fork from codeberg.org

This commit is contained in:
“xHuPo” 2024-09-12 18:35:01 +08:00
commit 50a258ea59
67 changed files with 4587 additions and 0 deletions

9
.ecrc Normal file
View file

@ -0,0 +1,9 @@
{
"Exclude": [
".git",
"go.mod", "go.sum",
"vendor",
"LICENSE",
"_test.go"
]
}

17
.editorconfig Normal file
View file

@ -0,0 +1,17 @@
root = true
[*]
indent_style = space
indent_size = 2
tab_width = 2
end_of_line = lf
charset = utf-8
trim_trailing_whitespace = true
insert_final_newline = true
[*.go]
indent_style = tab
[*.md]
trim_trailing_whitespace = false
indent_size = 1

11
.env-dev Normal file
View file

@ -0,0 +1,11 @@
ACME_API=https://acme.mock.directory
ACME_ACCEPT_TERMS=true
PAGES_DOMAIN=localhost.mock.directory
RAW_DOMAIN=raw.localhost.mock.directory
PAGES_BRANCHES=pages,master,main
GITEA_ROOT=https://codeberg.org
PORT=4430
HTTP_PORT=8880
ENABLE_HTTP_SERVER=true
LOG_LEVEL=trace
ACME_ACCOUNT_CONFIG=integration/acme-account.json

10
.gitignore vendored Normal file
View file

@ -0,0 +1,10 @@
.idea/
.cache/
*.iml
key-database.pogreb/
acme-account.json
build/
vendor/
pages
certs.sqlite
.bash_history

34
.golangci.yml Normal file
View file

@ -0,0 +1,34 @@
linters-settings:
gocritic:
enabled-tags:
- diagnostic
- experimental
- opinionated
- performance
- style
disabled-checks:
- importShadow
- ifElseChain
- hugeParam
linters:
disable-all: true
enable:
- unconvert
- gocritic
- gofumpt
- bidichk
- errcheck
- gofmt
- goimports
- gosimple
- govet
- ineffassign
- misspell
- staticcheck
- typecheck
- unused
- whitespace
run:
timeout: 5m

8
.prettierrc.json Normal file
View file

@ -0,0 +1,8 @@
{
"semi": true,
"trailingComma": "all",
"singleQuote": true,
"printWidth": 120,
"tabWidth": 2,
"endOfLine": "lf"
}

19
.yamllint.yaml Normal file
View file

@ -0,0 +1,19 @@
extends: default
rules:
comments:
require-starting-space: false
ignore-shebangs: true
min-spaces-from-content: 1
braces:
min-spaces-inside: 1
max-spaces-inside: 1
document-start:
present: false
indentation:
spaces: 2
indent-sequences: true
line-length:
max: 256
new-lines:
type: unix

36
Dockerfile Normal file
View file

@ -0,0 +1,36 @@
# Set the default Go version as a build argument
ARG XGO="go-1.21.x"
# Use xgo (a Go cross-compiler tool) as build image
FROM --platform=$BUILDPLATFORM techknowlogick/xgo:${XGO} as build
# Set the working directory and copy the source code
WORKDIR /go/src/codeberg.org/codeberg/pages
COPY . /go/src/codeberg.org/codeberg/pages
# Set the target architecture (can be set using --build-arg), buildx set it automatically
ARG TARGETOS TARGETARCH
# Build the binary using xgo
RUN --mount=type=cache,target=/root/.cache/go-build \
--mount=type=cache,target=/go/pkg \
GOOS=${TARGETOS} GOARCH=${TARGETARCH} CGO_ENABLED=1 \
xgo -x -v --targets=${TARGETOS}/${TARGETARCH} -tags='sqlite sqlite_unlock_notify netgo' -ldflags='-s -w -extldflags "-static" -linkmode external' -out pages .
RUN mv -vf /build/pages-* /go/src/codeberg.org/codeberg/pages/pages
# Use a scratch image as the base image for the final container,
# which will contain only the built binary and the CA certificates
FROM scratch
# Copy the built binary and the CA certificates from the build container to the final container
COPY --from=build /go/src/codeberg.org/codeberg/pages/pages /pages
COPY --from=build \
/etc/ssl/certs/ca-certificates.crt \
/etc/ssl/certs/ca-certificates.crt
# Expose ports 80 and 443 for the built binary to listen on
EXPOSE 80/tcp
EXPOSE 443/tcp
# Set the entrypoint for the container to the built binary
ENTRYPOINT ["/pages"]

51
FEATURES.md Normal file
View file

@ -0,0 +1,51 @@
# Features
## Custom domains
Custom domains can be used by creating a `.domains` file with the domain name, e.g.:
```text
codeberg.page
```
You also have to set some DNS records, see the [Codeberg Documentation](https://docs.codeberg.org/codeberg-pages/using-custom-domain/).
## Redirects
Redirects can be created with a `_redirects` file with the following format:
```text
# Comment
from to [status]
```
- Lines starting with `#` are ignored
- `from` - the path to redirect from (Note: repository and branch names are removed from request URLs)
- `to` - the path or URL to redirect to
- `status` - status code to use when redirecting (default 301)
### Status codes
- `200` - returns content from specified path (no external URLs) without changing the URL (rewrite)
- `301` - Moved Permanently (Permanent redirect)
- `302` - Found (Temporary redirect)
### Examples
#### SPA (single-page application) rewrite
Redirects all paths to `/index.html` for single-page apps.
```text
/* /index.html 200
```
#### Splats
Redirects every path under `/articles` to `/posts` while keeping the path.
```text
/articles/* /posts/:splat 302
```
Example: `/articles/2022/10/12/post-1/` -> `/posts/2022/10/12/post-1/`

51
Justfile Normal file
View file

@ -0,0 +1,51 @@
CGO_FLAGS := '-extldflags "-static" -linkmode external'
TAGS := 'sqlite sqlite_unlock_notify netgo'
dev *FLAGS:
#!/usr/bin/env bash
set -euxo pipefail
set -a # automatically export all variables
source .env-dev
set +a
go run -tags '{{TAGS}}' . {{FLAGS}}
build:
CGO_ENABLED=1 go build -tags '{{TAGS}}' -ldflags '-s -w {{CGO_FLAGS}}' -v -o build/codeberg-pages-server ./
build-tag VERSION:
CGO_ENABLED=1 go build -tags '{{TAGS}}' -ldflags '-s -w -X "codeberg.org/codeberg/pages/server/version.Version={{VERSION}}" {{CGO_FLAGS}}' -v -o build/codeberg-pages-server ./
lint: tool-golangci tool-gofumpt
golangci-lint run --timeout 5m --build-tags integration
# TODO: run editorconfig-checker
fmt: tool-gofumpt
gofumpt -w --extra .
clean:
go clean ./...
tool-golangci:
@hash golangci-lint> /dev/null 2>&1; if [ $? -ne 0 ]; then \
go install github.com/golangci/golangci-lint/cmd/golangci-lint@latest; \
fi
tool-gofumpt:
@hash gofumpt> /dev/null 2>&1; if [ $? -ne 0 ]; then \
go install mvdan.cc/gofumpt@latest; \
fi
test:
go test -race -cover -tags '{{TAGS}}' codeberg.org/codeberg/pages/config/ codeberg.org/codeberg/pages/html/ codeberg.org/codeberg/pages/server/...
test-run TEST:
go test -race -tags '{{TAGS}}' -run "^{{TEST}}$" codeberg.org/codeberg/pages/config/ codeberg.org/codeberg/pages/html/ codeberg.org/codeberg/pages/server/...
integration:
go test -race -tags 'integration {{TAGS}}' codeberg.org/codeberg/pages/integration/...
integration-run TEST:
go test -race -tags 'integration {{TAGS}}' -run "^{{TEST}}$" codeberg.org/codeberg/pages/integration/...
docker:
docker run --rm -it --user $(id -u) -v $(pwd):/work --workdir /work -e HOME=/work codeberg.org/6543/docker-images/golang_just

305
LICENSE Normal file
View file

@ -0,0 +1,305 @@
European Union Public Licence v. 1.2
EUPL © the European Union 2007, 2016
This European Union Public Licence (the 'EUPL') applies to the Work (as defined
below) which is provided under the terms of this Licence. Any use of the Work,
other than as authorised under this Licence is prohibited (to the extent such
use is covered by a right of the copyright holder of the Work).
The Work is provided under the terms of this Licence when the Licensor (as
defined below) has placed the following notice immediately following the copyright
notice for the Work:
Licensed under the EUPL
or has expressed by any other means his willingness to license under the EUPL.
1. Definitions
In this Licence, the following terms have the following meaning:
— 'The Licence': this Licence.
— 'The Original Work': the work or software distributed or communicated by
the Licensor under this Licence, available as Source Code and also as Executable
Code as the case may be.
— 'Derivative Works': the works or software that could be created by the Licensee,
based upon the Original Work or modifications thereof. This Licence does not
define the extent of modification or dependence on the Original Work required
in order to classify a work as a Derivative Work; this extent is determined
by copyright law applicable in the country mentioned in Article 15.
— 'The Work': the Original Work or its Derivative Works.
— 'The Source Code': the human-readable form of the Work which is the most
convenient for people to study and modify.
— 'The Executable Code': any code which has generally been compiled and which
is meant to be interpreted by a computer as a program.
— 'The Licensor': the natural or legal person that distributes or communicates
the Work under the Licence.
— 'Contributor(s)': any natural or legal person who modifies the Work under
the Licence, or otherwise contributes to the creation of a Derivative Work.
— 'The Licensee' or 'You': any natural or legal person who makes any usage
of the Work under the terms of the Licence.
— 'Distribution' or 'Communication': any act of selling, giving, lending,
renting, distributing, communicating, transmitting, or otherwise making available,
online or offline, copies of the Work or providing access to its essential
functionalities at the disposal of any other natural or legal person.
2. Scope of the rights granted by the Licence
The Licensor hereby grants You a worldwide, royalty-free, non-exclusive, sublicensable
licence to do the following, for the duration of copyright vested in the Original
Work:
— use the Work in any circumstance and for all usage,
— reproduce the Work,
— modify the Work, and make Derivative Works based upon the Work,
— communicate to the public, including the right to make available or display
the Work or copies thereof to the public and perform publicly, as the case
may be, the Work,
— distribute the Work or copies thereof,
— lend and rent the Work or copies thereof,
— sublicense rights in the Work or copies thereof.
Those rights can be exercised on any media, supports and formats, whether
now known or later invented, as far as the applicable law permits so.
In the countries where moral rights apply, the Licensor waives his right to
exercise his moral right to the extent allowed by law in order to make effective
the licence of the economic rights here above listed.
The Licensor grants to the Licensee royalty-free, non-exclusive usage rights
to any patents held by the Licensor, to the extent necessary to make use of
the rights granted on the Work under this Licence.
3. Communication of the Source Code
The Licensor may provide the Work either in its Source Code form, or as Executable
Code. If the Work is provided as Executable Code, the Licensor provides in
addition a machine-readable copy of the Source Code of the Work along with
each copy of the Work that the Licensor distributes or indicates, in a notice
following the copyright notice attached to the Work, a repository where the
Source Code is easily and freely accessible for as long as the Licensor continues
to distribute or communicate the Work.
4. Limitations on copyright
Nothing in this Licence is intended to deprive the Licensee of the benefits
from any exception or limitation to the exclusive rights of the rights owners
in the Work, of the exhaustion of those rights or of other applicable limitations
thereto.
5. Obligations of the Licensee
The grant of the rights mentioned above is subject to some restrictions and
obligations imposed on the Licensee. Those obligations are the following:
Attribution right: The Licensee shall keep intact all copyright, patent or
trademarks notices and all notices that refer to the Licence and to the disclaimer
of warranties. The Licensee must include a copy of such notices and a copy
of the Licence with every copy of the Work he/she distributes or communicates.
The Licensee must cause any Derivative Work to carry prominent notices stating
that the Work has been modified and the date of modification.
Copyleft clause: If the Licensee distributes or communicates copies of the
Original Works or Derivative Works, this Distribution or Communication will
be done under the terms of this Licence or of a later version of this Licence
unless the Original Work is expressly distributed only under this version
of the Licence — for example by communicating 'EUPL v. 1.2 only'. The Licensee
(becoming Licensor) cannot offer or impose any additional terms or conditions
on the Work or Derivative Work that alter or restrict the terms of the Licence.
Compatibility clause: If the Licensee Distributes or Communicates Derivative
Works or copies thereof based upon both the Work and another work licensed
under a Compatible Licence, this Distribution or Communication can be done
under the terms of this Compatible Licence. For the sake of this clause, 'Compatible
Licence' refers to the licences listed in the appendix attached to this Licence.
Should the Licensee's obligations under the Compatible Licence conflict with
his/her obligations under this Licence, the obligations of the Compatible
Licence shall prevail.
Provision of Source Code: When distributing or communicating copies of the
Work, the Licensee will provide a machine-readable copy of the Source Code
or indicate a repository where this Source will be easily and freely available
for as long as the Licensee continues to distribute or communicate the Work.
Legal Protection: This Licence does not grant permission to use the trade
names, trademarks, service marks, or names of the Licensor, except as required
for reasonable and customary use in describing the origin of the Work and
reproducing the content of the copyright notice.
6. Chain of Authorship
The original Licensor warrants that the copyright in the Original Work granted
hereunder is owned by him/her or licensed to him/her and that he/she has the
power and authority to grant the Licence.
Each Contributor warrants that the copyright in the modifications he/she brings
to the Work are owned by him/her or licensed to him/her and that he/she has
the power and authority to grant the Licence.
Each time You accept the Licence, the original Licensor and subsequent Contributors
grant You a licence to their contributions to the Work, under the terms of
this Licence.
7. Disclaimer of Warranty
The Work is a work in progress, which is continuously improved by numerous
Contributors. It is not a finished work and may therefore contain defects
or 'bugs' inherent to this type of development.
For the above reason, the Work is provided under the Licence on an 'as is'
basis and without warranties of any kind concerning the Work, including without
limitation merchantability, fitness for a particular purpose, absence of defects
or errors, accuracy, non-infringement of intellectual property rights other
than copyright as stated in Article 6 of this Licence.
This disclaimer of warranty is an essential part of the Licence and a condition
for the grant of any rights to the Work.
8. Disclaimer of Liability
Except in the cases of wilful misconduct or damages directly caused to natural
persons, the Licensor will in no event be liable for any direct or indirect,
material or moral, damages of any kind, arising out of the Licence or of the
use of the Work, including without limitation, damages for loss of goodwill,
work stoppage, computer failure or malfunction, loss of data or any commercial
damage, even if the Licensor has been advised of the possibility of such damage.
However, the Licensor will be liable under statutory product liability laws
as far such laws apply to the Work.
9. Additional agreements
While distributing the Work, You may choose to conclude an additional agreement,
defining obligations or services consistent with this Licence. However, if
accepting obligations, You may act only on your own behalf and on your sole
responsibility, not on behalf of the original Licensor or any other Contributor,
and only if You agree to indemnify, defend, and hold each Contributor harmless
for any liability incurred by, or claims asserted against such Contributor
by the fact You have accepted any warranty or additional liability.
10. Acceptance of the Licence
The provisions of this Licence can be accepted by clicking on an icon 'I agree'
placed under the bottom of a window displaying the text of this Licence or
by affirming consent in any other similar way, in accordance with the rules
of applicable law. Clicking on that icon indicates your clear and irrevocable
acceptance of this Licence and all of its terms and conditions.
Similarly, you irrevocably accept this Licence and all of its terms and conditions
by exercising any rights granted to You by Article 2 of this Licence, such
as the use of the Work, the creation by You of a Derivative Work or the Distribution
or Communication by You of the Work or copies thereof.
11. Information to the public
In case of any Distribution or Communication of the Work by means of electronic
communication by You (for example, by offering to download the Work from a
remote location) the distribution channel or media (for example, a website)
must at least provide to the public the information requested by the applicable
law regarding the Licensor, the Licence and the way it may be accessible,
concluded, stored and reproduced by the Licensee.
12. Termination of the Licence
The Licence and the rights granted hereunder will terminate automatically
upon any breach by the Licensee of the terms of the Licence.
Such a termination will not terminate the licences of any person who has received
the Work from the Licensee under the Licence, provided such persons remain
in full compliance with the Licence.
13. Miscellaneous
Without prejudice of Article 9 above, the Licence represents the complete
agreement between the Parties as to the Work.
If any provision of the Licence is invalid or unenforceable under applicable
law, this will not affect the validity or enforceability of the Licence as
a whole. Such provision will be construed or reformed so as necessary to make
it valid and enforceable.
The European Commission may publish other linguistic versions or new versions
of this Licence or updated versions of the Appendix, so far this is required
and reasonable, without reducing the scope of the rights granted by the Licence.
New versions of the Licence will be published with a unique version number.
All linguistic versions of this Licence, approved by the European Commission,
have identical value. Parties can take advantage of the linguistic version
of their choice.
14. Jurisdiction
Without prejudice to specific agreement between parties,
— any litigation resulting from the interpretation of this License, arising
between the European Union institutions, bodies, offices or agencies, as a
Licensor, and any Licensee, will be subject to the jurisdiction of the Court
of Justice of the European Union, as laid down in article 272 of the Treaty
on the Functioning of the European Union,
— any litigation arising between other parties and resulting from the interpretation
of this License, will be subject to the exclusive jurisdiction of the competent
court where the Licensor resides or conducts its primary business.
15. Applicable Law
Without prejudice to specific agreement between parties,
— this Licence shall be governed by the law of the European Union Member State
where the Licensor has his seat, resides or has his registered office,
— this licence shall be governed by Belgian law if the Licensor has no seat,
residence or registered office inside a European Union Member State.
Appendix
'Compatible Licences' according to Article 5 EUPL are:
— GNU General Public License (GPL) v. 2, v. 3
— GNU Affero General Public License (AGPL) v. 3
— Open Software License (OSL) v. 2.1, v. 3.0
— Eclipse Public License (EPL) v. 1.0
— CeCILL v. 2.0, v. 2.1
— Mozilla Public Licence (MPL) v. 2
— GNU Lesser General Public Licence (LGPL) v. 2.1, v. 3
— Creative Commons Attribution-ShareAlike v. 3.0 Unported (CC BY-SA 3.0) for
works other than software
— European Union Public Licence (EUPL) v. 1.1, v. 1.2
— Québec Free and Open-Source Licence — Reciprocity (LiLiQ-R) or Strong Reciprocity
(LiLiQ-R+).
The European Commission may update this Appendix to later versions of the
above licences without producing a new version of the EUPL, as long as they
provide the rights granted in Article 2 of this Licence and protect the covered
Source Code from exclusive appropriation.
All other changes or additions to this Appendix require the production of
a new EUPL version.

141
README.md Normal file
View file

@ -0,0 +1,141 @@
# Codeberg Pages
[![License: EUPL-1.2](https://img.shields.io/badge/License-EUPL--1.2-blue)](https://opensource.org/license/eupl-1-2/)
[![status-badge](https://ci.codeberg.org/api/badges/Codeberg/pages-server/status.svg)](https://ci.codeberg.org/Codeberg/pages-server)
<a href="https://matrix.to/#/#gitea-pages-server:matrix.org" title="Join the Matrix room at https://matrix.to/#/#gitea-pages-server:matrix.org">
<img src="https://img.shields.io/matrix/gitea-pages-server:matrix.org?label=matrix">
</a>
Gitea lacks the ability to host static pages from Git.
The Codeberg Pages Server addresses this lack by implementing a standalone service
that connects to Gitea via API.
It is suitable to be deployed by other Gitea instances, too, to offer static pages hosting to their users.
**End user documentation** can mainly be found at the [Wiki](https://codeberg.org/Codeberg/pages-server/wiki/Overview)
and the [Codeberg Documentation](https://docs.codeberg.org/codeberg-pages/).
<a href="https://codeberg.org/Codeberg/pages-server"> <img src="https://codeberg.org/Codeberg/GetItOnCodeberg/raw/branch/main/get-it-on-blue-on-white.svg" alt="Get It On Codeberg" width="250"/> </a>
## Quickstart
This is the new Codeberg Pages server, a solution for serving static pages from Gitea repositories.
Mapping custom domains is not static anymore, but can be done with DNS:
1. add a `.domains` text file to your repository, containing the allowed domains, separated by new lines. The
first line will be the canonical domain/URL; all other occurrences will be redirected to it.
2. add a CNAME entry to your domain, pointing to `[[{branch}.]{repo}.]{owner}.codeberg.page` (repo defaults to
"pages", "branch" defaults to the default branch if "repo" is "pages", or to "pages" if "repo" is something else.
If the branch name contains slash characters, you need to replace "/" in the branch name to "~"):
`www.example.org. IN CNAME main.pages.example.codeberg.page.`
3. if a CNAME is set for "www.example.org", you can redirect there from the naked domain by adding an ALIAS record
for "example.org" (if your provider allows ALIAS or similar records, otherwise use A/AAAA), together with a TXT
record that points to your repo (just like the CNAME record):
`example.org IN ALIAS codeberg.page.`
`example.org IN TXT main.pages.example.codeberg.page.`
Certificates are generated, updated and cleaned up automatically via Let's Encrypt through a TLS challenge.
## Chat for admins & devs
[matrix: #gitea-pages-server:matrix.org](https://matrix.to/#/#gitea-pages-server:matrix.org)
## Deployment
**Warning: Some Caveats Apply**
> Currently, the deployment requires you to have some knowledge of system administration as well as understanding and building code,
> so you can eventually edit non-configurable and codeberg-specific settings.
> In the future, we'll try to reduce these and make hosting Codeberg Pages as easy as setting up Gitea.
> If you consider using Pages in practice, please consider contacting us first,
> we'll then try to share some basic steps and document the current usage for admins
> (might be changing in the current state).
Deploying the software itself is very easy. You can grab a current release binary or build yourself,
configure the environment as described below, and you are done.
The hard part is about adding **custom domain support** if you intend to use it.
SSL certificates (request + renewal) is automatically handled by the Pages Server,
but if you want to run it on a shared IP address (and not a standalone),
you'll need to configure your reverse proxy not to terminate the TLS connections,
but forward the requests on the IP level to the Pages Server.
You can check out a proof of concept in the `examples/haproxy-sni` folder,
and especially have a look at [this section of the haproxy.cfg](https://codeberg.org/Codeberg/pages-server/src/branch/main/examples/haproxy-sni/haproxy.cfg#L38).
If you want to test a change, you can open a PR and ask for the label `build_pr_image` to be added.
This will trigger a build of the PR which will build a docker image to be used for testing.
### Environment Variables
- `ACME_ACCEPT_TERMS` (default: use self-signed certificate): Set this to "true" to accept the Terms of Service of your ACME provider.
- `ACME_API` (default: <https://acme-v02.api.letsencrypt.org/directory>): set this to <https://acme.mock.directory> to use invalid certificates without any verification (great for debugging). ZeroSSL might be better in the future as it doesn't have rate limits and doesn't clash with the official Codeberg certificates (which are using Let's Encrypt), but I couldn't get it to work yet.
- `ACME_EAB_KID` & `ACME_EAB_HMAC` (default: don't use EAB): EAB credentials, for example for ZeroSSL.
- `ACME_EMAIL` (default: `noreply@example.email`): Set the email sent to the ACME API server to receive, for example, renewal reminders.
- `ACME_USE_RATE_LIMITS` (default: true): Set this to false to disable rate limits, e.g. with ZeroSSL.
- `DNS_PROVIDER` (default: use self-signed certificate): Code of the ACME DNS provider for the main domain wildcard. See <https://go-acme.github.io/lego/dns/> for available values & additional environment variables.
- `ENABLE_HTTP_SERVER` (default: false): Set this to true to enable the HTTP-01 challenge and redirect all other HTTP requests to HTTPS. Currently only works with port 80.
- `GITEA_API_TOKEN` (default: empty): API token for the Gitea instance to access non-public (e.g. limited) repos.
- `GITEA_ROOT` (default: `https://codeberg.org`): root of the upstream Gitea instance.
- `HOST` & `PORT` (default: `[::]` & `443`): listen address.
- `LOG_LEVEL` (default: warn): Set this to specify the level of logging.
- `NO_DNS_01` (default: `false`): Disable the use of ACME DNS. This means that the wildcard certificate is self-signed and all domains and subdomains will have a distinct certificate. Because this may lead to a rate limit from the ACME provider, this option is not recommended for Gitea/Forgejo instances with open registrations or a great number of users/orgs.
- `PAGES_DOMAIN` (default: `codeberg.page`): main domain for pages.
- `RAW_DOMAIN` (default: `raw.codeberg.page`): domain for raw resources (must be subdomain of `PAGES_DOMAIN`).
## Contributing to the development
The Codeberg team is very open to your contribution.
Since we are working nicely in a team, it might be hard at times to get started
(still check out the issues, we always aim to have some things to get you started).
If you have any questions, want to work on a feature or could imagine collaborating with us for some time,
feel free to ping us in an issue or in a general [Matrix chat room](#chat-for-admins--devs).
You can also contact the maintainer(s) of this project:
- [crapStone](https://codeberg.org/crapStone) [(Matrix)](https://matrix.to/#/@crapstone:obermui.de)
Previous maintainers:
- [momar](https://codeberg.org/momar) [(Matrix)](https://matrix.to/#/@moritz:wuks.space)
- [6543](https://codeberg.org/6543) [(Matrix)](https://matrix.to/#/@marddl:obermui.de)
### First steps
The code of this repository is split in several modules.
The [Architecture is explained](https://codeberg.org/Codeberg/pages-server/wiki/Architecture) in the wiki.
The `cmd` folder holds the data necessary for interacting with the service via the cli.
The heart of the software lives in the `server` folder and is split in several modules.
Again: Feel free to get in touch with us for any questions that might arise.
Thank you very much.
### Test Server
Make sure you have [golang](https://go.dev) v1.21 or newer and [just](https://just.systems/man/en/) installed.
run `just dev`
now these pages should work:
- <https://cb_pages_tests.localhost.mock.directory:4430/images/827679288a.jpg>
- <https://momar.localhost.mock.directory:4430/ci-testing/>
- <https://momar.localhost.mock.directory:4430/pag/@master/>
- <https://mock-pages.codeberg-test.org:4430/README.md>
### Profiling
> This section is just a collection of commands for quick reference. If you want to learn more about profiling read [this](https://go.dev/doc/diagnostics) article or google `golang profiling`.
First enable profiling by supplying the cli arg `--enable-profiling` or using the environment variable `EENABLE_PROFILING`.
Get cpu and mem stats:
```bash
go tool pprof -raw -output=cpu.txt 'http://localhost:9999/debug/pprof/profile?seconds=60' &
curl -so mem.txt 'http://localhost:9999/debug/pprof/heap?seconds=60'
```
More endpoints are documented here: <https://pkg.go.dev/net/http/pprof>

129
cli/flags.go Normal file
View file

@ -0,0 +1,129 @@
package cli
import (
"github.com/urfave/cli/v2"
)
var (
ServerFlags = []cli.Flag{
// #############
// ### Forge ###
// #############
// ForgeRoot specifies the root URL of the Forge instance, without a trailing slash.
&cli.StringFlag{
Name: "forge-root",
Aliases: []string{"gitea-root"},
Usage: "specifies the root URL of the Forgejo/Gitea instance, without a trailing slash.",
EnvVars: []string{"FORGE_ROOT", "GITEA_ROOT"},
},
// ForgeApiToken specifies an api token for the Forge instance
&cli.StringFlag{
Name: "forge-api-token",
Aliases: []string{"gitea-api-token"},
Usage: "specifies an api token for the Forgejo/Gitea instance",
EnvVars: []string{"FORGE_API_TOKEN", "GITEA_API_TOKEN"},
},
&cli.BoolFlag{
Name: "enable-lfs-support",
Usage: "enable lfs support, gitea must be version v1.17.0 or higher",
EnvVars: []string{"ENABLE_LFS_SUPPORT"},
Value: false,
},
&cli.BoolFlag{
Name: "enable-symlink-support",
Usage: "follow symlinks if enabled, gitea must be version v1.18.0 or higher",
EnvVars: []string{"ENABLE_SYMLINK_SUPPORT"},
Value: false,
},
&cli.StringFlag{
Name: "default-mime-type",
Usage: "specifies the default mime type for files that don't have a specific mime type.",
EnvVars: []string{"DEFAULT_MIME_TYPE"},
Value: "application/octet-stream",
},
&cli.StringSliceFlag{
Name: "forbidden-mime-types",
Usage: "specifies the forbidden mime types. Use this flag multiple times for multiple mime types.",
EnvVars: []string{"FORBIDDEN_MIME_TYPES"},
},
// ###########################
// ### Page Server Domains ###
// ###########################
// MainDomainSuffix specifies the main domain (starting with a dot) for which subdomains shall be served as static
// pages, or used for comparison in CNAME lookups. Static pages can be accessed through
// http://{owner}.{MainDomain}[/{repo}], with repo defaulting to "pages".
&cli.StringFlag{
Name: "pages-domain",
Usage: "specifies the main domain (starting with a dot) for which subdomains shall be served as static pages",
EnvVars: []string{"PAGES_DOMAIN"},
},
// RawDomain specifies the domain from which raw repository content shall be served in the following format:
// http://{RawDomain}/{owner}/{repo}[/{branch|tag|commit}/{version}]/{filepath...}
// (set to []byte(nil) to disable raw content hosting)
&cli.StringFlag{
Name: "raw-domain",
Usage: "specifies the domain from which raw repository content shall be served, not set disable raw content hosting",
EnvVars: []string{"RAW_DOMAIN"},
},
// #########################
// ### Page Server Setup ###
// #########################
&cli.StringFlag{
Name: "host",
Usage: "specifies host of listening address",
EnvVars: []string{"HOST"},
Value: "[::]",
},
&cli.UintFlag{
Name: "port",
Usage: "specifies the http port to listen to ssl requests",
EnvVars: []string{"PORT", "HTTP_PORT"},
Value: 8080,
},
// Default branches to fetch assets from
&cli.StringSliceFlag{
Name: "pages-branch",
Usage: "define a branch to fetch assets from. Use this flag multiple times for multiple branches.",
EnvVars: []string{"PAGES_BRANCHES"},
Value: cli.NewStringSlice("pages"),
},
&cli.StringSliceFlag{
Name: "allowed-cors-domains",
Usage: "specify allowed CORS domains. Use this flag multiple times for multiple domains.",
EnvVars: []string{"ALLOWED_CORS_DOMAINS"},
},
&cli.StringSliceFlag{
Name: "blacklisted-paths",
Usage: "return an error on these url paths.Use this flag multiple times for multiple paths.",
EnvVars: []string{"BLACKLISTED_PATHS"},
},
&cli.StringFlag{
Name: "log-level",
Value: "warn",
Usage: "specify at which log level should be logged. Possible options: info, warn, error, fatal",
EnvVars: []string{"LOG_LEVEL"},
},
&cli.StringFlag{
Name: "config-file",
Usage: "specify the location of the config file",
Aliases: []string{"config"},
EnvVars: []string{"CONFIG_FILE"},
},
&cli.BoolFlag{
Name: "enable-profiling",
Usage: "enables the go http profiling endpoints",
EnvVars: []string{"ENABLE_PROFILING"},
},
&cli.StringFlag{
Name: "profiling-address",
Usage: "specify ip address and port the profiling server should listen on",
EnvVars: []string{"PROFILING_ADDRESS"},
Value: "localhost:9999",
},
}
)

17
cli/setup.go Normal file
View file

@ -0,0 +1,17 @@
package cli
import (
"github.com/urfave/cli/v2"
"pages-server/server/version"
)
func CreatePagesApp() *cli.App {
app := cli.NewApp()
app.Name = "pages-server"
app.Version = version.Version
app.Usage = "pages server"
app.Flags = ServerFlags
return app
}

View file

@ -0,0 +1,17 @@
logLevel = 'trace'
[server]
host = '127.0.0.1'
port = 443
mainDomain = 'codeberg.page'
rawDomain = 'raw.codeberg.page'
allowedCorsDomains = ['fonts.codeberg.org', 'design.codeberg.org']
blacklistedPaths = ['do/not/use']
[forge]
root = 'https://codeberg.org'
token = 'XXXXXXXX'
lfsEnabled = true
followSymlinks = true
defaultMimeType = "application/wasm"
forbiddenMimeTypes = ["text/html"]

26
config/config.go Normal file
View file

@ -0,0 +1,26 @@
package config
type Config struct {
LogLevel string `default:"warn"`
Server ServerConfig
Forge ForgeConfig
}
type ServerConfig struct {
Host string `default:"127.0.0.1"`
Port uint16 `default:"8080"`
MainDomain string
RawDomain string
PagesBranches []string
AllowedCorsDomains []string
BlacklistedPaths []string
}
type ForgeConfig struct {
Root string
Token string
LFSEnabled bool `default:"false"`
FollowSymlinks bool `default:"false"`
DefaultMimeType string `default:"application/octet-stream"`
ForbiddenMimeTypes []string
}

103
config/setup.go Normal file
View file

@ -0,0 +1,103 @@
package config
import (
"os"
"path"
"github.com/creasty/defaults"
"github.com/pelletier/go-toml/v2"
"github.com/rs/zerolog/log"
"github.com/urfave/cli/v2"
)
var ALWAYS_BLACKLISTED_PATHS = []string{
"/.well-known/acme-challenge/",
}
func NewDefaultConfig() Config {
config := Config{}
if err := defaults.Set(&config); err != nil {
panic(err)
}
// defaults does not support setting arrays from strings
config.Server.PagesBranches = []string{"main", "master", "pages"}
return config
}
func ReadConfig(ctx *cli.Context) (*Config, error) {
config := NewDefaultConfig()
// if config is not given as argument return empty config
if !ctx.IsSet("config-file") {
return &config, nil
}
configFile := path.Clean(ctx.String("config-file"))
log.Debug().Str("config-file", configFile).Msg("reading config file")
content, err := os.ReadFile(configFile)
if err != nil {
return nil, err
}
err = toml.Unmarshal(content, &config)
return &config, err
}
func MergeConfig(ctx *cli.Context, config *Config) {
if ctx.IsSet("log-level") {
config.LogLevel = ctx.String("log-level")
}
mergeServerConfig(ctx, &config.Server)
mergeForgeConfig(ctx, &config.Forge)
}
func mergeServerConfig(ctx *cli.Context, config *ServerConfig) {
if ctx.IsSet("host") {
config.Host = ctx.String("host")
}
if ctx.IsSet("port") {
config.Port = uint16(ctx.Uint("port"))
}
if ctx.IsSet("pages-domain") {
config.MainDomain = ctx.String("pages-domain")
}
if ctx.IsSet("raw-domain") {
config.RawDomain = ctx.String("raw-domain")
}
if ctx.IsSet("pages-branch") {
config.PagesBranches = ctx.StringSlice("pages-branch")
}
if ctx.IsSet("allowed-cors-domains") {
config.AllowedCorsDomains = ctx.StringSlice("allowed-cors-domains")
}
if ctx.IsSet("blacklisted-paths") {
config.BlacklistedPaths = ctx.StringSlice("blacklisted-paths")
}
// add the paths that should always be blacklisted
config.BlacklistedPaths = append(config.BlacklistedPaths, ALWAYS_BLACKLISTED_PATHS...)
}
func mergeForgeConfig(ctx *cli.Context, config *ForgeConfig) {
if ctx.IsSet("forge-root") {
config.Root = ctx.String("forge-root")
}
if ctx.IsSet("forge-api-token") {
config.Token = ctx.String("forge-api-token")
}
if ctx.IsSet("enable-lfs-support") {
config.LFSEnabled = ctx.Bool("enable-lfs-support")
}
if ctx.IsSet("enable-symlink-support") {
config.FollowSymlinks = ctx.Bool("enable-symlink-support")
}
if ctx.IsSet("default-mime-type") {
config.DefaultMimeType = ctx.String("default-mime-type")
}
if ctx.IsSet("forbidden-mime-types") {
config.ForbiddenMimeTypes = ctx.StringSlice("forbidden-mime-types")
}
}

413
config/setup_test.go Normal file
View file

@ -0,0 +1,413 @@
package config
import (
"context"
"os"
"testing"
"github.com/pelletier/go-toml/v2"
"github.com/stretchr/testify/assert"
"github.com/urfave/cli/v2"
cmd "pages-server/cli"
)
func runApp(t *testing.T, fn func(*cli.Context) error, args []string) {
app := cmd.CreatePagesApp()
app.Action = fn
appCtx, appCancel := context.WithCancel(context.Background())
defer appCancel()
// os.Args always contains the binary name
args = append([]string{"testing"}, args...)
err := app.RunContext(appCtx, args)
assert.NoError(t, err)
}
// fixArrayFromCtx fixes the number of "changed" strings in a string slice according to the number of values in the context.
// This is a workaround because the cli library has a bug where the number of values in the context gets bigger the more tests are run.
func fixArrayFromCtx(ctx *cli.Context, key string, expected []string) []string {
if ctx.IsSet(key) {
ctxSlice := ctx.StringSlice(key)
if len(ctxSlice) > 1 {
for i := 1; i < len(ctxSlice); i++ {
expected = append([]string{"changed"}, expected...)
}
}
}
return expected
}
func readTestConfig() (*Config, error) {
content, err := os.ReadFile("assets/test_config.toml")
if err != nil {
return nil, err
}
expectedConfig := NewDefaultConfig()
err = toml.Unmarshal(content, &expectedConfig)
if err != nil {
return nil, err
}
return &expectedConfig, nil
}
func TestReadConfigShouldReturnEmptyConfigWhenConfigArgEmpty(t *testing.T) {
runApp(
t,
func(ctx *cli.Context) error {
cfg, err := ReadConfig(ctx)
expected := NewDefaultConfig()
assert.Equal(t, &expected, cfg)
return err
},
[]string{},
)
}
func TestReadConfigShouldReturnConfigFromFileWhenConfigArgPresent(t *testing.T) {
runApp(
t,
func(ctx *cli.Context) error {
cfg, err := ReadConfig(ctx)
if err != nil {
return err
}
expectedConfig, err := readTestConfig()
if err != nil {
return err
}
assert.Equal(t, expectedConfig, cfg)
return nil
},
[]string{"--config-file", "assets/test_config.toml"},
)
}
func TestValuesReadFromConfigFileShouldBeOverwrittenByArgs(t *testing.T) {
runApp(
t,
func(ctx *cli.Context) error {
cfg, err := ReadConfig(ctx)
if err != nil {
return err
}
MergeConfig(ctx, cfg)
expectedConfig, err := readTestConfig()
if err != nil {
return err
}
expectedConfig.LogLevel = "debug"
expectedConfig.Forge.Root = "not-codeberg.org"
expectedConfig.Server.Host = "172.17.0.2"
expectedConfig.Server.BlacklistedPaths = append(expectedConfig.Server.BlacklistedPaths, ALWAYS_BLACKLISTED_PATHS...)
assert.Equal(t, expectedConfig, cfg)
return nil
},
[]string{
"--config-file", "assets/test_config.toml",
"--log-level", "debug",
"--forge-root", "not-codeberg.org",
"--host", "172.17.0.2",
},
)
}
func TestMergeConfigShouldReplaceAllExistingValuesGivenAllArgsExist(t *testing.T) {
runApp(
t,
func(ctx *cli.Context) error {
cfg := &Config{
LogLevel: "original",
Server: ServerConfig{
Host: "original",
Port: 8080,
MainDomain: "original",
RawDomain: "original",
PagesBranches: []string{"original"},
AllowedCorsDomains: []string{"original"},
BlacklistedPaths: []string{"original"},
},
Forge: ForgeConfig{
Root: "original",
Token: "original",
LFSEnabled: false,
FollowSymlinks: false,
DefaultMimeType: "original",
ForbiddenMimeTypes: []string{"original"},
},
}
MergeConfig(ctx, cfg)
expectedConfig := &Config{
LogLevel: "changed",
Server: ServerConfig{
Host: "changed",
Port: 8443,
MainDomain: "changed",
RawDomain: "changed",
PagesBranches: []string{"changed"},
AllowedCorsDomains: []string{"changed"},
BlacklistedPaths: append([]string{"changed"}, ALWAYS_BLACKLISTED_PATHS...),
},
Forge: ForgeConfig{
Root: "changed",
Token: "changed",
LFSEnabled: true,
FollowSymlinks: true,
DefaultMimeType: "changed",
ForbiddenMimeTypes: []string{"changed"},
},
}
assert.Equal(t, expectedConfig, cfg)
return nil
},
[]string{
"--log-level", "changed",
// Server
"--pages-domain", "changed",
"--raw-domain", "changed",
"--allowed-cors-domains", "changed",
"--blacklisted-paths", "changed",
"--pages-branch", "changed",
"--host", "changed",
"--port", "8443",
// Forge
"--forge-root", "changed",
"--forge-api-token", "changed",
"--enable-lfs-support",
"--enable-symlink-support",
"--default-mime-type", "changed",
"--forbidden-mime-types", "changed",
// Database
"--db-type", "changed",
"--db-conn", "changed",
// ACME
"--acme-email", "changed",
"--acme-api-endpoint", "changed",
"--acme-accept-terms",
"--acme-use-rate-limits",
"--acme-eab-hmac", "changed",
"--acme-eab-kid", "changed",
"--dns-provider", "changed",
"--no-dns-01",
"--acme-account-config", "changed",
},
)
}
func TestMergeServerConfigShouldReplaceAllExistingValuesGivenAllArgsExist(t *testing.T) {
for range []uint8{0, 1} {
runApp(
t,
func(ctx *cli.Context) error {
cfg := &ServerConfig{
Host: "original",
Port: 8080,
MainDomain: "original",
RawDomain: "original",
AllowedCorsDomains: []string{"original"},
BlacklistedPaths: []string{"original"},
}
mergeServerConfig(ctx, cfg)
expectedConfig := &ServerConfig{
Host: "changed",
Port: 8080,
MainDomain: "changed",
RawDomain: "changed",
AllowedCorsDomains: fixArrayFromCtx(ctx, "allowed-cors-domains", []string{"changed"}),
BlacklistedPaths: fixArrayFromCtx(ctx, "blacklisted-paths", append([]string{"changed"}, ALWAYS_BLACKLISTED_PATHS...)),
}
assert.Equal(t, expectedConfig, cfg)
return nil
},
[]string{
"--pages-domain", "changed",
"--raw-domain", "changed",
"--allowed-cors-domains", "changed",
"--blacklisted-paths", "changed",
"--host", "changed",
"--port", "8443",
},
)
}
}
func TestMergeServerConfigShouldReplaceOnlyOneValueExistingValueGivenOnlyOneArgExists(t *testing.T) {
type testValuePair struct {
args []string
callback func(*ServerConfig)
}
testValuePairs := []testValuePair{
{args: []string{"--host", "changed"}, callback: func(sc *ServerConfig) { sc.Host = "changed" }},
{args: []string{"--port", "8080"}, callback: func(sc *ServerConfig) { sc.Port = 8080 }},
{args: []string{"--pages-domain", "changed"}, callback: func(sc *ServerConfig) { sc.MainDomain = "changed" }},
{args: []string{"--raw-domain", "changed"}, callback: func(sc *ServerConfig) { sc.RawDomain = "changed" }},
{args: []string{"--pages-branch", "changed"}, callback: func(sc *ServerConfig) { sc.PagesBranches = []string{"changed"} }},
{args: []string{"--allowed-cors-domains", "changed"}, callback: func(sc *ServerConfig) { sc.AllowedCorsDomains = []string{"changed"} }},
{args: []string{"--blacklisted-paths", "changed"}, callback: func(sc *ServerConfig) { sc.BlacklistedPaths = []string{"changed"} }},
}
for _, pair := range testValuePairs {
runApp(
t,
func(ctx *cli.Context) error {
cfg := ServerConfig{
Host: "original",
Port: 8080,
MainDomain: "original",
RawDomain: "original",
PagesBranches: []string{"original"},
AllowedCorsDomains: []string{"original"},
BlacklistedPaths: []string{"original"},
}
expectedConfig := cfg
pair.callback(&expectedConfig)
expectedConfig.BlacklistedPaths = append(expectedConfig.BlacklistedPaths, ALWAYS_BLACKLISTED_PATHS...)
expectedConfig.PagesBranches = fixArrayFromCtx(ctx, "pages-branch", expectedConfig.PagesBranches)
expectedConfig.AllowedCorsDomains = fixArrayFromCtx(ctx, "allowed-cors-domains", expectedConfig.AllowedCorsDomains)
expectedConfig.BlacklistedPaths = fixArrayFromCtx(ctx, "blacklisted-paths", expectedConfig.BlacklistedPaths)
mergeServerConfig(ctx, &cfg)
assert.Equal(t, expectedConfig, cfg)
return nil
},
pair.args,
)
}
}
func TestMergeForgeConfigShouldReplaceAllExistingValuesGivenAllArgsExist(t *testing.T) {
runApp(
t,
func(ctx *cli.Context) error {
cfg := &ForgeConfig{
Root: "original",
Token: "original",
LFSEnabled: false,
FollowSymlinks: false,
DefaultMimeType: "original",
ForbiddenMimeTypes: []string{"original"},
}
mergeForgeConfig(ctx, cfg)
expectedConfig := &ForgeConfig{
Root: "changed",
Token: "changed",
LFSEnabled: true,
FollowSymlinks: true,
DefaultMimeType: "changed",
ForbiddenMimeTypes: fixArrayFromCtx(ctx, "forbidden-mime-types", []string{"changed"}),
}
assert.Equal(t, expectedConfig, cfg)
return nil
},
[]string{
"--forge-root", "changed",
"--forge-api-token", "changed",
"--enable-lfs-support",
"--enable-symlink-support",
"--default-mime-type", "changed",
"--forbidden-mime-types", "changed",
},
)
}
func TestMergeForgeConfigShouldReplaceOnlyOneValueExistingValueGivenOnlyOneArgExists(t *testing.T) {
type testValuePair struct {
args []string
callback func(*ForgeConfig)
}
testValuePairs := []testValuePair{
{args: []string{"--forge-root", "changed"}, callback: func(gc *ForgeConfig) { gc.Root = "changed" }},
{args: []string{"--forge-api-token", "changed"}, callback: func(gc *ForgeConfig) { gc.Token = "changed" }},
{args: []string{"--enable-lfs-support"}, callback: func(gc *ForgeConfig) { gc.LFSEnabled = true }},
{args: []string{"--enable-symlink-support"}, callback: func(gc *ForgeConfig) { gc.FollowSymlinks = true }},
{args: []string{"--default-mime-type", "changed"}, callback: func(gc *ForgeConfig) { gc.DefaultMimeType = "changed" }},
{args: []string{"--forbidden-mime-types", "changed"}, callback: func(gc *ForgeConfig) { gc.ForbiddenMimeTypes = []string{"changed"} }},
}
for _, pair := range testValuePairs {
runApp(
t,
func(ctx *cli.Context) error {
cfg := ForgeConfig{
Root: "original",
Token: "original",
LFSEnabled: false,
FollowSymlinks: false,
DefaultMimeType: "original",
ForbiddenMimeTypes: []string{"original"},
}
expectedConfig := cfg
pair.callback(&expectedConfig)
mergeForgeConfig(ctx, &cfg)
expectedConfig.ForbiddenMimeTypes = fixArrayFromCtx(ctx, "forbidden-mime-types", expectedConfig.ForbiddenMimeTypes)
assert.Equal(t, expectedConfig, cfg)
return nil
},
pair.args,
)
}
}
func TestMergeForgeConfigShouldReplaceValuesGivenGiteaOptionsExist(t *testing.T) {
runApp(
t,
func(ctx *cli.Context) error {
cfg := &ForgeConfig{
Root: "original",
Token: "original",
}
mergeForgeConfig(ctx, cfg)
expectedConfig := &ForgeConfig{
Root: "changed",
Token: "changed",
}
assert.Equal(t, expectedConfig, cfg)
return nil
},
[]string{
"--gitea-root", "changed",
"--gitea-api-token", "changed",
},
)
}

16
example_config.toml Normal file
View file

@ -0,0 +1,16 @@
logLevel = 'debug'
[server]
host = '127.0.0.1'
port = 8080
mainDomain = 'codeberg.page'
rawDomain = 'raw.codeberg.page'
pagesBranches = ["pages"]
allowedCorsDomains = []
blacklistedPaths = []
[forge]
root = 'https://codeberg.org'
token = 'ASDF1234'
lfsEnabled = true
followSymlinks = true

1
examples/haproxy-sni/.gitignore vendored Normal file
View file

@ -0,0 +1 @@
*.dump

View file

@ -0,0 +1,25 @@
# HAProxy with SNI & Host-based rules
This is a proof of concept, enabling HAProxy to use _either_ SNI to redirect to backends with their own HTTPS certificates (which are then fully exposed to the client; HAProxy only proxies on a TCP level in that case), _as well as_ to terminate HTTPS and use the Host header to redirect to backends that use HTTP (or a new HTTPS connection).
## How it works
1. The `http_redirect_frontend` is only there to listen on port 80 and redirect every request to HTTPS.
2. The `https_sni_frontend` listens on port 443 and chooses a backend based on the SNI hostname of the TLS connection.
3. The `https_termination_backend` passes all requests to a unix socket (using the plain TCP data).
4. The `https_termination_frontend` listens on said unix socket, terminates the HTTPS connections and then chooses a backend based on the Host header.
In the example (see [haproxy.cfg](haproxy.cfg)), the `pages_backend` is listening via HTTPS and is providing its own HTTPS certificates, while the `gitea_backend` only provides HTTP.
## How to test
```bash
docker-compose up &
./test.sh
docker-compose down
# For manual testing: all HTTPS URLs connect to localhost:443 & certificates are not verified.
./test.sh [curl-options...] <url>
```
![Screenshot of the test script's output](/attachments/c82d79ea-7586-4d4b-b340-3ad0030185d6)

View file

@ -0,0 +1,8 @@
-----BEGIN DH PARAMETERS-----
MIIBCAKCAQEA//////////+t+FRYortKmq/cViAnPTzx2LnFg84tNpWp4TZBFGQz
+8yTnc4kmz75fS/jY2MMddj2gbICrsRhetPfHtXV/WVhJDP1H18GbtCFY2VVPe0a
87VXE15/V8k1mE8McODmi3fipona8+/och3xWKE2rec1MKzKT0g6eXq8CrGCsyT7
YdEIqUuyyOP7uWrat2DX9GgdT0Kj3jlN9K5W7edjcrsZCwenyO4KbXCeAvzhzffi
7MA0BM0oNC9hkXL+nOmFg/+OTxIy7vKBg8P+OxtMb61zO7X8vC7CIAXFjvGDfRaD
ssbzSibBsu/6iGtCOGEoXJf//////////wIBAg==
-----END DH PARAMETERS-----

View file

@ -0,0 +1,21 @@
version: '3'
services:
haproxy:
image: haproxy
ports: ['443:443']
volumes:
- ./haproxy.cfg:/usr/local/etc/haproxy/haproxy.cfg:ro
- ./dhparam.pem:/etc/ssl/dhparam.pem:ro
- ./haproxy-certificates:/etc/ssl/private/haproxy:ro
cap_add:
- NET_ADMIN
gitea:
image: caddy
volumes:
- ./gitea-www:/srv:ro
- ./gitea.Caddyfile:/etc/caddy/Caddyfile:ro
pages:
image: caddy
volumes:
- ./pages-www:/srv:ro
- ./pages.Caddyfile:/etc/caddy/Caddyfile:ro

View file

@ -0,0 +1 @@
Hello to Gitea!

View file

@ -0,0 +1,3 @@
http://codeberg.org
file_server

View file

@ -0,0 +1,26 @@
-----BEGIN CERTIFICATE-----
MIIEUDCCArigAwIBAgIRAMq3iwF963VGkzXFpbrpAtkwDQYJKoZIhvcNAQELBQAw
gYkxHjAcBgNVBAoTFW1rY2VydCBkZXZlbG9wbWVudCBDQTEvMC0GA1UECwwmbW9t
YXJAbW9yaXR6LWxhcHRvcCAoTW9yaXR6IE1hcnF1YXJkdCkxNjA0BgNVBAMMLW1r
Y2VydCBtb21hckBtb3JpdHotbGFwdG9wIChNb3JpdHogTWFycXVhcmR0KTAeFw0y
MTA2MDYwOTQ4NDFaFw0yMzA5MDYwOTQ4NDFaMFoxJzAlBgNVBAoTHm1rY2VydCBk
ZXZlbG9wbWVudCBjZXJ0aWZpY2F0ZTEvMC0GA1UECwwmbW9tYXJAbW9yaXR6LWxh
cHRvcCAoTW9yaXR6IE1hcnF1YXJkdCkwggEiMA0GCSqGSIb3DQEBAQUAA4IBDwAw
ggEKAoIBAQCrSPSPM6grNZMG4ZKFCVxuXu+qkHdzSR96QUxi00VkIrkGPmyMN7q7
rUQJto9C9guJio3n7y3Bvr5kBjICjyWQd7GfkVuYgiYiG/O2hy1u1dIMCAB/Zhx1
F1mvRfn/Q4eZk2GSOUM+kC0xaNsn2827VGLOGFywUhRmu7J9QSQ3x1Pi5BME7eNC
AKup0CbrMrZSzKAEuYujLY0UYRxUrguMnV60wxJDCYE14YDxn9t0g7wQmzyndupk
AMLNJZX5L83RA6vUEuTVYBFcyB0Fu3oBLQ31y5QOZ7WF/QiO5cPicQJI/oyXlHq4
97BWS/H28kj1H5ZM8+5yhCYDtgj7dERpAgMBAAGjYTBfMA4GA1UdDwEB/wQEAwIF
oDATBgNVHSUEDDAKBggrBgEFBQcDATAfBgNVHSMEGDAWgBSOSXQZqt2gjbTOkE9Q
ddI8SYPqrDAXBgNVHREEEDAOggxjb2RlYmVyZy5vcmcwDQYJKoZIhvcNAQELBQAD
ggGBAJ/57DGqfuOa3aS/nLeAzl8komvyHuoOZi9yDK2Jqr+COxP58zSu8xwhiZfc
TJvIyB9QR7imGiQ7fEKby40q8uxGGx13oY7gQy7PG8hHk2dkfDZuSQacnpPRC3W0
0dL2CQIog6rw6jJHjxneitkX9FUmOnHIKy7LHya0Sthg36Z0Qw5JA3SCy6OQNepR
R2XzwTZ0KFk6gAuKCto8ENUlU5lV9PM4X3U0cBOIc5LJAPM+cxEDUocFtFqKJPbe
YYlSeB200YhYOdi+x34n9xnQjFu/jVlWF+Y0tMBB1WWq6rZbnuylwWLYQZAo10Co
D3oWsYRlD/ZL7X20ztIy8vRXz33ugnxxf88Q7csWDYb4S325svLfI2EjciIxYmBo
dSJxXRQkadjIoI7gNvzeWBkYSJpQUbaD4nT2xRS8vfuv42/DrIehb8SbTivHmcB3
OibpWIvDtS1B8thIlzl0edb+8pb6mof7pOBxoZdcBsSAk2/48s+jfRHfD9XcuKnv
hGCdSQ==
-----END CERTIFICATE-----

View file

@ -0,0 +1,28 @@
-----BEGIN PRIVATE KEY-----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-----END PRIVATE KEY-----

View file

@ -0,0 +1,99 @@
#####################################
## Global Configuration & Defaults ##
#####################################
global
log stderr format iso local7
# generated 2021-06-05, Mozilla Guideline v5.6, HAProxy 2.1, OpenSSL 1.1.1d, intermediate configuration
# https://ssl-config.mozilla.org/#server=haproxy&version=2.1&config=intermediate&openssl=1.1.1d&guideline=5.6
ssl-default-bind-ciphers ECDHE-ECDSA-AES128-GCM-SHA256:ECDHE-RSA-AES128-GCM-SHA256:ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:DHE-RSA-AES128-GCM-SHA256:DHE-RSA-AES256-GCM-SHA384
ssl-default-bind-ciphersuites TLS_AES_128_GCM_SHA256:TLS_AES_256_GCM_SHA384:TLS_CHACHA20_POLY1305_SHA256
ssl-default-bind-options prefer-client-ciphers no-sslv3 no-tlsv10 no-tlsv11 no-tls-tickets
ssl-default-server-ciphers ECDHE-ECDSA-AES128-GCM-SHA256:ECDHE-RSA-AES128-GCM-SHA256:ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:DHE-RSA-AES128-GCM-SHA256:DHE-RSA-AES256-GCM-SHA384
ssl-default-server-ciphersuites TLS_AES_128_GCM_SHA256:TLS_AES_256_GCM_SHA384:TLS_CHACHA20_POLY1305_SHA256
ssl-default-server-options no-sslv3 no-tlsv10 no-tlsv11 no-tls-tickets
# curl https://ssl-config.mozilla.org/ffdhe2048.txt > /path/to/dhparam
ssl-dh-param-file /etc/ssl/dhparam.pem
defaults
log global
timeout connect 30000
timeout check 300000
timeout client 300000
timeout server 300000
############################################################################
## Frontends: HTTP; HTTPS → HTTPS SNI-based; HTTPS → HTTP(S) header-based ##
############################################################################
frontend http_redirect_frontend
# HTTP backend to redirect everything to HTTPS
bind :::80 v4v6
mode http
http-request redirect scheme https
frontend https_sni_frontend
# TCP backend to forward to HTTPS backends based on SNI
bind :::443 v4v6
mode tcp
# Wait up to 5s for a SNI header & only accept TLS connections
tcp-request inspect-delay 5s
tcp-request content capture req.ssl_sni len 255
log-format "%ci:%cp -> %[capture.req.hdr(0)] @ %f (%fi:%fp) -> %b (%bi:%bp)"
tcp-request content accept if { req.ssl_hello_type 1 }
###################################################
## Rules: forward to HTTPS(S) header-based rules ##
###################################################
acl use_http_backend req.ssl_sni -i "codeberg.org"
acl use_http_backend req.ssl_sni -i "join.codeberg.org"
# TODO: use this if no SNI exists
use_backend https_termination_backend if use_http_backend
############################
## Rules: HTTPS SNI-based ##
############################
# use_backend xyz_backend if { req.ssl_sni -i "xyz" }
default_backend pages_backend
frontend https_termination_frontend
# Terminate TLS for HTTP backends
bind /tmp/haproxy-tls-termination.sock accept-proxy ssl strict-sni alpn h2,http/1.1 crt /etc/ssl/private/haproxy/
mode http
# HSTS (63072000 seconds)
http-response set-header Strict-Transport-Security max-age=63072000
http-request capture req.hdr(Host) len 255
log-format "%ci:%cp -> %[capture.req.hdr(0)] @ %f (%fi:%fp) -> %b (%bi:%bp)"
##################################
## Rules: HTTPS(S) header-based ##
##################################
use_backend gitea_backend if { hdr(host) -i codeberg.org }
backend https_termination_backend
# Redirect to the terminating HTTPS frontend for all HTTP backends
server https_termination_server /tmp/haproxy-tls-termination.sock send-proxy-v2-ssl-cn
mode tcp
###############################
## Backends: HTTPS SNI-based ##
###############################
backend pages_backend
# Pages server is a HTTP backend that uses its own certificates for custom domains
server pages_server pages:443
mode tcp
####################################
## Backends: HTTP(S) header-based ##
####################################
backend gitea_backend
server gitea_server gitea:80
mode http

View file

@ -0,0 +1 @@
Hello to Pages!

View file

@ -0,0 +1,4 @@
https://example-page.org
tls internal
file_server

View file

@ -0,0 +1,22 @@
#!/bin/sh
if [ $# -gt 0 ]; then
exec curl -k --resolve '*:443:127.0.0.1' "$@"
fi
fail() {
echo "[FAIL] $@"
exit 1
}
echo "Connecting to Gitea..."
res=$(curl https://codeberg.org -sk --resolve '*:443:127.0.0.1' --trace-ascii gitea.dump | tee /dev/stderr)
echo "$res" | grep -Fx 'Hello to Gitea!' >/dev/null || fail "Gitea didn't answer"
grep '^== Info: issuer: O=mkcert development CA;' gitea.dump || { grep grep '^== Info: issuer:' gitea.dump; fail "Gitea didn't use the correct certificate!"; }
echo "Connecting to Pages..."
res=$(curl https://example-page.org -sk --resolve '*:443:127.0.0.1' --trace-ascii pages.dump | tee /dev/stderr)
echo "$res" | grep -Fx 'Hello to Pages!' >/dev/null || fail "Pages didn't answer"
grep '^== Info: issuer: CN=Caddy Local Authority\b' pages.dump || { grep '^== Info: issuer:' pages.dump; fail "Pages didn't use the correct certificate!"; }
echo "All tests succeeded"
rm *.dump

73
flake.lock generated Normal file
View file

@ -0,0 +1,73 @@
{
"nodes": {
"flake-utils": {
"inputs": {
"systems": "systems"
},
"locked": {
"lastModified": 1710146030,
"narHash": "sha256-SZ5L6eA7HJ/nmkzGG7/ISclqe6oZdOZTNoesiInkXPQ=",
"owner": "numtide",
"repo": "flake-utils",
"rev": "b1d9ab70662946ef0850d488da1c9019f3a9752a",
"type": "github"
},
"original": {
"id": "flake-utils",
"type": "indirect"
}
},
"nixpkgs": {
"locked": {
"lastModified": 1716715802,
"narHash": "sha256-usk0vE7VlxPX8jOavrtpOqphdfqEQpf9lgedlY/r66c=",
"owner": "NixOS",
"repo": "nixpkgs",
"rev": "e2dd4e18cc1c7314e24154331bae07df76eb582f",
"type": "github"
},
"original": {
"id": "nixpkgs",
"type": "indirect"
}
},
"root": {
"inputs": {
"flake-utils": "flake-utils",
"nixpkgs": "nixpkgs",
"systems": "systems_2"
}
},
"systems": {
"locked": {
"lastModified": 1681028828,
"narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
"owner": "nix-systems",
"repo": "default",
"rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
"type": "github"
},
"original": {
"owner": "nix-systems",
"repo": "default",
"type": "github"
}
},
"systems_2": {
"locked": {
"lastModified": 1681028828,
"narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
"owner": "nix-systems",
"repo": "default",
"rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
"type": "github"
},
"original": {
"id": "systems",
"type": "indirect"
}
}
},
"root": "root",
"version": 7
}

27
flake.nix Normal file
View file

@ -0,0 +1,27 @@
{
outputs = {
self,
nixpkgs,
flake-utils,
systems,
}:
flake-utils.lib.eachSystem (import systems)
(system: let
pkgs = import nixpkgs {
inherit system;
};
in {
devShells.default = pkgs.mkShell {
buildInputs = with pkgs; [
gcc
go
gofumpt
golangci-lint
gopls
gotools
go-tools
sqlite-interactive
];
};
});
}

40
go.mod Normal file
View file

@ -0,0 +1,40 @@
module pages-server
go 1.21
toolchain go1.21.4
require (
code.gitea.io/sdk/gitea v0.17.1
github.com/OrlovEvgeny/go-mcache v0.0.0-20200121124330-1a8195b34f3a
github.com/creasty/defaults v1.7.0
github.com/hashicorp/golang-lru/v2 v2.0.7
github.com/joho/godotenv v1.4.0
github.com/microcosm-cc/bluemonday v1.0.26
github.com/pelletier/go-toml/v2 v2.1.0
github.com/rs/zerolog v1.27.0
github.com/stretchr/testify v1.8.4
github.com/urfave/cli/v2 v2.3.0
golang.org/x/exp v0.0.0-20240719175910-8a7402abbf56
)
require (
github.com/aymerick/douceur v0.2.0 // indirect
github.com/cpuguy83/go-md2man/v2 v2.0.0 // indirect
github.com/davecgh/go-spew v1.1.1 // indirect
github.com/davidmz/go-pageant v1.0.2 // indirect
github.com/go-fed/httpsig v1.1.0 // indirect
github.com/gorilla/css v1.0.0 // indirect
github.com/hashicorp/go-version v1.6.0 // indirect
github.com/kr/pretty v0.1.0 // indirect
github.com/mattn/go-colorable v0.1.12 // indirect
github.com/mattn/go-isatty v0.0.14 // indirect
github.com/pmezard/go-difflib v1.0.0 // indirect
github.com/russross/blackfriday/v2 v2.0.1 // indirect
github.com/shurcooL/sanitized_anchor_name v1.0.0 // indirect
golang.org/x/crypto v0.17.0 // indirect
golang.org/x/net v0.17.0 // indirect
golang.org/x/sys v0.15.0 // indirect
gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15 // indirect
gopkg.in/yaml.v3 v3.0.1 // indirect
)

120
go.sum Normal file
View file

@ -0,0 +1,120 @@
code.gitea.io/sdk/gitea v0.17.1 h1:3jCPOG2ojbl8AcfaUCRYLT5MUcBMFwS0OSK2mA5Zok8=
code.gitea.io/sdk/gitea v0.17.1/go.mod h1:aCnBqhHpoEWA180gMbaCtdX9Pl6BWBAuuP2miadoTNM=
github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
github.com/OrlovEvgeny/go-mcache v0.0.0-20200121124330-1a8195b34f3a h1:Cf4CrDeyrIcuIiJZEZJAH5dapqQ6J3OmP/vHPbDjaFA=
github.com/OrlovEvgeny/go-mcache v0.0.0-20200121124330-1a8195b34f3a/go.mod h1:ig6eVXkYn/9dz0Vm8UdLf+E0u1bE6kBSn3n2hqk6jas=
github.com/aymerick/douceur v0.2.0 h1:Mv+mAeH1Q+n9Fr+oyamOlAkUNPWPlA8PPGR0QAaYuPk=
github.com/aymerick/douceur v0.2.0/go.mod h1:wlT5vV2O3h55X9m7iVYN0TBM0NH/MmbLnd30/FjWUq4=
github.com/coreos/go-systemd/v22 v22.3.3-0.20220203105225-a9a7ef127534/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSVTIJ3seZv2GcEnc=
github.com/cpuguy83/go-md2man/v2 v2.0.0-20190314233015-f79a8a8ca69d/go.mod h1:maD7wRr/U5Z6m/iR4s+kqSMx2CaBsrgA7czyZG/E6dU=
github.com/cpuguy83/go-md2man/v2 v2.0.0 h1:EoUDS0afbrsXAZ9YQ9jdu/mZ2sXgT1/2yyNng4PGlyM=
github.com/cpuguy83/go-md2man/v2 v2.0.0/go.mod h1:maD7wRr/U5Z6m/iR4s+kqSMx2CaBsrgA7czyZG/E6dU=
github.com/creasty/defaults v1.7.0 h1:eNdqZvc5B509z18lD8yc212CAqJNvfT1Jq6L8WowdBA=
github.com/creasty/defaults v1.7.0/go.mod h1:iGzKe6pbEHnpMPtfDXZEr0NVxWnPTjb1bbDy08fPzYM=
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/davidmz/go-pageant v1.0.2 h1:bPblRCh5jGU+Uptpz6LgMZGD5hJoOt7otgT454WvHn0=
github.com/davidmz/go-pageant v1.0.2/go.mod h1:P2EDDnMqIwG5Rrp05dTRITj9z2zpGcD9efWSkTNKLIE=
github.com/go-fed/httpsig v1.1.0 h1:9M+hb0jkEICD8/cAiNqEB66R87tTINszBRTjwjQzWcI=
github.com/go-fed/httpsig v1.1.0/go.mod h1:RCMrTZvN1bJYtofsG4rd5NaO5obxQ5xBkdiS7xsT7bM=
github.com/godbus/dbus/v5 v5.0.4/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
github.com/gorilla/css v1.0.0 h1:BQqNyPTi50JCFMTw/b67hByjMVXZRwGha6wxVGkeihY=
github.com/gorilla/css v1.0.0/go.mod h1:Dn721qIggHpt4+EFCcTLTU/vk5ySda2ReITrtgBl60c=
github.com/hashicorp/go-version v1.6.0 h1:feTTfFNnjP967rlCxM/I9g701jU+RN74YKx2mOkIeek=
github.com/hashicorp/go-version v1.6.0/go.mod h1:fltr4n8CU8Ke44wwGCBoEymUuxUHl09ZGVZPK5anwXA=
github.com/hashicorp/golang-lru/v2 v2.0.7 h1:a+bsQ5rvGLjzHuww6tVxozPZFVghXaHOwFs4luLUK2k=
github.com/hashicorp/golang-lru/v2 v2.0.7/go.mod h1:QeFd9opnmA6QUJc5vARoKUSoFhyfM2/ZepoAG6RGpeM=
github.com/joho/godotenv v1.4.0 h1:3l4+N6zfMWnkbPEXKng2o2/MR5mSwTrBih4ZEkkz1lg=
github.com/joho/godotenv v1.4.0/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4=
github.com/kr/pretty v0.1.0 h1:L/CwN0zerZDmRFUapSPitk6f+Q3+0za1rQkzVuMiMFI=
github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
github.com/kr/text v0.1.0 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE=
github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
github.com/mattn/go-colorable v0.1.12 h1:jF+Du6AlPIjs2BiUiQlKOX0rt3SujHxPnksPKZbaA40=
github.com/mattn/go-colorable v0.1.12/go.mod h1:u5H1YNBxpqRaxsYJYSkiCWKzEfiAb1Gb520KVy5xxl4=
github.com/mattn/go-isatty v0.0.14 h1:yVuAays6BHfxijgZPzw+3Zlu5yQgKGP2/hcQbHb7S9Y=
github.com/mattn/go-isatty v0.0.14/go.mod h1:7GGIvUiUoEMVVmxf/4nioHXj79iQHKdU27kJ6hsGG94=
github.com/microcosm-cc/bluemonday v1.0.26 h1:xbqSvqzQMeEHCqMi64VAs4d8uy6Mequs3rQ0k/Khz58=
github.com/microcosm-cc/bluemonday v1.0.26/go.mod h1:JyzOCs9gkyQyjs+6h10UEVSe02CGwkhd72Xdqh78TWs=
github.com/pelletier/go-toml/v2 v2.1.0 h1:FnwAJ4oYMvbT/34k9zzHuZNrhlz48GB3/s6at6/MHO4=
github.com/pelletier/go-toml/v2 v2.1.0/go.mod h1:tJU2Z3ZkXwnxa4DPO899bsyIoywizdUvyaeZurnPPDc=
github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/rs/xid v1.3.0/go.mod h1:trrq9SKmegXys3aeAKXMUTdJsYXVwGY3RLcfgqegfbg=
github.com/rs/zerolog v1.27.0 h1:1T7qCieN22GVc8S4Q2yuexzBb1EqjbgjSH9RohbMjKs=
github.com/rs/zerolog v1.27.0/go.mod h1:7frBqO0oezxmnO7GF86FY++uy8I0Tk/If5ni1G9Qc0U=
github.com/russross/blackfriday/v2 v2.0.1 h1:lPqVAte+HuHNfhJ/0LC98ESWRz8afy9tM/0RK8m9o+Q=
github.com/russross/blackfriday/v2 v2.0.1/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
github.com/shurcooL/sanitized_anchor_name v1.0.0 h1:PdmoCO6wvbs+7yrJyMORt4/BmY5IYyJwS/kOiWx8mHo=
github.com/shurcooL/sanitized_anchor_name v1.0.0/go.mod h1:1NzhyTcUVG4SuEtjjoZeVRXNmyL/1OwPU0+IJeTBvfc=
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 v1.7.0/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 v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
github.com/urfave/cli/v2 v2.3.0 h1:qph92Y649prgesehzOrQjdWyxFOp/QVM+6imKHad91M=
github.com/urfave/cli/v2 v2.3.0/go.mod h1:LJmUH05zAU44vOAcrfzZQKsZbVcdbOG8rtL3/XcUArI=
github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
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 v0.0.0-20210513164829-c07d793c2f9a/go.mod h1:P+XmwS30IXTQdn5tA2iutPOUgjI07+tq3H3K9MVA1s8=
golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
golang.org/x/crypto v0.17.0 h1:r8bRNjWL3GshPW3gkd+RpvzWrZAwPS49OmTGZ/uhM4k=
golang.org/x/crypto v0.17.0/go.mod h1:gCAAfMLgwOJRpTjQ2zCCt2OcSfYMTeZVSRtQlPC7Nq4=
golang.org/x/exp v0.0.0-20240719175910-8a7402abbf56 h1:2dVuKD2vS7b0QIHQbpyTISPd0LeHDbnYEryqj5Q1ug8=
golang.org/x/exp v0.0.0-20240719175910-8a7402abbf56/go.mod h1:M4RDyNAINzryxdtnbRXRL/OHtkFuWGRjvuhBJpk2IlY=
golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
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 v0.17.0 h1:pVaXccu2ozPjCXewfr1S7xza/zcXTity9cCdXQYSjIM=
golang.org/x/net v0.17.0/go.mod h1:NxSsAGuq816PNPmqtQdLE42eU2Fs7NoRIZrHJAlaCOE=
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=
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20210630005230-0f9fa26af87c/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20210927094055-39ccf1dd6fa6/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.15.0 h1:h48lPFYpsTvQJZF4EKyI4aLHaev3CxivZmv7yZig9pc=
golang.org/x/sys v0.15.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
golang.org/x/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo=
golang.org/x/term v0.15.0 h1:y/Oo/a/q3IXu26lQgl04j/gjuBDOBlx7X6Om1j2CPW4=
golang.org/x/term v0.15.0/go.mod h1:BDl952bC7+uMoWR75FIrCDx79TPU9oHkTZ9yRbYOrX0=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
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/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15 h1:YR8cESwS4TdDjEe65xsg0ogRM/Nc3DYOhEAlW+xobZo=
gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/yaml.v2 v2.2.3/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

54
html/html.go Normal file
View file

@ -0,0 +1,54 @@
package html
import (
_ "embed"
"net/http"
"text/template" // do not use html/template here, we sanitize the message before passing it to the template
"pages-server/server/context"
"github.com/microcosm-cc/bluemonday"
"github.com/rs/zerolog/log"
)
//go:embed templates/error.html
var errorPage string
var (
errorTemplate = template.Must(template.New("error").Parse(errorPage))
sanitizer = createBlueMondayPolicy()
)
type TemplateContext struct {
StatusCode int
StatusText string
Message string
}
// ReturnErrorPage sets the response status code and writes the error page to the response body.
// The error page contains a sanitized version of the message and the statusCode both in text and numeric form.
//
// Currently, only the following html tags are supported: <code>
func ReturnErrorPage(ctx *context.Context, msg string, statusCode int) {
ctx.RespWriter.Header().Set("Content-Type", "text/html; charset=utf-8")
ctx.RespWriter.WriteHeader(statusCode)
templateContext := TemplateContext{
StatusCode: statusCode,
StatusText: http.StatusText(statusCode),
Message: sanitizer.Sanitize(msg),
}
err := errorTemplate.Execute(ctx.RespWriter, templateContext)
if err != nil {
log.Err(err).Str("message", msg).Int("status", statusCode).Msg("could not write response")
}
}
func createBlueMondayPolicy() *bluemonday.Policy {
p := bluemonday.NewPolicy()
p.AllowElements("code")
return p
}

54
html/html_test.go Normal file
View file

@ -0,0 +1,54 @@
package html
import (
"testing"
"github.com/stretchr/testify/assert"
)
func TestSanitizerSimpleString(t *testing.T) {
str := "simple text message without any html elements"
assert.Equal(t, str, sanitizer.Sanitize(str))
}
func TestSanitizerStringWithCodeTag(t *testing.T) {
str := "simple text message with <code>html</code> tag"
assert.Equal(t, str, sanitizer.Sanitize(str))
}
func TestSanitizerStringWithCodeTagWithAttribute(t *testing.T) {
str := "simple text message with <code id=\"code\">html</code> tag"
expected := "simple text message with <code>html</code> tag"
assert.Equal(t, expected, sanitizer.Sanitize(str))
}
func TestSanitizerStringWithATag(t *testing.T) {
str := "simple text message with <a>a link to another page</a>"
expected := "simple text message with a link to another page"
assert.Equal(t, expected, sanitizer.Sanitize(str))
}
func TestSanitizerStringWithATagAndHref(t *testing.T) {
str := "simple text message with <a href=\"http://evil.site\">a link to another page</a>"
expected := "simple text message with a link to another page"
assert.Equal(t, expected, sanitizer.Sanitize(str))
}
func TestSanitizerStringWithImgTag(t *testing.T) {
str := "simple text message with a <img alt=\"not found\" src=\"http://evil.site\">"
expected := "simple text message with a "
assert.Equal(t, expected, sanitizer.Sanitize(str))
}
func TestSanitizerStringWithImgTagAndOnerrorAttribute(t *testing.T) {
str := "simple text message with a <img alt=\"not found\" src=\"http://evil.site\" onerror=\"alert(secret)\">"
expected := "simple text message with a "
assert.Equal(t, expected, sanitizer.Sanitize(str))
}

53
html/templates/error.html Normal file
View file

@ -0,0 +1,53 @@
<!doctype html>
<html class="codeberg-design">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width" />
<title>{{.StatusText}}</title>
<link rel="stylesheet" href="https://design.codeberg.org/design-kit/codeberg.css" />
<link rel="stylesheet" href="https://fonts.codeberg.org/dist/inter/Inter%20Web/inter.css" />
<style>
body {
margin: 0;
padding: 1rem;
box-sizing: border-box;
width: 100%;
min-height: 100vh;
display: flex;
flex-direction: column;
align-items: center;
justify-content: center;
}
code {
border-radius: 0.25rem;
padding: 0.25rem;
background-color: silver;
}
</style>
</head>
<body>
<svg xmlns="http://www.w3.org/2000/svg" height="10em" viewBox="0 0 24 24" fill="var(--blue-color)">
<path
d="M 9 2 C 5.1458514 2 2 5.1458514 2 9 C 2 12.854149 5.1458514 16 9 16 C 10.747998 16 12.345009 15.348024 13.574219 14.28125 L 14 14.707031 L 14 16 L 19.585938 21.585938 C 20.137937 22.137937 21.033938 22.137938 21.585938 21.585938 C 22.137938 21.033938 22.137938 20.137938 21.585938 19.585938 L 16 14 L 14.707031 14 L 14.28125 13.574219 C 15.348024 12.345009 16 10.747998 16 9 C 16 5.1458514 12.854149 2 9 2 z M 9 4 C 11.773268 4 14 6.2267316 14 9 C 14 11.773268 11.773268 14 9 14 C 6.2267316 14 4 11.773268 4 9 C 4 6.2267316 6.2267316 4 9 4 z"
/>
</svg>
<h1 class="mb-0 text-primary">{{.StatusText}} ({{.StatusCode}})!</h1>
<h5 class="text-center" style="max-width: 25em">
<p>Sorry, but this page couldn't be served.</p>
<p><b>"{{.Message}}"</b></p>
<p>
We hope this isn't a problem on our end ;) - Make sure to check the
<a href="https://docs.codeberg.org/codeberg-pages/troubleshooting/" target="_blank"
>troubleshooting section in the Docs</a
>!
</p>
</h5>
<small class="text-muted">
<img src="https://design.codeberg.org/logo-kit/icon.svg" class="align-top" />
Static pages made easy -
<a href="https://codeberg.page">Codeberg Pages</a>
</small>
</body>
</html>

282
integration/get_test.go Normal file
View file

@ -0,0 +1,282 @@
//go:build integration
// +build integration
package integration
import (
"bytes"
"crypto/tls"
"io"
"log"
"net/http"
"net/http/cookiejar"
"strings"
"testing"
"github.com/stretchr/testify/assert"
)
func TestGetRedirect(t *testing.T) {
log.Println("=== TestGetRedirect ===")
// test custom domain redirect
resp, err := getTestHTTPSClient().Get("https://calciumdibromid.localhost.mock.directory:4430")
if !assert.NoError(t, err) {
t.FailNow()
}
if !assert.EqualValues(t, http.StatusTemporaryRedirect, resp.StatusCode) {
t.FailNow()
}
assert.EqualValues(t, "https://www.cabr2.de/", resp.Header.Get("Location"))
assert.EqualValues(t, `<a href="https://www.cabr2.de/">Temporary Redirect</a>.`, strings.TrimSpace(string(getBytes(resp.Body))))
}
func TestGetContent(t *testing.T) {
log.Println("=== TestGetContent ===")
// test get image
resp, err := getTestHTTPSClient().Get("https://cb_pages_tests.localhost.mock.directory:4430/images/827679288a.jpg")
assert.NoError(t, err)
if !assert.EqualValues(t, http.StatusOK, resp.StatusCode) {
t.FailNow()
}
assert.EqualValues(t, "image/jpeg", resp.Header.Get("Content-Type"))
assert.EqualValues(t, "124635", resp.Header.Get("Content-Length"))
assert.EqualValues(t, 124635, getSize(resp.Body))
assert.Len(t, resp.Header.Get("ETag"), 42)
// specify branch
resp, err = getTestHTTPSClient().Get("https://cb_pages_tests.localhost.mock.directory:4430/pag/@master/")
assert.NoError(t, err)
if !assert.NotNil(t, resp) {
t.FailNow()
}
assert.EqualValues(t, http.StatusOK, resp.StatusCode)
assert.EqualValues(t, "text/html; charset=utf-8", resp.Header.Get("Content-Type"))
assert.True(t, getSize(resp.Body) > 1000)
assert.Len(t, resp.Header.Get("ETag"), 44)
// access branch name contains '/'
resp, err = getTestHTTPSClient().Get("https://cb_pages_tests.localhost.mock.directory:4430/blumia/@docs~main/")
assert.NoError(t, err)
if !assert.EqualValues(t, http.StatusOK, resp.StatusCode) {
t.FailNow()
}
assert.EqualValues(t, "text/html; charset=utf-8", resp.Header.Get("Content-Type"))
assert.True(t, getSize(resp.Body) > 100)
assert.Len(t, resp.Header.Get("ETag"), 44)
// TODO: test get of non cacheable content (content size > fileCacheSizeLimit)
}
func TestCustomDomain(t *testing.T) {
log.Println("=== TestCustomDomain ===")
resp, err := getTestHTTPSClient().Get("https://mock-pages.codeberg-test.org:4430/README.md")
assert.NoError(t, err)
if !assert.NotNil(t, resp) {
t.FailNow()
}
assert.EqualValues(t, http.StatusOK, resp.StatusCode)
assert.EqualValues(t, "text/markdown; charset=utf-8", resp.Header.Get("Content-Type"))
assert.EqualValues(t, "106", resp.Header.Get("Content-Length"))
assert.EqualValues(t, 106, getSize(resp.Body))
}
func TestCustomDomainRedirects(t *testing.T) {
log.Println("=== TestCustomDomainRedirects ===")
// test redirect from default pages domain to custom domain
resp, err := getTestHTTPSClient().Get("https://6543.localhost.mock.directory:4430/test_pages-server_custom-mock-domain/@main/README.md")
assert.NoError(t, err)
if !assert.NotNil(t, resp) {
t.FailNow()
}
assert.EqualValues(t, http.StatusTemporaryRedirect, resp.StatusCode)
assert.EqualValues(t, "text/html; charset=utf-8", resp.Header.Get("Content-Type"))
// TODO: custom port is not evaluated (witch does hurt tests & dev env only)
// assert.EqualValues(t, "https://mock-pages.codeberg-test.org:4430/@main/README.md", resp.Header.Get("Location"))
assert.EqualValues(t, "https://mock-pages.codeberg-test.org/@main/README.md", resp.Header.Get("Location"))
assert.EqualValues(t, `https:/codeberg.org/6543/test_pages-server_custom-mock-domain/src/branch/main/README.md; rel="canonical"; rel="canonical"`, resp.Header.Get("Link"))
// test redirect from an custom domain to the primary custom domain (www.example.com -> example.com)
// regression test to https://codeberg.org/Codeberg/pages-server/issues/153
resp, err = getTestHTTPSClient().Get("https://mock-pages-redirect.codeberg-test.org:4430/README.md")
assert.NoError(t, err)
if !assert.NotNil(t, resp) {
t.FailNow()
}
assert.EqualValues(t, http.StatusTemporaryRedirect, resp.StatusCode)
assert.EqualValues(t, "text/html; charset=utf-8", resp.Header.Get("Content-Type"))
// TODO: custom port is not evaluated (witch does hurt tests & dev env only)
// assert.EqualValues(t, "https://mock-pages.codeberg-test.org:4430/README.md", resp.Header.Get("Location"))
assert.EqualValues(t, "https://mock-pages.codeberg-test.org/README.md", resp.Header.Get("Location"))
}
func TestRawCustomDomain(t *testing.T) {
log.Println("=== TestRawCustomDomain ===")
// test raw domain response for custom domain branch
resp, err := getTestHTTPSClient().Get("https://raw.localhost.mock.directory:4430/cb_pages_tests/raw-test/example") // need cb_pages_tests fork
assert.NoError(t, err)
if !assert.NotNil(t, resp) {
t.FailNow()
}
assert.EqualValues(t, http.StatusOK, resp.StatusCode)
assert.EqualValues(t, "text/plain; charset=utf-8", resp.Header.Get("Content-Type"))
assert.EqualValues(t, "76", resp.Header.Get("Content-Length"))
assert.EqualValues(t, 76, getSize(resp.Body))
}
func TestRawIndex(t *testing.T) {
log.Println("=== TestRawIndex ===")
// test raw domain response for index.html
resp, err := getTestHTTPSClient().Get("https://raw.localhost.mock.directory:4430/cb_pages_tests/raw-test/@branch-test/index.html") // need cb_pages_tests fork
assert.NoError(t, err)
if !assert.NotNil(t, resp) {
t.FailNow()
}
assert.EqualValues(t, http.StatusOK, resp.StatusCode)
assert.EqualValues(t, "text/plain; charset=utf-8", resp.Header.Get("Content-Type"))
assert.EqualValues(t, "597", resp.Header.Get("Content-Length"))
assert.EqualValues(t, 597, getSize(resp.Body))
}
func TestGetNotFound(t *testing.T) {
log.Println("=== TestGetNotFound ===")
// test custom not found pages
resp, err := getTestHTTPSClient().Get("https://cb_pages_tests.localhost.mock.directory:4430/pages-404-demo/blah")
assert.NoError(t, err)
if !assert.NotNil(t, resp) {
t.FailNow()
}
assert.EqualValues(t, http.StatusNotFound, resp.StatusCode)
assert.EqualValues(t, "text/html; charset=utf-8", resp.Header.Get("Content-Type"))
assert.EqualValues(t, "37", resp.Header.Get("Content-Length"))
assert.EqualValues(t, 37, getSize(resp.Body))
}
func TestRedirect(t *testing.T) {
log.Println("=== TestRedirect ===")
// test redirects
resp, err := getTestHTTPSClient().Get("https://cb_pages_tests.localhost.mock.directory:4430/some_redirects/redirect")
assert.NoError(t, err)
if !assert.NotNil(t, resp) {
t.FailNow()
}
assert.EqualValues(t, http.StatusMovedPermanently, resp.StatusCode)
assert.EqualValues(t, "https://example.com/", resp.Header.Get("Location"))
}
func TestSPARedirect(t *testing.T) {
log.Println("=== TestSPARedirect ===")
// test SPA redirects
url := "https://cb_pages_tests.localhost.mock.directory:4430/some_redirects/app/aqdjw"
resp, err := getTestHTTPSClient().Get(url)
assert.NoError(t, err)
if !assert.NotNil(t, resp) {
t.FailNow()
}
assert.EqualValues(t, http.StatusOK, resp.StatusCode)
assert.EqualValues(t, url, resp.Request.URL.String())
assert.EqualValues(t, "text/html; charset=utf-8", resp.Header.Get("Content-Type"))
assert.EqualValues(t, "258", resp.Header.Get("Content-Length"))
assert.EqualValues(t, 258, getSize(resp.Body))
}
func TestSplatRedirect(t *testing.T) {
log.Println("=== TestSplatRedirect ===")
// test splat redirects
resp, err := getTestHTTPSClient().Get("https://cb_pages_tests.localhost.mock.directory:4430/some_redirects/articles/qfopefe")
assert.NoError(t, err)
if !assert.NotNil(t, resp) {
t.FailNow()
}
assert.EqualValues(t, http.StatusMovedPermanently, resp.StatusCode)
assert.EqualValues(t, "/posts/qfopefe", resp.Header.Get("Location"))
}
func TestFollowSymlink(t *testing.T) {
log.Printf("=== TestFollowSymlink ===\n")
// file symlink
resp, err := getTestHTTPSClient().Get("https://cb_pages_tests.localhost.mock.directory:4430/tests_for_pages-server/@main/link")
assert.NoError(t, err)
if !assert.NotNil(t, resp) {
t.FailNow()
}
assert.EqualValues(t, http.StatusOK, resp.StatusCode)
assert.EqualValues(t, "application/octet-stream", resp.Header.Get("Content-Type"))
assert.EqualValues(t, "4", resp.Header.Get("Content-Length"))
body := getBytes(resp.Body)
assert.EqualValues(t, 4, len(body))
assert.EqualValues(t, "abc\n", string(body))
// relative file links (../index.html file in this case)
resp, err = getTestHTTPSClient().Get("https://cb_pages_tests.localhost.mock.directory:4430/tests_for_pages-server/@main/dir_aim/some/")
assert.NoError(t, err)
if !assert.NotNil(t, resp) {
t.FailNow()
}
assert.EqualValues(t, http.StatusOK, resp.StatusCode)
assert.EqualValues(t, "text/html; charset=utf-8", resp.Header.Get("Content-Type"))
assert.EqualValues(t, "an index\n", string(getBytes(resp.Body)))
}
func TestLFSSupport(t *testing.T) {
log.Printf("=== TestLFSSupport ===\n")
resp, err := getTestHTTPSClient().Get("https://cb_pages_tests.localhost.mock.directory:4430/tests_for_pages-server/@main/lfs.txt")
assert.NoError(t, err)
if !assert.NotNil(t, resp) {
t.FailNow()
}
assert.EqualValues(t, http.StatusOK, resp.StatusCode)
body := strings.TrimSpace(string(getBytes(resp.Body)))
assert.EqualValues(t, 12, len(body))
assert.EqualValues(t, "actual value", body)
}
func TestGetOptions(t *testing.T) {
log.Println("=== TestGetOptions ===")
req, _ := http.NewRequest(http.MethodOptions, "https://mock-pages.codeberg-test.org:4430/README.md", http.NoBody)
resp, err := getTestHTTPSClient().Do(req)
assert.NoError(t, err)
if !assert.NotNil(t, resp) {
t.FailNow()
}
assert.EqualValues(t, http.StatusNoContent, resp.StatusCode)
assert.EqualValues(t, "GET, HEAD, OPTIONS", resp.Header.Get("Allow"))
}
func TestHttpRedirect(t *testing.T) {
log.Println("=== TestHttpRedirect ===")
resp, err := getTestHTTPSClient().Get("http://mock-pages.codeberg-test.org:8880/README.md")
assert.NoError(t, err)
if !assert.NotNil(t, resp) {
t.FailNow()
}
assert.EqualValues(t, http.StatusMovedPermanently, resp.StatusCode)
assert.EqualValues(t, "text/html; charset=utf-8", resp.Header.Get("Content-Type"))
assert.EqualValues(t, "https://mock-pages.codeberg-test.org:4430/README.md", resp.Header.Get("Location"))
}
func getTestHTTPSClient() *http.Client {
cookieJar, _ := cookiejar.New(nil)
return &http.Client{
Jar: cookieJar,
CheckRedirect: func(_ *http.Request, _ []*http.Request) error {
return http.ErrUseLastResponse
},
Transport: &http.Transport{
TLSClientConfig: &tls.Config{InsecureSkipVerify: true},
},
}
}
func getBytes(stream io.Reader) []byte {
buf := new(bytes.Buffer)
_, _ = buf.ReadFrom(stream)
return buf.Bytes()
}
func getSize(stream io.Reader) int {
buf := new(bytes.Buffer)
_, _ = buf.ReadFrom(stream)
return buf.Len()
}

69
integration/main_test.go Normal file
View file

@ -0,0 +1,69 @@
//go:build integration
// +build integration
package integration
import (
"context"
"log"
"os"
"testing"
"time"
"github.com/urfave/cli/v2"
cmd "codeberg.org/codeberg/pages/cli"
"codeberg.org/codeberg/pages/server"
)
func TestMain(m *testing.M) {
log.Println("=== TestMain: START Server ===")
serverCtx, serverCancel := context.WithCancel(context.Background())
if err := startServer(serverCtx); err != nil {
log.Fatalf("could not start server: %v", err)
}
defer func() {
serverCancel()
log.Println("=== TestMain: Server STOPPED ===")
}()
time.Sleep(10 * time.Second)
m.Run()
}
func startServer(ctx context.Context) error {
args := []string{"integration"}
setEnvIfNotSet("ACME_API", "https://acme.mock.directory")
setEnvIfNotSet("PAGES_DOMAIN", "localhost.mock.directory")
setEnvIfNotSet("RAW_DOMAIN", "raw.localhost.mock.directory")
setEnvIfNotSet("PAGES_BRANCHES", "pages,main,master")
setEnvIfNotSet("PORT", "4430")
setEnvIfNotSet("HTTP_PORT", "8880")
setEnvIfNotSet("ENABLE_HTTP_SERVER", "true")
setEnvIfNotSet("DB_TYPE", "sqlite3")
setEnvIfNotSet("GITEA_ROOT", "https://codeberg.org")
setEnvIfNotSet("LOG_LEVEL", "trace")
setEnvIfNotSet("ENABLE_LFS_SUPPORT", "true")
setEnvIfNotSet("ENABLE_SYMLINK_SUPPORT", "true")
setEnvIfNotSet("ACME_ACCOUNT_CONFIG", "integration/acme-account.json")
app := cli.NewApp()
app.Name = "pages-server"
app.Action = server.Serve
app.Flags = cmd.ServerFlags
go func() {
if err := app.RunContext(ctx, args); err != nil {
log.Fatalf("run server error: %v", err)
}
}()
return nil
}
func setEnvIfNotSet(key, value string) {
if _, set := os.LookupEnv(key); !set {
os.Setenv(key, value)
}
}

21
main.go Normal file
View file

@ -0,0 +1,21 @@
package main
import (
"os"
_ "github.com/joho/godotenv/autoload"
"github.com/rs/zerolog/log"
"pages-server/cli"
"pages-server/server"
)
func main() {
app := cli.CreatePagesApp()
app.Action = server.Serve
if err := app.Run(os.Args); err != nil {
log.Error().Err(err).Msg("A fatal error occurred")
os.Exit(1)
}
}

27
renovate.json Normal file
View file

@ -0,0 +1,27 @@
{
"$schema": "https://docs.renovatebot.com/renovate-schema.json",
"extends": [
"config:recommended",
":maintainLockFilesWeekly",
":enablePreCommit",
"schedule:automergeDaily",
"schedule:weekends"
],
"automergeType": "branch",
"automergeMajor": false,
"automerge": true,
"prConcurrentLimit": 5,
"labels": ["dependencies"],
"packageRules": [
{
"matchManagers": ["gomod", "dockerfile"]
},
{
"groupName": "golang deps non-major",
"matchManagers": ["gomod"],
"matchUpdateTypes": ["minor", "patch"],
"extends": ["schedule:daily"]
}
],
"postUpdateOptions": ["gomodTidy", "gomodUpdateImportPaths"]
}

10
server/cache/interface.go vendored Normal file
View file

@ -0,0 +1,10 @@
package cache
import "time"
// ICache is an interface that defines how the pages server interacts with the cache.
type ICache interface {
Set(key string, value interface{}, ttl time.Duration) error
Get(key string) (interface{}, bool)
Remove(key string)
}

7
server/cache/memory.go vendored Normal file
View file

@ -0,0 +1,7 @@
package cache
import "github.com/OrlovEvgeny/go-mcache"
func NewInMemoryCache() ICache {
return mcache.New()
}

62
server/context/context.go Normal file
View file

@ -0,0 +1,62 @@
package context
import (
stdContext "context"
"net/http"
"pages-server/server/utils"
)
type Context struct {
RespWriter http.ResponseWriter
Req *http.Request
StatusCode int
}
func New(w http.ResponseWriter, r *http.Request) *Context {
return &Context{
RespWriter: w,
Req: r,
StatusCode: http.StatusOK,
}
}
func (c *Context) Context() stdContext.Context {
if c.Req != nil {
return c.Req.Context()
}
return stdContext.Background()
}
func (c *Context) Response() *http.Response {
if c.Req != nil && c.Req.Response != nil {
return c.Req.Response
}
return nil
}
func (c *Context) String(raw string, status ...int) {
code := http.StatusOK
if len(status) != 0 {
code = status[0]
}
c.RespWriter.WriteHeader(code)
_, _ = c.RespWriter.Write([]byte(raw))
}
func (c *Context) Redirect(uri string, statusCode int) {
http.Redirect(c.RespWriter, c.Req, uri, statusCode)
}
// Path returns the cleaned requested path.
func (c *Context) Path() string {
return utils.CleanPath(c.Req.URL.Path)
}
func (c *Context) Host() string {
return c.Req.URL.Host
}
func (c *Context) TrimHostPort() string {
return utils.TrimHostPort(c.Req.Host)
}

66
server/dns/dns.go Normal file
View file

@ -0,0 +1,66 @@
package dns
import (
"net"
"strings"
"time"
"github.com/hashicorp/golang-lru/v2/expirable"
)
const (
lookupCacheValidity = 30 * time.Second
defaultPagesRepo = "pages"
)
// TODO(#316): refactor to not use global variables
var lookupCache *expirable.LRU[string, string] = expirable.NewLRU[string, string](4096, nil, lookupCacheValidity)
// GetTargetFromDNS searches for CNAME or TXT entries on the request domain ending with MainDomainSuffix.
// If everything is fine, it returns the target data.
func GetTargetFromDNS(domain, mainDomainSuffix, firstDefaultBranch string) (targetOwner, targetRepo, targetBranch string) {
// Get CNAME or TXT
var cname string
var err error
if entry, ok := lookupCache.Get(domain); ok {
cname = entry
} else {
cname, err = net.LookupCNAME(domain)
cname = strings.TrimSuffix(cname, ".")
if err != nil || !strings.HasSuffix(cname, mainDomainSuffix) {
cname = ""
// TODO: check if the A record matches!
names, err := net.LookupTXT(domain)
if err == nil {
for _, name := range names {
name = strings.TrimSuffix(strings.TrimSpace(name), ".")
if strings.HasSuffix(name, mainDomainSuffix) {
cname = name
break
}
}
}
}
_ = lookupCache.Add(domain, cname)
}
if cname == "" {
return
}
cnameParts := strings.Split(strings.TrimSuffix(cname, mainDomainSuffix), ".")
targetOwner = cnameParts[len(cnameParts)-1]
if len(cnameParts) > 1 {
targetRepo = cnameParts[len(cnameParts)-2]
}
if len(cnameParts) > 2 {
targetBranch = cnameParts[len(cnameParts)-3]
}
if targetRepo == "" {
targetRepo = defaultPagesRepo
}
if targetBranch == "" && targetRepo != defaultPagesRepo {
targetBranch = firstDefaultBranch
}
// if targetBranch is still empty, the caller must find the default branch
return
}

127
server/gitea/cache.go Normal file
View file

@ -0,0 +1,127 @@
package gitea
import (
"bytes"
"fmt"
"io"
"net/http"
"time"
"github.com/rs/zerolog/log"
"pages-server/server/cache"
)
const (
// defaultBranchCacheTimeout specifies the timeout for the default branch cache. It can be quite long.
defaultBranchCacheTimeout = 15 * time.Minute
// branchExistenceCacheTimeout specifies the timeout for the branch timestamp & existence cache. It should be shorter
// than fileCacheTimeout, as that gets invalidated if the branch timestamp has changed. That way, repo changes will be
// picked up faster, while still allowing the content to be cached longer if nothing changes.
branchExistenceCacheTimeout = 5 * time.Minute
// fileCacheTimeout specifies the timeout for the file content cache - you might want to make this quite long, depending
// on your available memory.
// TODO: move as option into cache interface
fileCacheTimeout = 5 * time.Minute
// ownerExistenceCacheTimeout specifies the timeout for the existence of a repo/org
ownerExistenceCacheTimeout = 5 * time.Minute
// fileCacheSizeLimit limits the maximum file size that will be cached, and is set to 1 MB by default.
fileCacheSizeLimit = int64(1000 * 1000)
)
type FileResponse struct {
Exists bool
IsSymlink bool
ETag string
MimeType string
Body []byte
}
func (f FileResponse) IsEmpty() bool {
return len(f.Body) == 0
}
func (f FileResponse) createHttpResponse(cacheKey string) (header http.Header, statusCode int) {
header = make(http.Header)
if f.Exists {
statusCode = http.StatusOK
} else {
statusCode = http.StatusNotFound
}
if f.IsSymlink {
header.Set(giteaObjectTypeHeader, objTypeSymlink)
}
header.Set(ETagHeader, f.ETag)
header.Set(ContentTypeHeader, f.MimeType)
header.Set(ContentLengthHeader, fmt.Sprintf("%d", len(f.Body)))
header.Set(PagesCacheIndicatorHeader, "true")
log.Trace().Msgf("fileCache for %q used", cacheKey)
return header, statusCode
}
type BranchTimestamp struct {
Branch string
Timestamp time.Time
notFound bool
}
type writeCacheReader struct {
originalReader io.ReadCloser
buffer *bytes.Buffer
fileResponse *FileResponse
cacheKey string
cache cache.ICache
hasError bool
}
func (t *writeCacheReader) Read(p []byte) (n int, err error) {
log.Trace().Msgf("[cache] read %q", t.cacheKey)
n, err = t.originalReader.Read(p)
if err != nil && err != io.EOF {
log.Trace().Err(err).Msgf("[cache] original reader for %q has returned an error", t.cacheKey)
t.hasError = true
} else if n > 0 {
_, _ = t.buffer.Write(p[:n])
}
return
}
func (t *writeCacheReader) Close() error {
doWrite := !t.hasError
fc := *t.fileResponse
fc.Body = t.buffer.Bytes()
if fc.IsEmpty() {
log.Trace().Msg("[cache] file response is empty")
doWrite = false
}
if doWrite {
err := t.cache.Set(t.cacheKey, fc, fileCacheTimeout)
if err != nil {
log.Trace().Err(err).Msgf("[cache] writer for %q has returned an error", t.cacheKey)
}
}
log.Trace().Msgf("cacheReader for %q saved=%t closed", t.cacheKey, doWrite)
return t.originalReader.Close()
}
func (f FileResponse) CreateCacheReader(r io.ReadCloser, cache cache.ICache, cacheKey string) io.ReadCloser {
if r == nil || cache == nil || cacheKey == "" {
log.Error().Msg("could not create CacheReader")
return nil
}
return &writeCacheReader{
originalReader: r,
buffer: bytes.NewBuffer(make([]byte, 0)),
fileResponse: &f,
cache: cache,
cacheKey: cacheKey,
}
}

330
server/gitea/client.go Normal file
View file

@ -0,0 +1,330 @@
package gitea
import (
"bytes"
"errors"
"fmt"
"io"
"mime"
"net/http"
"net/url"
"path"
"strconv"
"strings"
"time"
"code.gitea.io/sdk/gitea"
"github.com/rs/zerolog/log"
"pages-server/config"
"pages-server/server/cache"
"pages-server/server/version"
)
var ErrorNotFound = errors.New("not found")
const (
// cache key prefixes
branchTimestampCacheKeyPrefix = "branchTime"
defaultBranchCacheKeyPrefix = "defaultBranch"
rawContentCacheKeyPrefix = "rawContent"
ownerExistenceKeyPrefix = "ownerExist"
// pages server
PagesCacheIndicatorHeader = "X-Pages-Cache"
symlinkReadLimit = 10000
// gitea
giteaObjectTypeHeader = "X-Gitea-Object-Type"
objTypeSymlink = "symlink"
// std
ETagHeader = "ETag"
ContentTypeHeader = "Content-Type"
ContentLengthHeader = "Content-Length"
)
type Client struct {
sdkClient *gitea.Client
responseCache cache.ICache
giteaRoot string
followSymlinks bool
supportLFS bool
forbiddenMimeTypes map[string]bool
defaultMimeType string
}
func NewClient(cfg config.ForgeConfig, respCache cache.ICache) (*Client, error) {
// url.Parse returns valid on almost anything...
rootURL, err := url.ParseRequestURI(cfg.Root)
if err != nil {
return nil, fmt.Errorf("invalid forgejo/gitea root url: %w", err)
}
giteaRoot := strings.TrimSuffix(rootURL.String(), "/")
stdClient := http.Client{Timeout: 10 * time.Second}
forbiddenMimeTypes := make(map[string]bool, len(cfg.ForbiddenMimeTypes))
for _, mimeType := range cfg.ForbiddenMimeTypes {
forbiddenMimeTypes[mimeType] = true
}
defaultMimeType := cfg.DefaultMimeType
if defaultMimeType == "" {
defaultMimeType = "application/octet-stream"
}
sdk, err := gitea.NewClient(
giteaRoot,
gitea.SetHTTPClient(&stdClient),
gitea.SetToken(cfg.Token),
gitea.SetUserAgent("pages-server/"+version.Version),
)
return &Client{
sdkClient: sdk,
responseCache: respCache,
giteaRoot: giteaRoot,
followSymlinks: cfg.FollowSymlinks,
supportLFS: cfg.LFSEnabled,
forbiddenMimeTypes: forbiddenMimeTypes,
defaultMimeType: defaultMimeType,
}, err
}
func (client *Client) ContentWebLink(targetOwner, targetRepo, branch, resource string) string {
return path.Join(client.giteaRoot, targetOwner, targetRepo, "src/branch", branch, resource)
}
func (client *Client) GiteaRawContent(targetOwner, targetRepo, ref, resource string) ([]byte, error) {
reader, _, _, err := client.ServeRawContent(targetOwner, targetRepo, ref, resource)
if err != nil {
return nil, err
}
defer reader.Close()
return io.ReadAll(reader)
}
func (client *Client) ServeRawContent(targetOwner, targetRepo, ref, resource string) (io.ReadCloser, http.Header, int, error) {
cacheKey := fmt.Sprintf("%s/%s/%s|%s|%s", rawContentCacheKeyPrefix, targetOwner, targetRepo, ref, resource)
log := log.With().Str("cache_key", cacheKey).Logger()
log.Trace().Msg("try file in cache")
// handle if cache entry exist
if cache, ok := client.responseCache.Get(cacheKey); ok {
cache := cache.(FileResponse)
cachedHeader, cachedStatusCode := cache.createHttpResponse(cacheKey)
// TODO: check against some timestamp mismatch?!?
if cache.Exists {
log.Debug().Msg("[cache] exists")
if cache.IsSymlink {
linkDest := string(cache.Body)
log.Debug().Msgf("[cache] follow symlink from %q to %q", resource, linkDest)
return client.ServeRawContent(targetOwner, targetRepo, ref, linkDest)
} else if !cache.IsEmpty() {
log.Debug().Msgf("[cache] return %d bytes", len(cache.Body))
return io.NopCloser(bytes.NewReader(cache.Body)), cachedHeader, cachedStatusCode, nil
} else if cache.IsEmpty() {
log.Debug().Msg("[cache] is empty")
}
}
}
log.Trace().Msg("file not in cache")
// not in cache, open reader via gitea api
reader, resp, err := client.sdkClient.GetFileReader(targetOwner, targetRepo, ref, resource, client.supportLFS)
if resp != nil {
switch resp.StatusCode {
case http.StatusOK:
// first handle symlinks
{
objType := resp.Header.Get(giteaObjectTypeHeader)
log.Trace().Msgf("server raw content object %q", objType)
if client.followSymlinks && objType == objTypeSymlink {
defer reader.Close()
// read limited chars for symlink
linkDestBytes, err := io.ReadAll(io.LimitReader(reader, symlinkReadLimit))
if err != nil {
return nil, nil, http.StatusInternalServerError, err
}
linkDest := strings.TrimSpace(string(linkDestBytes))
// handle relative links
// we first remove the link from the path, and make a relative join (resolve parent paths like "/../" too)
linkDest = path.Join(path.Dir(resource), linkDest)
// we store symlink not content to reduce duplicates in cache
fileResponse := FileResponse{
Exists: true,
IsSymlink: true,
Body: []byte(linkDest),
ETag: resp.Header.Get(ETagHeader),
}
log.Trace().Msgf("file response has %d bytes", len(fileResponse.Body))
if err := client.responseCache.Set(cacheKey, fileResponse, fileCacheTimeout); err != nil {
log.Error().Err(err).Msg("[cache] error on cache write")
}
log.Debug().Msgf("follow symlink from %q to %q", resource, linkDest)
return client.ServeRawContent(targetOwner, targetRepo, ref, linkDest)
}
}
// now we are sure it's content so set the MIME type
mimeType := client.getMimeTypeByExtension(resource)
resp.Response.Header.Set(ContentTypeHeader, mimeType)
if !shouldRespBeSavedToCache(resp.Response) {
return reader, resp.Response.Header, resp.StatusCode, err
}
// now we write to cache and respond at the same time
fileResp := FileResponse{
Exists: true,
ETag: resp.Header.Get(ETagHeader),
MimeType: mimeType,
}
return fileResp.CreateCacheReader(reader, client.responseCache, cacheKey), resp.Response.Header, resp.StatusCode, nil
case http.StatusNotFound:
if err := client.responseCache.Set(cacheKey, FileResponse{
Exists: false,
ETag: resp.Header.Get(ETagHeader),
}, fileCacheTimeout); err != nil {
log.Error().Err(err).Msg("[cache] error on cache write")
}
return nil, resp.Response.Header, http.StatusNotFound, ErrorNotFound
default:
return nil, resp.Response.Header, resp.StatusCode, fmt.Errorf("unexpected status code '%d'", resp.StatusCode)
}
}
return nil, nil, http.StatusInternalServerError, err
}
func (client *Client) GiteaGetRepoBranchTimestamp(repoOwner, repoName, branchName string) (*BranchTimestamp, error) {
cacheKey := fmt.Sprintf("%s/%s/%s/%s", branchTimestampCacheKeyPrefix, repoOwner, repoName, branchName)
if stamp, ok := client.responseCache.Get(cacheKey); ok && stamp != nil {
branchTimeStamp := stamp.(*BranchTimestamp)
if branchTimeStamp.notFound {
log.Trace().Msgf("[cache] use branch %q not found", branchName)
return &BranchTimestamp{}, ErrorNotFound
}
log.Trace().Msgf("[cache] use branch %q exist", branchName)
return branchTimeStamp, nil
}
branch, resp, err := client.sdkClient.GetRepoBranch(repoOwner, repoName, branchName)
if err != nil {
if resp != nil && resp.StatusCode == http.StatusNotFound {
log.Trace().Msgf("[cache] set cache branch %q not found", branchName)
if err := client.responseCache.Set(cacheKey, &BranchTimestamp{Branch: branchName, notFound: true}, branchExistenceCacheTimeout); err != nil {
log.Error().Err(err).Msg("[cache] error on cache write")
}
return &BranchTimestamp{}, ErrorNotFound
}
return &BranchTimestamp{}, err
}
if resp.StatusCode != http.StatusOK {
return &BranchTimestamp{}, fmt.Errorf("unexpected status code '%d'", resp.StatusCode)
}
stamp := &BranchTimestamp{
Branch: branch.Name,
Timestamp: branch.Commit.Timestamp,
}
log.Trace().Msgf("set cache branch [%s] exist", branchName)
if err := client.responseCache.Set(cacheKey, stamp, branchExistenceCacheTimeout); err != nil {
log.Error().Err(err).Msg("[cache] error on cache write")
}
return stamp, nil
}
func (client *Client) GiteaGetRepoDefaultBranch(repoOwner, repoName string) (string, error) {
cacheKey := fmt.Sprintf("%s/%s/%s", defaultBranchCacheKeyPrefix, repoOwner, repoName)
if branch, ok := client.responseCache.Get(cacheKey); ok && branch != nil {
return branch.(string), nil
}
repo, resp, err := client.sdkClient.GetRepo(repoOwner, repoName)
if err != nil {
return "", err
}
if resp.StatusCode != http.StatusOK {
return "", fmt.Errorf("unexpected status code '%d'", resp.StatusCode)
}
branch := repo.DefaultBranch
if err := client.responseCache.Set(cacheKey, branch, defaultBranchCacheTimeout); err != nil {
log.Error().Err(err).Msg("[cache] error on cache write")
}
return branch, nil
}
func (client *Client) GiteaCheckIfOwnerExists(owner string) (bool, error) {
cacheKey := fmt.Sprintf("%s/%s", ownerExistenceKeyPrefix, owner)
if exist, ok := client.responseCache.Get(cacheKey); ok && exist != nil {
return exist.(bool), nil
}
_, resp, err := client.sdkClient.GetUserInfo(owner)
if resp.StatusCode == http.StatusOK && err == nil {
if err := client.responseCache.Set(cacheKey, true, ownerExistenceCacheTimeout); err != nil {
log.Error().Err(err).Msg("[cache] error on cache write")
}
return true, nil
} else if resp.StatusCode != http.StatusNotFound {
return false, err
}
_, resp, err = client.sdkClient.GetOrg(owner)
if resp.StatusCode == http.StatusOK && err == nil {
if err := client.responseCache.Set(cacheKey, true, ownerExistenceCacheTimeout); err != nil {
log.Error().Err(err).Msg("[cache] error on cache write")
}
return true, nil
} else if resp.StatusCode != http.StatusNotFound {
return false, err
}
if err := client.responseCache.Set(cacheKey, false, ownerExistenceCacheTimeout); err != nil {
log.Error().Err(err).Msg("[cache] error on cache write")
}
return false, nil
}
func (client *Client) getMimeTypeByExtension(resource string) string {
mimeType := mime.TypeByExtension(path.Ext(resource))
mimeTypeSplit := strings.SplitN(mimeType, ";", 2)
if client.forbiddenMimeTypes[mimeTypeSplit[0]] || mimeType == "" {
mimeType = client.defaultMimeType
}
log.Trace().Msgf("probe mime of %q is %q", resource, mimeType)
return mimeType
}
func shouldRespBeSavedToCache(resp *http.Response) bool {
if resp == nil {
return false
}
contentLengthRaw := resp.Header.Get(ContentLengthHeader)
if contentLengthRaw == "" {
return false
}
contentLength, err := strconv.ParseInt(contentLengthRaw, 10, 64)
if err != nil {
log.Error().Err(err).Msg("could not parse content length")
}
// if content to big or could not be determined we not cache it
return contentLength > 0 && contentLength < fileCacheSizeLimit
}

114
server/handler/handler.go Normal file
View file

@ -0,0 +1,114 @@
package handler
import (
"net/http"
"strings"
"github.com/rs/zerolog/log"
"pages-server/config"
"pages-server/html"
"pages-server/server/cache"
"pages-server/server/context"
"pages-server/server/gitea"
)
const (
headerAccessControlAllowOrigin = "Access-Control-Allow-Origin"
headerAccessControlAllowMethods = "Access-Control-Allow-Methods"
defaultPagesRepo = "pages"
)
// Handler handles a single HTTP request to the web server.
func Handler(
cfg config.ServerConfig,
giteaClient *gitea.Client,
canonicalDomainCache, redirectsCache cache.ICache,
) http.HandlerFunc {
return func(w http.ResponseWriter, req *http.Request) {
log.Debug().Msg("\n----------------------------------------------------------")
log := log.With().Strs("Handler", []string{req.Host, req.RequestURI}).Logger()
ctx := context.New(w, req)
ctx.RespWriter.Header().Set("Server", "pages-server")
// Force new default from specification (since November 2020) - see https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Referrer-Policy#strict-origin-when-cross-origin
ctx.RespWriter.Header().Set("Referrer-Policy", "strict-origin-when-cross-origin")
// Enable browser caching for up to 10 minutes
ctx.RespWriter.Header().Set("Cache-Control", "public, max-age=600")
trimmedHost := ctx.TrimHostPort()
// Add HSTS for RawDomain and MainDomain
if hsts := getHSTSHeader(trimmedHost, cfg.MainDomain, cfg.RawDomain); hsts != "" {
ctx.RespWriter.Header().Set("Strict-Transport-Security", hsts)
}
// Handle all http methods
ctx.RespWriter.Header().Set("Allow", http.MethodGet+", "+http.MethodHead+", "+http.MethodOptions)
switch ctx.Req.Method {
case http.MethodOptions:
// return Allow header
ctx.RespWriter.WriteHeader(http.StatusNoContent)
return
case http.MethodGet,
http.MethodHead:
// end switch case and handle allowed requests
break
default:
// Block all methods not required for static pages
ctx.String("Method not allowed", http.StatusMethodNotAllowed)
return
}
// Block blacklisted paths (like ACME challenges)
for _, blacklistedPath := range cfg.BlacklistedPaths {
if strings.HasPrefix(ctx.Path(), blacklistedPath) {
html.ReturnErrorPage(ctx, "requested path is blacklisted", http.StatusForbidden)
return
}
}
// Allow CORS for specified domains
allowCors := false
for _, allowedCorsDomain := range cfg.AllowedCorsDomains {
if strings.EqualFold(trimmedHost, allowedCorsDomain) {
allowCors = true
break
}
}
if allowCors {
ctx.RespWriter.Header().Set(headerAccessControlAllowOrigin, "*")
ctx.RespWriter.Header().Set(headerAccessControlAllowMethods, http.MethodGet+", "+http.MethodHead)
}
// Prepare request information to Gitea
pathElements := strings.Split(strings.Trim(ctx.Path(), "/"), "/")
if cfg.RawDomain != "" && strings.EqualFold(trimmedHost, cfg.RawDomain) {
log.Debug().Msg("raw domain request detected")
handleRaw(log, ctx, giteaClient,
cfg.MainDomain,
trimmedHost,
pathElements,
canonicalDomainCache, redirectsCache)
} else if strings.HasSuffix(trimmedHost, cfg.MainDomain) {
log.Debug().Msg("subdomain request detected")
handleSubDomain(log, ctx, giteaClient,
cfg.MainDomain,
cfg.PagesBranches,
trimmedHost,
pathElements,
canonicalDomainCache, redirectsCache)
} else {
log.Debug().Msg("custom domain request detected")
handleCustomDomain(log, ctx, giteaClient,
cfg.MainDomain,
trimmedHost,
pathElements,
cfg.PagesBranches[0],
canonicalDomainCache, redirectsCache)
}
}
}

View file

@ -0,0 +1,73 @@
package handler
import (
"net/http"
"path"
"strings"
"pages-server/html"
"pages-server/server/cache"
"pages-server/server/context"
"pages-server/server/dns"
"pages-server/server/gitea"
"pages-server/server/upstream"
"github.com/rs/zerolog"
)
func handleCustomDomain(log zerolog.Logger, ctx *context.Context, giteaClient *gitea.Client,
mainDomainSuffix string,
trimmedHost string,
pathElements []string,
firstDefaultBranch string,
canonicalDomainCache, redirectsCache cache.ICache,
) {
// Serve pages from custom domains
targetOwner, targetRepo, targetBranch := dns.GetTargetFromDNS(trimmedHost, mainDomainSuffix, firstDefaultBranch)
if targetOwner == "" {
html.ReturnErrorPage(ctx,
"could not obtain repo owner from custom domain",
http.StatusFailedDependency)
return
}
pathParts := pathElements
canonicalLink := false
if strings.HasPrefix(pathElements[0], "@") {
targetBranch = pathElements[0][1:]
pathParts = pathElements[1:]
canonicalLink = true
}
// Try to use the given repo on the given branch or the default branch
log.Debug().Msg("custom domain preparations, now trying with details from DNS")
if targetOpt, works := tryBranch(log, ctx, giteaClient, &upstream.Options{
TryIndexPages: true,
TargetOwner: targetOwner,
TargetRepo: targetRepo,
TargetBranch: targetBranch,
TargetPath: path.Join(pathParts...),
}, canonicalLink); works {
canonicalDomain, valid := targetOpt.CheckCanonicalDomain(giteaClient, trimmedHost, mainDomainSuffix, canonicalDomainCache)
if !valid {
html.ReturnErrorPage(ctx, "domain not specified in <code>.domains</code> file", http.StatusMisdirectedRequest)
return
} else if canonicalDomain != trimmedHost {
// only redirect if the target is also a codeberg page!
targetOwner, _, _ = dns.GetTargetFromDNS(strings.SplitN(canonicalDomain, "/", 2)[0], mainDomainSuffix, firstDefaultBranch)
if targetOwner != "" {
ctx.Redirect("http://"+canonicalDomain+"/"+targetOpt.TargetPath, http.StatusTemporaryRedirect)
return
}
html.ReturnErrorPage(ctx, "target is no codeberg page", http.StatusFailedDependency)
return
}
log.Debug().Msg("tryBranch, now trying upstream 7")
tryUpstream(ctx, giteaClient, mainDomainSuffix, trimmedHost, targetOpt, canonicalDomainCache, redirectsCache)
return
}
html.ReturnErrorPage(ctx, "could not find target for custom domain", http.StatusFailedDependency)
}

View file

@ -0,0 +1,71 @@
package handler
import (
"fmt"
"net/http"
"path"
"strings"
"github.com/rs/zerolog"
"pages-server/html"
"pages-server/server/cache"
"pages-server/server/context"
"pages-server/server/gitea"
"pages-server/server/upstream"
)
func handleRaw(log zerolog.Logger, ctx *context.Context, giteaClient *gitea.Client,
mainDomainSuffix string,
trimmedHost string,
pathElements []string,
canonicalDomainCache, redirectsCache cache.ICache,
) {
// Serve raw content from RawDomain
log.Debug().Msg("raw domain")
if len(pathElements) < 2 {
html.ReturnErrorPage(
ctx,
"a url in the form of <code>http://{domain}/{owner}/{repo}[/@{branch}]/{path}</code> is required",
http.StatusBadRequest,
)
return
}
// raw.codeberg.org/example/myrepo/@main/index.html
if len(pathElements) > 2 && strings.HasPrefix(pathElements[2], "@") {
log.Debug().Msg("raw domain preparations, now trying with specified branch")
if targetOpt, works := tryBranch(log, ctx, giteaClient, &upstream.Options{
ServeRaw: true,
TargetOwner: pathElements[0],
TargetRepo: pathElements[1],
TargetBranch: pathElements[2][1:],
TargetPath: path.Join(pathElements[3:]...),
}, true); works {
log.Trace().Msg("tryUpstream: serve raw domain with specified branch")
tryUpstream(ctx, giteaClient, mainDomainSuffix, trimmedHost, targetOpt, canonicalDomainCache, redirectsCache)
return
}
log.Debug().Msg("missing branch info")
html.ReturnErrorPage(ctx, "missing branch info", http.StatusFailedDependency)
return
}
log.Debug().Msg("raw domain preparations, now trying with default branch")
if targetOpt, works := tryBranch(log, ctx, giteaClient, &upstream.Options{
TryIndexPages: false,
ServeRaw: true,
TargetOwner: pathElements[0],
TargetRepo: pathElements[1],
TargetPath: path.Join(pathElements[2:]...),
}, true); works {
log.Trace().Msg("tryUpstream: serve raw domain with default branch")
tryUpstream(ctx, giteaClient, mainDomainSuffix, trimmedHost, targetOpt, canonicalDomainCache, redirectsCache)
} else {
html.ReturnErrorPage(ctx,
fmt.Sprintf("raw domain could not find repo <code>%s/%s</code> or repo is empty", targetOpt.TargetOwner, targetOpt.TargetRepo),
http.StatusNotFound)
}
}

View file

@ -0,0 +1,156 @@
package handler
import (
"fmt"
"net/http"
"path"
"strings"
"github.com/rs/zerolog"
"golang.org/x/exp/slices"
"pages-server/html"
"pages-server/server/cache"
"pages-server/server/context"
"pages-server/server/gitea"
"pages-server/server/upstream"
)
func handleSubDomain(log zerolog.Logger, ctx *context.Context, giteaClient *gitea.Client,
mainDomainSuffix string,
defaultPagesBranches []string,
trimmedHost string,
pathElements []string,
canonicalDomainCache, redirectsCache cache.ICache,
) {
// Serve pages from subdomains of MainDomainSuffix
log.Debug().Msg("main domain suffix")
targetOwner := strings.TrimSuffix(trimmedHost, mainDomainSuffix)
targetRepo := pathElements[0]
if targetOwner == "www" {
// www.codeberg.page redirects to codeberg.page // TODO: rm hardcoded - use cname?
ctx.Redirect("http://"+mainDomainSuffix[1:]+ctx.Path(), http.StatusPermanentRedirect)
return
}
// Check if the first directory is a repo with the second directory as a branch
// example.codeberg.page/myrepo/@main/index.html
if len(pathElements) > 1 && strings.HasPrefix(pathElements[1], "@") {
if targetRepo == defaultPagesRepo {
// example.codeberg.org/pages/@... redirects to example.codeberg.org/@...
ctx.Redirect("/"+strings.Join(pathElements[1:], "/"), http.StatusTemporaryRedirect)
return
}
log.Debug().Msg("main domain preparations, now trying with specified repo & branch")
if targetOpt, works := tryBranch(log, ctx, giteaClient, &upstream.Options{
TryIndexPages: true,
TargetOwner: targetOwner,
TargetRepo: pathElements[0],
TargetBranch: pathElements[1][1:],
TargetPath: path.Join(pathElements[2:]...),
}, true); works {
log.Trace().Msg("tryUpstream: serve with specified repo and branch")
tryUpstream(ctx, giteaClient, mainDomainSuffix, trimmedHost, targetOpt, canonicalDomainCache, redirectsCache)
} else {
html.ReturnErrorPage(
ctx,
formatSetBranchNotFoundMessage(pathElements[1][1:], targetOwner, pathElements[0]),
http.StatusFailedDependency,
)
}
return
}
// Check if the first directory is a branch for the defaultPagesRepo
// example.codeberg.page/@main/index.html
if strings.HasPrefix(pathElements[0], "@") {
targetBranch := pathElements[0][1:]
// if the default pages branch can be determined exactly, it does not need to be set
if len(defaultPagesBranches) == 1 && slices.Contains(defaultPagesBranches, targetBranch) {
// example.codeberg.org/@pages/... redirects to example.codeberg.org/...
ctx.Redirect("/"+strings.Join(pathElements[1:], "/"), http.StatusTemporaryRedirect)
return
}
log.Debug().Msg("main domain preparations, now trying with specified branch")
if targetOpt, works := tryBranch(log, ctx, giteaClient, &upstream.Options{
TryIndexPages: true,
TargetOwner: targetOwner,
TargetRepo: defaultPagesRepo,
TargetBranch: targetBranch,
TargetPath: path.Join(pathElements[1:]...),
}, true); works {
log.Trace().Msg("tryUpstream: serve default pages repo with specified branch")
tryUpstream(ctx, giteaClient, mainDomainSuffix, trimmedHost, targetOpt, canonicalDomainCache, redirectsCache)
} else {
html.ReturnErrorPage(
ctx,
formatSetBranchNotFoundMessage(targetBranch, targetOwner, defaultPagesRepo),
http.StatusFailedDependency,
)
}
return
}
for _, defaultPagesBranch := range defaultPagesBranches {
// Check if the first directory is a repo with a default pages branch
// example.codeberg.page/myrepo/index.html
// example.codeberg.page/{PAGES_BRANCHE}/... is not allowed here.
log.Debug().Msg("main domain preparations, now trying with specified repo")
if pathElements[0] != defaultPagesBranch {
if targetOpt, works := tryBranch(log, ctx, giteaClient, &upstream.Options{
TryIndexPages: true,
TargetOwner: targetOwner,
TargetRepo: pathElements[0],
TargetBranch: defaultPagesBranch,
TargetPath: path.Join(pathElements[1:]...),
}, false); works {
log.Debug().Msg("tryBranch, now trying upstream 5")
tryUpstream(ctx, giteaClient, mainDomainSuffix, trimmedHost, targetOpt, canonicalDomainCache, redirectsCache)
return
}
}
// Try to use the defaultPagesRepo on an default pages branch
// example.codeberg.page/index.html
log.Debug().Msg("main domain preparations, now trying with default repo")
if targetOpt, works := tryBranch(log, ctx, giteaClient, &upstream.Options{
TryIndexPages: true,
TargetOwner: targetOwner,
TargetRepo: defaultPagesRepo,
TargetBranch: defaultPagesBranch,
TargetPath: path.Join(pathElements...),
}, false); works {
log.Debug().Msg("tryBranch, now trying upstream 6")
tryUpstream(ctx, giteaClient, mainDomainSuffix, trimmedHost, targetOpt, canonicalDomainCache, redirectsCache)
return
}
}
// Try to use the defaultPagesRepo on its default branch
// example.codeberg.page/index.html
log.Debug().Msg("main domain preparations, now trying with default repo/branch")
if targetOpt, works := tryBranch(log, ctx, giteaClient, &upstream.Options{
TryIndexPages: true,
TargetOwner: targetOwner,
TargetRepo: defaultPagesRepo,
TargetPath: path.Join(pathElements...),
}, false); works {
log.Debug().Msg("tryBranch, now trying upstream 6")
tryUpstream(ctx, giteaClient, mainDomainSuffix, trimmedHost, targetOpt, canonicalDomainCache, redirectsCache)
return
}
// Couldn't find a valid repo/branch
html.ReturnErrorPage(ctx,
fmt.Sprintf("could not find a valid repository or branch for repository: <code>%s</code>", targetRepo),
http.StatusNotFound)
}
func formatSetBranchNotFoundMessage(branch, owner, repo string) string {
return fmt.Sprintf("explicitly set branch <code>%q</code> does not exist at <code>%s/%s</code>", branch, owner, repo)
}

View file

@ -0,0 +1,59 @@
package handler
import (
"net/http"
"net/http/httptest"
"testing"
"time"
"pages-server/config"
"pages-server/server/cache"
"pages-server/server/gitea"
"github.com/rs/zerolog/log"
)
func TestHandlerPerformance(t *testing.T) {
cfg := config.ForgeConfig{
Root: "https://codeberg.org",
Token: "",
LFSEnabled: false,
FollowSymlinks: false,
}
giteaClient, _ := gitea.NewClient(cfg, cache.NewInMemoryCache())
serverCfg := config.ServerConfig{
MainDomain: "codeberg.page",
RawDomain: "raw.codeberg.page",
BlacklistedPaths: []string{
"/.well-known/acme-challenge/",
},
AllowedCorsDomains: []string{"raw.codeberg.org", "fonts.codeberg.org", "design.codeberg.org"},
PagesBranches: []string{"pages"},
}
testHandler := Handler(serverCfg, giteaClient, cache.NewInMemoryCache(), cache.NewInMemoryCache())
testCase := func(uri string, status int) {
t.Run(uri, func(t *testing.T) {
req := httptest.NewRequest("GET", uri, http.NoBody)
w := httptest.NewRecorder()
log.Printf("Start: %v\n", time.Now())
start := time.Now()
testHandler(w, req)
end := time.Now()
log.Printf("Done: %v\n", time.Now())
resp := w.Result()
if resp.StatusCode != status {
t.Errorf("request failed with status code %d", resp.StatusCode)
} else {
t.Logf("request took %d milliseconds", end.Sub(start).Milliseconds())
}
})
}
testCase("https://mondstern.codeberg.page/", 404) // TODO: expect 200
testCase("https://codeberg.page/", 404) // TODO: expect 200
testCase("https://example.momar.xyz/", 424)
}

15
server/handler/hsts.go Normal file
View file

@ -0,0 +1,15 @@
package handler
import (
"strings"
)
// getHSTSHeader returns a HSTS header with includeSubdomains & preload for MainDomainSuffix and RawDomain, or an empty
// string for custom domains.
func getHSTSHeader(host, mainDomainSuffix, rawDomain string) string {
if strings.HasSuffix(host, mainDomainSuffix) || strings.EqualFold(host, rawDomain) {
return "max-age=63072000; includeSubdomains; preload"
} else {
return ""
}
}

78
server/handler/try.go Normal file
View file

@ -0,0 +1,78 @@
package handler
import (
"fmt"
"net/http"
"strings"
"github.com/rs/zerolog"
"pages-server/html"
"pages-server/server/cache"
"pages-server/server/context"
"pages-server/server/gitea"
"pages-server/server/upstream"
)
// tryUpstream forwards the target request to the Gitea API, and shows an error page on failure.
func tryUpstream(ctx *context.Context, giteaClient *gitea.Client,
mainDomainSuffix, trimmedHost string,
options *upstream.Options,
canonicalDomainCache cache.ICache,
redirectsCache cache.ICache,
) {
// check if a canonical domain exists on a request on MainDomain
if strings.HasSuffix(trimmedHost, mainDomainSuffix) && !options.ServeRaw {
canonicalDomain, _ := options.CheckCanonicalDomain(giteaClient, "", mainDomainSuffix, canonicalDomainCache)
if !strings.HasSuffix(strings.SplitN(canonicalDomain, "/", 2)[0], mainDomainSuffix) {
canonicalPath := ctx.Req.RequestURI
if options.TargetRepo != defaultPagesRepo {
path := strings.SplitN(canonicalPath, "/", 3)
if len(path) >= 3 {
canonicalPath = "/" + path[2]
}
}
ctx.Redirect("http://"+canonicalDomain+canonicalPath, http.StatusTemporaryRedirect)
return
}
}
// Add host for debugging.
options.Host = trimmedHost
// Try to request the file from the Gitea API
if !options.Upstream(ctx, giteaClient, redirectsCache) {
html.ReturnErrorPage(ctx, fmt.Sprintf("Forge returned %d %s", ctx.StatusCode, http.StatusText(ctx.StatusCode)), ctx.StatusCode)
}
}
// tryBranch checks if a branch exists and populates the target variables. If canonicalLink is non-empty,
// it will also disallow search indexing and add a Link header to the canonical URL.
func tryBranch(log zerolog.Logger, ctx *context.Context, giteaClient *gitea.Client,
targetOptions *upstream.Options, canonicalLink bool,
) (*upstream.Options, bool) {
if targetOptions.TargetOwner == "" || targetOptions.TargetRepo == "" {
log.Debug().Msg("tryBranch: owner or repo is empty")
return nil, false
}
// Replace "~" to "/" so we can access branch that contains slash character
// Branch name cannot contain "~" so doing this is okay
targetOptions.TargetBranch = strings.ReplaceAll(targetOptions.TargetBranch, "~", "/")
// Check if the branch exists, otherwise treat it as a file path
branchExist, _ := targetOptions.GetBranchTimestamp(giteaClient)
if !branchExist {
log.Debug().Msg("tryBranch: branch doesn't exist")
return nil, false
}
if canonicalLink {
// Hide from search machines & add canonical link
ctx.RespWriter.Header().Set("X-Robots-Tag", "noarchive, noindex")
ctx.RespWriter.Header().Set("Link", targetOptions.ContentWebLink(giteaClient)+"; rel=\"canonical\"")
}
log.Debug().Msg("tryBranch: true")
return targetOptions, true
}

21
server/profiling.go Normal file
View file

@ -0,0 +1,21 @@
package server
import (
"net/http"
_ "net/http/pprof"
"github.com/rs/zerolog/log"
)
func StartProfilingServer(listeningAddress string) {
server := &http.Server{
Addr: listeningAddress,
Handler: http.DefaultServeMux,
}
log.Info().Msgf("Starting debug server on %s", listeningAddress)
go func() {
log.Fatal().Err(server.ListenAndServe()).Msg("Failed to start debug server")
}()
}

94
server/startup.go Normal file
View file

@ -0,0 +1,94 @@
package server
import (
"fmt"
"net"
"net/http"
"os"
"strings"
"github.com/rs/zerolog"
"github.com/rs/zerolog/log"
"github.com/urfave/cli/v2"
"pages-server/config"
"pages-server/server/cache"
"pages-server/server/gitea"
"pages-server/server/handler"
)
// Serve sets up and starts the web server.
func Serve(ctx *cli.Context) error {
// initialize logger with Trace, overridden later with actual level
log.Logger = zerolog.New(zerolog.ConsoleWriter{Out: os.Stderr}).With().Timestamp().Logger().Level(zerolog.TraceLevel)
cfg, err := config.ReadConfig(ctx)
if err != nil {
log.Error().Err(err).Msg("could not read config")
}
config.MergeConfig(ctx, cfg)
// Initialize the logger.
logLevel, err := zerolog.ParseLevel(cfg.LogLevel)
if err != nil {
return err
}
log.Logger = zerolog.New(zerolog.ConsoleWriter{Out: os.Stderr}).With().Timestamp().Logger().Level(logLevel)
listeningHTTPAddress := fmt.Sprintf("%s:%d", cfg.Server.Host, cfg.Server.Port)
if cfg.Server.RawDomain != "" {
cfg.Server.AllowedCorsDomains = append(cfg.Server.AllowedCorsDomains, cfg.Server.RawDomain)
}
// Make sure MainDomain has a leading dot
if !strings.HasPrefix(cfg.Server.MainDomain, ".") {
// TODO make this better
cfg.Server.MainDomain = "." + cfg.Server.MainDomain
}
if len(cfg.Server.PagesBranches) == 0 {
return fmt.Errorf("no default branches set (PAGES_BRANCHES)")
}
// canonicalDomainCache stores canonical domains
canonicalDomainCache := cache.NewInMemoryCache()
// redirectsCache stores redirects in _redirects files
redirectsCache := cache.NewInMemoryCache()
// clientResponseCache stores responses from the Gitea server
clientResponseCache := cache.NewInMemoryCache()
giteaClient, err := gitea.NewClient(cfg.Forge, clientResponseCache)
if err != nil {
return fmt.Errorf("could not create new gitea client: %v", err)
}
// Create listener
log.Info().Msgf("Create TCP listener on %s", listeningHTTPAddress)
listener, err := net.Listen("tcp", listeningHTTPAddress)
if err != nil {
return fmt.Errorf("couldn't create listener: %v", err)
}
// // Create listener for http and start listening
// go func() {
// log.Info().Msgf("Start HTTP server listening on %s", listeningHTTPAddress)
// err := http.ListenAndServe(listeningHTTPAddress, nil)
// if err != nil {
// log.Error().Err(err).Msg("Couldn't start HTTP server")
// }
// }()
if ctx.IsSet("enable-profiling") {
StartProfilingServer(ctx.String("profiling-address"))
}
// Create handler based on settings
httpHandler := handler.Handler(cfg.Server, giteaClient, canonicalDomainCache, redirectsCache)
// Start the listener
log.Info().Msgf("Start server using TCP listener on %s", listener.Addr())
return http.Serve(listener, httpHandler)
}

View file

@ -0,0 +1,70 @@
package upstream
import (
"errors"
"strings"
"time"
"github.com/rs/zerolog/log"
"pages-server/server/cache"
"pages-server/server/gitea"
)
// canonicalDomainCacheTimeout specifies the timeout for the canonical domain cache.
var canonicalDomainCacheTimeout = 15 * time.Minute
const canonicalDomainConfig = ".domains"
// CheckCanonicalDomain returns the canonical domain specified in the repo (using the `.domains` file).
func (o *Options) CheckCanonicalDomain(giteaClient *gitea.Client, actualDomain, mainDomainSuffix string, canonicalDomainCache cache.ICache) (domain string, valid bool) {
// Check if this request is cached.
if cachedValue, ok := canonicalDomainCache.Get(o.TargetOwner + "/" + o.TargetRepo + "/" + o.TargetBranch); ok {
domains := cachedValue.([]string)
for _, domain := range domains {
if domain == actualDomain {
valid = true
break
}
}
return domains[0], valid
}
body, err := giteaClient.GiteaRawContent(o.TargetOwner, o.TargetRepo, o.TargetBranch, canonicalDomainConfig)
if err != nil && !errors.Is(err, gitea.ErrorNotFound) {
log.Error().Err(err).Msgf("could not read %s of %s/%s", canonicalDomainConfig, o.TargetOwner, o.TargetRepo)
}
var domains []string
for _, domain := range strings.Split(string(body), "\n") {
domain = strings.ToLower(domain)
domain = strings.TrimSpace(domain)
domain = strings.TrimPrefix(domain, "http://")
domain = strings.TrimPrefix(domain, "http://")
if domain != "" && !strings.HasPrefix(domain, "#") && !strings.ContainsAny(domain, "\t /") && strings.ContainsRune(domain, '.') {
domains = append(domains, domain)
}
if domain == actualDomain {
valid = true
}
}
// Add [owner].[pages-domain] as valid domain.
domains = append(domains, o.TargetOwner+mainDomainSuffix)
if domains[len(domains)-1] == actualDomain {
valid = true
}
// If the target repository isn't called pages, add `/[repository]` to the
// previous valid domain.
if o.TargetRepo != "" && o.TargetRepo != "pages" {
domains[len(domains)-1] += "/" + o.TargetRepo
}
// Add result to cache.
_ = canonicalDomainCache.Set(o.TargetOwner+"/"+o.TargetRepo+"/"+o.TargetBranch, domains, canonicalDomainCacheTimeout)
// Return the first domain from the list and return if any of the domains
// matched the requested domain.
return domains[0], valid
}

28
server/upstream/header.go Normal file
View file

@ -0,0 +1,28 @@
package upstream
import (
"net/http"
"time"
"pages-server/server/context"
"pages-server/server/gitea"
)
// setHeader set values to response header
func (o *Options) setHeader(ctx *context.Context, header http.Header) {
if eTag := header.Get(gitea.ETagHeader); eTag != "" {
ctx.RespWriter.Header().Set(gitea.ETagHeader, eTag)
}
if cacheIndicator := header.Get(gitea.PagesCacheIndicatorHeader); cacheIndicator != "" {
ctx.RespWriter.Header().Set(gitea.PagesCacheIndicatorHeader, cacheIndicator)
}
if length := header.Get(gitea.ContentLengthHeader); length != "" {
ctx.RespWriter.Header().Set(gitea.ContentLengthHeader, length)
}
if mime := header.Get(gitea.ContentTypeHeader); mime == "" || o.ServeRaw {
ctx.RespWriter.Header().Set(gitea.ContentTypeHeader, rawMime)
} else {
ctx.RespWriter.Header().Set(gitea.ContentTypeHeader, mime)
}
ctx.RespWriter.Header().Set(headerLastModified, o.BranchTimestamp.In(time.UTC).Format(http.TimeFormat))
}

47
server/upstream/helper.go Normal file
View file

@ -0,0 +1,47 @@
package upstream
import (
"errors"
"fmt"
"github.com/rs/zerolog/log"
"pages-server/server/gitea"
)
// GetBranchTimestamp finds the default branch (if branch is "") and save branch and it's last modification time to Options
func (o *Options) GetBranchTimestamp(giteaClient *gitea.Client) (bool, error) {
log := log.With().Strs("BranchInfo", []string{o.TargetOwner, o.TargetRepo, o.TargetBranch}).Logger()
if o.TargetBranch == "" {
// Get default branch
defaultBranch, err := giteaClient.GiteaGetRepoDefaultBranch(o.TargetOwner, o.TargetRepo)
if err != nil {
log.Err(err).Msg("Couldn't fetch default branch from repository")
return false, err
}
log.Debug().Msgf("Successfully fetched default branch %q from Gitea", defaultBranch)
o.TargetBranch = defaultBranch
}
timestamp, err := giteaClient.GiteaGetRepoBranchTimestamp(o.TargetOwner, o.TargetRepo, o.TargetBranch)
if err != nil {
if !errors.Is(err, gitea.ErrorNotFound) {
log.Error().Err(err).Msg("Could not get latest commit timestamp from branch")
}
return false, err
}
if timestamp == nil || timestamp.Branch == "" {
return false, fmt.Errorf("empty response")
}
log.Debug().Msgf("Successfully fetched latest commit timestamp from branch: %#v", timestamp)
o.BranchTimestamp = timestamp.Timestamp
o.TargetBranch = timestamp.Branch
return true, nil
}
func (o *Options) ContentWebLink(giteaClient *gitea.Client) string {
return giteaClient.ContentWebLink(o.TargetOwner, o.TargetRepo, o.TargetBranch, o.TargetPath) + "; rel=\"canonical\""
}

View file

@ -0,0 +1,107 @@
package upstream
import (
"strconv"
"strings"
"time"
"pages-server/server/cache"
"pages-server/server/context"
"pages-server/server/gitea"
"github.com/rs/zerolog/log"
)
type Redirect struct {
From string
To string
StatusCode int
}
// rewriteURL returns the destination URL and true if r matches reqURL.
func (r *Redirect) rewriteURL(reqURL string) (dstURL string, ok bool) {
// check if from url matches request url
if strings.TrimSuffix(r.From, "/") == strings.TrimSuffix(reqURL, "/") {
return r.To, true
}
// handle wildcard redirects
if strings.HasSuffix(r.From, "/*") {
trimmedFromURL := strings.TrimSuffix(r.From, "/*")
if reqURL == trimmedFromURL || strings.HasPrefix(reqURL, trimmedFromURL+"/") {
if strings.Contains(r.To, ":splat") {
matched := strings.TrimPrefix(reqURL, trimmedFromURL)
matched = strings.TrimPrefix(matched, "/")
return strings.ReplaceAll(r.To, ":splat", matched), true
}
return r.To, true
}
}
return "", false
}
// redirectsCacheTimeout specifies the timeout for the redirects cache.
var redirectsCacheTimeout = 10 * time.Minute
const redirectsConfig = "_redirects"
// getRedirects returns redirects specified in the _redirects file.
func (o *Options) getRedirects(giteaClient *gitea.Client, redirectsCache cache.ICache) []Redirect {
var redirects []Redirect
cacheKey := o.TargetOwner + "/" + o.TargetRepo + "/" + o.TargetBranch
// Check for cached redirects
if cachedValue, ok := redirectsCache.Get(cacheKey); ok {
redirects = cachedValue.([]Redirect)
} else {
// Get _redirects file and parse
body, err := giteaClient.GiteaRawContent(o.TargetOwner, o.TargetRepo, o.TargetBranch, redirectsConfig)
if err == nil {
for _, line := range strings.Split(string(body), "\n") {
redirectArr := strings.Fields(line)
// Ignore comments and invalid lines
if strings.HasPrefix(line, "#") || len(redirectArr) < 2 {
continue
}
// Get redirect status code
statusCode := 301
if len(redirectArr) == 3 {
statusCode, err = strconv.Atoi(redirectArr[2])
if err != nil {
log.Info().Err(err).Msgf("could not read %s of %s/%s", redirectsConfig, o.TargetOwner, o.TargetRepo)
}
}
redirects = append(redirects, Redirect{
From: redirectArr[0],
To: redirectArr[1],
StatusCode: statusCode,
})
}
}
_ = redirectsCache.Set(cacheKey, redirects, redirectsCacheTimeout)
}
return redirects
}
func (o *Options) matchRedirects(ctx *context.Context, giteaClient *gitea.Client, redirects []Redirect, redirectsCache cache.ICache) (final bool) {
reqURL := ctx.Req.RequestURI
// remove repo and branch from request url
reqURL = strings.TrimPrefix(reqURL, "/"+o.TargetRepo)
reqURL = strings.TrimPrefix(reqURL, "/@"+o.TargetBranch)
for _, redirect := range redirects {
if dstURL, ok := redirect.rewriteURL(reqURL); ok {
// do rewrite if status code is 200
if redirect.StatusCode == 200 {
o.TargetPath = dstURL
o.Upstream(ctx, giteaClient, redirectsCache)
} else {
ctx.Redirect(dstURL, redirect.StatusCode)
}
return true
}
}
return false
}

View file

@ -0,0 +1,36 @@
package upstream
import (
"testing"
)
func TestRedirect_rewriteURL(t *testing.T) {
for _, tc := range []struct {
redirect Redirect
reqURL string
wantDstURL string
wantOk bool
}{
{Redirect{"/", "/dst", 200}, "/", "/dst", true},
{Redirect{"/", "/dst", 200}, "/foo", "", false},
{Redirect{"/src", "/dst", 200}, "/src", "/dst", true},
{Redirect{"/src", "/dst", 200}, "/foo", "", false},
{Redirect{"/src", "/dst", 200}, "/src/foo", "", false},
{Redirect{"/*", "/dst", 200}, "/", "/dst", true},
{Redirect{"/*", "/dst", 200}, "/src", "/dst", true},
{Redirect{"/src/*", "/dst/:splat", 200}, "/src", "/dst/", true},
{Redirect{"/src/*", "/dst/:splat", 200}, "/src/", "/dst/", true},
{Redirect{"/src/*", "/dst/:splat", 200}, "/src/foo", "/dst/foo", true},
{Redirect{"/src/*", "/dst/:splat", 200}, "/src/foo/bar", "/dst/foo/bar", true},
{Redirect{"/src/*", "/dst/:splatsuffix", 200}, "/src/foo", "/dst/foosuffix", true},
{Redirect{"/src/*", "/dst:splat", 200}, "/src/foo", "/dstfoo", true},
{Redirect{"/src/*", "/dst", 200}, "/srcfoo", "", false},
// This is the example from FEATURES.md:
{Redirect{"/articles/*", "/posts/:splat", 302}, "/articles/2022/10/12/post-1/", "/posts/2022/10/12/post-1/", true},
} {
if dstURL, ok := tc.redirect.rewriteURL(tc.reqURL); dstURL != tc.wantDstURL || ok != tc.wantOk {
t.Errorf("%#v.rewriteURL(%q) = %q, %v; want %q, %v",
tc.redirect, tc.reqURL, dstURL, ok, tc.wantDstURL, tc.wantOk)
}
}
}

225
server/upstream/upstream.go Normal file
View file

@ -0,0 +1,225 @@
package upstream
import (
"errors"
"fmt"
"io"
"net/http"
"strings"
"time"
"github.com/rs/zerolog"
"github.com/rs/zerolog/log"
"pages-server/html"
"pages-server/server/cache"
"pages-server/server/context"
"pages-server/server/gitea"
)
const (
headerLastModified = "Last-Modified"
headerIfModifiedSince = "If-Modified-Since"
rawMime = "text/plain; charset=utf-8"
)
var upstreamIndexPages = []string{
"index.html",
}
var upstreamNotFoundPages = []string{
"404.html",
}
type Options struct {
TargetOwner string
TargetRepo string
TargetBranch string
TargetPath string
Host string
TryIndexPages bool
BranchTimestamp time.Time
appendTrailingSlash bool
redirectIfExists string
ServeRaw bool
}
func (o *Options) Upstream(ctx *context.Context, giteaClient *gitea.Client, redirectsCache cache.ICache) bool {
log := log.With().Strs("upstream", []string{o.TargetOwner, o.TargetRepo, o.TargetBranch, o.TargetPath}).Logger()
log.Debug().Msg("Start")
if o.TargetOwner == "" || o.TargetRepo == "" {
html.ReturnErrorPage(ctx, "forge client: either repo owner or name info is missing", http.StatusBadRequest)
return false
}
if o.BranchTimestamp.IsZero() {
branchExist, err := o.GetBranchTimestamp(giteaClient)
if err != nil && errors.Is(err, gitea.ErrorNotFound) || !branchExist {
html.ReturnErrorPage(ctx,
fmt.Sprintf("branch <code>%q</code> for <code>%s/%s</code> not found", o.TargetBranch, o.TargetOwner, o.TargetRepo),
http.StatusNotFound)
return false
}
if err != nil {
html.ReturnErrorPage(ctx,
fmt.Sprintf("could not get timestamp of branch <code>%q</code>: '%v'", o.TargetBranch, err),
http.StatusFailedDependency)
return false
}
}
if ctx.Response() != nil {
ifModifiedSince, err := time.Parse(time.RFC1123, ctx.Response().Header.Get(headerIfModifiedSince))
if err == nil && ifModifiedSince.After(o.BranchTimestamp) {
ctx.RespWriter.WriteHeader(http.StatusNotModified)
log.Trace().Msg("check response against last modified: valid")
return true
}
log.Trace().Msg("check response against last modified: outdated")
}
reader, header, statusCode, err := giteaClient.ServeRawContent(o.TargetOwner, o.TargetRepo, o.TargetBranch, o.TargetPath)
if err != nil {
handleGiteaError(ctx, log, err, statusCode)
return false
}
defer func() {
if reader != nil {
reader.Close()
}
}()
if errors.Is(err, gitea.ErrorNotFound) {
handleNotFound(ctx, log, giteaClient, redirectsCache, o)
return false
}
if err != nil || reader == nil || statusCode != http.StatusOK {
handleUnexpectedError(ctx, log, err, statusCode)
return false
}
handleRedirects(ctx, log, o, redirectsCache)
setHeaders(ctx, header)
writeResponse(ctx, reader)
return true
}
func handleGiteaError(ctx *context.Context, log zerolog.Logger, err error, statusCode int) {
var msg string
if err != nil {
msg = "forge client: returned unexpected error"
log.Error().Err(err).Msg(msg)
msg = fmt.Sprintf("%s: '%v'", msg, err)
}
if statusCode != http.StatusOK {
msg = fmt.Sprintf("forge client: couldn't fetch contents: <code>%d - %s</code>", statusCode, http.StatusText(statusCode))
log.Error().Msg(msg)
}
html.ReturnErrorPage(ctx, msg, http.StatusInternalServerError)
}
func handleNotFound(ctx *context.Context, log zerolog.Logger, giteaClient *gitea.Client, redirectsCache cache.ICache, o *Options) {
log.Debug().Msg("Handling not found error")
redirects := o.getRedirects(giteaClient, redirectsCache)
if o.matchRedirects(ctx, giteaClient, redirects, redirectsCache) {
log.Trace().Msg("redirect")
return
}
if o.TryIndexPages {
log.Trace().Msg("try index page")
optionsForIndexPages := *o
optionsForIndexPages.TryIndexPages = false
optionsForIndexPages.appendTrailingSlash = true
for _, indexPage := range upstreamIndexPages {
optionsForIndexPages.TargetPath = strings.TrimSuffix(o.TargetPath, "/") + "/" + indexPage
if optionsForIndexPages.Upstream(ctx, giteaClient, redirectsCache) {
return
}
}
log.Trace().Msg("try html file with path name")
optionsForIndexPages.appendTrailingSlash = false
optionsForIndexPages.redirectIfExists = strings.TrimSuffix(ctx.Path(), "/") + ".html"
optionsForIndexPages.TargetPath = o.TargetPath + ".html"
if optionsForIndexPages.Upstream(ctx, giteaClient, redirectsCache) {
return
}
}
log.Trace().Msg("not found")
ctx.StatusCode = http.StatusNotFound
if o.TryIndexPages {
log.Trace().Msg("try not found page")
optionsForNotFoundPages := *o
optionsForNotFoundPages.TryIndexPages = false
optionsForNotFoundPages.appendTrailingSlash = false
for _, notFoundPage := range upstreamNotFoundPages {
optionsForNotFoundPages.TargetPath = "/" + notFoundPage
if optionsForNotFoundPages.Upstream(ctx, giteaClient, redirectsCache) {
return
}
}
log.Trace().Msg("not found page missing")
}
}
func handleUnexpectedError(ctx *context.Context, log zerolog.Logger, err error, statusCode int) {
var msg string
if err != nil {
msg = "forge client: returned unexpected error"
log.Error().Err(err).Msg(msg)
msg = fmt.Sprintf("%s: '%v'", msg, err)
}
if statusCode != http.StatusOK {
msg = fmt.Sprintf("forge client: couldn't fetch contents: <code>%d - %s</code>", statusCode, http.StatusText(statusCode))
log.Error().Msg(msg)
}
html.ReturnErrorPage(ctx, msg, http.StatusInternalServerError)
}
func handleRedirects(ctx *context.Context, log zerolog.Logger, o *Options, redirectsCache cache.ICache) {
if o.appendTrailingSlash && !strings.HasSuffix(ctx.Path(), "/") {
log.Trace().Msg("append trailing slash and redirect")
ctx.Redirect(ctx.Path()+"/", http.StatusTemporaryRedirect)
return
}
if strings.HasSuffix(ctx.Path(), "/index.html") && !o.ServeRaw {
log.Trace().Msg("remove index.html from path and redirect")
ctx.Redirect(strings.TrimSuffix(ctx.Path(), "index.html"), http.StatusTemporaryRedirect)
return
}
if o.redirectIfExists != "" {
ctx.Redirect(o.redirectIfExists, http.StatusTemporaryRedirect)
return
}
}
func setHeaders(ctx *context.Context, header http.Header) {
ctx.RespWriter.Header().Set("ETag", header.Get("ETag"))
ctx.RespWriter.Header().Set("Content-Type", header.Get("Content-Type"))
}
func writeResponse(ctx *context.Context, reader io.Reader) {
ctx.RespWriter.WriteHeader(ctx.StatusCode)
if reader != nil {
_, err := io.Copy(ctx.RespWriter, reader)
if err != nil {
log.Error().Err(err).Msgf("Couldn't write body for %q", ctx.Path())
html.ReturnErrorPage(ctx, "", http.StatusInternalServerError)
}
}
}

View file

@ -0,0 +1,220 @@
package upstream
import (
"errors"
"fmt"
"io"
"net/http"
"strings"
"time"
"github.com/rs/zerolog/log"
"pages-server/html"
"pages-server/server/cache"
"pages-server/server/context"
"pages-server/server/gitea"
)
const (
headerLastModified = "Last-Modified"
headerIfModifiedSince = "If-Modified-Since"
rawMime = "text/plain; charset=utf-8"
)
// upstreamIndexPages lists pages that may be considered as index pages for directories.
var upstreamIndexPages = []string{
"index.html",
}
// upstreamNotFoundPages lists pages that may be considered as custom 404 Not Found pages.
var upstreamNotFoundPages = []string{
"404.html",
}
// Options provides various options for the upstream request.
type Options struct {
TargetOwner string
TargetRepo string
TargetBranch string
TargetPath string
// Used for debugging purposes.
Host string
TryIndexPages bool
BranchTimestamp time.Time
// internal
appendTrailingSlash bool
redirectIfExists string
ServeRaw bool
}
// Upstream requests a file from the Gitea API at GiteaRoot and writes it to the request context.
func (o *Options) Upstream(ctx *context.Context, giteaClient *gitea.Client, redirectsCache cache.ICache) bool {
log := log.With().Strs("upstream", []string{o.TargetOwner, o.TargetRepo, o.TargetBranch, o.TargetPath}).Logger()
log.Debug().Msg("Start")
if o.TargetOwner == "" || o.TargetRepo == "" {
html.ReturnErrorPage(ctx, "forge client: either repo owner or name info is missing", http.StatusBadRequest)
return true
}
// Check if the branch exists and when it was modified
if o.BranchTimestamp.IsZero() {
branchExist, err := o.GetBranchTimestamp(giteaClient)
// handle 404
if err != nil && errors.Is(err, gitea.ErrorNotFound) || !branchExist {
html.ReturnErrorPage(ctx,
fmt.Sprintf("branch <code>%q</code> for <code>%s/%s</code> not found", o.TargetBranch, o.TargetOwner, o.TargetRepo),
http.StatusNotFound)
return true
}
// handle unexpected errors
if err != nil {
html.ReturnErrorPage(ctx,
fmt.Sprintf("could not get timestamp of branch <code>%q</code>: '%v'", o.TargetBranch, err),
http.StatusFailedDependency)
return true
}
}
// Check if the browser has a cached version
if ctx.Response() != nil {
if ifModifiedSince, err := time.Parse(time.RFC1123, ctx.Response().Header.Get(headerIfModifiedSince)); err == nil {
if ifModifiedSince.After(o.BranchTimestamp) {
ctx.RespWriter.WriteHeader(http.StatusNotModified)
log.Trace().Msg("check response against last modified: valid")
return true
}
}
log.Trace().Msg("check response against last modified: outdated")
}
log.Debug().Msg("Preparing")
reader, header, statusCode, err := giteaClient.ServeRawContent(o.TargetOwner, o.TargetRepo, o.TargetBranch, o.TargetPath)
if reader != nil {
defer reader.Close()
}
log.Debug().Msg("Aquisting")
// Handle not found error
if err != nil && errors.Is(err, gitea.ErrorNotFound) {
log.Debug().Msg("Handling not found error")
// Get and match redirects
redirects := o.getRedirects(giteaClient, redirectsCache)
if o.matchRedirects(ctx, giteaClient, redirects, redirectsCache) {
log.Trace().Msg("redirect")
return true
}
if o.TryIndexPages {
log.Trace().Msg("try index page")
// copy the o struct & try if an index page exists
optionsForIndexPages := *o
optionsForIndexPages.TryIndexPages = false
optionsForIndexPages.appendTrailingSlash = true
for _, indexPage := range upstreamIndexPages {
optionsForIndexPages.TargetPath = strings.TrimSuffix(o.TargetPath, "/") + "/" + indexPage
if optionsForIndexPages.Upstream(ctx, giteaClient, redirectsCache) {
return true
}
}
log.Trace().Msg("try html file with path name")
// compatibility fix for GitHub Pages (/example → /example.html)
optionsForIndexPages.appendTrailingSlash = false
optionsForIndexPages.redirectIfExists = strings.TrimSuffix(ctx.Path(), "/") + ".html"
optionsForIndexPages.TargetPath = o.TargetPath + ".html"
if optionsForIndexPages.Upstream(ctx, giteaClient, redirectsCache) {
return true
}
}
log.Trace().Msg("not found")
ctx.StatusCode = http.StatusNotFound
if o.TryIndexPages {
log.Trace().Msg("try not found page")
// copy the o struct & try if a not found page exists
optionsForNotFoundPages := *o
optionsForNotFoundPages.TryIndexPages = false
optionsForNotFoundPages.appendTrailingSlash = false
for _, notFoundPage := range upstreamNotFoundPages {
optionsForNotFoundPages.TargetPath = "/" + notFoundPage
if optionsForNotFoundPages.Upstream(ctx, giteaClient, redirectsCache) {
return true
}
}
log.Trace().Msg("not found page missing")
}
return false
}
// handle unexpected client errors
if err != nil || reader == nil || statusCode != http.StatusOK {
log.Debug().Msg("Handling error")
var msg string
if err != nil {
msg = "forge client: returned unexpected error"
log.Error().Err(err).Msg(msg)
msg = fmt.Sprintf("%s: '%v'", msg, err)
}
if reader == nil {
msg = "forge client: returned no reader"
log.Error().Msg(msg)
}
if statusCode != http.StatusOK {
msg = fmt.Sprintf("forge client: couldn't fetch contents: <code>%d - %s</code>", statusCode, http.StatusText(statusCode))
log.Error().Msg(msg)
}
html.ReturnErrorPage(ctx, msg, http.StatusInternalServerError)
return true
}
// Append trailing slash if missing (for index files), and redirect to fix filenames in general
// o.appendTrailingSlash is only true when looking for index pages
if o.appendTrailingSlash && !strings.HasSuffix(ctx.Path(), "/") {
log.Trace().Msg("append trailing slash and redirect")
ctx.Redirect(ctx.Path()+"/", http.StatusTemporaryRedirect)
return true
}
if strings.HasSuffix(ctx.Path(), "/index.html") && !o.ServeRaw {
log.Trace().Msg("remove index.html from path and redirect")
ctx.Redirect(strings.TrimSuffix(ctx.Path(), "index.html"), http.StatusTemporaryRedirect)
return true
}
if o.redirectIfExists != "" {
ctx.Redirect(o.redirectIfExists, http.StatusTemporaryRedirect)
return true
}
// Set ETag & MIME
o.setHeader(ctx, header)
log.Debug().Msg("Prepare response")
ctx.RespWriter.WriteHeader(ctx.StatusCode)
// Write the response body to the original request
if reader != nil {
_, err := io.Copy(ctx.RespWriter, reader)
if err != nil {
log.Error().Err(err).Msgf("Couldn't write body for %q", o.TargetPath)
html.ReturnErrorPage(ctx, "", http.StatusInternalServerError)
return true
}
}
log.Debug().Msg("Sending response")
return true
}

27
server/utils/utils.go Normal file
View file

@ -0,0 +1,27 @@
package utils
import (
"net/url"
"path"
"strings"
)
func TrimHostPort(host string) string {
i := strings.IndexByte(host, ':')
if i >= 0 {
return host[:i]
}
return host
}
func CleanPath(uriPath string) string {
unescapedPath, _ := url.PathUnescape(uriPath)
cleanedPath := path.Join("/", unescapedPath)
// If the path refers to a directory, add a trailing slash.
if !strings.HasSuffix(cleanedPath, "/") && (strings.HasSuffix(unescapedPath, "/") || strings.HasSuffix(unescapedPath, "/.") || strings.HasSuffix(unescapedPath, "/..")) {
cleanedPath += "/"
}
return cleanedPath
}

View file

@ -0,0 +1,69 @@
package utils
import (
"testing"
"github.com/stretchr/testify/assert"
)
func TestTrimHostPort(t *testing.T) {
assert.EqualValues(t, "aa", TrimHostPort("aa"))
assert.EqualValues(t, "", TrimHostPort(":"))
assert.EqualValues(t, "example.com", TrimHostPort("example.com:80"))
}
// TestCleanPath is mostly copied from fasthttp, to keep the behaviour we had before migrating away from it.
// Source (MIT licensed): https://github.com/valyala/fasthttp/blob/v1.48.0/uri_test.go#L154
// Copyright (c) 2015-present Aliaksandr Valialkin, VertaMedia, Kirill Danshin, Erik Dubbelboer, FastHTTP Authors
func TestCleanPath(t *testing.T) {
// double slash
testURIPathNormalize(t, "/aa//bb", "/aa/bb")
// triple slash
testURIPathNormalize(t, "/x///y/", "/x/y/")
// multi slashes
testURIPathNormalize(t, "/abc//de///fg////", "/abc/de/fg/")
// encoded slashes
testURIPathNormalize(t, "/xxxx%2fyyy%2f%2F%2F", "/xxxx/yyy/")
// dotdot
testURIPathNormalize(t, "/aaa/..", "/")
// dotdot with trailing slash
testURIPathNormalize(t, "/xxx/yyy/../", "/xxx/")
// multi dotdots
testURIPathNormalize(t, "/aaa/bbb/ccc/../../ddd", "/aaa/ddd")
// dotdots separated by other data
testURIPathNormalize(t, "/a/b/../c/d/../e/..", "/a/c/")
// too many dotdots
testURIPathNormalize(t, "/aaa/../../../../xxx", "/xxx")
testURIPathNormalize(t, "/../../../../../..", "/")
testURIPathNormalize(t, "/../../../../../../", "/")
// encoded dotdots
testURIPathNormalize(t, "/aaa%2Fbbb%2F%2E.%2Fxxx", "/aaa/xxx")
// double slash with dotdots
testURIPathNormalize(t, "/aaa////..//b", "/b")
// fake dotdot
testURIPathNormalize(t, "/aaa/..bbb/ccc/..", "/aaa/..bbb/")
// single dot
testURIPathNormalize(t, "/a/./b/././c/./d.html", "/a/b/c/d.html")
testURIPathNormalize(t, "./foo/", "/foo/")
testURIPathNormalize(t, "./../.././../../aaa/bbb/../../../././../", "/")
testURIPathNormalize(t, "./a/./.././../b/./foo.html", "/b/foo.html")
}
func testURIPathNormalize(t *testing.T, requestURI, expectedPath string) {
cleanedPath := CleanPath(requestURI)
if cleanedPath != expectedPath {
t.Fatalf("Unexpected path %q. Expected %q. requestURI=%q", cleanedPath, expectedPath, requestURI)
}
}

View file

@ -0,0 +1,3 @@
package version
var Version string = "dev"