csvsmith 0.7.2__tar.gz → 0.8.0__tar.gz

{csvsmith-0.7.2/src/csvsmith.egg-info → csvsmith-0.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: csvsmith
-Version: 0.7.2
+Version: 0.8.0
 Summary: Small CSV utilities: row deduplication, classification, row filtering, and CLI helpers.
 Author-email: Eiichi YAMAMOTO <info@yeiichi.com>
 License: MIT License
@@ -39,6 +39,9 @@ Requires-Python: >=3.10
 Description-Content-Type: text/x-rst
 License-File: LICENSE
 Requires-Dist: openpyxl>=3.1
+Provides-Extra: docs
+Requires-Dist: sphinx<9,>=8; extra == "docs"
+Requires-Dist: furo>=2024.8.6; extra == "docs"
 Dynamic: license-file
 
 csvsmith
@@ -84,6 +87,7 @@ Features
 - Convert Excel workbooks to CSV
 - Move files by suffix
 - Find matching values inside CSV files
+- Concatenate CSV files with identical headers
 - Use the tools either from Python or from the command line
 
 Installation
@@ -111,17 +115,11 @@ You can use the library from Python:
 
 .. code-block:: python
 
-   from csvsmith import (
-       clean_numeric,
-       dedupe_with_report,
-       excel_to_csv,
-       find_matches_in_csv,
-       move_by_suffix,
-   )
+   from csvsmith.utils.clean_numeric import clean_currency_numeric
 
-   print(clean_numeric("1,234.56"))
+   print(clean_currency_numeric("$1,234.56"))
 
-Or use the command-line interface:
+For command-line usage, use single quotes around values containing ``$``:
 
 .. code-block:: console
 
@@ -138,6 +136,17 @@ Clean numeric values:
 
    csvsmith clean-numeric "1,234.56" --sep "," --decimal "."
 
+Clean currency-prefixed numeric values:
+
+.. code-block:: console
+
+   csvsmith clean-currency-numeric '$1,234.56' --sep "," --decimal "."
+
+.. note::
+
+   Use single quotes for values containing ``$``. Double quotes may trigger
+   shell expansion and change the input unexpectedly.
+
 Filter rows in a CSV:
 
 .. code-block:: console
@@ -174,6 +183,12 @@ Find matches in a CSV:
 
    csvsmith find-matches input.csv target --ignore-case --ignore-whitespace
 
+Concatenate CSV files:
+
+.. code-block:: console
+
+   csvsmith strict-concat file1.csv file2.csv -o combined.csv
+
 Find matches in a CSV
 ---------------------
 
@@ -233,7 +248,7 @@ File and conversion helpers:
 
 .. code-block:: python
 
-   from csvsmith import excel_to_csv, move_by_suffix
+   from csvsmith import excel_to_csv, move_by_suffix, strict_concat_rows, save_csv
 
 String comparison utilities:
 

{csvsmith-0.7.2 → csvsmith-0.8.0}/README.rst

@@ -41,6 +41,7 @@ Features
 - Convert Excel workbooks to CSV
 - Move files by suffix
 - Find matching values inside CSV files
+- Concatenate CSV files with identical headers
 - Use the tools either from Python or from the command line
 
 Installation
@@ -68,17 +69,11 @@ You can use the library from Python:
 
 .. code-block:: python
 
-   from csvsmith import (
-       clean_numeric,
-       dedupe_with_report,
-       excel_to_csv,
-       find_matches_in_csv,
-       move_by_suffix,
-   )
+   from csvsmith.utils.clean_numeric import clean_currency_numeric
 
-   print(clean_numeric("1,234.56"))
+   print(clean_currency_numeric("$1,234.56"))
 
-Or use the command-line interface:
+For command-line usage, use single quotes around values containing ``$``:
 
 .. code-block:: console
 
@@ -95,6 +90,17 @@ Clean numeric values:
 
    csvsmith clean-numeric "1,234.56" --sep "," --decimal "."
 
+Clean currency-prefixed numeric values:
+
+.. code-block:: console
+
+   csvsmith clean-currency-numeric '$1,234.56' --sep "," --decimal "."
+
+.. note::
+
+   Use single quotes for values containing ``$``. Double quotes may trigger
+   shell expansion and change the input unexpectedly.
+
 Filter rows in a CSV:
 
 .. code-block:: console
@@ -131,6 +137,12 @@ Find matches in a CSV:
 
    csvsmith find-matches input.csv target --ignore-case --ignore-whitespace
 
+Concatenate CSV files:
+
+.. code-block:: console
+
+   csvsmith strict-concat file1.csv file2.csv -o combined.csv
+
 Find matches in a CSV
 ---------------------
 
@@ -190,7 +202,7 @@ File and conversion helpers:
 
 .. code-block:: python
 
-   from csvsmith import excel_to_csv, move_by_suffix
+   from csvsmith import excel_to_csv, move_by_suffix, strict_concat_rows, save_csv
 
 String comparison utilities:
 

{csvsmith-0.7.2 → csvsmith-0.8.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "csvsmith"
-version = "0.7.2"
+version = "0.8.0"
 description = "Small CSV utilities: row deduplication, classification, row filtering, and CLI helpers."
 readme = "README.rst"
 requires-python = ">=3.10"
@@ -35,6 +35,12 @@ dependencies = [
   "openpyxl>=3.1",
 ]
 
+[project.optional-dependencies]
+docs = [
+  "sphinx>=8,<9",
+  "furo>=2024.8.6",
+]
+
 [project.urls]
 Homepage = "https://github.com/yeiichi/csvsmith"
 Repository = "https://github.com/yeiichi/csvsmith"

{csvsmith-0.7.2 → csvsmith-0.8.0}/src/csvsmith/__init__.py

@@ -16,6 +16,8 @@ Public API:
 - Relation
 - Result
 - analyze_pair
+- strict_concat_rows
+- save_csv
 
 Compatibility aliases:
 - CSVCleaner
@@ -28,10 +30,11 @@ Submodules:
 - csvsmith.filter_rows
 - csvsmith.excel2csv
 - csvsmith.move_files
+- csvsmith.strict_concat
 - csvsmith.cli (CLI entrypoint)
 """
 
-__version__ = "0.7.2"
+__version__ = "0.8.0"
 
 from .tools.classify import CSVClassifier
 from .tools.excel2csv import excel_to_csv
@@ -43,6 +46,7 @@ from .tools.row_dedup import (
     find_duplicate_rows,
     dedupe_with_report,
 )
+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
 from .utils.io import (
@@ -68,4 +72,6 @@ __all__ = [
     "Result",
     "analyze_pair",
     "clean_numeric",
-]
+    "strict_concat_rows",
+    "save_csv",
+]

{csvsmith-0.7.2 → csvsmith-0.8.0}/src/csvsmith/cli.py

@@ -9,13 +9,14 @@ from typing import Optional, Sequence
 from . import __version__
 from .tools.classify import CSVClassifier
 from .tools.excel2csv import excel_to_csv
-from .utils.clean_numeric import clean_numeric
+from .utils.clean_numeric import clean_currency_numeric, clean_numeric
 from .tools.filter_rows import DropRowsBySubstring
 from .tools.move_files import move_by_suffix, normalize_suffixes
 from .tools.row_dedup import (
     dedupe_with_report,
     find_duplicate_rows,
 )
+from .tools.strict_concat import save_csv, strict_concat_rows
 from .tools.find_matches_in_csv import find_matches_in_csv
 from .utils.distance import analyze_pair
 from .utils.io import read_csv_rows, write_csv_rows
@@ -149,6 +150,21 @@ def cmd_clean_numeric(args: argparse.Namespace) -> int:
     return 0
 
 
+def cmd_clean_currency_numeric(args: argparse.Namespace) -> int:
+    try:
+        cleaned = clean_currency_numeric(
+            args.value,
+            sep=args.sep,
+            decimal=args.decimal,
+            relaxed=args.relaxed,
+        )
+        print(cleaned)
+    except ValueError as e:
+        print(f"Error: {e}", file=sys.stderr)
+        return 1
+    return 0
+
+
 def cmd_find_matches(args: argparse.Namespace) -> int:
     results = find_matches_in_csv(
         args.input,
@@ -165,6 +181,23 @@ def cmd_find_matches(args: argparse.Namespace) -> int:
     return 0
 
 
+def cmd_strict_concat(args: argparse.Namespace) -> int:
+    input_dir = Path(args.input_dir)
+    if not input_dir.is_dir():
+        print(f"Error: input directory not found: {input_dir}", file=sys.stderr)
+        return 1
+
+    try:
+        rows = strict_concat_rows(input_dir)
+        save_csv(rows, args.output)
+    except Exception as e:
+        print(f"Error: {e}", file=sys.stderr)
+        return 1
+
+    print(f"Wrote concatenated CSV to: {args.output}")
+    return 0
+
+
 def _add_find_matches_parser(subparsers) -> None:
     parser = subparsers.add_parser("find-matches", help="Find matches in a CSV file.")
     parser.add_argument("input", help="Input CSV file.")
@@ -175,6 +208,16 @@ def _add_find_matches_parser(subparsers) -> None:
     parser.set_defaults(func=cmd_find_matches)
 
 
+def _add_strict_concat_parser(subparsers) -> None:
+    parser = subparsers.add_parser(
+        "strict-concat",
+        help="Concatenate CSVs in a directory only when all headers match exactly.",
+    )
+    parser.add_argument("input_dir", help="Directory containing CSV files to concatenate.")
+    parser.add_argument("-o", "--output", required=True, help="Output CSV file path.")
+    parser.set_defaults(func=cmd_strict_concat)
+
+
 def _add_row_duplicates_parser(subparsers) -> None:
     parser = subparsers.add_parser("row-duplicates", help="Find duplicate rows in a CSV.")
     parser.add_argument("input", help="Input CSV file.")
@@ -272,6 +315,22 @@ def _add_clean_numeric_parser(subparsers) -> None:
     parser.set_defaults(func=cmd_clean_numeric)
 
 
+def _add_clean_currency_numeric_parser(subparsers) -> None:
+    parser = subparsers.add_parser(
+        "clean-currency-numeric",
+        help="Clean and convert a currency-prefixed numeric string to float.",
+    )
+    parser.add_argument("value", help="Numeric value to clean.")
+    parser.add_argument("--sep", default=",", help="Group separator (default: ,).")
+    parser.add_argument("--decimal", default=".", help="Decimal separator (default: .).")
+    parser.add_argument(
+        "--relaxed",
+        action="store_true",
+        help="Return the original input when it is not numeric.",
+    )
+    parser.set_defaults(func=cmd_clean_currency_numeric)
+
+
 def build_parser() -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser(
         prog="csvsmith",
@@ -286,6 +345,7 @@ def build_parser() -> argparse.ArgumentParser:
 
     _add_row_duplicates_parser(subparsers)
     _add_find_matches_parser(subparsers)
+    _add_strict_concat_parser(subparsers)
     _add_dedupe_parser(subparsers)
     _add_classify_parser(subparsers)
     _add_move_files_parser(subparsers)
@@ -293,6 +353,7 @@ def build_parser() -> argparse.ArgumentParser:
     _add_drop_rows_parser(subparsers)
     _add_string_distance_parser(subparsers)
     _add_clean_numeric_parser(subparsers)
+    _add_clean_currency_numeric_parser(subparsers)
 
     return parser
 

csvsmith-0.8.0/src/csvsmith/tools/strict_concat.py

@@ -0,0 +1,101 @@
+import csv
+from collections.abc import Iterable
+from pathlib import Path
+
+
+def find_csvs(csv_dir: Path | str) -> list[Path]:
+    """
+    Find all CSV files in the specified directory.
+
+    This function searches for all files with a ``.csv`` extension in the given
+    directory and returns a sorted list of their paths.
+
+    :param csv_dir: The directory to search for CSV files. This can be provided
+        as either a ``Path`` object or a string representing the path to the
+        directory.
+    :type csv_dir: Path | str
+    :return: Sorted list of paths to all ``.csv`` files found in the specified
+        directory.
+    :rtype: list[Path]
+    """
+    return sorted(Path(csv_dir).glob("*.csv"))
+
+
+def read_header(csv_path: Path) -> list[str]:
+    """
+    Reads the header row of a given CSV file.
+
+    This function opens a CSV file located at the specified path, reads its first
+    row, and returns it as a list of strings. The file is assumed to be encoded
+    in UTF-8 with optional BOM (Byte Order Mark). If the CSV file is empty, a
+    ValueError is raised indicating the problem. The CSV file is expected to be
+    opened in read mode with no newline translation.
+
+    :param csv_path: The path to the CSV file to read the header from.
+    :type csv_path: Path
+    :return: A list of strings representing the header row of the CSV file.
+    :rtype: list[str]
+    :raises ValueError: If the CSV file is empty and no header can be retrieved.
+    """
+    with csv_path.open(encoding="utf-8-sig", newline="") as f:
+        reader = csv.reader(f)
+        try:
+            return next(reader)
+        except StopIteration as e:
+            raise ValueError(f"Empty CSV: {csv_path}") from e
+
+
+def _validate_headers_match(csv_paths: list[Path]) -> list[str]:
+    """
+    Validates that the headers of all provided CSV files match each other. The function compares the
+    header of each CSV file in the input list against the header of the first file. If a mismatch
+    is encountered, a ValueError is raised indicating the problematic file. The function returns
+    the header of the first file if all headers are consistent.
+
+    :param csv_paths: A list of Path objects representing the file paths to the CSV files to validate.
+    :type csv_paths: list[Path]
+    :return: A list of strings representing the matched header of the first CSV file.
+    :rtype: list[str]
+    """
+    expected_header = read_header(csv_paths[0])
+    for csv_path in csv_paths[1:]:
+        if read_header(csv_path) != expected_header:
+            raise ValueError(f"Header mismatch: {csv_path}")
+    return expected_header
+
+
+def strict_concat_rows(csv_dir: Path | str) -> list[list[str]]:
+    """
+    Concatenates rows from multiple CSV files into a list of lists of strings, ensuring
+    the headers across all CSV files match. The output includes a new column indicating
+    the file stem.
+
+    :param csv_dir: Directory containing the CSV files or a specific path to a CSV file.
+    :type csv_dir: Path | str
+    :return: A list of lists, where each inner list represents a row from the concatenated
+        CSV files. The first row contains the headers, including a "file_stem" column.
+    :rtype: list[list[str]]
+    :raises FileNotFoundError: If no CSV files are found in the provided directory.
+    """
+    csv_paths = find_csvs(csv_dir)
+    if not csv_paths:
+        raise FileNotFoundError(f"No CSV files found in: {csv_dir}")
+    
+    expected_header = _validate_headers_match(csv_paths)
+    out_rows: list[list[str]] = [["file_stem", *expected_header]]
+    
+    for csv_path in csv_paths:
+        with csv_path.open(encoding="utf-8-sig", newline="") as f:
+            reader = csv.reader(f)
+            next(reader)  # skip header
+            for row in reader:
+                out_rows.append([csv_path.stem, *row])
+    return out_rows
+
+
+def save_csv(rows: Iterable[list[str]], out_path: Path | str) -> None:
+    """Write rows to out_path."""
+    out_path = Path(out_path)
+    with out_path.open("w", encoding="utf-8", newline="") as f:
+        writer = csv.writer(f)
+        writer.writerows(rows)

csvsmith-0.8.0/src/csvsmith/utils/clean_numeric.py

@@ -0,0 +1,124 @@
+import re
+from typing import Any
+
+NON_BREAKING_SPACE = "\xa0"
+SEPARATOR_PATTERN = re.compile(r"[ _\xa0]")
+NUMBER_PATTERN = re.compile(r"^-?(?:\d+|\d*\.\d+)$")
+INVALID_NUMBER_MESSAGE = "Could not convert {value!r} to a valid number."
+CURRENCY_PREFIX_PATTERN = re.compile(r"^[\$€£¥₹]")
+
+
+def strip_currency_prefix(value: Any) -> Any:
+    """
+    Remove a single common currency symbol from the start of a value.
+    """
+    text = str(value).strip()
+    if text and CURRENCY_PREFIX_PATTERN.match(text):
+        return text[1:].strip()
+    return value
+
+
+def _normalize_numeric_text(value: Any, *, sep: str, decimal: str) -> str:
+    """
+    Normalize a numeric text string for consistent formatting.
+
+    Converts a given value to a string representation and ensures normalization of numeric formatting,
+    such as removing group separators, converting localized decimal separators, and handling negative
+    values enclosed in parentheses.
+    """
+    numeric_text = str(value).strip()
+
+    if numeric_text.startswith("(") and numeric_text.endswith(")"):
+        numeric_text = f"-{numeric_text[1:-1]}"
+
+    if sep:
+        numeric_text = numeric_text.replace(sep, "")
+
+    if decimal != ".":
+        numeric_text = numeric_text.replace(decimal, ".")
+
+    return numeric_text
+
+
+def _has_valid_grouping(numeric_text: str, *, decimal: str) -> bool:
+    """
+    Checks whether a numeric text string has valid grouping based on a specified decimal character.
+    """
+    if not numeric_text:
+        return False
+
+    unsigned_text = numeric_text[1:] if numeric_text.startswith("-") else numeric_text
+
+    if unsigned_text.count(decimal) > 1:
+        return False
+
+    integer_text, _, fraction_text = unsigned_text.partition(decimal)
+
+    if not integer_text and not fraction_text:
+        return False
+
+    for part in (integer_text, fraction_text):
+        if not part:
+            continue
+        if part.startswith("_") or part.endswith("_"):
+            return False
+        if part.startswith(" ") or part.endswith(" "):
+            return False
+        if part.startswith(NON_BREAKING_SPACE) or part.endswith(NON_BREAKING_SPACE):
+            return False
+        if "__" in part or "  " in part or NON_BREAKING_SPACE * 2 in part:
+            return False
+
+    stripped_text = SEPARATOR_PATTERN.sub("", numeric_text)
+    return bool(NUMBER_PATTERN.fullmatch(stripped_text))
+
+
+def _strip_group_separators(numeric_text: str) -> str:
+    return SEPARATOR_PATTERN.sub("", numeric_text)
+
+
+def _invalid_number_error(value: Any) -> ValueError:
+    return ValueError(INVALID_NUMBER_MESSAGE.format(value=value))
+
+
+def clean_numeric(
+        value: Any, *, sep: str = ",", decimal: str = ".", relaxed: bool = False
+) -> float | Any:
+    """
+    Cleans and converts a given input to a float by normalizing its numeric representation.
+    """
+    if value is None:
+        return 0.0
+
+    normalized_text = _normalize_numeric_text(value, sep=sep, decimal=decimal)
+
+    if not _has_valid_grouping(normalized_text, decimal=decimal):
+        if relaxed:
+            return value
+        raise _invalid_number_error(value)
+
+    candidate_text = _strip_group_separators(normalized_text)
+
+    try:
+        return float(candidate_text)
+    except ValueError as exc:
+        if relaxed:
+            return value
+        raise _invalid_number_error(value) from exc
+
+
+def clean_currency_numeric(
+        value: Any, *, sep: str = ",", decimal: str = ".", relaxed: bool = False
+) -> float | Any:
+    """
+    Cleans and converts a currency-prefixed numeric string to a float.
+    """
+    if value is None:
+        return 0.0
+
+    return clean_numeric(
+        strip_currency_prefix(value),
+        sep=sep,
+        decimal=decimal,
+        relaxed=relaxed,
+    )

{csvsmith-0.7.2 → csvsmith-0.8.0/src/csvsmith.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: csvsmith
-Version: 0.7.2
+Version: 0.8.0
 Summary: Small CSV utilities: row deduplication, classification, row filtering, and CLI helpers.
 Author-email: Eiichi YAMAMOTO <info@yeiichi.com>
 License: MIT License
@@ -39,6 +39,9 @@ Requires-Python: >=3.10
 Description-Content-Type: text/x-rst
 License-File: LICENSE
 Requires-Dist: openpyxl>=3.1
+Provides-Extra: docs
+Requires-Dist: sphinx<9,>=8; extra == "docs"
+Requires-Dist: furo>=2024.8.6; extra == "docs"
 Dynamic: license-file
 
 csvsmith
@@ -84,6 +87,7 @@ Features
 - Convert Excel workbooks to CSV
 - Move files by suffix
 - Find matching values inside CSV files
+- Concatenate CSV files with identical headers
 - Use the tools either from Python or from the command line
 
 Installation
@@ -111,17 +115,11 @@ You can use the library from Python:
 
 .. code-block:: python
 
-   from csvsmith import (
-       clean_numeric,
-       dedupe_with_report,
-       excel_to_csv,
-       find_matches_in_csv,
-       move_by_suffix,
-   )
+   from csvsmith.utils.clean_numeric import clean_currency_numeric
 
-   print(clean_numeric("1,234.56"))
+   print(clean_currency_numeric("$1,234.56"))
 
-Or use the command-line interface:
+For command-line usage, use single quotes around values containing ``$``:
 
 .. code-block:: console
 
@@ -138,6 +136,17 @@ Clean numeric values:
 
    csvsmith clean-numeric "1,234.56" --sep "," --decimal "."
 
+Clean currency-prefixed numeric values:
+
+.. code-block:: console
+
+   csvsmith clean-currency-numeric '$1,234.56' --sep "," --decimal "."
+
+.. note::
+
+   Use single quotes for values containing ``$``. Double quotes may trigger
+   shell expansion and change the input unexpectedly.
+
 Filter rows in a CSV:
 
 .. code-block:: console
@@ -174,6 +183,12 @@ Find matches in a CSV:
 
    csvsmith find-matches input.csv target --ignore-case --ignore-whitespace
 
+Concatenate CSV files:
+
+.. code-block:: console
+
+   csvsmith strict-concat file1.csv file2.csv -o combined.csv
+
 Find matches in a CSV
 ---------------------
 
@@ -233,7 +248,7 @@ File and conversion helpers:
 
 .. code-block:: python
 
-   from csvsmith import excel_to_csv, move_by_suffix
+   from csvsmith import excel_to_csv, move_by_suffix, strict_concat_rows, save_csv
 
 String comparison utilities:
 

{csvsmith-0.7.2 → csvsmith-0.8.0}/src/csvsmith.egg-info/SOURCES.txt

@@ -16,6 +16,7 @@ src/csvsmith/tools/filter_rows.py
 src/csvsmith/tools/find_matches_in_csv.py
 src/csvsmith/tools/move_files.py
 src/csvsmith/tools/row_dedup.py
+src/csvsmith/tools/strict_concat.py
 src/csvsmith/utils/__init__.py
 src/csvsmith/utils/clean_numeric.py
 src/csvsmith/utils/distance.py
@@ -30,4 +31,5 @@ tests/test_find_matches_in_csv.py
 tests/test_move_files.py
 tests/test_normalize.py
 tests/test_row_dedup.py
+tests/test_strict_concat.py
 tests/test_string_distance.py

csvsmith-0.8.0/src/csvsmith.egg-info/requires.txt

@@ -0,0 +1,5 @@
+openpyxl>=3.1
+
+[docs]
+sphinx<9,>=8
+furo>=2024.8.6

{csvsmith-0.7.2 → csvsmith-0.8.0}/tests/test_clean_numeric.py

@@ -1,5 +1,12 @@
 import pytest
-from csvsmith.utils.clean_numeric import clean_numeric
+from csvsmith.cli import build_parser, main
+from csvsmith.utils.clean_numeric import clean_currency_numeric, clean_numeric
+
+
+def test_main_help():
+    with pytest.raises(SystemExit) as excinfo:
+        main(["--help"])
+    assert excinfo.value.code == 0
 
 
 def test_clean_numeric_with_valid_integer_string() -> None:
@@ -34,3 +41,28 @@ def test_clean_numeric_with_multiple_decimal_points_raises_valueerror() -> None:
 
 def test_clean_numeric_with_none_value() -> None:
     assert clean_numeric(None) == 0.0
+
+
+def test_clean_currency_numeric_with_currency_prefix() -> None:
+    assert clean_currency_numeric("$1,000") == 1000.0
+
+
+def test_clean_currency_numeric_with_euro_prefix() -> None:
+    assert clean_currency_numeric("€1,000.50") == 1000.5
+
+
+def test_clean_numeric_still_rejects_currency_prefix() -> None:
+    with pytest.raises(ValueError, match=r"Could not convert '\$1,000'.*"):
+        clean_numeric("$1,000")
+
+
+def test_cli_parses_clean_currency_numeric_command():
+    parser = build_parser()
+    args = parser.parse_args(
+        ["clean-currency-numeric", "$1,234.56", "--sep", ",", "--decimal", "."]
+    )
+
+    assert args.command == "clean-currency-numeric"
+    assert args.value == "$1,234.56"
+    assert args.sep == ","
+    assert args.decimal == "."

{csvsmith-0.7.2 → csvsmith-0.8.0}/tests/test_cli.py

@@ -138,12 +138,22 @@ def test_cli_parses_clean_numeric_command():
     assert args.decimal == "."
 
 
-def test_cli_parses_clean_numeric_command_with_relaxed_mode():
+def test_cli_parses_clean_currency_numeric_command():
     parser = build_parser()
     args = parser.parse_args(
-        ["clean-numeric", "not-a-number", "--relaxed"]
+        ["clean-currency-numeric", "$1,234.56", "--sep", ",", "--decimal", "."]
     )
 
+    assert args.command == "clean-currency-numeric"
+    assert args.value == "$1,234.56"
+    assert args.sep == ","
+    assert args.decimal == "."
+
+
+def test_cli_parses_clean_numeric_command_with_relaxed_mode():
+    parser = build_parser()
+    args = parser.parse_args(["clean-numeric", "not-a-number", "--relaxed"])
+
     assert args.command == "clean-numeric"
     assert args.value == "not-a-number"
     assert args.relaxed is True
@@ -178,3 +188,12 @@ def test_cli_parses_find_matches_command():
     assert args.ignore_case is True
     assert args.ignore_whitespace is True
     assert args.no_nfkc is True
+
+
+def test_cli_parses_strict_concat_command():
+    parser = build_parser()
+    args = parser.parse_args(["strict-concat", "input_dir", "-o", "output.csv"])
+
+    assert args.command == "strict-concat"
+    assert args.input_dir == "input_dir"
+    assert args.output == "output.csv"

csvsmith-0.8.0/tests/test_strict_concat.py

@@ -0,0 +1,102 @@
+import csv
+from pathlib import Path
+
+import pytest
+
+from csvsmith.tools.strict_concat import strict_concat_rows
+
+
+def write_csv(path: Path, rows: list[list[str]]):
+    with path.open("w", newline="", encoding="utf-8") as f:
+        writer = csv.writer(f)
+        writer.writerows(rows)
+
+
+def test_strict_concat_happy(tmp_path):
+    f1 = tmp_path / "a.csv"
+    f2 = tmp_path / "b.csv"
+
+    write_csv(f1, [["id", "name"], ["1", "Alice"]])
+    write_csv(f2, [["id", "name"], ["2", "Bob"]])
+
+    rows = strict_concat_rows(tmp_path)
+
+    assert rows == [
+        ["file_stem", "id", "name"],
+        ["a", "1", "Alice"],
+        ["b", "2", "Bob"],
+    ]
+
+
+def test_strict_concat_header_mismatch(tmp_path):
+    write_csv(tmp_path / "a.csv", [["id", "name"], ["1", "Alice"]])
+    write_csv(tmp_path / "b.csv", [["id", "age"], ["2", "30"]])
+
+    with pytest.raises(ValueError, match="Header mismatch"):
+        strict_concat_rows(tmp_path)
+
+
+def test_strict_concat_empty_dir(tmp_path):
+    with pytest.raises(FileNotFoundError):
+        strict_concat_rows(tmp_path)
+
+    def test_strict_concat_with_non_csv_files(tmp_path):
+        # Create sample CSV files.
+        write_csv(tmp_path / "a.csv", [["id", "name"], ["1", "Alice"]])
+        write_csv(tmp_path / "b.csv", [["id", "name"], ["2", "Bob"]])
+
+        # Create some non-CSV files in the same directory.
+        (tmp_path / "file1.txt").write_text("This is a text file.", encoding="utf-8")
+        (tmp_path / "file2.doc").write_text("This is a Word document.", encoding="utf-8")
+
+        # Call function and check results ignore non-CSV files.
+        rows = strict_concat_rows(tmp_path)
+        assert rows == [
+            ["file_stem", "id", "name"],
+            ["a", "1", "Alice"],
+            ["b", "2", "Bob"],
+        ]
+
+
+def test_strict_concat_empty_csv(tmp_path):
+    (tmp_path / "a.csv").write_text("", encoding="utf-8")
+
+    with pytest.raises(ValueError, match="Empty CSV"):
+        strict_concat_rows(tmp_path)
+
+
+def test_header_only_files(tmp_path):
+    write_csv(tmp_path / "a.csv", [["id", "name"]])
+    write_csv(tmp_path / "b.csv", [["id", "name"]])
+
+    rows = strict_concat_rows(tmp_path)
+
+    assert rows == [["file_stem", "id", "name"]]
+
+
+def test_strict_concat_cli(tmp_path, capsys):
+    from csvsmith.cli import main
+    f1 = tmp_path / "a.csv"
+    f2 = tmp_path / "b.csv"
+    out = tmp_path / "out.csv"
+
+    write_csv(f1, [["id", "name"], ["1", "Alice"]])
+    write_csv(f2, [["id", "name"], ["2", "Bob"]])
+
+    exit_code = main(["strict-concat", str(tmp_path), "-o", str(out)])
+
+    assert exit_code == 0
+    assert out.exists()
+    
+    with out.open(encoding="utf-8") as f:
+        reader = csv.reader(f)
+        rows = list(reader)
+    
+    assert rows == [
+        ["file_stem", "id", "name"],
+        ["a", "1", "Alice"],
+        ["b", "2", "Bob"],
+    ]
+    
+    captured = capsys.readouterr()
+    assert "Wrote concatenated CSV to:" in captured.out

csvsmith-0.7.2/src/csvsmith/utils/clean_numeric.py

@@ -1,124 +0,0 @@
-import re
-from typing import Any
-
-NON_BREAKING_SPACE = "\xa0"
-SEPARATOR_PATTERN = re.compile(r"[ _\xa0]")
-NUMBER_PATTERN = re.compile(r"^-?(?:\d+|\d*\.\d+)$")
-
-
-def _normalize_numeric_text(value: Any, *, sep: str, decimal: str) -> str:
-    """
-    Normalize a numeric text string for consistent formatting.
-
-    Converts a given value to a string representation and ensures normalization of numeric formatting,
-    such as removing group separators, converting localized decimal separators, and handling negative
-    values enclosed in parentheses.
-
-    :param value: The value to be normalized, which may be of any type.
-    :type value: Any
-    :param sep: The character used as a group separator in the input value, which will be removed
-        during normalization.
-    :type sep: str
-    :param decimal: The character used as the decimal separator in the input value, which will
-        be replaced with a standard period ('.') during normalization.
-    :type decimal: str
-    :return: A normalized numeric string with consistent formatting.
-    :rtype: str
-    """
-    numeric_text = str(value).strip()
-
-    if numeric_text.startswith("(") and numeric_text.endswith(")"):
-        numeric_text = f"-{numeric_text[1:-1]}"
-
-    if sep:
-        numeric_text = numeric_text.replace(sep, "")
-
-    if decimal != ".":
-        numeric_text = numeric_text.replace(decimal, ".")
-
-    return numeric_text
-
-
-def _has_valid_grouping(numeric_text: str, *, decimal: str) -> bool:
-    """
-    Checks whether a numeric text string has valid grouping based on a specified decimal character.
-
-    This function validates the structure of the given numeric text to determine if it adheres to allowed
-    grouping conventions. It ensures the string does not contain invalid or misplaced group separators,
-    decimal points, or spacing characters.
-
-    :param numeric_text: A string representing the numeric text to be validated.
-    :type numeric_text: str
-    :param decimal: A string representing the character used as the decimal point.
-    :type decimal: str
-    :return: True if the numeric text satisfies the grouping rules; otherwise, False.
-    :rtype: bool
-    """
-    if not numeric_text:
-        return False
-
-    unsigned_text = numeric_text[1:] if numeric_text.startswith("-") else numeric_text
-
-    if unsigned_text.count(decimal) > 1:
-        return False
-
-    integer_text, _, fraction_text = unsigned_text.partition(decimal)
-
-    if not integer_text and not fraction_text:
-        return False
-
-    for part in (integer_text, fraction_text):
-        if not part:
-            continue
-        if part.startswith("_") or part.endswith("_"):
-            return False
-        if part.startswith(" ") or part.endswith(" "):
-            return False
-        if part.startswith(NON_BREAKING_SPACE) or part.endswith(NON_BREAKING_SPACE):
-            return False
-        if "__" in part or "  " in part or NON_BREAKING_SPACE * 2 in part:
-            return False
-
-    stripped_text = SEPARATOR_PATTERN.sub("", numeric_text)
-    return bool(NUMBER_PATTERN.fullmatch(stripped_text))
-
-
-def clean_numeric(
-    value: Any, *, sep: str = ",", decimal: str = ".", relaxed: bool = False
-) -> float | Any:
-    """
-    Cleans and converts a given input to a float by normalizing its numeric representation.
-    Handles separators and decimal points based on the provided arguments. If the input
-    value is invalid or cannot be converted, a ValueError is raised unless relaxed mode
-    is enabled.
-
-    :param value: The input value to be cleaned and converted.
-    :type value: Any
-    :param sep: The character used as a thousands separator in the input value. Default is ",".
-    :type sep: str
-    :param decimal: The character used as a decimal point in the input value. Default is ".".
-    :type decimal: str
-    :param relaxed: If True, return the original input when it is not numeric.
-    :type relaxed: bool
-    :return: The cleaned and converted numeric value as a float, or the original value in relaxed mode.
-    :rtype: float | Any
-    :raises ValueError: If the input value cannot be converted to a valid number and relaxed is False.
-    """
-    if value is None:
-        return 0.0
-
-    normalized_number_text = _normalize_numeric_text(value, sep=sep, decimal=decimal)
-
-    if not _has_valid_grouping(normalized_number_text, decimal=decimal):
-        if relaxed:
-            return value
-        raise ValueError(f"Could not convert {value!r} to a valid number.")
-
-    numeric_text = SEPARATOR_PATTERN.sub("", normalized_number_text)
-
-    try:
-        return float(numeric_text)
-    except ValueError as exc:
-        if relaxed:
-            return value
-        raise ValueError(f"Could not convert {value!r} to a valid number.") from exc

csvsmith-0.7.2/src/csvsmith.egg-info/requires.txt

@@ -1 +0,0 @@
-openpyxl>=3.1