How can I write a stored procedure that imports data from a CSV file and populates the table?
Most other solutions here require that you create the table in advance/manually. This may not be practical in some cases (e.g., if you have a lot of columns in the destination table). So, the approach below may come handy.
Providing the path and column count of your csv file, you can use the following function to load your table to a temp table that will be named as target_table
:
The top row is assumed to have the column names.
create or replace function data.load_csv_file
(
target_table text,
csv_path text,
col_count integer
)
returns void as $$
declare
iter integer; -- dummy integer to iterate columns with
col text; -- variable to keep the column name at each iteration
col_first text; -- first column name, e.g., top left corner on a csv file or spreadsheet
begin
create table temp_table ();
-- add just enough number of columns
for iter in 1..col_count
loop
execute format('alter table temp_table add column col_%s text;', iter);
end loop;
-- copy the data from csv file
execute format('copy temp_table from %L with delimiter '','' quote ''"'' csv ', csv_path);
iter := 1;
col_first := (select col_1 from temp_table limit 1);
-- update the column names based on the first row which has the column names
for col in execute format('select unnest(string_to_array(trim(temp_table::text, ''()''), '','')) from temp_table where col_1 = %L', col_first)
loop
execute format('alter table temp_table rename column col_%s to %s', iter, col);
iter := iter + 1;
end loop;
-- delete the columns row
execute format('delete from temp_table where %s = %L', col_first, col_first);
-- change the temp table name to the name given as parameter, if not blank
if length(target_table) > 0 then
execute format('alter table temp_table rename to %I', target_table);
end if;
end;
$$ language plpgsql;