nm-tool-forge 0.2.4__tar.gz → 0.2.5__tar.gz

{nm_tool_forge-0.2.4 → nm_tool_forge-0.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nm-tool-forge
-Version: 0.2.4
+Version: 0.2.5
 Summary: Analyze MigMan log files and generate aggregated CSV, Markdown, HTML, and optional PDF reports.
 Author-email: Stefan Ewald <s.ew@outlook.de>
 License-Expression: MIT

{nm_tool_forge-0.2.4 → nm_tool_forge-0.2.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "nm-tool-forge"
-version = "0.2.4"
+version = "0.2.5"
 description = "Analyze MigMan log files and generate aggregated CSV, Markdown, HTML, and optional PDF reports."
 readme = { file = "README.md", content-type = "text/markdown" }
 requires-python = ">=3.10"

{nm_tool_forge-0.2.4 → nm_tool_forge-0.2.5}/src/csvchunking/__init__.py

@@ -1,4 +1,4 @@
 from .chunker import ChunkResult, split_csv
 
 __all__ = ["ChunkResult", "split_csv"]
-__version__ = "0.2.4"
+__version__ = "0.2.5"

{nm_tool_forge-0.2.4 → nm_tool_forge-0.2.5}/src/csvchunking/chunker.py

@@ -1,33 +1,50 @@
-import csv
-from dataclasses import dataclass
-from pathlib import Path
-
-
-@dataclass(frozen=True)
-class ChunkResult:
+import csv
+import re
+from dataclasses import dataclass
+from pathlib import Path
+
+
+@dataclass(frozen=True)
+class ChunkResult:
     input_file: Path
     output_dir: Path
-    chunk_size: int
-    data_rows_processed: int
-    files_created: int
-    output_files: tuple[Path, ...]
-
-
-def split_csv(
-    input_file: Path,
-    chunk_size: int,
-    encoding: str = "utf-8-sig",
-) -> ChunkResult:
-    if not Path(input_file).is_file():
-        raise FileNotFoundError(f"Input file not found: {input_file}")
-    if chunk_size <= 0:
-        raise ValueError("chunk_size must be greater than 0")
+    chunk_size: int
+    data_rows_processed: int
+    files_created: int
+    output_files: tuple[Path, ...]
+
+
+def cleanup_existing_chunks(output_dir: Path, input_file: Path) -> None:
+    output_dir = Path(output_dir)
+    if not output_dir.exists():
+        return
+
+    input_file = Path(input_file)
+    pattern = re.compile(
+        rf"^{re.escape(input_file.stem)}_\d{{2,}}{re.escape(input_file.suffix)}$"
+    )
+
+    for existing_file in output_dir.iterdir():
+        if existing_file.is_file() and pattern.fullmatch(existing_file.name):
+            existing_file.unlink()
+
+
+def split_csv(
+    input_file: Path,
+    chunk_size: int,
+    encoding: str = "utf-8-sig",
+) -> ChunkResult:
+    if not Path(input_file).is_file():
+        raise FileNotFoundError(f"Input file not found: {input_file}")
+    if chunk_size <= 0:
+        raise ValueError("chunk_size must be greater than 0")
 
     input_file = Path(input_file)
     output_dir = input_file.parent / input_file.stem
     output_dir.mkdir(exist_ok=True)
+    cleanup_existing_chunks(output_dir, input_file)
 
-    # Detect the delimiter automatically.
+    # Detect the delimiter automatically.
     with open(input_file, encoding=encoding, newline="") as f:
         sample = f.read(4096)
         f.seek(0)
@@ -38,10 +55,10 @@ def split_csv(
             dialect = csv.excel
             dialect.delimiter = ";"
         reader = csv.reader(f, dialect)
-        try:
-            header = next(reader)
-        except StopIteration as exc:
-            raise ValueError("Input file is empty.") from exc
+        try:
+            header = next(reader)
+        except StopIteration as exc:
+            raise ValueError("Input file is empty.") from exc
         chunk = []
         file_count = 0
         data_rows = 0

{nm_tool_forge-0.2.4 → nm_tool_forge-0.2.5}/src/loganalysis/__init__.py

@@ -13,4 +13,4 @@ __all__ = [
     "run_analysis",
 ]
 
-__version__ = "0.2.4"
+__version__ = "0.2.5"

{nm_tool_forge-0.2.4 → nm_tool_forge-0.2.5}/src/nm_tool_forge.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nm-tool-forge
-Version: 0.2.4
+Version: 0.2.5
 Summary: Analyze MigMan log files and generate aggregated CSV, Markdown, HTML, and optional PDF reports.
 Author-email: Stefan Ewald <s.ew@outlook.de>
 License-Expression: MIT

nm_tool_forge-0.2.5/tests/test_csvchunking.py

@@ -0,0 +1,153 @@
+import pytest
+
+from csvchunking.chunker import split_csv
+
+
+def make_csv(tmp_path, name, header, rows, encoding="utf-8-sig", delimiter=";"):
+    file = tmp_path / name
+    with open(file, "w", encoding=encoding, newline="") as f:
+        f.write(delimiter.join(header) + "\n")
+        for row in rows:
+            f.write(delimiter.join(row) + "\n")
+    return file
+
+
+def test_regular_split(tmp_path):
+    header = ["col1", "col2"]
+    rows = [["A", "1"], ["B", "2"], ["C", "3"], ["D", "4"], ["E", "5"]]
+    file = make_csv(tmp_path, "sample.csv", header, rows)
+    result = split_csv(file, chunk_size=2)
+    assert result.files_created == 3
+    for out in result.output_files:
+        with open(out, encoding="utf-8-sig") as f:
+            lines = f.read().splitlines()
+            assert lines[0] == "col1;col2"
+    assert (result.output_dir / "sample_01.csv").exists()
+    assert (result.output_dir / "sample_02.csv").exists()
+    assert (result.output_dir / "sample_03.csv").exists()
+
+
+def test_header_in_each_file(tmp_path):
+    header = ["foo", "bar"]
+    rows = [["x", "1"], ["y", "2"], ["z", "3"]]
+    file = make_csv(tmp_path, "test.csv", header, rows)
+    result = split_csv(file, chunk_size=1)
+    for out in result.output_files:
+        with open(out, encoding="utf-8-sig") as f:
+            assert f.readline().strip() == "foo;bar"
+
+
+def test_filename_with_spaces(tmp_path):
+    header = ["a", "b"]
+    rows = [["1", "2"]]
+    file = make_csv(tmp_path, "Part-Storage Areas Relationships.csv", header, rows)
+    result = split_csv(file, chunk_size=1)
+    assert result.output_dir.name == "Part-Storage Areas Relationships"
+    assert (result.output_dir / "Part-Storage Areas Relationships_01.csv").exists()
+
+
+def test_cleanup_removes_stale_matching_chunk_files(tmp_path):
+    header = ["col1", "col2"]
+    rows = [["A", "1"], ["B", "2"], ["C", "3"], ["D", "4"]]
+    file = make_csv(tmp_path, "sample.csv", header, rows)
+    output_dir = tmp_path / "sample"
+    output_dir.mkdir()
+    for name in ("sample_01.csv", "sample_02.csv", "sample_03.csv"):
+        (output_dir / name).write_text("old chunk\n", encoding="utf-8-sig")
+
+    result = split_csv(file, chunk_size=2)
+
+    assert result.files_created == 2
+    assert (result.output_dir / "sample_01.csv").exists()
+    assert (result.output_dir / "sample_02.csv").exists()
+    assert not (result.output_dir / "sample_03.csv").exists()
+
+
+def test_cleanup_keeps_non_matching_csv_files_and_subdirectories(tmp_path):
+    header = ["col1", "col2"]
+    rows = [["A", "1"], ["B", "2"]]
+    file = make_csv(tmp_path, "sample.csv", header, rows)
+    output_dir = tmp_path / "sample"
+    output_dir.mkdir()
+    preserved_files = [
+        "notes.csv",
+        "sample_backup.csv",
+        "sample_old.csv",
+        "other_01.csv",
+        "sample_1.csv",
+    ]
+    for name in preserved_files:
+        (output_dir / name).write_text("keep\n", encoding="utf-8-sig")
+    matching_subdir = output_dir / "sample_99.csv"
+    matching_subdir.mkdir()
+    (matching_subdir / "nested.txt").write_text("keep nested\n", encoding="utf-8-sig")
+
+    result = split_csv(file, chunk_size=1)
+
+    for name in preserved_files:
+        assert (result.output_dir / name).exists()
+    assert matching_subdir.is_dir()
+    assert (matching_subdir / "nested.txt").exists()
+
+
+def test_cleanup_filename_with_spaces_uses_exact_chunk_pattern(tmp_path):
+    header = ["a", "b"]
+    rows = [["1", "2"], ["3", "4"], ["5", "6"], ["7", "8"]]
+    filename = "Part-Storage Areas Relationships.csv"
+    file = make_csv(tmp_path, filename, header, rows)
+    output_dir = tmp_path / "Part-Storage Areas Relationships"
+    output_dir.mkdir()
+    for name in (
+        "Part-Storage Areas Relationships_01.csv",
+        "Part-Storage Areas Relationships_02.csv",
+        "Part-Storage Areas Relationships_99.csv",
+    ):
+        (output_dir / name).write_text("old chunk\n", encoding="utf-8-sig")
+    backup_file = output_dir / "Part-Storage Areas Relationships_backup.csv"
+    backup_file.write_text("keep\n", encoding="utf-8-sig")
+
+    result = split_csv(file, chunk_size=2)
+
+    assert result.output_dir == output_dir
+    assert (result.output_dir / "Part-Storage Areas Relationships_01.csv").exists()
+    assert (result.output_dir / "Part-Storage Areas Relationships_02.csv").exists()
+    assert not (result.output_dir / "Part-Storage Areas Relationships_99.csv").exists()
+    assert backup_file.exists()
+    assert "old chunk" not in (
+        result.output_dir / "Part-Storage Areas Relationships_01.csv"
+    ).read_text(encoding="utf-8-sig")
+
+
+def test_cleanup_repeated_run_removes_extra_chunks(tmp_path):
+    header = ["col1", "col2"]
+    first_rows = [["A", "1"], ["B", "2"], ["C", "3"], ["D", "4"], ["E", "5"]]
+    file = make_csv(tmp_path, "sample.csv", header, first_rows)
+    first_result = split_csv(file, chunk_size=2)
+    assert first_result.files_created == 3
+    assert (first_result.output_dir / "sample_03.csv").exists()
+
+    second_rows = [["A", "1"], ["B", "2"]]
+    make_csv(tmp_path, "sample.csv", header, second_rows)
+    second_result = split_csv(file, chunk_size=2)
+
+    assert second_result.files_created == 1
+    assert (second_result.output_dir / "sample_01.csv").exists()
+    assert not (second_result.output_dir / "sample_02.csv").exists()
+    assert not (second_result.output_dir / "sample_03.csv").exists()
+
+
+def test_invalid_chunk_size(tmp_path):
+    header = ["a", "b"]
+    rows = [["1", "2"]]
+    file = make_csv(tmp_path, "fail.csv", header, rows)
+    with pytest.raises(ValueError):
+        split_csv(file, chunk_size=0)
+    with pytest.raises(ValueError):
+        split_csv(file, chunk_size=-1)
+
+
+def test_empty_file(tmp_path):
+    file = tmp_path / "empty.csv"
+    file.write_text("")
+    with pytest.raises(ValueError):
+        split_csv(file, chunk_size=1)

nm_tool_forge-0.2.4/tests/test_csvchunking.py

@@ -1,63 +0,0 @@
-import pytest
-
-from csvchunking.chunker import split_csv
-
-
-def make_csv(tmp_path, name, header, rows, encoding="utf-8-sig", delimiter=";"):
-    file = tmp_path / name
-    with open(file, "w", encoding=encoding, newline="") as f:
-        f.write(delimiter.join(header) + "\n")
-        for row in rows:
-            f.write(delimiter.join(row) + "\n")
-    return file
-
-
-def test_regular_split(tmp_path):
-    header = ["col1", "col2"]
-    rows = [["A", "1"], ["B", "2"], ["C", "3"], ["D", "4"], ["E", "5"]]
-    file = make_csv(tmp_path, "sample.csv", header, rows)
-    result = split_csv(file, chunk_size=2)
-    assert result.files_created == 3
-    for out in result.output_files:
-        with open(out, encoding="utf-8-sig") as f:
-            lines = f.read().splitlines()
-            assert lines[0] == "col1;col2"
-    assert (result.output_dir / "sample_01.csv").exists()
-    assert (result.output_dir / "sample_02.csv").exists()
-    assert (result.output_dir / "sample_03.csv").exists()
-
-
-def test_header_in_each_file(tmp_path):
-    header = ["foo", "bar"]
-    rows = [["x", "1"], ["y", "2"], ["z", "3"]]
-    file = make_csv(tmp_path, "test.csv", header, rows)
-    result = split_csv(file, chunk_size=1)
-    for out in result.output_files:
-        with open(out, encoding="utf-8-sig") as f:
-            assert f.readline().strip() == "foo;bar"
-
-
-def test_filename_with_spaces(tmp_path):
-    header = ["a", "b"]
-    rows = [["1", "2"]]
-    file = make_csv(tmp_path, "Part-Storage Areas Relationships.csv", header, rows)
-    result = split_csv(file, chunk_size=1)
-    assert result.output_dir.name == "Part-Storage Areas Relationships"
-    assert (result.output_dir / "Part-Storage Areas Relationships_01.csv").exists()
-
-
-def test_invalid_chunk_size(tmp_path):
-    header = ["a", "b"]
-    rows = [["1", "2"]]
-    file = make_csv(tmp_path, "fail.csv", header, rows)
-    with pytest.raises(ValueError):
-        split_csv(file, chunk_size=0)
-    with pytest.raises(ValueError):
-        split_csv(file, chunk_size=-1)
-
-
-def test_empty_file(tmp_path):
-    file = tmp_path / "empty.csv"
-    file.write_text("")
-    with pytest.raises(ValueError):
-        split_csv(file, chunk_size=1)