csvsmith 0.11.1__tar.gz → 0.13.0__tar.gz

{csvsmith-0.11.1/src/csvsmith.egg-info → csvsmith-0.13.0}/PKG-INFO

@@ -1,37 +1,15 @@
 Metadata-Version: 2.4
 Name: csvsmith
-Version: 0.11.1
+Version: 0.13.0
 Summary: Small CSV utilities: row deduplication, classification, row filtering, and CLI helpers.
 Author-email: Eiichi YAMAMOTO <info@yeiichi.com>
-License: MIT License
-        
-        Copyright (c) 2026 Eiichi YAMAMOTO 
-        
-        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.
-        
+License-Expression: MIT
 Project-URL: Homepage, https://github.com/yeiichi/csvsmith
 Project-URL: Repository, https://github.com/yeiichi/csvsmith
 Project-URL: Documentation, https://csvsmith.readthedocs.io/en/latest/
 Keywords: csv,deduplication,data-filtering,file-organization,filtering
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: License :: OSI Approved :: MIT License
 Classifier: Intended Audience :: Developers
 Classifier: Topic :: Software Development :: Libraries
 Classifier: Topic :: Utilities

{csvsmith-0.11.1 → csvsmith-0.13.0}/pyproject.toml

@@ -1,14 +1,15 @@
 [build-system]
-requires = ["setuptools>=68.0", "wheel"]
+requires = ["setuptools>=77.0", "wheel"]
 build-backend = "setuptools.build_meta"
 
 [project]
 name = "csvsmith"
-version = "0.11.1"
+version = "0.13.0"
 description = "Small CSV utilities: row deduplication, classification, row filtering, and CLI helpers."
 readme = "README.rst"
 requires-python = ">=3.10"
-license = { file = "LICENSE" }
+license = "MIT"
+license-files = ["LICENSE"]
 
 authors = [
   { name = "Eiichi YAMAMOTO", email = "info@yeiichi.com" }
@@ -25,7 +26,6 @@ keywords = [
 classifiers = [
   "Programming Language :: Python :: 3",
   "Programming Language :: Python :: 3 :: Only",
-  "License :: OSI Approved :: MIT License",
   "Intended Audience :: Developers",
   "Topic :: Software Development :: Libraries",
   "Topic :: Utilities",

{csvsmith-0.11.1 → csvsmith-0.13.0}/src/csvsmith/__init__.py

@@ -21,6 +21,7 @@ Public API:
 - concentrate_csv
 - rehydrate_csv
 - create_sample_csv
+- strip_utf8_bom
 - DataFrame
 - build_filter
 - infer_type
@@ -42,7 +43,12 @@ Submodules:
 - csvsmith.cli (CLI entrypoint)
 """
 
-__version__ = "0.8.0"
+from importlib.metadata import PackageNotFoundError, version
+
+try:
+    __version__ = version("csvsmith")
+except PackageNotFoundError:
+    __version__ = "0.0.0"
 
 from .tools.classify import CSVClassifier
 from .tools.csv_viewer import DataFrame, build_filter, infer_type
@@ -67,6 +73,7 @@ from .tools.row_dedup import (
     dedupe_with_report,
 )
 from .tools.sample_csv import SampleCSVResult, create_sample_csv
+from .tools.strip_bom import StripBomResult, strip_utf8_bom
 from .tools.strict_concat import save_csv, strict_concat_rows
 from .utils.clean_numeric import clean_numeric
 from .utils.distance import StringDistance, Relation, Result, analyze_pair
@@ -101,6 +108,8 @@ __all__ = [
     "rehydrate_csv",
     "SampleCSVResult",
     "create_sample_csv",
+    "StripBomResult",
+    "strip_utf8_bom",
     "DataFrame",
     "build_filter",
     "infer_type",

{csvsmith-0.11.1 → csvsmith-0.13.0}/src/csvsmith/cli.py

@@ -24,6 +24,7 @@ from .tools.sample_csv import (
     DEFAULT_ROW_COUNT,
     create_sample_csv,
 )
+from .tools.strip_bom import strip_utf8_bom
 from .tools.strict_concat import save_csv, strict_concat_rows
 from .tools.find_matches_in_csv import find_matches_in_csv
 from .tools.knapsack_csv import mark_knapsack_csv
@@ -204,6 +205,18 @@ def cmd_find_matches(args: argparse.Namespace) -> int:
     return 0
 
 
+def cmd_strip_bom(args: argparse.Namespace) -> int:
+    try:
+        result = strip_utf8_bom(args.input, args.output, in_place=args.in_place)
+    except (OSError, ValueError) as e:
+        print(f"Error: {e}", file=sys.stderr)
+        return 1
+
+    status = "removed BOM" if result.removed else "no BOM found"
+    print(f"Wrote CSV to: {result.output_path} ({status})")
+    return 0
+
+
 def cmd_strict_concat(args: argparse.Namespace) -> int:
     input_dir = Path(args.input_dir)
     if not input_dir.is_dir():
@@ -388,6 +401,25 @@ def _add_find_matches_parser(subparsers) -> None:
     parser.set_defaults(func=cmd_find_matches)
 
 
+def _add_strip_bom_parser(subparsers) -> None:
+    parser = subparsers.add_parser(
+        "strip-bom",
+        help="Remove a leading UTF-8 BOM from a CSV file.",
+    )
+    parser.add_argument("input", help="Input CSV file.")
+    parser.add_argument(
+        "-o",
+        "--output",
+        help="Output CSV file (default: <input-stem>.no-bom.csv).",
+    )
+    parser.add_argument(
+        "--in-place",
+        action="store_true",
+        help="Rewrite the input file instead of writing a separate output file.",
+    )
+    parser.set_defaults(func=cmd_strip_bom)
+
+
 def _add_strict_concat_parser(subparsers) -> None:
     parser = subparsers.add_parser(
         "strict-concat",
@@ -664,6 +696,7 @@ def build_parser() -> argparse.ArgumentParser:
 
     _add_row_duplicates_parser(subparsers)
     _add_find_matches_parser(subparsers)
+    _add_strip_bom_parser(subparsers)
     _add_strict_concat_parser(subparsers)
     _add_concentrate_parser(subparsers)
     _add_rehydrate_parser(subparsers)

{csvsmith-0.11.1 → csvsmith-0.13.0}/src/csvsmith/tools/csv_viewer.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import csv
+import io
 import operator
 from pathlib import Path
 from typing import Any, Callable, TextIO
@@ -88,6 +89,28 @@ class DataFrame:
         """Return the first ``n`` rows formatted as a text table."""
         return self.render(end=n)
 
+    def to_csv(
+        self,
+        filepath: str | Path | None = None,
+        *,
+        encoding: str = "utf-8",
+    ) -> str | Path:
+        """Return the ``DataFrame`` as CSV, or write it to ``filepath``."""
+        output = io.StringIO()
+        writer = csv.writer(output)
+        writer.writerow(self.columns)
+        for index in range(len(self)):
+            writer.writerow([self._data[column][index] for column in self.columns])
+        csv_text = output.getvalue()
+
+        if filepath is None:
+            return csv_text
+
+        path = Path(filepath)
+        path.parent.mkdir(parents=True, exist_ok=True)
+        path.write_text(csv_text, encoding=encoding, newline="")
+        return path
+
     def select(self, columns: list[str]) -> DataFrame:
         """Return a new ``DataFrame`` with the selected columns."""
         missing = [column for column in columns if column not in self._data]

csvsmith-0.13.0/src/csvsmith/tools/strip_bom.py

@@ -0,0 +1,52 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from pathlib import Path
+
+
+UTF8_BOM = b"\xef\xbb\xbf"
+
+
+@dataclass(frozen=True)
+class StripBomResult:
+    input_path: Path
+    output_path: Path
+    removed: bool
+
+
+def default_output_path(csv_path: str | Path) -> Path:
+    """Return the default output path for a BOM-stripped CSV."""
+    path = Path(csv_path)
+    return path.with_name(f"{path.stem}.no-bom{path.suffix}")
+
+
+def strip_utf8_bom(
+    csv_path: str | Path,
+    output_path: str | Path | None = None,
+    *,
+    in_place: bool = False,
+) -> StripBomResult:
+    """Remove a leading UTF-8 BOM from a CSV file while preserving all other bytes."""
+    input_path = Path(csv_path)
+    if in_place and output_path is not None:
+        raise ValueError("--in-place cannot be used with --output")
+
+    if in_place:
+        resolved_output_path = input_path
+    elif output_path:
+        resolved_output_path = Path(output_path)
+    else:
+        resolved_output_path = default_output_path(input_path)
+
+    data = input_path.read_bytes()
+    removed = data.startswith(UTF8_BOM)
+    output_data = data[len(UTF8_BOM) :] if removed else data
+
+    resolved_output_path.parent.mkdir(parents=True, exist_ok=True)
+    resolved_output_path.write_bytes(output_data)
+
+    return StripBomResult(
+        input_path=input_path,
+        output_path=resolved_output_path,
+        removed=removed,
+    )

{csvsmith-0.11.1 → csvsmith-0.13.0/src/csvsmith.egg-info}/PKG-INFO

@@ -1,37 +1,15 @@
 Metadata-Version: 2.4
 Name: csvsmith
-Version: 0.11.1
+Version: 0.13.0
 Summary: Small CSV utilities: row deduplication, classification, row filtering, and CLI helpers.
 Author-email: Eiichi YAMAMOTO <info@yeiichi.com>
-License: MIT License
-        
-        Copyright (c) 2026 Eiichi YAMAMOTO 
-        
-        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.
-        
+License-Expression: MIT
 Project-URL: Homepage, https://github.com/yeiichi/csvsmith
 Project-URL: Repository, https://github.com/yeiichi/csvsmith
 Project-URL: Documentation, https://csvsmith.readthedocs.io/en/latest/
 Keywords: csv,deduplication,data-filtering,file-organization,filtering
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: License :: OSI Approved :: MIT License
 Classifier: Intended Audience :: Developers
 Classifier: Topic :: Software Development :: Libraries
 Classifier: Topic :: Utilities

{csvsmith-0.11.1 → csvsmith-0.13.0}/src/csvsmith.egg-info/SOURCES.txt

@@ -21,6 +21,7 @@ src/csvsmith/tools/move_files.py
 src/csvsmith/tools/row_dedup.py
 src/csvsmith/tools/sample_csv.py
 src/csvsmith/tools/strict_concat.py
+src/csvsmith/tools/strip_bom.py
 src/csvsmith/utils/__init__.py
 src/csvsmith/utils/clean_numeric.py
 src/csvsmith/utils/distance.py
@@ -40,4 +41,5 @@ tests/test_normalize.py
 tests/test_row_dedup.py
 tests/test_sample_csv.py
 tests/test_strict_concat.py
-tests/test_string_distance.py
+tests/test_string_distance.py
+tests/test_strip_bom.py

{csvsmith-0.11.1 → csvsmith-0.13.0}/tests/test_cli.py

@@ -1,7 +1,15 @@
+from importlib.metadata import version
+
 import pytest
+
+import csvsmith
 from csvsmith.cli import build_parser, main
 
 
+def test_package_version_matches_metadata():
+    assert csvsmith.__version__ == version("csvsmith")
+
+
 def test_main_help():
     with pytest.raises(SystemExit) as excinfo:
         main(["--help"])
@@ -190,6 +198,26 @@ def test_cli_parses_find_matches_command():
     assert args.no_nfkc is True
 
 
+def test_cli_parses_strip_bom_command():
+    parser = build_parser()
+    args = parser.parse_args(["strip-bom", "input.csv", "-o", "output.csv"])
+
+    assert args.command == "strip-bom"
+    assert args.input == "input.csv"
+    assert args.output == "output.csv"
+    assert args.in_place is False
+
+
+def test_cli_parses_strip_bom_command_in_place():
+    parser = build_parser()
+    args = parser.parse_args(["strip-bom", "input.csv", "--in-place"])
+
+    assert args.command == "strip-bom"
+    assert args.input == "input.csv"
+    assert args.output is None
+    assert args.in_place is True
+
+
 def test_cli_parses_strict_concat_command():
     parser = build_parser()
     args = parser.parse_args(["strict-concat", "input_dir", "-o", "output.csv"])

{csvsmith-0.11.1 → csvsmith-0.13.0}/tests/test_csv_viewer.py

@@ -70,6 +70,58 @@ def test_dataframe_filter_supports_numeric_comparisons(tmp_path):
     assert df["name"] == ["Alice"]
 
 
+def test_dataframe_to_csv_returns_csv_string(tmp_path):
+    source = tmp_path / "sample.csv"
+    write_csv(
+        source,
+        [
+            ["name", "score", "note"],
+            ["Alice", "10", "Hello, Tokyo"],
+            ["Bob", "8", "Line\nbreak"],
+        ],
+    )
+
+    df = DataFrame.from_csv(source).filter(build_filter("score", ">", "7"))
+
+    assert (
+        df.to_csv()
+        == 'name,score,note\r\nAlice,10,"Hello, Tokyo"\r\nBob,8,"Line\nbreak"\r\n'
+    )
+
+
+def test_dataframe_to_csv_writes_csv_file(tmp_path):
+    source = tmp_path / "sample.csv"
+    output = tmp_path / "exports" / "filtered.csv"
+    write_csv(
+        source,
+        [
+            ["name", "score", "note"],
+            ["Alice", "10", "Hello, Tokyo"],
+            ["Bob", "8", "Line\nbreak"],
+        ],
+    )
+
+    df = DataFrame.from_csv(source).filter(build_filter("score", ">", "8"))
+
+    result = df.to_csv(output)
+
+    assert result == output
+    assert output.read_text(encoding="utf-8") == "name,score,note\nAlice,10,\"Hello, Tokyo\"\n"
+
+
+def test_dataframe_to_csv_round_trips_with_from_csv(tmp_path):
+    source = tmp_path / "sample.csv"
+    output = tmp_path / "output.csv"
+    write_csv(source, [["id", "name"], ["001", "Alice"], ["002", "Bob"]])
+
+    DataFrame.from_csv(source, convert_types=False).to_csv(output)
+
+    round_tripped = DataFrame.from_csv(output, convert_types=False)
+    assert round_tripped.columns == ["id", "name"]
+    assert round_tripped["id"] == ["001", "002"]
+    assert round_tripped["name"] == ["Alice", "Bob"]
+
+
 def test_view_command_filters_and_selects_columns(tmp_path, capsys):
     source = tmp_path / "sample.csv"
     write_csv(

csvsmith-0.13.0/tests/test_strip_bom.py

@@ -0,0 +1,63 @@
+import pytest
+
+from csvsmith.cli import main
+from csvsmith.tools.strip_bom import UTF8_BOM, default_output_path, strip_utf8_bom
+
+
+def test_strip_utf8_bom_writes_default_output_without_bom(tmp_path):
+    source = tmp_path / "input.csv"
+    source.write_bytes(UTF8_BOM + b"id,name\r\n1,Alice\r\n")
+
+    result = strip_utf8_bom(source)
+
+    assert result.output_path == tmp_path / "input.no-bom.csv"
+    assert result.removed is True
+    assert result.output_path.read_bytes() == b"id,name\r\n1,Alice\r\n"
+    assert source.read_bytes().startswith(UTF8_BOM)
+
+
+def test_strip_utf8_bom_preserves_file_without_bom(tmp_path):
+    source = tmp_path / "input.csv"
+    output = tmp_path / "output.csv"
+    source.write_bytes(b"id,name\n1,Alice\n")
+
+    result = strip_utf8_bom(source, output)
+
+    assert result.output_path == output
+    assert result.removed is False
+    assert output.read_bytes() == b"id,name\n1,Alice\n"
+
+
+def test_strip_utf8_bom_can_rewrite_in_place(tmp_path):
+    source = tmp_path / "input.csv"
+    source.write_bytes(UTF8_BOM + b"id,name\n1,Alice\n")
+
+    result = strip_utf8_bom(source, in_place=True)
+
+    assert result.output_path == source
+    assert result.removed is True
+    assert source.read_bytes() == b"id,name\n1,Alice\n"
+
+
+def test_strip_utf8_bom_rejects_in_place_with_output(tmp_path):
+    source = tmp_path / "input.csv"
+    source.write_bytes(UTF8_BOM + b"id,name\n")
+
+    with pytest.raises(ValueError, match="--in-place"):
+        strip_utf8_bom(source, tmp_path / "output.csv", in_place=True)
+
+
+def test_default_output_path_handles_multi_dot_names():
+    assert default_output_path("report.final.csv").name == "report.final.no-bom.csv"
+
+
+def test_strip_bom_cli_writes_requested_output(tmp_path, capsys):
+    source = tmp_path / "input.csv"
+    output = tmp_path / "clean.csv"
+    source.write_bytes(UTF8_BOM + b"id,name\n1,Alice\n")
+
+    exit_code = main(["strip-bom", str(source), "-o", str(output)])
+
+    assert exit_code == 0
+    assert output.read_bytes() == b"id,name\n1,Alice\n"
+    assert "removed BOM" in capsys.readouterr().out