xlsx-and-csv-read (#3)

Reviewed-on: #3 Co-authored-by: Vishesh 'ironeagle' Bangotra <aetoskia@gmail.com> Co-committed-by: Vishesh 'ironeagle' Bangotra <aetoskia@gmail.com>
2026-08-24 20:19:33 +00:00
parent a188e78283
commit c3f3c9e57b
38 changed files with 1847 additions and 656 deletions
--- a/tests/test_xlsx_simple.py
+++ b/tests/test_xlsx_simple.py
@@ -0,0 +1,118 @@
+import datetime
+from io import BytesIO
+
+import openpyxl
+import pytest
+
+from omniread import (
+    # core
+    Content,
+    ContentType,
+
+    # xlsx
+    FileSystemXlsxClient,
+    XlsxParser,
+    XlsxScraper,
+)
+
+
+def _fixture_xlsx_bytes() -> bytes:
+    wb = openpyxl.Workbook()
+    ws = wb.active
+    ws.title = "Statement"
+    ws.append(["DETAILED STATEMENT", None, None, ""])
+    ws.append([])
+    ws.append(["S No", "Value Date", "Txn Date", "Remarks", "Withdrawal", "Deposit", "Balance"])
+    ws.append([1, "01/06/2026", "01/06/2026", "UPI/NPCI BHIM/bhimcashback@h/B", 0.0, 10.0, 250285.24])
+    row = 4
+    ws.cell(row=row, column=5).value = 100.0  # ensure float rendering path
+    buf = BytesIO()
+    wb.save(buf)
+    return buf.getvalue()
+
+
+@pytest.fixture
+def xlsx_bytes() -> bytes:
+    return _fixture_xlsx_bytes()
+
+
+@pytest.fixture
+def xlsx_path(tmp_path, xlsx_bytes):
+    p = tmp_path / "statement.xlsx"
+    p.write_bytes(xlsx_bytes)
+    return p
+
+
+def test_content_type_value():
+    assert ContentType.XLSX.value == (
+        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
+    )
+
+
+def test_scraper_round_trip(xlsx_path, xlsx_bytes):
+    scraper = XlsxScraper(client=FileSystemXlsxClient())
+    content = scraper.fetch(xlsx_path)
+
+    assert content.raw == xlsx_bytes
+    assert content.content_type is ContentType.XLSX
+
+
+def test_client_missing_file_raises(tmp_path):
+    with pytest.raises(FileNotFoundError):
+        FileSystemXlsxClient().fetch(tmp_path / "nope.xlsx")
+
+
+def test_client_directory_raises(tmp_path):
+    with pytest.raises(ValueError):
+        FileSystemXlsxClient().fetch(tmp_path)
+
+
+def test_parser_rows_skip_empty_and_trim(xlsx_bytes):
+    parser = XlsxParser(Content(raw=xlsx_bytes, source="mem", content_type=ContentType.XLSX))
+
+    rows = parser.rows()
+
+    # empty row dropped by skip_empty; metadata + header + data remain
+    assert len(rows) == 3
+    assert rows[0] == ["DETAILED STATEMENT"]
+    header = rows[1]
+    assert header[:7] == ["S No", "Value Date", "Txn Date", "Remarks", "Withdrawal", "Deposit", "Balance"]
+    data = rows[2]
+    assert data[3] == "UPI/NPCI BHIM/bhimcashback@h/B"
+    assert data[6] == "250285.24"
+
+
+def test_parser_keep_empty_rows(xlsx_bytes):
+    parser = XlsxParser(Content(raw=xlsx_bytes, source="mem", content_type=ContentType.XLSX))
+
+    rows = parser.rows(skip_empty=False)
+
+    assert len(rows) == 4  # includes blank second row and padded metadata row
+
+
+def test_parser_sheet_selection_and_names(xlsx_bytes):
+    parser = XlsxParser(Content(raw=xlsx_bytes, source="mem", content_type=ContentType.XLSX))
+
+    assert parser.sheet_names == ["Statement"]
+    assert parser.rows(sheet="Statement") == parser.rows(sheet=0)
+    assert parser.parse() == parser.rows()
+
+    with pytest.raises(ValueError, match="not found"):
+        parser.rows(sheet="Missing")
+
+
+def test_parser_date_cell_isoformat():
+    wb = openpyxl.Workbook()
+    ws = wb.active
+    ws.append([datetime.date(2026, 6, 1), "x"])
+    buf = BytesIO()
+    wb.save(buf)
+
+    parser = XlsxParser(Content(raw=buf.getvalue(), source="mem", content_type=ContentType.XLSX))
+    # openpyxl surfaces date cells as datetime; ISO rendering keeps determinism
+    assert parser.parse()[0][0] == "2026-06-01T00:00:00"
+
+
+def test_parser_rejects_non_xlsx_content():
+    with pytest.raises(ValueError, match="does not support"):
+        XlsxParser(Content(raw=b"<html></html>", source="mem", content_type=ContentType.HTML))