Quer.ee third-party data and code notices
=========================================

Quer.ee is a GPLv3 fork of uBlock Origin. See LICENSE.txt for the extension
license and full warranty disclaimer. The following notices cover additional
data and code incorporated into Quer.ee-specific filtering.

Maigret profile-address data (offline source tools only)
-------------------------------------------------------
Source: https://github.com/soxoj/maigret/blob/main/maigret/resources/data.json
Snapshot retrieved November 9, 2026; SHA-256:
5980aab8043dac0d2cba37779c3164b4c951d589d7e4989a8697c29d584545bc
Copyright (c) 2020-2026 Soxoj, MIT license.
The unmodified data and full notice are in tools/vendor/maigret/.
Quer.ee expands known account-address templates during organization imports to
avoid promoting a hosted profile into a whole-host ownership claim. No Maigret
account searches are performed, and its data is not bundled into the XPI.

UT1 blacklists
--------------
Shopping, banking, and press domain data are adapted from blacklists managed by
Universite Toulouse Capitole and Fabrice Prigent, mirrored by Olivier Berten at
https://github.com/olbat/ut1-blacklists. The source lists are licensed under
Creative Commons Attribution-ShareAlike 4.0 International:
https://creativecommons.org/licenses/by-sa/4.0/

Quer.ee selects categories, normalizes and removes domains, and compiles the
remaining data into a hostname trie. The adapted UT1-derived portions remain
available under CC BY-SA 4.0.

Directory of Open Access Journals (DOAJ)
---------------------------------------
Scholarly journal website data come from the public DOAJ journal CSV:
https://doaj.org/csv
Journal metadata is released under CC0 1.0:
https://doaj.org/terms/
https://creativecommons.org/publicdomain/zero/1.0/

Quer.ee selects root journal homepage URLs, normalizes their hostnames, excludes
shared services and social platforms, and compiles them into the existing
publication trie. Journal records with paths, queries or fragments are omitted
instead of assigning their entire host to a journal. The source is not used to
infer corporate ownership or nonprofit status.

Dropship Filters
----------------
Retailer domain data are adapted from Lalaggi's Dropship Filters project:
https://gitlab.com/Lalaggi/dropship-filters. The source is licensed under
Creative Commons Attribution-ShareAlike 4.0 International:
https://creativecommons.org/licenses/by-sa/4.0/

Quer.ee selects and normalizes domains and compiles them into a hostname trie.
The adapted Dropship Filters-derived portion remains available under
CC BY-SA 4.0.
The complete Redirects & Affiliates file is also used for visible outgoing-link
checks under Advertising signals, alongside Soteria. Its 23 anchored domain rules
retain their hostname/subdomain scope; no entries are hand-pruned. The raw file
and its CC BY-SA 4.0 declaration are included under
assets/queree/website-lists/affiliate-links/dropship-redirects.txt, with pinned
revision and byte hashes in the source archive's website-list provenance.

Charity Commission for England and Wales
----------------------------------------
Registered-charity website data come from the Charity Commission public
register. Quer.ee selects registered records whose website and contact-email
domains agree, removes nonexclusive hosts, and compiles the remaining domains.
Contains public sector information licensed under the Open Government Licence
v3.0: https://www.nationalarchives.gov.uk/doc/open-government-licence/version/3/

Australian Charities and Not-for-profits Commission
---------------------------------------------------
Registered-charity website data come from the Australian Charities and
Not-for-profits Commission (ACNC):
https://data.gov.au/data/dataset/acnc-register

Licensed under Creative Commons Attribution 3.0 Australia:
https://creativecommons.org/licenses/by/3.0/au/

Quer.ee normalizes the website fields, removes platforms and nonexclusive
hosts, and compiles the remaining domains into a hostname trie.

United States Internal Revenue Service
--------------------------------------
Small-charity website declarations come from the IRS Form 990-N bulk download:
https://apps.irs.gov/pub/epostcard/data-download-epostcard.zip
Current charity status comes from all four regional EO BMF extracts:
https://www.irs.gov/charities-non-profits/exempt-organizations-business-master-file-extract-eo-bmf

These are US federal government public data. Quer.ee selects recent,
nonterminated declarations with current subsection 03/status 01, removes
invalid, shared-provider and known-commercial hosts, and compiles the remaining
hostnames. Filing websites are self-reported, not proof of domain ownership.
Only EIN/domain associations are retained; officer and address fields are not.

National Center for Charitable Statistics, Urban Institute
---------------------------------------------------------
Larger-charity website declarations are extracted from the prepared Form 990
and 990-EZ header tables in NCCS IRS 990 Efile Data, Jesse Lecy, 2026, v3.1:
https://urbaninstitute.github.io/nccs/catalogs/catalog-efile-v3_1.html

These cleaned NCCS data are licensed under Open Data Commons Attribution
License v1.0 (ODC-BY): https://opendatacommons.org/licenses/by/1-0/
Dataset terms: https://urbaninstitute.github.io/nccs/terms/

Quer.ee combines recent declarations with 990-N, selects the latest tax period
and filing timestamp, checks current IRS charity status, removes invalid,
shared and known-commercial hosts, and compiles a hostname index. Only
EIN/domain associations are retained. The underlying IRS data are public domain.

Wikidata
--------
Company, organisation-homepage, university, government, charity, museum and
botanical-garden website data are derived from Wikidata queries. Wikidata
structured data are dedicated to the public domain
under CC0 1.0: https://creativecommons.org/publicdomain/zero/1.0/
Quer.ee selects specified entity classes, normalizes website domains, removes
platforms and nonexclusive hosts, and compiles the remaining domains.
Conflicting organisation claims involving a company's non-homepage address are
resolved in Quer.ee's manually reviewed TSV, licensed with the project under
GPL-3.0-only. Builds read those decisions directly; other records keep their
source classification. Unresolved conflicting claims are omitted from the broader
import. Original supplier records and query recipes are retained as evidence.

YC company directory
--------------------
Company website, ID, status and nonprofit fields come from the yc-oss/api
mirror of Y Combinator's company directory:
https://github.com/yc-oss/api
https://yc-oss.github.io/api/companies/all.json
Upstream directory: https://www.ycombinator.com/companies

The mirror declares no license. Quer.ee selects Active/Public records whose
nonprofit field is false, normalizes website domains, removes shared hosts,
and compiles the remaining domains into its hostname index.

Punycode.js
-----------
The bundled src/lib/punycode.js is Punycode.js 1.3.2 by Mathias Bynens:
https://github.com/mathiasbynens/punycode.js
https://github.com/mathiasbynens/punycode.js/blob/v1.3.2/LICENSE-MIT.txt
Licensed under MIT:

Copyright Mathias Bynens <https://mathiasbynens.be/>

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.

AdGuard Base filter
-------------------
The pinned AdGuard Base filter snapshot is from AdGuard Filters:
https://github.com/AdguardTeam/AdguardFilters
It is licensed under GPLv3; LICENSE.txt contains the GPLv3 terms.

HaGeZi Referral Blocklist
-------------------------
Affiliate and tracking referral hostname data come from HaGeZi's Referral
Blocklist:
https://github.com/hagezi/dns-blocklists

The source is licensed under GPLv3; LICENSE.txt contains the GPLv3 terms.
The snapshot and importer are retained under research/referral-lists in the
source archive. They are not used by the Firefox extension.

HaGeZi Pop-Up Ads
----------------
The unchanged Adblock source is included as assets/queree/popupads.txt:
https://github.com/hagezi/dns-blocklists
Pinned input: adblock/popupads.txt at commit
eb7db8ed27237af2f3c0cb79c9c735e3e076dbad.
It is licensed under GPLv3; LICENSE.txt contains the GPLv3 terms.
Quer.ee loads it through uBO's native asset and filtering machinery.

EasyList Spanish
----------------
The bundled fallback snapshot comes from:
https://easylist-downloads.adblockplus.org/easylistspanish.txt
It retains its source header and license link. EasyList's dual GPLv3/CC-BY-SA
licensing is documented at https://easylist.to/pages/licence.html.
The runtime subscription uses uBO's existing EasyList Spanish asset, with the
bundled snapshot available when the remote source is unavailable.

HaGeZi NSFW
------------
Adult-content hostnames come from HaGeZi's NSFW domain list:
https://github.com/hagezi/dns-blocklists
Pinned input: wildcard/nsfw-onlydomains.txt at commit
81bbd1b9009893d65358146b23282647634c26be.

The source is licensed under GPLv3; LICENSE.txt contains the GPLv3 terms.
The unchanged raw input is included in the source archive under
assets/queree/adult-lists/, not in the installed extension.
Quer.ee preserves listed hostname and tenant boundaries and compiles these
domains into its existing hostname trie and server source taxonomy. This is an
adult-eligibility rule, not an ownership category or a navigation blocklist.

PeterDaveHello URL Shorteners
-----------------------------
General-purpose URL-shortener hostname data come from:
https://github.com/PeterDaveHello/url-shorteners

The source is licensed under CC-BY-SA-4.0. Its metadata is retained with the
archived referral-list research, not used by the Firefox extension.

Commerce fingerprints
---------------------
Quer.ee's generated commerce fingerprints use these preferred sources:

- OpenTechalyzer by Houseofmvps, MIT License:
  https://github.com/Houseofmvps/opentechalyzer
- WebAppAnalyzer by Enthec, GPLv3:
  https://github.com/enthec/webappanalyzer

Their exact source snapshots and license files are included in the
corresponding Quer.ee source archive.

Super SEO Spam Suppressor
-------------------------
Quer.ee uses the upstream Fake stores domain category, Advertorials URL category,
and Affiliate marketing English/French/Multi domain files, not the combined
blocklist or its AI-authorship restrictions:
https://github.com/NotaInutilis/Super-SEO-Spam-Suppressor

These selected sources use the upstream custom permissive license, version 1,
October 2013. Its complete, unchanged text is included as
assets/queree/website-lists/LICENSE in the extension and source archive. The raw
selected source files are retained there only in the source archive.
Fake-store domains are compiled
into the existing hostname index; advertorial paths preserve upstream uBlacklist
match-pattern scope. Source membership is attributed evidence, not an independent
finding that every destination is fraudulent or every article was paid for.
Affiliate-publisher domains supply Advertising signals and site-wide index
exclusions, labeled Listed affiliate publisher, not proof of ads on each page.

Soteria nou affiliate endpoints
------------------------------
Quer.ee checks visible outbound page links against the complete affiliate.txt
file from https://github.com/soteria-nou/domain-list (136 domains in this snapshot).
The upstream data permits non-commercial copying and distribution with the
original URL included; it is not licensed as GPL. Its unchanged source and full
upstream README, including those terms, are included under
assets/queree/website-lists/affiliate-links/. The common revision, source URLs
and byte hashes are recorded in the source archive's website-list provenance.
Generated affiliateLinkSources data retains the same upstream terms.
Matches supply Advertising signals labeled Affiliate or tracked link, not a
claim of commission payment or a publisher-wide classification. No entries
have been hand-pruned, including the upstream file's broader business addresses.

uBlacklist match-pattern
------------------------
The unchanged @ublacklist/match-pattern 2.0.0 code by iorate matches the native
URL patterns: https://github.com/iorate/ublacklist
It is licensed under MIT. The complete notice is included alongside the code
under js/queree/vendor/ublacklist/LICENSE in the XPI, and under
src/js/queree/vendor/ublacklist/LICENSE in the source archive.

Ghostery TrackerDB (downloaded data)
-----------------------------------
The extension downloads selected advertising-tracking request rules directly
from Ghostery's published TrackerDB data:
https://github.com/ghostery/trackerdb
Copyright 2017 Ghostery GmbH. Downloaded data license: CC BY-NC-SA 4.0:
https://creativecommons.org/licenses/by-nc-sa/4.0/
No TrackerDB dataset or Ghostery matcher code is bundled in this extension.
The downloaded data retains its own license, not the extension's GPL license.
