tab-cli 0.1.2__tar.gz → 0.1.3__tar.gz

tab_cli-0.1.3/CHANGELOG.md

@@ -0,0 +1,8 @@
+ - 0.1.3:
+   - Separate `tab view` from `tab cat`: `tab view` does not convert formats, `tab cat` does.
+   - Added `--max-cell-len` option to `tab view` to truncate long cell contents.
+ - 0.1.2:
+   - Bugfix on reading directories.
+ - 0.1.1:
+   - Better credential handling for Azure Blob Storage and Google Cloud Storage.
+ - 0.1.0: Initial release

{tab_cli-0.1.2 → tab_cli-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tab-cli
-Version: 0.1.2
+Version: 0.1.3
 Summary: A CLI tool for tabular data
 Author-email: Tongfei Chen <tongfei@pm.me>
 License-File: LICENSE
@@ -26,4 +26,11 @@ Description-Content-Type: text/markdown
 
 # tab
 
+![pypi](https://img.shields.io/pypi/v/tab-cli)
+```sh
+pip install tab-cli
+```
+
 A CLI tool for viewing, querying, and converting tabular data files. Supports AWS / Azure / Google Cloud Storage URLs.
+
+ - Documentation: [docs](https://tongfei.me/tab)

tab_cli-0.1.3/README.md

@@ -0,0 +1,10 @@
+# tab
+
+![pypi](https://img.shields.io/pypi/v/tab-cli)
+```sh
+pip install tab-cli
+```
+
+A CLI tool for viewing, querying, and converting tabular data files. Supports AWS / Azure / Google Cloud Storage URLs.
+
+ - Documentation: [docs](https://tongfei.me/tab)

{tab_cli-0.1.2 → tab_cli-0.1.3}/docs/cli-ref.md

@@ -2,7 +2,7 @@
 
 ## `tab view`
 
-View tabular data from a data file, or a directory of partitions of data files.
+View tabular data from a data file in a rich CLI format, or a directory of partitions of data files.
 
 ```bash
 tab view $path [OPTIONS]
@@ -13,9 +13,9 @@ Options:
 | Option                  | Description                                                                                               |
 |-------------------------|-----------------------------------------------------------------------------------------------------------|
 | `-i` / `--input-format` | Input format (`parquet`, `csv`, `tsv`, `jsonl`, `avro`). Auto-detected from extension if omitted.         |
-| `-o` / `--output-format` | Output format (`parquet`, `csv`, `tsv`, `jsonl`, `avro`). If not specified, print Rich table in terminal. |
 | `--limit`               | Maximum number of rows to display.                                                                        |
 | `--skip`                | Number of rows to skip from the beginning.                                                                |
+| `--max-cell-len`        | Truncate cell contents longer than this.                                                                 |
 
 ## `tab schema`
 

{tab_cli-0.1.2/site → tab_cli-0.1.3/docs}/gen_assets.sh

@@ -1,3 +1,3 @@
 mkdir -p docs/assets
-uv run tab view docs/test.csv -o table-svg 2> docs/assets/test.svg
+uv run tab view tests/assets/test.csv -o table-svg 2> docs/assets/test.svg
 uv run tab sql 'SELECT * FROM t WHERE Metric_A_Value > 80' docs/test.csv -o table-svg 2> docs/assets/test-where.svg

{tab_cli-0.1.2 → tab_cli-0.1.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "tab-cli"
-version = "0.1.2"
+version = "0.1.3"
 description = "A CLI tool for tabular data"
 authors = [{name = "Tongfei Chen", email = "tongfei@pm.me"}]
 readme = "README.md"
@@ -26,12 +26,16 @@ azure = ["adlfs>=2025.1.0", "azure-identity>=1.10.0"]
 dev = [
     "ruff>=0.14.14",
     "ty>=0.0.14",
-    "mkdocs-material>=9.0.0"
+    "mkdocs-material>=9.0.0",
+    "pytest>=8.0",
 ]
 
 [project.scripts]
 tab = "tab_cli.cli:main"
 
+[tool.hatch.build.targets.wheel]
+packages = ["src/tab_cli"]
+
 [build-system]
 requires = ["hatchling"]
 build-backend = "hatchling.build"

{tab_cli-0.1.2 → tab_cli-0.1.3/src}/tab_cli/cli.py

@@ -11,6 +11,7 @@ from rich.logging import RichHandler
 
 from tab_cli import config
 from tab_cli.handlers import TableWriter, infer_reader, infer_writer
+from tab_cli.handlers.cli_table import CliTableFormatter
 
 app = typer.Typer(
     help="A CLI tool for viewing and manipulating tabular data.",
@@ -46,32 +47,28 @@ def main_callback(
     )
 
 
-def _output(
+def _apply_limit(
     lf: pl.LazyFrame,
     limit: int | None,
     skip: int,
-    output: str | None,
-) -> None:
-    show_truncation = limit is None and output is None
-    actual_limit = 20 if show_truncation else limit
-
-    if show_truncation:
-        assert actual_limit is not None
-        lf = lf.slice(skip, length=actual_limit + 1)
+    default_limit: int | None = None,
+) -> tuple[pl.LazyFrame, bool]:
+    """Apply skip/limit to a LazyFrame, optionally detecting truncation.
+
+    If limit is None and default_limit is set, caps at default_limit rows
+    and returns whether the data was truncated.
+    """
+    if limit is None and default_limit is not None:
+        lf = lf.slice(skip, length=default_limit + 1)
         df = lf.collect()
-        truncated = len(df) > actual_limit
+        truncated = len(df) > default_limit
         if truncated:
-            df = df.head(actual_limit)
-        lf = df.lazy()
+            df = df.head(default_limit)
+        return df.lazy(), truncated
     else:
-        if skip > 0 or actual_limit is not None:
-            lf = lf.slice(skip, length=actual_limit)
-        truncated = False
-
-    writer = infer_writer(output, truncated=show_truncation and truncated)
-
-    for chunk in writer.write(lf):
-        sys.stdout.buffer.write(chunk)
+        if skip > 0 or limit is not None:
+            lf = lf.slice(skip, length=limit)
+        return lf, False
 
 
 @app.command()
@@ -79,13 +76,16 @@ def view(
     path: Annotated[str, typer.Argument(help="Path to the data file or directory")],
     limit: Annotated[Optional[int], typer.Option("--limit", help="Maximum number of rows to display")] = None,
     skip: Annotated[int, typer.Option("--skip", help="Number of rows to skip")] = 0,
-    input: Annotated[Optional[str], typer.Option("-i", "--input-format", help="Input format")] = None,
-    output: Annotated[Optional[str], typer.Option("-o", "--output-format", help="Output format")] = None,
+    input: Annotated[Optional[str], typer.Option("-i", "--input-format", help="Input format, auto-detected from extension if omitted")] = None,
+    max_cell_len: Annotated[Optional[int], typer.Option("--max-cell-len", help="Truncate cell contents longer than this")] = None,
 ) -> None:
-    """View tabular data from a file."""
+    """View tabular data as a formatted table."""
     reader = infer_reader(path, format=input)
     lf = reader.read(path)
-    _output(lf, limit=limit, skip=skip, output=output)
+    lf, truncated = _apply_limit(lf, limit=limit, skip=skip, default_limit=20 if limit is None else None)
+    writer = CliTableFormatter(truncated=truncated, max_cell_len=max_cell_len)
+    for chunk in writer.write(lf):
+        sys.stdout.buffer.write(chunk)
 
 @app.command()
 def schema(
@@ -113,7 +113,11 @@ def sql(
     lf = reader.read(path)
     ctx = pl.SQLContext(t=lf, eager=False)
     result_lf = ctx.execute(query)
-    _output(result_lf, limit=limit, skip=skip, output=output)
+    show_truncation = limit is None and output is None
+    result_lf, truncated = _apply_limit(result_lf, limit=limit, skip=skip, default_limit=20 if show_truncation else None)
+    writer = infer_writer(output, truncated=truncated)
+    for chunk in writer.write(result_lf):
+        sys.stdout.buffer.write(chunk)
 
 
 @app.command()
@@ -156,11 +160,17 @@ def cat(
     input: Annotated[Optional[str], typer.Option("-i", "--input-format", help="Input format")] = None,
     output: Annotated[Optional[str], typer.Option("-o", "--output-format", help="Output format")] = None,
 ) -> None:
-    """Concatenate tabular data from multiple files."""
+    """Concatenate tabular data from multiple files, or just print a single file."""
     reader = infer_reader(paths[0], format=input)
     files = [reader.read(path) for path in paths]
     lf = pl.concat(files, how="vertical")
-    _output(lf, limit=None, skip=0, output=output)
+    if output is not None:
+        writer = infer_writer(format=output)
+    else:
+        writer = infer_writer(format=reader.format.extension())
+        assert isinstance(writer, TableWriter)
+    for chunk in writer.write(lf):
+        sys.stdout.buffer.write(chunk)
 
 
 def main() -> None:

{tab_cli-0.1.2 → tab_cli-0.1.3/src}/tab_cli/formats/avro.py

@@ -14,7 +14,7 @@ class AvroFormat(FormatHandler):
     """Handler for Avro files."""
 
     def extension(self) -> str:
-        return ".avro"
+        return "avro"
 
     def supports_glob(self) -> bool:
         # polars_fastavro doesn't support glob patterns

{tab_cli-0.1.2 → tab_cli-0.1.3/src}/tab_cli/formats/csv.py

@@ -16,7 +16,7 @@ class CsvFormat(FormatHandler):
         self.separator = separator
 
     def extension(self) -> str:
-        return ".csv" if self.separator == "," else ".tsv"
+        return "csv" if self.separator == "," else "tsv"
 
     def supports_glob(self) -> bool:
         return True

{tab_cli-0.1.2 → tab_cli-0.1.3/src}/tab_cli/formats/jsonl.py

@@ -13,7 +13,7 @@ class JsonlFormat(FormatHandler):
     """Handler for JSONL files."""
 
     def extension(self) -> str:
-        return ".jsonl"
+        return "jsonl"
 
     def supports_glob(self) -> bool:
         return True

{tab_cli-0.1.2 → tab_cli-0.1.3/src}/tab_cli/formats/parquet.py

@@ -13,7 +13,7 @@ class ParquetFormat(FormatHandler):
     """Handler for Parquet files."""
 
     def extension(self) -> str:
-        return ".parquet"
+        return "parquet"
 
     def supports_glob(self) -> bool:
         return True

{tab_cli-0.1.2 → tab_cli-0.1.3/src}/tab_cli/handlers/__init__.py

@@ -74,20 +74,21 @@ def infer_reader(path: str, format: str | None = None) -> TableReader:
     return TableReader(backend, fmt)
 
 
-def infer_writer(format: str | None = None, truncated: bool = False) -> TableWriter:
+def infer_writer(format: str | None = None, truncated: bool = False, max_cell_len: int | None = None) -> TableWriter:
     """Infer the writer for a format.
 
     Args:
         format: Output format. If None, returns CLI table formatter.
         truncated: Whether the output is truncated (for CLI display).
+        max_cell_len: Maximum cell content length for CLI table display.
 
     Returns:
         TableWriter for the format.
     """
     if format is None:
-        return CliTableFormatter(truncated=truncated)
+        return CliTableFormatter(truncated=truncated, max_cell_len=max_cell_len)
     if format == "table-svg":
-        return CliTableFormatter(truncated=truncated, svg_capture=True)
+        return CliTableFormatter(truncated=truncated, svg_capture=True, max_cell_len=max_cell_len)
 
     fmt = _FORMAT_MAP.get(format.lower())
     if fmt is None:

{tab_cli-0.1.2 → tab_cli-0.1.3/src}/tab_cli/handlers/base.py

@@ -119,7 +119,7 @@ class TableReader:
     def schema(self, url: str) -> TableSchema:
         if self.backend.is_directory(url):
             # Get schema from first file
-            files = list(self.backend.list_files(url, self.format.extension()))
+            files = list(self.backend.list_files(url, "." + self.format.extension()))
             if not files:
                 raise ValueError(f"No {self.format.extension()} files found in {url}")
             url = files[0].url
@@ -151,7 +151,7 @@ class TableReader:
 
     def _summary_directory(self, url: str) -> TableSummary:
         """Aggregate summary from all files in directory."""
-        files = list(self.backend.list_files(url, self.format.extension()))
+        files = list(self.backend.list_files(url, "." + self.format.extension()))
         if not files:
             raise ValueError(f"No {self.format.extension()} files found in {url}")
 

{tab_cli-0.1.2 → tab_cli-0.1.3/src}/tab_cli/handlers/cli_table.py

@@ -11,9 +11,15 @@ from tab_cli.style import _ALT_ROW_STYLE_0, _ALT_ROW_STYLE_1, _KEY_STYLE
 
 
 class CliTableFormatter(TableWriter):
-    def __init__(self, truncated: bool = False, svg_capture: bool = False):
+    def __init__(self, truncated: bool = False, svg_capture: bool = False, max_cell_len: int | None = None):
         self.truncated = truncated
         self.svg_capture = svg_capture
+        self.max_cell_len = max_cell_len
+
+    def _truncate(self, value: str) -> str:
+        if self.max_cell_len is not None and len(value) > self.max_cell_len:
+            return value[:self.max_cell_len] + "..."
+        return value
 
     def extension(self) -> str:
         return ".txt"
@@ -32,7 +38,7 @@ class CliTableFormatter(TableWriter):
 
         for batch in lf.collect_batches():
             for row in batch.iter_rows():
-                table.add_row(*[str(v) if v is not None else "" for v in row])
+                table.add_row(*[self._truncate(str(v)) if v is not None else "" for v in row])
 
         if self.truncated:
             table.add_row(*["..." for _ in lf.collect_schema().names()])

tab_cli-0.1.3/tests/test_cli.py

@@ -0,0 +1,108 @@
+"""Tests for the tab CLI commands."""
+
+import os
+
+from typer.testing import CliRunner
+
+from tab_cli.cli import app
+
+runner = CliRunner()
+TEST_CSV = os.path.join(os.path.dirname(__file__), "assets", "test.csv")
+
+
+class TestView:
+    def test_basic(self):
+        result = runner.invoke(app, ["view", TEST_CSV])
+        assert result.exit_code == 0
+        assert "P001" in result.output
+        assert "Control" in result.output
+
+    def test_limit(self):
+        result = runner.invoke(app, ["view", TEST_CSV, "--limit", "2"])
+        assert result.exit_code == 0
+        assert "P001" in result.output
+        # Row 3 (P002 second row) should not appear
+        assert "P003" not in result.output
+        # No truncation indicator when explicit limit
+        assert "..." not in result.output
+
+    def test_skip(self):
+        result = runner.invoke(app, ["view", TEST_CSV, "--skip", "6", "--limit", "10"])
+        assert result.exit_code == 0
+        # First 6 rows skipped; only P004 rows remain
+        assert "P001" not in result.output
+        assert "P004" in result.output
+
+    def test_max_cell_len(self):
+        result = runner.invoke(app, ["view", TEST_CSV, "--max-cell-len", "5"])
+        assert result.exit_code == 0
+        # "Control" (7 chars) should be truncated to "Contr..."
+        assert "Contr..." in result.output
+        # "P001" (4 chars) fits within 5, should appear as-is
+        assert "P001" in result.output
+
+    def test_no_output_flag(self):
+        result = runner.invoke(app, ["view", TEST_CSV, "-o", "csv"])
+        assert result.exit_code != 0
+
+    def test_truncation_indicator(self):
+        """With no --limit and more than 20 rows, truncation '...' should appear.
+        Our test.csv only has 8 rows, so no truncation."""
+        result = runner.invoke(app, ["view", TEST_CSV])
+        assert result.exit_code == 0
+        # 8 rows < 20 default limit, so no truncation
+        lines_with_ellipsis = [l for l in result.output.splitlines() if l.strip() == "...   ...   ...   ...   ...   ..."]
+        assert len(lines_with_ellipsis) == 0
+
+
+class TestCat:
+    def test_basic_outputs_csv(self):
+        result = runner.invoke(app, ["cat", TEST_CSV])
+        assert result.exit_code == 0
+        # Should output in CSV format (the input format), not a Rich table
+        assert "Participant_ID," in result.output or "Participant_ID\t" in result.output or "P001" in result.output
+
+    def test_output_format_csv(self):
+        result = runner.invoke(app, ["cat", TEST_CSV, "-o", "csv"])
+        assert result.exit_code == 0
+        lines = result.output.strip().splitlines()
+        # CSV header
+        assert "Participant_ID" in lines[0]
+        # Should have header + 8 data rows
+        assert len(lines) == 9
+
+    def test_output_format_tsv(self):
+        result = runner.invoke(app, ["cat", TEST_CSV, "-o", "tsv"])
+        assert result.exit_code == 0
+        lines = result.output.strip().splitlines()
+        assert "\t" in lines[0]
+
+    def test_no_rich_table(self):
+        """cat without -o should NOT produce a Rich formatted table."""
+        result = runner.invoke(app, ["cat", TEST_CSV])
+        assert result.exit_code == 0
+        # Rich tables use box-drawing chars; CSV output won't
+        assert "─" not in result.output
+
+
+class TestSql:
+    def test_basic_table_output(self):
+        result = runner.invoke(app, ["sql", "SELECT * FROM t WHERE Status = 'Baseline'", TEST_CSV])
+        assert result.exit_code == 0
+        assert "Baseline" in result.output
+        # Should show as a table by default (no -o)
+        assert "Active" not in result.output
+
+    def test_with_output_format(self):
+        result = runner.invoke(app, ["sql", "SELECT Participant_ID, Status FROM t", TEST_CSV, "-o", "csv"])
+        assert result.exit_code == 0
+        lines = result.output.strip().splitlines()
+        assert "Participant_ID" in lines[0]
+        assert "Status" in lines[0]
+
+    def test_limit(self):
+        result = runner.invoke(app, ["sql", "SELECT * FROM t", TEST_CSV, "--limit", "2"])
+        assert result.exit_code == 0
+        # Should have limited rows
+        count = sum(1 for line in result.output.splitlines() if "P00" in line)
+        assert count <= 2

tab_cli-0.1.2/CHANGELOG.md

@@ -1,5 +0,0 @@
- - 0.1.2:
-   - Bugfix on reading directories.
- - 0.1.1:
-   - Better credential handling for Azure Blob Storage and Google Cloud Storage.
- - 0.1.0: Initial release

tab_cli-0.1.2/README.md

@@ -1,3 +0,0 @@
-# tab
-
-A CLI tool for viewing, querying, and converting tabular data files. Supports AWS / Azure / Google Cloud Storage URLs.