Function parse_sql

hardness_eval.py:527–574

(toks, start_idx, tables_with_alias, schema)

def parse_sql(toks, start_idx, tables_with_alias, schema):
    isBlock = False  # indicate whether this is a block of sql/sub-sql
    len_ = len(toks)
    idx = start_idx

    sql = {}
    if toks[idx] == '(':
        isBlock = True
        idx += 1

    # parse from clause in order to get default tables
    from_end_idx, table_units, conds, default_tables = parse_from(toks, start_idx, tables_with_alias, schema)
    sql['from'] = {'table_units': table_units, 'conds': conds}
    # select clause
    _, select_col_units = parse_select(toks, idx, tables_with_alias, schema, default_tables)
    idx = from_end_idx
    sql['select'] = select_col_units
    # where clause
    idx, where_conds = parse_where(toks, idx, tables_with_alias, schema, default_tables)
    sql['where'] = where_conds
    # group by clause
    idx, group_col_units = parse_group_by(toks, idx, tables_with_alias, schema, default_tables)
    sql['groupBy'] = group_col_units
    # having clause
    idx, having_conds = parse_having(toks, idx, tables_with_alias, schema, default_tables)
    sql['having'] = having_conds
    # order by clause
    idx, order_col_units = parse_order_by(toks, idx, tables_with_alias, schema, default_tables)
    sql['orderBy'] = order_col_units
    # limit clause
    idx, limit_val = parse_limit(toks, idx)
    sql['limit'] = limit_val

    idx = skip_semicolon(toks, idx)
    if isBlock:
        assert toks[idx] == ')'
        idx += 1  # skip ')'
    idx = skip_semicolon(toks, idx)

    # intersect/union/except clause
    for op in SQL_OPS:  # initialize IUE
        sql[op] = None
    if idx < len_ and toks[idx] in SQL_OPS:
        sql_op = toks[idx]
        idx += 1
        idx, IUE_sql = parse_sql(toks, idx, tables_with_alias, schema)
        sql[sql_op] = IUE_sql
    return idx, sql


def load_data(fpath):