BUG: Python Parser skipping over items if BOM present in first element of header (#36365)

Author: asishm

doc/source/whatsnew/v1.2.0.rst

@@ -321,6 +321,7 @@ I/O
 - :meth:`to_csv` did not support zip compression for binary file object not having a filename (:issue:`35058`)
 - :meth:`to_csv` and :meth:`read_csv` did not honor `compression` and `encoding` for path-like objects that are internally converted to file-like objects (:issue:`35677`, :issue:`26124`, and :issue:`32392`)
 - :meth:`to_picke` and :meth:`read_pickle` did not support compression for file-objects (:issue:`26237`, :issue:`29054`, and :issue:`29570`)
+- Bug in :meth:`read_csv` with `engine='python'` truncating data if multiple items present in first row and first element started with BOM (:issue:`36343`)
 
 Plotting
 ^^^^^^^^

pandas/io/parsers.py

@@ -2886,14 +2886,12 @@ def _check_for_bom(self, first_row):
  # quotation mark.
  if len(first_row_bom) > end + 1:
  new_row += first_row_bom[end + 1 :]
- return [new_row] + first_row[1:]
 
- elif len(first_row_bom) > 1:
- return [first_row_bom[1:]]
  else:
- # First row is just the BOM, so we
- # return an empty string.
- return [""]
+
+ # No quotation so just remove BOM from first element
+ new_row = first_row_bom[1:]
+ return [new_row] + first_row[1:]
 
  def _is_line_empty(self, line):
  """

pandas/tests/io/parser/test_common.py

@@ -2128,6 +2128,16 @@ def test_first_row_bom(all_parsers):
  tm.assert_frame_equal(result, expected)
 
 
+def test_first_row_bom_unquoted(all_parsers):
+ # see gh-36343
+ parser = all_parsers
+ data = """\ufeffHead1	Head2	Head3"""
+
+ result = parser.read_csv(StringIO(data), delimiter="\t")
+ expected = DataFrame(columns=["Head1", "Head2", "Head3"])
+ tm.assert_frame_equal(result, expected)
+
+
 def test_integer_precision(all_parsers):
  # Gh 7072
  s = """1,1;0;0;0;1;1;3844;3844;3844;1;1;1;1;1;1;0;0;1;1;0;0,,,4321583677327450765