Add Xylem project

preparation/xylem/.dockerignore

@@ -0,0 +1,24 @@
+# Build artifacts
+_build/
+deps/
+
+# IDE
+.vscode/
+.idea/
+*.iml
+
+# Test
+test/
+
+# Docs
+doc/
+
+# Git
+.git/
+.gitignore
+
+# macOS
+.DS_Store
+
+# Temp
+tmp/

preparation/xylem/.formatter.exs

@@ -0,0 +1,4 @@
+# Used by "mix format"
+[
+  inputs: ["{mix,.formatter}.exs", "{config,lib,test}/**/*.{ex,exs}"]
+]

preparation/xylem/.gitignore

@@ -0,0 +1,26 @@
+# The directory Mix will write compiled artifacts to.
+/_build/
+
+# If you run "mix test --cover", coverage assets end up here.
+/cover/
+
+# The directory Mix downloads your dependencies sources to.
+/deps/
+
+# Where third-party dependencies like ExDoc output generated docs.
+/doc/
+
+# If the VM crashes, it generates a dump, let's ignore it too.
+erl_crash.dump
+
+# Also ignore archive artifacts (built via "mix archive.build").
+*.ez
+
+# Ignore package tarball (built via "mix hex.build").
+xylem-*.tar
+
+# Temporary files, for example, from tests.
+/tmp/
+
+# Output data
+/priv/data/wikidata/

preparation/xylem/Dockerfile

@@ -0,0 +1,29 @@
+FROM elixir:1.18.4-otp-27-slim
+
+# CA-Zertifikate für HTTPS-Downloads installieren
+RUN apt-get update && apt-get install -y ca-certificates && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+# Fix this issue on Apple Silicon: https://elixirforum.com/t/unable-to-compile-default-elixir-project-from-the-getting-started-guide/57199/12
+ENV ERL_FLAGS="+JPperf true"
+
+ENV MIX_ENV=prod
+
+# Hex und rebar installieren
+RUN mix local.hex --force && \
+    mix local.rebar --force
+
+# Dependencies zuerst kopieren (für besseres Caching)
+COPY mix.exs mix.lock ./
+RUN mix deps.get && mix deps.compile
+
+# Restlichen Code kopieren
+COPY config config
+COPY lib lib
+
+RUN mix compile
+
+VOLUME ["/app/data", "/app/priv"]
+
+ENTRYPOINT ["mix", "xylem.generate"]

preparation/xylem/README.md

@@ -0,0 +1,45 @@
+# Xylem
+
+Daten-Pipeline für das BaumBie-Projekt. Lädt Baumarten-Daten von Wikidata basierend auf einer CSV-Datei mit Wikidata-IDs.
+
+**Input:** `data/Baumarten-wikidata.csv` (CSV mit Wikidata-IDs)
+**Output:** `priv/data/wikidata/raw/*.ttl` (RDF-Daten im Turtle-Format)
+
+
+## Nutzung mit Docker
+
+### Image bauen
+
+```bash
+docker compose build
+```
+
+### Pipeline ausführen
+
+```bash
+# Alle Spezies verarbeiten
+docker compose run --rm xylem
+
+# Anzahl limitieren
+docker compose run --rm xylem --limit 10
+```
+
+### Optionen
+
+- `--csv PATH` - Pfad zur Input-CSV-Datei (default: `data/Baumarten-wikidata.csv`)
+- `--raw PATH` - Verzeichnis für die Output-TTL-Dateien (default: `priv/data/wikidata/raw`)
+- `--limit N` - Nur N Spezies verarbeiten
+
+
+## Lokale Entwicklung (mit Elixir)
+
+```bash
+# Dependencies installieren
+mix deps.get
+
+# Tests
+mix test
+
+# Pipeline ausführen
+mix xylem.generate
+```

preparation/xylem/config/config.exs

@@ -0,0 +1,9 @@
+import Config
+
+config :sparql_client,
+  protocol_version: "1.1",
+  update_request_method: :direct
+
+config :tesla, :adapter, Tesla.Adapter.Hackney
+
+import_config "#{Mix.env()}.exs"

preparation/xylem/config/dev.exs

@@ -0,0 +1 @@
+import Config

preparation/xylem/config/prod.exs

@@ -0,0 +1 @@
+import Config

preparation/xylem/config/test.exs

@@ -0,0 +1,6 @@
+import Config
+
+config :exvcr,
+  vcr_cassette_library_dir: "test/fixtures/vcr_cassettes"
+
+config :logger, level: :warning