Merge pull request 'CI: build-only validation; drop make/python/github-context deps' (#1) from feature/initial-producer into master

.gitea/workflows/build.yaml

@@ -1,14 +1,15 @@
 name: build
 
-# Builds the dictionary DAWGs on every push/PR (validation) and, on a vX.Y.Z tag,
+# Validation gate: rebuilds the three dictionary DAWGs on every push/PR and checks they are
-# packages them flat into scrabble-dawg-<tag>.tar.gz and attaches it to the Gitea release.
+# non-empty. The build pins the published scrabble-solver builders (GOPRIVATE -> direct VCS
-# The build pins the published scrabble-solver builders (GOPRIVATE -> direct VCS fetch from
+# fetch from this Gitea), so the on-disk format and letter indexing match the running backend
-# this Gitea), so the on-disk format matches the running backend exactly.
+# exactly. Release artifacts (scrabble-dawg-<tag>.tar.gz attached to the Gitea release) are
+# published from this output; see README.md. Inlined go run (no make/python dependency on the
+# runner).
 
 on:
   push:
     branches: [master]
-    tags: ['v*']
   pull_request:
     branches: [master]
 
@@ -32,31 +33,11 @@ jobs:
 
       - name: Build DAWGs
         run: |
-          make dawg
+          mkdir -p dawg
+          go run ./cmd/builddict -dict dictionaries/english/sowpods.txt -alphabet latin   -name en_sowpods  -out dawg
+          go run ./cmd/builddict -dict dictprep/russian/scrabble.txt    -alphabet russian -name ru_scrabble -out dawg
+          go run ./cmd/builddict -dict dictprep/russian/erudit.txt      -alphabet russian -name ru_erudit   -out 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"

Makefile

@@ -5,14 +5,14 @@
 # format and letter indexing match the running backend exactly (no index drift):
 #   en_sowpods.dawg  — English SOWPODS (Latin alphabet)
 #   ru_scrabble.dawg — Russian Scrabble nouns (Cyrillic, 33 letters)
-#   ru_erudit.dawg   — Эрудит (the same list with Ё→Е folded and de-duped)
+#   ru_erudit.dawg   — Эрудит (the Ё→Е folded + de-duped list, committed as russian/erudit.txt)
 #
-# The CI workflow packages dawg/*.dawg into a release artifact on a vX.Y.Z tag.
+# CI builds the DAWGs as a validation gate; release artifacts are published from this output
+# (see README.md). Regenerate russian/erudit.txt from scrabble.txt with dictprep/fold_yo.py.
 
 export GOPRIVATE := gitea.iliadenisov.ru/*
 
 GO        ?= go
-PYTHON    ?= python3
 DAWG_DIR  := dawg
 BUILDDICT := $(GO) run ./cmd/builddict
 
@@ -27,8 +27,7 @@ dawg-ru:
 	$(BUILDDICT) -dict dictprep/russian/scrabble.txt -alphabet russian -name ru_scrabble -out $(DAWG_DIR)
 
 dawg-erudit:
-	$(PYTHON) dictprep/fold_yo.py dictprep/russian/scrabble.txt > /tmp/ru_erudit_words.txt
+	$(BUILDDICT) -dict dictprep/russian/erudit.txt -alphabet russian -name ru_erudit -out $(DAWG_DIR)
-	$(BUILDDICT) -dict /tmp/ru_erudit_words.txt -alphabet russian -name ru_erudit -out $(DAWG_DIR)
 
 clean-dawg:
 	rm -f $(DAWG_DIR)/*.dawg

README.md

@@ -19,20 +19,23 @@ byte-identical to the solver's committed test fixtures.
 | --- | --- | --- |
 | `en_sowpods.dawg` | English (SOWPODS) | `dictionaries/english/sowpods.txt` |
 | `ru_scrabble.dawg` | Russian Scrabble | `dictprep/russian/scrabble.txt` |
-| `ru_erudit.dawg` | Эрудит | the Russian list with Ё→Е folded (`dictprep/fold_yo.py`) |
+| `ru_erudit.dawg` | Эрудит | `dictprep/russian/erudit.txt` (Ё→Е folded `scrabble.txt`, via `dictprep/fold_yo.py`) |
 
-The CI (`.gitea/workflows/build.yaml`) builds them on every push/PR and, on a `vX.Y.Z` tag,
+The CI (`.gitea/workflows/build.yaml`) rebuilds them on every push/PR as a validation gate
-packages them flat into `scrabble-dawg-<tag>.tar.gz` and attaches it to the Gitea release. The
+(inlined `go run`, no `make`/`python` needed on the runner). Release artifacts are published per
-backend deploy unpacks that tarball into `BACKEND_DICT_DIR`; **one semver label versions the
+version (see **Release** below): the three DAWGs packaged flat into `scrabble-dawg-<tag>.tar.gz`
-whole set** (additive — a new version is a new release, never breaking a running backend).
+and attached to the Gitea release for the `vX.Y.Z` tag. The backend deploy unpacks that tarball
+into `BACKEND_DICT_DIR`; **one semver label versions the whole set** (additive — a new version is
+a new release, never breaking a running backend).
 
 ## Sources / provenance
 
 - **English:** `dictionaries/english/sowpods.txt`, vendored from
   [`kamilmielnik/scrabble-dictionaries`](https://github.com/kamilmielnik/scrabble-dictionaries).
 - **Russian:** `dictprep/russian/scrabble.txt`, derived from the Russian academic orthographic
-  dictionary by the tooling under `dictprep/` (see `dictprep/README.md`). Only the prepared word
+  dictionary by the tooling under `dictprep/` (see `dictprep/README.md`); `dictprep/russian/erudit.txt`
-  list is vendored; the heavy upstream source (the orfo PDF/text) is not.
+  is its Ё→Е folded form (`dictprep/fold_yo.py`). Only the prepared word lists are vendored; the
+  heavy upstream source (the orfo PDF/text) is not.
 
 ## Build
 
@@ -41,4 +44,20 @@ make dawg     # -> dawg/{en_sowpods,ru_scrabble,ru_erudit}.dawg
 ```
 
 Requires Go (module deps fetched with `GOPRIVATE=gitea.iliadenisov.ru/*`, exported by the
-Makefile) and `python3` (for the Ё→Е fold).
+Makefile). No `python` is needed for the build — the Ё→Е fold is committed as `erudit.txt`;
+regenerate it with `python3 dictprep/fold_yo.py dictprep/russian/scrabble.txt > dictprep/russian/erudit.txt`.
+
+## Release
+
+CI builds and validates the DAWGs but does not upload them (the release upload needs a write
+token, kept out of CI for now — a future enhancement). To publish a version, tag it and attach
+the artifact to its Gitea release:
+
+```sh
+make dawg
+tar czf scrabble-dawg-vX.Y.Z.tar.gz -C dawg en_sowpods.dawg ru_scrabble.dawg ru_erudit.dawg
+# create the Gitea release for tag vX.Y.Z and upload scrabble-dawg-vX.Y.Z.tar.gz as an asset
+```
+
+The backend consumes it at
+`https://gitea.iliadenisov.ru/developer/scrabble-dictionary/releases/download/vX.Y.Z/scrabble-dawg-vX.Y.Z.tar.gz`.