etlplus 0.12.3__tar.gz → 0.13.0__tar.gz

{etlplus-0.12.3/etlplus.egg-info → etlplus-0.13.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: etlplus
-Version: 0.12.3
+Version: 0.13.0
 Summary: A Swiss Army knife for simple ETL operations
 Home-page: https://github.com/Dagitali/ETLPlus
 Author: ETLPlus Team
@@ -68,6 +68,21 @@ package and command-line interface for data extraction, validation, transformati
   - [Features](#features)
   - [Installation](#installation)
   - [Quickstart](#quickstart)
+  - [Data Connectors](#data-connectors)
+    - [REST APIs (`api`)](#rest-apis-api)
+    - [Databases (`database`)](#databases-database)
+    - [Files (`file`)](#files-file)
+      - [Stubbed / Placeholder](#stubbed--placeholder)
+      - [Tabular \& Delimited Text](#tabular--delimited-text)
+      - [Semi-Structured Text](#semi-structured-text)
+      - [Columnar / Analytics-Friendly](#columnar--analytics-friendly)
+      - [Binary Serialization and Interchange](#binary-serialization-and-interchange)
+      - [Databases and Embedded Storage](#databases-and-embedded-storage)
+      - [Spreadsheets](#spreadsheets)
+      - [Statistical / Scientific / Numeric Computing](#statistical--scientific--numeric-computing)
+      - [Logs and Event Streams](#logs-and-event-streams)
+      - [Data Archives](#data-archives)
+      - [Templates](#templates)
   - [Usage](#usage)
     - [Command Line Interface](#command-line-interface)
       - [Argument Order and Required Options](#argument-order-and-required-options)
@@ -191,6 +206,140 @@ assert validate(filtered, rules)["valid"]
 load(filtered, "file", "temp/sample_output.json", file_format="json")
 ```
 
+## Data Connectors
+
+Data connectors abstract sources from which to extract data and targets to which to load data. They
+are differentiated by their types, each of which is represented in the subsections below.
+
+### REST APIs (`api`)
+
+ETLPlus can extract from REST APIs and load results via common HTTP methods. Supported operations
+include GET for extract and PATCH/POST/PUT for load.
+
+### Databases (`database`)
+
+Database connectors use connection strings for extraction and loading, and
+DDL can be rendered from table specs for migrations or schema checks.
+
+### Files (`file`)
+
+Recognized file formats are listed in the tables below. Support for reading to or writing from a recognized file format is marked as:
+
+- **Y**: implemented (may require optional dependencies)
+- **N**: stubbed or not yet implemented
+
+#### Stubbed / Placeholder
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `stub` | N | Placeholder format for tests and future connectors. |
+
+#### Tabular & Delimited Text
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `csv` | Y | Y | Comma-Separated Values |
+| `dat` | N | N | Generic data file, often delimited or fixed-width |
+| `fwf` | N | N | Fixed-Width Fields |
+| `psv` | N | N | Pipe-Separated Values |
+| `tab` | N | N | Often synonymous with TSV |
+| `tsv` | Y | Y | Tab-Separated Values |
+| `txt` | Y | Y | Plain text, often delimited or fixed-width |
+
+#### Semi-Structured Text
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `cfg` | N | N | Config-style key-value pairs |
+| `conf` | N | N | Config-style key-value pairs |
+| `ini` | N | N | Config-style key-value pairs |
+| `json` | Y | Y | JavaScript Object Notation |
+| `ndjson` | Y | Y | Newline-Delimited JSON |
+| `properties` | N | N | Java-style key-value pairs |
+| `toml` | N | N | Tom's Obvious Minimal Language |
+| `xml` | Y | Y | Extensible Markup Language |
+| `yaml` | Y | Y | YAML Ain't Markup Language |
+
+#### Columnar / Analytics-Friendly
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `arrow` | N | N | Apache Arrow IPC |
+| `feather` | Y | Y | Apache Arrow Feather |
+| `orc` | Y | Y | Optimized Row Columnar; common in Hadoop |
+| `parquet` | Y | Y | Apache Parquet; common in Big Data |
+
+#### Binary Serialization and Interchange
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `avro` | Y | Y | Apache Avro |
+| `bson` | N | N | Binary JSON; common with MongoDB exports/dumps |
+| `cbor` | N | N | Concise Binary Object Representation |
+| `ion` | N | N | Amazon Ion |
+| `msgpack` | N | N | MessagePack |
+| `pb` | N | N | Protocol Buffers (Google Protobuf) |
+| `pbf` | N | N | Protocolbuffer Binary Format; often for GIS data |
+| `proto` | N | N | Protocol Buffers schema; often in .pb / .bin |
+
+#### Databases and Embedded Storage
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `accdb` | N | N | Microsoft Access (newer format) |
+| `duckdb` | N | N | DuckDB |
+| `mdb` | N | N | Microsoft Access (older format) |
+| `sqlite` | N | N | SQLite |
+
+#### Spreadsheets
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `numbers` | N | N | Apple Numbers |
+| `ods` | N | N | OpenDocument |
+| `wks` | N | N | Lotus 1-2-3  |
+| `xls` | Y | Y | Microsoft Excel (BIFF) |
+| `xlsm` | N | N | Microsoft Excel Macro-Enabled (Open XML) |
+| `xlsx` | Y | Y | Microsoft Excel (Open XML) |
+
+#### Statistical / Scientific / Numeric Computing
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `dta` | N | N | Stata |
+| `hdf5` | N | N | Hierarchical Data Format |
+| `mat` | N | N | MATLAB |
+| `nc` | N | N | NetCDF |
+| `rda` | N | N | RData workspace/object |
+| `rds` | N | N | R data |
+| `sas7bdat` | N | N | SAS data |
+| `sav` | N | N | SPSS data |
+| `sylk` | N | N | Symbolic Link |
+| `xpt` | N | N | SAS Transport |
+| `zsav` | N | N | Compressed SPSS data |
+
+#### Logs and Event Streams
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `log` | N | N | Generic log file |
+
+#### Data Archives
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `gz` | Y | Y | Gzip-compressed file |
+| `zip` | Y | Y | ZIP archive |
+
+#### Templates
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `hbs` | N | N | Handlebars |
+| `jinja2` | N | N | Jinja2 |
+| `mustache` | N | N | Mustache |
+| `vm` | N | N | Apache Velocity |
+
 ## Usage
 
 ### Command Line Interface

{etlplus-0.12.3 → etlplus-0.13.0}/README.md

@@ -18,6 +18,21 @@ package and command-line interface for data extraction, validation, transformati
   - [Features](#features)
   - [Installation](#installation)
   - [Quickstart](#quickstart)
+  - [Data Connectors](#data-connectors)
+    - [REST APIs (`api`)](#rest-apis-api)
+    - [Databases (`database`)](#databases-database)
+    - [Files (`file`)](#files-file)
+      - [Stubbed / Placeholder](#stubbed--placeholder)
+      - [Tabular \& Delimited Text](#tabular--delimited-text)
+      - [Semi-Structured Text](#semi-structured-text)
+      - [Columnar / Analytics-Friendly](#columnar--analytics-friendly)
+      - [Binary Serialization and Interchange](#binary-serialization-and-interchange)
+      - [Databases and Embedded Storage](#databases-and-embedded-storage)
+      - [Spreadsheets](#spreadsheets)
+      - [Statistical / Scientific / Numeric Computing](#statistical--scientific--numeric-computing)
+      - [Logs and Event Streams](#logs-and-event-streams)
+      - [Data Archives](#data-archives)
+      - [Templates](#templates)
   - [Usage](#usage)
     - [Command Line Interface](#command-line-interface)
       - [Argument Order and Required Options](#argument-order-and-required-options)
@@ -141,6 +156,140 @@ assert validate(filtered, rules)["valid"]
 load(filtered, "file", "temp/sample_output.json", file_format="json")
 ```
 
+## Data Connectors
+
+Data connectors abstract sources from which to extract data and targets to which to load data. They
+are differentiated by their types, each of which is represented in the subsections below.
+
+### REST APIs (`api`)
+
+ETLPlus can extract from REST APIs and load results via common HTTP methods. Supported operations
+include GET for extract and PATCH/POST/PUT for load.
+
+### Databases (`database`)
+
+Database connectors use connection strings for extraction and loading, and
+DDL can be rendered from table specs for migrations or schema checks.
+
+### Files (`file`)
+
+Recognized file formats are listed in the tables below. Support for reading to or writing from a recognized file format is marked as:
+
+- **Y**: implemented (may require optional dependencies)
+- **N**: stubbed or not yet implemented
+
+#### Stubbed / Placeholder
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `stub` | N | Placeholder format for tests and future connectors. |
+
+#### Tabular & Delimited Text
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `csv` | Y | Y | Comma-Separated Values |
+| `dat` | N | N | Generic data file, often delimited or fixed-width |
+| `fwf` | N | N | Fixed-Width Fields |
+| `psv` | N | N | Pipe-Separated Values |
+| `tab` | N | N | Often synonymous with TSV |
+| `tsv` | Y | Y | Tab-Separated Values |
+| `txt` | Y | Y | Plain text, often delimited or fixed-width |
+
+#### Semi-Structured Text
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `cfg` | N | N | Config-style key-value pairs |
+| `conf` | N | N | Config-style key-value pairs |
+| `ini` | N | N | Config-style key-value pairs |
+| `json` | Y | Y | JavaScript Object Notation |
+| `ndjson` | Y | Y | Newline-Delimited JSON |
+| `properties` | N | N | Java-style key-value pairs |
+| `toml` | N | N | Tom's Obvious Minimal Language |
+| `xml` | Y | Y | Extensible Markup Language |
+| `yaml` | Y | Y | YAML Ain't Markup Language |
+
+#### Columnar / Analytics-Friendly
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `arrow` | N | N | Apache Arrow IPC |
+| `feather` | Y | Y | Apache Arrow Feather |
+| `orc` | Y | Y | Optimized Row Columnar; common in Hadoop |
+| `parquet` | Y | Y | Apache Parquet; common in Big Data |
+
+#### Binary Serialization and Interchange
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `avro` | Y | Y | Apache Avro |
+| `bson` | N | N | Binary JSON; common with MongoDB exports/dumps |
+| `cbor` | N | N | Concise Binary Object Representation |
+| `ion` | N | N | Amazon Ion |
+| `msgpack` | N | N | MessagePack |
+| `pb` | N | N | Protocol Buffers (Google Protobuf) |
+| `pbf` | N | N | Protocolbuffer Binary Format; often for GIS data |
+| `proto` | N | N | Protocol Buffers schema; often in .pb / .bin |
+
+#### Databases and Embedded Storage
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `accdb` | N | N | Microsoft Access (newer format) |
+| `duckdb` | N | N | DuckDB |
+| `mdb` | N | N | Microsoft Access (older format) |
+| `sqlite` | N | N | SQLite |
+
+#### Spreadsheets
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `numbers` | N | N | Apple Numbers |
+| `ods` | N | N | OpenDocument |
+| `wks` | N | N | Lotus 1-2-3  |
+| `xls` | Y | Y | Microsoft Excel (BIFF) |
+| `xlsm` | N | N | Microsoft Excel Macro-Enabled (Open XML) |
+| `xlsx` | Y | Y | Microsoft Excel (Open XML) |
+
+#### Statistical / Scientific / Numeric Computing
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `dta` | N | N | Stata |
+| `hdf5` | N | N | Hierarchical Data Format |
+| `mat` | N | N | MATLAB |
+| `nc` | N | N | NetCDF |
+| `rda` | N | N | RData workspace/object |
+| `rds` | N | N | R data |
+| `sas7bdat` | N | N | SAS data |
+| `sav` | N | N | SPSS data |
+| `sylk` | N | N | Symbolic Link |
+| `xpt` | N | N | SAS Transport |
+| `zsav` | N | N | Compressed SPSS data |
+
+#### Logs and Event Streams
+
+| Format | Supported | Description |
+| --- | --- | --- |
+| `log` | N | N | Generic log file |
+
+#### Data Archives
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `gz` | Y | Y | Gzip-compressed file |
+| `zip` | Y | Y | ZIP archive |
+
+#### Templates
+
+| Format | Read | Write | Description |
+| --- | --- | --- | --- |
+| `hbs` | N | N | Handlebars |
+| `jinja2` | N | N | Jinja2 |
+| `mustache` | N | N | Mustache |
+| `vm` | N | N | Apache Velocity |
+
 ## Usage
 
 ### Command Line Interface

{etlplus-0.12.3 → etlplus-0.13.0}/docs/pipeline-guide.md

@@ -390,10 +390,20 @@ target:
 ```yaml
 jobs:
   - name: file_to_file_customers
+    depends_on: [seed_customers]
     extract: { source: customers_csv }
     validate: { ruleset: customers_basic }
     transform: { pipeline: clean_customers }
     load: { target: customers_json_out }
+  - name: seed_customers
+    extract: { source: seed_customers_csv }
+    load: { target: customers_db_out }
+```
+
+Notes:
+
+- `depends_on` is optional and can be a string or list of job names.
+- Jobs without dependencies run first when ordered as a DAG.
 
 ## Running pipelines (CLI and Python)
 

{etlplus-0.12.3 → etlplus-0.13.0}/etlplus/config/jobs.py

@@ -34,10 +34,7 @@ __all__ = [
 ]
 
 
-# SECTION: TYPE ALIASES ===================================================== #
-
-
-# SECTION: CLASSES ========================================================== #
+# SECTION: DATA CLASSES ===================================================== #
 
 
 @dataclass(kw_only=True, slots=True)
@@ -100,6 +97,8 @@ class JobConfig:
         Unique job name.
     description : str | None
         Optional human-friendly description.
+    depends_on : list[str]
+        Optional job dependency list. Dependencies must refer to other jobs.
     extract : ExtractRef | None
         Extraction reference.
     validate : ValidationRef | None
@@ -114,6 +113,7 @@ class JobConfig:
 
     name: str
     description: str | None = None
+    depends_on: list[str] = field(default_factory=list)
     extract: ExtractRef | None = None
     validate: ValidationRef | None = None
     transform: TransformRef | None = None
@@ -149,9 +149,19 @@ class JobConfig:
         if description is not None and not isinstance(description, str):
             description = str(description)
 
+        depends_raw = data.get('depends_on')
+        depends_on: list[str] = []
+        if isinstance(depends_raw, str):
+            depends_on = [depends_raw]
+        elif isinstance(depends_raw, list):
+            for entry in depends_raw:
+                if isinstance(entry, str):
+                    depends_on.append(entry)
+
         return cls(
             name=name,
             description=description,
+            depends_on=depends_on,
             extract=ExtractRef.from_obj(data.get('extract')),
             validate=ValidationRef.from_obj(data.get('validate')),
             transform=TransformRef.from_obj(data.get('transform')),

etlplus-0.13.0/etlplus/dag.py

@@ -0,0 +1,103 @@
+"""
+:mod:`etlplus.dag` module.
+
+Lightweight directed acyclic graph (DAG) helpers for ordering jobs based on
+``depends_on``.
+"""
+
+from __future__ import annotations
+
+from collections import deque
+from dataclasses import dataclass
+
+from .config.jobs import JobConfig
+
+# SECTION: EXPORTS ========================================================== #
+
+
+__all__ = [
+    'DagError',
+    'topological_sort_jobs',
+]
+
+
+# SECTION: ERRORS =========================================================== #
+
+
+@dataclass(slots=True)
+class DagError(ValueError):
+    """
+    Raised when the job dependency graph is invalid.
+
+    Attributes
+    ----------
+    message : str
+        Error message.
+    """
+
+    # -- Attributes -- #
+
+    message: str
+
+    # -- Magic Methods (Object Representation) -- #
+
+    def __str__(self) -> str:
+        return self.message
+
+
+# SECTION: FUNCTIONS ======================================================== #
+
+
+def topological_sort_jobs(
+    jobs: list[JobConfig],
+) -> list[JobConfig]:
+    """
+    Return jobs in topological order based on ``depends_on``.
+
+    Parameters
+    ----------
+    jobs : list[JobConfig]
+        List of job configurations to sort.
+
+    Returns
+    -------
+    list[JobConfig]
+        Jobs sorted in topological order.
+
+    Raises
+    ------
+    DagError
+        If a dependency is missing, self-referential, or when a cycle is
+        detected.
+    """
+    index = {job.name: job for job in jobs}
+    edges: dict[str, set[str]] = {name: set() for name in index}
+    indegree: dict[str, int] = {name: 0 for name in index}
+
+    for job in jobs:
+        for dep in job.depends_on:
+            if dep not in index:
+                raise DagError(
+                    f'Unknown dependency "{dep}" in job "{job.name}"',
+                )
+            if dep == job.name:
+                raise DagError(f'Job "{job.name}" depends on itself')
+            if job.name not in edges[dep]:
+                edges[dep].add(job.name)
+                indegree[job.name] += 1
+
+    queue = deque(sorted(name for name, deg in indegree.items() if deg == 0))
+    ordered: list[str] = []
+
+    while queue:
+        name = queue.popleft()
+        ordered.append(name)
+        for child in sorted(edges[name]):
+            indegree[child] -= 1
+            if indegree[child] == 0:
+                queue.append(child)
+
+    if len(ordered) != len(jobs):
+        raise DagError('Dependency cycle detected')
+
+    return [index[name] for name in ordered]

etlplus-0.13.0/etlplus/file/_imports.py

@@ -0,0 +1,141 @@
+"""
+:mod:`etlplus.file._imports` module.
+
+Shared helpers for optional dependency imports.
+"""
+
+from __future__ import annotations
+
+from importlib import import_module
+from typing import Any
+
+# SECTION: INTERNAL CONSTANTS =============================================== #
+
+
+_MODULE_CACHE: dict[str, Any] = {}
+
+
+# SECTION: INTERNAL FUNCTIONS =============================================== #
+
+
+def _error_message(
+    module_name: str,
+    format_name: str,
+) -> str:
+    """
+    Build an import error message for an optional dependency.
+
+    Parameters
+    ----------
+    module_name : str
+        Module name to look up.
+    format_name : str
+        Human-readable format name for templated messages.
+
+    Returns
+    -------
+    str
+        Formatted error message.
+    """
+    return (
+        f'{format_name} support requires '
+        f'optional dependency "{module_name}".\n'
+        f'Install with: pip install {module_name}'
+    )
+
+
+# SECTION: FUNCTIONS ======================================================== #
+
+
+def get_optional_module(
+    module_name: str,
+    *,
+    error_message: str,
+) -> Any:
+    """
+    Return an optional dependency module, caching on first import.
+
+    Parameters
+    ----------
+    module_name : str
+        Name of the module to import.
+    error_message : str
+        Error message to surface when the module is missing.
+
+    Returns
+    -------
+    Any
+        The imported module.
+
+    Raises
+    ------
+    ImportError
+        If the optional dependency is missing.
+    """
+    cached = _MODULE_CACHE.get(module_name)
+    if cached is not None:  # pragma: no cover - tiny branch
+        return cached
+    try:
+        module = import_module(module_name)
+    except ImportError as e:  # pragma: no cover
+        raise ImportError(error_message) from e
+    _MODULE_CACHE[module_name] = module
+    return module
+
+
+def get_fastavro() -> Any:
+    """
+    Return the fastavro module, importing it on first use.
+
+    Raises an informative ImportError if the optional dependency is missing.
+
+    Notes
+    -----
+    Prefer :func:`get_optional_module` for new call sites.
+    """
+    return get_optional_module(
+        'fastavro',
+        error_message=_error_message('fastavro', format_name='AVRO'),
+    )
+
+
+def get_pandas(
+    format_name: str,
+) -> Any:
+    """
+    Return the pandas module, importing it on first use.
+
+    Parameters
+    ----------
+    format_name : str
+        Human-readable format name for error messages.
+
+    Returns
+    -------
+    Any
+        The pandas module.
+
+    Notes
+    -----
+    Prefer :func:`get_optional_module` for new call sites.
+    """
+    return get_optional_module(
+        'pandas',
+        error_message=_error_message('pandas', format_name=format_name),
+    )
+
+
+def get_yaml() -> Any:
+    """
+    Return the PyYAML module, importing it on first use.
+
+    Raises an informative ImportError if the optional dependency is missing.
+
+    Notes
+    -----
+    Prefer :func:`get_optional_module` for new call sites.
+    """
+    return get_optional_module(
+        'yaml',
+        error_message=_error_message('PyYAML', format_name='YAML'),
+    )

{etlplus-0.12.3 → etlplus-0.13.0}/etlplus/file/_io.py

@@ -107,6 +107,7 @@ def write_delimited(path: Path, data: JSONData, *, delimiter: str) -> int:
         return 0
 
     fieldnames = sorted({key for row in rows for key in row})
+    path.parent.mkdir(parents=True, exist_ok=True)
     with path.open('w', encoding='utf-8', newline='') as handle:
         writer = csv.DictWriter(
             handle,