Compare commits

..

2 Commits

Author SHA1 Message Date
Xe Iaso
50e48df993 fix(Dockerfile): add HEALTHCHECK
Signed-off-by: Xe Iaso <me@xeiaso.net>
2025-06-13 15:24:42 -04:00
Xe Iaso
5e38c7d730 feat: build with docker buildx bake
Signed-off-by: Xe Iaso <me@xeiaso.net>
2025-06-10 09:00:57 -04:00
185 changed files with 3247 additions and 9255 deletions

View File

@@ -9,4 +9,4 @@ exclude_dir = ["var", "vendor", "docs", "node_modules"]
[logger]
time = true
# to change flags at runtime, prepend with -- e.g. $ air -- --target http://localhost:3000 --difficulty 20 --use-remote-address
# to change flags at runtime, prepend with -- e.g. $ air -- --target http://localhost:3000 --difficulty 20 --use-remote-address

View File

@@ -1,12 +0,0 @@
FROM ghcr.io/xe/devcontainer-base/pre/go
WORKDIR /app
COPY go.mod go.sum package.json package-lock.json ./
RUN go install github.com/a-h/templ/cmd/templ \
&& npx --yes playwright@1.52.0 install --with-deps\
&& apt-get update \
&& apt-get -y install zstd brotli \
&& mkdir -p /home/vscode/.local/share/fish \
&& chown -R vscode:vscode /home/vscode/.local/share/fish \
&& chown -R vscode:vscode /go

View File

@@ -1,13 +0,0 @@
# Anubis Dev Container
Anubis offers a [development container](https://containers.dev/) image in order to make it easier to contribute to the project. This image is based on [Xe/devcontainer-base/go](https://github.com/Xe/devcontainer-base/tree/main/src/go), which is based on Debian Bookworm with the following customizations:
- [Fish](https://fishshell.com/) as the shell complete with a custom theme
- [Go](https://go.dev) at the most recent stable version
- [Node.js](https://nodejs.org/en) at the most recent stable version
- [Atuin](https://atuin.sh/) to sync shell history between your host OS and the development container
- [Docker](https://docker.com) to manage and build Anubis container images from inside the development container
- [Ko](https://ko.build/) to build production-ready Anubis container images
- [Neovim](https://neovim.io/) for use with Git
This development container is tested and known to work with [Visual Studio Code](https://code.visualstudio.com/). If you run into problems with it outside of VS Code, please file an issue and let us know what editor you are using.

View File

@@ -1,34 +0,0 @@
// For format details, see https://aka.ms/devcontainer.json. For config options, see the
// README at: https://github.com/devcontainers/templates/tree/main/src/debian
{
"name": "Dev",
// Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
"build": {
"dockerfile": "./Dockerfile",
"context": "..",
"cacheFrom": [
"type=registry,ref=ghcr.io/techarohq/anubis/devcontainer"
]
},
"postStartCommand": "npm ci && go mod download",
"features": {
"ghcr.io/xe/devcontainer-features/ko:1.1.0": {}
},
"initializeCommand": "mkdir -p ${localEnv:HOME}${localEnv:USERPROFILE}/.local/share/atuin",
"customizations": {
"vscode": {
"extensions": [
"esbenp.prettier-vscode",
"ms-azuretools.vscode-containers",
"golang.go",
"unifiedjs.vscode-mdx",
"a-h.templ",
"redhat.vscode-yaml"
]
}
},
"forwardPorts": [
8923,
3000
]
}

25
.dockerignore Normal file
View File

@@ -0,0 +1,25 @@
.env
*.deb
*.rpm
# Additional package locks
pnpm-lock.yaml
yarn.lock
# Go binaries and test artifacts
main
*.test
node_modules
# MacOS
.DS_store
# Intellij
.idea
# how does this get here
doc/VERSION
web/static/js/*
!web/static/js/.gitignore

2
.gitattributes vendored
View File

@@ -1 +1 @@
**/*_templ.go linguist-generated=true
web/index_templ.go linguist-generated

View File

@@ -2,4 +2,4 @@ github
https
ssh
ubuntu
workarounds
workarounds

View File

@@ -83,11 +83,6 @@
^\Q.github/FUNDING.yml\E$
^\Q.github/workflows/spelling.yml\E$
^data/crawlers/
^docs/blog/tags\.yml$
^docs/manifest/.*$
^docs/static/\.nojekyll$
^lib/policy/config/testdata/bad/unparseable\.json$
ignore$
robots.txt
^lib/localization/locales/.*\.json$
^lib/localization/.*_test.go$

View File

@@ -6,15 +6,8 @@ amazonbot
anthro
anubis
anubistest
apk
Applebot
archlinux
asnc
asnchecker
asns
aspirational
atuin
azuretools
badregexes
bdba
berr
@@ -30,15 +23,13 @@ Brightbot
broked
Bytespider
cachebuster
cachediptoasn
Caddyfile
caninetools
Cardyb
celchecker
celphase
CELPHASE
cerr
certresolver
cespare
CGNAT
cgr
chainguard
@@ -46,24 +37,23 @@ chall
challengemozilla
checkpath
checkresult
chen
chibi
cidranger
ckie
cloudflare
Codespaces
confd
containerbuild
coreutils
Cotoyogi
CRDs
Cromite
crt
Cscript
daemonizing
DDOS
Debian
debrpm
decaymap
decompiling
Diffbot
discordapp
discordbot
@@ -71,16 +61,13 @@ distros
dnf
dnsbl
dnserr
domainhere
dracula
dronebl
droneblresponse
duckduckbot
eerror
ellenjoe
emacs
enbyware
etld
everyones
evilbot
evilsite
@@ -99,24 +86,17 @@ Fordola
forgejo
fsys
fullchain
gaissmai
Galvus
geoip
geoipchecker
gha
gipc
gitea
godotenv
goland
gomod
goodbot
googlebot
govulncheck
goyaml
GPG
GPT
gptbot
grpcprom
grw
Hashcash
hashrate
@@ -126,33 +106,26 @@ hebis
hec
hmc
hostable
htmlc
htmx
httpdebug
Huawei
hypertext
iaskspider
iat
ifm
Imagesift
imgproxy
impressum
inp
IPTo
iptoasn
iss
isset
ivh
Jenomis
JGit
joho
journalctl
jshelter
JWTs
kagi
kagibot
keikaku
Keyfunc
keypair
KHTML
kinda
@@ -187,7 +160,6 @@ mozilla
nbf
netsurf
nginx
nicksnyder
nobots
NONINFRINGEMENT
nosleep
@@ -195,8 +167,8 @@ OCOB
ogtags
omgili
omgilibot
onionservice
openai
opengraph
openrc
pag
palemoon
@@ -217,19 +189,15 @@ privkey
promauto
promhttp
proofofwork
publicsuffix
pwcmd
pwuser
qualys
qwant
qwantbot
rac
rawler
rcvar
redhat
redir
redirectscheme
refactors
relayd
reputational
reqmeta
@@ -246,13 +214,10 @@ sebest
secretplans
selfsigned
Semrush
Seo
setsebool
shellcheck
Sidetrade
simprint
sitemap
skopeo
sls
sni
Sourceware
@@ -269,27 +234,20 @@ subrequest
SVCNAME
tagline
tarballs
tarrif
techaro
techarohq
templ
templruntime
testarea
Thancred
thoth
thothmock
Tik
Timpibot
torproject
traefik
uberspace
unifiedjs
unixhttpd
unmarshal
unparseable
uuidgen
uvx
UXP
Valkey
Varis
Velen
vendored
@@ -303,7 +261,6 @@ websecure
websites
Webzio
wildbase
withthothmock
wordpress
Workaround
workdir
@@ -317,7 +274,6 @@ xess
xff
XForwarded
XNG
XOB
XReal
yae
YAMLTo
@@ -327,6 +283,4 @@ yourdomain
yoursite
Zenos
zizmor
zombocom
Zonbocom
zos

View File

@@ -273,6 +273,14 @@
# Most people only have two hands. Reword.
\b(?i)on the third hand\b
# Should be `Open Graph`
# unless talking about a specific Open Graph implementation:
# - Java
# - Node
# - Py
# - Ruby
\bOpenGraph\b
# Should be `OpenShift`
\bOpenshift\b

View File

@@ -131,4 +131,4 @@ go install(?:\s+[a-z]+\.[-@\w/.]+)+
# hit-count: 1 file-count: 1
# microsoft
\b(?:https?://|)(?:(?:(?:blogs|download\.visualstudio|docs|msdn2?|research)\.|)microsoft|blogs\.msdn)\.co(?:m|\.\w\w)/[-_a-zA-Z0-9()=./%]*
\b(?:https?://|)(?:(?:(?:blogs|download\.visualstudio|docs|msdn2?|research)\.|)microsoft|blogs\.msdn)\.co(?:m|\.\w\w)/[-_a-zA-Z0-9()=./%]*

View File

@@ -1,47 +0,0 @@
name: Dev container prebuild
on:
push:
branches: ["main"]
tags: ["v*.*.*"]
jobs:
devcontainer:
runs-on: ubuntu-24.04
steps:
- name: Checkout code
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-tags: true
fetch-depth: 0
persist-credentials: false
- name: Set up QEMU
uses: docker/setup-qemu-action@29109295f81e9208d7d86ff1c6c12d2833863392 # v3.6.0
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
- uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
with:
node-version: latest
- run: |
sudo apt-get update
sudo apt-get -y install skopeo
- name: Log into registry
if: github.event_name != 'pull_request'
uses: docker/login-action@343f7c4344506bcbf9b4de18042ae17996df046d # v3.0.0
with:
registry: ghcr.io
username: techarohq
password: ${{ secrets.GITHUB_TOKEN }}
- name: Pre-build dev container image
uses: devcontainers/ci@8bf61b26e9c3a98f69cb6ce2f88d24ff59b785c6 # v0.3.1900000417
with:
imageName: ghcr.io/techarohq/anubis/devcontainer
cacheFrom: ghcr.io/techarohq/anubis/devcontainer
push: always
platform: linux/amd64,linux/arm64

View File

@@ -22,7 +22,7 @@ jobs:
persist-credentials: false
- name: Set up Homebrew
uses: Homebrew/actions/setup-homebrew@main
uses: Homebrew/actions/setup-homebrew@master
- name: Setup Homebrew cellar cache
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3

View File

@@ -3,8 +3,8 @@ name: Docker image builds
on:
workflow_dispatch:
push:
branches: ["main"]
tags: ["v*"]
branches: [ "main" ]
tags: [ "v*" ]
env:
DOCKER_METADATA_SET_OUTPUT_ENV: "true"
@@ -32,7 +32,7 @@ jobs:
echo "IMAGE=ghcr.io/${GITHUB_REPOSITORY,,}" >> $GITHUB_ENV
- name: Set up Homebrew
uses: Homebrew/actions/setup-homebrew@main
uses: Homebrew/actions/setup-homebrew@master
- name: Setup Homebrew cellar cache
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
@@ -55,7 +55,7 @@ jobs:
run: |
brew bundle
- name: Log into registry
- name: Log into registry
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
@@ -77,8 +77,9 @@ jobs:
DOCKER_REPO: ${{ env.IMAGE }}
SLOG_LEVEL: debug
- name: Generate artifact attestation
uses: actions/attest-build-provenance@e8998f949152b193b063cb0ec769d69d929409be # v2.4.0
uses: actions/attest-build-provenance@db473fddc028af60658334401dc6fa3ffd8669fd # v2.3.0
with:
subject-name: ${{ env.IMAGE }}
subject-digest: ${{ steps.build.outputs.digest }}

View File

@@ -22,7 +22,7 @@ jobs:
persist-credentials: false
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- name: Log into registry
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
@@ -50,14 +50,14 @@ jobs:
push: true
- name: Apply k8s manifests to aeacus
uses: actions-hub/kubectl@d50394b7d704525f93faefce1e65a6329ff67271 # v1.33.2
uses: actions-hub/kubectl@f632a31512a74cb35940627c49c20f67723cbaaf # v1.33.1
env:
KUBE_CONFIG: ${{ secrets.LIMSA_LOMINSA_KUBECONFIG }}
with:
args: apply -k docs/manifest
- name: Apply k8s manifests to aeacus
uses: actions-hub/kubectl@d50394b7d704525f93faefce1e65a6329ff67271 # v1.33.2
uses: actions-hub/kubectl@f632a31512a74cb35940627c49c20f67723cbaaf # v1.33.1
env:
KUBE_CONFIG: ${{ secrets.LIMSA_LOMINSA_KUBECONFIG }}
with:

View File

@@ -18,7 +18,7 @@ jobs:
persist-credentials: false
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- name: Docker meta
id: meta

View File

@@ -25,7 +25,7 @@ jobs:
sudo apt-get install -y build-essential
- name: Set up Homebrew
uses: Homebrew/actions/setup-homebrew@main
uses: Homebrew/actions/setup-homebrew@master
- name: Setup Homebrew cellar cache
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3

View File

@@ -25,7 +25,7 @@ jobs:
sudo apt-get install -y build-essential
- name: Set up Homebrew
uses: Homebrew/actions/setup-homebrew@main
uses: Homebrew/actions/setup-homebrew@master
- name: Setup Homebrew cellar cache
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3

View File

@@ -27,7 +27,7 @@ jobs:
sudo apt-get install -y build-essential
- name: Set up Homebrew
uses: Homebrew/actions/setup-homebrew@main
uses: Homebrew/actions/setup-homebrew@master
- name: Setup Homebrew cellar cache
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3

View File

@@ -1,37 +0,0 @@
name: Regenerate ssh ci runner image
on:
# pull_request:
# branches: ["main"]
schedule:
- cron: "0 0 1,8,15,22 * *"
workflow_dispatch:
permissions:
pull-requests: write
contents: write
packages: write
jobs:
ssh-ci-rebuild:
if: github.repository == 'TecharoHQ/anubis'
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-tags: true
fetch-depth: 0
persist-credentials: false
- name: Log into registry
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
username: ${{ github.repository_owner }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
- name: Build and push
run: |
cd ./test/ssh-ci
docker buildx bake --push

View File

@@ -1,37 +0,0 @@
name: SSH CI
on:
push:
branches: ["main"]
# pull_request:
# branches: ["main"]
permissions:
contents: read
jobs:
ssh:
if: github.repository == 'TecharoHQ/anubis'
runs-on: ubuntu-24.04
strategy:
matrix:
host:
- ubuntu@riscv64.techaro.lol
- ci@ppc64le.techaro.lol
steps:
- name: Checkout code
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-tags: true
fetch-depth: 0
persist-credentials: false
- name: Install CI target SSH key
uses: shimataro/ssh-key-action@d4fffb50872869abe2d9a9098a6d9c5aa7d16be4 # v2.7.0
with:
key: ${{ secrets.CI_SSH_KEY }}
name: id_rsa
known_hosts: ${{ secrets.CI_SSH_KNOWN_HOSTS }}
- name: Run CI
run: bash test/ssh-ci/rigging.sh ${{ matrix.host }}
env:
GITHUB_RUN_ID: ${{ github.run_id }}

View File

@@ -21,7 +21,7 @@ jobs:
persist-credentials: false
- name: Install the latest version of uv
uses: astral-sh/setup-uv@bd01e18f51369d5a26f1651c3cb451d3417e3bba # v6.3.1
uses: astral-sh/setup-uv@f0ec1fc3b38f5e7cd731bb6ce540c5af426746bb # v6.1.0
- name: Run zizmor 🌈
run: uvx zizmor --format sarif . > results.sarif
@@ -29,7 +29,7 @@ jobs:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Upload SARIF file
uses: github/codeql-action/upload-sarif@39edc492dbe16b1465b0cafca41432d857bdb31a # v3.29.1
uses: github/codeql-action/upload-sarif@fca7ace96b7d713c7035871441bd52efbe39e27e # v3.28.19
with:
sarif_file: results.sarif
category: zizmor

2
.gitignore vendored
View File

@@ -20,5 +20,3 @@ node_modules
# how does this get here
doc/VERSION
web/static/locales/*.json

View File

@@ -1,10 +0,0 @@
{
"recommendations": [
"esbenp.prettier-vscode",
"ms-azuretools.vscode-containers",
"golang.go",
"unifiedjs.vscode-mdx",
"a-h.templ",
"redhat.vscode-yaml"
]
}

27
.vscode/launch.json vendored
View File

@@ -1,27 +0,0 @@
{
// Use IntelliSense to learn about possible attributes.
// Hover to view descriptions of existing attributes.
// For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
"version": "0.2.0",
"configurations": [
{
"name": "Launch Package",
"type": "go",
"request": "launch",
"mode": "auto",
"program": "${fileDirname}"
},
{
"name": "Anubis [dev]",
"command": "npm run dev",
"request": "launch",
"type": "node-terminal"
},
{
"name": "Start Docs",
"command": "cd docs && npm ci && npm run start",
"request": "launch",
"type": "node-terminal"
}
]
}

19
.vscode/settings.json vendored
View File

@@ -11,24 +11,5 @@
"zig": false,
"javascript": false,
"properties": false
},
"[markdown]": {
"editor.wordWrap": "wordWrapColumn",
"editor.wordWrapColumn": 80,
"editor.wordBasedSuggestions": "off"
},
"[mdx]": {
"editor.wordWrap": "wordWrapColumn",
"editor.wordWrapColumn": 80,
"editor.wordBasedSuggestions": "off"
},
"[nunjucks]": {
"editor.wordWrap": "wordWrapColumn",
"editor.wordWrapColumn": 80,
"editor.wordBasedSuggestions": "off"
},
"cSpell.enabledFileTypes": {
"mdx": true,
"md": true
}
}

30
Dockerfile Normal file
View File

@@ -0,0 +1,30 @@
ARG ALPINE_VERSION=edge
FROM --platform=${BUILDPLATFORM} alpine:${ALPINE_VERSION} AS build
ARG TARGETOS
ARG TARGETARCH
ARG COMPONENT=anubis
ARG VERSION=devel-docker
RUN apk -U add go nodejs git build-base git npm bash zstd brotli gzip
WORKDIR /app
COPY go.mod go.sum ./
RUN go mod download
COPY . .
RUN --mount=type=cache,target=/root/.cache npm ci && npm run assets
RUN --mount=type=cache,target=/root/.cache GOOS=${TARGETOS} GOARCH=${TARGETARCH} CGO_ENABLED=0 GOARM=7 go build -gcflags "all=-N -l" -o /app/bin/${COMPONENT} -ldflags "-s -w -extldflags -static -X github.com/TecharoHQ/anubis.Version=${VERSION}" ./cmd/${COMPONENT}
FROM alpine:${ALPINE_VERSION} AS run
WORKDIR /app
RUN apk -U add ca-certificates mailcap
COPY --from=build /app/bin/anubis /app/bin/anubis
CMD ["/app/bin/anubis"]
HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 CMD [ "/app/bin/anubis", "--healthcheck" ]
LABEL org.opencontainers.image.source="https://github.com/TecharoHQ/anubis"

View File

@@ -18,7 +18,6 @@ assets: deps
build: assets
$(GO) build -o ./var/anubis ./cmd/anubis
$(GO) build -o ./var/robots2policy ./cmd/robots2policy
@echo "Anubis is now built to ./var/anubis"
lint: assets
@@ -28,7 +27,6 @@ lint: assets
prebaked-build:
$(GO) build -o ./var/anubis -ldflags "-X 'github.com/TecharoHQ/anubis.Version=$(VERSION)'" ./cmd/anubis
$(GO) build -o ./var/robots2policy -ldflags "-X 'github.com/TecharoHQ/anubis.Version=$(VERSION)'" ./cmd/robots2policy
test: assets
$(GO) test ./...

View File

@@ -9,7 +9,6 @@
![GitHub go.mod Go version](https://img.shields.io/github/go-mod/go-version/TecharoHQ/anubis)
![language count](https://img.shields.io/github/languages/count/TecharoHQ/anubis)
![repo size](https://img.shields.io/github/repo-size/TecharoHQ/anubis)
[![GitHub Sponsors](https://img.shields.io/github/sponsors/Xe)](https://github.com/sponsors/Xe)
## Sponsors

View File

@@ -1 +1 @@
1.20.0
1.19.1

View File

@@ -11,11 +11,12 @@ var Version = "devel"
// CookieName is the name of the cookie that Anubis uses in order to validate
// access.
var CookieName = "techaro.lol-anubis-auth"
const CookieName = "techaro.lol-anubis-auth"
// TestCookieName is the name of the cookie that Anubis uses in order to check
// if cookies are enabled on the client's browser.
var TestCookieName = "techaro.lol-anubis-cookie-verification"
// WithDomainCookieName is the name that is prepended to the per-domain cookie used when COOKIE_DOMAIN is set.
const WithDomainCookieName = "techaro.lol-anubis-auth-for-"
const TestCookieName = "techaro.lol-anubis-cookie-test-if-you-block-this-anubis-wont-work"
// CookieDefaultExpirationTime is the amount of time before the cookie/JWT expires.
const CookieDefaultExpirationTime = 7 * 24 * time.Hour

View File

@@ -30,13 +30,11 @@ import (
"github.com/TecharoHQ/anubis"
"github.com/TecharoHQ/anubis/data"
"github.com/TecharoHQ/anubis/internal"
"github.com/TecharoHQ/anubis/internal/thoth"
libanubis "github.com/TecharoHQ/anubis/lib"
botPolicy "github.com/TecharoHQ/anubis/lib/policy"
"github.com/TecharoHQ/anubis/lib/policy/config"
"github.com/TecharoHQ/anubis/web"
"github.com/facebookgo/flagenv"
_ "github.com/joho/godotenv/autoload"
"github.com/prometheus/client_golang/prometheus/promhttp"
)
@@ -46,12 +44,8 @@ var (
bindNetwork = flag.String("bind-network", "tcp", "network family to bind HTTP to, e.g. unix, tcp")
challengeDifficulty = flag.Int("difficulty", anubis.DefaultDifficulty, "difficulty of the challenge")
cookieDomain = flag.String("cookie-domain", "", "if set, the top-level domain that the Anubis cookie will be valid for")
cookieDynamicDomain = flag.Bool("cookie-dynamic-domain", false, "if set, automatically set the cookie Domain value based on the request domain")
cookieExpiration = flag.Duration("cookie-expiration-time", anubis.CookieDefaultExpirationTime, "The amount of time the authorization cookie is valid for")
cookiePrefix = flag.String("cookie-prefix", "techaro.lol-anubis", "prefix for browser cookies created by Anubis")
cookiePartitioned = flag.Bool("cookie-partitioned", false, "if true, sets the partitioned flag on Anubis cookies, enabling CHIPS support")
hs512Secret = flag.String("hs512-secret", "", "secret used to sign JWTs, uses ed25519 if not set")
cookieSecure = flag.Bool("cookie-secure", true, "if true, sets the secure flag on Anubis cookies")
ed25519PrivateKeyHex = flag.String("ed25519-private-key-hex", "", "private key used to sign JWTs, if not set a random one will be assigned")
ed25519PrivateKeyHexFile = flag.String("ed25519-private-key-hex-file", "", "file name containing value for ed25519-private-key-hex")
metricsBind = flag.String("metrics-bind", ":9090", "network address to bind metrics to")
@@ -61,7 +55,6 @@ var (
policyFname = flag.String("policy-fname", "", "full path to anubis policy document (defaults to a sensible built-in policy)")
redirectDomains = flag.String("redirect-domains", "", "list of domains separated by commas which anubis is allowed to redirect to. Leaving this unset allows any domain.")
slogLevel = flag.String("slog-level", "INFO", "logging level (see https://pkg.go.dev/log/slog#hdr-Levels)")
stripBasePrefix = flag.Bool("strip-base-prefix", false, "if true, strips the base prefix from requests forwarded to the target server")
target = flag.String("target", "http://localhost:3923", "target to reverse proxy to, set to an empty string to disable proxying when only using auth request")
targetSNI = flag.String("target-sni", "", "if set, the value of the TLS handshake hostname when forwarding requests to the target")
targetHost = flag.String("target-host", "", "if set, the value of the Host header when forwarding requests to the target")
@@ -76,10 +69,6 @@ var (
webmasterEmail = flag.String("webmaster-email", "", "if set, displays webmaster's email on the reject page for appeals")
versionFlag = flag.Bool("version", false, "print Anubis version")
xffStripPrivate = flag.Bool("xff-strip-private", true, "if set, strip private addresses from X-Forwarded-For")
thothInsecure = flag.Bool("thoth-insecure", false, "if set, connect to Thoth over plain HTTP/2, don't enable this unless support told you to")
thothURL = flag.String("thoth-url", "", "if set, URL for Thoth, the IP reputation database for Anubis")
thothToken = flag.String("thoth-token", "", "if set, API token for Thoth, the IP reputation database for Anubis")
)
func keyFromHex(value string) (ed25519.PrivateKey, error) {
@@ -109,41 +98,8 @@ func doHealthCheck() error {
return nil
}
// parseBindNetFromAddr determine bind network and address based on the given network and address.
func parseBindNetFromAddr(address string) (string, string) {
defaultScheme := "http://"
if !strings.Contains(address, "://") {
if strings.HasPrefix(address, ":") {
address = defaultScheme + "localhost" + address
} else {
address = defaultScheme + address
}
}
bindUri, err := url.Parse(address)
if err != nil {
log.Fatal(fmt.Errorf("failed to parse bind URL: %w", err))
}
switch bindUri.Scheme {
case "unix":
return "unix", bindUri.Path
case "tcp", "http", "https":
return "tcp", bindUri.Host
default:
log.Fatal(fmt.Errorf("unsupported network scheme %s in address %s", bindUri.Scheme, address))
}
return "", address
}
func setupListener(network string, address string) (net.Listener, string) {
formattedAddress := ""
if network == "" {
// keep compatibility
network, address = parseBindNetFromAddr(address)
}
switch network {
case "unix":
formattedAddress = "unix:" + address
@@ -276,29 +232,7 @@ func main() {
}
}
if *cookieDomain != "" && *cookieDynamicDomain {
log.Fatalf("you can't set COOKIE_DOMAIN and COOKIE_DYNAMIC_DOMAIN at the same time")
}
ctx := context.Background()
// Thoth configuration
switch {
case *thothURL != "" && *thothToken == "":
slog.Warn("THOTH_URL is set but no THOTH_TOKEN is set")
case *thothURL == "" && *thothToken != "":
slog.Warn("THOTH_TOKEN is set but no THOTH_URL is set")
case *thothURL != "" && *thothToken != "":
slog.Debug("connecting to Thoth")
thothClient, err := thoth.New(ctx, *thothURL, *thothToken, *thothInsecure)
if err != nil {
log.Fatalf("can't dial thoth at %s: %v", *thothURL, err)
}
ctx = thoth.With(ctx, thothClient)
}
policy, err := libanubis.LoadPoliciesOrDefault(ctx, *policyFname, *challengeDifficulty)
policy, err := libanubis.LoadPoliciesOrDefault(*policyFname, *challengeDifficulty)
if err != nil {
log.Fatalf("can't parse policy file: %v", err)
}
@@ -326,20 +260,12 @@ func main() {
} else if strings.HasSuffix(*basePrefix, "/") {
log.Fatalf("[misconfiguration] base-prefix must not end with a slash")
}
if *stripBasePrefix && *basePrefix == "" {
log.Fatalf("[misconfiguration] strip-base-prefix is set to true, but base-prefix is not set, " +
"this may result in unexpected behavior")
}
var ed25519Priv ed25519.PrivateKey
if *hs512Secret != "" && (*ed25519PrivateKeyHex != "" || *ed25519PrivateKeyHexFile != "") {
log.Fatal("do not specify both HS512 and ED25519 secrets")
} else if *hs512Secret != "" {
ed25519Priv = ed25519.PrivateKey(*hs512Secret)
} else if *ed25519PrivateKeyHex != "" && *ed25519PrivateKeyHexFile != "" {
var priv ed25519.PrivateKey
if *ed25519PrivateKeyHex != "" && *ed25519PrivateKeyHexFile != "" {
log.Fatal("do not specify both ED25519_PRIVATE_KEY_HEX and ED25519_PRIVATE_KEY_HEX_FILE")
} else if *ed25519PrivateKeyHex != "" {
ed25519Priv, err = keyFromHex(*ed25519PrivateKeyHex)
priv, err = keyFromHex(*ed25519PrivateKeyHex)
if err != nil {
log.Fatalf("failed to parse and validate ED25519_PRIVATE_KEY_HEX: %v", err)
}
@@ -349,12 +275,12 @@ func main() {
log.Fatalf("failed to read ED25519_PRIVATE_KEY_HEX_FILE %s: %v", *ed25519PrivateKeyHexFile, err)
}
ed25519Priv, err = keyFromHex(string(bytes.TrimSpace(hexFile)))
priv, err = keyFromHex(string(bytes.TrimSpace(hexFile)))
if err != nil {
log.Fatalf("failed to parse and validate content of ED25519_PRIVATE_KEY_HEX_FILE: %v", err)
}
} else {
_, ed25519Priv, err = ed25519.GenerateKey(rand.Reader)
_, priv, err = ed25519.GenerateKey(rand.Reader)
if err != nil {
log.Fatalf("failed to generate ed25519 key: %v", err)
}
@@ -376,35 +302,21 @@ func main() {
slog.Warn("REDIRECT_DOMAINS is not set, Anubis will only redirect to the same domain a request is coming from, see https://anubis.techaro.lol/docs/admin/configuration/redirect-domains")
}
anubis.CookieName = *cookiePrefix + "-auth"
anubis.TestCookieName = *cookiePrefix + "-cookie-verification"
// If OpenGraph configuration values are not set in the config file, use the
// values from flags / envvars.
if !policy.OpenGraph.Enabled {
policy.OpenGraph.Enabled = *ogPassthrough
policy.OpenGraph.ConsiderHost = *ogCacheConsiderHost
policy.OpenGraph.TimeToLive = *ogTimeToLive
policy.OpenGraph.Override = map[string]string{}
}
s, err := libanubis.New(libanubis.Options{
BasePrefix: *basePrefix,
StripBasePrefix: *stripBasePrefix,
Next: rp,
Policy: policy,
ServeRobotsTXT: *robotsTxt,
ED25519PrivateKey: ed25519Priv,
HS512Secret: []byte(*hs512Secret),
CookieDomain: *cookieDomain,
CookieDynamicDomain: *cookieDynamicDomain,
CookieExpiration: *cookieExpiration,
CookiePartitioned: *cookiePartitioned,
RedirectDomains: redirectDomainsList,
Target: *target,
WebmasterEmail: *webmasterEmail,
OpenGraph: policy.OpenGraph,
CookieSecure: *cookieSecure,
BasePrefix: *basePrefix,
Next: rp,
Policy: policy,
ServeRobotsTXT: *robotsTxt,
PrivateKey: priv,
CookieDomain: *cookieDomain,
CookieExpiration: *cookieExpiration,
CookiePartitioned: *cookiePartitioned,
OGPassthrough: *ogPassthrough,
OGTimeToLive: *ogTimeToLive,
RedirectDomains: redirectDomainsList,
Target: *target,
WebmasterEmail: *webmasterEmail,
OGCacheConsidersHost: *ogCacheConsiderHost,
})
if err != nil {
log.Fatalf("can't construct libanubis.Server: %v", err)

View File

@@ -1,78 +0,0 @@
/*
Batch process robots.txt files from archives like https://github.com/nrjones8/robots-dot-txt-archive-bot/tree/master/data/cleaned
into Anubis CEL policies. Usage: go run batch_process.go <directory with robots.txt files>
*/
package main
import (
"fmt"
"io/fs"
"log"
"os"
"os/exec"
"path/filepath"
"strings"
)
func main() {
if len(os.Args) < 2 {
fmt.Println("Usage: go run batch_process.go <cleaned_directory>")
fmt.Println("Example: go run batch_process.go ./cleaned")
os.Exit(1)
}
cleanedDir := os.Args[1]
outputDir := "generated_policies"
// Create output directory
if err := os.MkdirAll(outputDir, 0755); err != nil {
log.Fatalf("Failed to create output directory: %v", err)
}
count := 0
err := filepath.WalkDir(cleanedDir, func(path string, d fs.DirEntry, err error) error {
if err != nil {
return err
}
// Skip directories
if d.IsDir() {
return nil
}
// Generate policy name from file path
relPath, _ := filepath.Rel(cleanedDir, path)
policyName := strings.ReplaceAll(relPath, "/", "-")
policyName = strings.TrimSuffix(policyName, "-robots.txt")
policyName = strings.ReplaceAll(policyName, ".", "-")
outputFile := filepath.Join(outputDir, policyName+".yaml")
cmd := exec.Command("go", "run", "main.go",
"-input", path,
"-output", outputFile,
"-name", policyName,
"-format", "yaml")
if err := cmd.Run(); err != nil {
fmt.Printf("Warning: Failed to process %s: %v\n", path, err)
return nil // Continue processing other files
}
count++
if count%100 == 0 {
fmt.Printf("Processed %d files...\n", count)
} else if count%10 == 0 {
fmt.Print(".")
}
return nil
})
if err != nil {
log.Fatalf("Error walking directory: %v", err)
}
fmt.Printf("Successfully processed %d robots.txt files\n", count)
fmt.Printf("Generated policies saved to: %s/\n", outputDir)
}

View File

@@ -1,313 +0,0 @@
package main
import (
"bufio"
"encoding/json"
"flag"
"fmt"
"io"
"log"
"net/http"
"os"
"regexp"
"strings"
"github.com/TecharoHQ/anubis/lib/policy/config"
"sigs.k8s.io/yaml"
)
var (
inputFile = flag.String("input", "", "path to robots.txt file (use - for stdin)")
outputFile = flag.String("output", "", "output file path (use - for stdout, defaults to stdout)")
outputFormat = flag.String("format", "yaml", "output format: yaml or json")
baseAction = flag.String("action", "CHALLENGE", "default action for disallowed paths: ALLOW, DENY, CHALLENGE, WEIGH")
crawlDelay = flag.Int("crawl-delay-weight", 0, "if > 0, add weight adjustment for crawl-delay (difficulty adjustment)")
policyName = flag.String("name", "robots-txt-policy", "name for the generated policy")
userAgentDeny = flag.String("deny-user-agents", "DENY", "action for specifically blocked user agents: DENY, CHALLENGE")
helpFlag = flag.Bool("help", false, "show help")
)
type RobotsRule struct {
UserAgent string
Disallows []string
Allows []string
CrawlDelay int
IsBlacklist bool // true if this is a specifically denied user agent
}
type AnubisRule struct {
Expression *config.ExpressionOrList `yaml:"expression,omitempty" json:"expression,omitempty"`
Challenge *config.ChallengeRules `yaml:"challenge,omitempty" json:"challenge,omitempty"`
Weight *config.Weight `yaml:"weight,omitempty" json:"weight,omitempty"`
Name string `yaml:"name" json:"name"`
Action string `yaml:"action" json:"action"`
}
func init() {
flag.Usage = func() {
fmt.Fprintf(os.Stderr, "Usage of %s:\n", os.Args[0])
fmt.Fprintf(os.Stderr, "%s [options] -input <robots.txt>\n\n", os.Args[0])
flag.PrintDefaults()
fmt.Fprintln(os.Stderr, "\nExamples:")
fmt.Fprintln(os.Stderr, " # Convert local robots.txt file")
fmt.Fprintln(os.Stderr, " robots2policy -input robots.txt -output policy.yaml")
fmt.Fprintln(os.Stderr, "")
fmt.Fprintln(os.Stderr, " # Convert from URL")
fmt.Fprintln(os.Stderr, " robots2policy -input https://example.com/robots.txt -format json")
fmt.Fprintln(os.Stderr, "")
fmt.Fprintln(os.Stderr, " # Read from stdin, write to stdout")
fmt.Fprintln(os.Stderr, " curl https://example.com/robots.txt | robots2policy -input -")
os.Exit(2)
}
}
func main() {
flag.Parse()
if len(flag.Args()) > 0 || *helpFlag || *inputFile == "" {
flag.Usage()
}
// Read robots.txt
var input io.Reader
if *inputFile == "-" {
input = os.Stdin
} else if strings.HasPrefix(*inputFile, "http://") || strings.HasPrefix(*inputFile, "https://") {
resp, err := http.Get(*inputFile)
if err != nil {
log.Fatalf("failed to fetch robots.txt from URL: %v", err)
}
defer resp.Body.Close()
input = resp.Body
} else {
file, err := os.Open(*inputFile)
if err != nil {
log.Fatalf("failed to open input file: %v", err)
}
defer file.Close()
input = file
}
// Parse robots.txt
rules, err := parseRobotsTxt(input)
if err != nil {
log.Fatalf("failed to parse robots.txt: %v", err)
}
// Convert to Anubis rules
anubisRules := convertToAnubisRules(rules)
// Check if any rules were generated
if len(anubisRules) == 0 {
log.Fatal("no valid rules generated from robots.txt - file may be empty or contain no disallow directives")
}
// Generate output
var output []byte
switch strings.ToLower(*outputFormat) {
case "yaml":
output, err = yaml.Marshal(anubisRules)
case "json":
output, err = json.MarshalIndent(anubisRules, "", " ")
default:
log.Fatalf("unsupported output format: %s (use yaml or json)", *outputFormat)
}
if err != nil {
log.Fatalf("failed to marshal output: %v", err)
}
// Write output
if *outputFile == "" || *outputFile == "-" {
fmt.Print(string(output))
} else {
err = os.WriteFile(*outputFile, output, 0644)
if err != nil {
log.Fatalf("failed to write output file: %v", err)
}
fmt.Printf("Generated Anubis policy written to %s\n", *outputFile)
}
}
func parseRobotsTxt(input io.Reader) ([]RobotsRule, error) {
scanner := bufio.NewScanner(input)
var rules []RobotsRule
var currentRule *RobotsRule
for scanner.Scan() {
line := strings.TrimSpace(scanner.Text())
// Skip empty lines and comments
if line == "" || strings.HasPrefix(line, "#") {
continue
}
// Split on first colon
parts := strings.SplitN(line, ":", 2)
if len(parts) != 2 {
continue
}
directive := strings.TrimSpace(strings.ToLower(parts[0]))
value := strings.TrimSpace(parts[1])
switch directive {
case "user-agent":
// Start a new rule section
if currentRule != nil {
rules = append(rules, *currentRule)
}
currentRule = &RobotsRule{
UserAgent: value,
Disallows: make([]string, 0),
Allows: make([]string, 0),
}
case "disallow":
if currentRule != nil && value != "" {
currentRule.Disallows = append(currentRule.Disallows, value)
}
case "allow":
if currentRule != nil && value != "" {
currentRule.Allows = append(currentRule.Allows, value)
}
case "crawl-delay":
if currentRule != nil {
if delay, err := parseIntSafe(value); err == nil {
currentRule.CrawlDelay = delay
}
}
}
}
// Don't forget the last rule
if currentRule != nil {
rules = append(rules, *currentRule)
}
// Mark blacklisted user agents (those with "Disallow: /")
for i := range rules {
for _, disallow := range rules[i].Disallows {
if disallow == "/" {
rules[i].IsBlacklist = true
break
}
}
}
return rules, scanner.Err()
}
func parseIntSafe(s string) (int, error) {
var result int
_, err := fmt.Sscanf(s, "%d", &result)
return result, err
}
func convertToAnubisRules(robotsRules []RobotsRule) []AnubisRule {
var anubisRules []AnubisRule
ruleCounter := 0
for _, robotsRule := range robotsRules {
userAgent := robotsRule.UserAgent
// Handle crawl delay as weight adjustment (do this first before any continues)
if robotsRule.CrawlDelay > 0 && *crawlDelay > 0 {
ruleCounter++
rule := AnubisRule{
Name: fmt.Sprintf("%s-crawl-delay-%d", *policyName, ruleCounter),
Action: "WEIGH",
Weight: &config.Weight{Adjust: *crawlDelay},
}
if userAgent == "*" {
rule.Expression = &config.ExpressionOrList{
All: []string{"true"}, // Always applies
}
} else {
rule.Expression = &config.ExpressionOrList{
All: []string{fmt.Sprintf("userAgent.contains(%q)", userAgent)},
}
}
anubisRules = append(anubisRules, rule)
}
// Handle blacklisted user agents (complete deny/challenge)
if robotsRule.IsBlacklist {
ruleCounter++
rule := AnubisRule{
Name: fmt.Sprintf("%s-blacklist-%d", *policyName, ruleCounter),
Action: *userAgentDeny,
}
if userAgent == "*" {
// This would block everything - convert to a weight adjustment instead
rule.Name = fmt.Sprintf("%s-global-restriction-%d", *policyName, ruleCounter)
rule.Action = "WEIGH"
rule.Weight = &config.Weight{Adjust: 20} // Increase difficulty significantly
rule.Expression = &config.ExpressionOrList{
All: []string{"true"}, // Always applies
}
} else {
rule.Expression = &config.ExpressionOrList{
All: []string{fmt.Sprintf("userAgent.contains(%q)", userAgent)},
}
}
anubisRules = append(anubisRules, rule)
continue
}
// Handle specific disallow rules
for _, disallow := range robotsRule.Disallows {
if disallow == "/" {
continue // Already handled as blacklist above
}
ruleCounter++
rule := AnubisRule{
Name: fmt.Sprintf("%s-disallow-%d", *policyName, ruleCounter),
Action: *baseAction,
}
// Build CEL expression
var conditions []string
// Add user agent condition if not wildcard
if userAgent != "*" {
conditions = append(conditions, fmt.Sprintf("userAgent.contains(%q)", userAgent))
}
// Add path condition
pathCondition := buildPathCondition(disallow)
conditions = append(conditions, pathCondition)
rule.Expression = &config.ExpressionOrList{
All: conditions,
}
anubisRules = append(anubisRules, rule)
}
}
return anubisRules
}
func buildPathCondition(robotsPath string) string {
// Handle wildcards in robots.txt paths
if strings.Contains(robotsPath, "*") || strings.Contains(robotsPath, "?") {
// Convert robots.txt wildcards to regex
regex := regexp.QuoteMeta(robotsPath)
regex = strings.ReplaceAll(regex, `\*`, `.*`) // * becomes .*
regex = strings.ReplaceAll(regex, `\?`, `.`) // ? becomes .
regex = "^" + regex
return fmt.Sprintf("path.matches(%q)", regex)
}
// Simple prefix match for most cases
return fmt.Sprintf("path.startsWith(%q)", robotsPath)
}

View File

@@ -1,418 +0,0 @@
package main
import (
"encoding/json"
"fmt"
"os"
"path/filepath"
"reflect"
"strings"
"testing"
"gopkg.in/yaml.v3"
)
type TestCase struct {
name string
robotsFile string
expectedFile string
options TestOptions
}
type TestOptions struct {
format string
action string
crawlDelayWeight int
policyName string
deniedAction string
}
func TestDataFileConversion(t *testing.T) {
testCases := []TestCase{
{
name: "simple_default",
robotsFile: "simple.robots.txt",
expectedFile: "simple.yaml",
options: TestOptions{format: "yaml"},
},
{
name: "simple_json",
robotsFile: "simple.robots.txt",
expectedFile: "simple.json",
options: TestOptions{format: "json"},
},
{
name: "simple_deny_action",
robotsFile: "simple.robots.txt",
expectedFile: "deny-action.yaml",
options: TestOptions{format: "yaml", action: "DENY"},
},
{
name: "simple_custom_name",
robotsFile: "simple.robots.txt",
expectedFile: "custom-name.yaml",
options: TestOptions{format: "yaml", policyName: "my-custom-policy"},
},
{
name: "blacklist_with_crawl_delay",
robotsFile: "blacklist.robots.txt",
expectedFile: "blacklist.yaml",
options: TestOptions{format: "yaml", crawlDelayWeight: 3},
},
{
name: "wildcards",
robotsFile: "wildcards.robots.txt",
expectedFile: "wildcards.yaml",
options: TestOptions{format: "yaml"},
},
{
name: "empty_file",
robotsFile: "empty.robots.txt",
expectedFile: "empty.yaml",
options: TestOptions{format: "yaml"},
},
{
name: "complex_scenario",
robotsFile: "complex.robots.txt",
expectedFile: "complex.yaml",
options: TestOptions{format: "yaml", crawlDelayWeight: 5},
},
}
for _, tc := range testCases {
t.Run(tc.name, func(t *testing.T) {
robotsPath := filepath.Join("testdata", tc.robotsFile)
expectedPath := filepath.Join("testdata", tc.expectedFile)
// Read robots.txt input
robotsFile, err := os.Open(robotsPath)
if err != nil {
t.Fatalf("Failed to open robots file %s: %v", robotsPath, err)
}
defer robotsFile.Close()
// Parse robots.txt
rules, err := parseRobotsTxt(robotsFile)
if err != nil {
t.Fatalf("Failed to parse robots.txt: %v", err)
}
// Set test options
oldFormat := *outputFormat
oldAction := *baseAction
oldCrawlDelay := *crawlDelay
oldPolicyName := *policyName
oldDeniedAction := *userAgentDeny
if tc.options.format != "" {
*outputFormat = tc.options.format
}
if tc.options.action != "" {
*baseAction = tc.options.action
}
if tc.options.crawlDelayWeight > 0 {
*crawlDelay = tc.options.crawlDelayWeight
}
if tc.options.policyName != "" {
*policyName = tc.options.policyName
}
if tc.options.deniedAction != "" {
*userAgentDeny = tc.options.deniedAction
}
// Restore options after test
defer func() {
*outputFormat = oldFormat
*baseAction = oldAction
*crawlDelay = oldCrawlDelay
*policyName = oldPolicyName
*userAgentDeny = oldDeniedAction
}()
// Convert to Anubis rules
anubisRules := convertToAnubisRules(rules)
// Generate output
var actualOutput []byte
switch strings.ToLower(*outputFormat) {
case "yaml":
actualOutput, err = yaml.Marshal(anubisRules)
case "json":
actualOutput, err = json.MarshalIndent(anubisRules, "", " ")
}
if err != nil {
t.Fatalf("Failed to marshal output: %v", err)
}
// Read expected output
expectedOutput, err := os.ReadFile(expectedPath)
if err != nil {
t.Fatalf("Failed to read expected file %s: %v", expectedPath, err)
}
if strings.ToLower(*outputFormat) == "yaml" {
var actualData []interface{}
var expectedData []interface{}
err = yaml.Unmarshal(actualOutput, &actualData)
if err != nil {
t.Fatalf("Failed to unmarshal actual output: %v", err)
}
err = yaml.Unmarshal(expectedOutput, &expectedData)
if err != nil {
t.Fatalf("Failed to unmarshal expected output: %v", err)
}
// Compare data structures
if !compareData(actualData, expectedData) {
actualStr := strings.TrimSpace(string(actualOutput))
expectedStr := strings.TrimSpace(string(expectedOutput))
t.Errorf("Output mismatch for %s\nExpected:\n%s\n\nActual:\n%s", tc.name, expectedStr, actualStr)
}
} else {
var actualData []interface{}
var expectedData []interface{}
err = json.Unmarshal(actualOutput, &actualData)
if err != nil {
t.Fatalf("Failed to unmarshal actual JSON output: %v", err)
}
err = json.Unmarshal(expectedOutput, &expectedData)
if err != nil {
t.Fatalf("Failed to unmarshal expected JSON output: %v", err)
}
// Compare data structures
if !compareData(actualData, expectedData) {
actualStr := strings.TrimSpace(string(actualOutput))
expectedStr := strings.TrimSpace(string(expectedOutput))
t.Errorf("Output mismatch for %s\nExpected:\n%s\n\nActual:\n%s", tc.name, expectedStr, actualStr)
}
}
})
}
}
func TestCaseInsensitiveParsing(t *testing.T) {
robotsTxt := `User-Agent: *
Disallow: /admin
Crawl-Delay: 10
User-agent: TestBot
disallow: /test
crawl-delay: 5
USER-AGENT: UpperBot
DISALLOW: /upper
CRAWL-DELAY: 20`
reader := strings.NewReader(robotsTxt)
rules, err := parseRobotsTxt(reader)
if err != nil {
t.Fatalf("Failed to parse case-insensitive robots.txt: %v", err)
}
expectedRules := 3
if len(rules) != expectedRules {
t.Errorf("Expected %d rules, got %d", expectedRules, len(rules))
}
// Check that all crawl delays were parsed
for i, rule := range rules {
expectedDelays := []int{10, 5, 20}
if rule.CrawlDelay != expectedDelays[i] {
t.Errorf("Rule %d: expected crawl delay %d, got %d", i, expectedDelays[i], rule.CrawlDelay)
}
}
}
func TestVariousOutputFormats(t *testing.T) {
robotsTxt := `User-agent: *
Disallow: /admin`
reader := strings.NewReader(robotsTxt)
rules, err := parseRobotsTxt(reader)
if err != nil {
t.Fatalf("Failed to parse robots.txt: %v", err)
}
oldPolicyName := *policyName
*policyName = "test-policy"
defer func() { *policyName = oldPolicyName }()
anubisRules := convertToAnubisRules(rules)
// Test YAML output
yamlOutput, err := yaml.Marshal(anubisRules)
if err != nil {
t.Fatalf("Failed to marshal YAML: %v", err)
}
if !strings.Contains(string(yamlOutput), "name: test-policy-disallow-1") {
t.Errorf("YAML output doesn't contain expected rule name")
}
// Test JSON output
jsonOutput, err := json.MarshalIndent(anubisRules, "", " ")
if err != nil {
t.Fatalf("Failed to marshal JSON: %v", err)
}
if !strings.Contains(string(jsonOutput), `"name": "test-policy-disallow-1"`) {
t.Errorf("JSON output doesn't contain expected rule name")
}
}
func TestDifferentActions(t *testing.T) {
robotsTxt := `User-agent: *
Disallow: /admin`
testActions := []string{"ALLOW", "DENY", "CHALLENGE", "WEIGH"}
for _, action := range testActions {
t.Run("action_"+action, func(t *testing.T) {
reader := strings.NewReader(robotsTxt)
rules, err := parseRobotsTxt(reader)
if err != nil {
t.Fatalf("Failed to parse robots.txt: %v", err)
}
oldAction := *baseAction
*baseAction = action
defer func() { *baseAction = oldAction }()
anubisRules := convertToAnubisRules(rules)
if len(anubisRules) != 1 {
t.Fatalf("Expected 1 rule, got %d", len(anubisRules))
}
if anubisRules[0].Action != action {
t.Errorf("Expected action %s, got %s", action, anubisRules[0].Action)
}
})
}
}
func TestPolicyNaming(t *testing.T) {
robotsTxt := `User-agent: *
Disallow: /admin
Disallow: /private
User-agent: BadBot
Disallow: /`
testNames := []string{"custom-policy", "my-rules", "site-protection"}
for _, name := range testNames {
t.Run("name_"+name, func(t *testing.T) {
reader := strings.NewReader(robotsTxt)
rules, err := parseRobotsTxt(reader)
if err != nil {
t.Fatalf("Failed to parse robots.txt: %v", err)
}
oldName := *policyName
*policyName = name
defer func() { *policyName = oldName }()
anubisRules := convertToAnubisRules(rules)
// Check that all rule names use the custom prefix
for _, rule := range anubisRules {
if !strings.HasPrefix(rule.Name, name+"-") {
t.Errorf("Rule name %s doesn't start with expected prefix %s-", rule.Name, name)
}
}
})
}
}
func TestCrawlDelayWeights(t *testing.T) {
robotsTxt := `User-agent: *
Disallow: /admin
Crawl-delay: 10
User-agent: SlowBot
Disallow: /slow
Crawl-delay: 60`
testWeights := []int{1, 5, 10, 25}
for _, weight := range testWeights {
t.Run(fmt.Sprintf("weight_%d", weight), func(t *testing.T) {
reader := strings.NewReader(robotsTxt)
rules, err := parseRobotsTxt(reader)
if err != nil {
t.Fatalf("Failed to parse robots.txt: %v", err)
}
oldWeight := *crawlDelay
*crawlDelay = weight
defer func() { *crawlDelay = oldWeight }()
anubisRules := convertToAnubisRules(rules)
// Count weight rules and verify they have correct weight
weightRules := 0
for _, rule := range anubisRules {
if rule.Action == "WEIGH" && rule.Weight != nil {
weightRules++
if rule.Weight.Adjust != weight {
t.Errorf("Expected weight %d, got %d", weight, rule.Weight.Adjust)
}
}
}
expectedWeightRules := 2 // One for *, one for SlowBot
if weightRules != expectedWeightRules {
t.Errorf("Expected %d weight rules, got %d", expectedWeightRules, weightRules)
}
})
}
}
func TestBlacklistActions(t *testing.T) {
robotsTxt := `User-agent: BadBot
Disallow: /
User-agent: SpamBot
Disallow: /`
testActions := []string{"DENY", "CHALLENGE"}
for _, action := range testActions {
t.Run("blacklist_"+action, func(t *testing.T) {
reader := strings.NewReader(robotsTxt)
rules, err := parseRobotsTxt(reader)
if err != nil {
t.Fatalf("Failed to parse robots.txt: %v", err)
}
oldAction := *userAgentDeny
*userAgentDeny = action
defer func() { *userAgentDeny = oldAction }()
anubisRules := convertToAnubisRules(rules)
// All rules should be blacklist rules with the specified action
for _, rule := range anubisRules {
if !strings.Contains(rule.Name, "blacklist") {
t.Errorf("Expected blacklist rule, got %s", rule.Name)
}
if rule.Action != action {
t.Errorf("Expected action %s, got %s", action, rule.Action)
}
}
})
}
}
// compareData performs a deep comparison of two data structures,
// ignoring differences that are semantically equivalent in YAML/JSON
func compareData(actual, expected interface{}) bool {
return reflect.DeepEqual(actual, expected)
}

View File

@@ -1,15 +0,0 @@
# Test with blacklisted user agents
User-agent: *
Disallow: /admin
Crawl-delay: 10
User-agent: BadBot
Disallow: /
User-agent: SpamBot
Disallow: /
Crawl-delay: 60
User-agent: Googlebot
Disallow: /search
Crawl-delay: 5

View File

@@ -1,30 +0,0 @@
- action: WEIGH
expression: "true"
name: robots-txt-policy-crawl-delay-1
weight:
adjust: 3
- action: CHALLENGE
expression: path.startsWith("/admin")
name: robots-txt-policy-disallow-2
- action: DENY
expression: userAgent.contains("BadBot")
name: robots-txt-policy-blacklist-3
- action: WEIGH
expression: userAgent.contains("SpamBot")
name: robots-txt-policy-crawl-delay-4
weight:
adjust: 3
- action: DENY
expression: userAgent.contains("SpamBot")
name: robots-txt-policy-blacklist-5
- action: WEIGH
expression: userAgent.contains("Googlebot")
name: robots-txt-policy-crawl-delay-6
weight:
adjust: 3
- action: CHALLENGE
expression:
all:
- userAgent.contains("Googlebot")
- path.startsWith("/search")
name: robots-txt-policy-disallow-7

View File

@@ -1,30 +0,0 @@
# Complex real-world example
User-agent: *
Disallow: /admin/
Disallow: /private/
Disallow: /api/internal/
Allow: /api/public/
Crawl-delay: 5
User-agent: Googlebot
Disallow: /search/
Allow: /api/
Crawl-delay: 2
User-agent: Bingbot
Disallow: /search/
Disallow: /admin/
Crawl-delay: 10
User-agent: BadBot
Disallow: /
User-agent: SeoBot
Disallow: /
Crawl-delay: 300
# Test with various patterns
User-agent: TestBot
Disallow: /*/admin
Disallow: /temp*.html
Disallow: /file?.log

View File

@@ -1,71 +0,0 @@
- action: WEIGH
expression: "true"
name: robots-txt-policy-crawl-delay-1
weight:
adjust: 5
- action: CHALLENGE
expression: path.startsWith("/admin/")
name: robots-txt-policy-disallow-2
- action: CHALLENGE
expression: path.startsWith("/private/")
name: robots-txt-policy-disallow-3
- action: CHALLENGE
expression: path.startsWith("/api/internal/")
name: robots-txt-policy-disallow-4
- action: WEIGH
expression: userAgent.contains("Googlebot")
name: robots-txt-policy-crawl-delay-5
weight:
adjust: 5
- action: CHALLENGE
expression:
all:
- userAgent.contains("Googlebot")
- path.startsWith("/search/")
name: robots-txt-policy-disallow-6
- action: WEIGH
expression: userAgent.contains("Bingbot")
name: robots-txt-policy-crawl-delay-7
weight:
adjust: 5
- action: CHALLENGE
expression:
all:
- userAgent.contains("Bingbot")
- path.startsWith("/search/")
name: robots-txt-policy-disallow-8
- action: CHALLENGE
expression:
all:
- userAgent.contains("Bingbot")
- path.startsWith("/admin/")
name: robots-txt-policy-disallow-9
- action: DENY
expression: userAgent.contains("BadBot")
name: robots-txt-policy-blacklist-10
- action: WEIGH
expression: userAgent.contains("SeoBot")
name: robots-txt-policy-crawl-delay-11
weight:
adjust: 5
- action: DENY
expression: userAgent.contains("SeoBot")
name: robots-txt-policy-blacklist-12
- action: CHALLENGE
expression:
all:
- userAgent.contains("TestBot")
- path.matches("^/.*/admin")
name: robots-txt-policy-disallow-13
- action: CHALLENGE
expression:
all:
- userAgent.contains("TestBot")
- path.matches("^/temp.*\\.html")
name: robots-txt-policy-disallow-14
- action: CHALLENGE
expression:
all:
- userAgent.contains("TestBot")
- path.matches("^/file.\\.log")
name: robots-txt-policy-disallow-15

View File

@@ -1,6 +0,0 @@
- action: CHALLENGE
expression: path.startsWith("/admin/")
name: my-custom-policy-disallow-1
- action: CHALLENGE
expression: path.startsWith("/private")
name: my-custom-policy-disallow-2

View File

@@ -1,6 +0,0 @@
- action: DENY
expression: path.startsWith("/admin/")
name: robots-txt-policy-disallow-1
- action: DENY
expression: path.startsWith("/private")
name: robots-txt-policy-disallow-2

View File

@@ -1,2 +0,0 @@
# Empty robots.txt (comments only)
# No actual rules

View File

@@ -1 +0,0 @@
[]

View File

@@ -1,12 +0,0 @@
[
{
"action": "CHALLENGE",
"expression": "path.startsWith(\"/admin/\")",
"name": "robots-txt-policy-disallow-1"
},
{
"action": "CHALLENGE",
"expression": "path.startsWith(\"/private\")",
"name": "robots-txt-policy-disallow-2"
}
]

View File

@@ -1,5 +0,0 @@
# Simple robots.txt test
User-agent: *
Disallow: /admin/
Disallow: /private
Allow: /public

View File

@@ -1,6 +0,0 @@
- action: CHALLENGE
expression: path.startsWith("/admin/")
name: robots-txt-policy-disallow-1
- action: CHALLENGE
expression: path.startsWith("/private")
name: robots-txt-policy-disallow-2

View File

@@ -1,6 +0,0 @@
# Test wildcard patterns
User-agent: *
Disallow: /search*
Disallow: /*/private
Disallow: /file?.txt
Disallow: /admin/*?action=delete

View File

@@ -1,12 +0,0 @@
- action: CHALLENGE
expression: path.matches("^/search.*")
name: robots-txt-policy-disallow-1
- action: CHALLENGE
expression: path.matches("^/.*/private")
name: robots-txt-policy-disallow-2
- action: CHALLENGE
expression: path.matches("^/file.\\.txt")
name: robots-txt-policy-disallow-3
- action: CHALLENGE
expression: path.matches("^/admin/.*.action=delete")
name: robots-txt-policy-disallow-4

View File

@@ -51,29 +51,6 @@ bots:
# report_as: 4 # lie to the operator
# algorithm: slow # intentionally waste CPU cycles and time
# Requires a subscription to Thoth to use, see
# https://anubis.techaro.lol/docs/admin/thoth#geoip-based-filtering
- name: countries-with-aggressive-scrapers
action: WEIGH
geoip:
countries:
- BR
- CN
weight:
adjust: 10
# Requires a subscription to Thoth to use, see
# https://anubis.techaro.lol/docs/admin/thoth#asn-based-filtering
- name: aggressive-asns-without-functional-abuse-contact
action: WEIGH
asns:
match:
- 13335 # Cloudflare
- 136907 # Huawei Cloud
- 45102 # Alibaba Cloud
weight:
adjust: 10
# Generic catchall rule
- name: generic-browser
user_agent_regex: >-
@@ -84,59 +61,6 @@ bots:
dnsbl: false
# #
# impressum:
# # Displayed at the bottom of every page rendered by Anubis.
# footer: >-
# This website is hosted by Zombocom. If you have any complaints or notes
# about the service, please contact
# <a href="mailto:contact@domainhere.example">contact@domainhere.example</a>
# and we will assist you as soon as possible.
# # The imprint page that will be linked to at the footer of every Anubis page.
# page:
# # The HTML <title> of the page
# title: Imprint and Privacy Policy
# # The HTML contents of the page. The exact contents of this page can
# # and will vary by locale. Please consult with a lawyer if you are not
# # sure what to put here
# body: >-
# <p>Last updated: June 2025</p>
# <h2>Information that is gathered from visitors</h2>
# <p>In common with other websites, log files are stored on the web server saving details such as the visitor's IP address, browser type, referring page and time of visit.</p>
# <p>Cookies may be used to remember visitor preferences when interacting with the website.</p>
# <p>Where registration is required, the visitor's email and a username will be stored on the server.</p>
# <!-- ... -->
# Open Graph passthrough configuration, see here for more information:
# https://anubis.techaro.lol/docs/admin/configuration/open-graph/
openGraph:
# Enables Open Graph passthrough
enabled: false
# Enables the use of the HTTP host in the cache key, this enables
# caching metadata for multiple http hosts at once.
considerHost: false
# How long cached OpenGraph metadata should last in memory
ttl: 24h
# # If set, return these opengraph values instead of looking them up with
# # the target service.
# #
# # Correlates to properties in https://ogp.me/
# override:
# # og:title is required, it is the title of the website
# "og:title": "Techaro Anubis"
# "og:description": >-
# Anubis is a Web AI Firewall Utility that helps you fight the bots
# away so that you can maintain uptime at work!
# "description": >-
# Anubis is a Web AI Firewall Utility that helps you fight the bots
# away so that you can maintain uptime at work!
# By default, send HTTP 200 back to clients that either get issued a challenge
# or a denial. This seems weird, but this is load-bearing due to the fact that
# the most aggressive scraper bots seem to really, really, want an HTTP 200 and
@@ -144,57 +68,3 @@ openGraph:
status_codes:
CHALLENGE: 200
DENY: 200
# The weight thresholds for when to trigger individual challenges. Any
# CHALLENGE will take precedence over this.
#
# A threshold has four configuration options:
#
# - name: the name that is reported down the stack and used for metrics
# - expression: A CEL expression with the request weight in the variable
# weight
# - action: the Anubis action to apply, similar to in a bot policy
# - challenge: which challenge to send to the user, similar to in a bot policy
#
# See https://anubis.techaro.lol/docs/admin/configuration/thresholds for more
# information.
thresholds:
# By default Anubis ships with the following thresholds:
- name: minimal-suspicion # This client is likely fine, its soul is lighter than a feather
expression: weight <= 0 # a feather weighs zero units
action: ALLOW # Allow the traffic through
# For clients that had some weight reduced through custom rules, give them a
# lightweight challenge.
- name: mild-suspicion
expression:
all:
- weight > 0
- weight < 10
action: CHALLENGE
challenge:
# https://anubis.techaro.lol/docs/admin/configuration/challenges/metarefresh
algorithm: metarefresh
difficulty: 1
report_as: 1
# For clients that are browser-like but have either gained points from custom rules or
# report as a standard browser.
- name: moderate-suspicion
expression:
all:
- weight >= 10
- weight < 20
action: CHALLENGE
challenge:
# https://anubis.techaro.lol/docs/admin/configuration/challenges/proof-of-work
algorithm: fast
difficulty: 2 # two leading zeros, very fast for most clients
report_as: 2
# For clients that are browser like and have gained many points from custom rules
- name: extreme-suspicion
expression: weight >= 20
action: CHALLENGE
challenge:
# https://anubis.techaro.lol/docs/admin/configuration/challenges/proof-of-work
algorithm: fast
difficulty: 4
report_as: 4

View File

@@ -2,5 +2,5 @@
# Note: Blocks human-directed/non-training user agents
- name: "ai-robots-txt"
user_agent_regex: >-
AI2Bot|Ai2Bot-Dolma|aiHitBot|Amazonbot|Andibot|anthropic-ai|Applebot|Applebot-Extended|bedrockbot|Brightbot 1.0|Bytespider|CCBot|ChatGPT-User|Claude-SearchBot|Claude-User|Claude-Web|ClaudeBot|cohere-ai|cohere-training-data-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google-CloudVertexBot|Google-Extended|GoogleOther|GoogleOther-Image|GoogleOther-Video|GPTBot|iaskspider/2.0|ICC-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo Bot|meta-externalagent|Meta-ExternalAgent|meta-externalfetcher|Meta-ExternalFetcher|MistralAI-User/1.0|MyCentralAIScraperBot|NovaAct|OAI-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient.com|Perplexity-User|PerplexityBot|PetalBot|PhindBot|Poseidon Research Crawler|QualifiedBot|QuillBot|quillbot.com|SBIntuitionsBot|Scrapy|SemrushBot|SemrushBot-BA|SemrushBot-CT|SemrushBot-OCOB|SemrushBot-SI|SemrushBot-SWA|Sidetrade indexer bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot
AI2Bot|Ai2Bot-Dolma|aiHitBot|Amazonbot|Andibot|anthropic-ai|Applebot|Applebot-Extended|bedrockbot|Brightbot 1.0|Bytespider|CCBot|ChatGPT-User|Claude-SearchBot|Claude-User|Claude-Web|ClaudeBot|cohere-ai|cohere-training-data-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google-CloudVertexBot|Google-Extended|GoogleOther|GoogleOther-Image|GoogleOther-Video|GPTBot|iaskspider/2.0|ICC-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo Bot|meta-externalagent|Meta-ExternalAgent|meta-externalfetcher|Meta-ExternalFetcher|MistralAI-User/1.0|NovaAct|OAI-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient.com|Perplexity-User|PerplexityBot|PetalBot|PhindBot|QualifiedBot|QuillBot|quillbot.com|SBIntuitionsBot|Scrapy|SemrushBot-OCOB|SemrushBot-SWA|Sidetrade indexer bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot
action: DENY

View File

@@ -1,12 +1,13 @@
variable "ALPINE_VERSION" { default = "3.22" }
variable "GITHUB_SHA" { default = "devel" }
group "default" {
targets = [
"ci-runner",
"anubis",
]
}
target "ci-runner" {
target "anubis" {
args = {
ALPINE_VERSION = "3.22"
}
@@ -21,6 +22,6 @@ target "ci-runner" {
]
pull = true
tags = [
"ghcr.io/techarohq/anubis/ci-runner:latest"
"ghcr.io/techarohq/anubis:${GITHUB_SHA}"
]
}

View File

@@ -1,14 +0,0 @@
---
slug: welcome
title: Welcome to the Anubis blog!
authors: [xe]
tags: [intro]
---
Hello, world!
At Techaro, we've been working on making Anubis even better, and in the process we want to share what we've done, how it works, and signal boost cool things the community has done. As things happen, we'll blog about them so that you can learn from our struggles.
More details to come soon!
{/* truncate */}

View File

@@ -1,248 +0,0 @@
---
slug: release/v1.20.0
title: Anubis v1.20.0 is now available!
authors: [xe]
tags: [release]
image: sunburst.webp
---
![](./sunburst.webp)
Hey all!
Today we released [Anubis v1.20.0: Thancred Waters](https://github.com/TecharoHQ/anubis/releases/tag/v1.20.0). This adds a lot of new and exciting features to Anubis, including but not limited to the `WEIGH` action, custom weight thresholds, Imprint/impressum support, and a no-JS challenge. Here's what you need to know so you can protect your websites in new and exciting ways!
{/* truncate */}
## Sponsoring the product
If you rely on Anubis to keep your website safe, please consider sponsoring the project on [GitHub Sponsors](https://github.com/sponsors/Xe) or [Patreon](https://patreon.com/cadey). Funding helps pay hosting bills and offset the time spent on making this project the best it can be. Every little bit helps and when enough money is raised, [I can make Anubis my full-time job](https://github.com/TecharoHQ/anubis/discussions/278).
I am waiting to hear back from NLNet on if Anubis was selected for funding or not. Let's hope it is!
## Deprecation warning: `DEFAULT_DIFFICULTY`
Anubis v1.20.0 is the last version to support the `DEFAULT_DIFFICULTY` flag in the exact way it currently does. In future versions, this will be ineffectual and you should use the [custom threshold system](/docs/admin/configuration/thresholds) instead.
If this becomes an imposition in practice, this will be reverted.
## Chrome won't show "invalid response" after "Success!"
There were a bunch of smaller fixes in Anubis this time around, but the biggest one was finally squashing the ["invalid response" after "Success!" issue](https://github.com/TecharoHQ/anubis/issues/564) that had been plaguing Chrome users. This was a really annoying issue to track down but it was discovered while we were working on better end-to-end / functional testing: [Chrome randomizes the `Accept-Language` header](https://github.com/explainers-by-googlers/reduce-accept-language) so that websites can't do fingerprinting as easily.
When Anubis issues a challenge, it grabs [information that the browser sends to the user](/docs/design/how-anubis-works#challenge-format) to create a challenge string. Anubis doesn't store these challenge strings anywhere, and when a solution is being checked it calculates the challenge string from the request. This means that they'd get a challenge on one end, compute the response for that challenge, and then the server would validate that against a different challenge. This server-side validation would fail, leading to the user seeing "invalid response" after the client reported success.
I suspect this was why Vanadium and Cromite were having sporadic issues as well.
## New Features
The biggest feature in Anubis is the "weight" subsystem. This allows administrators to make custom rules that change the suspicion level of a request without having to take immediate action. As an example, consider the self-hostable git forge [Gitea](https://about.gitea.com/). When you load a page in Gitea, it creates a session cookie that your browser sends with every request. Weight allows you to mark a request that includes a Gitea session token as _less_ suspicious:
```yaml
- name: gitea-session-token
action: WEIGH
expression:
all:
# Check if the request has a Cookie header
- '"Cookie" in headers'
# Check if the request's Cookie header contains the Gitea session token
- headers["Cookie"].contains("i_love_gitea=")
# Remove 5 weight points
weight:
adjust: -5
```
This is different from the past where you could only allow every request with a Gitea session token, meaning that the invention of lying would allow malicious clients to bypass protection.
Weight is added and removed whenever a `WEIGH` rule is encountered. When all rules are processed and the request doesn't match any `ALLOW`, `CHALLENGE`, or `DENY` rules, Anubis uses [weight thresholds](/docs/admin/configuration/thresholds) to figure out how to handle that request. Thresholds are defined in the [policy file](/docs/admin/policies) alongside your bot rules:
```yaml
thresholds:
- name: minimal-suspicion # This client is likely fine, its soul is lighter than a feather
expression: weight <= 0 # a feather weighs zero units
action: ALLOW # Allow the traffic through
# For clients that had some weight reduced through custom rules, give them a
# lightweight challenge.
- name: mild-suspicion
expression:
all:
- weight > 0
- weight < 10
action: CHALLENGE
challenge:
# https://anubis.techaro.lol/docs/admin/configuration/challenges/metarefresh
algorithm: metarefresh
difficulty: 1
report_as: 1
# For clients that are browser-like but have either gained points from custom rules or
# report as a standard browser.
- name: moderate-suspicion
expression:
all:
- weight >= 10
- weight < 20
action: CHALLENGE
challenge:
# https://anubis.techaro.lol/docs/admin/configuration/challenges/proof-of-work
algorithm: fast
difficulty: 2 # two leading zeros, very fast for most clients
report_as: 2
# For clients that are browser like and have gained many points from custom rules
- name: extreme-suspicion
expression: weight >= 20
action: CHALLENGE
challenge:
# https://anubis.techaro.lol/docs/admin/configuration/challenges/proof-of-work
algorithm: fast
difficulty: 4
report_as: 4
```
:::note
If you don't have thresholds defined in your Anubis policy file, Anubis will default to the "legacy" behaviour where browser-like clients get a challenge at the default difficulty.
:::
This lets most clients through if they pass a simple [proof of work challenge](/docs/admin/configuration/challenges/proof-of-work), but any clients that are less suspicious (like ones with a Gitea session token) are given the lightweight [Meta Refresh](/docs/admin/configuration/challenges/metarefresh) challenge instead.
Threshold expressions are like [Bot rule expressions](/docs/admin/configuration/expressions), but there's only one input: the request's weight. If no thresholds match, the request is allowed through.
### Imprint/Impressum Support
European countries like Germany [require an imprint/impressum](https://www.ionos.com/digitalguide/websites/digital-law/a-case-for-thinking-global-germanys-impressum-laws/) to be present in the footer of their website. This allows users to contact someone on the team behind a website in case they run into issues. This also must generally have a separate page where users can view an extended imprint with other information like a privacy policy or a copyright notice.
Anubis v1.20.0 and later [has support for showing imprints](/docs/admin/configuration/impressum). You can configure two kinds of imprints:
1. An imprint that is shown in the footer of every Anubis page.
2. An extended imprint / privacy policy that is shown when users click on the "Imprint" link. For example, [here's the imprint for the website you're looking at right now](https://anubis.techaro.lol/.within.website/x/cmd/anubis/api/imprint).
Imprints are configured in [the policy file](/docs/admin/policies/):
```yaml
impressum:
# Displayed at the bottom of every page rendered by Anubis.
footer: >-
This website is hosted by Zombocom. If you have any complaints or notes
about the service, please contact
<a href="mailto:contact@zombocom.example">contact@zombocom.example</a> and
we will assist you as soon as possible.
# The imprint page that will be linked to at the footer of every Anubis page.
page:
# The HTML <title> of the page
title: Imprint and Privacy Policy
# The HTML contents of the page. The exact contents of this page can
# and will vary by locale. Please consult with a lawyer if you are not
# sure what to put here.
body: >-
<p>Last updated: June 2025</p>
<h2>Information that is gathered from visitors</h2>
<p>In common with other websites, log files are stored on the web server
saving details such as the visitor's IP address, browser type, referring
page and time of visit.</p>
<p>Cookies may be used to remember visitor preferences when interacting
with the website.</p>
<p>Where registration is required, the visitor's email and a username
will be stored on the server.</p>
<!-- ... -->
```
If this is insufficient, please [file an issue](https://github.com/TecharoHQ/anubis/issues/new) with a link to the relevant legislation for your country so that this feature can be amended and improved.
### No-JS Challenge
One of the first issues in Anubis before it was moved to the [TecharoHQ org](https://github.com/TecharoHQ) was a request [to support challenging browsers without using JavaScript](https://github.com/Xe/x/issues/651). This is a pretty challenging thing to do without rethinking how Anubis works from a fundamentally low level, and with v1.20.0, [Anubis finally has support for running without client-side JavaScript](https://github.com/TecharoHQ/anubis/issues/95) thanks to the [Meta Refresh](/docs/admin/configuration/challenges/metarefresh) challenge.
When Anubis decides it needs to send a challenge to your browser, it sends a challenge page. Historically, this challenge page is [an HTML template](https://github.com/TecharoHQ/anubis/blob/main/web/index.templ) that kicks off some JavaScript, reads the challenge information out of the page body, and then solves it as fast as possible in order to let users see the website they want to visit.
In v1.20.0, Anubis has a challenge registry to hold [different client challenge implementations](/docs/category/challenges). This allows us to implement anything we want as long as it can render a page to show a challenge and then check if the result is correct. This is going to be used to implement a WebAssembly-based proof of work option (one that will be way more efficient than the existing browser JS version), but as a proof of concept I implemented a simple challenge using [HTML `<meta refresh>`](https://en.wikipedia.org/wiki/Meta_refresh).
In my testing, this has worked with every browser I have thrown it at (including CLI browsers, the browser embedded in emacs, etc.). The default configuration of Anubis does use the [meta refresh challenge](/docs/admin/configuration/challenges/metarefresh) for [clients with a very low suspicion](/docs/admin/configuration/thresholds), but by default clients will be sent an [easy proof of work challenge](/docs/admin/configuration/challenges/proof-of-work).
If the false positive rate of this challenge turns out to not be very high in practice, the meta refresh challenge will be enabled by default for browsers in future versions of Anubis.
### `robots2policy`
Anubis was created because crawler bots don't respect [`robots.txt` files](https://www.robotstxt.org/). Administrators have been working on refining and crafting their `robots.txt` files for years, and one common comment is that people don't know where to start crafting their own rules.
Anubis now ships with a [`robots2policy` tool](/docs/admin/robots2policy) that lets you convert your `robots.txt` file to an Anubis policy.
```text
robots2policy -input https://github.com/robots.txt
```
:::note
If you installed Anubis from [an OS package](/docs/admin/native-install), you may need to run `anubis-robots2policy` instead of `robots2policy`.
:::
We hope that this will help you get started with Anubis faster. We are working on a version of this that will run in the documentation via WebAssembly.
### Open Graph configuration is being moved to the policy file
Anubis supports reading [Open Graph tags](/docs/admin/configuration/open-graph) from target services and returning them in challenge pages. This makes the right metadata show up when linking services protected by Anubis in chat applications or on social media.
In order to test the migration of all of the configuration to the policy file, Open Graph configuration has been moved to the policy file. For more information, please read [the Open Graph configuration options](/docs/admin/configuration/open-graph#configuration-options).
You can also set default Open Graph tags:
```yaml
openGraph:
enabled: true
ttl: 24h
# If set, return these opengraph values instead of looking them up with
# the target service.
#
# Correlates to properties in https://ogp.me/
override:
# og:title is required, it is the title of the website
"og:title": "Techaro Anubis"
"og:description": >-
Anubis is a Web AI Firewall Utility that helps you fight the bots
away so that you can maintain uptime at work!
"description": >-
Anubis is a Web AI Firewall Utility that helps you fight the bots
away so that you can maintain uptime at work!
```
## Improvements and optimizations
One of the biggest improvements we've made in v1.20.0 is replacing [SHA-256 with xxhash](https://github.com/TecharoHQ/anubis/pull/676). Anubis uses hashes all over the place to help with identifying clients, matching against rules when allowing traffic through, in error messages sent to users, and more. Historically these have been done with [SHA-256](https://en.wikipedia.org/wiki/SHA-2), however this has been having a mild performance impact in real-world use. As a result, we now use [xxhash](https://xxhash.com/) when possible. This makes policy matching 3x faster in some scenarios and reduces memory usage across the board.
Anubis now uses [bart](https://pkg.go.dev/github.com/gaissmai/bart) for doing IP address matching when you specify addresses in a `remote_address` check configuration or when you are matching against [advanced checks](/docs/admin/thoth). This uses the same kind of IP address routing configuration that your OS kernel does, making it very fast to query information about IP addresses. This makes IP address range matches anywhere from 3-14 times faster depending on the number of addresses it needs to match against. For more information and benchmarks, check out [@JasonLovesDoggo](https://github.com/JasonLovesDoggo)'s PR: [perf: replace cidranger with bart for significant performance improvements #675](https://github.com/TecharoHQ/anubis/pull/675).
## What's up next?
v1.21.0 is already shaping up to be a massive improvement as Anubis adds [internationalization](https://en.wikipedia.org/wiki/Internationalization) support, allowing your users to see its messages in the language they're most comfortable with.
So far Anubis supports the following languages:
- English (Simplified and Traditional)
- French
- Portugese (Brazil)
- Spanish
If you want to contribute translations, please [file an issue](https://github.com/TecharoHQ/anubis/issues/new) with your language of choice or submit a pull request to [the `lib/localization/locales` folder](https://github.com/TecharoHQ/anubis/tree/main/lib/localization/locales). We are about to introduce features to the translation stack, so you may want to hold off a hot minute, but we welcome any and all contributions to making Anubis useful to a global audience.
Other things we plan to do:
- Move configuration to the policy file
- Support reloading the policy file at runtime without having to restart Anubis
- Detecting if a client is "brand new"
- A [Valkey](https://valkey.io/)-backed store for sharing information between instances of Anubis
- Augmenting No-JS support in the paid product
- TLS fingerprinting
- Automated testing improvements in CI (FreeBSD CI support, better automated integration/functional testing, etc.)
## Conclusion
I hope that these features let you get the same Anubis power you've come to know and love and increases the things you can do with it! I've been really excited to ship [thresholds](/docs/admin/configuration/thresholds) and the cloud-based services for Anubis.
If you run into any problems, please [file an issue](https://github.com/TecharoHQ/anubis/issues/new). Otherwise, have a good day and get back to making your communities great.

Binary file not shown.

Before

Width:  |  Height:  |  Size: 9.2 KiB

View File

@@ -1,9 +0,0 @@
xe:
name: Xe Iaso
title: CEO @ Techaro
url: https://github.com/Xe
image_url: https://github.com/Xe.png
email: xe@techaro.lol
page: true
socials:
github: Xe

View File

@@ -10,152 +10,16 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [Unreleased]
<!-- This changes the project to: -->
- Add `COOKIE_SECURE` option to set the cookie [Secure flag](https://developer.mozilla.org/en-US/docs/Web/HTTP/Guides/Cookies#block_access_to_your_cookies)
- Sets cookie defaults to use [SameSite: None](https://web.dev/articles/samesite-cookies-explained)
- Determine the `BIND_NETWORK`/`--bind-network` value from the bind address ([#677](https://github.com/TecharoHQ/anubis/issues/677)).
- Implement localization system. Find locale files in lib/localization/locales/.
- Implement a [development container](https://containers.dev/) manifest to make contributions easier.
- Fix dynamic cookie domains functionality ([#731](https://github.com/TecharoHQ/anubis/pull/731))
- Add option for custom cookie prefix ([#732](https://github.com/TecharoHQ/anubis/pull/732))
## v1.20.0: Thancred Waters
The big ticket items are as follows:
- Implement a no-JS challenge method: [`metarefresh`](./admin/configuration/challenges/metarefresh.mdx) ([#95](https://github.com/TecharoHQ/anubis/issues/95))
- Implement request "weight", allowing administrators to customize the behaviour of Anubis based on specific criteria
- Implement GeoIP and ASN based checks via [Thoth](https://anubis.techaro.lol/docs/admin/thoth) ([#206](https://github.com/TecharoHQ/anubis/issues/206))
- Add [custom weight thresholds](./admin/configuration/thresholds.mdx) via CEL ([#688](https://github.com/TecharoHQ/anubis/pull/688))
- Move Open Graph configuration [to the policy file](./admin/configuration/open-graph.mdx)
- Enable support for Open Graph metadata to be returned by default instead of doing lookups against the target
- Add `robots2policy` CLI utility to convert robots.txt files to Anubis challenge policies using CEL expressions ([#409](https://github.com/TecharoHQ/anubis/issues/409))
- Refactor challenge presentation logic to use a challenge registry
- Allow challenge implementations to register HTTP routes
- [Imprint/Impressum support](./admin/configuration/impressum.mdx) ([#362](https://github.com/TecharoHQ/anubis/issues/362))
- Fix "invalid response" after "Success!" in Chromium ([#564](https://github.com/TecharoHQ/anubis/issues/564))
A lot of performance improvements have been made:
- Replace internal SHA256 hashing with xxhash for 4-6x performance improvement in policy evaluation and cache operations
- Optimized the OGTags subsystem with reduced allocations and runtime per request by up to 66%
- Replace cidranger with bart for IP range checking, improving IP matching performance by 3-20x with zero heap
allocations
And some cleanups/refactors were added:
- Fix OpenGraph passthrough ([#717](https://github.com/TecharoHQ/anubis/issues/717))
- Remove the unused `/test-error` endpoint and update the testing endpoint `/make-challenge` to only be enabled in
development
- Add `--xff-strip-private` flag/envvar to toggle skipping X-Forwarded-For private addresses or not
- Bump AI-robots.txt to version 1.37
- Requests can have their weight be adjusted, if a request weighs zero or less than it is allowed through
- Refactor challenge presentation logic to use a challenge registry
- Allow challenge implementations to register HTTP routes
- Implement a no-JS challenge method: [`metarefresh`](./admin/configuration/challenges/metarefresh.mdx) ([#95](https://github.com/TecharoHQ/anubis/issues/95))
- Bump AI-robots.txt to version 1.34
- Make progress bar styling more compatible (UXP, etc)
- Add `--strip-base-prefix` flag/envvar to strip the base prefix from request paths when forwarding to target servers
- Fix an off-by-one in the default threshold config
- Add functionality for HS512 JWT algorithm
- Add support for dynamic cookie domains with the `--cookie-dynamic-domain`/`COOKIE_DYNAMIC_DOMAIN` flag/envvar
Request weight is one of the biggest ticket features in Anubis. This enables Anubis to be much closer to a Web Application Firewall and when combined with custom thresholds allows administrators to have Anubis take advanced reactions. For more information about request weight, see [the request weight section](./admin/policies.mdx#request-weight) of the policy file documentation.
TL;DR when you have one or more WEIGHT rules like this:
```yaml
bots:
- name: gitea-session-token
action: WEIGH
expression:
all:
- '"Cookie" in headers'
- headers["Cookie"].contains("i_love_gitea=")
# Remove 5 weight points
weight:
adjust: -5
```
You can configure custom thresholds like this:
```yaml
thresholds:
- name: minimal-suspicion # This client is likely fine, its soul is lighter than a feather
expression: weight < 0 # a feather weighs zero units
action: ALLOW # Allow the traffic through
# For clients that had some weight reduced through custom rules, give them a
# lightweight challenge.
- name: mild-suspicion
expression:
all:
- weight >= 0
- weight < 10
action: CHALLENGE
challenge:
# https://anubis.techaro.lol/docs/admin/configuration/challenges/metarefresh
algorithm: metarefresh
difficulty: 1
report_as: 1
# For clients that are browser-like but have either gained points from custom
# rules or report as a standard browser.
- name: moderate-suspicion
expression:
all:
- weight >= 10
- weight < 20
action: CHALLENGE
challenge:
# https://anubis.techaro.lol/docs/admin/configuration/challenges/proof-of-work
algorithm: fast
difficulty: 2 # two leading zeros, very fast for most clients
report_as: 2
# For clients that are browser like and have gained many points from custom
# rules
- name: extreme-suspicion
expression: weight >= 20
action: CHALLENGE
challenge:
# https://anubis.techaro.lol/docs/admin/configuration/challenges/proof-of-work
algorithm: fast
difficulty: 4
report_as: 4
```
These thresholds apply when no other `ALLOW`, `DENY`, or `CHALLENGE` rule matches the request. `WEIGHT` rules add and remove request weight as needed:
```yaml
bots:
- name: gitea-session-token
action: WEIGH
expression:
all:
- '"Cookie" in headers'
- headers["Cookie"].contains("i_love_gitea=")
# Remove 5 weight points
weight:
adjust: -5
- name: bot-like-user-agent
action: WEIGH
expression: '"Bot" in userAgent'
# Add 5 weight points
weight:
adjust: 5
```
Of note: the default "generic browser" rule assigns 10 weight points:
```yaml
# Generic catchall rule
- name: generic-browser
user_agent_regex: >-
Mozilla|Opera
action: WEIGH
weight:
adjust: 10
```
Adjust this as you see fit.
## v1.19.1: Jenomis cen Lexentale - Echo 1
@@ -291,6 +155,7 @@ Other changes:
- Moved all CSS inline to the Xess package, changed colors to be CSS variables
- Set or append to `X-Forwarded-For` header unless the remote connects over a loopback address [#328](https://github.com/TecharoHQ/anubis/issues/328)
- Fixed mojeekbot user agent regex
- Added support for running anubis behind a base path (e.g. `/myapp`)
- Reduce Anubis' paranoia with user cookies ([#365](https://github.com/TecharoHQ/anubis/pull/365))
- Added support for Open Graph passthrough while using unix sockets
- The Open Graph subsystem now passes the HTTP `HOST` header through to the origin

View File

@@ -1,70 +0,0 @@
# Imprint / Impressum configuration
Some jurisdictions (such as the European Union and specifically Germany) [must have contact information freely available](https://www.privacycompany.eu/blog/the-imprint-requirement-a-must-have-for-companies-from-outside-germany) on an imprint/impressum page. Anubis supports creating an Anubis-specific imprint page for your organization with the `impressum` block in your bot policy file. For example:
```yaml
impressum:
# Displayed at the bottom of every page rendered by Anubis.
footer: >-
This website is hosted by Techaro. If you have any complaints or notes
about the service, please contact
<a href="mailto:contact@techaro.lol">contact@techaro.lol</a> and we
will assist you as soon as possible.
# The imprint page that will be linked to at the footer of every Anubis page.
page:
# The HTML <title> of the page
title: Imprint and Privacy Policy
# The HTML contents of the page. The exact contents of this page can
# and will vary by locale. Please consult with a lawyer if you are not
# sure what to put here
body: >-
<p>Last updated: June 2025</p>
<h2>Information that is gathered from visitors</h2>
<p>In common with other websites, log files are stored on the web server saving details such as the visitor's IP address, browser type, referring page and time of visit.</p>
<p>Cookies may be used to remember visitor preferences when interacting with the website.</p>
<p>Where registration is required, the visitor's email and a username will be stored on the server.</p>
<!-- ... -->
```
If you are subscribed to and using [advanced classification features](../thoth.mdx), be sure to disclose the following:
```html
<h2>Techaro Anubis</h2>
<p>
This website uses a service called
<a href="https://anubis.techaro.lol">Anubis</a> by
<a href="https://techaro.lol">Techaro</a> to filter malicious traffic. Anubis
requires the use of browser cookies to ensure that web clients are running
conformant software. Anubis also may report the following data to Techaro to
improve service quality:
</p>
<ul>
<li>
IP address (for purposes of matching against geo-location and BGP autonomous
systems numbers), which is stored in-memory and not persisted to disk.
</li>
<li>
Unique browser fingerprints (such as HTTP request fingerprints and
encryption system fingerprints), which may be stored on Techaro's side for a
period of up to one month.
</li>
<li>
HTTP request metadata that may include things such as the User-Agent header
and other identifiers.
</li>
</ul>
<p>
This data is processed and stored for the legitimate interest of combatting
abusive web clients. This data is encrypted at rest as much as possible and is
only decrypted in memory for the purposes of fulfilling requests.
</p>
```

View File

@@ -9,45 +9,12 @@ This page provides detailed information on how to configure [Open Graph tag](htt
## Configuration Options
Open Graph settings are configured in the `openGraph` section of the [Policy File](../policies.mdx).
```yaml
openGraph:
# Enables Open Graph passthrough
enabled: true
# Enables the use of the HTTP host in the cache key, this enables
# caching metadata for multiple http hosts at once.
considerHost: true
# How long cached OpenGraph metadata should last in memory
ttl: 24h
# If set, return these opengraph values instead of looking them up with
# the target service.
#
# Correlates to properties in https://ogp.me/
override:
# og:title is required, it is the title of the website
"og:title": "Techaro Anubis"
"og:description": >-
Anubis is a Web AI Firewall Utility that helps you fight the bots
away so that you can maintain uptime at work!
"description": >-
Anubis is a Web AI Firewall Utility that helps you fight the bots
away so that you can maintain uptime at work!
```
<details>
<summary>Configuration flags / envvars (old)</summary>
Open Graph passthrough used to be configured with configuration flags / environment variables. Reference to these settings are maintained for backwards compatibility's sake.
| Name | Description | Type | Default | Example |
| ------------------------ | --------------------------------------------------------- | -------- | ------- | ----------------------------- |
| `OG_PASSTHROUGH` | Enables or disables the Open Graph tag passthrough system | Boolean | `true` | `OG_PASSTHROUGH=true` |
| `OG_EXPIRY_TIME` | Configurable cache expiration time for Open Graph tags | Duration | `24h` | `OG_EXPIRY_TIME=1h` |
| `OG_CACHE_CONSIDER_HOST` | Enables or disables the use of the host in the cache key | Boolean | `false` | `OG_CACHE_CONSIDER_HOST=true` |
</details>
## Usage
To configure Open Graph tags, you can set the following environment variables, environment file or as flags in your Anubis configuration:

View File

@@ -1,140 +0,0 @@
# Weight Threshold Configuration
Anubis offers the ability to assign "weight" to requests. This is a custom level of suspicion that rules can add to or remove from. For example, here's how you assign 10 weight points to anything that might be a browser:
```yaml
# botPolicies.yaml
bots:
- name: generic-browser
user_agent_regex: >-
Mozilla|Opera
action: WEIGH
weight:
adjust: 10
```
Thresholds let you take this per-request weight value and take actions in response to it. Thresholds are defined alongside your bot configuration in `botPolicies.yaml`.
:::note
Thresholds DO NOT apply when a request matches a bot rule with the CHALLENGE action. Thresholds only apply when requests don't match any terminal bot rules.
:::
```yaml
# botPolicies.yaml
bots: ...
thresholds:
- name: minimal-suspicion
expression: weight < 0
action: ALLOW
- name: mild-suspicion
expression:
all:
- weight >= 0
- weight < 10
action: CHALLENGE
challenge:
algorithm: metarefresh
difficulty: 1
report_as: 1
- name: moderate-suspicion
expression:
all:
- weight >= 10
- weight < 20
action: CHALLENGE
challenge:
algorithm: fast
difficulty: 2
report_as: 2
- name: extreme-suspicion
expression: weight >= 20
action: CHALLENGE
challenge:
algorithm: fast
difficulty: 4
report_as: 4
```
This defines a suite of 4 thresholds:
1. If the request weight is less than zero, allow it through.
2. If the request weight is greater than or equal to zero, but less than ten: give it [a very lightweight challenge](./challenges/metarefresh.mdx).
3. If the request weight is greater than or equal to ten, but less than twenty: give it [a slightly heavier challenge](./challenges/proof-of-work.mdx).
4. Otherwise, give it [the heaviest challenge](./challenges/proof-of-work.mdx).
Thresholds can be configured with the following options:
<table>
<thead>
<tr>
<th>Name</th>
<th>Description</th>
<th>Example</th>
</tr>
</thead>
<tbody>
<tr>
<td>`name`</td>
<td>The human-readable name for this threshold.</td>
<td>
```yaml
name: extreme-suspicion
```
</td>
</tr>
<tr>
<td>`expression`</td>
<td>A [CEL](https://cel.dev/) expression taking the request weight and returning true or false</td>
<td>
To check if the request weight is less than zero:
```yaml
expression: weight < 0
```
To check if it's between 0 and 10 (inclusive):
```yaml
expression:
all:
- weight >= 0
- weight < 10
```
</td>
</tr>
<tr>
<td>`action`</td>
<td>The Anubis action to apply: `ALLOW`, `CHALLENGE`, or `DENY`</td>
<td>
```yaml
action: ALLOW
```
If you set the CHALLENGE action, you must set challenge details:
```yaml
action: CHALLENGE
challenge:
algorithm: metarefresh
difficulty: 1
report_as: 1
```
</td>
</tr>
</tbody>
</table>

View File

@@ -34,6 +34,27 @@ These examples assume that you are using a setup where your nginx configuration
:::
## Dependencies
Install the following dependencies for proxying HTTP:
<Tabs>
<TabItem value="rpm" label="Red Hat / RPM" default>
```text
dnf -y install mod_proxy_html
```
</TabItem>
<TabItem value="deb" label="Debian / Ubuntu / apt">
```text
apt-get install -y libapache2-mod-proxy-html libxml2-dev
```
</TabItem>
</Tabs>
## Configuration
Assuming you are protecting `anubistest.techaro.lol`, you need the following server configuration blocks:

View File

@@ -4,6 +4,9 @@ title: Setting up Anubis
import RandomKey from "@site/src/components/RandomKey";
import Tabs from "@theme/Tabs";
import TabItem from "@theme/TabItem";
Anubis is meant to sit between your reverse proxy (such as Nginx or Caddy) and your target service. One instance of Anubis must be used per service you are protecting.
<center>
@@ -42,19 +45,7 @@ Anubis has very minimal system requirements. I suspect that 128Mi of ram may be
For more detailed information on installing Anubis with native packages, please read [the native install directions](./native-install.mdx).
## Configuration
Anubis is configurable via environment variables and [the policy file](./policies.mdx). Most settings are currently exposed with environment variables but they are being slowly moved over to the policy file.
### Configuration via the policy file
Currently the following settings are configurable via the policy file:
- [Bot policies](./policies.mdx)
- [Open Graph passthrough](./configuration/open-graph.mdx)
- [Weight thresholds](./configuration/thresholds.mdx)
### Environment variables
## Environment variables
Anubis uses these environment variables for configuration:
@@ -64,23 +55,20 @@ Anubis uses these environment variables for configuration:
| `BIND` | `:8923` | The network address that Anubis listens on. For `unix`, set this to a path: `/run/anubis/instance.sock` |
| `BIND_NETWORK` | `tcp` | The address family that Anubis listens on. Accepts `tcp`, `unix` and anything Go's [`net.Listen`](https://pkg.go.dev/net#Listen) supports. |
| `COOKIE_DOMAIN` | unset | The domain the Anubis challenge pass cookie should be set to. This should be set to the domain you bought from your registrar (EG: `techaro.lol` if your webapp is running on `anubis.techaro.lol`). See this [stackoverflow explanation of cookies](https://stackoverflow.com/a/1063760) for more information.<br/><br/>Note that unlike `REDIRECT_DOMAINS`, you should never include a port number in this variable. |
| `COOKIE_DYNAMIC_DOMAIN` | false | If set to true, automatically set cookie domain fields based on the hostname of the request. EG: if you are making a request to `anubis.techaro.lol`, the Anubis cookie will be valid for any subdomain of `techaro.lol`. |
| `COOKIE_EXPIRATION_TIME` | `168h` | The amount of time the authorization cookie is valid for. |
| `COOKIE_PARTITIONED` | `false` | If set to `true`, enables the [partitioned (CHIPS) flag](https://developers.google.com/privacy-sandbox/cookies/chips), meaning that Anubis inside an iframe has a different set of cookies than the domain hosting the iframe. |
| `COOKIE_SECURE` | `true` | If set to `true`, enables the [Secure flag](https://developer.mozilla.org/en-US/docs/Web/HTTP/Guides/Cookies#block_access_to_your_cookies), meaning that the cookies will only be transmitted over HTTPS. If Anubis is used in an unsecure context (plain HTTP), this will be need to be set to false |
| `DIFFICULTY` | `4` | The difficulty of the challenge, or the number of leading zeroes that must be in successful responses. |
| `ED25519_PRIVATE_KEY_HEX` | unset | The hex-encoded ed25519 private key used to sign Anubis responses. If this is not set, Anubis will generate one for you. This should be exactly 64 characters long. See below for details. |
| `ED25519_PRIVATE_KEY_HEX_FILE` | unset | Path to a file containing the hex-encoded ed25519 private key. Only one of this or its sister option may be set. |
| `METRICS_BIND` | `:9090` | The network address that Anubis serves Prometheus metrics on. See `BIND` for more information. |
| `METRICS_BIND_NETWORK` | `tcp` | The address family that the Anubis metrics server listens on. See `BIND_NETWORK` for more information. |
| `OG_EXPIRY_TIME` | `24h` | The expiration time for the Open Graph tag cache. Prefer using [the policy file](./configuration/open-graph.mdx) to configure the Open Graph subsystem. |
| `OG_PASSTHROUGH` | `false` | If set to `true`, Anubis will enable Open Graph tag passthrough. Prefer using [the policy file](./configuration/open-graph.mdx) to configure the Open Graph subsystem. |
| `OG_CACHE_CONSIDER_HOST` | `false` | If set to `true`, Anubis will consider the host in the Open Graph tag cache key. Prefer using [the policy file](./configuration/open-graph.mdx) to configure the Open Graph subsystem. |
| `OG_EXPIRY_TIME` | `24h` | The expiration time for the Open Graph tag cache. |
| `OG_PASSTHROUGH` | `false` | If set to `true`, Anubis will enable Open Graph tag passthrough. |
| `OG_CACHE_CONSIDER_HOST` | `false` | If set to `true`, Anubis will consider the host in the Open Graph tag cache key. |
| `POLICY_FNAME` | unset | The file containing [bot policy configuration](./policies.mdx). See the bot policy documentation for more details. If unset, the default bot policy configuration is used. |
| `REDIRECT_DOMAINS` | unset | If set, restrict the domains that Anubis can redirect to when passing a challenge.<br/><br/>If this is unset, Anubis may redirect to any domain which could cause security issues in the unlikely case that an attacker passes a challenge for your browser and then tricks you into clicking a link to your domain.<br/><br/>Note that if you are hosting Anubis on a non-standard port (`https://example:com:8443`, `http://www.example.net:8080`, etc.), you must also include the port number here. |
| `SERVE_ROBOTS_TXT` | `false` | If set `true`, Anubis will serve a default `robots.txt` file that disallows all known AI scrapers by name and then additionally disallows every scraper. This is useful if facts and circumstances make it difficult to change the underlying service to serve such a `robots.txt` file. |
| `SOCKET_MODE` | `0770` | _Only used when at least one of the `*_BIND_NETWORK` variables are set to `unix`._ The socket mode (permissions) for Unix domain sockets. |
| `STRIP_BASE_PREFIX` | `false` | If set to `true`, strips the base prefix from request paths when forwarding to the target server. This is useful when your target service expects to receive requests without the base prefix. For example, with `BASE_PREFIX=/foo` and `STRIP_BASE_PREFIX=true`, a request to `/foo/bar` would be forwarded to the target as `/bar`. |
| `TARGET` | `http://localhost:3923` | The URL of the service that Anubis should forward valid requests to. Supports Unix domain sockets, set this to a URI like so: `unix:///path/to/socket.sock`. |
| `USE_REMOTE_ADDRESS` | unset | If set to `true`, Anubis will take the client's IP from the network socket. For production deployments, it is expected that a reverse proxy is used in front of Anubis, which pass the IP using headers, instead. |
| `WEBMASTER_EMAIL` | unset | If set, shows a contact email address when rendering error pages. This email address will be how users can get in contact with administrators. |
@@ -95,12 +83,11 @@ If you don't know or understand what these settings mean, ignore them. These are
:::
| Environment Variable | Default value | Explanation |
| :---------------------------- | :------------ | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `TARGET_SNI` | unset | If set, overrides the TLS handshake hostname in requests forwarded to `TARGET`. |
| `TARGET_HOST` | unset | If set, overrides the Host header in requests forwarded to `TARGET`. |
| `TARGET_INSECURE_SKIP_VERIFY` | `false` | If `true`, skip TLS certificate validation for targets that listen over `https`. If your backend does not listen over `https`, ignore this setting. |
| `HS512_SECRET` | unset | Secret string for JWT HS512 algorithm. If this is not set, Anubis will use ED25519 as defined via the variables above. The longer the better; 128 chars should suffice. |
| Environment Variable | Default value | Explanation |
| :---------------------------- | :------------ | :-------------------------------------------------------------------------------------------------------------------------------------------------- |
| `TARGET_SNI` | unset | If set, overrides the TLS handshake hostname in requests forwarded to `TARGET`. |
| `TARGET_HOST` | unset | If set, overrides the Host header in requests forwarded to `TARGET`. |
| `TARGET_INSECURE_SKIP_VERIFY` | `false` | If `true`, skip TLS certificate validation for targets that listen over `https`. If your backend does not listen over `https`, ignore this setting. |
</details>
@@ -142,22 +129,6 @@ With corresponding Anubis configuration:
BASE_PREFIX=/myapp
```
#### Stripping Base Prefix
If your target service doesn't expect to receive the base prefix in request paths, you can use the `STRIP_BASE_PREFIX` option:
```
BASE_PREFIX=/myapp
STRIP_BASE_PREFIX=true
```
With this configuration:
- A request to `/myapp/api/users` would be forwarded to your target service as `/api/users`
- A request to `/myapp/` would be forwarded as `/`
This is particularly useful when working with applications that weren't designed to handle path prefixes. However, note that if your target application generates absolute redirects or links (like `/login` instead of `./login`), these may break the subpath routing since they won't include the base prefix.
### Key generation
To generate an ed25519 private key, you can use this command:

View File

@@ -233,10 +233,6 @@ remote_addresses:
</TabItem>
</Tabs>
## Imprint / Impressum support
Anubis has support for showing imprint / impressum information. This is defined in the `impressum` block of your configuration. See [Imprint / Impressum configuration](./configuration/impressum.mdx) for more information.
## Risk calculation for downstream services
In case your service needs it for risk calculation reasons, Anubis exposes information about the rules that any requests match using a few headers:
@@ -265,11 +261,17 @@ Anubis rules can also add or remove "weight" from requests, allowing administrat
adjust: -5
```
This would remove five weight points from the request, which would make Anubis present the [Meta Refresh challenge](./configuration/challenges/metarefresh.mdx) in the default configuration.
This would remove five weight points from the request, making Anubis present the [Meta Refresh challenge](./configuration/challenges/metarefresh.mdx).
### Weight Thresholds
For more information on configuring weight thresholds, see [Weight Threshold Configuration](./configuration/thresholds.mdx)
Weight thresholds and challenge associations will be configurable with CEL expressions in the configuration file in an upcoming patch, for now here's how Anubis configures the weight thresholds:
| Weight Expression | Action |
| -----------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------- |
| `weight < 0` (weight is less than 0) | Allow the request through. |
| `weight < 10` (weight is less than 10) | Challenge the client with the [Meta Refresh challenge](./configuration/challenges/metarefresh.mdx) at the default difficulty level. |
| `weight >= 10` (weight is greater than or equal to 10) | Challenge the client with the [Proof of Work challenge](./configuration/challenges/proof-of-work.mdx) at the default difficulty level. |
### Advice

View File

@@ -1,84 +0,0 @@
---
title: robots2policy CLI Tool
sidebar_position: 50
---
The `robots2policy` tool converts robots.txt files into Anubis challenge policies. It reads robots.txt rules and generates equivalent CEL expressions for path matching and user-agent filtering.
## Installation
Install directly with Go:
```bash
go install github.com/TecharoHQ/anubis/cmd/robots2policy@latest
```
## Usage
Basic conversion from URL:
```bash
robots2policy -input https://www.example.com/robots.txt
```
Convert local file to YAML:
```bash
robots2policy -input robots.txt -output policy.yaml
```
Convert with custom settings:
```bash
robots2policy -input robots.txt -action DENY -format json
```
## Options
| Flag | Description | Default |
|-----------------------|--------------------------------------------------------------------|---------------------|
| `-input` | robots.txt file path or URL (use `-` for stdin) | *required* |
| `-output` | Output file (use `-` for stdout) | stdout |
| `-format` | Output format: `yaml` or `json` | `yaml` |
| `-action` | Action for disallowed paths: `ALLOW`, `DENY`, `CHALLENGE`, `WEIGH` | `CHALLENGE` |
| `-name` | Policy name prefix | `robots-txt-policy` |
| `-crawl-delay-weight` | Weight adjustment for crawl-delay rules | `3` |
| `-deny-user-agents` | Action for blacklisted user agents | `DENY` |
## Example
Input robots.txt:
```txt
User-agent: *
Disallow: /admin/
Disallow: /private
User-agent: BadBot
Disallow: /
```
Generated policy:
```yaml
- name: robots-txt-policy-disallow-1
action: CHALLENGE
expression:
single: path.startsWith("/admin/")
- name: robots-txt-policy-disallow-2
action: CHALLENGE
expression:
single: path.startsWith("/private")
- name: robots-txt-policy-blacklist-3
action: DENY
expression:
single: userAgent.contains("BadBot")
```
## Using the Generated Policy
Save the output and import it in your main policy file:
```yaml
import:
- path: "./robots-policy.yaml"
```
The tool handles wildcard patterns, user-agent specific rules, and blacklisted bots automatically.

View File

@@ -1,81 +0,0 @@
# Thoth-based advanced checks
Status: Beta
Anubis instances are normally isolated. Each Anubis instance has its own configuration and exists in roughly its own world without any long term memory between requests. As threats, workarounds, and AI scraper toolchains evolve, administrators will need a way to get more up to date information faster than Anubis' release cycle.
Thus, Thoth is being created. Thoth is the reputation database for Anubis. Thoth feeds information to Anubis so that it can make better decisions about which traffic is innocuous and which traffic is suspicious.
:::note
Thoth is hosted by [Techaro](https://techaro.lol). Thoth is a paid service. Thoth is opt-in and requires manual intervention (including payment) to use. The code that powers Thoth is currently closed source.
To get access to Thoth, please subscribe [on GitHub Sponsors](https://github.com/sponsors/Xe) and [email Xe](mailto:xe@techaro.lol). This will be self-service soon.
:::
## Implementation
Thoth is a web service that listens over [gRPC](https://grpc.io/). Thoth's API is documented in protocol buffer definitions in the GitHub repo [TecharoHQ/thoth-proto](https://github.com/TecharoHQ/thoth-proto).
Thoth is designed to be _informative_, not _authoritative_. Thoth cannot and will not arbitrarily block requests, origins, or other traffic. Thoth is there to inform Anubis and influence the weight of requests so that upstream resources can be protected. Additionally, Anubis aggressively caches data from Thoth such that over time Anubis will not need to request data very often. This makes the fast path for repeat visitors even faster and reduces the amount of data that Thoth is exposed to.
## Thoth features
Thoth is currently in active development. Currently, Thoth provides the following features to Anubis:
- BGP Autonomous System (ASN) based filtering
- GeoIP location based filtering
### ASN-based filtering
When companies link their backbone infrastructure to the Internet, they do so via a [BGP Autonomous System](<https://en.wikipedia.org/wiki/Autonomous_system_(Internet)>), denoted by a number (the Autonomous System Number or ASN). Every IP address on the Internet is owned by an ASN with a 1:1 lookup that does not change very frequently.
Anubis uses Thoth to match IP addresses to BGP Autonomous Systems so that you can either issue arbitrary challenges to individual internet service providers (such as Cloudflare or Huawei Cloud) or, at the administrator's explicit instruction, block them altogether. For example, here's how you add 10 weight points to requests from Cloudflare, Huawei Cloud, and Alibaba Cloud:
```yaml
- name: aggressive-asns-without-functional-abuse-contact
action: WEIGH
asns:
match:
- 13335 # Cloudflare
- 136907 # Huawei Cloud
- 45102 # Alibaba Cloud
weight:
adjust: 10
```
You can look up details for [AS13335](https://bgp.tools/as/13335) or any of these other top offenders on [bgp.tools](https://bgp.tools).
### GeoIP-based filtering
In extreme cases, an administrator may have to take action against an entire country. This is not an ideal circumstance, but sometimes reality forces their hands and the administrators just want to sleep at night.
Anubis uses Thoth to look up the geographic location registered to an IP address. This lookup is not the best and will get better with time, but you ship what you can so you can make it better for next time.
For example, to add 10 weight points to requests from Brazil and China:
```yaml
- name: countries-with-aggressive-scrapers
action: WEIGH
geoip:
countries:
- BR
- CN
weight:
adjust: 10
```
Use this with care.
## Work-in-progress features
This section is a bit aspirational and is where Thoth will end up rather than things you can use today.
In general, a lot of Thoth features are focused on taking the same Anubis you know and love and making it better, smarter, and less paranoid. These include:
- Private rulesets for advanced patterns, current known exploits, and other recognition tactics that need to be kept cloak and dagger for operational security reasons
- Private challenge implementations via WebAssembly, including advanced browser detection logic
- Reputation querying so that Thoth can arbitrarily influence the weight of requests based on the net aggregate pass rate so that the most common browsers can get through with no challenge issued at all
- APIs for trusted administrators to report abusive request fingerprints so that Anubis can react to threats as they evolve
- A way for Anubis to periodically report the pass rate per ASN and other fingerprints so that methodology can be improved

View File

@@ -107,6 +107,7 @@ This ensures that the token has enough metadata to prove that the token is valid
Challenges are formed by taking some user request metadata and using that to generate a SHA-256 checksum. The following request headers are used:
- `Accept-Encoding`: The content encodings that the requestor supports, such as gzip.
- `Accept-Language`: The language that the requestor would prefer the server respond in, such as English.
- `X-Real-Ip`: The IP address of the requestor, as set by a reverse proxy server.
- `User-Agent`: The user agent string of the requestor.
- The current time in UTC rounded to the nearest week.

View File

@@ -58,9 +58,7 @@ This will build all static assets (CSS, JavaScript) for distribution.
make build
```
From this point it is up to you to make sure that `./var/anubis` and `./var/robots2policy` end up in
the right place. You may want to consult the `./run` folder for useful files such as a systemd unit
and `anubis.env.default` file.
From this point it is up to you to make sure that `./var/anubis` ends up in the right place. You may want to consult the `./run` folder for useful files such as a systemd unit and `anubis.env.default` file.
## "Pre-baked" tarball
@@ -77,7 +75,7 @@ When using this tarball, all you need to do is build `./cmd/anubis`:
make prebaked-build
```
Anubis will be built to `./var/anubis` and the robots2policy tool to `./var/robots2policy`.
Anubis will be built to `./var/anubis`.
## Development dependencies

View File

@@ -2,10 +2,6 @@
title: Local development
---
If you use an editor with [Development containers](https://containers.dev) support, load this repo's [devcontainer configuration](https://github.com/TecharoHQ/anubis/tree/main/.devcontainer). Skip to [Running Anubis locally](#running-anubis-locally) if you are using the devcontainer.
This enables you to contribute from [GitHub Codespaces](https://github.com/features/codespaces) or other web-based editors.
:::note
TL;DR: `npm ci && npm run dev`

View File

@@ -14,7 +14,6 @@ title: Anubis
![GitHub go.mod Go version](https://img.shields.io/github/go-mod/go-version/TecharoHQ/anubis)
![language count](https://img.shields.io/github/languages/count/TecharoHQ/anubis)
![repo size](https://img.shields.io/github/repo-size/TecharoHQ/anubis)
[![GitHub Sponsors](https://img.shields.io/github/sponsors/Xe)](https://github.com/sponsors/Xe)
## Sponsors

View File

@@ -41,24 +41,13 @@ This page contains a non-exhaustive list with all websites using Anubis.
- https://minihoot.site
- https://catgirl.click/
- https://wiki.dolphin-emu.org/
- https://squirreljme.cc/
- https://gitlab.postmarketos.org/
- https://wiki.koha-community.org/
- https://extensions.typo3.org/
- <details>
<summary>FreeCAD</summary>
- https://forum.freecad.org/
- https://wiki.freecad.org/
</details>
- <details>
<summary>ReactOS</summary>
- https://reactos.org/forum
- https://reactos.org/wiki
- https://git.reactos.org
</details>
- <details>
<summary>ScummVM</summary>
- https://bugs.scummvm.org/
- https://forums.scummvm.org/
- https://wiki.scummvm.org/
</details>

View File

@@ -47,21 +47,21 @@ const config: Config = {
editUrl:
'https://github.com/TecharoHQ/anubis/tree/main/docs/',
},
blog: {
showReadingTime: true,
feedOptions: {
type: ['rss', 'atom', "json"],
xslt: true,
},
// Please change this to your repo.
// Remove this to remove the "edit this page" links.
editUrl:
'https://github.com/facebook/docusaurus/tree/main/packages/create-docusaurus/templates/shared/',
// Useful options to enforce blogging best practices
onInlineTags: 'warn',
onInlineAuthors: 'warn',
onUntruncatedBlogPosts: 'warn',
},
// blog: {
// showReadingTime: true,
// feedOptions: {
// type: ['rss', 'atom', "json"],
// xslt: true,
// },
// // Please change this to your repo.
// // Remove this to remove the "edit this page" links.
// editUrl:
// 'https://github.com/facebook/docusaurus/tree/main/packages/create-docusaurus/templates/shared/',
// // Useful options to enforce blogging best practices
// onInlineTags: 'warn',
// onInlineAuthors: 'warn',
// onUntruncatedBlogPosts: 'warn',
// },
theme: {
customCss: './src/css/custom.css',
},
@@ -86,14 +86,9 @@ const config: Config = {
type: 'docSidebar',
sidebarId: 'tutorialSidebar',
position: 'left',
label: 'Docs',
},
{ to: '/blog', label: 'Blog', position: 'left' },
{
href: 'https://github.com/sponsors/Xe',
label: "Sponsorship",
position: 'left'
label: 'Tutorial',
},
// { to: '/blog', label: 'Blog', position: 'left' },
{
href: 'https://github.com/TecharoHQ/anubis',
label: 'GitHub',
@@ -133,10 +128,6 @@ const config: Config = {
{
title: 'More',
items: [
{
label: 'Blog',
to: '/blog',
},
{
label: 'GitHub',
href: 'https://github.com/TecharoHQ/anubis',

View File

@@ -1,6 +0,0 @@
apiVersion: onepassword.com/v1
kind: OnePasswordItem
metadata:
name: anubis-docs-thoth
spec:
itemPath: "vaults/lc5zo4zjz3if3mkeuhufjmgmui/items/pwguumqcmtxvqbeb7y4gj7l36i"

View File

@@ -51,13 +51,6 @@ bots:
# report_as: 4 # lie to the operator
# algorithm: slow # intentionally waste CPU cycles and time
- name: rss-feed-blog
action: ALLOW
expression:
any:
- path.startsWith("/blog/atom.")
- path.startsWith("/blog/rss.")
# Generic catchall rule
- name: generic-browser
user_agent_regex: >-
@@ -70,55 +63,6 @@ bots:
dnsbl: false
impressum:
footer: |
This website is hosted by Techaro. If you have any complaints or notes about the service, please contact <a href="mailto:contact@techaro.lol">contact@techaro.lol</a> and we will assist you as soon as possible.
page:
title: Privacy Policy
body: |
<p>Last updated: June 2025</p>
<h2>Information that is gathered from visitors</h2>
<p>In common with other websites, log files are stored on the web server saving details such as the visitor's IP address, browser type, referring page and time of visit.</p>
<p>Cookies may be used to remember visitor preferences when interacting with the website.</p>
<p>Where registration is required, the visitor's email and a username will be stored on the server.</p>
<h2>How the Information is used</h2>
<p>The information is used to enhance the vistor's experience when using the website to display personalised content and possibly advertising.</p>
<p>E-mail addresses will not be sold, rented or leased to 3rd parties.</p>
<p>E-mail may be sent to inform you of news of our services or offers by us or our affiliates.</p>
<h2>Visitor Options</h2>
<p>If you have subscribed to one of our services, you may unsubscribe by following the instructions which are included in e-mail that you receive.</p>
<p>You may be able to block cookies via your browser settings but this may prevent you from access to certain features of the website.</p>
<h2>Cookies</h2>
<p>Cookies are small digital signature files that are stored by your web browser that allow your preferences to be recorded when visiting the website. Also they may be used to track your return visits to the website.</p>
<p>3rd party advertising companies may also use cookies for tracking purposes.</p>
<h2>Techaro Anubis</h2>
<p>This website uses a service called <a href="https://anubis.techaro.lol">Anubis</a> to filter malicious traffic. Anubis requires the use of browser cookies to ensure that web clients are running conformant software. Anubis also may report the following data to Techaro to improve service quality:</p>
<ul>
<li>IP address (for purposes of matching against geo-location and BGP autonomous systems numbers), which is stored in-memory and not persisted to disk.</li>
<li>Unique browser fingerprints (such as HTTP request fingerprints and encryption system fingerprints), which may be stored on Techaro's side for a period of up to one month.</li>
<li>HTTP request metadata that may include things such as the User-Agent header and other identifiers.</li>
</ul>
<p>This data is processed and stored for the legitimate interest of combatting abusive web clients. This data is encrypted at rest as much as possible and is only decrypted in memory for the purposes of fulfilling requests.</p>
# By default, send HTTP 200 back to clients that either get issued a challenge
# or a denial. This seems weird, but this is load-bearing due to the fact that
# the most aggressive scraper bots seem to really, really, want an HTTP 200 and

View File

@@ -38,8 +38,6 @@ spec:
value: "4"
- name: "METRICS_BIND"
value: ":9090"
- name: "OG_PASSTHROUGH"
value: "true"
- name: "POLICY_FNAME"
value: "/xe/cfg/anubis/botPolicies.yaml"
- name: "SERVE_ROBOTS_TXT"
@@ -68,6 +66,3 @@ spec:
- ALL
seccompProfile:
type: RuntimeDefault
envFrom:
- secretRef:
name: anubis-docs-thoth

View File

@@ -1,9 +1,7 @@
resources:
- 1password.yaml
- deployment.yaml
- ingress.yaml
- onionservice.yaml
- poddisruptionbudget.yaml
- service.yaml
configMapGenerator:

View File

@@ -1,9 +0,0 @@
apiVersion: policy/v1
kind: PodDisruptionBudget
metadata:
name: anubis-docs
spec:
minAvailable: 1
selector:
matchLabels:
app: anubis-docs

3083
docs/package-lock.json generated

File diff suppressed because it is too large Load Diff

View File

@@ -15,9 +15,9 @@
"typecheck": "tsc"
},
"dependencies": {
"@docusaurus/core": "^3.8.1",
"@docusaurus/preset-classic": "^3.8.1",
"@docusaurus/theme-mermaid": "^3.8.1",
"@docusaurus/core": "3.7.0",
"@docusaurus/preset-classic": "3.7.0",
"@docusaurus/theme-mermaid": "^3.7.0",
"@mdx-js/react": "^3.0.0",
"clsx": "^2.0.0",
"prism-react-renderer": "^2.3.0",
@@ -25,9 +25,9 @@
"react-dom": "^19.0.0"
},
"devDependencies": {
"@docusaurus/module-type-aliases": "^3.8.1",
"@docusaurus/tsconfig": "^3.8.1",
"@docusaurus/types": "^3.8.1",
"@docusaurus/module-type-aliases": "3.7.0",
"@docusaurus/tsconfig": "3.7.0",
"@docusaurus/types": "3.7.0",
"typescript": "~5.6.2"
},
"browserslist": {
@@ -45,4 +45,4 @@
"engines": {
"node": ">=18.0"
}
}
}

Binary file not shown.

Before

Width:  |  Height:  |  Size: 476 B

After

Width:  |  Height:  |  Size: 2.1 KiB

55
go.mod
View File

@@ -3,35 +3,24 @@ module github.com/TecharoHQ/anubis
go 1.24.2
require (
github.com/TecharoHQ/thoth-proto v0.4.0
github.com/a-h/templ v0.3.906
github.com/cespare/xxhash/v2 v2.3.0
github.com/a-h/templ v0.3.898
github.com/facebookgo/flagenv v0.0.0-20160425205200-fcd59fca7456
github.com/gaissmai/bart v0.20.4
github.com/golang-jwt/jwt/v5 v5.2.2
github.com/google/cel-go v0.25.0
github.com/grpc-ecosystem/go-grpc-middleware/providers/prometheus v1.1.0
github.com/grpc-ecosystem/go-grpc-middleware/v2 v2.3.2
github.com/joho/godotenv v1.5.1
github.com/nicksnyder/go-i18n/v2 v2.6.0
github.com/playwright-community/playwright-go v0.5200.0
github.com/prometheus/client_golang v1.22.0
github.com/sebest/xff v0.0.0-20210106013422-671bd2870b3a
github.com/yl2chen/cidranger v1.0.2
golang.org/x/net v0.41.0
golang.org/x/text v0.26.0
google.golang.org/grpc v1.73.0
gopkg.in/yaml.v3 v3.0.1
k8s.io/apimachinery v0.33.2
sigs.k8s.io/yaml v1.5.0
k8s.io/apimachinery v0.33.1
)
require (
al.essio.dev/pkg/shellescape v1.6.0 // indirect
buf.build/gen/go/bufbuild/protovalidate/protocolbuffers/go v1.36.6-20250425153114-8976f5be98c1.1 // indirect
cel.dev/expr v0.23.1 // indirect
dario.cat/mergo v1.0.2 // indirect
github.com/AlekSi/pointer v1.2.0 // indirect
github.com/BurntSushi/toml v1.5.0 // indirect
github.com/BurntSushi/toml v1.4.1-0.20240526193622-a339e1f7089c // indirect
github.com/Masterminds/goutils v1.1.1 // indirect
github.com/Masterminds/semver/v3 v3.3.1 // indirect
github.com/Masterminds/sprig/v3 v3.3.0 // indirect
@@ -46,10 +35,10 @@ require (
github.com/blakesmith/ar v0.0.0-20190502131153-809d4375e1fb // indirect
github.com/cavaliergopher/cpio v1.0.1 // indirect
github.com/cenkalti/backoff/v4 v4.3.0 // indirect
github.com/cespare/xxhash/v2 v2.3.0 // indirect
github.com/cli/browser v1.3.0 // indirect
github.com/cli/go-gh v0.1.0 // indirect
github.com/cloudflare/circl v1.6.1 // indirect
github.com/cpuguy83/go-md2man/v2 v2.0.6 // indirect
github.com/cloudflare/circl v1.6.0 // indirect
github.com/cyphar/filepath-securejoin v0.4.1 // indirect
github.com/deckarep/golang-set/v2 v2.8.0 // indirect
github.com/dlclark/regexp2 v1.11.4 // indirect
@@ -69,21 +58,18 @@ require (
github.com/gobwas/glob v0.2.3 // indirect
github.com/goccy/go-yaml v1.12.0 // indirect
github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8 // indirect
github.com/google/go-github/v70 v70.0.0 // indirect
github.com/google/go-querystring v1.1.0 // indirect
github.com/google/pprof v0.0.0-20230207041349-798e818bf904 // indirect
github.com/google/rpmpack v0.6.1-0.20250405124433-758cc6896cbc // indirect
github.com/google/uuid v1.6.0 // indirect
github.com/goreleaser/chglog v0.7.0 // indirect
github.com/goreleaser/fileglob v1.3.0 // indirect
github.com/goreleaser/nfpm/v2 v2.42.1 // indirect
github.com/hashicorp/go-version v1.7.0 // indirect
github.com/huandu/xstrings v1.5.0 // indirect
github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 // indirect
github.com/kevinburke/ssh_config v1.2.0 // indirect
github.com/klauspost/compress v1.18.0 // indirect
github.com/klauspost/pgzip v1.2.6 // indirect
github.com/mattn/go-colorable v0.1.14 // indirect
github.com/mattn/go-colorable v0.1.13 // indirect
github.com/mattn/go-isatty v0.0.20 // indirect
github.com/mitchellh/copystructure v1.2.0 // indirect
github.com/mitchellh/reflectwalk v1.0.2 // indirect
@@ -94,51 +80,40 @@ require (
github.com/prometheus/client_model v0.6.1 // indirect
github.com/prometheus/common v0.62.0 // indirect
github.com/prometheus/procfs v0.15.1 // indirect
github.com/russross/blackfriday/v2 v2.1.0 // indirect
github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3 // indirect
github.com/shopspring/decimal v1.4.0 // indirect
github.com/sirupsen/logrus v1.9.3 // indirect
github.com/skeema/knownhosts v1.3.1 // indirect
github.com/spf13/afero v1.14.0 // indirect
github.com/spf13/cast v1.7.1 // indirect
github.com/stoewer/go-strcase v1.3.0 // indirect
github.com/suzuki-shunsuke/logrus-error v0.1.4 // indirect
github.com/suzuki-shunsuke/pinact v1.6.0 // indirect
github.com/suzuki-shunsuke/urfave-cli-help-all v0.0.4 // indirect
github.com/stoewer/go-strcase v1.2.0 // indirect
github.com/ulikunitz/xz v0.5.12 // indirect
github.com/urfave/cli/v2 v2.27.6 // indirect
github.com/xanzy/ssh-agent v0.3.3 // indirect
github.com/xrash/smetrics v0.0.0-20240521201337-686a1a2994c1 // indirect
gitlab.com/digitalxero/go-conventional-commit v1.0.7 // indirect
go.yaml.in/yaml/v2 v2.4.2 // indirect
go.yaml.in/yaml/v3 v3.0.3 // indirect
golang.org/x/crypto v0.39.0 // indirect
golang.org/x/exp v0.0.0-20240719175910-8a7402abbf56 // indirect
golang.org/x/exp/typeparams v0.0.0-20231108232855-2478ac86f678 // indirect
golang.org/x/mod v0.25.0 // indirect
golang.org/x/oauth2 v0.28.0 // indirect
golang.org/x/sync v0.15.0 // indirect
golang.org/x/sys v0.33.0 // indirect
golang.org/x/telemetry v0.0.0-20240522233618-39ace7a40ae7 // indirect
golang.org/x/term v0.32.0 // indirect
golang.org/x/tools v0.34.0 // indirect
golang.org/x/text v0.26.0 // indirect
golang.org/x/tools v0.33.0 // indirect
golang.org/x/vuln v1.1.4 // indirect
golang.org/x/xerrors v0.0.0-20240716161551-93cc26a95ae9 // indirect
google.golang.org/genproto/googleapis/api v0.0.0-20250324211829-b45e905df463 // indirect
google.golang.org/genproto/googleapis/rpc v0.0.0-20250324211829-b45e905df463 // indirect
google.golang.org/protobuf v1.36.6 // indirect
google.golang.org/genproto/googleapis/api v0.0.0-20240826202546-f6391c0de4c7 // indirect
google.golang.org/genproto/googleapis/rpc v0.0.0-20240826202546-f6391c0de4c7 // indirect
google.golang.org/protobuf v1.36.5 // indirect
gopkg.in/warnings.v0 v0.1.2 // indirect
gopkg.in/yaml.v3 v3.0.1 // indirect
honnef.co/go/tools v0.6.1 // indirect
mvdan.cc/sh/v3 v3.11.0 // indirect
sigs.k8s.io/json v0.0.0-20241010143419-9aa6b5e7a4b3 // indirect
sigs.k8s.io/yaml v1.4.0 // indirect
)
tool (
github.com/TecharoHQ/yeet/cmd/yeet
github.com/a-h/templ/cmd/templ
github.com/nicksnyder/go-i18n/v2/goi18n
github.com/suzuki-shunsuke/pinact/cmd/pinact
golang.org/x/tools/cmd/deadcode
golang.org/x/tools/cmd/goimports
golang.org/x/tools/cmd/stringer
golang.org/x/vuln/cmd/govulncheck

117
go.sum
View File

@@ -1,15 +1,13 @@
al.essio.dev/pkg/shellescape v1.6.0 h1:NxFcEqzFSEVCGN2yq7Huv/9hyCEGVa/TncnOOBBeXHA=
al.essio.dev/pkg/shellescape v1.6.0/go.mod h1:6sIqp7X2P6mThCQ7twERpZTuigpr6KbZWtls1U8I890=
buf.build/gen/go/bufbuild/protovalidate/protocolbuffers/go v1.36.6-20250425153114-8976f5be98c1.1 h1:YhMSc48s25kr7kv31Z8vf7sPUIq5YJva9z1mn/hAt0M=
buf.build/gen/go/bufbuild/protovalidate/protocolbuffers/go v1.36.6-20250425153114-8976f5be98c1.1/go.mod h1:avRlCjnFzl98VPaeCtJ24RrV/wwHFzB8sWXhj26+n/U=
cel.dev/expr v0.23.1 h1:K4KOtPCJQjVggkARsjG9RWXP6O4R73aHeJMa/dmCQQg=
cel.dev/expr v0.23.1/go.mod h1:hLPLo1W4QUmuYdA72RBX06QTs6MXw941piREPl3Yfiw=
dario.cat/mergo v1.0.2 h1:85+piFYR1tMbRrLcDwR18y4UKJ3aH1Tbzi24VRW1TK8=
dario.cat/mergo v1.0.2/go.mod h1:E/hbnu0NxMFBjpMIE34DRGLWqDy0g5FuKDhCb31ngxA=
github.com/AlekSi/pointer v1.2.0 h1:glcy/gc4h8HnG2Z3ZECSzZ1IX1x2JxRVuDzaJwQE0+w=
github.com/AlekSi/pointer v1.2.0/go.mod h1:gZGfd3dpW4vEc/UlyfKKi1roIqcCgwOIvb0tSNSBle0=
github.com/BurntSushi/toml v1.5.0 h1:W5quZX/G/csjUnuI8SUYlsHs9M38FC7znL0lIO+DvMg=
github.com/BurntSushi/toml v1.5.0/go.mod h1:ukJfTF/6rtPPRCnwkur4qwRxa8vTRFBF0uk2lLoLwho=
github.com/BurntSushi/toml v1.4.1-0.20240526193622-a339e1f7089c h1:pxW6RcqyfI9/kWtOwnv/G+AzdKuy2ZrqINhenH4HyNs=
github.com/BurntSushi/toml v1.4.1-0.20240526193622-a339e1f7089c/go.mod h1:ukJfTF/6rtPPRCnwkur4qwRxa8vTRFBF0uk2lLoLwho=
github.com/DataDog/zstd v1.5.5 h1:oWf5W7GtOLgp6bciQYDmhHHjdhYkALu6S/5Ni9ZgSvQ=
github.com/DataDog/zstd v1.5.5/go.mod h1:g4AWEaM3yOg3HYfnJ3YIawPnVdXJh9QME85blwSAmyw=
github.com/MakeNowJust/heredoc v1.0.0/go.mod h1:mG5amYoWBHf8vpLOuehzbGGw0EHxpZZ6lCpQ4fNJ8LE=
@@ -30,14 +28,12 @@ github.com/ProtonMail/gopenpgp/v2 v2.7.1 h1:Awsg7MPc2gD3I7IFac2qE3Gdls0lZW8SzrFZ
github.com/ProtonMail/gopenpgp/v2 v2.7.1/go.mod h1:/BU5gfAVwqyd8EfC3Eu7zmuhwYQpKs+cGD8M//iiaxs=
github.com/Songmu/gitconfig v0.2.0 h1:pX2++u4KUq+K2k/ZCzGXLtkD3ceCqIdi0tDyb+IbSyo=
github.com/Songmu/gitconfig v0.2.0/go.mod h1:cB5bYJer+pl7W8g6RHFwL/0X6aJROVrYuHlvc7PT+hE=
github.com/TecharoHQ/thoth-proto v0.4.0 h1:UbkvfgCku0Dm1R6O4ug3HOsJNnE6F3wB8x+Dpw2lzFI=
github.com/TecharoHQ/thoth-proto v0.4.0/go.mod h1:IcGnZt3iYUZQVEa0Lwk5l4ix0hCeXlWUV1TJMZvbWx0=
github.com/TecharoHQ/yeet v0.6.0 h1:RCBAjr7wIlllsgy0tpvWpLX7jsZgu2tiuBY3RrprcR0=
github.com/TecharoHQ/yeet v0.6.0/go.mod h1:bj2V4Fg8qKQXoiuPZa3HuawrE8g+LsOQv/9q2WyGSsA=
github.com/a-h/parse v0.0.0-20250122154542-74294addb73e h1:HjVbSQHy+dnlS6C3XajZ69NYAb5jbGNfHanvm1+iYlo=
github.com/a-h/parse v0.0.0-20250122154542-74294addb73e/go.mod h1:3mnrkvGpurZ4ZrTDbYU84xhwXW2TjTKShSwjRi2ihfQ=
github.com/a-h/templ v0.3.906 h1:ZUThc8Q9n04UATaCwaG60pB1AqbulLmYEAMnWV63svg=
github.com/a-h/templ v0.3.906/go.mod h1:FFAu4dI//ESmEN7PQkJ7E7QfnSEMdcnu7QrAY8Dn334=
github.com/a-h/templ v0.3.898 h1:g9oxL/dmM6tvwRe2egJS8hBDQTncokbMoOFk1oJMX7s=
github.com/a-h/templ v0.3.898/go.mod h1:oLBbZVQ6//Q6zpvSMPTuBK0F3qOtBdFBcGRspcT+VNQ=
github.com/andybalholm/brotli v1.1.0 h1:eLKJA0d02Lf0mVpIDgYnqXcUn0GqVmEFny3VuID1U3M=
github.com/andybalholm/brotli v1.1.0/go.mod h1:sms7XGricyQI9K10gOSf56VKKWS4oLer58Q+mhRPtnY=
github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be h1:9AeTilPcZAjCFIImctFaOjnTIavg87rW78vTPkQqLI8=
@@ -67,10 +63,8 @@ github.com/cli/go-gh v0.1.0 h1:kMqFmC3ECBrV2UKzlOHjNOTTchExVc5tjNHtCqk/zYk=
github.com/cli/go-gh v0.1.0/go.mod h1:eTGWl99EMZ+3Iau5C6dHyGAJRRia65MtdBtuhWc+84o=
github.com/cli/safeexec v1.0.0/go.mod h1:Z/D4tTN8Vs5gXYHDCbaM1S/anmEDnJb1iW0+EJ5zx3Q=
github.com/cli/shurcooL-graphql v0.0.1/go.mod h1:U7gCSuMZP/Qy7kbqkk5PrqXEeDgtfG5K+W+u8weorps=
github.com/cloudflare/circl v1.6.1 h1:zqIqSPIndyBh1bjLVVDHMPpVKqp8Su/V+6MeDzzQBQ0=
github.com/cloudflare/circl v1.6.1/go.mod h1:uddAzsPgqdMAYatqJ0lsjX1oECcQLIlRpzZh3pJrofs=
github.com/cpuguy83/go-md2man/v2 v2.0.6 h1:XJtiaUW6dEEqVuZiMTn1ldk455QWwEIsMIJlo5vtkx0=
github.com/cpuguy83/go-md2man/v2 v2.0.6/go.mod h1:oOW0eioCTA6cOiMLiUPZOpcVxMig6NIQQ7OS05n1F4g=
github.com/cloudflare/circl v1.6.0 h1:cr5JKic4HI+LkINy2lg3W2jF8sHCVTBncJr5gIIq7qk=
github.com/cloudflare/circl v1.6.0/go.mod h1:uddAzsPgqdMAYatqJ0lsjX1oECcQLIlRpzZh3pJrofs=
github.com/creack/pty v1.1.24 h1:bJrF4RRfyJnbTJqzRLHzcGaZK1NeM5kTC9jGgovnR1s=
github.com/creack/pty v1.1.24/go.mod h1:08sCNb52WyoAwi2QDyzUCTgcvVFhUzewun7wtTfvcwE=
github.com/cyphar/filepath-securejoin v0.4.1 h1:JyxxyPEaktOD+GAnqIqTf9A8tHyAG22rowi7HkoSU1s=
@@ -105,8 +99,6 @@ github.com/frankban/quicktest v1.14.6 h1:7Xjx+VpznH+oBnejlPUj8oUpdxnVs4f8XU8WnHk
github.com/frankban/quicktest v1.14.6/go.mod h1:4ptaffx2x8+WTWXmUCuVU6aPUX1/Mz7zb5vbUoiM6w0=
github.com/fsnotify/fsnotify v1.8.0 h1:dAwr6QBTBZIkG8roQaJjGof0pp0EeF+tNV7YBP3F/8M=
github.com/fsnotify/fsnotify v1.8.0/go.mod h1:8jBTzvmWwFyi3Pb8djgCCO5IBqzKJ/Jwo8TRcHyHii0=
github.com/gaissmai/bart v0.20.4 h1:Ik47r1fy3jRVU+1eYzKSW3ho2UgBVTVnUS8O993584U=
github.com/gaissmai/bart v0.20.4/go.mod h1:cEed+ge8dalcbpi8wtS9x9m2hn/fNJH5suhdGQOHnYk=
github.com/gliderlabs/ssh v0.3.8 h1:a4YXD1V7xMF9g5nTkdfnja3Sxy1PVDCj1Zg4Wb8vY6c=
github.com/gliderlabs/ssh v0.3.8/go.mod h1:xYoytBv1sV0aL3CavoDuJIQNURXkkfPA/wxQ1pL1fAU=
github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 h1:+zs/tPmkDkHx3U66DAb0lQFJrpS6731Oaa12ikc+DiI=
@@ -119,10 +111,6 @@ github.com/go-git/go-git/v5 v5.14.0 h1:/MD3lCrGjCen5WfEAzKg00MJJffKhC8gzS80ycmCi
github.com/go-git/go-git/v5 v5.14.0/go.mod h1:Z5Xhoia5PcWA3NF8vRLURn9E5FRhSl7dGj9ItW3Wk5k=
github.com/go-jose/go-jose/v3 v3.0.4 h1:Wp5HA7bLQcKnf6YYao/4kpRpVMp/yf6+pJKV8WFSaNY=
github.com/go-jose/go-jose/v3 v3.0.4/go.mod h1:5b+7YgP7ZICgJDBdfjZaIt+H/9L9T/YQrVfLAMboGkQ=
github.com/go-logr/logr v1.4.2 h1:6pFjapn8bFcIbiKo3XT4j/BhANplGihG6tvd+8rYgrY=
github.com/go-logr/logr v1.4.2/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag=
github.com/go-logr/stdr v1.2.2/go.mod h1:mMo/vtBO5dYbehREoey6XUKy/eSumjCCveDpRre4VKE=
github.com/go-playground/assert/v2 v2.0.1/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4=
github.com/go-playground/locales v0.13.0 h1:HyWk6mgj5qFqCT5fjGBuRArbVDfE4hi8+e8ceBS/t7Q=
github.com/go-playground/locales v0.13.0/go.mod h1:taPMhCMXrRLJO55olJkUXHZBHCxTMfnGwq/HNwmWNS8=
@@ -146,20 +134,13 @@ github.com/golang-jwt/jwt/v5 v5.2.2 h1:Rl4B7itRWVtYIHFrSNd7vhTiz9UpLdi6gZhZ3wEeD
github.com/golang-jwt/jwt/v5 v5.2.2/go.mod h1:pqrtFR0X4osieyHYxtmOUWsAWrfe1Q5UVIyoH402zdk=
github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8 h1:f+oWsMOmNPc8JmEHVZIycC7hBoQxHH9pNKQORJNozsQ=
github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8/go.mod h1:wcDNUvekVysuuOpQKo3191zZyTpiI6se1N1ULghS0sw=
github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek=
github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps=
github.com/google/cel-go v0.25.0 h1:jsFw9Fhn+3y2kBbltZR4VEz5xKkcIFRPDnuEzAGv5GY=
github.com/google/cel-go v0.25.0/go.mod h1:hjEb6r5SuOSlhCHmFoLzu8HGCERvIsDAbxDAyNU/MmI=
github.com/google/go-cmdtest v0.4.1-0.20220921163831-55ab3332a786 h1:rcv+Ippz6RAtvaGgKxc+8FQIpxHgsF+HBzPyYL2cyVU=
github.com/google/go-cmdtest v0.4.1-0.20220921163831-55ab3332a786/go.mod h1:apVn/GCasLZUVpAJ6oWAuyP7Ne7CEsQbTnc0plM3m+o=
github.com/google/go-cmp v0.5.2/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
github.com/google/go-github/v70 v70.0.0 h1:/tqCp5KPrcvqCc7vIvYyFYTiCGrYvaWoYMGHSQbo55o=
github.com/google/go-github/v70 v70.0.0/go.mod h1:xBUZgo8MI3lUL/hwxl3hlceJW1U8MVnXP3zUyI+rhQY=
github.com/google/go-querystring v1.1.0 h1:AnCroh3fv4ZBgVIf1Iwtovgjaw/GiKJo8M8yD/fhyJ8=
github.com/google/go-querystring v1.1.0/go.mod h1:Kcdr2DB4koayq7X8pmAG4sNG59So17icRSOU623lUBU=
github.com/google/pprof v0.0.0-20230207041349-798e818bf904 h1:4/hN5RUoecvl+RmJRE2YxKWtnnQls6rQjjW5oV7qg2U=
github.com/google/pprof v0.0.0-20230207041349-798e818bf904/go.mod h1:uglQLonpP8qtYCYyzA+8c/9qtqgA3qsXGYqCPKARAFg=
github.com/google/renameio v0.1.0 h1:GOZbcHa3HfsPKPlmyPyN2KEohoMXOhdMbHrvbpl2QaA=
@@ -178,20 +159,12 @@ github.com/goreleaser/fileglob v1.3.0 h1:/X6J7U8lbDpQtBvGcwwPS6OpzkNVlVEsFUVRx9+
github.com/goreleaser/fileglob v1.3.0/go.mod h1:Jx6BoXv3mbYkEzwm9THo7xbr5egkAraxkGorbJb4RxU=
github.com/goreleaser/nfpm/v2 v2.42.1 h1:xu2pLRgQuz2ab+YZFoeIzwU/M5jjjCKDGwv1lRbVGvk=
github.com/goreleaser/nfpm/v2 v2.42.1/go.mod h1:dY53KWYKebkOocxgkmpM7SRX0Nv5hU+jEu2kIaM4/LI=
github.com/grpc-ecosystem/go-grpc-middleware/providers/prometheus v1.1.0 h1:QGLs/O40yoNK9vmy4rhUGBVyMf1lISBGtXRpsu/Qu/o=
github.com/grpc-ecosystem/go-grpc-middleware/providers/prometheus v1.1.0/go.mod h1:hM2alZsMUni80N33RBe6J0e423LB+odMj7d3EMP9l20=
github.com/grpc-ecosystem/go-grpc-middleware/v2 v2.3.2 h1:sGm2vDRFUrQJO/Veii4h4zG2vvqG6uWNkBHSTqXOZk0=
github.com/grpc-ecosystem/go-grpc-middleware/v2 v2.3.2/go.mod h1:wd1YpapPLivG6nQgbf7ZkG1hhSOXDhhn4MLTknx2aAc=
github.com/h2non/parth v0.0.0-20190131123155-b4df798d6542/go.mod h1:Ow0tF8D4Kplbc8s8sSb3V2oUCygFHVp8gC3Dn6U4MNI=
github.com/hashicorp/go-version v1.7.0 h1:5tqGy27NaOTB8yJKUZELlFAS/LTKJkrmONwQKeRZfjY=
github.com/hashicorp/go-version v1.7.0/go.mod h1:fltr4n8CU8Ke44wwGCBoEymUuxUHl09ZGVZPK5anwXA=
github.com/henvic/httpretty v0.0.6/go.mod h1:X38wLjWXHkXT7r2+uK8LjCMne9rsuNaBLJ+5cU2/Pmo=
github.com/huandu/xstrings v1.5.0 h1:2ag3IFq9ZDANvthTwTiqSSZLjDc+BedvHPAp5tJy2TI=
github.com/huandu/xstrings v1.5.0/go.mod h1:y5/lhBue+AyNmUVz9RLU9xbLR0o4KIIExikq4ovT0aE=
github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 h1:BQSFePA1RWJOlocH6Fxy8MmwDt+yVQYULKfN0RoTN8A=
github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99/go.mod h1:1lJo3i6rXxKeerYnT8Nvf0QmHCRC1n8sfWVwXF2Frvo=
github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0=
github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4=
github.com/jtolds/gls v4.20.0+incompatible h1:xdiiI2gbIgH/gLH7ADydsJ1uDOEzR8yvV7C0MuV77Wo=
github.com/jtolds/gls v4.20.0+incompatible/go.mod h1:QJZ7F/aHp+rZTRtaJ1ow/lLfFfVYBRgL+9YlvaHOwJU=
github.com/kevinburke/ssh_config v1.2.0 h1:x584FjTGwHzMwvHx18PXxbBVzfnxogHaAReU4gf13a4=
@@ -217,9 +190,8 @@ github.com/matryer/is v1.4.0 h1:sosSmIWwkYITGrxZ25ULNDeKiMNzFSr4V/eqBQP0PeE=
github.com/matryer/is v1.4.0/go.mod h1:8I/i5uYgLzgsgEloJE1U6xx5HkBQpAZvepWuujKwMRU=
github.com/mattn/go-colorable v0.1.8/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope9wVRipJSqc=
github.com/mattn/go-colorable v0.1.9/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope9wVRipJSqc=
github.com/mattn/go-colorable v0.1.13 h1:fFA4WZxdEF4tXPZVKMLwD8oUnCTTo08duU7wxecdEvA=
github.com/mattn/go-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovkB8vQcUbaXHg=
github.com/mattn/go-colorable v0.1.14 h1:9A9LHSqF/7dyVVX6g0U9cwm9pG3kP9gSzcuIPHPsaIE=
github.com/mattn/go-colorable v0.1.14/go.mod h1:6LmQG8QLFO4G5z1gPvYEzlUgJ2wF+stgPZH1UqBm1s8=
github.com/mattn/go-isatty v0.0.12/go.mod h1:cbi8OIDigv2wuxKPP5vlRcQ1OAZbq2CE4Kysco4FUpU=
github.com/mattn/go-isatty v0.0.14/go.mod h1:7GGIvUiUoEMVVmxf/4nioHXj79iQHKdU27kJ6hsGG94=
github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
@@ -237,8 +209,6 @@ github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8m
github.com/natefinch/atomic v1.0.1 h1:ZPYKxkqQOx3KZ+RsbnP/YsgvxWQPGxjC0oBt2AhwV0A=
github.com/natefinch/atomic v1.0.1/go.mod h1:N/D/ELrljoqDyT3rZrsUmtsuzvHkeB/wWjHV22AZRbM=
github.com/nbio/st v0.0.0-20140626010706-e9e8d9816f32/go.mod h1:9wM+0iRr9ahx58uYLpLIr5fm8diHn0JbqRycJi6w0Ms=
github.com/nicksnyder/go-i18n/v2 v2.6.0 h1:C/m2NNWNiTB6SK4Ao8df5EWm3JETSTIGNXBpMJTxzxQ=
github.com/nicksnyder/go-i18n/v2 v2.6.0/go.mod h1:88sRqr0C6OPyJn0/KRNaEz1uWorjxIKP7rUUcvycecE=
github.com/onsi/gomega v1.35.1 h1:Cwbd75ZBPxFSuZ6T+rN/WCb/gOc6YgFBXLlZLhC7Ds4=
github.com/onsi/gomega v1.35.1/go.mod h1:PvZbdDc8J6XJEpDK4HCuRBm8a6Fzp9/DmhC9C7yFlog=
github.com/pjbgf/sha1cd v0.3.2 h1:a9wb0bp1oC2TGwStyn0Umc/IGKQnEgF0vVaZ8QF8eo4=
@@ -261,8 +231,6 @@ github.com/prometheus/procfs v0.15.1/go.mod h1:fB45yRUv8NstnjriLhBQLuOUt+WW4BsoG
github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
github.com/rogpeppe/go-internal v1.14.1 h1:UQB4HGPB6osV0SQTLymcB4TgvyWu6ZyliaW0tI/otEQ=
github.com/rogpeppe/go-internal v1.14.1/go.mod h1:MaRKkUm5W0goXpeCfT7UZI6fk/L7L7so1lCWt35ZSgc=
github.com/russross/blackfriday/v2 v2.1.0 h1:JIOH55/0cWyOuilr9/qlrm0BSXldqnqwMsf35Ld67mk=
github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
github.com/sassoftware/go-rpmutils v0.4.0 h1:ojND82NYBxgwrV+mX1CWsd5QJvvEZTKddtCdFLPWhpg=
github.com/sassoftware/go-rpmutils v0.4.0/go.mod h1:3goNWi7PGAT3/dlql2lv3+MSN5jNYPjT5mVcQcIsYzI=
github.com/sebest/xff v0.0.0-20210106013422-671bd2870b3a h1:iLcLb5Fwwz7g/DLK89F+uQBDeAhHhwdzB5fSlVdhGcM=
@@ -272,67 +240,35 @@ github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3/go.mod h1:A0bzQcvG
github.com/shopspring/decimal v1.4.0 h1:bxl37RwXBklmTi0C79JfXCEBD1cqqHt0bbgBAGFp81k=
github.com/shopspring/decimal v1.4.0/go.mod h1:gawqmDU56v4yIKSwfBSFip1HdCCXN8/+DMd9qYNcwME=
github.com/sirupsen/logrus v1.7.0/go.mod h1:yWOB1SBYBC5VeMP7gHvWumXLIWorT60ONWic61uBYv0=
github.com/sirupsen/logrus v1.9.3 h1:dueUQJ1C2q9oE3F7wvmSGAaVtTmUizReu6fjN8uqzbQ=
github.com/sirupsen/logrus v1.9.3/go.mod h1:naHLuLoDiP4jHNo9R0sCBMtWGeIprob74mVsIT4qYEQ=
github.com/skeema/knownhosts v1.3.1 h1:X2osQ+RAjK76shCbvhHHHVl3ZlgDm8apHEHFqRjnBY8=
github.com/skeema/knownhosts v1.3.1/go.mod h1:r7KTdC8l4uxWRyK2TpQZ/1o5HaSzh06ePQNxPwTcfiY=
github.com/smarty/assertions v1.15.0 h1:cR//PqUBUiQRakZWqBiFFQ9wb8emQGDb0HeGdqGByCY=
github.com/smarty/assertions v1.15.0/go.mod h1:yABtdzeQs6l1brC900WlRNwj6ZR55d7B+E8C6HtKdec=
github.com/smartystreets/goconvey v1.8.1 h1:qGjIddxOk4grTu9JPOU31tVfq3cNdBlNa5sSznIX1xY=
github.com/smartystreets/goconvey v1.8.1/go.mod h1:+/u4qLyY6x1jReYOp7GOM2FSt8aP9CzCZL03bI28W60=
github.com/spf13/afero v1.14.0 h1:9tH6MapGnn/j0eb0yIXiLjERO8RB6xIVZRDCX7PtqWA=
github.com/spf13/afero v1.14.0/go.mod h1:acJQ8t0ohCGuMN3O+Pv0V0hgMxNYDlvdk+VTfyZmbYo=
github.com/spf13/cast v1.7.1 h1:cuNEagBQEHWN1FnbGEjCXL2szYEXqfJPbP2HNUaca9Y=
github.com/spf13/cast v1.7.1/go.mod h1:ancEpBxwJDODSW/UG4rDrAqiKolqNNh2DX3mk86cAdo=
github.com/stoewer/go-strcase v1.3.0 h1:g0eASXYtp+yvN9fK8sH94oCIk0fau9uV1/ZdJ0AVEzs=
github.com/stoewer/go-strcase v1.3.0/go.mod h1:fAH5hQ5pehh+j3nZfvwdk2RgEgQjAoM8wodgtPmh1xo=
github.com/stoewer/go-strcase v1.2.0 h1:Z2iHWqGXH00XYgqDmNgQbIBxf3wrNq0F3feEy0ainaU=
github.com/stoewer/go-strcase v1.2.0/go.mod h1:IBiWB2sKIp3wVVQ3Y035++gc+knqhUQag1KpM8ahLw8=
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5cxcmMvtA=
github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA=
github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
github.com/suzuki-shunsuke/logrus-error v0.1.4 h1:nWo98uba1fANHdZ9Y5pJ2RKs/PpVjrLzRp5m+mRb9KE=
github.com/suzuki-shunsuke/logrus-error v0.1.4/go.mod h1:WsVvvw6SKSt08/fB2qbnsKIMJA4K1MYCUprqsBJbMiM=
github.com/suzuki-shunsuke/pinact v1.6.0 h1:2QvSzREOquwLwKXhF9Hj0AInE/Rl63SZz9dKkHFC6so=
github.com/suzuki-shunsuke/pinact v1.6.0/go.mod h1:FDUMck0mmL0mcnNZ23Vjh/aOR5cIdZhF1IIpGksT4dQ=
github.com/suzuki-shunsuke/urfave-cli-help-all v0.0.4 h1:YGHgrVjGTYHY98II6zijXUHP+OyvrzSCvd8m9iUcaK8=
github.com/suzuki-shunsuke/urfave-cli-help-all v0.0.4/go.mod h1:sSi6xaUaHfaqu32ECLeyE7NTMv+ZM5dW0JikhllaalY=
github.com/thlib/go-timezone-local v0.0.0-20210907160436-ef149e42d28e/go.mod h1:/Tnicc6m/lsJE0irFMA0LfIwTBo4QP7A8IfyIv4zZKI=
github.com/ulikunitz/xz v0.5.12 h1:37Nm15o69RwBkXM0J6A5OlE67RZTfzUxTj8fB3dfcsc=
github.com/ulikunitz/xz v0.5.12/go.mod h1:nbz6k7qbPmH4IRqmfOplQw/tblSgqTqBwxkY0oWt/14=
github.com/urfave/cli/v2 v2.27.6 h1:VdRdS98FNhKZ8/Az8B7MTyGQmpIr36O1EHybx/LaZ4g=
github.com/urfave/cli/v2 v2.27.6/go.mod h1:3Sevf16NykTbInEnD0yKkjDAeZDS0A6bzhBH5hrMvTQ=
github.com/xanzy/ssh-agent v0.3.3 h1:+/15pJfg/RsTxqYcX6fHqOXZwwMP+2VyYWJeWM2qQFM=
github.com/xanzy/ssh-agent v0.3.3/go.mod h1:6dzNDKs0J9rVPHPhaGCukekBHKqfl+L3KghI1Bc68Uw=
github.com/xi2/xz v0.0.0-20171230120015-48954b6210f8 h1:nIPpBwaJSVYIxUFsDv3M8ofmx9yWTog9BfvIu0q41lo=
github.com/xi2/xz v0.0.0-20171230120015-48954b6210f8/go.mod h1:HUYIGzjTL3rfEspMxjDjgmT5uz5wzYJKVo23qUhYTos=
github.com/xrash/smetrics v0.0.0-20240521201337-686a1a2994c1 h1:gEOO8jv9F4OT7lGCjxCBTO/36wtF6j2nSip77qHd4x4=
github.com/xrash/smetrics v0.0.0-20240521201337-686a1a2994c1/go.mod h1:Ohn+xnUBiLI6FVj/9LpzZWtj1/D6lUovWYBkxHVV3aM=
github.com/yl2chen/cidranger v1.0.2 h1:lbOWZVCG1tCRX4u24kuM1Tb4nHqWkDxwLdoS+SevawU=
github.com/yl2chen/cidranger v1.0.2/go.mod h1:9U1yz7WPYDwf0vpNWFaeRh0bjwz5RVgRy/9UEQfHl0g=
github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
gitlab.com/digitalxero/go-conventional-commit v1.0.7 h1:8/dO6WWG+98PMhlZowt/YjuiKhqhGlOCwlIV8SqqGh8=
gitlab.com/digitalxero/go-conventional-commit v1.0.7/go.mod h1:05Xc2BFsSyC5tKhK0y+P3bs0AwUtNuTp+mTpbCU/DZ0=
go.opentelemetry.io/auto/sdk v1.1.0 h1:cH53jehLUN6UFLY71z+NDOiNJqDdPRaXzTel0sJySYA=
go.opentelemetry.io/auto/sdk v1.1.0/go.mod h1:3wSPjt5PWp2RhlCcmmOial7AvC4DQqZb7a7wCow3W8A=
go.opentelemetry.io/otel v1.35.0 h1:xKWKPxrxB6OtMCbmMY021CqC45J+3Onta9MqjhnusiQ=
go.opentelemetry.io/otel v1.35.0/go.mod h1:UEqy8Zp11hpkUrL73gSlELM0DupHoiq72dR+Zqel/+Y=
go.opentelemetry.io/otel/metric v1.35.0 h1:0znxYu2SNyuMSQT4Y9WDWej0VpcsxkuklLa4/siN90M=
go.opentelemetry.io/otel/metric v1.35.0/go.mod h1:nKVFgxBZ2fReX6IlyW28MgZojkoAkJGaE8CpgeAU3oE=
go.opentelemetry.io/otel/sdk v1.35.0 h1:iPctf8iprVySXSKJffSS79eOjl9pvxV9ZqOWT0QejKY=
go.opentelemetry.io/otel/sdk v1.35.0/go.mod h1:+ga1bZliga3DxJ3CQGg3updiaAJoNECOgJREo9KHGQg=
go.opentelemetry.io/otel/sdk/metric v1.35.0 h1:1RriWBmCKgkeHEhM7a2uMjMUfP7MsOF5JpUCaEqEI9o=
go.opentelemetry.io/otel/sdk/metric v1.35.0/go.mod h1:is6XYCUMpcKi+ZsOvfluY5YstFnhW0BidkR+gL+qN+w=
go.opentelemetry.io/otel/trace v1.35.0 h1:dPpEfJu1sDIqruz7BHFG3c7528f6ddfSWfFDVt/xgMs=
go.opentelemetry.io/otel/trace v1.35.0/go.mod h1:WUk7DtFp1Aw2MkvqGdwiXYDZZNvA/1J8o6xRXLrIkyc=
go.yaml.in/yaml/v2 v2.4.2 h1:DzmwEr2rDGHl7lsFgAHxmNz/1NlQ7xLIrlN2h5d1eGI=
go.yaml.in/yaml/v2 v2.4.2/go.mod h1:081UH+NErpNdqlCXm3TtEran0rJZGxAYx9hb/ELlsPU=
go.yaml.in/yaml/v3 v3.0.3 h1:bXOww4E/J3f66rav3pX3m8w6jDE4knZjGOw8b5Y6iNE=
go.yaml.in/yaml/v3 v3.0.3/go.mod h1:tBHosrYAkRZjRAOREWbDnBXUf08JOwYq++0QNwQiWzI=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
@@ -357,8 +293,6 @@ golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
golang.org/x/net v0.41.0 h1:vBTly1HeNPEn3wtREYfy4GZ/NECgw2Cnl+nK6Nz3uvw=
golang.org/x/net v0.41.0/go.mod h1:B/K4NNqkfmg07DQYrbwvSluqCJOOXwUjeb/5lOisjbA=
golang.org/x/oauth2 v0.28.0 h1:CrgCKl8PPAVtLnU3c+EDw6x11699EWlsDeWNWKdIOkc=
golang.org/x/oauth2 v0.28.0/go.mod h1:onh5ek6nERTohokkhCD/y2cV4Do3fxFHFuAejCkRWT8=
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
@@ -410,24 +344,21 @@ golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGm
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
golang.org/x/tools v0.34.0 h1:qIpSLOxeCYGg9TrcJokLBG4KFA6d795g0xkBkiESGlo=
golang.org/x/tools v0.34.0/go.mod h1:pAP9OwEaY1CAW3HOmg3hLZC5Z0CCmzjAF2UQMSqNARg=
golang.org/x/tools v0.33.0 h1:4qz2S3zmRxbGIhDIAgjxvFutSvH5EfnsYrRBj0UI0bc=
golang.org/x/tools v0.33.0/go.mod h1:CIJMaWEY88juyUfo7UbgPqbC8rU2OqfAV1h2Qp0oMYI=
golang.org/x/vuln v1.1.4 h1:Ju8QsuyhX3Hk8ma3CesTbO8vfJD9EvUBgHvkxHBzj0I=
golang.org/x/vuln v1.1.4/go.mod h1:F+45wmU18ym/ca5PLTPLsSzr2KppzswxPP603ldA67s=
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20220609144429-65e65417b02f/go.mod h1:K8+ghG5WaK9qNqU5K3HdILfMLy1f3aNYFI/wnl100a8=
golang.org/x/xerrors v0.0.0-20240716161551-93cc26a95ae9 h1:LLhsEBxRTBLuKlQxFBYUOU8xyFgXv6cOTp2HASDlsDk=
golang.org/x/xerrors v0.0.0-20240716161551-93cc26a95ae9/go.mod h1:NDW/Ps6MPRej6fsCIbMTohpP40sJ/P/vI1MoTEGwX90=
google.golang.org/genproto/googleapis/api v0.0.0-20250324211829-b45e905df463 h1:hE3bRWtU6uceqlh4fhrSnUyjKHMKB9KrTLLG+bc0ddM=
google.golang.org/genproto/googleapis/api v0.0.0-20250324211829-b45e905df463/go.mod h1:U90ffi8eUL9MwPcrJylN5+Mk2v3vuPDptd5yyNUiRR8=
google.golang.org/genproto/googleapis/rpc v0.0.0-20250324211829-b45e905df463 h1:e0AIkUUhxyBKh6ssZNrAMeqhA7RKUj42346d1y02i2g=
google.golang.org/genproto/googleapis/rpc v0.0.0-20250324211829-b45e905df463/go.mod h1:qQ0YXyHHx3XkvlzUtpXDkS29lDSafHMZBAZDc03LQ3A=
google.golang.org/grpc v1.73.0 h1:VIWSmpI2MegBtTuFt5/JWy2oXxtjJ/e89Z70ImfD2ok=
google.golang.org/grpc v1.73.0/go.mod h1:50sbHOUqWoCQGI8V2HQLJM0B+LMlIUjNSZmow7EVBQc=
google.golang.org/protobuf v1.36.6 h1:z1NpPI8ku2WgiWnf+t9wTPsn6eP1L7ksHUlkfLvd9xY=
google.golang.org/protobuf v1.36.6/go.mod h1:jduwjTPXsFjZGTmRluh+L6NjiWu7pchiJ2/5YcXBHnY=
google.golang.org/genproto/googleapis/api v0.0.0-20240826202546-f6391c0de4c7 h1:YcyjlL1PRr2Q17/I0dPk2JmYS5CDXfcdb2Z3YRioEbw=
google.golang.org/genproto/googleapis/api v0.0.0-20240826202546-f6391c0de4c7/go.mod h1:OCdP9MfskevB/rbYvHTsXTtKC+3bHWajPdoKgjcYkfo=
google.golang.org/genproto/googleapis/rpc v0.0.0-20240826202546-f6391c0de4c7 h1:2035KHhUv+EpyB+hWgJnaWKJOdX1E95w2S8Rr4uWKTs=
google.golang.org/genproto/googleapis/rpc v0.0.0-20240826202546-f6391c0de4c7/go.mod h1:UqMtugtsSgubUsoxbuAoiCXvqvErP7Gf0so0mK9tHxU=
google.golang.org/protobuf v1.36.5 h1:tPhr+woSbjfYvY6/GPufUoYizxw1cF/yFoxJ2fmpwlM=
google.golang.org/protobuf v1.36.5/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
@@ -444,8 +375,8 @@ gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
honnef.co/go/tools v0.6.1 h1:R094WgE8K4JirYjBaOpz/AvTyUu/3wbmAoskKN/pxTI=
honnef.co/go/tools v0.6.1/go.mod h1:3puzxxljPCe8RGJX7BIy1plGbxEOZni5mR2aXe3/uk4=
k8s.io/apimachinery v0.33.2 h1:IHFVhqg59mb8PJWTLi8m1mAoepkUNYmptHsV+Z1m5jY=
k8s.io/apimachinery v0.33.2/go.mod h1:BHW0YOu7n22fFv/JkYOEfkUYNRN0fj0BlvMFWA7b+SM=
k8s.io/apimachinery v0.33.1 h1:mzqXWV8tW9Rw4VeW9rEkqvnxj59k1ezDUl20tFK/oM4=
k8s.io/apimachinery v0.33.1/go.mod h1:BHW0YOu7n22fFv/JkYOEfkUYNRN0fj0BlvMFWA7b+SM=
mvdan.cc/sh/v3 v3.11.0 h1:q5h+XMDRfUGUedCqFFsjoFjrhwf2Mvtt1rkMvVz0blw=
mvdan.cc/sh/v3 v3.11.0/go.mod h1:LRM+1NjoYCzuq/WZ6y44x14YNAI0NK7FLPeQSaFagGg=
pault.ag/go/debian v0.18.0 h1:nr0iiyOU5QlG1VPnhZLNhnCcHx58kukvBJp+dvaM6CQ=
@@ -454,5 +385,5 @@ pault.ag/go/topsort v0.1.1 h1:L0QnhUly6LmTv0e3DEzbN2q6/FGgAcQvaEw65S53Bg4=
pault.ag/go/topsort v0.1.1/go.mod h1:r1kc/L0/FZ3HhjezBIPaNVhkqv8L0UJ9bxRuHRVZ0q4=
sigs.k8s.io/json v0.0.0-20241010143419-9aa6b5e7a4b3 h1:/Rv+M11QRah1itp8VhT6HoVx1Ray9eB4DBr+K+/sCJ8=
sigs.k8s.io/json v0.0.0-20241010143419-9aa6b5e7a4b3/go.mod h1:18nIHnGi6636UCz6m8i4DhaJ65T6EruyzmoQqI2BVDo=
sigs.k8s.io/yaml v1.5.0 h1:M10b2U7aEUY6hRtU870n2VTPgR5RZiL/I6Lcc2F4NUQ=
sigs.k8s.io/yaml v1.5.0/go.mod h1:wZs27Rbxoai4C0f8/9urLZtZtF3avA3gKvGyPdDqTO4=
sigs.k8s.io/yaml v1.4.0 h1:Mk1wCc2gy/F0THH0TAp1QYyJNzRm2KCLy3o5ASXVI5E=
sigs.k8s.io/yaml v1.4.0/go.mod h1:Ejl7/uTz7PSA4eKMyQCUTnhZYNmLIl+5c2lQPGR2BPY=

View File

@@ -3,23 +3,10 @@ package internal
import (
"crypto/sha256"
"encoding/hex"
"strconv"
"github.com/cespare/xxhash/v2"
)
// SHA256sum computes a cryptographic hash. Still used for proof-of-work challenges
// where we need the security properties of a cryptographic hash function.
func SHA256sum(text string) string {
hash := sha256.New()
hash.Write([]byte(text))
return hex.EncodeToString(hash.Sum(nil))
}
// FastHash is a high-performance non-cryptographic hash function suitable for
// internal caching, policy rule identification, and other performance-critical
// use cases where cryptographic security is not required.
func FastHash(text string) string {
h := xxhash.Sum64String(text)
return strconv.FormatUint(h, 16)
}

View File

@@ -1,261 +0,0 @@
package internal
import (
"fmt"
"strings"
"testing"
)
// XXHash64sum is a test alias for FastHash to benchmark against SHA256
func XXHash64sum(text string) string {
return FastHash(text)
}
// Test data that matches real usage patterns in the codebase
var (
// Typical policy checker inputs
policyInputs = []string{
"User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
"User-Agent: bot/1.0",
"User-Agent: GoogleBot/2.1",
"/robots.txt",
"/api/.*",
"10.0.0.0/8",
"192.168.1.0/24",
"172.16.0.0/12",
}
// Challenge data from challengeFor function
challengeInputs = []string{
"Accept-Language=en-US,X-Real-IP=192.168.1.100,User-Agent=Mozilla/5.0,WeekTime=2025-06-16T00:00:00Z,Fingerprint=abc123,Difficulty=5",
"Accept-Language=fr-FR,X-Real-IP=10.0.0.50,User-Agent=Chrome/91.0,WeekTime=2025-06-16T00:00:00Z,Fingerprint=def456,Difficulty=3",
"Accept-Language=es-ES,X-Real-IP=172.16.1.1,User-Agent=Safari/14.0,WeekTime=2025-06-16T00:00:00Z,Fingerprint=ghi789,Difficulty=7",
}
// Bot rule patterns
botRuleInputs = []string{
"GoogleBot::path:/robots.txt",
"BingBot::useragent:Mozilla/5.0 (compatible; bingbot/2.0)",
"FacebookBot::headers:Accept-Language,User-Agent",
"TwitterBot::cidr:192.168.1.0/24",
}
// CEL expressions from policy rules
celInputs = []string{
`request.headers["User-Agent"].contains("bot")`,
`request.path.startsWith("/api/") && request.method == "POST"`,
`request.remoteAddress in ["192.168.1.0/24", "10.0.0.0/8"]`,
`request.userAgent.matches(".*[Bb]ot.*") || request.userAgent.matches(".*[Cc]rawler.*")`,
}
// Thoth ASN checker inputs
asnInputs = []string{
"ASNChecker\nAS 15169\nAS 8075\nAS 32934",
"ASNChecker\nAS 13335\nAS 16509\nAS 14061",
"ASNChecker\nAS 36351\nAS 20940\nAS 8100",
}
)
func BenchmarkSHA256_PolicyInputs(b *testing.B) {
b.ResetTimer()
for i := 0; i < b.N; i++ {
input := policyInputs[i%len(policyInputs)]
_ = SHA256sum(input)
}
}
func BenchmarkXXHash_PolicyInputs(b *testing.B) {
b.ResetTimer()
for i := 0; i < b.N; i++ {
input := policyInputs[i%len(policyInputs)]
_ = XXHash64sum(input)
}
}
func BenchmarkSHA256_ChallengeInputs(b *testing.B) {
b.ResetTimer()
for i := 0; i < b.N; i++ {
input := challengeInputs[i%len(challengeInputs)]
_ = SHA256sum(input)
}
}
func BenchmarkXXHash_ChallengeInputs(b *testing.B) {
b.ResetTimer()
for i := 0; i < b.N; i++ {
input := challengeInputs[i%len(challengeInputs)]
_ = XXHash64sum(input)
}
}
func BenchmarkSHA256_BotRuleInputs(b *testing.B) {
b.ResetTimer()
for i := 0; i < b.N; i++ {
input := botRuleInputs[i%len(botRuleInputs)]
_ = SHA256sum(input)
}
}
func BenchmarkXXHash_BotRuleInputs(b *testing.B) {
b.ResetTimer()
for i := 0; i < b.N; i++ {
input := botRuleInputs[i%len(botRuleInputs)]
_ = XXHash64sum(input)
}
}
func BenchmarkSHA256_CELInputs(b *testing.B) {
b.ResetTimer()
for i := 0; i < b.N; i++ {
input := celInputs[i%len(celInputs)]
_ = SHA256sum(input)
}
}
func BenchmarkXXHash_CELInputs(b *testing.B) {
b.ResetTimer()
for i := 0; i < b.N; i++ {
input := celInputs[i%len(celInputs)]
_ = XXHash64sum(input)
}
}
func BenchmarkSHA256_ASNInputs(b *testing.B) {
b.ResetTimer()
for i := 0; i < b.N; i++ {
input := asnInputs[i%len(asnInputs)]
_ = SHA256sum(input)
}
}
func BenchmarkXXHash_ASNInputs(b *testing.B) {
b.ResetTimer()
for i := 0; i < b.N; i++ {
input := asnInputs[i%len(asnInputs)]
_ = XXHash64sum(input)
}
}
// Benchmark the policy list hashing used in checker.go
func BenchmarkSHA256_PolicyList(b *testing.B) {
b.ResetTimer()
for i := 0; i < b.N; i++ {
var sb strings.Builder
for _, input := range policyInputs {
fmt.Fprintln(&sb, SHA256sum(input))
}
_ = SHA256sum(sb.String())
}
}
func BenchmarkXXHash_PolicyList(b *testing.B) {
b.ResetTimer()
for i := 0; i < b.N; i++ {
var sb strings.Builder
for _, input := range policyInputs {
fmt.Fprintln(&sb, XXHash64sum(input))
}
_ = XXHash64sum(sb.String())
}
}
// Tests that xxhash doesn't have collisions in realistic scenarios
func TestHashCollisions(t *testing.T) {
allInputs := append(append(append(append(policyInputs, challengeInputs...), botRuleInputs...), celInputs...), asnInputs...)
// Start with realistic inputs from actual usage
xxhashHashes := make(map[string]string)
for _, input := range allInputs {
hash := XXHash64sum(input)
if existing, exists := xxhashHashes[hash]; exists {
t.Errorf("XXHash collision detected: %q and %q both hash to %s", input, existing, hash)
}
xxhashHashes[hash] = input
}
t.Logf("Basic test: %d realistic inputs, no collisions", len(allInputs))
// Test similar strings that might cause hash collisions
prefixes := []string{"User-Agent: ", "X-Real-IP: ", "Accept-Language: ", "Host: "}
suffixes := []string{"bot", "crawler", "spider", "scraper", "Mozilla", "Chrome", "Safari", "Firefox"}
variations := []string{"", "/1.0", "/2.0", " (compatible)", " (Windows)", " (Linux)", " (Mac)"}
stressCount := 0
for _, prefix := range prefixes {
for _, suffix := range suffixes {
for _, variation := range variations {
for i := 0; i < 100; i++ {
input := fmt.Sprintf("%s%s%s-%d", prefix, suffix, variation, i)
hash := XXHash64sum(input)
if existing, exists := xxhashHashes[hash]; exists {
t.Errorf("XXHash collision in stress test: %q and %q both hash to %s", input, existing, hash)
}
xxhashHashes[hash] = input
stressCount++
}
}
}
}
t.Logf("Stress test 1: %d similar string variations, no collisions", stressCount)
// Test sequential patterns that might be problematic
patterns := []string{
"192.168.1.%d",
"10.0.0.%d",
"172.16.%d.1",
"challenge-%d",
"bot-rule-%d",
"policy-%016x",
"session-%016x",
}
seqCount := 0
for _, pattern := range patterns {
for i := 0; i < 10000; i++ {
input := fmt.Sprintf(pattern, i)
hash := XXHash64sum(input)
if existing, exists := xxhashHashes[hash]; exists {
t.Errorf("XXHash collision in sequential test: %q and %q both hash to %s", input, existing, hash)
}
xxhashHashes[hash] = input
seqCount++
}
}
t.Logf("Stress test 2: %d sequential patterns, no collisions", seqCount)
totalInputs := len(allInputs) + stressCount + seqCount
t.Logf("TOTAL: Tested %d inputs across realistic scenarios - NO COLLISIONS", totalInputs)
}
// Verify xxhash output works as cache keys
func TestXXHashFormat(t *testing.T) {
testCases := []string{
"short",
"",
"very long string with lots of content that might be used in policy checking and other internal hashing scenarios",
"User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
}
for _, input := range testCases {
hash := XXHash64sum(input)
// Check it's valid hex
if len(hash) == 0 {
t.Errorf("Empty hash for input %q", input)
}
// xxhash is 64-bit so max 16 hex chars
if len(hash) > 16 {
t.Errorf("Hash too long for input %q: %s (length %d)", input, hash, len(hash))
}
// Make sure it's all hex characters
for _, char := range hash {
if !((char >= '0' && char <= '9') || (char >= 'a' && char <= 'f')) {
t.Errorf("Non-hex character %c in hash %s for input %q", char, hash, input)
}
}
t.Logf("Input: %q -> Hash: %s", input, hash)
}
}

View File

@@ -13,10 +13,6 @@ func (c *OGTagCache) GetOGTags(url *url.URL, originalHost string) (map[string]st
return nil, errors.New("nil URL provided, cannot fetch OG tags")
}
if len(c.ogOverride) != 0 {
return c.ogOverride, nil
}
target := c.getTarget(url)
cacheKey := c.generateCacheKey(target, originalHost)

View File

@@ -7,49 +7,10 @@ import (
"reflect"
"testing"
"time"
"github.com/TecharoHQ/anubis/lib/policy/config"
)
func TestCacheReturnsDefault(t *testing.T) {
want := map[string]string{
"og:title": "Foo bar",
"og:description": "The best website ever made!!!1!",
}
cache := NewOGTagCache("", config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: false,
Override: want,
})
u, err := url.Parse("https://anubis.techaro.lol")
if err != nil {
t.Fatal(err)
}
result, err := cache.GetOGTags(u, "anubis.techaro.lol")
if err != nil {
t.Fatal(err)
}
for k, v := range want {
t.Run(k, func(t *testing.T) {
if got := result[k]; got != v {
t.Logf("want: tags[%q] = %q", k, v)
t.Logf("got: tags[%q] = %q", k, got)
t.Error("invalid result from function")
}
})
}
}
func TestCheckCache(t *testing.T) {
cache := NewOGTagCache("http://example.com", config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: false,
})
cache := NewOGTagCache("http://example.com", true, time.Minute, false)
// Set up test data
urlStr := "http://example.com/page"
@@ -108,11 +69,7 @@ func TestGetOGTags(t *testing.T) {
defer ts.Close()
// Create an instance of OGTagCache with a short TTL for testing
cache := NewOGTagCache(ts.URL, config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: false,
})
cache := NewOGTagCache(ts.URL, true, 1*time.Minute, false)
// Parse the test server URL
parsedURL, err := url.Parse(ts.URL)
@@ -259,11 +216,7 @@ func TestGetOGTagsWithHostConsideration(t *testing.T) {
for _, tc := range testCases {
t.Run(tc.name, func(t *testing.T) {
loadCount = 0 // Reset load count for each test case
cache := NewOGTagCache(ts.URL, config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: tc.ogCacheConsiderHost,
})
cache := NewOGTagCache(ts.URL, true, 1*time.Minute, tc.ogCacheConsiderHost)
for i, req := range tc.requests {
ogTags, err := cache.GetOGTags(parsedURL, req.host)

View File

@@ -10,7 +10,6 @@ import (
"testing"
"time"
"github.com/TecharoHQ/anubis/lib/policy/config"
"golang.org/x/net/html"
)
@@ -81,11 +80,7 @@ func TestFetchHTMLDocument(t *testing.T) {
}))
defer ts.Close()
cache := NewOGTagCache("", config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: false,
})
cache := NewOGTagCache("", true, time.Minute, false)
doc, err := cache.fetchHTMLDocument(ts.URL, "anything")
if tt.expectError {
@@ -112,11 +107,7 @@ func TestFetchHTMLDocumentInvalidURL(t *testing.T) {
t.Skip("test requires theoretical network egress")
}
cache := NewOGTagCache("", config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: false,
})
cache := NewOGTagCache("", true, time.Minute, false)
doc, err := cache.fetchHTMLDocument("http://invalid.url.that.doesnt.exist.example", "anything")

View File

@@ -6,8 +6,6 @@ import (
"net/url"
"testing"
"time"
"github.com/TecharoHQ/anubis/lib/policy/config"
)
func TestIntegrationGetOGTags(t *testing.T) {
@@ -106,11 +104,7 @@ func TestIntegrationGetOGTags(t *testing.T) {
for _, tc := range testCases {
t.Run(tc.name, func(t *testing.T) {
// Create cache instance
cache := NewOGTagCache(ts.URL, config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: false,
})
cache := NewOGTagCache(ts.URL, true, 1*time.Minute, false)
// Create URL for test
testURL, _ := url.Parse(ts.URL)

View File

@@ -1,150 +0,0 @@
package ogtags
import (
"net/url"
"runtime"
"strings"
"testing"
"github.com/TecharoHQ/anubis/lib/policy/config"
"golang.org/x/net/html"
)
func BenchmarkGetTarget(b *testing.B) {
tests := []struct {
name string
target string
paths []string
}{
{
name: "HTTP",
target: "http://example.com",
paths: []string{"/", "/path", "/path/to/resource", "/path?query=1&foo=bar"},
},
{
name: "Unix",
target: "unix:///var/run/app.sock",
paths: []string{"/", "/api/endpoint", "/api/endpoint?param=value"},
},
}
for _, tt := range tests {
b.Run(tt.name, func(b *testing.B) {
cache := NewOGTagCache(tt.target, config.OpenGraph{})
urls := make([]*url.URL, len(tt.paths))
for i, path := range tt.paths {
u, _ := url.Parse(path)
urls[i] = u
}
b.ResetTimer()
b.ReportAllocs()
for i := 0; i < b.N; i++ {
_ = cache.getTarget(urls[i%len(urls)])
}
})
}
}
func BenchmarkExtractOGTags(b *testing.B) {
htmlSamples := []string{
`<html><head>
<meta property="og:title" content="Test Title">
<meta property="og:description" content="Test Description">
<meta name="keywords" content="test,keywords">
</head><body></body></html>`,
`<html><head>
<meta property="og:title" content="Page Title">
<meta property="og:type" content="website">
<meta property="og:url" content="https://example.com">
<meta property="og:image" content="https://example.com/image.jpg">
<meta property="twitter:card" content="summary_large_image">
<meta property="twitter:title" content="Twitter Title">
<meta name="description" content="Page description">
<meta name="author" content="John Doe">
</head><body><div><p>Content</p></div></body></html>`,
}
cache := NewOGTagCache("http://example.com", config.OpenGraph{})
docs := make([]*html.Node, len(htmlSamples))
for i, sample := range htmlSamples {
doc, _ := html.Parse(strings.NewReader(sample))
docs[i] = doc
}
b.ResetTimer()
b.ReportAllocs()
for i := 0; i < b.N; i++ {
_ = cache.extractOGTags(docs[i%len(docs)])
}
}
// Memory usage test
func TestMemoryUsage(t *testing.T) {
cache := NewOGTagCache("http://example.com", config.OpenGraph{})
// Force GC and wait for it to complete
runtime.GC()
var m1 runtime.MemStats
runtime.ReadMemStats(&m1)
// Run getTarget many times
u, _ := url.Parse("/path/to/resource?query=1&foo=bar&baz=qux")
for i := 0; i < 10000; i++ {
_ = cache.getTarget(u)
}
// Force GC after operations
runtime.GC()
var m2 runtime.MemStats
runtime.ReadMemStats(&m2)
allocatedBytes := int64(m2.TotalAlloc) - int64(m1.TotalAlloc)
allocatedKB := float64(allocatedBytes) / 1024.0
allocatedPerOp := float64(allocatedBytes) / 10000.0
t.Logf("Memory allocated for 10k getTarget calls:")
t.Logf(" Total: %.2f KB (%.2f MB)", allocatedKB, allocatedKB/1024.0)
t.Logf(" Per operation: %.2f bytes", allocatedPerOp)
// Test extractOGTags memory usage
htmlDoc := `<html><head>
<meta property="og:title" content="Test Title">
<meta property="og:description" content="Test Description">
<meta property="og:image" content="https://example.com/image.jpg">
<meta property="twitter:card" content="summary">
<meta name="keywords" content="test,keywords,example">
<meta name="author" content="Test Author">
<meta property="unknown:tag" content="Should be ignored">
</head><body></body></html>`
doc, _ := html.Parse(strings.NewReader(htmlDoc))
runtime.GC()
runtime.ReadMemStats(&m1)
for i := 0; i < 1000; i++ {
_ = cache.extractOGTags(doc)
}
runtime.GC()
runtime.ReadMemStats(&m2)
allocatedBytes = int64(m2.TotalAlloc) - int64(m1.TotalAlloc)
allocatedKB = float64(allocatedBytes) / 1024.0
allocatedPerOp = float64(allocatedBytes) / 1000.0
t.Logf("Memory allocated for 1k extractOGTags calls:")
t.Logf(" Total: %.2f KB (%.2f MB)", allocatedKB, allocatedKB/1024.0)
t.Logf(" Per operation: %.2f bytes", allocatedPerOp)
// Sanity checks
if allocatedPerOp > 10000 {
t.Errorf("extractOGTags allocating too much memory per operation: %.2f bytes", allocatedPerOp)
}
}

View File

@@ -10,34 +10,27 @@ import (
"time"
"github.com/TecharoHQ/anubis/decaymap"
"github.com/TecharoHQ/anubis/lib/policy/config"
)
const (
maxContentLength = 8 << 20 // 8 MiB is enough for anyone
maxContentLength = 16 << 20 // 16 MiB in bytes, if there is a reasonable reason that you need more than this...Why?
httpTimeout = 5 * time.Second /*todo: make this configurable?*/
schemeSeparatorLength = 3 // Length of "://"
querySeparatorLength = 1 // Length of "?" for query strings
)
type OGTagCache struct {
cache *decaymap.Impl[string, map[string]string]
targetURL *url.URL
client *http.Client
// Pre-built strings for optimization
unixPrefix string // "http://unix"
cache *decaymap.Impl[string, map[string]string]
targetURL *url.URL
client *http.Client
approvedTags []string
approvedPrefixes []string
ogTimeToLive time.Duration
ogCacheConsiderHost bool
ogPassthrough bool
ogOverride map[string]string
}
func NewOGTagCache(target string, conf config.OpenGraph) *OGTagCache {
func NewOGTagCache(target string, ogPassthrough bool, ogTimeToLive time.Duration, ogTagsConsiderHost bool) *OGTagCache {
// Predefined approved tags and prefixes
// In the future, these could come from configuration
defaultApprovedTags := []string{"description", "keywords", "author"}
defaultApprovedPrefixes := []string{"og:", "twitter:", "fediverse:"}
@@ -78,51 +71,37 @@ func NewOGTagCache(target string, conf config.OpenGraph) *OGTagCache {
return &OGTagCache{
cache: decaymap.New[string, map[string]string](),
targetURL: parsedTargetURL,
ogPassthrough: conf.Enabled,
ogTimeToLive: conf.TimeToLive,
ogCacheConsiderHost: conf.ConsiderHost,
ogOverride: conf.Override,
targetURL: parsedTargetURL, // Store the parsed URL
ogPassthrough: ogPassthrough,
ogTimeToLive: ogTimeToLive,
ogCacheConsiderHost: ogTagsConsiderHost, // todo: refactor to be a separate struct
approvedTags: defaultApprovedTags,
approvedPrefixes: defaultApprovedPrefixes,
client: client,
unixPrefix: "http://unix",
}
}
// getTarget constructs the target URL string for fetching OG tags.
// Optimized to minimize allocations by building strings directly.
// For Unix sockets, it creates a "fake" HTTP URL that the custom dialer understands.
func (c *OGTagCache) getTarget(u *url.URL) string {
var escapedPath = u.EscapedPath() // will cause an allocation if path contains special characters
if c.targetURL.Scheme == "unix" {
// Build URL string directly without creating intermediate URL object
var sb strings.Builder
sb.Grow(len(c.unixPrefix) + len(escapedPath) + len(u.RawQuery) + querySeparatorLength) // Pre-allocate
sb.WriteString(c.unixPrefix)
sb.WriteString(escapedPath)
if u.RawQuery != "" {
sb.WriteByte('?')
sb.WriteString(u.RawQuery)
// The custom dialer ignores the host, but we need a valid http URL structure.
// Use "unix" as a placeholder host. Path and Query from original request are appended.
fakeURL := &url.URL{
Scheme: "http", // Scheme must be http/https for client.Get
Host: "unix", // Arbitrary host, ignored by custom dialer
Path: u.Path,
RawQuery: u.RawQuery,
}
return sb.String()
return fakeURL.String()
}
// For regular http/https targets, build URL string directly
var sb strings.Builder
// Pre-calculate size: scheme + "://" + host + path + "?" + query
estimatedSize := len(c.targetURL.Scheme) + schemeSeparatorLength + len(c.targetURL.Host) + len(escapedPath) + len(u.RawQuery) + querySeparatorLength
sb.Grow(estimatedSize)
// For regular http/https targets
target := *c.targetURL // Make a copy
target.Path = u.Path
target.RawQuery = u.RawQuery
return target.String()
sb.WriteString(c.targetURL.Scheme)
sb.WriteString("://")
sb.WriteString(c.targetURL.Host)
sb.WriteString(escapedPath)
if u.RawQuery != "" {
sb.WriteByte('?')
sb.WriteString(u.RawQuery)
}
return sb.String()
}
func (c *OGTagCache) Cleanup() {

View File

@@ -1,310 +0,0 @@
package ogtags
import (
"net/url"
"strings"
"testing"
"unicode/utf8"
"github.com/TecharoHQ/anubis/lib/policy/config"
"golang.org/x/net/html"
)
// FuzzGetTarget tests getTarget with various inputs
func FuzzGetTarget(f *testing.F) {
// Seed corpus with interesting test cases
testCases := []struct {
target string
path string
query string
}{
{"http://example.com", "/", ""},
{"http://example.com", "/path", "q=1"},
{"unix:///tmp/socket", "/api", "key=value"},
{"https://example.com:8080", "/path/to/resource", "a=1&b=2"},
{"http://example.com", "/path with spaces", "q=hello world"},
{"http://example.com", "/path/❤️/emoji", "emoji=🎉"},
{"http://example.com", "/path/../../../etc/passwd", ""},
{"http://example.com", "/path%2F%2E%2E%2F", "q=%3Cscript%3E"},
{"unix:///var/run/app.sock", "/../../etc/passwd", ""},
{"http://[::1]:8080", "/ipv6", "test=1"},
{"http://example.com", strings.Repeat("/very/long/path", 100), strings.Repeat("param=value&", 100)},
{"http://example.com", "/path%20with%20encoded", "q=%20encoded%20"},
{"http://example.com", "/пример/кириллица", "q=тест"},
{"http://example.com", "/中文/路径", "查询=值"},
{"", "/path", "q=1"}, // Empty target
}
for _, tc := range testCases {
f.Add(tc.target, tc.path, tc.query)
}
f.Fuzz(func(t *testing.T, target, path, query string) {
// Skip invalid UTF-8 to focus on realistic inputs
if !utf8.ValidString(target) || !utf8.ValidString(path) || !utf8.ValidString(query) {
t.Skip()
}
// Create cache - should not panic
cache := NewOGTagCache(target, config.OpenGraph{})
// Create URL
u := &url.URL{
Path: path,
RawQuery: query,
}
// Call getTarget - should not panic
result := cache.getTarget(u)
// Basic validation
if result == "" {
t.Errorf("getTarget returned empty string for target=%q, path=%q, query=%q", target, path, query)
}
// Verify result is a valid URL (for non-empty targets)
if target != "" {
parsedResult, err := url.Parse(result)
if err != nil {
t.Errorf("getTarget produced invalid URL %q: %v", result, err)
} else {
// For unix sockets, verify the scheme is http
if strings.HasPrefix(target, "unix:") && parsedResult.Scheme != "http" {
t.Errorf("Unix socket URL should have http scheme, got %q", parsedResult.Scheme)
}
}
}
// Ensure no memory corruption by calling multiple times
for i := 0; i < 3; i++ {
result2 := cache.getTarget(u)
if result != result2 {
t.Errorf("getTarget not deterministic: %q != %q", result, result2)
}
}
})
}
// FuzzExtractOGTags tests extractOGTags with various HTML inputs
func FuzzExtractOGTags(f *testing.F) {
// Seed corpus with interesting HTML cases
htmlCases := []string{
`<html><head><meta property="og:title" content="Test"></head></html>`,
`<meta property="og:title" content="No HTML tags">`,
`<html><head>` + strings.Repeat(`<meta property="og:title" content="Many tags">`, 1000) + `</head></html>`,
`<html><head><meta property="og:title" content="<script>alert('xss')</script>"></head></html>`,
`<html><head><meta property="og:title" content="Line1&#10;Line2"></head></html>`,
`<html><head><meta property="og:emoji" content="❤️🎉🎊"></head></html>`,
`<html><head><meta property="og:title" content="` + strings.Repeat("A", 10000) + `"></head></html>`,
`<html><head><meta property="og:title" content='Single quotes'></head></html>`,
`<html><head><meta property=og:title content=no-quotes></head></html>`,
`<html><head><meta name="keywords" content="test,keywords"></head></html>`,
`<html><head><meta property="unknown:tag" content="Should be ignored"></head></html>`,
`<html><head><meta property="` + strings.Repeat("og:", 100) + `title" content="Nested prefixes"></head></html>`,
`<html>` + strings.Repeat(`<div>`, 1000) + `<meta property="og:title" content="Deep nesting">` + strings.Repeat(`</div>`, 1000) + `</html>`,
`<!DOCTYPE html><html xmlns="http://www.w3.org/1999/xhtml"><head><meta property="og:title" content="With doctype"/></head></html>`,
`<html><head><meta property="" content="Empty property"></head></html>`,
`<html><head><meta content="Content only"></head></html>`,
`<html><head><meta property="og:title"></head></html>`, // No content
``, // Empty HTML
`<html><head><meta property="og:title" content="Кириллица"></head></html>`,
`<html><head><meta property="og:title" content="中文内容"></head></html>`,
`<html><head><!--<meta property="og:title" content="Commented out">--></head></html>`,
`<html><head><META PROPERTY="OG:TITLE" CONTENT="UPPERCASE"></head></html>`,
}
for _, htmlc := range htmlCases {
f.Add(htmlc)
}
f.Fuzz(func(t *testing.T, htmlContent string) {
// Skip invalid UTF-8
if !utf8.ValidString(htmlContent) {
t.Skip()
}
// Parse HTML - may fail on invalid input
doc, err := html.Parse(strings.NewReader(htmlContent))
if err != nil {
// This is expected for malformed HTML
return
}
cache := NewOGTagCache("http://example.com", config.OpenGraph{})
// Should not panic
tags := cache.extractOGTags(doc)
// Validate results
for property, content := range tags {
// Ensure property is approved
approved := false
for _, prefix := range cache.approvedPrefixes {
if strings.HasPrefix(property, prefix) {
approved = true
break
}
}
if !approved {
for _, tag := range cache.approvedTags {
if property == tag {
approved = true
break
}
}
}
if !approved {
t.Errorf("Unapproved property %q was extracted", property)
}
// Ensure content is valid string
if !utf8.ValidString(content) {
t.Errorf("Invalid UTF-8 in content for property %q", property)
}
}
// Test determinism
tags2 := cache.extractOGTags(doc)
if len(tags) != len(tags2) {
t.Errorf("extractOGTags not deterministic: different lengths %d != %d", len(tags), len(tags2))
}
for k, v := range tags {
if tags2[k] != v {
t.Errorf("extractOGTags not deterministic: %q=%q != %q=%q", k, v, k, tags2[k])
}
}
})
}
// FuzzGetTargetRoundTrip tests that getTarget produces valid URLs that can be parsed back
func FuzzGetTargetRoundTrip(f *testing.F) {
f.Add("http://example.com", "/path/to/resource", "key=value&foo=bar")
f.Add("unix:///tmp/socket", "/api/endpoint", "param=test")
f.Fuzz(func(t *testing.T, target, path, query string) {
if !utf8.ValidString(target) || !utf8.ValidString(path) || !utf8.ValidString(query) {
t.Skip()
}
cache := NewOGTagCache(target, config.OpenGraph{})
u := &url.URL{Path: path, RawQuery: query}
result := cache.getTarget(u)
if result == "" {
return
}
// Parse the result back
parsed, err := url.Parse(result)
if err != nil {
t.Errorf("getTarget produced unparseable URL: %v", err)
return
}
// For non-unix targets, verify path preservation (accounting for encoding)
if !strings.HasPrefix(target, "unix:") && target != "" {
// The paths should match after normalization
expectedPath := u.EscapedPath()
if parsed.EscapedPath() != expectedPath {
t.Errorf("Path not preserved: want %q, got %q", expectedPath, parsed.EscapedPath())
}
// Query should be preserved exactly
if parsed.RawQuery != query {
t.Errorf("Query not preserved: want %q, got %q", query, parsed.RawQuery)
}
}
})
}
// FuzzExtractMetaTagInfo tests the extractMetaTagInfo function directly
func FuzzExtractMetaTagInfo(f *testing.F) {
// Seed with various attribute combinations
f.Add("og:title", "Test Title", "property")
f.Add("keywords", "test,keywords", "name")
f.Add("og:description", "A description with \"quotes\"", "property")
f.Add("twitter:card", "summary", "property")
f.Add("unknown:tag", "Should be filtered", "property")
f.Add("", "Content without property", "property")
f.Add("og:title", "", "property") // Property without content
f.Fuzz(func(t *testing.T, propertyValue, contentValue, propertyKey string) {
if !utf8.ValidString(propertyValue) || !utf8.ValidString(contentValue) || !utf8.ValidString(propertyKey) {
t.Skip()
}
// Create a meta node
node := &html.Node{
Type: html.ElementNode,
Data: "meta",
Attr: []html.Attribute{
{Key: propertyKey, Val: propertyValue},
{Key: "content", Val: contentValue},
},
}
cache := NewOGTagCache("http://example.com", config.OpenGraph{})
// Should not panic
property, content := cache.extractMetaTagInfo(node)
// If property is returned, it must be approved
if property != "" {
approved := false
for _, prefix := range cache.approvedPrefixes {
if strings.HasPrefix(property, prefix) {
approved = true
break
}
}
if !approved {
for _, tag := range cache.approvedTags {
if property == tag {
approved = true
break
}
}
}
if !approved {
t.Errorf("extractMetaTagInfo returned unapproved property: %q", property)
}
}
// Content should match input if property is approved
if property != "" && content != contentValue {
t.Errorf("Content mismatch: want %q, got %q", contentValue, content)
}
})
}
// Benchmark comparison for the fuzzed scenarios
func BenchmarkFuzzedGetTarget(b *testing.B) {
// Test with various challenging inputs found during fuzzing
inputs := []struct {
name string
target string
path string
query string
}{
{"Simple", "http://example.com", "/api", "k=v"},
{"LongPath", "http://example.com", strings.Repeat("/segment", 50), ""},
{"LongQuery", "http://example.com", "/", strings.Repeat("param=value&", 50)},
{"Unicode", "http://example.com", "/путь/路径/path", "q=значение"},
{"Encoded", "http://example.com", "/path%20with%20spaces", "q=%3Cscript%3E"},
{"Unix", "unix:///tmp/socket.sock", "/api/v1/resource", "id=123&format=json"},
}
for _, input := range inputs {
b.Run(input.name, func(b *testing.B) {
cache := NewOGTagCache(input.target, config.OpenGraph{})
u := &url.URL{Path: input.path, RawQuery: input.query}
b.ResetTimer()
b.ReportAllocs()
for i := 0; i < b.N; i++ {
_ = cache.getTarget(u)
}
})
}
}

View File

@@ -13,8 +13,6 @@ import (
"strings"
"testing"
"time"
"github.com/TecharoHQ/anubis/lib/policy/config"
)
func TestNewOGTagCache(t *testing.T) {
@@ -40,11 +38,7 @@ func TestNewOGTagCache(t *testing.T) {
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
cache := NewOGTagCache(tt.target, config.OpenGraph{
Enabled: tt.ogPassthrough,
TimeToLive: tt.ogTimeToLive,
ConsiderHost: false,
})
cache := NewOGTagCache(tt.target, tt.ogPassthrough, tt.ogTimeToLive, false)
if cache == nil {
t.Fatal("expected non-nil cache, got nil")
@@ -80,11 +74,7 @@ func TestNewOGTagCache_UnixSocket(t *testing.T) {
socketPath := filepath.Join(tempDir, "test.sock")
target := "unix://" + socketPath
cache := NewOGTagCache(target, config.OpenGraph{
Enabled: true,
TimeToLive: 5 * time.Minute,
ConsiderHost: false,
})
cache := NewOGTagCache(target, true, 5*time.Minute, false)
if cache == nil {
t.Fatal("expected non-nil cache, got nil")
@@ -165,11 +155,7 @@ func TestGetTarget(t *testing.T) {
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
cache := NewOGTagCache(tt.target, config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: false,
})
cache := NewOGTagCache(tt.target, false, time.Minute, false)
u := &url.URL{
Path: tt.path,
@@ -189,9 +175,7 @@ func TestGetTarget(t *testing.T) {
func TestIntegrationGetOGTags_UnixSocket(t *testing.T) {
tempDir := t.TempDir()
// XXX(Xe): if this is named longer, macOS fails with `bind: invalid argument`
// because the unix socket path is too long. I love computers.
socketPath := filepath.Join(tempDir, "t")
socketPath := filepath.Join(tempDir, "anubis-test.sock")
// Ensure the socket does not exist initially
_ = os.Remove(socketPath)
@@ -238,11 +222,7 @@ func TestIntegrationGetOGTags_UnixSocket(t *testing.T) {
// Create cache instance pointing to the Unix socket
targetURL := "unix://" + socketPath
cache := NewOGTagCache(targetURL, config.OpenGraph{
Enabled: true,
TimeToLive: time.Minute,
ConsiderHost: false,
})
cache := NewOGTagCache(targetURL, true, 1*time.Minute, false)
// Create a dummy URL for the request (path and query matter)
testReqURL, _ := url.Parse("/some/page?query=1")

View File

@@ -12,12 +12,15 @@ func (c *OGTagCache) extractOGTags(doc *html.Node) map[string]string {
var traverseNodes func(*html.Node)
traverseNodes = func(n *html.Node) {
// isOGMetaTag only checks if it's a <meta> tag.
// The actual filtering happens in extractMetaTagInfo now.
if isOGMetaTag(n) {
property, content := c.extractMetaTagInfo(n)
if property != "" {
ogTags[property] = content
}
}
for child := n.FirstChild; child != nil; child = child.NextSibling {
traverseNodes(child)
}
@@ -36,40 +39,43 @@ func isOGMetaTag(n *html.Node) bool {
}
// extractMetaTagInfo extracts property and content from a meta tag
// *and* checks if the property is approved.
// Returns empty property string if the tag is not approved.
func (c *OGTagCache) extractMetaTagInfo(n *html.Node) (property, content string) {
var propertyKey string
var rawProperty string // Store the property found before approval check
// Single pass through attributes, using range to avoid bounds checking
for _, attr := range n.Attr {
switch attr.Key {
case "property", "name":
propertyKey = attr.Val
case "content":
if attr.Key == "property" || attr.Key == "name" {
rawProperty = attr.Val
}
if attr.Key == "content" {
content = attr.Val
}
// Early exit if we have both
if propertyKey != "" && content != "" {
}
// Check if the rawProperty is approved
isApproved := false
for _, prefix := range c.approvedPrefixes {
if strings.HasPrefix(rawProperty, prefix) {
isApproved = true
break
}
}
if propertyKey == "" {
return "", content
}
// Check prefixes first (more common case)
for _, prefix := range c.approvedPrefixes {
if strings.HasPrefix(propertyKey, prefix) {
return propertyKey, content
// Check exact approved tags if not already approved by prefix
if !isApproved {
for _, tag := range c.approvedTags {
if rawProperty == tag {
isApproved = true
break
}
}
}
// Check exact matches
for _, tag := range c.approvedTags {
if propertyKey == tag {
return propertyKey, content
}
// Only return the property if it's approved
if isApproved {
property = rawProperty
}
return "", content
// Content is returned regardless, but property will be "" if not approved
return property, content
}

View File

@@ -6,18 +6,13 @@ import (
"testing"
"time"
"github.com/TecharoHQ/anubis/lib/policy/config"
"golang.org/x/net/html"
)
// TestExtractOGTags updated with correct expectations based on filtering logic
func TestExtractOGTags(t *testing.T) {
// Use a cache instance that reflects the default approved lists
testCache := NewOGTagCache("", config.OpenGraph{
Enabled: false,
ConsiderHost: false,
TimeToLive: time.Minute,
})
testCache := NewOGTagCache("", false, time.Minute, false)
// Manually set approved tags/prefixes based on the user request for clarity
testCache.approvedTags = []string{"description"}
testCache.approvedPrefixes = []string{"og:"}
@@ -194,11 +189,7 @@ func TestIsOGMetaTag(t *testing.T) {
func TestExtractMetaTagInfo(t *testing.T) {
// Use a cache instance that reflects the default approved lists
testCache := NewOGTagCache("", config.OpenGraph{
Enabled: false,
ConsiderHost: false,
TimeToLive: time.Minute,
})
testCache := NewOGTagCache("", false, time.Minute, false)
testCache.approvedTags = []string{"description"}
testCache.approvedPrefixes = []string{"og:"}

View File

@@ -595,7 +595,7 @@ func spawnAnubisWithOptions(t *testing.T, basePrefix string) string {
fmt.Fprintf(w, "<html><body><span id=anubis-test>%d</span></body></html>", time.Now().Unix())
})
policy, err := libanubis.LoadPoliciesOrDefault(t.Context(), "", anubis.DefaultDifficulty)
policy, err := libanubis.LoadPoliciesOrDefault("", anubis.DefaultDifficulty)
if err != nil {
t.Fatal(err)
}

View File

@@ -1,69 +0,0 @@
package thoth
import (
"context"
"errors"
"fmt"
"log/slog"
"net/http"
"strings"
"time"
"github.com/TecharoHQ/anubis/internal"
"github.com/TecharoHQ/anubis/lib/checker"
iptoasnv1 "github.com/TecharoHQ/thoth-proto/gen/techaro/thoth/iptoasn/v1"
)
func (c *Client) ASNCheckerFor(asns []uint32) checker.Impl {
asnMap := map[uint32]struct{}{}
var sb strings.Builder
fmt.Fprintln(&sb, "ASNChecker")
for _, asn := range asns {
asnMap[asn] = struct{}{}
fmt.Fprintln(&sb, "AS", asn)
}
return &ASNChecker{
iptoasn: c.IPToASN,
asns: asnMap,
hash: internal.FastHash(sb.String()),
}
}
type ASNChecker struct {
iptoasn iptoasnv1.IpToASNServiceClient
asns map[uint32]struct{}
hash string
}
func (asnc *ASNChecker) Check(r *http.Request) (bool, error) {
ctx, cancel := context.WithTimeout(r.Context(), 500*time.Millisecond)
defer cancel()
ipInfo, err := asnc.iptoasn.Lookup(ctx, &iptoasnv1.LookupRequest{
IpAddress: r.Header.Get("X-Real-Ip"),
})
if err != nil {
switch {
case errors.Is(err, context.DeadlineExceeded):
slog.Debug("error contacting thoth", "err", err, "actionable", false)
return false, nil
default:
slog.Error("error contacting thoth, please contact support", "err", err, "actionable", true)
return false, nil
}
}
// If IP is not publicly announced, return false
if !ipInfo.GetAnnounced() {
return false, nil
}
_, ok := asnc.asns[uint32(ipInfo.GetAsNumber())]
return ok, nil
}
func (asnc *ASNChecker) Hash() string {
return asnc.hash
}

View File

@@ -1,81 +0,0 @@
package thoth_test
import (
"fmt"
"net/http/httptest"
"testing"
"github.com/TecharoHQ/anubis/internal/thoth"
"github.com/TecharoHQ/anubis/lib/checker"
iptoasnv1 "github.com/TecharoHQ/thoth-proto/gen/techaro/thoth/iptoasn/v1"
)
var _ checker.Impl = &thoth.ASNChecker{}
func TestASNChecker(t *testing.T) {
cli := loadSecrets(t)
asnc := cli.ASNCheckerFor([]uint32{13335})
for _, cs := range []struct {
ipAddress string
wantMatch bool
wantError bool
}{
{
ipAddress: "1.1.1.1",
wantMatch: true,
wantError: false,
},
{
ipAddress: "2.2.2.2",
wantMatch: false,
wantError: false,
},
{
ipAddress: "taco",
wantMatch: false,
wantError: false,
},
{
ipAddress: "127.0.0.1",
wantMatch: false,
wantError: false,
},
} {
t.Run(fmt.Sprintf("%v", cs), func(t *testing.T) {
req := httptest.NewRequest("GET", "/", nil)
req.Header.Set("X-Real-Ip", cs.ipAddress)
match, err := asnc.Check(req)
if match != cs.wantMatch {
t.Errorf("Wanted match: %v, got: %v", cs.wantMatch, match)
}
switch {
case err != nil && !cs.wantError:
t.Errorf("Did not want error but got: %v", err)
case err == nil && cs.wantError:
t.Error("Wanted error but got none")
}
})
}
}
func BenchmarkWithCache(b *testing.B) {
cli := loadSecrets(b)
req := &iptoasnv1.LookupRequest{IpAddress: "1.1.1.1"}
_, err := cli.IPToASN.Lookup(b.Context(), req)
if err != nil {
b.Error(err)
}
for b.Loop() {
_, err := cli.IPToASN.Lookup(b.Context(), req)
if err != nil {
b.Error(err)
}
}
}

View File

@@ -1,39 +0,0 @@
package thoth
import (
"context"
"google.golang.org/grpc"
"google.golang.org/grpc/metadata"
)
func authUnaryClientInterceptor(token string) grpc.UnaryClientInterceptor {
return func(
ctx context.Context,
method string,
req interface{},
reply interface{},
cc *grpc.ClientConn,
invoker grpc.UnaryInvoker,
opts ...grpc.CallOption,
) error {
md := metadata.Pairs("authorization", "Bearer "+token)
ctx = metadata.NewOutgoingContext(ctx, md)
return invoker(ctx, method, req, reply, cc, opts...)
}
}
func authStreamClientInterceptor(token string) grpc.StreamClientInterceptor {
return func(
ctx context.Context,
desc *grpc.StreamDesc,
cc *grpc.ClientConn,
method string,
streamer grpc.Streamer,
opts ...grpc.CallOption,
) (grpc.ClientStream, error) {
md := metadata.Pairs("authorization", "Bearer "+token)
ctx = metadata.NewOutgoingContext(ctx, md)
return streamer(ctx, desc, cc, method, opts...)
}
}

View File

@@ -1,84 +0,0 @@
package thoth
import (
"context"
"errors"
"fmt"
"log/slog"
"net/netip"
iptoasnv1 "github.com/TecharoHQ/thoth-proto/gen/techaro/thoth/iptoasn/v1"
"github.com/gaissmai/bart"
"google.golang.org/grpc"
)
type IPToASNWithCache struct {
next iptoasnv1.IpToASNServiceClient
table *bart.Table[*iptoasnv1.LookupResponse]
}
func NewIpToASNWithCache(next iptoasnv1.IpToASNServiceClient) *IPToASNWithCache {
result := &IPToASNWithCache{
next: next,
table: &bart.Table[*iptoasnv1.LookupResponse]{},
}
for _, pfx := range []netip.Prefix{
netip.MustParsePrefix("10.0.0.0/8"), // RFC 1918
netip.MustParsePrefix("172.16.0.0/12"), // RFC 1918
netip.MustParsePrefix("192.168.0.0/16"), // RFC 1918
netip.MustParsePrefix("127.0.0.0/8"), // Loopback
netip.MustParsePrefix("169.254.0.0/16"), // Link-local
netip.MustParsePrefix("100.64.0.0/10"), // CGNAT
netip.MustParsePrefix("192.0.0.0/24"), // Protocol assignments
netip.MustParsePrefix("192.0.2.0/24"), // TEST-NET-1
netip.MustParsePrefix("198.18.0.0/15"), // Benchmarking
netip.MustParsePrefix("198.51.100.0/24"), // TEST-NET-2
netip.MustParsePrefix("203.0.113.0/24"), // TEST-NET-3
netip.MustParsePrefix("240.0.0.0/4"), // Reserved
netip.MustParsePrefix("255.255.255.255/32"), // Broadcast
netip.MustParsePrefix("fc00::/7"), // Unique local address
netip.MustParsePrefix("fe80::/10"), // Link-local
netip.MustParsePrefix("::1/128"), // Loopback
netip.MustParsePrefix("::/128"), // Unspecified
netip.MustParsePrefix("100::/64"), // Discard-only
netip.MustParsePrefix("2001:db8::/32"), // Documentation
} {
result.table.Insert(pfx, &iptoasnv1.LookupResponse{Announced: false})
}
return result
}
func (ip2asn *IPToASNWithCache) Lookup(ctx context.Context, lr *iptoasnv1.LookupRequest, opts ...grpc.CallOption) (*iptoasnv1.LookupResponse, error) {
addr, err := netip.ParseAddr(lr.GetIpAddress())
if err != nil {
return nil, fmt.Errorf("input is not an IP address: %w", err)
}
cachedResponse, ok := ip2asn.table.Lookup(addr)
if ok {
return cachedResponse, nil
}
resp, err := ip2asn.next.Lookup(ctx, lr, opts...)
if err != nil {
return nil, err
}
var errs []error
for _, cidr := range resp.GetCidr() {
pfx, err := netip.ParsePrefix(cidr)
if err != nil {
errs = append(errs, err)
continue
}
ip2asn.table.Insert(pfx, resp)
}
if len(errs) != 0 {
slog.Error("errors parsing IP prefixes", "err", errors.Join(errs...))
}
return resp, nil
}

View File

@@ -1,14 +0,0 @@
package thoth
import "context"
type ctxKey struct{}
func With(ctx context.Context, cli *Client) context.Context {
return context.WithValue(ctx, ctxKey{}, cli)
}
func FromContext(ctx context.Context) (*Client, bool) {
cli, ok := ctx.Value(ctxKey{}).(*Client)
return cli, ok
}

View File

@@ -1,68 +0,0 @@
package thoth
import (
"context"
"errors"
"fmt"
"log/slog"
"net/http"
"strings"
"time"
"github.com/TecharoHQ/anubis/lib/checker"
iptoasnv1 "github.com/TecharoHQ/thoth-proto/gen/techaro/thoth/iptoasn/v1"
)
func (c *Client) GeoIPCheckerFor(countries []string) checker.Impl {
countryMap := map[string]struct{}{}
var sb strings.Builder
fmt.Fprintln(&sb, "GeoIPChecker")
for _, cc := range countries {
countryMap[cc] = struct{}{}
fmt.Fprintln(&sb, cc)
}
return &GeoIPChecker{
IPToASN: c.IPToASN,
Countries: countryMap,
hash: sb.String(),
}
}
type GeoIPChecker struct {
IPToASN iptoasnv1.IpToASNServiceClient
Countries map[string]struct{}
hash string
}
func (gipc *GeoIPChecker) Check(r *http.Request) (bool, error) {
ctx, cancel := context.WithTimeout(r.Context(), 500*time.Millisecond)
defer cancel()
ipInfo, err := gipc.IPToASN.Lookup(ctx, &iptoasnv1.LookupRequest{
IpAddress: r.Header.Get("X-Real-Ip"),
})
if err != nil {
switch {
case errors.Is(err, context.DeadlineExceeded):
slog.Debug("error contacting thoth", "err", err, "actionable", false)
return false, nil
default:
slog.Error("error contacting thoth, please contact support", "err", err, "actionable", true)
return false, nil
}
}
// If IP is not publicly announced, return false
if !ipInfo.GetAnnounced() {
return false, nil
}
_, ok := gipc.Countries[strings.ToLower(ipInfo.GetCountryCode())]
return ok, nil
}
func (gipc *GeoIPChecker) Hash() string {
return gipc.hash
}

View File

@@ -1,63 +0,0 @@
package thoth_test
import (
"fmt"
"net/http/httptest"
"testing"
"github.com/TecharoHQ/anubis/internal/thoth"
"github.com/TecharoHQ/anubis/lib/checker"
)
var _ checker.Impl = &thoth.GeoIPChecker{}
func TestGeoIPChecker(t *testing.T) {
cli := loadSecrets(t)
asnc := cli.GeoIPCheckerFor([]string{"us"})
for _, cs := range []struct {
ipAddress string
wantMatch bool
wantError bool
}{
{
ipAddress: "1.1.1.1",
wantMatch: true,
wantError: false,
},
{
ipAddress: "2.2.2.2",
wantMatch: false,
wantError: false,
},
{
ipAddress: "taco",
wantMatch: false,
wantError: false,
},
{
ipAddress: "127.0.0.1",
wantMatch: false,
wantError: false,
},
} {
t.Run(fmt.Sprintf("%v", cs), func(t *testing.T) {
req := httptest.NewRequest("GET", "/", nil)
req.Header.Set("X-Real-Ip", cs.ipAddress)
match, err := asnc.Check(req)
if match != cs.wantMatch {
t.Errorf("Wanted match: %v, got: %v", cs.wantMatch, match)
}
switch {
case err != nil && !cs.wantError:
t.Errorf("Did not want error but got: %v", err)
case err == nil && cs.wantError:
t.Error("Wanted error but got none")
}
})
}
}

Some files were not shown because too many files have changed in this diff Show More