@@ -611,17 +611,17 @@ def try_remove_ws(x):
611611 )
612612 assert df .shape == ground_truth .shape
613613 old = [
614- "First Vietnamese American BankIn Vietnamese" ,
615- "Westernbank Puerto RicoEn Espanol" ,
616- "R-G Premier Bank of Puerto RicoEn Espanol" ,
617- "EurobankEn Espanol" ,
618- "Sanderson State BankEn Espanol" ,
619- "Washington Mutual Bank(Including its subsidiary Washington "
614+ "First Vietnamese American Bank In Vietnamese" ,
615+ "Westernbank Puerto Rico En Espanol" ,
616+ "R-G Premier Bank of Puerto Rico En Espanol" ,
617+ "Eurobank En Espanol" ,
618+ "Sanderson State Bank En Espanol" ,
619+ "Washington Mutual Bank (Including its subsidiary Washington "
620620 "Mutual Bank FSB)" ,
621- "Silver State BankEn Espanol" ,
622- "AmTrade International BankEn Espanol" ,
623- "Hamilton Bank, NAEn Espanol" ,
624- "The Citizens Savings BankPioneer Community Bank, Inc." ,
621+ "Silver State Bank En Espanol" ,
622+ "AmTrade International Bank En Espanol" ,
623+ "Hamilton Bank, NA En Espanol" ,
624+ "The Citizens Savings Bank Pioneer Community Bank, Inc." ,
625625 ]
626626 new = [
627627 "First Vietnamese American Bank" ,
@@ -1295,27 +1295,7 @@ def test_parse_br_as_space(self):
12951295 <th>A</th>
12961296 </tr>
12971297 <tr>
1298- <td>world1<br>word2</td>
1299- </tr>
1300- </table>
1301- """ )[0 ]
1302-
1303- expected = DataFrame (data = [["word1 word2" ]], columns = ["A" ])
1304-
1305- tm .assert_frame_equal (result , expected )
1306-
1307- def test_parse_br_tail_retained (self ):
1308- # Ensure text after br are retained when they are replaced with a space.
1309- # See:
1310- # https://stackoverflow.com/q/33281217 and
1311- # https://stackoverflow.com/questions/12545897/convert-br-to-end-line/48628074#comment84810813_34640357
1312- result = self .read_html ("""
1313- <table>
1314- <tr>
1315- <th>A</th>
1316- </tr>
1317- <tr>
1318- <td>world1<br>word2</td>
1298+ <td>word1<br>word2</td>
13191299 </tr>
13201300 </table>
13211301 """ )[0 ]
0 commit comments