fauxdata-cli 0.1.1__tar.gz → 0.1.2__tar.gz

fauxdata_cli-0.1.2/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Andrea Borruso <aborruso@gmail.com>
+
+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.

fauxdata_cli-0.1.2/LOG.md

@@ -0,0 +1,34 @@
+# Log
+
+## 2026-03-06 — v0.1.2
+
+- Bump to 0.1.2 and publish to PyPI
+
+## 2026-03-06 (feature)
+
+- `--version` / `-V` flag nel CLI (`fauxdata --version` → `fauxdata 0.1.1`)
+- Coverage threshold 80% in pytest config (`--cov-fail-under=80`); attuale: 83.76%
+- Nuovo campo `pattern` in ColumnSchema: genera stringhe che matchano un regex via pointblank
+- Nuovo campo `null_probability` in ColumnSchema: controllo granulare dei null (0.0–1.0), con validazione in parsing
+- Rimossa dipendenza `faker` (non usata, pointblank gestisce tutto)
+- Fix generator: `null_probability=None` non passato a pointblank (causa TypeError)
+- Test aggiornati: 79/79 pass
+
+## 2026-03-06 (tests)
+
+- Add pytest test suite: 65 tests, 100% pass, 0.44s
+- `tests/test_schema.py`: unit tests for YAML schema parsing (valid/invalid cases)
+- `tests/test_output.py`: unit tests for export functions (all formats, stdout, errors)
+- `tests/test_generator.py`: integration tests for generation (types, seed, unique, presets)
+- `tests/test_validator.py`: integration tests for validation rules (pass/fail scenarios)
+- `tests/test_cli.py`: CLI smoke tests via `typer.testing.CliRunner`
+- Add `[dependency-groups] dev` in `pyproject.toml` (pytest, pytest-cov); config via `[tool.pytest.ini_options]`
+
+## 2026-03-06
+
+- Initial implementation of `fauxdata` CLI
+- Stack: pointblank 0.22 (native generation + validation), polars, typer, rich, pyfiglet, questionary
+- Commands: `init`, `generate`, `validate`, `preview`
+- Example schemas: `people.yml`, `orders.yml`, `events.yml`
+- All schemas generate and validate cleanly (all rules PASS)
+- `locale` field at schema level maps to pointblank `country=` param

{fauxdata_cli-0.1.1 → fauxdata_cli-0.1.2}/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.4
 Name: fauxdata-cli
-Version: 0.1.1
+Version: 0.1.2
 Summary: CLI for generating and validating fake datasets
 Project-URL: Homepage, https://aborruso.github.io/fauxdata/
 Project-URL: Repository, https://github.com/aborruso/fauxdata
 Project-URL: Bug Tracker, https://github.com/aborruso/fauxdata/issues
+License-File: LICENSE
 Requires-Python: >=3.11
-Requires-Dist: faker>=26.0
 Requires-Dist: pointblank>=0.22
 Requires-Dist: polars>=1.0
 Requires-Dist: pyfiglet>=1.0

fauxdata_cli-0.1.2/docs/deployment.md

@@ -0,0 +1,90 @@
+# Deployment rules
+
+## Pre-release checklist (always)
+
+1. Run tests locally — must all pass:
+
+```bash
+uv run pytest
+```
+
+Coverage must stay above 80%. If it drops, fix before proceeding.
+
+2. Bump version in **both**:
+   - `src/fauxdata/__init__.py` → `__version__ = "X.Y.Z"`
+   - `pyproject.toml` → `version = "X.Y.Z"`
+
+3. Update `LOG.md` with a summary of changes under a new date heading.
+
+---
+
+## GitHub release (tag + release notes)
+
+```bash
+# Create and push annotated tag
+git tag -a vX.Y.Z -m "vX.Y.Z"
+git push origin vX.Y.Z
+```
+
+Then create a GitHub release via `gh`:
+
+```bash
+gh release create vX.Y.Z \
+  --title "vX.Y.Z" \
+  --notes "$(cat <<'EOF'
+## What's new
+
+- Short bullet list of user-facing changes
+- Include new fields, commands, bug fixes
+
+## Breaking changes
+
+- List any breaking changes here (or remove section if none)
+
+## Installation
+
+\`\`\`bash
+pip install fauxdata-cli==X.Y.Z
+\`\`\`
+
+Full changelog: https://github.com/aborruso/fauxdata/commits/vX.Y.Z
+EOF
+)"
+```
+
+Release notes style: **concise, nerd-friendly, technical**. List the actual changes with enough detail that a developer understands what changed and why.
+
+---
+
+## PyPI publish (via twine)
+
+```bash
+# Build
+uv build
+
+# Check the dist
+twine check dist/*
+
+# Publish
+twine upload dist/*
+```
+
+Requires `~/.pypirc` configured with PyPI token, or set `TWINE_USERNAME`/`TWINE_PASSWORD` env vars.
+
+---
+
+## Order of operations
+
+```
+uv run pytest          # must pass 100%
+bump version           # __init__.py + pyproject.toml
+update LOG.md
+git commit + git push
+git tag + git push tag
+gh release create      # with release notes
+uv build
+twine check dist/*
+twine upload dist/*
+```
+
+Never publish to PyPI without a corresponding GitHub release.

{fauxdata_cli-0.1.1 → fauxdata_cli-0.1.2}/docs/index.html

@@ -5,8 +5,32 @@
 <meta name="viewport" content="width=device-width, initial-scale=1.0">
 <title>fauxdata — fake data, done right</title>
 <meta name="description" content="fauxdata is a CLI tool for generating and validating realistic fake datasets from YAML schemas. Locale-aware, pipeline-friendly, powered by pointblank.">
+<meta name="keywords" content="fake data, synthetic data, dataset generator, CLI, YAML schema, pointblank, data testing, fake dataset, CSV generator, Parquet">
+<meta name="author" content="Andrea Borruso">
+<meta name="robots" content="index, follow">
+<link rel="canonical" href="https://aborruso.github.io/fauxdata/">
+
+<!-- Open Graph -->
+<meta property="og:type" content="website">
+<meta property="og:url" content="https://aborruso.github.io/fauxdata/">
 <meta property="og:title" content="fauxdata — fake data, done right">
 <meta property="og:description" content="Generate and validate realistic fake datasets from YAML schemas. Because fake data can actually be better than real data.">
+<meta property="og:image" content="https://aborruso.github.io/fauxdata/share.png">
+<meta property="og:image:width" content="1200">
+<meta property="og:image:height" content="630">
+<meta property="og:image:alt" content="fauxdata — CLI tool for generating realistic fake datasets">
+<meta property="og:site_name" content="fauxdata">
+<meta property="og:locale" content="en_US">
+
+<!-- Twitter Card -->
+<meta name="twitter:card" content="summary_large_image">
+<meta name="twitter:url" content="https://aborruso.github.io/fauxdata/">
+<meta name="twitter:title" content="fauxdata — fake data, done right">
+<meta name="twitter:description" content="Generate and validate realistic fake datasets from YAML schemas. Because fake data can actually be better than real data.">
+<meta name="twitter:image" content="https://aborruso.github.io/fauxdata/share.png">
+<meta name="twitter:image:alt" content="fauxdata — CLI tool for generating realistic fake datasets">
+<meta name="twitter:creator" content="@aborruso">
+
 <link rel="preconnect" href="https://fonts.googleapis.com">
 <link href="https://fonts.googleapis.com/css2?family=IBM+Plex+Mono:ital,wght@0,300;0,400;0,600;0,700;1,400&family=VT323&display=swap" rel="stylesheet">
 <style>
@@ -876,11 +900,13 @@
         <span class="t-line dim" style="padding-left:2rem">| duckdb -c "SELECT status, COUNT(*) FROM '/dev/stdin' GROUP BY ALL"</span>
         <br>
         <span class="t-line t-out">┌───────────┬──────────┐</span>
-        <span class="t-line t-out">│ status    │ count(*) │</span>
-        <span class="t-line t-out">│ delivered │ 3124     │</span>
-        <span class="t-line t-out">│ shipped   │ 2891     │</span>
-        <span class="t-line t-out">│ pending   │ 2003     │</span>
-        <span class="t-line t-out">│ cancelled │ 1982     │</span>
+        <span class="t-line t-out">│  status   │ count(*) │</span>
+        <span class="t-line t-out">│  varchar  │  int64   │</span>
+        <span class="t-line t-out">├───────────┼──────────┤</span>
+        <span class="t-line t-out">│ delivered │     3124 │</span>
+        <span class="t-line t-out">│ shipped   │     2891 │</span>
+        <span class="t-line t-out">│ pending   │     2003 │</span>
+        <span class="t-line t-out">│ cancelled │     1982 │</span>
         <span class="t-line t-out">└───────────┴──────────┘</span>
       </div>
     </div>

{fauxdata_cli-0.1.1 → fauxdata_cli-0.1.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "fauxdata-cli"
-version = "0.1.1"
+version = "0.1.2"
 description = "CLI for generating and validating fake datasets"
 readme = "README.md"
 requires-python = ">=3.11"
@@ -12,7 +12,6 @@ dependencies = [
     "questionary>=2.0",
     "polars>=1.0",
     "pyyaml>=6.0",
-    "faker>=26.0",
 ]
 
 [project.urls]
@@ -23,6 +22,16 @@ Repository = "https://github.com/aborruso/fauxdata"
 [project.scripts]
 fauxdata = "fauxdata.main:app"
 
+[dependency-groups]
+dev = [
+    "pytest>=8.0",
+    "pytest-cov>=5.0",
+]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "--tb=short --cov=fauxdata --cov-report=term-missing --cov-fail-under=80"
+
 [build-system]
 requires = ["hatchling"]
 build-backend = "hatchling.build"

{fauxdata_cli-0.1.1 → fauxdata_cli-0.1.2}/src/fauxdata/__init__.py

@@ -1,3 +1,3 @@
 """fauxdata - CLI for generating and validating fake datasets."""
 
-__version__ = "0.1.0"
+__version__ = "0.1.2"

{fauxdata_cli-0.1.1 → fauxdata_cli-0.1.2}/src/fauxdata/commands/generate.py

@@ -61,13 +61,22 @@ def _print_schema_table(schema, n: int, seed):
     t = Table(title=f"Schema: {schema.name}", show_header=True, header_style="bold magenta")
     t.add_column("Column", style="cyan")
     t.add_column("Type")
-    t.add_column("Preset/Values")
+    t.add_column("Preset/Pattern/Values")
     t.add_column("Min")
     t.add_column("Max")
     t.add_column("Unique")
+    t.add_column("Null%")
 
     for col in schema.columns:
-        preset_val = col.preset or (str(col.values) if col.values else "-")
+        if col.pattern:
+            preset_val = f"pattern:{col.pattern}"
+        elif col.preset:
+            preset_val = col.preset
+        elif col.values:
+            preset_val = str(col.values)
+        else:
+            preset_val = "-"
+        null_pct = f"{int(col.null_probability * 100)}%" if col.null_probability else "-"
         t.add_row(
             col.name,
             col.col_type,
@@ -75,6 +84,7 @@ def _print_schema_table(schema, n: int, seed):
             str(col.min) if col.min is not None else "-",
             str(col.max) if col.max is not None else "-",
             "yes" if col.unique else "no",
+            null_pct,
         )
 
     console.print(t)

{fauxdata_cli-0.1.1 → fauxdata_cli-0.1.2}/src/fauxdata/generator.py

@@ -30,8 +30,10 @@ def _build_pb_schema(schema: SchemaConfig) -> pb.Schema:
 
 def _col_to_field(col: ColumnSchema):
     """Convert a ColumnSchema to a pointblank field spec."""
-    nullable = col.nullable
+    nullable = col.nullable or (col.null_probability is not None and col.null_probability > 0)
     unique = col.unique
+    # Build optional kwargs only when null_probability is explicitly set
+    np_kwargs = {"null_probability": col.null_probability} if col.null_probability is not None else {}
 
     if col.col_type == "int":
         return pb.int_field(
@@ -39,6 +41,7 @@ def _col_to_field(col: ColumnSchema):
             max_val=int(col.max) if col.max is not None else None,
             nullable=nullable,
             unique=unique,
+            **np_kwargs,
         )
 
     elif col.col_type == "float":
@@ -47,10 +50,11 @@ def _col_to_field(col: ColumnSchema):
             max_val=float(col.max) if col.max is not None else None,
             nullable=nullable,
             unique=unique,
+            **np_kwargs,
         )
 
     elif col.col_type == "bool":
-        return pb.bool_field(nullable=nullable)
+        return pb.bool_field(nullable=nullable, **np_kwargs)
 
     elif col.col_type == "date":
         return pb.date_field(
@@ -58,6 +62,7 @@ def _col_to_field(col: ColumnSchema):
             max_date=str(col.max) if col.max is not None else None,
             nullable=nullable,
             unique=unique,
+            **np_kwargs,
         )
 
     elif col.col_type == "datetime":
@@ -66,15 +71,18 @@ def _col_to_field(col: ColumnSchema):
             max_date=str(col.max) if col.max is not None else None,
             nullable=nullable,
             unique=unique,
+            **np_kwargs,
         )
 
     elif col.col_type == "string":
         if col.values:
-            return pb.string_field(allowed=col.values, nullable=nullable)
+            return pb.string_field(allowed=col.values, nullable=nullable, **np_kwargs)
+        elif col.pattern:
+            return pb.string_field(pattern=col.pattern, nullable=nullable, unique=unique, **np_kwargs)
         elif col.preset:
-            return pb.string_field(preset=col.preset, nullable=nullable, unique=unique)
+            return pb.string_field(preset=col.preset, nullable=nullable, unique=unique, **np_kwargs)
         else:
-            return pb.string_field(nullable=nullable, unique=unique)
+            return pb.string_field(nullable=nullable, unique=unique, **np_kwargs)
 
     else:
-        return pb.string_field(nullable=nullable)
+        return pb.string_field(nullable=nullable, **np_kwargs)

{fauxdata_cli-0.1.1 → fauxdata_cli-0.1.2}/src/fauxdata/main.py

@@ -9,6 +9,8 @@ import typer
 from rich import print as rprint
 from rich.console import Console
 
+from fauxdata import __version__
+
 app = typer.Typer(
     name="fauxdata",
     help="Generate and validate fake datasets from YAML schemas.",
@@ -23,8 +25,20 @@ def _banner():
     rprint("[dim]Generate and validate realistic fake datasets[/dim]\n")
 
 
+def _version_callback(value: bool):
+    if value:
+        rprint(f"fauxdata {__version__}")
+        raise typer.Exit()
+
+
 @app.callback(invoke_without_command=True)
-def main(ctx: typer.Context):
+def main(
+    ctx: typer.Context,
+    version: Optional[bool] = typer.Option(
+        None, "--version", "-V", callback=_version_callback, is_eager=True,
+        help="Show version and exit.",
+    ),
+):
     if ctx.invoked_subcommand is None:
         _banner()
         rprint(ctx.get_help())

{fauxdata_cli-0.1.1 → fauxdata_cli-0.1.2}/src/fauxdata/schema.py

@@ -57,6 +57,8 @@ class ColumnSchema:
     locale: str | None = None
     precision: int | None = None
     values: list | None = None  # for in_set
+    pattern: str | None = None  # regex pattern for string generation
+    null_probability: float | None = None  # e.g. 0.1 = 10% nulls
 
 
 @dataclass
@@ -142,6 +144,10 @@ def _parse_column(name: str, data: dict) -> ColumnSchema:
     if preset and preset not in STRING_PRESETS:
         raise ValueError(f"Column '{name}': unknown preset '{preset}'. Valid: {STRING_PRESETS}")
 
+    null_probability = data.get("null_probability", None)
+    if null_probability is not None and not (0.0 <= float(null_probability) <= 1.0):
+        raise ValueError(f"Column '{name}': null_probability must be between 0.0 and 1.0")
+
     return ColumnSchema(
         name=name,
         col_type=col_type,
@@ -153,6 +159,8 @@ def _parse_column(name: str, data: dict) -> ColumnSchema:
         locale=data.get("locale", None),
         precision=data.get("precision", None),
         values=data.get("values", None),
+        pattern=data.get("pattern", None),
+        null_probability=float(null_probability) if null_probability is not None else None,
     )
 
 

fauxdata_cli-0.1.2/tests/conftest.py

@@ -0,0 +1,39 @@
+"""Shared fixtures for fauxdata tests."""
+
+import pytest
+import polars as pl
+
+from fauxdata.schema import SchemaConfig, ColumnSchema, ValidationRule
+
+
+@pytest.fixture
+def minimal_schema():
+    """A minimal SchemaConfig with one int and one string column."""
+    return SchemaConfig(
+        name="test",
+        rows=10,
+        seed=42,
+        locale="US",
+        output_format="csv",
+        columns=[
+            ColumnSchema(name="id", col_type="int", min=1, max=100, unique=True),
+            ColumnSchema(name="name", col_type="string", preset="name"),
+        ],
+    )
+
+
+@pytest.fixture
+def simple_df():
+    """A small deterministic DataFrame for validation tests."""
+    return pl.DataFrame({
+        "id": [1, 2, 3],
+        "age": [25, 40, 55],
+        "email": ["a@b.com", "c@d.com", "e@f.com"],
+    })
+
+
+@pytest.fixture
+def people_schema_path():
+    """Path to the existing people.yml schema."""
+    from pathlib import Path
+    return str(Path(__file__).parent.parent / "schemas" / "people.yml")

fauxdata_cli-0.1.2/tests/test_cli.py

@@ -0,0 +1,112 @@
+"""Smoke tests for the fauxdata CLI using typer's CliRunner."""
+
+import textwrap
+import pytest
+from typer.testing import CliRunner
+
+from fauxdata.main import app
+
+runner = CliRunner()
+
+
+def test_cli_no_args():
+    """Running fauxdata with no args should show help."""
+    result = runner.invoke(app, [])
+    assert result.exit_code == 0
+    assert "fauxdata" in result.output.lower() or "generate" in result.output.lower()
+
+
+def test_cli_help():
+    result = runner.invoke(app, ["--help"])
+    assert result.exit_code == 0
+    assert "generate" in result.output
+
+
+def test_cli_generate_help():
+    result = runner.invoke(app, ["generate", "--help"])
+    assert result.exit_code == 0
+    assert "--rows" in result.output
+    assert "--format" in result.output
+
+
+def test_cli_generate_csv(tmp_path, people_schema_path):
+    out = tmp_path / "out.csv"
+    result = runner.invoke(app, ["generate", people_schema_path, "--rows", "5",
+                                  "--out", str(out), "--format", "csv", "--seed", "1"])
+    assert result.exit_code == 0, result.output
+    assert out.exists()
+
+
+def test_cli_generate_json(tmp_path, people_schema_path):
+    out = tmp_path / "out.json"
+    result = runner.invoke(app, ["generate", people_schema_path, "--rows", "5",
+                                  "--out", str(out), "--format", "json", "--seed", "1"])
+    assert result.exit_code == 0, result.output
+    assert out.exists()
+
+
+def test_cli_generate_parquet(tmp_path, people_schema_path):
+    out = tmp_path / "out.parquet"
+    result = runner.invoke(app, ["generate", people_schema_path, "--rows", "5",
+                                  "--out", str(out), "--format", "parquet", "--seed", "1"])
+    assert result.exit_code == 0, result.output
+    assert out.exists()
+
+
+def test_cli_generate_stdout(people_schema_path, capsys):
+    result = runner.invoke(app, ["generate", people_schema_path, "--rows", "3",
+                                  "--out", "-", "--format", "csv", "--seed", "1"])
+    assert result.exit_code == 0, result.output
+
+
+def test_cli_generate_with_validate(tmp_path, people_schema_path):
+    out = tmp_path / "out.csv"
+    result = runner.invoke(app, ["generate", people_schema_path, "--rows", "10",
+                                  "--out", str(out), "--format", "csv",
+                                  "--seed", "42", "--validate"])
+    assert result.exit_code == 0, result.output
+
+
+def test_cli_generate_missing_schema(tmp_path):
+    result = runner.invoke(app, ["generate", "/nonexistent/schema.yml"])
+    assert result.exit_code != 0
+
+
+def test_cli_validate(tmp_path, people_schema_path):
+    """Generate a file then validate it."""
+    out = tmp_path / "people.csv"
+    runner.invoke(app, ["generate", people_schema_path, "--rows", "10",
+                         "--out", str(out), "--format", "csv", "--seed", "42"])
+    result = runner.invoke(app, ["validate", str(out), people_schema_path])
+    assert result.exit_code == 0, result.output
+
+
+def test_cli_preview(tmp_path, people_schema_path):
+    out = tmp_path / "people.csv"
+    runner.invoke(app, ["generate", people_schema_path, "--rows", "20",
+                         "--out", str(out), "--format", "csv", "--seed", "42"])
+    result = runner.invoke(app, ["preview", str(out), "--rows", "5"])
+    assert result.exit_code == 0, result.output
+
+
+def test_cli_generate_inline_schema(tmp_path):
+    """Test with a minimal inline schema written to a tmp file."""
+    schema_yaml = textwrap.dedent("""\
+        name: mini
+        rows: 5
+        columns:
+          id:
+            type: int
+            min: 1
+            max: 100
+          label:
+            type: string
+            values: ["a", "b"]
+    """)
+    schema_path = tmp_path / "mini.yml"
+    schema_path.write_text(schema_yaml)
+    out = tmp_path / "mini.csv"
+    result = runner.invoke(app, ["generate", str(schema_path),
+                                  "--out", str(out), "--format", "csv", "--seed", "1"])
+    assert result.exit_code == 0, result.output
+    assert out.exists()