normalize-tabular-data 0.1.0__tar.gz

normalize_tabular_data-0.1.0/LICENSE

@@ -0,0 +1,24 @@
+Copyright (c) 2026, Members of Service Employees International Union (SEIU)
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice,
+   this list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.

normalize_tabular_data-0.1.0/PKG-INFO

@@ -0,0 +1,164 @@
+Metadata-Version: 2.4
+Name: normalize-tabular-data
+Version: 0.1.0
+Summary: TUI for normalizing tabular data with polars
+Author: David Mertz, Ph.D.
+Author-email: David Mertz, Ph.D. <mertz@gnosis.cx>
+License-Expression: BSD-2-Clause
+License-File: LICENSE
+Requires-Dist: gnosis-date-parser>=1.0.4
+Requires-Dist: textual>=8.2.8
+Requires-Dist: polars>=1.44,<2
+Requires-Dist: fastexcel>=0.10
+Requires-Dist: xlsxwriter>=0.9
+Requires-Python: >=3.14
+Description-Content-Type: text/markdown
+
+# normalize-tabular-data
+
+A terminal UI (Textual) for interactively normalizing tabular data, backed by
+[polars](https://pola.rs) for speed and
+[gnosis-date-parser](https://pypi.org/project/gnosis-date-parser/) for fuzzy
+date parsing at Rust speed.
+
+Load a file, see a preview, build up a pipeline of normalization operations
+(normalize messy dates, trim whitespace, rename a column, deduplicate,
+combine/split columns, drop columns), then save the
+cleaned result.
+
+## Running
+
+### Persistent install
+
+```bash
+uv tool install normalize-tabular-data
+# upgrade later with:
+uv tool upgrade normalize-tabular-data
+```
+
+### Ephemeral run (no install)
+
+`uvx` fetches into a throwaway environment each time:
+
+```bash
+uvx normalize-tabular-data
+# pin a specific version:
+uvx normalize-tabular-data==0.1.0
+```
+
+### Straight from a checkout
+
+```bash
+uv run normalize-tabular-data
+```
+
+### The TestPyPI sandbox
+
+The test build (uploaded via `make testpypi`) is not on PyPI; point uv
+at TestPyPI first and PyPI as the fallback index — the tool itself is
+found on TestPyPI, its dependencies (`textual`, `polars`, …) on PyPI:
+
+```bash
+uvx \
+  --index-url https://test.pypi.org/simple/ \
+  --extra-index-url https://pypi.org/simple/ \
+  normalize-tabular-data==0.1.0
+
+# or installed persistently:
+uv tool install \
+  --index-url https://test.pypi.org/simple/ \
+  --extra-index-url https://pypi.org/simple/ \
+  normalize-tabular-data==0.1.0
+```
+
+uv caches resolved packages aggressively: after a TestPyPI re-upload of
+the same version, add `--refresh-package normalize-tabular-data` so it
+re-consults the index rather than reusing the cached artifact.
+
+## Usage
+
+Launch with `normalize-tabular-data`. Keys:
+
+| Key | Action                      |
+|-----|-----------------------------|
+| `f` | (F)ile — open a file        |
+| `o` | (O)peration — choose an op  |
+| `p` | (P)lay script — reapply a saved `.ntd` sequence |
+| `u` | (U)ndo last applied step    |
+| `r` | (R)edo                      |
+| `s` | (S)ave the data in a format |
+| `q` | (Q)uit                      |
+
+## Operations
+
+- **Normalize dates** — parse a messy date column of *any* input format into
+  canonical UTC datetimes; unparseable values become null.
+- **Trim whitespace** — strip edges and collapse internal whitespace runs,
+  per selected columns.
+- Rename a column — click its header in the preview and type the new name.
+- **Deduplicate rows** — on all or selected columns, keeping first or last.
+- **Combine columns** — concatenate two or more columns with a separator.
+- **Split column** — break one column into `{col}_1..{col}_k`; a blank
+  delimiter splits on runs of whitespace.
+- **Remove columns** — drop selected columns entirely.
+
+## Formats
+
+Reads: CSV, TSV, JSON lines, Parquet, Excel (`.xlsx`/`.xls` — first sheet).
+Writes: CSV, TSV, JSON lines, Parquet, Excel (`.xlsx`).
+
+Large files are previewed with a random sample of 250 rows; every operation
+still runs on the full data.
+
+## Operation scripts (`.ntd`)
+
+Every open file keeps an internal log of the operations performed on it. When
+saving, the dialog offers a **Save sequence of operations?** checkbox
+(unticked by default); with it ticked, a second dialog asks where to write
+the script — suggested `<table>.ntd`, any other extension you type is kept.
+
+The script is plain ASCII text, one operation per line, e.g.:
+
+```
+# normalize-tabular-data script
+# source: employees.csv
+# table: /data/employees-normalized.csv
+# saved: 2026-10-05T12:30:11
+trim_collapse(columns=["Dept", "Name"])
+date_normalize(column="Hired Date")
+```
+
+## Playing a script back
+
+Press `p` (available while a file is loaded) to pick a script file: the
+dialog previews the highlighted `.ntd` file (syntax-highlighted, first 40
+lines) before you confirm. Its operations are applied, in order, to the table you have open. If any step
+cannot be performed against the currently loaded file — a column it
+renames, trims or splits is missing, the operation is unknown — playing
+stops with an alert naming the failing step, and every step the script had
+already applied is rolled back, so the table is left exactly as it was.
+
+![TUI preview](docs/screenshot.png)
+
+## Publishing
+
+PyPI credentials live in `$HOME/.pypirc` (sections `[pypi]` and
+`[testpypi]`); uploads go through `twine`, which honors that file —
+`uv publish` does not read `.pypirc`, so it is not used here.
+
+```bash
+make dist       # build sdist+wheel into dist/ and run `twine check`
+make testpypi   # upload to the TestPyPI sandbox (login section [testpypi])
+make pypi       # upload to PyPI (login section [pypi])
+twine upload    # equivalent of `make pypi`, minus a fresh build
+```
+
+The targets fail fast if the package metadata does not pass `twine check`,
+and `twine` runs with `--non-interactive` so a missing or wrong
+credential aborts the upload instead of prompting mid-run.
+
+## License
+
+BSD 2-Clause. Copyright (c) 2026, Service Employees International Union (SEIU). 
+
+See [LICENSE](LICENSE).

normalize_tabular_data-0.1.0/README.md

@@ -0,0 +1,148 @@
+# normalize-tabular-data
+
+A terminal UI (Textual) for interactively normalizing tabular data, backed by
+[polars](https://pola.rs) for speed and
+[gnosis-date-parser](https://pypi.org/project/gnosis-date-parser/) for fuzzy
+date parsing at Rust speed.
+
+Load a file, see a preview, build up a pipeline of normalization operations
+(normalize messy dates, trim whitespace, rename a column, deduplicate,
+combine/split columns, drop columns), then save the
+cleaned result.
+
+## Running
+
+### Persistent install
+
+```bash
+uv tool install normalize-tabular-data
+# upgrade later with:
+uv tool upgrade normalize-tabular-data
+```
+
+### Ephemeral run (no install)
+
+`uvx` fetches into a throwaway environment each time:
+
+```bash
+uvx normalize-tabular-data
+# pin a specific version:
+uvx normalize-tabular-data==0.1.0
+```
+
+### Straight from a checkout
+
+```bash
+uv run normalize-tabular-data
+```
+
+### The TestPyPI sandbox
+
+The test build (uploaded via `make testpypi`) is not on PyPI; point uv
+at TestPyPI first and PyPI as the fallback index — the tool itself is
+found on TestPyPI, its dependencies (`textual`, `polars`, …) on PyPI:
+
+```bash
+uvx \
+  --index-url https://test.pypi.org/simple/ \
+  --extra-index-url https://pypi.org/simple/ \
+  normalize-tabular-data==0.1.0
+
+# or installed persistently:
+uv tool install \
+  --index-url https://test.pypi.org/simple/ \
+  --extra-index-url https://pypi.org/simple/ \
+  normalize-tabular-data==0.1.0
+```
+
+uv caches resolved packages aggressively: after a TestPyPI re-upload of
+the same version, add `--refresh-package normalize-tabular-data` so it
+re-consults the index rather than reusing the cached artifact.
+
+## Usage
+
+Launch with `normalize-tabular-data`. Keys:
+
+| Key | Action                      |
+|-----|-----------------------------|
+| `f` | (F)ile — open a file        |
+| `o` | (O)peration — choose an op  |
+| `p` | (P)lay script — reapply a saved `.ntd` sequence |
+| `u` | (U)ndo last applied step    |
+| `r` | (R)edo                      |
+| `s` | (S)ave the data in a format |
+| `q` | (Q)uit                      |
+
+## Operations
+
+- **Normalize dates** — parse a messy date column of *any* input format into
+  canonical UTC datetimes; unparseable values become null.
+- **Trim whitespace** — strip edges and collapse internal whitespace runs,
+  per selected columns.
+- Rename a column — click its header in the preview and type the new name.
+- **Deduplicate rows** — on all or selected columns, keeping first or last.
+- **Combine columns** — concatenate two or more columns with a separator.
+- **Split column** — break one column into `{col}_1..{col}_k`; a blank
+  delimiter splits on runs of whitespace.
+- **Remove columns** — drop selected columns entirely.
+
+## Formats
+
+Reads: CSV, TSV, JSON lines, Parquet, Excel (`.xlsx`/`.xls` — first sheet).
+Writes: CSV, TSV, JSON lines, Parquet, Excel (`.xlsx`).
+
+Large files are previewed with a random sample of 250 rows; every operation
+still runs on the full data.
+
+## Operation scripts (`.ntd`)
+
+Every open file keeps an internal log of the operations performed on it. When
+saving, the dialog offers a **Save sequence of operations?** checkbox
+(unticked by default); with it ticked, a second dialog asks where to write
+the script — suggested `<table>.ntd`, any other extension you type is kept.
+
+The script is plain ASCII text, one operation per line, e.g.:
+
+```
+# normalize-tabular-data script
+# source: employees.csv
+# table: /data/employees-normalized.csv
+# saved: 2026-10-05T12:30:11
+trim_collapse(columns=["Dept", "Name"])
+date_normalize(column="Hired Date")
+```
+
+## Playing a script back
+
+Press `p` (available while a file is loaded) to pick a script file: the
+dialog previews the highlighted `.ntd` file (syntax-highlighted, first 40
+lines) before you confirm. Its operations are applied, in order, to the table you have open. If any step
+cannot be performed against the currently loaded file — a column it
+renames, trims or splits is missing, the operation is unknown — playing
+stops with an alert naming the failing step, and every step the script had
+already applied is rolled back, so the table is left exactly as it was.
+
+![TUI preview](docs/screenshot.png)
+
+## Publishing
+
+PyPI credentials live in `$HOME/.pypirc` (sections `[pypi]` and
+`[testpypi]`); uploads go through `twine`, which honors that file —
+`uv publish` does not read `.pypirc`, so it is not used here.
+
+```bash
+make dist       # build sdist+wheel into dist/ and run `twine check`
+make testpypi   # upload to the TestPyPI sandbox (login section [testpypi])
+make pypi       # upload to PyPI (login section [pypi])
+twine upload    # equivalent of `make pypi`, minus a fresh build
+```
+
+The targets fail fast if the package metadata does not pass `twine check`,
+and `twine` runs with `--non-interactive` so a missing or wrong
+credential aborts the upload instead of prompting mid-run.
+
+## License
+
+BSD 2-Clause. Copyright (c) 2026, Service Employees International Union (SEIU). 
+
+See [LICENSE](LICENSE).

normalize_tabular_data-0.1.0/pyproject.toml

@@ -0,0 +1,34 @@
+[project]
+name = "normalize-tabular-data"
+version = "0.1.0"
+description = "TUI for normalizing tabular data with polars"
+readme = "README.md"
+license = "BSD-2-Clause"
+license-files = ["LICENSE"]
+requires-python = ">=3.14"
+dependencies = [
+    "gnosis-date-parser>=1.0.4",
+    "textual>=8.2.8",
+    "polars>=1.44,<2",
+    "fastexcel>=0.10",
+    "xlsxwriter>=0.9",
+]
+
+[[project.authors]]
+name = "David Mertz, Ph.D."
+email = "mertz@gnosis.cx"
+
+[project.scripts]
+normalize-tabular-data = "normalize_tabular_data:main"
+
+[dependency-groups]
+dev = [
+    "pytest>=8",
+    "pytest-asyncio>=0.25",
+    "ruff>=0.16.10",
+    "twine>=7.0.0",
+]
+
+[build-system]
+requires = ["uv_build>=0.12.3,<0.13.0"]
+build-backend = "uv_build"

normalize_tabular_data-0.1.0/pyproject.toml.orig

@@ -0,0 +1,33 @@
+[project]
+name = "normalize-tabular-data"
+version = "0.1.0"
+description = "TUI for normalizing tabular data with polars"
+readme = "README.md"
+license = "BSD-2-Clause"
+license-files = ["LICENSE"]
+authors = [
+    { name = "David Mertz, Ph.D.", email = "mertz@gnosis.cx" }
+]
+requires-python = ">=3.14"
+dependencies = [
+    "gnosis-date-parser>=1.0.4",
+    "textual>=8.2.8",
+    "polars>=1.44,<2",
+    "fastexcel>=0.10",
+    "xlsxwriter>=0.9",
+]
+
+[dependency-groups]
+dev = [
+    "pytest>=8",
+    "pytest-asyncio>=0.25",
+    "ruff>=0.16.10",
+    "twine>=7.0.0",
+]
+
+[project.scripts]
+normalize-tabular-data = "normalize_tabular_data:main"
+
+[build-system]
+requires = ["uv_build>=0.12.3,<0.13.0"]
+build-backend = "uv_build"

normalize_tabular_data-0.1.0/src/normalize_tabular_data/__init__.py

@@ -0,0 +1,18 @@
+"""normalize-tabular-data: TUI for normalizing tabular data with polars."""
+
+__version__ = "0.1.0"
+
+
+def main() -> None:
+    try:
+        from normalize_tabular_data.app import NormalizeApp
+    except ImportError as exc:  # helpful message if an optional engine is missing
+        import sys
+
+        print(
+            f"normalize-tabular-data is missing a dependency ({exc}).\n"
+            "Reinstall with: uv tool install --force --reinstall normalize-tabular-data",
+            file=sys.stderr,
+        )
+        raise SystemExit(1)
+    NormalizeApp().run()

normalize_tabular_data-0.1.0/src/normalize_tabular_data/__main__.py

@@ -0,0 +1,4 @@
+from normalize_tabular_data import main
+
+if __name__ == "__main__":
+    main()