cowork-bot: graceful optional-dependency import errors + optional-dependency groups

.github/workflows/cowork-auto-pr.yml

@@ -0,0 +1,28 @@
+# Seeded by the repo-improver-rotation Cowork job into cowork/improve-* branches.
+# Opens a PR automatically when such a branch is pushed (sandbox cannot reach
+# the GitHub API directly; this runs server-side with the repo's GITHUB_TOKEN).
+name: cowork-auto-pr
+on:
+  push:
+    branches: ['cowork/improve-**']
+permissions:
+  contents: read
+  pull-requests: write
+jobs:
+  ensure-pr:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Open PR for this branch if none exists
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: |
+          set -eu
+          existing=$(gh pr list --repo "$GITHUB_REPOSITORY" --head "$GITHUB_REF_NAME" --state open --json number --jq 'length')
+          if [ "$existing" = "0" ]; then
+            gh pr create --repo "$GITHUB_REPOSITORY" \
+              --head "$GITHUB_REF_NAME" \
+              --title "cowork-bot: automated improvements ($GITHUB_REF_NAME)" \
+              --body "Automated improvement PR from the Cowork repo-improver rotation (one coherent senior-dev improvement per run; see individual commit messages). Subsequent runs push additional commits to this PR rather than opening new ones."
+          else
+            echo "Open PR already exists for $GITHUB_REF_NAME — nothing to do."
+          fi

pyproject.toml

@@ -45,6 +45,10 @@ dev = [
     "pytest-cov>=7.1.0",
     "ruff>=0.15.20",
 ]
+parquet = ["pandas>=2.0.0", "pyarrow>=14.0.0"]
+avro = ["fastavro>=1.12.2"]
+protobuf = ["protobuf>=7.34.1"]
+all = ["datamorph[parquet,avro,protobuf]"]
 
 [project.scripts]
 datamorph = "datamorph.cli:cli"

src/datamorph/converters.py

@@ -284,7 +284,12 @@ def write_stream(self, rows: RowStream, path: str | Path) -> int:
 
 class YamlReader(FormatReader):
     def read_stream(self, path: str | Path) -> RowStream:
-        import yaml
+        try:
+            import yaml
+        except ImportError as e:
+            raise ImportError(
+                "YAML support requires PyYAML: pip install pyyaml"
+            ) from e
 
         with open(path, "r", encoding="utf-8") as f:
             data = yaml.safe_load(f)
@@ -298,7 +303,12 @@ def read_stream(self, path: str | Path) -> RowStream:
 
 class YamlWriter(FormatWriter):
     def write_stream(self, rows: RowStream, path: str | Path) -> int:
-        import yaml
+        try:
+            import yaml
+        except ImportError as e:
+            raise ImportError(
+                "YAML support requires PyYAML: pip install pyyaml"
+            ) from e
 
         rows_list = list(rows)
         with open(path, "w", encoding="utf-8") as f:
@@ -317,7 +327,13 @@ def write_stream(self, rows: RowStream, path: str | Path) -> int:
 
 class ParquetReader(FormatReader):
     def read_stream(self, path: str | Path) -> RowStream:
-        import pyarrow.parquet as pq
+        try:
+            import pyarrow.parquet as pq
+        except ImportError as e:
+            raise ImportError(
+                "Parquet support requires the 'parquet' extra: "
+                "pip install 'datamorph[parquet]'"
+            ) from e
 
         pf = pq.ParquetFile(path)
         for batch in pf.iter_batches():
@@ -330,9 +346,15 @@ def read_stream(self, path: str | Path) -> RowStream:
 
 class ParquetWriter(FormatWriter):
     def write_stream(self, rows: RowStream, path: str | Path) -> int:
-        import pandas as pd
-        import pyarrow as pa
-        import pyarrow.parquet as pq
+        try:
+            import pandas as pd
+            import pyarrow as pa
+            import pyarrow.parquet as pq
+        except ImportError as e:
+            raise ImportError(
+                "Parquet support requires the 'parquet' extra: "
+                "pip install 'datamorph[parquet]'"
+            ) from e
 
         rows_list = list(rows)
         if not rows_list:
@@ -351,7 +373,13 @@ def write_stream(self, rows: RowStream, path: str | Path) -> int:
 
 class AvroReader(FormatReader):
     def read_stream(self, path: str | Path) -> RowStream:
-        import fastavro
+        try:
+            import fastavro
+        except ImportError as e:
+            raise ImportError(
+                "Avro support requires the 'avro' extra: "
+                "pip install 'datamorph[avro]'"
+            ) from e
 
         with open(path, "rb") as f:
             reader = fastavro.reader(f)
@@ -361,7 +389,13 @@ def read_stream(self, path: str | Path) -> RowStream:
 
 class AvroWriter(FormatWriter):
     def write_stream(self, rows: RowStream, path: str | Path) -> int:
-        import fastavro
+        try:
+            import fastavro
+        except ImportError as e:
+            raise ImportError(
+                "Avro support requires the 'avro' extra: "
+                "pip install 'datamorph[avro]'"
+            ) from e
 
         rows_list = list(rows)
         if not rows_list: