jerry-thomas 1.0.0__tar.gz → 1.0.1__tar.gz

{jerry_thomas-1.0.0 → jerry_thomas-1.0.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: jerry-thomas
-Version: 1.0.0
+Version: 1.0.1
 Summary: Jerry-Thomas: a stream-first, plugin-friendly data pipeline (mixology-themed CLI)
 Author: Anders Skott Lind
 License: MIT

{jerry_thomas-1.0.0 → jerry_thomas-1.0.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "jerry-thomas"
-version = "1.0.0"
+version = "1.0.1"
 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-1.0.0 → jerry_thomas-1.0.1}/src/datapipeline/cli/commands/plugin.py

@@ -1,10 +1,14 @@
+import logging
 from pathlib import Path
 from datapipeline.services.scaffold.plugin import scaffold_plugin
 
 
+logger = logging.getLogger(__name__)
+
+
 def bar(subcmd: str, name: str | None, out: str) -> None:
     if subcmd == "init":
         if not name:
-            print("[error] Plugin name is required. Use 'jerry plugin init <name>' or pass -n/--name.")
+            logger.error("Plugin name is required. Use 'jerry plugin init <name>' or pass -n/--name.")
             raise SystemExit(2)
         scaffold_plugin(name, Path(out))

jerry_thomas-1.0.1/src/datapipeline/services/scaffold/plugin.py

@@ -0,0 +1,93 @@
+from importlib.resources import as_file, files
+from pathlib import Path
+import logging
+import os
+
+import yaml
+
+from datapipeline.utils.load import load_yaml
+
+from ..constants import DEFAULT_IO_LOADER_EP
+
+logger = logging.getLogger(__name__)
+
+_RESERVED_PACKAGE_NAMES = {"datapipeline"}
+
+
+def _normalized_package_name(dist_name: str) -> str:
+    package_name = dist_name.replace("-", "_")
+    if package_name in _RESERVED_PACKAGE_NAMES:
+        logger.error(
+            "`datapipeline` is reserved for the core package. Choose a different plugin name."
+        )
+        raise SystemExit(1)
+    if not package_name.isidentifier():
+        logger.error(
+            "Plugin names must be valid Python identifiers once hyphens are replaced with underscores."
+        )
+        raise SystemExit(1)
+    return package_name
+
+
+def scaffold_plugin(name: str, outdir: Path) -> None:
+    target = (outdir / name).absolute()
+    if target.exists():
+        logger.error("`%s` already exists", target)
+        raise SystemExit(1)
+    import shutil
+
+    package_name = _normalized_package_name(name)
+    skeleton_ref = files("datapipeline") / "templates" / "plugin_skeleton"
+    with as_file(skeleton_ref) as skeleton_dir:
+        shutil.copytree(skeleton_dir, target)
+    pkg_dir = target / "src" / "{{PACKAGE_NAME}}"
+    pkg_dir.rename(target / "src" / package_name)
+    replacements = {
+        "{{PACKAGE_NAME}}": package_name,
+        "{{DIST_NAME}}": name,
+        "{{DEFAULT_IO_LOADER_EP}}": DEFAULT_IO_LOADER_EP,
+    }
+    for p in (target / "pyproject.toml", target / "README.md"):
+        text = p.read_text()
+        for placeholder, value in replacements.items():
+            text = text.replace(placeholder, value)
+        p.write_text(text)
+
+    # Move jerry.yaml up to the workspace root (current working directory) so
+    # users can run the CLI from the workspace without cd'ing into the plugin.
+    # We adjust plugin_root and dataset paths to point at the plugin directory
+    # relative to the workspace. Do not overwrite an existing workspace
+    # jerry.yaml.
+    plugin_jerry = target / "jerry.yaml"
+    workspace_root = Path.cwd().resolve()
+    workspace_jerry = workspace_root / "jerry.yaml"
+    if plugin_jerry.exists() and not workspace_jerry.exists():
+        try:
+            plugin_root_rel = target.relative_to(workspace_root)
+        except ValueError:
+            # Fall back to a relative path between arbitrary directories; this
+            # may include ".." segments.
+            try:
+                plugin_root_rel = Path(os.path.relpath(target, workspace_root))
+            except Exception:
+                plugin_root_rel = target
+
+        data = load_yaml(plugin_jerry)
+        data["plugin_root"] = plugin_root_rel.as_posix()
+        datasets = data.get("datasets") or {}
+        updated_datasets = {}
+        for alias, path in datasets.items():
+            p = Path(path)
+            if p.is_absolute():
+                updated_datasets[alias] = p.as_posix()
+            else:
+                updated_datasets[alias] = (plugin_root_rel / p).as_posix()
+        data["datasets"] = updated_datasets
+
+        workspace_jerry.write_text(
+            yaml.safe_dump(data, sort_keys=False), encoding="utf-8"
+        )
+        plugin_jerry.unlink()
+        logger.info("workspace jerry.yaml created at %s", workspace_jerry)
+
+    logger.info("plugin skeleton created at %s", target)

{jerry_thomas-1.0.0 → jerry_thomas-1.0.1}/src/datapipeline/templates/plugin_skeleton/README.md

@@ -10,6 +10,8 @@ Quick start
   - HTTP data: `jerry source add <provider>.<dataset> -t http -f <json|json-lines|csv>`
   - Synthetic: `jerry source add -p <provider> -d <dataset> -t synthetic`
 - Edit the generated `config/sources/*.yaml` to fill in the `path`, delimiter, etc.
+- `jerry.yaml` is placed in your workspace root (alongside the plugin folder) so
+  you can run CLI commands from there; `plugin_root` points back to this plugin.
 - Reinstall after EP changes (pyproject.toml) and restart Python processes:
   - Core: `cd lib/datapipeline && python -m pip install -e .`
   - This plugin: `python -m pip install -e .`

jerry_thomas-1.0.1/src/datapipeline/templates/plugin_skeleton/jerry.yaml

@@ -0,0 +1,34 @@
+# Workspace defaults. The scaffolder copies this to your workspace root (where
+# you ran `jerry plugin init`). CLI commands walk upward from cwd to find it.
+
+# Relative path from this workspace file back to the plugin root.
+plugin_root: . # e.g., "lib/myplugin" if your plugin lives under lib/
+
+# Dataset aliases for `--dataset`; values may be dirs (auto-append project.yaml).
+datasets:
+  example: example/project.yaml
+  your-second-example-dataset: your-dataset/project.yaml
+
+# Default dataset alias when --dataset/--project are omitted.
+default_dataset: example
+
+# Shared fallbacks used by all commands (unless overridden).
+shared:
+  visuals: AUTO # AUTO | TQDM | RICH | OFF
+  progress: BARS # AUTO | SPINNER | BARS | OFF
+  log_level: INFO # Default log level when not set elsewhere
+
+# Defaults for `jerry serve` (run-time options).
+serve:
+  # log_level: INFO # Uncomment to force INFO for serve runs
+  limit: null      # Cap vectors; null means unlimited
+  stage: null      # Preview a specific stage; null runs the full pipeline
+  output:
+    transport: stdout
+    format: print  # stdout: print|json-lines|json|csv|pickle
+    # directory: artifacts/serve # Required when transport=fs
+
+# Defaults for `jerry build` (artifact materialization).
+build:
+  # log_level: INFO # Uncomment to set build log level
+  mode: AUTO # AUTO | FORCE | OFF

{jerry_thomas-1.0.0 → jerry_thomas-1.0.1}/src/jerry_thomas.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: jerry-thomas
-Version: 1.0.0
+Version: 1.0.1
 Summary: Jerry-Thomas: a stream-first, plugin-friendly data pipeline (mixology-themed CLI)
 Author: Anders Skott Lind
 License: MIT

jerry_thomas-1.0.0/src/datapipeline/services/scaffold/plugin.py

@@ -1,49 +0,0 @@
-from importlib.resources import as_file, files
-from pathlib import Path
-
-from ..constants import DEFAULT_IO_LOADER_EP
-
-_RESERVED_PACKAGE_NAMES = {"datapipeline"}
-
-
-def _normalized_package_name(dist_name: str) -> str:
-    package_name = dist_name.replace("-", "_")
-    if package_name in _RESERVED_PACKAGE_NAMES:
-        print(
-            "[error] `datapipeline` is reserved for the core package. "
-            "Choose a different plugin name."
-        )
-        raise SystemExit(1)
-    if not package_name.isidentifier():
-        print(
-            "[error] Plugin names must be valid Python identifiers once hyphens are replaced "
-            "with underscores."
-        )
-        raise SystemExit(1)
-    return package_name
-
-
-def scaffold_plugin(name: str, outdir: Path) -> None:
-    target = (outdir / name).absolute()
-    if target.exists():
-        print(f"[error] `{target}` already exists")
-        raise SystemExit(1)
-    import shutil
-
-    package_name = _normalized_package_name(name)
-    skeleton_ref = files("datapipeline") / "templates" / "plugin_skeleton"
-    with as_file(skeleton_ref) as skeleton_dir:
-        shutil.copytree(skeleton_dir, target)
-    pkg_dir = target / "src" / "{{PACKAGE_NAME}}"
-    pkg_dir.rename(target / "src" / package_name)
-    replacements = {
-        "{{PACKAGE_NAME}}": package_name,
-        "{{DIST_NAME}}": name,
-        "{{DEFAULT_IO_LOADER_EP}}": DEFAULT_IO_LOADER_EP,
-    }
-    for p in (target / "pyproject.toml", target / "README.md"):
-        text = p.read_text()
-        for placeholder, value in replacements.items():
-            text = text.replace(placeholder, value)
-        p.write_text(text)
-    print(f"[new] plugin skeleton at {target}")

jerry_thomas-1.0.0/src/datapipeline/templates/plugin_skeleton/jerry.yaml

@@ -1,28 +0,0 @@
-# Workspace defaults. Move this file to the root of your workspace if you serve
-# configs outside the plugin repo; the CLI searches upward from cwd for jerry.yaml.
-
-plugin_root: . # relative path to the plugin repo root
-
-datasets:
-  example: example/project.yaml
-  your-second-example-dataset: your-dataset/project.yaml
-
-default_dataset: example
-
-shared:
-  visuals: AUTO # AUTO | TQDM | RICH | OFF
-  progress: BARS # AUTO | SPINNER | BARS | OFF
-  log_level: INFO
-
-serve:
-  # log_level: INFO
-  limit: null
-  stage: null
-  output:
-    transport: stdout
-    format: print # set to fs + directory for file outputs
-    # directory: artifacts/serve
-
-build:
-  # log_level: INFO
-  mode: AUTO # AUTO | FORCE | OFF