subtask-manager 0.1.0__tar.gz

subtask_manager-0.1.0/.gitattributes

@@ -0,0 +1,7 @@
+# .gitattributes
+* text=auto
+*.rs text
+*.js text
+*.html text
+*.css text
+# Add other file types as needed

subtask_manager-0.1.0/.gitignore

@@ -0,0 +1,5 @@
+target/
+.venv
+.ruff_cache
+__pycache__
+.env

subtask_manager-0.1.0/.python-version

@@ -0,0 +1 @@
+3.11

subtask_manager-0.1.0/Cargo.lock

@@ -0,0 +1,276 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "anyhow"
+version = "1.0.100"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a23eb6b1614318a8071c9b2521f36b424b2c83db5eb3a0fead4a6c0809af6e61"
+
+[[package]]
+name = "autocfg"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c08606f8c3cbf4ce6ec8e28fb0014a2c086708fe954eaa885384a6165172e7e8"
+
+[[package]]
+name = "cfg-if"
+version = "1.0.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2fd1289c04a9ea8cb22300a459a72a385d7c73d3259e2ed7dcb2af674838cfa9"
+
+[[package]]
+name = "heck"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
+
+[[package]]
+name = "indoc"
+version = "2.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f4c7245a08504955605670dbf141fceab975f15ca21570696aebe9d2e71576bd"
+
+[[package]]
+name = "libc"
+version = "0.2.176"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "58f929b4d672ea937a23a1ab494143d968337a5f47e56d0815df1e0890ddf174"
+
+[[package]]
+name = "memoffset"
+version = "0.9.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "488016bfae457b036d996092f6cb448677611ce4449e970ceaf42695203f218a"
+dependencies = [
+ "autocfg",
+]
+
+[[package]]
+name = "once_cell"
+version = "1.21.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"
+
+[[package]]
+name = "portable-atomic"
+version = "1.11.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f84267b20a16ea918e43c6a88433c2d54fa145c92a811b5b047ccbe153674483"
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.101"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "89ae43fd86e4158d6db51ad8e2b80f313af9cc74f5c0e03ccb87de09998732de"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "pyo3"
+version = "0.22.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f402062616ab18202ae8319da13fa4279883a2b8a9d9f83f20dbade813ce1884"
+dependencies = [
+ "cfg-if",
+ "indoc",
+ "libc",
+ "memoffset",
+ "once_cell",
+ "portable-atomic",
+ "pyo3-build-config",
+ "pyo3-ffi",
+ "pyo3-macros",
+ "unindent",
+]
+
+[[package]]
+name = "pyo3-build-config"
+version = "0.22.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b14b5775b5ff446dd1056212d778012cbe8a0fbffd368029fd9e25b514479c38"
+dependencies = [
+ "once_cell",
+ "target-lexicon",
+]
+
+[[package]]
+name = "pyo3-ffi"
+version = "0.22.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9ab5bcf04a2cdcbb50c7d6105de943f543f9ed92af55818fd17b660390fc8636"
+dependencies = [
+ "libc",
+ "pyo3-build-config",
+]
+
+[[package]]
+name = "pyo3-macros"
+version = "0.22.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fd24d897903a9e6d80b968368a34e1525aeb719d568dba8b3d4bfa5dc67d453"
+dependencies = [
+ "proc-macro2",
+ "pyo3-macros-backend",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "pyo3-macros-backend"
+version = "0.22.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "36c011a03ba1e50152b4b394b479826cad97e7a21eb52df179cd91ac411cbfbe"
+dependencies = [
+ "heck",
+ "proc-macro2",
+ "pyo3-build-config",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.40"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1885c039570dc00dcb4ff087a89e185fd56bae234ddc7f056a945bf36467248d"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "same-file"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "93fc1dc3aaa9bfed95e02e6eadabb4baf7e3078b0bd1b4d7b6b0b68378900502"
+dependencies = [
+ "winapi-util",
+]
+
+[[package]]
+name = "serde"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9a8e94ea7f378bd32cbbd37198a4a91436180c5bb472411e48b5ec2e2124ae9e"
+dependencies = [
+ "serde_core",
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_core"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "41d385c7d4ca58e59fc732af25c3983b67ac852c1a25000afe1175de458b67ad"
+dependencies = [
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_derive"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "strum"
+version = "0.27.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "af23d6f6c1a224baef9d3f61e287d2761385a5b88fdab4eb4c6f11aeb54c4bcf"
+dependencies = [
+ "strum_macros",
+]
+
+[[package]]
+name = "strum_macros"
+version = "0.27.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7695ce3845ea4b33927c055a39dc438a45b059f7c1b3d91d38d10355fb8cbca7"
+dependencies = [
+ "heck",
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "subtask_manager"
+version = "0.1.0"
+dependencies = [
+ "anyhow",
+ "pyo3",
+ "serde",
+ "strum",
+ "strum_macros",
+ "walkdir",
+]
+
+[[package]]
+name = "syn"
+version = "2.0.106"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ede7c438028d4436d71104916910f5bb611972c5cfd7f89b8300a8186e6fada6"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "target-lexicon"
+version = "0.12.16"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "61c41af27dd6d1e27b1b16b489db798443478cef1f06a660c96db617ba5de3b1"
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f63a545481291138910575129486daeaf8ac54aee4387fe7906919f7830c7d9d"
+
+[[package]]
+name = "unindent"
+version = "0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7264e107f553ccae879d21fbea1d6724ac785e8c3bfc762137959b5802826ef3"
+
+[[package]]
+name = "walkdir"
+version = "2.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "29790946404f91d9c5d06f9874efddea1dc06c5efe94541a7d6863108e3a5e4b"
+dependencies = [
+ "same-file",
+ "winapi-util",
+]
+
+[[package]]
+name = "winapi-util"
+version = "0.1.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
+dependencies = [
+ "windows-sys",
+]
+
+[[package]]
+name = "windows-link"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "45e46c0661abb7180e7b9c281db115305d49ca1709ab8242adf09666d2173c65"
+
+[[package]]
+name = "windows-sys"
+version = "0.61.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6f109e41dd4a3c848907eb83d5a42ea98b3769495597450cf6d153507b166f0f"
+dependencies = [
+ "windows-link",
+]

subtask_manager-0.1.0/Cargo.toml

@@ -0,0 +1,20 @@
+[package]
+name = "subtask_manager"
+version = "0.1.0"
+edition = "2021"
+readme = "README.md"
+
+[lib]
+name = "_core"
+# "cdylib" is necessary to produce a shared library for Python to import from.
+crate-type = ["cdylib"]
+
+[dependencies]
+anyhow = "1.0.100"
+# "extension-module" tells pyo3 we want to build an extension module (skips linking against libpython.so)
+# "abi3-py39" tells pyo3 (and maturin) to build using the stable ABI with minimum Python version 3.9
+pyo3 = { version = "0.22.4", features = ["extension-module", "abi3-py39"] }
+serde = { version = "1.0.228", features = ["derive"] }
+strum = { version = "0.27.2", features = ["derive"] }
+strum_macros = "0.27.2"
+walkdir = "2.5.0"

subtask_manager-0.1.0/PKG-INFO

@@ -0,0 +1,11 @@
+Metadata-Version: 2.4
+Name: subtask-manager
+Version: 0.1.0
+Requires-Dist: pydantic>=2.11.9
+Summary: ETL Subtask management library written in Rust
+Author-email: Din Gior <dingior10@gmail.com>
+License: MIT
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
+
+

subtask_manager-0.1.0/REFACTORING_SUMMARY.md

@@ -0,0 +1,180 @@
+# Refactoring Summary: Type-Safe Enum Parameters
+
+## Overview
+Refactored the `get_tasks()` method in `SubtaskManager` to accept enum types (`EtlStage`, `SystemType`, `TaskType`) instead of strings, improving type safety and API usability.
+
+## Changes Made
+
+### Before
+```python
+# String-based API (error-prone)
+tasks = manager.get_tasks(
+    etl_stage="extract",      # String - typos caught only at runtime
+    system_type="postgres",   # String - no IDE autocomplete
+    task_type="sql"           # String - magic values
+)
+```
+
+### After
+```python
+# Enum-based API (type-safe)
+tasks = manager.get_tasks(
+    etl_stage=EtlStage.Extract,        # Enum - IDE autocomplete
+    system_type=SystemType.PostgreSQL,  # Enum - compile-time safety
+    task_type=TaskType.Sql              # Enum - self-documenting
+)
+```
+
+## Technical Details
+
+### Function Signature Change
+
+**Previous signature:**
+```rust
+fn get_tasks(
+    &mut self,
+    py: Python,
+    etl_stage: Option<String>,
+    entity: Option<String>,
+    system_type: Option<String>,
+    task_type: Option<String>,
+    is_common: Option<bool>,
+    include_common: Option<bool>,
+) -> PyResult<Py<PyList>>
+```
+
+**New signature:**
+```rust
+fn get_tasks(
+    &mut self,
+    py: Python,
+    etl_stage: Option<EtlStage>,
+    entity: Option<String>,
+    system_type: Option<SystemType>,
+    task_type: Option<TaskType>,
+    is_common: Option<bool>,
+    include_common: Option<bool>,
+) -> PyResult<Py<PyList>>
+```
+
+### Code Simplification
+
+**Removed conversion logic:**
+```rust
+// OLD: Had to convert strings to enums
+let input_etl_stage = etl_stage
+    .as_ref()
+    .and_then(|es| EtlStage::from_alias(es).ok());
+
+let input_system_type = system_type
+    .as_ref()
+    .and_then(|st| SystemType::from_alias(st).ok());
+
+let input_task_type = task_type
+    .as_ref()
+    .and_then(|tt| TaskType::from_extension(tt).ok());
+```
+
+**NEW: Direct enum usage:**
+```rust
+// NEW: Use enums directly
+if let Some(ref es) = etl_stage {
+    if subtask.stage.as_ref() != Some(es) {
+        continue;
+    }
+}
+```
+
+## Benefits
+
+### 1. **Type Safety**
+- Compile-time checking prevents invalid values
+- No need to validate string inputs at runtime
+- Eliminates typos and magic strings
+
+### 2. **Better Developer Experience**
+- IDE autocomplete for all enum variants
+- Self-documenting code - clear what values are valid
+- Easier refactoring - renaming enums updates all usages
+
+### 3. **Performance**
+- Eliminates string-to-enum conversion overhead
+- More efficient comparison operations
+- Reduced runtime error handling
+
+### 4. **Cleaner Code**
+- Removed ~15 lines of conversion logic
+- Simplified filtering logic
+- More readable and maintainable
+
+## Migration Guide
+
+### For Python Users
+
+**Old usage (still works via `from_alias`):**
+```python
+# If you have strings from configuration files
+stage_str = "extract"
+stage_enum = EtlStage.from_alias(stage_str)
+tasks = manager.get_tasks(etl_stage=stage_enum)
+```
+
+**Recommended new usage:**
+```python
+from subtask_manager import SubtaskManager, EtlStage, SystemType, TaskType
+
+manager = SubtaskManager("./tasks")
+
+# Direct enum usage
+tasks = manager.get_tasks(
+    etl_stage=EtlStage.Extract,
+    system_type=SystemType.PostgreSQL,
+    task_type=TaskType.Sql
+)
+```
+
+### Enum Properties Available
+
+All enums expose these properties:
+- `.name` - Human-readable name
+- `.id` - Numeric identifier
+- `.aliases` (EtlStage, SystemType) - List of valid aliases
+- `.extensions` (TaskType) - List of file extensions
+
+Static methods:
+- `EtlStage.from_alias(str)` - Convert alias to enum
+- `SystemType.from_alias(str)` - Convert alias to enum
+- `TaskType.from_extension(str)` - Convert extension to enum
+
+## Examples
+
+See `example_enum_usage.py` for comprehensive examples including:
+- Basic filtering by enum
+- Combining multiple filters
+- Using enum properties
+- Converting strings to enums when needed
+
+## Backward Compatibility
+
+This is a **breaking change** for Python users who were passing strings directly to `get_tasks()`. 
+
+To maintain compatibility with existing code, consider:
+1. Using `from_alias()` to convert strings to enums
+2. Updating all call sites to use enum types
+3. Creating wrapper functions if needed
+
+## Testing
+
+Verified compilation with:
+```bash
+cargo check
+```
+
+All type checks pass successfully.
+
+## Future Improvements
+
+Consider similar refactoring for:
+- Other methods that accept string parameters
+- Configuration file parsing to return enums
+- Validation helpers that work with enums

subtask_manager-0.1.0/main.py

@@ -0,0 +1,44 @@
+from pathlib import Path
+
+from subtask_manager import (
+    EtlStage,
+    FileClassifier,
+    FileScanner,
+    Subtask,
+    SubtaskManager,
+    SystemType,
+    TaskType,
+)
+
+sm: SubtaskManager = SubtaskManager(
+    base_path="tests/test_data/subtasks",
+)
+for subtask in sm.subtasks:
+    print(subtask.entity)
+
+print(EtlStage.Postprocessing.aliases)
+
+print(SystemType.PostgreSQL.aliases)
+print(SystemType.PostgreSQL.id)
+print(EtlStage.Cleanup.id)
+
+print(SystemType.from_alias("pg") == SystemType.PostgreSQL)
+print(type(SystemType.from_alias("pg")))
+print(type(SystemType.PostgreSQL))
+
+print(TaskType.Graphql.extensions)
+
+fs = FileScanner(["py"])
+print(fs.extensions)
+
+
+# Using string path
+manager1 = SubtaskManager("tests/test_data/subtasks")
+print(manager1.base_path)
+
+# Using pathlib.Path
+manager2 = SubtaskManager(Path("tests/test_data/subtasks"))
+print(manager2.base_path)
+
+fcs = FileClassifier(Path("tests/test_data/subtasks"))
+print(fcs.base_path)

subtask_manager-0.1.0/pyproject.toml

@@ -0,0 +1,33 @@
+[project]
+name = "subtask-manager"
+version = "0.1.0"
+description = "ETL Subtask management library written in Rust"
+readme = "README.md"
+license = { text = "MIT" }
+authors = [
+    { name = "Din Gior", email = "dingior10@gmail.com" }
+]
+requires-python = ">=3.11"
+dependencies = [
+    "pydantic>=2.11.9",
+]
+
+[project.scripts]
+subtask-manager = "subtask_manager:main"
+
+[tool.maturin]
+module-name = "subtask_manager._core"
+python-packages = ["subtask_manager"]
+python-source = ""
+
+[build-system]
+requires = ["maturin>=1.0,<2.0"]
+build-backend = "maturin"
+
+[dependency-groups]
+dev = [
+    "maturin>=1.9.5",
+    "pyo3-stubgen>=0.3.0",
+    "pytest>=8.4.2",
+    "ruff>=0.13.2",
+]