feat: iterator over rust range

python/python_calamine/_python_calamine.pyi

@@ -1,13 +1,13 @@
 from __future__ import annotations
 
 import enum
+import typing
 from datetime import date, datetime, time, timedelta
 from os import PathLike
-from typing import Protocol
 
 ValueT = int | float | str | bool | time | date | datetime | timedelta
 
-class ReadBuffer(Protocol):
+class ReadBuffer(typing.Protocol):
  def seek(self) -> int: ...
  def read(self) -> bytes: ...
 
@@ -57,6 +57,8 @@ class CalamineSheet:
  By default, calamine skips empty rows/cols before data.
  For suppress this behaviour, set `skip_empty_area` to `False`.
  """
+ def iter_rows(self) -> typing.Iterator[list[ValueT]]:
+ """Retunrning data from sheet as iterator of lists."""
 
 class CalamineWorkbook:
  path: str | None

src/types/cell.rs

@@ -6,7 +6,7 @@ use pyo3::prelude::*;
 /// https://learn.microsoft.com/en-us/office/troubleshoot/excel/1900-and-1904-date-system
 static EXCEL_1900_1904_DIFF: f64 = 1462.0;
 
-#[derive(Debug)]
+#[derive(Debug, Clone)]
 pub enum CellValue {
  Int(i64),
  Float(f64),

src/types/sheet.rs

@@ -1,7 +1,7 @@
 use std::fmt::Display;
 use std::sync::Arc;
 
-use calamine::{DataType, Range, SheetType, SheetVisible};
+use calamine::{DataType, Range, Rows, SheetType, SheetVisible};
 use pyo3::class::basic::CompareOp;
 use pyo3::prelude::*;
 use pyo3::types::PyList;
@@ -199,4 +199,55 @@ impl CalamineSheet {
  }),
  ))
  }
+
+ fn iter_rows(&self) -> CalamineCellIterator {
+ CalamineCellIterator::from_range(Arc::clone(&self.range))
+ }
+}
+
+#[pyclass]
+pub struct CalamineCellIterator {
+ position: u32,
+ start: (u32, u32),
+ empty_row: Vec<CellValue>,
+ iter: Rows<'static, DataType>,
+ #[allow(dead_code)]
+ range: Arc<Range<DataType>>,
+}
+
+impl CalamineCellIterator {
+ fn from_range(range: Arc<Range<DataType>>) -> CalamineCellIterator {
+ let mut empty_row = Vec::with_capacity(range.width());
+ for _ in 0..range.width() {
+ empty_row.push(CellValue::String("".to_string()))
+ }
+ CalamineCellIterator {
+ empty_row,
+ position: 0,
+ start: range.start().unwrap(),
+ iter: unsafe { std::mem::transmute(range.rows()) },
+ range,
+ }
+ }
+}
+
+#[pymethods]
+impl CalamineCellIterator {
+ fn __iter__(slf: PyRef<'_, Self>) -> PyRef<'_, Self> {
+ slf
+ }
+
+ fn __next__(mut slf: PyRefMut<'_, Self>) -> Option<&PyList> {
+ slf.position += 1;
+ if slf.position > slf.start.0 {
+ slf.iter.next().map(|row| {
+ PyList::new(
+ slf.py(),
+ row.iter().map(<&DataType as Into<CellValue>>::into),
+ )
+ })
+ } else {
+ Some(PyList::new(slf.py(), slf.empty_row.clone()))
+ }
+ }
 }

tests/test_base.py

@@ -180,6 +180,30 @@ def test_xlsx_read():
  assert [] == reader.get_sheet_by_index(1).to_python(skip_empty_area=False)
 
 
+def test_xlsx_iter_rows():
+ names = ["Sheet1", "Sheet2", "Sheet3"]
+ data = [
+ ["", "", "", "", "", "", "", "", "", ""],
+ [
+ "String",
+ 1,
+ 1.1,
+ True,
+ False,
+ date(2010, 10, 10),
+ datetime(2010, 10, 10, 10, 10, 10),
+ time(10, 10, 10),
+ timedelta(hours=10, minutes=10, seconds=10, microseconds=100000),
+ timedelta(hours=255, minutes=10, seconds=10),
+ ],
+ ]
+
+ reader = CalamineWorkbook.from_object(PATH / "base.xlsx")
+
+ assert names == reader.sheet_names
+ assert data == list(reader.get_sheet_by_index(0).iter_rows())
+
+
 def test_nrows():
  reader = CalamineWorkbook.from_object(PATH / "base.xlsx")
  sheet = reader.get_sheet_by_name("Sheet3")