Initial dictionary producer: builddict, word-list sources, DAWG build + CI

- builddict drives the de-internalized scrabble-solver dictdawg/wordlist builders (pinned v1.0.0) to produce the three DAWGs (en_sowpods, ru_scrabble, ru_erudit), byte-identical to the solver's committed fixtures (same dafsa/alphabet v1.1.0 -> no index drift with the running backend). - Sources: english/sowpods.txt vendored from kamilmielnik/scrabble-dictionaries; russian/scrabble.txt + the dictprep tooling moved out of scrabble-solver. - CI builds the DAWGs on push/PR and, on a vX.Y.Z tag, packages them flat into scrabble-dawg-<tag>.tar.gz and attaches it to the Gitea release.
2026-06-04 19:18:19 +02:00
commit d04470b741
15 changed files with 352547 additions and 0 deletions
@@ -0,0 +1,62 @@
+name: build
+
+# Builds the dictionary DAWGs on every push/PR (validation) and, on a vX.Y.Z tag,
+# packages them flat into scrabble-dawg-<tag>.tar.gz and attaches it to the Gitea release.
+# The build pins the published scrabble-solver builders (GOPRIVATE -> direct VCS fetch from
+# this Gitea), so the on-disk format matches the running backend exactly.
+
+on:
+  push:
+    branches: [master]
+    tags: ['v*']
+  pull_request:
+    branches: [master]
+
+jobs:
+  dawg:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        shell: bash
+    env:
+      GOPRIVATE: gitea.iliadenisov.ru/*
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up Go
+        uses: actions/setup-go@v5
+        with:
+          go-version-file: go.mod
+          cache: true
+
+      - name: Build DAWGs
+        run: |
+          make dawg
+          ls -la dawg/
+          for f in en_sowpods ru_scrabble ru_erudit; do
+            test -s "dawg/$f.dawg" || { echo "missing dawg/$f.dawg"; exit 1; }
+          done
+
+      - name: Package and publish release artifact
+        if: startsWith(github.ref, 'refs/tags/v')
+        env:
+          TOKEN: ${{ github.token }}
+          API: ${{ github.server_url }}/api/v1/repos/${{ github.repository }}
+        run: |
+          set -eo pipefail
+          tag="${GITHUB_REF_NAME}"
+          art="scrabble-dawg-${tag}.tar.gz"
+          tar czf "$art" -C dawg en_sowpods.dawg ru_scrabble.dawg ru_erudit.dawg
+          # Create the release (or fetch it if it already exists), then upload the asset.
+          code=$(curl -sS -o /tmp/rel.json -w '%{http_code}' -X POST "$API/releases" \
+            -H "Authorization: token $TOKEN" -H 'Content-Type: application/json' \
+            -d "{\"tag_name\":\"$tag\",\"name\":\"$tag\",\"body\":\"Dictionary DAWG set $tag (en_sowpods, ru_scrabble, ru_erudit).\"}")
+          if [ "$code" != "201" ]; then
+            echo "release POST returned $code; fetching existing release for tag $tag"
+            curl -sS -o /tmp/rel.json "$API/releases/tags/$tag" -H "Authorization: token $TOKEN"
+          fi
+          rel_id=$(python3 -c 'import json;print(json.load(open("/tmp/rel.json"))["id"])')
+          curl -sS -X POST "$API/releases/$rel_id/assets?name=$art" \
+            -H "Authorization: token $TOKEN" -F "attachment=@$art" -o /tmp/asset.json
+          echo "published $art to release $rel_id"