TST: parser test coverage

Author: wesm

pandas/io/parsers.py

@@ -258,21 +258,22 @@ def __iter__(self):
 
     def _get_index_name(self):
         columns = self.columns
-        passed_names = self.names is not None
 
         try:
             line = self._next_line()
         except StopIteration:
             line = None
 
         # implicitly index_col=0 b/c 1 fewer column names
-        implicit_first_col = (line is not None and
-                              len(line) == len(columns) + 1)
+        if line is not None:
+            implicit_first_cols = len(line) - len(columns)
+        else:
+            implicit_first_cols = 0
 
         index_name = None
-        if implicit_first_col:
+        if implicit_first_cols > 0:
             if self.index_col is None:
-                self.index_col = 0
+                self.index_col = range(implicit_first_cols)
             index_name = None
         elif np.isscalar(self.index_col):
             index_name = columns.pop(self.index_col)

pandas/io/tests/test_parsers.py

@@ -1,5 +1,6 @@
 from cStringIO import StringIO
 from datetime import datetime
+import csv
 import os
 import unittest
 
@@ -9,7 +10,7 @@
 import numpy as np
 
 from pandas import DataFrame, Index
-from pandas.io.parsers import read_csv, read_table, ExcelFile
+from pandas.io.parsers import read_csv, read_table, ExcelFile, TextParser
 from pandas.util.testing import assert_almost_equal, assert_frame_equal
 import pandas._tseries as lib
 
@@ -246,6 +247,17 @@ def test_iterator(self):
         last_chunk = reader.get_chunk(5)
         assert_frame_equal(last_chunk, df[3:])
 
+        # pass list
+        lines = list(csv.reader(StringIO(self.data1)))
+        parser = TextParser(lines, index_col=0, chunksize=2)
+
+        df = read_csv(StringIO(self.data1), index_col=0)
+
+        chunks = list(parser)
+        assert_frame_equal(chunks[0], df[:2])
+        assert_frame_equal(chunks[1], df[2:4])
+        assert_frame_equal(chunks[2], df[4:])
+
     def test_header_not_first_line(self):
         data = """got,to,ignore,this,line
 got,to,ignore,this,line
@@ -290,7 +302,19 @@ def test_pass_names_with_index(self):
         assert_frame_equal(df, expected)
 
     def test_multi_index_no_level_names(self):
-        pass
+        data = """index1,index2,A,B,C,D
+foo,one,2,3,4,5
+foo,two,7,8,9,10
+foo,three,12,13,14,15
+bar,one,12,13,14,15
+bar,two,12,13,14,15
+"""
+        lines = data.split('\n')
+        no_header = '\n'.join(lines[1:])
+        names = ['A', 'B', 'C', 'D']
+        df = read_csv(StringIO(no_header), index_col=[0, 1], names=names)
+        expected = read_csv(StringIO(data), index_col=[0, 1])
+        assert_frame_equal(df, expected)
 
 class TestParseSQL(unittest.TestCase):