mirror of
https://github.com/dimitri/pgloader.git
synced 2026-01-29 11:01:06 +01:00
efd11ab759
The new WITH options allows the user to set values for the dynamic variables *copy-batch-rows*, *copy-batch-size* and *concurrent-batches*. That's needed in case like in issue #16 even with the batch size defaulting to what looks like a proper setup. In a longer term a review of the pgloader memory usage should be done seriously, the numbers being way higher than the batch sizes we do setup here.
48 lines
1.4 KiB
Fish
48 lines
1.4 KiB
Fish
/*
|
|
* The data file comes from the US census website:
|
|
*
|
|
* http://www.census.gov/geo/maps-data/data/gazetteer2013.html
|
|
*
|
|
* We import it directly into pgloader git repository so that we have at
|
|
* least a CSV test where we read from a local file...
|
|
*/
|
|
|
|
LOAD CSV
|
|
FROM data/2013_Gaz_113CDs_national.txt
|
|
(
|
|
usps, -- United States Postal Service State Abbreviation
|
|
geoid, -- Geographic Identifier
|
|
aland, -- Land Area (square meters)
|
|
awater, -- Water Area (square meters)
|
|
aland_sqmi, -- SQMI Land Area (square miles)
|
|
awater_sqmi, -- SQMI Water Area (square miles)
|
|
intptlat, -- Latitude (decimal degrees)
|
|
intptlong -- Longitude (decimal degrees)
|
|
)
|
|
|
|
INTO postgresql:///pgloader?districts
|
|
(
|
|
usps, geoid, aland, awater, aland_sqmi, awater_sqmi,
|
|
location point using (format nil "(~a,~a)" intptlong intptlat)
|
|
)
|
|
|
|
WITH truncate,
|
|
skip header = 1,
|
|
batch rows = 200,
|
|
batch size = 1024 kB,
|
|
batch concurrency = 3,
|
|
fields terminated by '\t'
|
|
|
|
BEFORE LOAD DO
|
|
$$ drop table if exists districts; $$,
|
|
$$ create table districts (
|
|
usps text,
|
|
geoid text,
|
|
aland bigint,
|
|
awater bigint,
|
|
aland_sqmi double precision,
|
|
awater_sqmi double precision,
|
|
location point
|
|
);
|
|
$$;
|