MCPcopy Create free account
hub / github.com/apache/arrow / test_header_skip_rows

Method test_header_skip_rows

python/pyarrow/tests/test_csv.py:471–514  ·  view source on GitHub ↗
(self)

Source from the content-addressed store, hash-verified

469 assert table.column_names == names
470
471 def test_header_skip_rows(self):
472 rows = b"ab,cd\nef,gh\nij,kl\nmn,op\n"
473
474 opts = ReadOptions()
475 opts.skip_rows = 1
476 table = self.read_bytes(rows, read_options=opts)
477 self.check_names(table, ["ef", "gh"])
478 assert table.to_pydict() == {
479 "ef": ["ij", "mn"],
480 "gh": ["kl", "op"],
481 }
482
483 opts.skip_rows = 3
484 table = self.read_bytes(rows, read_options=opts)
485 self.check_names(table, ["mn", "op"])
486 assert table.to_pydict() == {
487 "mn": [],
488 "op": [],
489 }
490
491 opts.skip_rows = 4
492 with pytest.raises(pa.ArrowInvalid):
493 # Not enough rows
494 table = self.read_bytes(rows, read_options=opts)
495
496 # Can skip rows with a different number of columns
497 rows = b"abcd\n,,,,,\nij,kl\nmn,op\n"
498 opts.skip_rows = 2
499 table = self.read_bytes(rows, read_options=opts)
500 self.check_names(table, ["ij", "kl"])
501 assert table.to_pydict() == {
502 "ij": ["mn"],
503 "kl": ["op"],
504 }
505
506 # Can skip all rows exactly when columns are given
507 opts.skip_rows = 4
508 opts.column_names = ['ij', 'kl']
509 table = self.read_bytes(rows, read_options=opts)
510 self.check_names(table, ["ij", "kl"])
511 assert table.to_pydict() == {
512 "ij": [],
513 "kl": [],
514 }
515
516 def test_skip_rows_after_names(self):
517 rows = b"ab,cd\nef,gh\nij,kl\nmn,op\n"

Callers 1

test_header_skip_rowsMethod · 0.45

Calls 3

read_bytesMethod · 0.95
check_namesMethod · 0.95
ReadOptionsClass · 0.90

Tested by

no test coverage detected