@@ -50,7 +50,7 @@ def parse(self, ahb_row_dataframe: pd.DataFrame) -> pd.DataFrame:
5050 """
5151
5252 def add_text_to_column (row_index : int , column_index : int , text : str ) -> None :
53- starts_with_known_suffix = any (text .startswith (suffix ) for suffix in KNOW_SUFFIXES )
53+ starts_with_known_suffix = any (text .startswith (suffix + " " ) for suffix in KNOW_SUFFIXES )
5454 if len (text ) > 0 :
5555 if len (ahb_row_dataframe .iat [row_index , column_index ]) > 0 and not starts_with_known_suffix :
5656 text = " " + text
@@ -73,14 +73,16 @@ def handle_tab_stops(
7373 paragraph : Paragraph , splitted_text_at_tabs : list [str ], row_index : int , column_indezes : list [int ]
7474 ) -> None :
7575 tab_stops_in_current_paragraph = get_tabstop_positions (paragraph = paragraph )
76+ if len (tab_stops_in_current_paragraph ) == len (splitted_text_at_tabs ) - 1 :
77+ # we have remaining parts from a qualifier or code
78+ tab_stops_in_current_paragraph = [
79+ paragraph .paragraph_format .left_indent ,
80+ * tab_stops_in_current_paragraph ,
81+ ]
7682 for tabstop in tab_stops_in_current_paragraph :
7783 for indicator_tabstop_position , column_index in zip (self .indicator_tabstop_positions , column_indezes ):
78- if len (tab_stops_in_current_paragraph ) == 1 :
79- if indicator_tabstop_position in (tabstop , paragraph .paragraph_format .left_indent ):
80- add_text_to_column (row_index , column_index , splitted_text_at_tabs .pop (0 ))
81- else :
82- if tabstop == indicator_tabstop_position :
83- add_text_to_column (row_index , column_index , splitted_text_at_tabs .pop (0 ))
84+ if tabstop == indicator_tabstop_position :
85+ add_text_to_column (row_index , column_index , splitted_text_at_tabs .pop (0 ))
8486
8587 def handle_no_tab_stops (splitted_text_at_tabs : list [str ], row_index : int ) -> None :
8688 if splitted_text_at_tabs :
0 commit comments