csvsmith 0.7.2__tar.gz → 0.7.3__tar.gz

{csvsmith-0.7.2/src/csvsmith.egg-info → csvsmith-0.7.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: csvsmith
-Version: 0.7.2
+Version: 0.7.3
 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
@@ -111,17 +114,11 @@ 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 +135,17 @@ 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

{csvsmith-0.7.2 → csvsmith-0.7.3}/README.rst

@@ -68,17 +68,11 @@ 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 +89,17 @@ 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

{csvsmith-0.7.2 → csvsmith-0.7.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "csvsmith"
-version = "0.7.2"
+version = "0.7.3"
 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-0.7.3}/src/csvsmith/__init__.py

@@ -31,7 +31,7 @@ Submodules:
 - csvsmith.cli (CLI entrypoint)
 """
 
-__version__ = "0.7.2"
+__version__ = "0.7.3"
 
 from .tools.classify import CSVClassifier
 from .tools.excel2csv import excel_to_csv

{csvsmith-0.7.2 → csvsmith-0.7.3}/src/csvsmith/cli.py

@@ -9,7 +9,7 @@ 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 (
@@ -149,6 +149,21 @@ 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,
@@ -272,6 +287,22 @@ 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",
@@ -293,6 +324,7 @@ 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-0.7.3/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-0.7.3/src/csvsmith.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: csvsmith
-Version: 0.7.2
+Version: 0.7.3
 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
@@ -111,17 +114,11 @@ 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 +135,17 @@ 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

csvsmith-0.7.3/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-0.7.3}/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-0.7.3}/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
@@ -177,4 +187,4 @@ def test_cli_parses_find_matches_command():
     assert args.target == "target"
     assert args.ignore_case is True
     assert args.ignore_whitespace is True
-    assert args.no_nfkc is True
+    assert args.no_nfkc is True

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