etlplus 0.16.10__tar.gz → 0.17.3__tar.gz

{etlplus-0.16.10 → etlplus-0.17.3}/.github/workflows/ci.yml

@@ -62,7 +62,11 @@ jobs:
         run: |
           ruff version
           ruff check .
-          ruff format --check .
+          # ruff format --check .
+          files="$(git ls-files '*.py')"
+          if [ -n "$files" ]; then
+            autopep8 --diff --exit-code --max-line-length=79 $files
+          fi
 
   test:
     runs-on: ubuntu-latest

{etlplus-0.16.10 → etlplus-0.17.3}/.ruff.toml

@@ -19,6 +19,10 @@ select = [
   "I",   # isort
   "UP",  # pyupgrade
 ]
+preview = true
+extend-select = [
+  "E203",  # Enforce autopep8 slice spacing (no space before ':')
+]
 ignore = [
   # Allow module-level variable use for caches/helpers, if needed
 ]

{etlplus-0.16.10 → etlplus-0.17.3}/Makefile

@@ -172,6 +172,11 @@ dist: ## Build sdist and wheel into ./dist using pyproject.toml
 	@$(PYTHON) -m twine check dist/*
 	@$(call ECHO_OK,"Built and validated distribution artifacts in ./dist")
 
+.PHONY: file
+file: venv ## Install package + file extras
+	@$(PYTHON) -m pip install -e $(PKG_DIR)[file]
+	@$(call ECHO_OK,"Installed etlplus + file extras")
+
 .PHONY: fix
 fix: ## Auto-fix with ruff
 	@$(VENV_BIN)/ruff check . --fix || (echo "Hint: run 'make dev' first" && false)
@@ -211,8 +216,11 @@ doclint: ## Run docstring linters (pydocstyle + pydoclint if available)
 .PHONY: fmt
 fmt: ## Format code with ruff (imports + fixes) and black
 	@$(VENV_BIN)/ruff check . --fix || (echo "Hint: run 'make dev' first" && false)
-	@$(VENV_BIN)/ruff format . || true
-	@$(VENV_BIN)/black . || true
+# 	@$(VENV_BIN)/ruff format . || true
+# 	@$(VENV_BIN)/black . || true
+	@$(VENV_BIN)/autopep8 --in-place --max-line-length=79 \
+	  --exclude .venv,dist,build,etlplus.egg-info,.mypy_cache,.pytest_cache \
+	  $(shell git ls-files '*.py') || true
 
 .PHONY: run
 run: ## Run the etlplus CLI (dry-run) using $(ENV)

{etlplus-0.16.10/etlplus.egg-info → etlplus-0.17.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: etlplus
-Version: 0.16.10
+Version: 0.17.3
 Summary: A Swiss Army knife for simple ETL operations
 Home-page: https://github.com/Dagitali/ETLPlus
 Author: ETLPlus Team
@@ -32,6 +32,7 @@ Requires-Dist: typer>=0.21.0
 Requires-Dist: xlrd>=2.0.2
 Requires-Dist: xlwt>=1.3.0
 Provides-Extra: dev
+Requires-Dist: autopep8>=2.3.2; extra == "dev"
 Requires-Dist: black>=25.9.0; extra == "dev"
 Requires-Dist: build>=1.2.2; extra == "dev"
 Requires-Dist: flake8>=7.3.0; extra == "dev"
@@ -44,6 +45,17 @@ Requires-Dist: ruff>=0.14.4; extra == "dev"
 Provides-Extra: docs
 Requires-Dist: sphinx>=4.0.0; extra == "docs"
 Requires-Dist: sphinx-rtd-theme>=1.0.0; extra == "docs"
+Provides-Extra: file
+Requires-Dist: pymongo>=4.9.1; extra == "file"
+Requires-Dist: cbor2>=5.6.4; extra == "file"
+Requires-Dist: duckdb>=1.1.0; extra == "file"
+Requires-Dist: msgpack>=1.0.8; extra == "file"
+Requires-Dist: netCDF4>=1.7.2; extra == "file"
+Requires-Dist: odfpy>=1.4.1; extra == "file"
+Requires-Dist: pyreadr>=0.5.2; extra == "file"
+Requires-Dist: pyreadstat>=1.3.3; extra == "file"
+Requires-Dist: tomli-w>=1.2.0; extra == "file"
+Requires-Dist: xarray>=2024.9.0; extra == "file"
 Dynamic: home-page
 Dynamic: license-file
 Dynamic: requires-python
@@ -176,6 +188,12 @@ For development:
 pip install -e ".[dev]"
 ```
 
+For full file-format support (optional extras):
+
+```bash
+pip install -e ".[file]"
+```
+
 ## Quickstart
 
 Get up and running in under a minute.
@@ -240,10 +258,10 @@ Recognized file formats are listed in the tables below. Support for reading to o
 | 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 |
+| `dat` | Y | Y | Generic data file, often delimited or fixed-width |
+| `fwf` | Y | Y | Fixed-Width Fields |
+| `psv` | Y | Y | Pipe-Separated Values |
+| `tab` | Y | Y | Often synonymous with TSV |
 | `tsv` | Y | Y | Tab-Separated Values |
 | `txt` | Y | Y | Plain text, often delimited or fixed-width |
 
@@ -253,11 +271,11 @@ Recognized file formats are listed in the tables below. Support for reading to o
 | --- | --- | --- | --- |
 | `cfg` | N | N | Config-style key-value pairs |
 | `conf` | N | N | Config-style key-value pairs |
-| `ini` | N | N | Config-style key-value pairs |
+| `ini` | Y | Y | 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 |
+| `properties` | Y | Y | Java-style key-value pairs |
+| `toml` | Y | Y | Tom's Obvious Minimal Language |
 | `xml` | Y | Y | Extensible Markup Language |
 | `yaml` | Y | Y | YAML Ain't Markup Language |
 
@@ -265,7 +283,7 @@ Recognized file formats are listed in the tables below. Support for reading to o
 
 | Format | Read | Write | Description |
 | --- | --- | --- | --- |
-| `arrow` | N | N | Apache Arrow IPC |
+| `arrow` | Y | Y | 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 |
@@ -275,48 +293,48 @@ Recognized file formats are listed in the tables below. Support for reading to o
 | 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 |
+| `bson` | Y | Y | Binary JSON; common with MongoDB exports/dumps |
+| `cbor` | Y | Y | Concise Binary Object Representation |
 | `ion` | N | N | Amazon Ion |
-| `msgpack` | N | N | MessagePack |
-| `pb` | N | N | Protocol Buffers (Google Protobuf) |
+| `msgpack` | Y | Y | MessagePack |
+| `pb` | Y | Y | Protocol Buffers (Google Protobuf) |
 | `pbf` | N | N | Protocolbuffer Binary Format; often for GIS data |
-| `proto` | N | N | Protocol Buffers schema; often in .pb / .bin |
+| `proto` | Y | Y | 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 |
+| `duckdb` | Y | Y | DuckDB |
 | `mdb` | N | N | Microsoft Access (older format) |
-| `sqlite` | N | N | SQLite |
+| `sqlite` | Y | Y | SQLite |
 
 #### Spreadsheets
 
 | Format | Read | Write | Description |
 | --- | --- | --- | --- |
 | `numbers` | N | N | Apple Numbers |
-| `ods` | N | N | OpenDocument |
+| `ods` | Y | Y | OpenDocument |
 | `wks` | N | N | Lotus 1-2-3  |
 | `xls` | Y | N | Microsoft Excel (BIFF; read-only) |
-| `xlsm` | N | N | Microsoft Excel Macro-Enabled (Open XML) |
+| `xlsm` | Y | Y | 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 |
+| `dta` | Y | Y | Stata |
+| `hdf5` | Y | 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 |
+| `nc` | Y | Y | NetCDF |
+| `rda` | Y | Y | RData workspace/object |
+| `rds` | Y | Y | R data |
+| `sas7bdat` | Y | N | SAS data |
+| `sav` | Y | Y | SPSS data |
 | `sylk` | N | N | Symbolic Link |
-| `xpt` | N | N | SAS Transport |
+| `xpt` | Y | Y | SAS Transport |
 | `zsav` | N | N | Compressed SPSS data |
 
 #### Logs and Event Streams

{etlplus-0.16.10 → etlplus-0.17.3}/README.md

@@ -126,6 +126,12 @@ For development:
 pip install -e ".[dev]"
 ```
 
+For full file-format support (optional extras):
+
+```bash
+pip install -e ".[file]"
+```
+
 ## Quickstart
 
 Get up and running in under a minute.
@@ -190,10 +196,10 @@ Recognized file formats are listed in the tables below. Support for reading to o
 | 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 |
+| `dat` | Y | Y | Generic data file, often delimited or fixed-width |
+| `fwf` | Y | Y | Fixed-Width Fields |
+| `psv` | Y | Y | Pipe-Separated Values |
+| `tab` | Y | Y | Often synonymous with TSV |
 | `tsv` | Y | Y | Tab-Separated Values |
 | `txt` | Y | Y | Plain text, often delimited or fixed-width |
 
@@ -203,11 +209,11 @@ Recognized file formats are listed in the tables below. Support for reading to o
 | --- | --- | --- | --- |
 | `cfg` | N | N | Config-style key-value pairs |
 | `conf` | N | N | Config-style key-value pairs |
-| `ini` | N | N | Config-style key-value pairs |
+| `ini` | Y | Y | 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 |
+| `properties` | Y | Y | Java-style key-value pairs |
+| `toml` | Y | Y | Tom's Obvious Minimal Language |
 | `xml` | Y | Y | Extensible Markup Language |
 | `yaml` | Y | Y | YAML Ain't Markup Language |
 
@@ -215,7 +221,7 @@ Recognized file formats are listed in the tables below. Support for reading to o
 
 | Format | Read | Write | Description |
 | --- | --- | --- | --- |
-| `arrow` | N | N | Apache Arrow IPC |
+| `arrow` | Y | Y | 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 |
@@ -225,48 +231,48 @@ Recognized file formats are listed in the tables below. Support for reading to o
 | 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 |
+| `bson` | Y | Y | Binary JSON; common with MongoDB exports/dumps |
+| `cbor` | Y | Y | Concise Binary Object Representation |
 | `ion` | N | N | Amazon Ion |
-| `msgpack` | N | N | MessagePack |
-| `pb` | N | N | Protocol Buffers (Google Protobuf) |
+| `msgpack` | Y | Y | MessagePack |
+| `pb` | Y | Y | Protocol Buffers (Google Protobuf) |
 | `pbf` | N | N | Protocolbuffer Binary Format; often for GIS data |
-| `proto` | N | N | Protocol Buffers schema; often in .pb / .bin |
+| `proto` | Y | Y | 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 |
+| `duckdb` | Y | Y | DuckDB |
 | `mdb` | N | N | Microsoft Access (older format) |
-| `sqlite` | N | N | SQLite |
+| `sqlite` | Y | Y | SQLite |
 
 #### Spreadsheets
 
 | Format | Read | Write | Description |
 | --- | --- | --- | --- |
 | `numbers` | N | N | Apple Numbers |
-| `ods` | N | N | OpenDocument |
+| `ods` | Y | Y | OpenDocument |
 | `wks` | N | N | Lotus 1-2-3  |
 | `xls` | Y | N | Microsoft Excel (BIFF; read-only) |
-| `xlsm` | N | N | Microsoft Excel Macro-Enabled (Open XML) |
+| `xlsm` | Y | Y | 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 |
+| `dta` | Y | Y | Stata |
+| `hdf5` | Y | 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 |
+| `nc` | Y | Y | NetCDF |
+| `rda` | Y | Y | RData workspace/object |
+| `rds` | Y | Y | R data |
+| `sas7bdat` | Y | N | SAS data |
+| `sav` | Y | Y | SPSS data |
 | `sylk` | N | N | Symbolic Link |
-| `xpt` | N | N | SAS Transport |
+| `xpt` | Y | Y | SAS Transport |
 | `zsav` | N | N | Compressed SPSS data |
 
 #### Logs and Event Streams

{etlplus-0.16.10 → etlplus-0.17.3}/etlplus/file/README.md

@@ -9,6 +9,12 @@ and writing data files.
   types
 - Exposes a `File` class with instance methods for reading and writing data
 
+Some formats require optional dependencies. Install with:
+
+```bash
+pip install -e ".[file]"
+```
+
 Back to project overview: see the top-level [README](../../README.md).
 
 - [`etlplus.file` Subpackage](#etlplusfile-subpackage)
@@ -29,21 +35,48 @@ matrix across all `FileFormat` values, see the top-level [README](../../README.m
 | Format    | Description                                 |
 |-----------|---------------------------------------------|
 | avro      | Apache Avro binary serialization            |
+| arrow     | Apache Arrow IPC                            |
+| bson      | Binary JSON (BSON)                          |
+| cbor      | Concise Binary Object Representation        |
 | csv       | Comma-separated values text files           |
+| dat       | Generic data files (delimited)              |
+| dta       | Stata datasets                              |
+| duckdb    | DuckDB database file                        |
 | feather   | Apache Arrow Feather columnar format        |
+| fwf       | Fixed-width formatted text files            |
 | gz        | Gzip-compressed files (see Compression)     |
+| hdf5      | Hierarchical Data Format                    |
+| ini       | INI config files                            |
 | json      | Standard JSON files                         |
+| msgpack   | MessagePack binary serialization            |
+| nc        | NetCDF datasets                             |
 | ndjson    | Newline-delimited JSON (JSON Lines)         |
+| ods       | OpenDocument spreadsheets                   |
 | orc       | Apache ORC columnar format                  |
 | parquet   | Apache Parquet columnar format              |
+| pb        | Protocol Buffers binary                     |
+| properties | Java-style properties                     |
+| proto     | Protocol Buffers schema                     |
+| psv       | Pipe-separated values text files            |
+| rda       | RData workspace bundles                     |
+| rds       | RDS datasets                                |
+| sas7bdat  | SAS datasets                                |
+| sav       | SPSS datasets                               |
+| sqlite    | SQLite database file                        |
+| tab       | Tab-delimited text files                    |
+| toml      | TOML config files                           |
 | tsv       | Tab-separated values text files             |
 | txt       | Plain text files                            |
 | xls       | Microsoft Excel (legacy .xls; read-only)    |
+| xlsm      | Microsoft Excel Macro-Enabled (XLSM)        |
 | xlsx      | Microsoft Excel (modern .xlsx)              |
+| xpt       | SAS transport files                         |
 | zip       | ZIP-compressed files (see Compression)      |
 | xml       | XML files                                   |
 | yaml      | YAML files                                  |
 
+Note: HDF5 support is read-only; writing is currently disabled.
+
 Compression formats (gz, zip) are also supported as wrappers for other formats. Formats not listed
 here are currently stubbed and will raise `NotImplementedError` on read/write.
 

{etlplus-0.16.10 → etlplus-0.17.3}/etlplus/file/_imports.py

@@ -22,6 +22,7 @@ _MODULE_CACHE: dict[str, Any] = {}
 def _error_message(
     module_name: str,
     format_name: str,
+    pip_name: str | None = None,
 ) -> str:
     """
     Build an import error message for an optional dependency.
@@ -32,16 +33,19 @@ def _error_message(
         Module name to look up.
     format_name : str
         Human-readable format name for templated messages.
+    pip_name : str | None, optional
+        Package name to suggest for installation. Defaults to *module_name*.
 
     Returns
     -------
     str
         Formatted error message.
     """
+    install_name = pip_name or module_name
     return (
         f'{format_name} support requires '
-        f'optional dependency "{module_name}".\n'
-        f'Install with: pip install {module_name}'
+        f'optional dependency "{install_name}".\n'
+        f'Install with: pip install {install_name}'
     )
 
 
@@ -84,19 +88,36 @@ def get_optional_module(
     return module
 
 
-def get_fastavro() -> Any:
+def get_dependency(
+    module_name: str,
+    *,
+    format_name: str,
+    pip_name: str | None = None,
+) -> Any:
     """
-    Return the fastavro module, importing it on first use.
+    Return an optional dependency module with a standardized error message.
 
-    Raises an informative ImportError if the optional dependency is missing.
+    Parameters
+    ----------
+    module_name : str
+        Name of the module to import.
+    format_name : str
+        Human-readable format name for error messages.
+    pip_name : str | None, optional
+        Package name to suggest for installation (defaults to *module_name*).
 
-    Notes
-    -----
-    Prefer :func:`get_optional_module` for new call sites.
+    Returns
+    -------
+    Any
+        The imported module.
     """
     return get_optional_module(
-        'fastavro',
-        error_message=_error_message('fastavro', format_name='AVRO'),
+        module_name,
+        error_message=_error_message(
+            module_name,
+            format_name=format_name,
+            pip_name=pip_name,
+        ),
     )
 
 
@@ -118,12 +139,9 @@ def get_pandas(
 
     Notes
     -----
-    Prefer :func:`get_optional_module` for new call sites.
+    Prefer :func:`get_dependency` for new call sites.
     """
-    return get_optional_module(
-        'pandas',
-        error_message=_error_message('pandas', format_name=format_name),
-    )
+    return get_dependency('pandas', format_name=format_name)
 
 
 def get_yaml() -> Any:
@@ -134,9 +152,6 @@ def get_yaml() -> Any:
 
     Notes
     -----
-    Prefer :func:`get_optional_module` for new call sites.
+    Prefer :func:`get_dependency` for new call sites.
     """
-    return get_optional_module(
-        'yaml',
-        error_message=_error_message('PyYAML', format_name='YAML'),
-    )
+    return get_dependency('yaml', format_name='YAML', pip_name='PyYAML')