkPublicSuffix 'example.COM' 'example.com'
+#checkPublicSuffix 'WwW.example.COM' 'example.com'
+## Leading dot.
+checkPublicSuffix '.com' null
+checkPublicSuffix '.example' null
+checkPublicSuffix '.example.com' null
+checkPublicSuffix '.example.example' null
+## Unlisted TLD.
+checkPublicSuffix 'example' null
+checkPublicSuffix 'example.example' 'example.example'
+checkPublicSuffix 'b.example.example' 'example.example'
+checkPublicSuffix 'a.b.example.example' 'example.example'
+## Listed, but non-Internet, TLD.
+##checkPublicSuffix 'local' null
+##checkPublicSuffix 'example.local' null
+##checkPublicSuffix 'b.example.local' null
+##checkPublicSuffix 'a.b.example.local' null
+## TLD with only 1 rule.
+checkPublicSuffix 'biz' null
+checkPublicSuffix 'domain.biz' 'domain.biz'
+checkPublicSuffix 'b.domain.biz' 'domain.biz'
+checkPublicSuffix 'a.b.domain.biz' 'domain.biz'
+## TLD with some 2-level rules.
+checkPublicSuffix 'com' null
+checkPublicSuffix 'example.com' 'example.com'
+checkPublicSuffix 'b.example.com' 'example.com'
+checkPublicSuffix 'a.b.example.com' 'example.com'
+checkPublicSuffix 'uk.com' null
+checkPublicSuffix 'example.uk.com' 'example.uk.com'
+checkPublicSuffix 'b.example.uk.com' 'example.uk.com'
+checkPublicSuffix 'a.b.example.uk.com' 'example.uk.com'
+checkPublicSuffix 'test.ac' 'test.ac'
+## TLD with only 1 (wildcard) rule.
+checkPublicSuffix 'il' null
+#checkPublicSuffix 'c.il' null
+#checkPublicSuffix 'b.c.il' 'b.c.il'
+#checkPublicSuffix 'a.b.c.il' 'b.c.il'
+## More complex TLD.
+checkPublicSuffix 'jp' null
+checkPublicSuffix 'test.jp' 'test.jp'
+checkPublicSuffix 'www.test.jp' 'test.jp'
+checkPublicSuffix 'ac.jp' null
+checkPublicSuffix 'test.ac.jp' 'test.ac.jp'
+checkPublicSuffix 'www.test.ac.jp' 'test.ac.jp'
+checkPublicSuffix 'kyoto.jp' null
+checkPublicSuffix 'test.kyoto.jp' 'test.kyoto.jp'
+checkPublicSuffix 'ide.kyoto.jp' null
+checkPublicSuffix 'b.ide.kyoto.jp' 'b.ide.kyoto.jp'
+checkPublicSuffix 'a.b.ide.kyoto.jp' 'b.ide.kyoto.jp'
+checkPublicSuffix 'c.kobe.jp' null
+checkPublicSuffix 'b.c.kobe.jp' 'b.c.kobe.jp'
+checkPublicSuffix 'a.b.c.kobe.jp' 'b.c.kobe.jp'
+checkPublicSuffix 'city.kobe.jp' 'city.kobe.jp'
+checkPublicSuffix 'www.city.kobe.jp' 'city.kobe.jp'
+## TLD with a wildcard rule and exceptions.
+checkPublicSuffix 'ck' null
+checkPublicSuffix 'test.ck' null
+checkPublicSuffix 'b.test.ck' 'b.test.ck'
+checkPublicSuffix 'a.b.test.ck' 'b.test.ck'
+checkPublicSuffix 'www.ck' 'www.ck'
+checkPublicSuffix 'www.www.ck' 'www.ck'
+## US K12.
+checkPublicSuffix 'us' null
+checkPublicSuffix 'test.us' 'test.us'
+checkPublicSuffix 'www.test.us' 'test.us'
+checkPublicSuffix 'ak.us' null
+checkPublicSuffix 'test.ak.us' 'test.ak.us'
+checkPublicSuffix 'www.test.ak.us' 'test.ak.us'
+checkPublicSuffix 'k12.ak.us' null
+checkPublicSuffix 'test.k12.ak.us' 'test.k12.ak.us'
+checkPublicSuffix 'www.test.k12.ak.us' 'test.k12.ak.us'
+## punycoded IDN labels.
+checkPublicSuffix 'xn--85x722f.com.cn' 'xn--85x722f.com.cn'
+checkPublicSuffix 'xn--85x722f.xn--55qx5d.cn' 'xn--85x722f.xn--55qx5d.cn'
+checkPublicSuffix 'www.xn--85x722f.xn--55qx5d.cn' 'xn--85x722f.xn--55qx5d.cn'
+checkPublicSuffix 'shishi.xn--55qx5d.cn' 'shishi.xn--55qx5d.cn'
+checkPublicSuffix 'xn--55qx5d.cn' null
+checkPublicSuffix 'xn--85x722f.xn--fiqs8s' 'xn--85x722f.xn--fiqs8s'
+checkPublicSuffix 'www.xn--85x722f.xn--fiqs8s' 'xn--85x722f.xn--fiqs8s'
+checkPublicSuffix 'shishi.xn--fiqs8s' 'shishi.xn--fiqs8s'
+checkPublicSuffix 'xn--fiqs8s' null