Fix sorting

This commit is contained in:
Sean Whalen
2025-06-08 20:17:21 -04:00
parent 87ae6175f2
commit 5975d8eb21
6 changed files with 44 additions and 42 deletions
+2 -2
View File
@@ -17,7 +17,7 @@ touch build/html/.nojekyll
if [ -d "./../parsedmarc-docs" ]; then
cp -rf build/html/* ../../parsedmarc-docs/
fi
sort.sh
python3 sortmaps.py
python3 tests.py
rm -rf dist/ build/
hatch build
hatch build
@@ -44,6 +44,7 @@ airtel.in,Airtel,ISP
airtelbroadband.in,Airtel,ISP
ajusa.com,AJ-USA,Retail
aknet.kg,AkNet,ISP
akura.ne.jp,Akura,Logistics
albatros.uz,Albatros Health Care,Healthcare
alembic.co.in,Alembic Pharmaceuticals,Healthcare
alestra.net.mx,Alestra,ISP
@@ -88,6 +89,7 @@ asl2.liguria.it,ASL2,Healthcare
asmecal.it,ASMENET CALABRIA,Government
assaytechnology.com,Assay Technology,Industrial
assentportal.com,Assent,SaaS
assp.org,American Society of Safety Professionals,Healthcare
atmailcloud.com,atmail,Email Provider
ats.ca,ATS Healthcare,Healthcare
atw.ne.jp,ATW,Web Host
@@ -135,6 +137,7 @@ bluehost.com,Bluehost,Web Host
bluemission.net,Blue Mission,Web Host
bluesea.org,Blue Sea Foundation,Marketing
bluetie.com,BlueTie,MSP
bnpparibas.fr,Banque BNP Paribas,Finance
bohc.co.jp,Benefit One Inc.,Retail
bostrad.com,Bostrad Supply Chain Ltd,Logistics
bov.com,Bank of Valletta,Finance
@@ -192,6 +195,7 @@ circleamedical.com,Circle A Medical,Healthcare
cirrushosting.com,Cirrus Hosting,Web Host
cisco.com,Cisco,Technology
ckt.net,Craw-Kan Telephone Cooperative,ISP
clarix.com,Clarix,MSP
claro.com.do,Claro,ISP
claro.com.ec,Claro,ISP
claro.net.do,Mail2World,Email Provider
@@ -213,6 +217,7 @@ codetel.net.do,codetel.net.do,ISP
coeficiente.net.mx,Coeficiente,ISP
cogeco.ca,Cogeco,ISP
cogeco.net,Cogoco,ISP
collectivhosting.com,Collectiv,Web Host
colocrossing.com,ColoCrossing,ISP
combell.com,Combell,Web Host
comcast.net,Comcast,ISP
@@ -220,6 +225,7 @@ comcastbusiness.net,Comcast Business,ISP
comfori.com,Comfori,SaaS
comline.com,West Coast Internet (WCI),ISP
communitect.com,Solutionreach,SaaS
complemar.com,Complemar,Logistics
compliancearchitects.net,Compliance Aarchitects,Healthcare
compu-type.net,Compu-Type,MSP
computronics.com,Computronics,Technology
@@ -1322,6 +1328,7 @@ verizonbusiness.com,Verizon Business,ISP
verointernet.com.br,Internet de Verdade,ISP
versanet.de,1&1 Versatel,ISP
vicc.co,Venco Imtiaz Contracting Co,Industrial
victorkaiser.com,Global Transport,Logistics
videotron.ca,Videotron,ISP
videotron.com,Videotron,ISP
viecuri.nl,VieCuri,Healthcare
@@ -1435,10 +1442,3 @@ zsttk.ru,TTK,ISP
zyner.net,Zyner,Email Provider
zyner.one,Zyner,Email Provider
zyner.org,Zyner,Email Provider
akura.ne.jp,Akura,Logistics
assp.org,American Society of Safety Professionals,Healthcare
complemar.com,Complemar,Logistics
victorkaiser.com,Global Transport,Logistics
bnpparibas.fr,Banque BNP Paribas,Finance
clarix.com,Clarix,MSP
collectivhosting.com,Collectiv,Web Host
1 base_reverse_dns name type
44 airtelbroadband.in Airtel ISP
45 ajusa.com AJ-USA Retail
46 aknet.kg AkNet ISP
47 akura.ne.jp Akura Logistics
48 albatros.uz Albatros Health Care Healthcare
49 alembic.co.in Alembic Pharmaceuticals Healthcare
50 alestra.net.mx Alestra ISP
89 asmecal.it ASMENET CALABRIA Government
90 assaytechnology.com Assay Technology Industrial
91 assentportal.com Assent SaaS
92 assp.org American Society of Safety Professionals Healthcare
93 atmailcloud.com atmail Email Provider
94 ats.ca ATS Healthcare Healthcare
95 atw.ne.jp ATW Web Host
137 bluemission.net Blue Mission Web Host
138 bluesea.org Blue Sea Foundation Marketing
139 bluetie.com BlueTie MSP
140 bnpparibas.fr Banque BNP Paribas Finance
141 bohc.co.jp Benefit One Inc. Retail
142 bostrad.com Bostrad Supply Chain Ltd Logistics
143 bov.com Bank of Valletta Finance
195 cirrushosting.com Cirrus Hosting Web Host
196 cisco.com Cisco Technology
197 ckt.net Craw-Kan Telephone Cooperative ISP
198 clarix.com Clarix MSP
199 claro.com.do Claro ISP
200 claro.com.ec Claro ISP
201 claro.net.do Mail2World Email Provider
217 coeficiente.net.mx Coeficiente ISP
218 cogeco.ca Cogeco ISP
219 cogeco.net Cogoco ISP
220 collectivhosting.com Collectiv Web Host
221 colocrossing.com ColoCrossing ISP
222 combell.com Combell Web Host
223 comcast.net Comcast ISP
225 comfori.com Comfori SaaS
226 comline.com West Coast Internet (WCI) ISP
227 communitect.com Solutionreach SaaS
228 complemar.com Complemar Logistics
229 compliancearchitects.net Compliance Aarchitects Healthcare
230 compu-type.net Compu-Type MSP
231 computronics.com Computronics Technology
1328 verointernet.com.br Internet de Verdade ISP
1329 versanet.de 1&1 Versatel ISP
1330 vicc.co Venco Imtiaz Contracting Co Industrial
1331 victorkaiser.com Global Transport Logistics
1332 videotron.ca Videotron ISP
1333 videotron.com Videotron ISP
1334 viecuri.nl VieCuri Healthcare
1442 zyner.net Zyner Email Provider
1443 zyner.one Zyner Email Provider
1444 zyner.org Zyner Email Provider
akura.ne.jp Akura Logistics
assp.org American Society of Safety Professionals Healthcare
complemar.com Complemar Logistics
victorkaiser.com Global Transport Logistics
bnpparibas.fr Banque BNP Paribas Finance
clarix.com Clarix MSP
collectivhosting.com Collectiv Web Host
@@ -1,10 +1,15 @@
200.in-addr.arpa
a7e.ru
a94434500-blog.com
adlucrumnewsletter.com
admin.corpivensa.gob.ve
aerospacevitro.us.com
albagroup-eg.com
anglishment.com
anteldata.net.uy
antis.edu
antonaoll.com
anviklass.org
aosau.net
arandomserver.com
asmecam.it
@@ -12,24 +17,30 @@ b8sales.com
bestinvestingtime.com
biocorp.com
bisno1.co.jp
blguss.com
bluenet.ch
bluhosting.com
bodiax.pp.ua
bost-law.com
brnonet.cz
brushinglegal.de
cavabeen.com
christus.mx
cloud-edm.com
cloudaccess.net
cloudlogin.co
cnode.io
commerceinsurance.com
coolblaze.com
cps.com.ar
ctla.co.kr
detrot.xyz
digi.net.my
dkginternet.com
doorsrv.com
dreamtechmedia.com
ds.network
emailgids.net
emailperegrine.com
epsilon-group.com
eyecandyhosting.xyz
@@ -48,16 +59,21 @@ hostingmichigan.com
hostname.localhost
hostnetwork.com
hostwhitelabel.com
i-mecca.net
idcfcloud.net
immenzaces.com
ip-147-135-108.us
itsidc.com
ivol.co
jalanet.co.id
jimishare.com
kahlaa.com
kbronet.com.tw
kdnursing.org
kitchenaildbd.com
legenditds.com
lighthouse-media.com
llsend.com
lohkal.com
lonestarmm.net
magnetmail.net
@@ -75,6 +91,7 @@ mysagestore.com
ncport.ru
nebdig.com
neovet-base.ru
netkl.org
nic.name
nidix.net
ogicom.net
@@ -86,10 +103,12 @@ passionatesmiles.com
planethoster.net
pmnhost.net
popiup.com
ports.net
prima.com.ar
prima.net.ar
proudserver.com
qontenciplc.autos
rapidns.com
raxa.host
sahacker-2020.com
samsales.site
@@ -123,22 +142,3 @@ xsfati.us.com
xspmail.jp
zerowebhosting.net
znlc.jp
cavabeen.com
llsend.com
blguss.com
itsidc.com
anviklass.org
a7e.ru
antis.edu
ctla.co.kr
ip-147-135-108.us
cloudaccess.net
netkl.org
bluenet.ch
i-mecca.net
emailgids.net
jimishare.com
anglishment.com
ports.net
rapidns.com
a94434500-blog.com
+2 -2
View File
@@ -1,6 +1,6 @@
akura.ne.jp
amazonaws.com
cloudaccess.net
linode.comn
h-serv.co.uk
linode.comn
plesk.pages
akura.ne.jp
-5
View File
@@ -1,5 +0,0 @@
#!/usr/bin/env bash
sort -o "parsedmarc/resources/maps/known_unknown_base_reverse_dns.txt" "parsedmarc/resources/maps/known_unknown_base_reverse_dns.txt"
sort -o "parsedmarc/resources/maps/public_suffix_overrides.txt" "parsedmarc/resources/maps/public_suffix_overrides.txt"
./sortmaps.py
+14 -7
View File
@@ -23,8 +23,16 @@ def sort_csv(filepath, column=0):
writer.writerow(header)
writer.writerows(sorted_rows)
def sort_list_file(filepath, lowercase=True, strip=True, deduplicate=True,
remove_blank_lines=True, ending_newline=True, newline="\n"):
def sort_list_file(
filepath,
lowercase=True,
strip=True,
deduplicate=True,
remove_blank_lines=True,
ending_newline=True,
newline="\n",
):
with open(filepath, mode="r", newline=newline) as infile:
lines = infile.readlines()
for i in range(len(lines)):
@@ -39,14 +47,13 @@ def sort_list_file(filepath, lowercase=True, strip=True, deduplicate=True,
lines.remove("")
lines = sorted(lines)
if ending_newline:
if lines[-1] != newline:
lines.append(newline)
if lines[-1] != "":
lines.append("")
with open(filepath, mode="w", newline=newline) as outfile:
outfile.write("\n".join(newline))
outfile.write(newline)
outfile.write("\n".join(lines))
for csv_file in map_files:
sort_csv(os.path.join(maps_dir, csv_file))
for list_file in list_files:
sort_list_file( os.path.join(maps_dir, list_file))
sort_list_file(os.path.join(maps_dir, list_file))