ci: publish image to ghcr.io (#1042)

Author: keegancsmith

.github/workflows/docker-version.sh

@@ -0,0 +1,13 @@
+#!/usr/bin/env bash
+
+set -euo pipefail
+
+# This is the pseudo-version that go.mod uses. We use the same version string
+# so that downstream consumers can line up image versions with module versions.
+version="$(TZ=UTC git --no-pager show \
+  --quiet \
+  --abbrev=12 \
+  --date='format-local:%Y%m%d%H%M%S' \
+  --format='0.0.0-%cd-%h')"
+
+printf 'value=%s\n' "$version" >>"$GITHUB_OUTPUT"

.github/workflows/docker.yml

@@ -0,0 +1,59 @@
+name: Publish Docker Image
+
+on:
+  push:
+    branches:
+      - main
+    tags:
+      - 'v*'
+  workflow_dispatch:
+
+jobs:
+  docker:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+    steps:
+      - name: checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: version
+        id: version
+        run: .github/workflows/docker-version.sh
+
+      - name: setup-buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: docker-meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ghcr.io/${{ github.repository }}
+          tags: |
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=raw,value=${{ steps.version.outputs.value }},enable={{is_default_branch}}
+            type=raw,value=latest,enable={{is_default_branch}}
+            type=sha,prefix=sha-,format=short
+
+      - name: login to ghcr.io
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: build and push
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+          build-args: |
+            VERSION=${{ steps.version.outputs.value }}

Dockerfile

@@ -1,25 +1,45 @@
-FROM golang:1.23.4-alpine3.19 AS builder
+# syntax=docker/dockerfile:1.7
+FROM golang:1.26.2-alpine AS builder
 
 RUN apk add --no-cache ca-certificates
 
 ENV CGO_ENABLED=0
-WORKDIR /go/src/github.com/sourcegraph/zoekt
+WORKDIR /src
 
-# Cache dependencies
+# Cache dependency resolution separately from source changes.
 COPY go.mod go.sum ./
-RUN go mod download
+RUN --mount=type=cache,target=/go/pkg/mod \
+    go mod download
+
+COPY . .
+ARG VERSION=dev
+RUN --mount=type=cache,target=/go/pkg/mod \
+    --mount=type=cache,target=/root/.cache/go-build \
+    mkdir -p /out && \
+    go build \
+      -trimpath \
+      -ldflags "-X github.com/sourcegraph/zoekt.Version=$VERSION" \
+      -o /out/ \
+      ./cmd/...
+
+FROM alpine:3
 
-COPY . ./
-ARG VERSION
-RUN go install -ldflags "-X github.com/sourcegraph/zoekt.Version=$VERSION" ./cmd/...
+RUN apk add --no-cache git ca-certificates bind-tools tini jansson wget
 
-FROM alpine:3.19 AS zoekt
+COPY --chmod=755 install-ctags-alpine.sh /usr/local/bin/install-ctags-alpine.sh
+RUN /usr/local/bin/install-ctags-alpine.sh && rm /usr/local/bin/install-ctags-alpine.sh
 
-RUN apk add --no-cache git ca-certificates bind-tools tini jansson wget
+RUN addgroup -S zoekt && \
+    adduser -S -G zoekt -h /home/zoekt zoekt && \
+    mkdir -p /data/index /home/zoekt && \
+    chown -R zoekt:zoekt /data /home/zoekt
+
+COPY --from=builder /out/ /usr/local/bin/
 
-COPY install-ctags-alpine.sh .
-RUN ./install-ctags-alpine.sh && rm install-ctags-alpine.sh
+USER zoekt
+WORKDIR /home/zoekt
 
-COPY --from=builder /go/bin/* /usr/local/bin/
+ENV DATA_DIR=/data/index
 
 ENTRYPOINT ["/sbin/tini", "--"]
+CMD ["zoekt-webserver", "-index", "/data/index", "-pprof", "-rpc"]

Dockerfile.indexserver

@@ -82,6 +82,25 @@ This will start a web server with a simple search UI at http://localhost:6070.
 See the [query syntax docs](doc/query_syntax.md) for more details on the query
 language.
 
+#### Container image
+
+Zoekt publishes a single container image at `ghcr.io/sourcegraph/zoekt`. It
+includes the Zoekt binaries, `git`, and `universal-ctags`. By default it runs
+`zoekt-webserver` against `/data/index`:
+
+    docker run --rm -p 6070:6070 -v "$PWD/index:/data/index" ghcr.io/sourcegraph/zoekt
+
+You can override the default command to run `zoekt-indexserver` instead. This
+example stores cloned repositories, logs, and indexes under `/data` and reads a
+mounted mirror config file:
+
+    docker run --rm \
+      -v "$PWD/config.json:/config.json:ro" \
+      -v "$PWD/token.txt:/home/zoekt/token.txt:ro" \
+      -v "$PWD/zoekt-data:/data" \
+      ghcr.io/sourcegraph/zoekt \
+      zoekt-indexserver -mirror_config /config.json -data_dir /data
+
 If you start the web server with `-rpc`, it exposes a [simple JSON search
 API](doc/json-api.md) at `http://localhost:6070/api/search`.