jerry-thomas 2.0.0__tar.gz → 2.0.1__tar.gz

{jerry_thomas-2.0.0 → jerry_thomas-2.0.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: jerry-thomas
-Version: 2.0.0
+Version: 2.0.1
 Summary: Jerry-Thomas: a stream-first, plugin-friendly data pipeline (mixology-themed CLI)
 Author: Anders Skott Lind
 License: MIT
@@ -75,32 +75,19 @@ For example: `jerry serve --project lib/my-datapipeline/project.yaml`.
 
 ```bash
 jerry plugin init my-datapipeline --out lib/
-python -m pip install -e lib/my-datapipeline
+
+# Note: import paths use the package name (hyphens become underscores), e.g.
+# `my_datapipeline` even if the dist folder is `my-datapipeline`.
 
 # One-stop wizard: scaffolds source YAML + DTO/parser + domain + mapper + contract.
+# See `docs/cli.md` for wizard tips and identity vs custom guidance.
 jerry inflow create
 
-# Wizard tips (identity vs custom)
-#
-# - Parser:
-#   - Choose "Identity parser" when the loader already yields dicts/objects that match your DTO shape,
-#     and no type conversion is needed.
-#   - Choose "Create new parser" when you need to parse timestamps, coerce types, rename fields,
-#     or drop/validate rows.
-#
-# - Mapper:
-#   - Choose "Identity mapper" only when your DTO already is the final domain record shape (for example you might have used jerry to output interim datasets):
-#     `time` is timezone-aware and identity fields are present.
-#   - Otherwise, choose "Create new mapper" to map DTO -> domain record and add light derived fields.
-#
-# After scaffolding, you typically still need to:
-# - Fill placeholders in `sources/*.yaml` (path/url/headers/etc.).
-# - Reference your stream contract id in `dataset.yaml` under `record_stream: <contract_id>` and pick a `field` for each feature.
-#
 # Reinstall after commands that update entry points (pyproject.toml).
 python -m pip install -e lib/my-datapipeline
 
-jerry serve --dataset your-dataset --limit 3
+# -> fill in your templates generated by 'jerry inflow create' and get ready to serve
+jerry serve --limit 3
 ```
 
 ---

{jerry_thomas-2.0.0 → jerry_thomas-2.0.1}/README.md

@@ -52,32 +52,19 @@ For example: `jerry serve --project lib/my-datapipeline/project.yaml`.
 
 ```bash
 jerry plugin init my-datapipeline --out lib/
-python -m pip install -e lib/my-datapipeline
+
+# Note: import paths use the package name (hyphens become underscores), e.g.
+# `my_datapipeline` even if the dist folder is `my-datapipeline`.
 
 # One-stop wizard: scaffolds source YAML + DTO/parser + domain + mapper + contract.
+# See `docs/cli.md` for wizard tips and identity vs custom guidance.
 jerry inflow create
 
-# Wizard tips (identity vs custom)
-#
-# - Parser:
-#   - Choose "Identity parser" when the loader already yields dicts/objects that match your DTO shape,
-#     and no type conversion is needed.
-#   - Choose "Create new parser" when you need to parse timestamps, coerce types, rename fields,
-#     or drop/validate rows.
-#
-# - Mapper:
-#   - Choose "Identity mapper" only when your DTO already is the final domain record shape (for example you might have used jerry to output interim datasets):
-#     `time` is timezone-aware and identity fields are present.
-#   - Otherwise, choose "Create new mapper" to map DTO -> domain record and add light derived fields.
-#
-# After scaffolding, you typically still need to:
-# - Fill placeholders in `sources/*.yaml` (path/url/headers/etc.).
-# - Reference your stream contract id in `dataset.yaml` under `record_stream: <contract_id>` and pick a `field` for each feature.
-#
 # Reinstall after commands that update entry points (pyproject.toml).
 python -m pip install -e lib/my-datapipeline
 
-jerry serve --dataset your-dataset --limit 3
+# -> fill in your templates generated by 'jerry inflow create' and get ready to serve
+jerry serve --limit 3
 ```
 
 ---

{jerry_thomas-2.0.0 → jerry_thomas-2.0.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "jerry-thomas"
-version = "2.0.0"
+version = "2.0.1"
 description = "Jerry-Thomas: a stream-first, plugin-friendly data pipeline (mixology-themed CLI)"
 readme = { file = "README.md", content-type = "text/markdown" }
 requires-python = ">=3.10"

{jerry_thomas-2.0.0 → jerry_thomas-2.0.1}/src/datapipeline/cli/commands/stream.py

@@ -39,11 +39,12 @@ from datapipeline.services.scaffold.utils import (
 
 def handle(*, plugin_root: Path | None = None, workspace: WorkspaceContext | None = None) -> None:
     root_dir, pkg_name, _ = pkg_root(plugin_root)
-    project_yaml = resolve_default_project_yaml(workspace) or resolve_project_yaml_path(root_dir)
+    project_yaml = resolve_default_project_yaml(
+        workspace) or resolve_project_yaml_path(root_dir)
 
     # Shared context
-    provider = prompt_required("Provider")
-    dataset = prompt_required("Dataset")
+    provider = prompt_required("Provider name (e.g. nasa)")
+    dataset = prompt_required("Dataset name (e.g. weather)")
     source_id = f"{provider}.{dataset}"
 
     # Collected actions (execute at end)
@@ -110,7 +111,8 @@ def handle(*, plugin_root: Path | None = None, workspace: WorkspaceContext | Non
                 ]
                 if choice == "fs":
                     fmt_options.append(("pickle", "pickle"))
-                fmt = pick_from_menu("Format:", fmt_options, allow_default=False)
+                fmt = pick_from_menu(
+                    "Format:", fmt_options, allow_default=False)
             else:
                 fmt = None
             loader_ep, loader_args = default_loader_config(choice, fmt)
@@ -142,7 +144,8 @@ def handle(*, plugin_root: Path | None = None, workspace: WorkspaceContext | Non
                 [(k, k) for k in sorted(parsers.keys())],
             )
         elif pchoice == "create":
-            dto_default = dto_class_name(f"{provider}_{dataset}") if provider and dataset else None
+            dto_default = dto_class_name(
+                f"{provider}_{dataset}") if provider and dataset else None
             dto_class, parser_create_dto = choose_existing_or_create_name(
                 label=LABEL_DTO_FOR_PARSER,
                 existing=sorted(list_dtos(root=plugin_root).keys()),
@@ -228,7 +231,8 @@ def handle(*, plugin_root: Path | None = None, workspace: WorkspaceContext | Non
                 default=default_mapper_name_for_identity(domain),
             )
         else:
-            mapper_name = choose_name("Mapper name", default=default_mapper_name(mapper_input_module, domain))
+            mapper_name = choose_name(
+                "Mapper name", default=default_mapper_name(mapper_input_module, domain))
     elif mchoice == "identity":
         mapper_ep = "identity"
     else:
@@ -264,9 +268,11 @@ def handle(*, plugin_root: Path | None = None, workspace: WorkspaceContext | Non
             domain=domain,
         )
     elif mchoice == "existing":
-        mapper_plan = MapperPlan(create=False, mapper_ep=mapper_ep, domain=domain)
+        mapper_plan = MapperPlan(
+            create=False, mapper_ep=mapper_ep, domain=domain)
     else:
-        mapper_plan = MapperPlan(create=False, mapper_ep="identity", domain=domain)
+        mapper_plan = MapperPlan(
+            create=False, mapper_ep="identity", domain=domain)
 
     plan = StreamPlan(
         provider=provider,

{jerry_thomas-2.0.0 → jerry_thomas-2.0.1}/src/datapipeline/pipeline/stages.py

@@ -25,7 +25,18 @@ from datapipeline.transforms.utils import get_field, partition_key
 
 def open_source_stream(context: PipelineContext, stream_alias: str) -> Source:
     runtime = context.runtime
-    return runtime.registries.stream_sources.get(stream_alias).stream()
+    registry = runtime.registries.stream_sources
+    try:
+        source = registry.get(stream_alias)
+    except KeyError as exc:
+        available = sorted(registry.keys())
+        available_text = ", ".join(available) if available else "(none)"
+        raise KeyError(
+            "Unknown record_stream "
+            f"'{stream_alias}'. Check dataset.yaml and contracts/ ids. "
+            f"Available streams: {available_text}"
+        ) from exc
+    return source.stream()
 
 
 def build_record_stream(

{jerry_thomas-2.0.0 → jerry_thomas-2.0.1}/src/datapipeline/services/paths.py

@@ -8,7 +8,16 @@ def pkg_root(start: Optional[Path] = None) -> tuple[Path, str, Path]:
     for d in [here, *here.parents]:
         pyproject = d / "pyproject.toml"
         if pyproject.exists():
-            return d, d.name, pyproject
+            pkg_name = d.name
+            src_dir = d / "src"
+            if src_dir.exists():
+                candidates = [
+                    p for p in src_dir.iterdir()
+                    if p.is_dir() and (p / "__init__.py").exists()
+                ]
+                if len(candidates) == 1:
+                    pkg_name = candidates[0].name
+            return d, pkg_name, pyproject
     print("[error] pyproject.toml not found (searched current and parent dirs)", file=sys.stderr)
     raise SystemExit(1)
 

{jerry_thomas-2.0.0 → jerry_thomas-2.0.1}/src/datapipeline/services/scaffold/stream_plan.py

@@ -8,6 +8,7 @@ from datapipeline.services.scaffold.mapper import create_mapper
 from datapipeline.services.scaffold.source_yaml import create_source_yaml
 from datapipeline.services.scaffold.contract_yaml import write_ingest_contract
 from datapipeline.services.scaffold.discovery import list_dtos
+from datapipeline.services.paths import pkg_root
 from datapipeline.services.scaffold.utils import error_exit, status
 
 
@@ -50,6 +51,17 @@ class StreamPlan:
 
 
 def execute_stream_plan(plan: StreamPlan) -> None:
+    pyproject_path = None
+    before_pyproject = None
+    try:
+        root_dir, _, pyproject = pkg_root(plan.root)
+        pyproject_path = pyproject
+        if pyproject_path.exists():
+            before_pyproject = pyproject_path.read_text()
+    except SystemExit:
+        pyproject_path = None
+        before_pyproject = None
+
     if plan.create_domain and plan.domain:
         create_domain(domain=plan.domain, root=plan.root)
 
@@ -108,3 +120,10 @@ def execute_stream_plan(plan: StreamPlan) -> None:
         mapper_entrypoint=mapper_ep or "identity",
     )
     status("ok", "Stream created.")
+    if pyproject_path and before_pyproject is not None:
+        after_pyproject = pyproject_path.read_text()
+        if after_pyproject != before_pyproject:
+            status(
+                "note",
+                f"Entry points updated; reinstall plugin: pip install -e {pyproject_path.parent}",
+            )

{jerry_thomas-2.0.0 → jerry_thomas-2.0.1}/src/datapipeline/templates/plugin_skeleton/your-dataset/project.yaml

@@ -9,7 +9,8 @@ paths:
   artifacts: ../artifacts/${project_name}/v${version}
   tasks: ./tasks
 globals:
-  group_by: <your-bucket-cadence>
+  # TODO: Set your grouping cadence (must match ^\d+(m|min|h|d)$).
+  group_by: 1h
   start_time: null
   end_time: null
   split:

{jerry_thomas-2.0.0 → jerry_thomas-2.0.1}/src/datapipeline/templates/plugin_skeleton/your-interim-data-builder/project.yaml

@@ -9,6 +9,7 @@ paths:
   artifacts: ../artifacts/${project_name}/v${version}
   tasks: ./tasks
 globals:
-  group_by: <your-bucket-cadence>
+  # TODO: Set your grouping cadence (must match ^\d+(m|min|h|d)$).
+  group_by: 1h
   start_time: null
   end_time: null

{jerry_thomas-2.0.0 → jerry_thomas-2.0.1}/src/datapipeline/templates/stubs/dto.py.j2

@@ -24,4 +24,4 @@ class {{CLASS_NAME}}:
     # currency: str
     """
     # TODO: define fields matching the '{{DOMAIN}}' source schema
-    raise NotImplementedError(f"Define fields for the DTO '{{CLASS_NAME}}'")
+    pass

{jerry_thomas-2.0.0 → jerry_thomas-2.0.1}/src/datapipeline/templates/stubs/filter.py.j2

@@ -11,6 +11,6 @@ def {{ FUNCTION_NAME }}(stream: Iterator[Any], field: str, target: Any) -> Itera
     Replace the condition below with your own logic.
     """
     for record in stream:
+        # TODO: implement filter logic
         # Example: pass through everything
         yield record
-

{jerry_thomas-2.0.0 → jerry_thomas-2.0.1}/src/datapipeline/templates/stubs/mappers/ingest.py.j2

@@ -10,6 +10,9 @@ def {{FUNCTION_NAME}}(
     **params: Any,
 ) -> Iterator[{{DOMAIN_RECORD}}]:
     """Map {{INPUT_CLASS}} records to domain-level {{DOMAIN_RECORD}} records."""
+    raise NotImplementedError(
+        "Implement mapper logic for {{INPUT_CLASS}} -> {{DOMAIN_RECORD}}"
+    )
     for record in stream:
         # TODO: construct {{DOMAIN_RECORD}} from record fields
         yield {{DOMAIN_RECORD}}(

{jerry_thomas-2.0.0 → jerry_thomas-2.0.1}/src/datapipeline/templates/stubs/parser.py.j2

@@ -22,4 +22,4 @@ class {{CLASS_NAME}}(DataParser[{{DTO_CLASS}}]):
         # return {{DTO_CLASS}}(
         #     ... map fields from `raw` ...
         # )
-        raise NotImplementedError
+        raise NotImplementedError("Implement parser logic for {{DTO_CLASS}}")

{jerry_thomas-2.0.0 → jerry_thomas-2.0.1}/src/datapipeline/templates/stubs/record.py.j2

@@ -13,6 +13,7 @@ class {{CLASS_NAME}}({{PARENT_CLASS}}):
 
     Add any additional fields you need for filtering/partitioning/grouping.
     """
+    # TODO: Add domain fields for filtering/partitioning/grouping.
     # Example extra fields (uncomment and adapt):
     # region: str # e.g. 'us-west', 'eu-central', etc.
     # exchange: str #   e.g. 'NASDAQ', 'NYSE', etc.

{jerry_thomas-2.0.0 → jerry_thomas-2.0.1}/src/jerry_thomas.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: jerry-thomas
-Version: 2.0.0
+Version: 2.0.1
 Summary: Jerry-Thomas: a stream-first, plugin-friendly data pipeline (mixology-themed CLI)
 Author: Anders Skott Lind
 License: MIT
@@ -75,32 +75,19 @@ For example: `jerry serve --project lib/my-datapipeline/project.yaml`.
 
 ```bash
 jerry plugin init my-datapipeline --out lib/
-python -m pip install -e lib/my-datapipeline
+
+# Note: import paths use the package name (hyphens become underscores), e.g.
+# `my_datapipeline` even if the dist folder is `my-datapipeline`.
 
 # One-stop wizard: scaffolds source YAML + DTO/parser + domain + mapper + contract.
+# See `docs/cli.md` for wizard tips and identity vs custom guidance.
 jerry inflow create
 
-# Wizard tips (identity vs custom)
-#
-# - Parser:
-#   - Choose "Identity parser" when the loader already yields dicts/objects that match your DTO shape,
-#     and no type conversion is needed.
-#   - Choose "Create new parser" when you need to parse timestamps, coerce types, rename fields,
-#     or drop/validate rows.
-#
-# - Mapper:
-#   - Choose "Identity mapper" only when your DTO already is the final domain record shape (for example you might have used jerry to output interim datasets):
-#     `time` is timezone-aware and identity fields are present.
-#   - Otherwise, choose "Create new mapper" to map DTO -> domain record and add light derived fields.
-#
-# After scaffolding, you typically still need to:
-# - Fill placeholders in `sources/*.yaml` (path/url/headers/etc.).
-# - Reference your stream contract id in `dataset.yaml` under `record_stream: <contract_id>` and pick a `field` for each feature.
-#
 # Reinstall after commands that update entry points (pyproject.toml).
 python -m pip install -e lib/my-datapipeline
 
-jerry serve --dataset your-dataset --limit 3
+# -> fill in your templates generated by 'jerry inflow create' and get ready to serve
+jerry serve --limit 3
 ```
 
 ---