normalize-tabular-data 0.1.3__tar.gz → 0.1.5__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (12) hide show
  1. {normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/PKG-INFO +52 -69
  2. {normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/README.md +51 -68
  3. {normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/pyproject.toml +1 -1
  4. {normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/pyproject.toml.orig +1 -1
  5. {normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/src/normalize_tabular_data/__init__.py +4 -3
  6. {normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/src/normalize_tabular_data/io.py +1 -1
  7. {normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/src/normalize_tabular_data/ops.py +1 -1
  8. {normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/LICENSE +0 -0
  9. {normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/src/normalize_tabular_data/__main__.py +0 -0
  10. {normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/src/normalize_tabular_data/app.py +0 -0
  11. {normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/src/normalize_tabular_data/screens.py +0 -0
  12. {normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/src/normalize_tabular_data/widgets.py +0 -0
{normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: normalize-tabular-data
3
- Version: 0.1.3
3
+ Version: 0.1.5
4
4
  Summary: TUI for normalizing tabular data with Polars
5
5
  Author: David Mertz, Ph.D.
6
6
  Author-email: David Mertz, Ph.D. <mertz@gnosis.cx>
@@ -15,55 +15,79 @@ Requires-Dist: platformdirs>=3.0
15
15
  Requires-Python: >=3.14
16
16
  Description-Content-Type: text/markdown
17
17
 
18
- # normalize-tabular-data
18
+ # normalize-tabular-data (NTD)
19
19
 
20
20
  A terminal UI (Textual) for interactively normalizing tabular data, backed by
21
21
  [polars](https://pola.rs) for speed and
22
22
  [gnosis-date-parser](https://pypi.org/project/gnosis-date-parser/) for fuzzy
23
- date parsing at Rust speed.
23
+ date parsing at Rust speed. NTD also supports purely command-line operations
24
+ for use in scripting.
25
+
26
+ **Quick start**: `uvx normalize-tabular-data`. No installation required if
27
+ you have `uv`.
24
28
 
25
29
  Load a file, see a preview, build up a pipeline of normalization operations
26
30
  (normalize messy dates, trim whitespace, rename a column, deduplicate,
27
- combine/split columns, drop columns), then save the
28
- cleaned result.
31
+ combine/split columns, drop columns), then save the cleaned result.
29
32
 
30
- ![TUI preview](https://raw.githubusercontent.com/SEIU-Tech/normalize-tabular-data/main/docs/screenshot.png)
33
+ ## Formats
31
34
 
32
- ## Running
35
+ Reads: CSV, TSV, JSON lines, Parquet, Excel (`.xlsx`/`.xls` — first sheet).
36
+ Writes: CSV, TSV, JSON lines, Parquet, Excel (`.xlsx`).
33
37
 
34
- ### Persistent install
38
+ Large files are previewed with a random sample of 250 rows; every operation
39
+ still runs on the full data.
35
40
 
36
- ```bash
37
- uv tool install normalize-tabular-data
38
- # upgrade later with:
39
- uv tool upgrade normalize-tabular-data
40
- ```
41
+ ## Running the Text User Interface
41
42
 
42
- ### Ephemeral run (no install)
43
+ ![TUI preview](https://raw.githubusercontent.com/SEIU-Tech/normalize-tabular-data/main/docs/screenshot.png)
43
44
 
44
- `uvx` fetches into a throwaway environment each time:
45
+ Installation and launch options — persistent install, ephemeral `uvx`
46
+ runs, running from a git checkout, the single-file launchers for
47
+ Linux/macOS/Windows, and installing them as desktop icons — are
48
+ described in
49
+ [docs/running-the-tool.md](https://github.com/SEIU-Tech/normalize-tabular-data/blob/main/docs/running-the-tool.md).
45
50
 
46
- ```bash
47
- uvx normalize-tabular-data
48
- # pin a specific version:
49
- uvx normalize-tabular-data==0.1.1
50
- ```
51
+ ## Capabilities in the TUI
51
52
 
52
- ### From a git checkout
53
+ Launch with `uvx normalize-tabular-data` (or a launcher). Keys:
53
54
 
54
- Within the directory of the cloned repository:
55
55
 
56
- ```bash
57
- uv run normalize-tabular-data
58
- ```
56
+ | Key | Action |
57
+ |-----|------------------------------|
58
+ | `f` | (F)ile — open a file |
59
+ | `o` | (O)peration — choose an op |
60
+ | `p` | (P)lay script — apply `.ntd` |
61
+ | `u` | (U)ndo last applied step |
62
+ | `r` | (R)edo |
63
+ | `s` | (S)ave the data in a format |
64
+ | `q` | (Q)uit |
59
65
 
60
- ## Command line
66
+ ## Operations
67
+
68
+ - **Normalize date(t)imes** — parse a messy date column of *any* input
69
+ format into canonical UTC datetimes at millisecond resolution;
70
+ unparseable values become null. CSV/TSV/JSONLines export serializes
71
+ datetime columns as second-resolution `year-month-dayThh:mm:ss`
72
+ strings; Parquet and Excel keep the real datetime values.
73
+ - **Normalize (d)ates** — the same match-anything parsing, condensed to
74
+ the UTC calendar date: the column becomes date-only ISO-8601
75
+ (`year-month-day`); unparseable values become null.
76
+ - **Trim whitespace** — strip edges and collapse internal whitespace runs,
77
+ per selected columns.
78
+ - Rename a column — click its header in the preview and type the new name.
79
+ - **Combine columns** — concatenate two or more columns with a separator.
80
+ - **Split column** — break one column into `{col}_1..{col}_k`; a blank
81
+ delimiter splits on runs of whitespace.
82
+ - **Remove columns** — drop selected columns entirely.
83
+ - **Deduplicate rows** — on all or selected columns, keeping first or last.
84
+
85
+ ## Command line usage
61
86
 
62
87
  An optional `FILE` argument names a table to open at startup, as if you
63
88
  had picked it from the in-app dialog.
64
89
 
65
90
  ```bash
66
- normalize-tabular-data data/members.csv # or with uvx/uv run
67
91
  uvx normalize-tabular-data data/members.tsv
68
92
  ```
69
93
 
@@ -104,47 +128,6 @@ to stdout itself and the step lines are suppressed, so stdout carries
104
128
  only the data. After a successful run the confirmation line goes to
105
129
  stderr.
106
130
 
107
- ## Usage
108
-
109
- Launch with `normalize-tabular-data`. Keys:
110
-
111
- | Key | Action |
112
- |-----|------------------------------|
113
- | `f` | (F)ile — open a file |
114
- | `o` | (O)peration — choose an op |
115
- | `p` | (P)lay script — apply `.ntd` |
116
- | `u` | (U)ndo last applied step |
117
- | `r` | (R)edo |
118
- | `s` | (S)ave the data in a format |
119
- | `q` | (Q)uit |
120
-
121
- ## Operations
122
-
123
- - **Normalize date(t)imes** — parse a messy date column of *any* input
124
- format into canonical UTC datetimes at millisecond resolution;
125
- unparseable values become null. CSV/TSV/JSONLines export serializes
126
- datetime columns as second-resolution `year-month-dayThh:mm:ss`
127
- strings; Parquet and Excel keep the real datetime values.
128
- - **Normalize (d)ates** — the same match-anything parsing, condensed to
129
- the UTC calendar date: the column becomes date-only ISO-8601
130
- (`year-month-day`); unparseable values become null.
131
- - **Trim whitespace** — strip edges and collapse internal whitespace runs,
132
- per selected columns.
133
- - Rename a column — click its header in the preview and type the new name.
134
- - **Combine columns** — concatenate two or more columns with a separator.
135
- - **Split column** — break one column into `{col}_1..{col}_k`; a blank
136
- delimiter splits on runs of whitespace.
137
- - **Remove columns** — drop selected columns entirely.
138
- - **Deduplicate rows** — on all or selected columns, keeping first or last.
139
-
140
- ## Formats
141
-
142
- Reads: CSV, TSV, JSON lines, Parquet, Excel (`.xlsx`/`.xls` — first sheet).
143
- Writes: CSV, TSV, JSON lines, Parquet, Excel (`.xlsx`).
144
-
145
- Large files are previewed with a random sample of 250 rows; every operation
146
- still runs on the full data.
147
-
148
131
  ## Operation scripts (`.ntd`)
149
132
 
150
133
  Every open file keeps an internal log of the operations performed on it. When
@@ -200,4 +183,4 @@ credential aborts the upload instead of prompting mid-run.
200
183
 
201
184
  BSD 2-Clause. Copyright (c) 2026, Service Employees International Union (SEIU).
202
185
 
203
- See [LICENSE](LICENSE).
186
+ See [LICENSE](https://github.com/SEIU-Tech/normalize-tabular-data/blob/main/LICENSE).
{normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/README.md RENAMED
@@ -1,52 +1,76 @@
1
- # normalize-tabular-data
1
+ # normalize-tabular-data (NTD)
2
2
 
3
3
  A terminal UI (Textual) for interactively normalizing tabular data, backed by
4
4
  [polars](https://pola.rs) for speed and
5
5
  [gnosis-date-parser](https://pypi.org/project/gnosis-date-parser/) for fuzzy
6
- date parsing at Rust speed.
6
+ date parsing at Rust speed. NTD also supports purely command-line operations
7
+ for use in scripting.
8
+
9
+ **Quick start**: `uvx normalize-tabular-data`. No installation required if
10
+ you have `uv`.
7
11
 
8
12
  Load a file, see a preview, build up a pipeline of normalization operations
9
13
  (normalize messy dates, trim whitespace, rename a column, deduplicate,
10
- combine/split columns, drop columns), then save the
11
- cleaned result.
14
+ combine/split columns, drop columns), then save the cleaned result.
12
15
 
13
- ![TUI preview](https://raw.githubusercontent.com/SEIU-Tech/normalize-tabular-data/main/docs/screenshot.png)
16
+ ## Formats
14
17
 
15
- ## Running
18
+ Reads: CSV, TSV, JSON lines, Parquet, Excel (`.xlsx`/`.xls` — first sheet).
19
+ Writes: CSV, TSV, JSON lines, Parquet, Excel (`.xlsx`).
16
20
 
17
- ### Persistent install
21
+ Large files are previewed with a random sample of 250 rows; every operation
22
+ still runs on the full data.
18
23
 
19
- ```bash
20
- uv tool install normalize-tabular-data
21
- # upgrade later with:
22
- uv tool upgrade normalize-tabular-data
23
- ```
24
+ ## Running the Text User Interface
24
25
 
25
- ### Ephemeral run (no install)
26
+ ![TUI preview](https://raw.githubusercontent.com/SEIU-Tech/normalize-tabular-data/main/docs/screenshot.png)
26
27
 
27
- `uvx` fetches into a throwaway environment each time:
28
+ Installation and launch options — persistent install, ephemeral `uvx`
29
+ runs, running from a git checkout, the single-file launchers for
30
+ Linux/macOS/Windows, and installing them as desktop icons — are
31
+ described in
32
+ [docs/running-the-tool.md](https://github.com/SEIU-Tech/normalize-tabular-data/blob/main/docs/running-the-tool.md).
28
33
 
29
- ```bash
30
- uvx normalize-tabular-data
31
- # pin a specific version:
32
- uvx normalize-tabular-data==0.1.1
33
- ```
34
+ ## Capabilities in the TUI
34
35
 
35
- ### From a git checkout
36
+ Launch with `uvx normalize-tabular-data` (or a launcher). Keys:
36
37
 
37
- Within the directory of the cloned repository:
38
38
 
39
- ```bash
40
- uv run normalize-tabular-data
41
- ```
39
+ | Key | Action |
40
+ |-----|------------------------------|
41
+ | `f` | (F)ile — open a file |
42
+ | `o` | (O)peration — choose an op |
43
+ | `p` | (P)lay script — apply `.ntd` |
44
+ | `u` | (U)ndo last applied step |
45
+ | `r` | (R)edo |
46
+ | `s` | (S)ave the data in a format |
47
+ | `q` | (Q)uit |
42
48
 
43
- ## Command line
49
+ ## Operations
50
+
51
+ - **Normalize date(t)imes** — parse a messy date column of *any* input
52
+ format into canonical UTC datetimes at millisecond resolution;
53
+ unparseable values become null. CSV/TSV/JSONLines export serializes
54
+ datetime columns as second-resolution `year-month-dayThh:mm:ss`
55
+ strings; Parquet and Excel keep the real datetime values.
56
+ - **Normalize (d)ates** — the same match-anything parsing, condensed to
57
+ the UTC calendar date: the column becomes date-only ISO-8601
58
+ (`year-month-day`); unparseable values become null.
59
+ - **Trim whitespace** — strip edges and collapse internal whitespace runs,
60
+ per selected columns.
61
+ - Rename a column — click its header in the preview and type the new name.
62
+ - **Combine columns** — concatenate two or more columns with a separator.
63
+ - **Split column** — break one column into `{col}_1..{col}_k`; a blank
64
+ delimiter splits on runs of whitespace.
65
+ - **Remove columns** — drop selected columns entirely.
66
+ - **Deduplicate rows** — on all or selected columns, keeping first or last.
67
+
68
+ ## Command line usage
44
69
 
45
70
  An optional `FILE` argument names a table to open at startup, as if you
46
71
  had picked it from the in-app dialog.
47
72
 
48
73
  ```bash
49
- normalize-tabular-data data/members.csv # or with uvx/uv run
50
74
  uvx normalize-tabular-data data/members.tsv
51
75
  ```
52
76
 
@@ -87,47 +111,6 @@ to stdout itself and the step lines are suppressed, so stdout carries
87
111
  only the data. After a successful run the confirmation line goes to
88
112
  stderr.
89
113
 
90
- ## Usage
91
-
92
- Launch with `normalize-tabular-data`. Keys:
93
-
94
- | Key | Action |
95
- |-----|------------------------------|
96
- | `f` | (F)ile — open a file |
97
- | `o` | (O)peration — choose an op |
98
- | `p` | (P)lay script — apply `.ntd` |
99
- | `u` | (U)ndo last applied step |
100
- | `r` | (R)edo |
101
- | `s` | (S)ave the data in a format |
102
- | `q` | (Q)uit |
103
-
104
- ## Operations
105
-
106
- - **Normalize date(t)imes** — parse a messy date column of *any* input
107
- format into canonical UTC datetimes at millisecond resolution;
108
- unparseable values become null. CSV/TSV/JSONLines export serializes
109
- datetime columns as second-resolution `year-month-dayThh:mm:ss`
110
- strings; Parquet and Excel keep the real datetime values.
111
- - **Normalize (d)ates** — the same match-anything parsing, condensed to
112
- the UTC calendar date: the column becomes date-only ISO-8601
113
- (`year-month-day`); unparseable values become null.
114
- - **Trim whitespace** — strip edges and collapse internal whitespace runs,
115
- per selected columns.
116
- - Rename a column — click its header in the preview and type the new name.
117
- - **Combine columns** — concatenate two or more columns with a separator.
118
- - **Split column** — break one column into `{col}_1..{col}_k`; a blank
119
- delimiter splits on runs of whitespace.
120
- - **Remove columns** — drop selected columns entirely.
121
- - **Deduplicate rows** — on all or selected columns, keeping first or last.
122
-
123
- ## Formats
124
-
125
- Reads: CSV, TSV, JSON lines, Parquet, Excel (`.xlsx`/`.xls` — first sheet).
126
- Writes: CSV, TSV, JSON lines, Parquet, Excel (`.xlsx`).
127
-
128
- Large files are previewed with a random sample of 250 rows; every operation
129
- still runs on the full data.
130
-
131
114
  ## Operation scripts (`.ntd`)
132
115
 
133
116
  Every open file keeps an internal log of the operations performed on it. When
@@ -183,4 +166,4 @@ credential aborts the upload instead of prompting mid-run.
183
166
 
184
167
  BSD 2-Clause. Copyright (c) 2026, Service Employees International Union (SEIU).
185
168
 
186
- See [LICENSE](LICENSE).
169
+ See [LICENSE](https://github.com/SEIU-Tech/normalize-tabular-data/blob/main/LICENSE).
{normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/pyproject.toml RENAMED
@@ -1,6 +1,6 @@
1
1
  [project]
2
2
  name = "normalize-tabular-data"
3
- version = "0.1.3"
3
+ version = "0.1.5"
4
4
  description = "TUI for normalizing tabular data with Polars"
5
5
  readme = "README.md"
6
6
  license = "BSD-2-Clause"
{normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/pyproject.toml.orig RENAMED
@@ -1,6 +1,6 @@
1
1
  [project]
2
2
  name = "normalize-tabular-data"
3
- version = "0.1.3"
3
+ version = "0.1.5"
4
4
  description = "TUI for normalizing tabular data with Polars"
5
5
  readme = "README.md"
6
6
  license = "BSD-2-Clause"
{normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/src/normalize_tabular_data/__init__.py RENAMED
@@ -1,4 +1,4 @@
1
- """normalize-tabular-data: TUI for normalizing tabular data with polars."""
1
+ """normalize-tabular-data: TUI for normalizing tabular data with Polars."""
2
2
 
3
3
  from __future__ import annotations
4
4
 
@@ -6,7 +6,7 @@ import argparse
6
6
  import sys
7
7
  from pathlib import Path
8
8
 
9
- __version__ = "0.1.3"
9
+ __version__ = "0.1.5"
10
10
 
11
11
 
12
12
  def _run_script(path: Path, script_path: Path, output: Path | None) -> int:
@@ -145,7 +145,8 @@ def main() -> None:
145
145
  except ImportError as exc: # helpful message if an optional engine is missing
146
146
  print(
147
147
  f"normalize-tabular-data is missing a dependency ({exc}).\n"
148
- "Reinstall with: uv tool install --force --reinstall normalize-tabular-data",
148
+ "Reinstall with: "
149
+ "uv tool install --force --reinstall normalize-tabular-data",
149
150
  file=sys.stderr,
150
151
  )
151
152
  raise SystemExit(1)
{normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/src/normalize_tabular_data/io.py RENAMED
@@ -1,4 +1,4 @@
1
- """Format dispatch: suffix -> polars read/write. No Textual imports."""
1
+ """Format dispatch: suffix -> Polars read/write. No Textual imports."""
2
2
 
3
3
  from __future__ import annotations
4
4
 
{normalize_tabular_data-0.1.3 → normalize_tabular_data-0.1.5}/src/normalize_tabular_data/ops.py RENAMED
@@ -1,6 +1,6 @@
1
1
  """Normalization engine: operation registry and re-computing pipeline.
2
2
 
3
- Pure polars — no Textual imports here, so the whole engine is testable
3
+ Pure Polars — no Textual imports here, so the whole engine is testable
4
4
  without a terminal.
5
5
  """
6
6