chage iterable typing to sequence; improve tests

README.md

@@ -141,10 +141,15 @@ df
 
 ## Changelog
 
+### 1.1.1 (2023-11-25)
+
+- Change `Iterable` typing to `Sequence` to account for order and allow multiple passes over data.
+- Improve tests.
+
 ### 1.1.0 (2023-11-25)
 
-- Fix read function return type: now return list of lists instead of generator
+- Fix read function return type: now return list of lists instead of generator.
 
 ### 1.0.0 (2023-11-25)
 
-- Initial release
+- Initial release.

csvmeta/__init__.py

@@ -2,4 +2,4 @@
 from csvmeta.write import DEFAULT_DIALECT, write
 
 __all__ = ["read", "metadata", "write", "DEFAULT_DIALECT"]
-__version__ = "1.1.0"
+__version__ = "1.1.1"

csvmeta/read.py

@@ -1,12 +1,12 @@
 import csv
 import json
 import os
-from typing import Iterable, Union
+from typing import Sequence, Union
 
 from csvmeta.write import DEFAULT_DIALECT
 
 
-def read(dirpath: str) -> Iterable[Iterable[str]]:
+def read(dirpath: str) -> Sequence[Sequence[str]]:
     """
     Read CSV data from the specified directory path.
 
@@ -19,18 +19,16 @@ def read(dirpath: str) -> Iterable[Iterable[str]]:
 
     Returns
     -------
-    Iterable[Iterable[str]]
-        An iterable of rows, where each row is an iterable of string values. The header is always returned as the first row.
+    Sequence[Sequence[str]]
+        A sequence of rows, where each row is a sequence of string values. The header is always returned as the first row.
     """
     meta = metadata(dirpath)
     dialect = meta.get("dialect", DEFAULT_DIALECT)
 
-    reader = _read_csv(dirpath, dialect)
+    return _read_csv(dirpath, dialect)
 
-    return list(reader)
 
-
-def _read_csv(dirpath: str, dialect: Union[str, dict]) -> Iterable[Iterable[str]]:
+def _read_csv(dirpath: str, dialect: Union[str, dict]) -> Sequence[Sequence[str]]:
     """
     Internal function to read a CSV file using the specified dialect.
 
@@ -43,17 +41,17 @@ def _read_csv(dirpath: str, dialect: Union[str, dict]) -> Iterable[Iterable[str]
 
     Returns
     -------
-    Iterable[Iterable[str]]
-        An iterable of rows, where each row is an iterable of string values.
+    Sequence[Sequence[str]]
+        A sequence of rows, where each row is a sequence of string values.
     """
     csv_filepath = os.path.join(dirpath, "data.csv")
     with open(csv_filepath, newline="") as csvfile:
         if isinstance(dialect, str):
             reader = csv.reader(csvfile, dialect=dialect)
         else:
             reader = csv.reader(csvfile, **dialect)
-        for row in reader:
-            yield row
+
+        return list(reader)
 
 
 def metadata(dirpath: str) -> dict:

csvmeta/write.py

@@ -1,15 +1,15 @@
 import csv
 import json
 import os
-from typing import Any, Iterable, Union
+from typing import Any, Sequence, Union
 
 _DialectType = Union[str, dict]
 
 DEFAULT_DIALECT = "unix"
 
 
 def write(
-    dirpath: str, rowsdata: Iterable[Iterable[Any]], dialect: _DialectType = DEFAULT_DIALECT, **additional_metadata
+    dirpath: str, rowsdata: Sequence[Sequence[Any]], dialect: _DialectType = DEFAULT_DIALECT, **additional_metadata
 ) -> None:
     """
     Write CSV data and optional metadata.
@@ -18,7 +18,7 @@ def write(
     ----------
     dirpath : str
         The directory path where the CSV file and metadata will be saved.
-    rowsdata : Iterable[Iterable[Any]]
+    rowsdata : Sequence[Sequence[Any]]
         The data to be written to the CSV file.
     dialect : str | dict, optional
         The dialect to be used for writing the CSV file, by default DEFAULT_DIALECT (unix). See https://docs.python.org/3/library/csv.html#csv-fmt-params for valid parameters and more information.
@@ -32,15 +32,15 @@ def write(
     _write_metadata(dirpath, dialect, **additional_metadata)
 
 
-def _write_csv(dirpath: str, rowsdata: Iterable[Iterable[Any]], dialect: _DialectType = DEFAULT_DIALECT) -> None:
+def _write_csv(dirpath: str, rowsdata: Sequence[Sequence[Any]], dialect: _DialectType = DEFAULT_DIALECT) -> None:
     """
     Internal function to write data to a CSV file.
 
     Parameters
     ----------
     dirpath : str
         The directory path where the CSV file will be saved.
-    rowsdata : Iterable[Iterable[Any]]
+    rowsdata : Sequence[Sequence[Any]]
         The data to be written to the CSV file.
     dialect : str | dict, optional
         The dialect to be used for writing the CSV file, by default DEFAULT_DIALECT.

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "csvmeta"
-version = "1.1.0"
+version = "1.1.1"
 description = "Lightweight csv read/write, keeping track of csv dialect and other metadata."
 authors = [{ name = "Olivier Binette", email = "[email protected]" }]
 readme = "README.md"

tests/conftest.py

@@ -5,11 +5,10 @@
 DIALECTS_LIST = [
     "excel",
     "unix",
-    {"delimiter": "|", "quotechar": "'", "quoting": csv.QUOTE_NONE, "lineterminator": "\n"},
+    {"delimiter": "|", "escapechar": "\\", "quotechar": "'", "quoting": csv.QUOTE_NONE, "lineterminator": "\n"},
     {
         "delimiter": ",",
-        "doublequote": False,
-        "escapechar": "\\",
+        "doublequote": True,
         "lineterminator": "\r\n",
         "quotechar": '"',
         "quoting": 0,  # Minimal quoting
@@ -39,7 +38,16 @@ def example_schema():
 @pytest.fixture
 def example_csv_data():
     # Return example CSV data
-    return [["Header1", "Header2"], ["Value1", "Value2"], ["Value3", "Value4"]]
+    return [
+        ["Header1", "Header2"],
+        ["Value1", None],
+        [0, 2 + 3j],
+        [True, False],
+        [1.0, Exception],
+        [dict(a=1, b=2), [3, 4]],
+        [{1, "a"}, (1, 2, 3)],
+        [csv.Dialect, csv.excel],
+    ]
 
 
 @pytest.fixture

tests/unit/test_read.py

@@ -31,7 +31,7 @@ def test_read_csv(tmpdir, example_csv_data, example_metadata, dialect):
 
     # Verify the read data matches the example data
     for expected_row, row in zip(example_csv_data, result):
-        assert list(row) == expected_row
+        assert list(row) == [str(x) if x is not None else "" for x in expected_row]
 
 
 def test_metadata(tmpdir, example_metadata):