dtypeflow 1.0.0__tar.gz → 1.2.0__tar.gz

{dtypeflow-1.0.0 → dtypeflow-1.2.0}/LICENSE

@@ -1,21 +1,21 @@
-MIT License
-
-Copyright (c) 2026 Pedro José Mora Gallegos
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+MIT License
+
+Copyright (c) 2026 Pedro José Mora Gallegos
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

{dtypeflow-1.0.0 → dtypeflow-1.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dtypeflow
-Version: 1.0.0
+Version: 1.2.0
 Summary: Terminal UI to infer CSV column dtypes and convert CSV to Parquet, locally.
 Keywords: csv,parquet,dtype,tui,textual,arrow
 Author: Pedro José Mora Gallegos
@@ -23,71 +23,86 @@ Project-URL: Repository, https://github.com/pedrojosemoragallegos/dtypeflow
 Project-URL: Issues, https://github.com/pedrojosemoragallegos/dtypeflow/issues
 Description-Content-Type: text/markdown
 
-# dtypeflow
-
-`dtypeflow` is a terminal UI to convert a CSV file to Parquet.
-
-Point it at a CSV file, and for each column it infers the tightest-fitting
-dtype (`Boolean`, unsigned/signed integers `UInt8`…`UInt64`/`Int8`…`Int64`,
-floats `Float16`/`Float32`/`Float64`, `String`, or `Dictionary`), shows the
-observed statistics, and lets you review or override the choice before
-writing the result to Parquet — all locally, no data leaves your machine.
-
-## Installation
-
-```bash
-uv tool install dtypeflow
-```
-
-Or with `pipx`:
-
-```bash
-pipx install dtypeflow
-```
-
-Or with `pip`:
-
-```bash
-pip install dtypeflow
-```
-
-## Usage
-
-Launch the picker and choose a CSV file interactively:
-
-```bash
-dtypeflow
-```
-
-Or pass a path directly to skip straight to configuring column types:
-
-```bash
-dtypeflow path/to/data.csv
-```
-
-The workflow has three steps:
-
-1. **Pick a file** — enter or browse for a CSV path.
-2. **Configure types** — for each column, review the recommended dtype, its
-   stats (unique values, samples, range/precision/scale), and pick from
-   compatible alternatives grouped by safety (Safe / Too small / Discouraged).
-3. **Export** — write the configured dataset to a Parquet file.
-
-## Development
-
-This project uses [uv](https://docs.astral.sh/uv/) for dependency management.
-
-```bash
-uv sync
-uv run dtypeflow
-```
-
-Lint:
-
-```bash
-uv run --with ruff ruff check src/
-```
-
-## License
-
-[MIT](LICENSE)
+# dtypeflow
+
+[![PyPI version](https://img.shields.io/pypi/v/dtypeflow)](https://pypi.org/project/dtypeflow/)
+[![Python Versions](https://img.shields.io/pypi/pyversions/dtypeflow)](https://pypi.org/project/dtypeflow/)
+[![Downloads](https://pepy.tech/badge/dtypeflow)](https://pepy.tech/project/dtypeflow)
+[![Wheel](https://img.shields.io/pypi/wheel/dtypeflow)](https://pypi.org/project/dtypeflow/)
+
+`dtypeflow` is a terminal UI to convert a CSV file to Parquet.
+
+Point it at a CSV file, and for each column it infers the tightest-fitting
+dtype (`Boolean`, unsigned/signed integers `UInt8`…`UInt64`/`Int8`…`Int64`,
+floats `Float16`/`Float32`/`Float64`, `String`, or `Dictionary`), shows the
+observed statistics, and lets you review or override the choice before
+writing the result to Parquet — all locally, no data leaves your machine.
+
+## Installation
+
+```bash
+uv tool install dtypeflow
+```
+
+Or with `pipx`:
+
+```bash
+pipx install dtypeflow
+```
+
+Or with `pip`:
+
+```bash
+pip install dtypeflow
+```
+
+## Usage
+
+```bash
+dtypeflow
+```
+
+The workflow has three steps:
+
+1. **Pick a file** — enter or browse for a CSV path and choose the delimiter
+   (Comma by default; Auto detects it from the first 64 KiB).
+2. **Configure types** — for each column, review the recommended dtype, its
+   stats (unique values, samples, range/precision/scale), and pick from
+   compatible alternatives grouped by safety (Safe / Too small / Discouraged).
+3. **Export** — write the configured dataset to a Parquet file.
+
+### Screenshots
+
+Alternatives for a column are grouped by how safe they are to apply:
+
+<table>
+<tr>
+<td align="center"><b>Safe</b></td>
+<td align="center"><b>Too small</b></td>
+<td align="center"><b>Discouraged</b></td>
+</tr>
+<tr>
+<td><img src="screenshots/26_warehouse_stock_safe.svg" alt="Safe dtype options for warehouse_stock" width="280"></td>
+<td><img src="screenshots/26_warehouse_stock_too_small.svg" alt="Too small dtype options for warehouse_stock" width="280"></td>
+<td><img src="screenshots/26_warehouse_stock_discouraged.svg" alt="Discouraged dtype options for warehouse_stock" width="280"></td>
+</tr>
+</table>
+
+## Development
+
+This project uses [uv](https://docs.astral.sh/uv/) for dependency management.
+
+```bash
+uv sync
+uv run dtypeflow
+```
+
+Lint:
+
+```bash
+uv run --with ruff ruff check src/
+```
+
+## License
+
+[MIT](LICENSE)

dtypeflow-1.2.0/README.md

@@ -0,0 +1,83 @@
+# dtypeflow
+
+[![PyPI version](https://img.shields.io/pypi/v/dtypeflow)](https://pypi.org/project/dtypeflow/)
+[![Python Versions](https://img.shields.io/pypi/pyversions/dtypeflow)](https://pypi.org/project/dtypeflow/)
+[![Downloads](https://pepy.tech/badge/dtypeflow)](https://pepy.tech/project/dtypeflow)
+[![Wheel](https://img.shields.io/pypi/wheel/dtypeflow)](https://pypi.org/project/dtypeflow/)
+
+`dtypeflow` is a terminal UI to convert a CSV file to Parquet.
+
+Point it at a CSV file, and for each column it infers the tightest-fitting
+dtype (`Boolean`, unsigned/signed integers `UInt8`…`UInt64`/`Int8`…`Int64`,
+floats `Float16`/`Float32`/`Float64`, `String`, or `Dictionary`), shows the
+observed statistics, and lets you review or override the choice before
+writing the result to Parquet — all locally, no data leaves your machine.
+
+## Installation
+
+```bash
+uv tool install dtypeflow
+```
+
+Or with `pipx`:
+
+```bash
+pipx install dtypeflow
+```
+
+Or with `pip`:
+
+```bash
+pip install dtypeflow
+```
+
+## Usage
+
+```bash
+dtypeflow
+```
+
+The workflow has three steps:
+
+1. **Pick a file** — enter or browse for a CSV path and choose the delimiter
+   (Comma by default; Auto detects it from the first 64 KiB).
+2. **Configure types** — for each column, review the recommended dtype, its
+   stats (unique values, samples, range/precision/scale), and pick from
+   compatible alternatives grouped by safety (Safe / Too small / Discouraged).
+3. **Export** — write the configured dataset to a Parquet file.
+
+### Screenshots
+
+Alternatives for a column are grouped by how safe they are to apply:
+
+<table>
+<tr>
+<td align="center"><b>Safe</b></td>
+<td align="center"><b>Too small</b></td>
+<td align="center"><b>Discouraged</b></td>
+</tr>
+<tr>
+<td><img src="screenshots/26_warehouse_stock_safe.svg" alt="Safe dtype options for warehouse_stock" width="280"></td>
+<td><img src="screenshots/26_warehouse_stock_too_small.svg" alt="Too small dtype options for warehouse_stock" width="280"></td>
+<td><img src="screenshots/26_warehouse_stock_discouraged.svg" alt="Discouraged dtype options for warehouse_stock" width="280"></td>
+</tr>
+</table>
+
+## Development
+
+This project uses [uv](https://docs.astral.sh/uv/) for dependency management.
+
+```bash
+uv sync
+uv run dtypeflow
+```
+
+Lint:
+
+```bash
+uv run --with ruff ruff check src/
+```
+
+## License
+
+[MIT](LICENSE)

{dtypeflow-1.0.0 → dtypeflow-1.2.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dtypeflow"
-version = "1.0.0"
+version = "1.2.0"
 description = "Terminal UI to infer CSV column dtypes and convert CSV to Parquet, locally."
 readme = "README.md"
 license = "MIT"

{dtypeflow-1.0.0 → dtypeflow-1.2.0}/pyproject.toml.orig

@@ -1,6 +1,6 @@
 [project]
 name = "dtypeflow"
-version = "1.0.0"
+version = "1.2.0"
 description = "Terminal UI to infer CSV column dtypes and convert CSV to Parquet, locally."
 readme = "README.md"
 license = "MIT"

{dtypeflow-1.0.0 → dtypeflow-1.2.0}/src/dtypeflow/__init__.py

@@ -1,5 +1,5 @@
-from __future__ import annotations
-
-from dtypeflow.core.profiler import profile
-
-__all__: list[str] = ["profile"]
+from __future__ import annotations
+
+from dtypeflow.core.profiler import profile
+
+__all__: list[str] = ["profile"]

{dtypeflow-1.0.0 → dtypeflow-1.2.0}/src/dtypeflow/core/__init__.py

@@ -1 +1 @@
-from __future__ import annotations
+from __future__ import annotations

{dtypeflow-1.0.0 → dtypeflow-1.2.0}/src/dtypeflow/core/candidate/__init__.py

@@ -1,40 +1,40 @@
-from __future__ import annotations
-
-from .base import Candidate, Compatibility
-from .factory import candidate_factory
-from .primitive import (
-    Boolean as BooleanCandidate,
-    Dictionary as DictionaryCandidate,
-    Float16 as Float16Candidate,
-    Float32 as Float32Candidate,
-    Float64 as Float64Candidate,
-    Int8 as Int8Candidate,
-    Int16 as Int16Candidate,
-    Int32 as Int32Candidate,
-    Int64 as Int64Candidate,
-    String as StringCandidate,
-    UInt8 as UInt8Candidate,
-    UInt16 as UInt16Candidate,
-    UInt32 as UInt32Candidate,
-    UInt64 as UInt64Candidate,
-)
-
-__all__: list[str] = [
-    "BooleanCandidate",
-    "Candidate",
-    "Compatibility",
-    "DictionaryCandidate",
-    "Float16Candidate",
-    "Float32Candidate",
-    "Float64Candidate",
-    "Int8Candidate",
-    "Int16Candidate",
-    "Int32Candidate",
-    "Int64Candidate",
-    "StringCandidate",
-    "UInt8Candidate",
-    "UInt16Candidate",
-    "UInt32Candidate",
-    "UInt64Candidate",
-    "candidate_factory",
-]
+from __future__ import annotations
+
+from .base import Candidate, Compatibility
+from .factory import candidate_factory
+from .primitive import (
+    Boolean as BooleanCandidate,
+    Dictionary as DictionaryCandidate,
+    Float16 as Float16Candidate,
+    Float32 as Float32Candidate,
+    Float64 as Float64Candidate,
+    Int8 as Int8Candidate,
+    Int16 as Int16Candidate,
+    Int32 as Int32Candidate,
+    Int64 as Int64Candidate,
+    String as StringCandidate,
+    UInt8 as UInt8Candidate,
+    UInt16 as UInt16Candidate,
+    UInt32 as UInt32Candidate,
+    UInt64 as UInt64Candidate,
+)
+
+__all__: list[str] = [
+    "BooleanCandidate",
+    "Candidate",
+    "Compatibility",
+    "DictionaryCandidate",
+    "Float16Candidate",
+    "Float32Candidate",
+    "Float64Candidate",
+    "Int8Candidate",
+    "Int16Candidate",
+    "Int32Candidate",
+    "Int64Candidate",
+    "StringCandidate",
+    "UInt8Candidate",
+    "UInt16Candidate",
+    "UInt32Candidate",
+    "UInt64Candidate",
+    "candidate_factory",
+]

{dtypeflow-1.0.0 → dtypeflow-1.2.0}/src/dtypeflow/core/candidate/base.py

@@ -1,37 +1,37 @@
-from __future__ import annotations
-
-from abc import ABC
-from enum import Enum, auto
-from typing import TYPE_CHECKING, ClassVar
-
-if TYPE_CHECKING:
-    from dtypeflow.core.dtype import Dtype
-
-
-class Compatibility(Enum):
-    FULL_RANGE_FIT = auto()
-    VALUES_PRESERVED = auto()
-    VALUES_NO_FIT = auto()
-    RANGE_NO_FIT = auto()
-    UNEVALUATED_NO_FIT = auto()
-    NOT_NUMERIC = auto()
-    OBSERVED_ONLY_FIT = auto()
-    DECIMAL_TRUNCATION = auto()
-    PRECISION_REDUCTION = auto()
-    BOOLEAN_MAPPING = auto()
-    DICTIONARY_ENCODING = auto()
-    DICTIONARY_INEFFICIENT = auto()
-
-
-class Candidate(ABC):
-    DTYPE: ClassVar[type[Dtype]]
-
-    def __init__(self, compatibility: Compatibility, /) -> None:
-        self._compatibility: Compatibility = compatibility
-
-    @property
-    def compatibility(self) -> Compatibility:
-        return self._compatibility
-
-    def __repr__(self) -> str:
-        return f"{type(self).__name__}(compatibility={self._compatibility.name})"
+from __future__ import annotations
+
+from abc import ABC
+from enum import Enum, auto
+from typing import TYPE_CHECKING, ClassVar
+
+if TYPE_CHECKING:
+    from dtypeflow.core.dtype import Dtype
+
+
+class Compatibility(Enum):
+    FULL_RANGE_FIT = auto()
+    VALUES_PRESERVED = auto()
+    VALUES_NO_FIT = auto()
+    RANGE_NO_FIT = auto()
+    UNEVALUATED_NO_FIT = auto()
+    NOT_NUMERIC = auto()
+    OBSERVED_ONLY_FIT = auto()
+    DECIMAL_TRUNCATION = auto()
+    PRECISION_REDUCTION = auto()
+    BOOLEAN_MAPPING = auto()
+    DICTIONARY_ENCODING = auto()
+    DICTIONARY_INEFFICIENT = auto()
+
+
+class Candidate(ABC):
+    DTYPE: ClassVar[type[Dtype]]
+
+    def __init__(self, compatibility: Compatibility, /) -> None:
+        self._compatibility: Compatibility = compatibility
+
+    @property
+    def compatibility(self) -> Compatibility:
+        return self._compatibility
+
+    def __repr__(self) -> str:
+        return f"{type(self).__name__}(compatibility={self._compatibility.name})"