fixed bug at line 1058 in file numpy/lib&npyio_impl.py; in function _…

…read(), called by loadtxt() method, when files are read in chunks to reduce memory overhead, max_rows lines were always loaded every time, also in the case max_rows>_loadtxt_chunksize, in which case it loaded chunks with the wrong size. A test has been added in numpy/lib/tests/test_loadtxt.py, to check for the array size loaded for different max_rows, less and greater than _loadtxt_chunksize.

numpy/lib/_npyio_impl.py

@@ -1055,7 +1055,7 @@ def _read(fname, *, delimiter=',', comment='#', quote='"',
                 next_arr = _load_from_filelike(
                     data, delimiter=delimiter, comment=comment, quote=quote,
                     imaginary_unit=imaginary_unit,
-                    usecols=usecols, skiplines=skiplines, max_rows=max_rows,
+                    usecols=usecols, skiplines=skiplines, max_rows=chunk_size,
                     converters=converters, dtype=dtype,
                     encoding=encoding, filelike=filelike,
                     byte_converters=byte_converters,

numpy/lib/tests/test_loadtxt.py

@@ -1043,3 +1043,13 @@ def test_field_growing_cases():
     for i in range(1, 1024):
         res = np.loadtxt(["," * i], delimiter=",", dtype=bytes)
         assert len(res) == i+1
+
+@pytest.mark.parametrize("nmax", (10000, 50000, 80000, 100000, 120000)) # less, equal, greater, twice and more than twice than _loadtxt_chunksize
+def test_maxrows_exceeding_chunksize(nmax):
+    file_length = 200000
+    data = ""
+    for i in range(file_length) :
+        data += "a 0.5 1\n"
+    txt = StringIO(data)
+    res = np.loadtxt(txt, dtype=str, delimiter=" ", max_rows=nmax)
+    assert len(res) == nmax