I just spent a bunch of time doing this. It's problematic because the postgres tools don't capture the sort and dist key info. I'll post full scripts to our public github repo in a bit, but for now here's a script that pulls all table definitions into create table statements. It doesn't address column compression types or primary keys yet, but it at least allows us to recreate tables in another database. Populating them is then a simple matter of scripting unload and load statements. The script isn't pretty due to a number of limitations of Redshift sql and me looking at it for too many hours, but it works well.
select tm.schemaname||'.'||tm.tablename, 'create table '||tm.schemaname||'.'||tm.tablename
||' ('
||cp.coldef
-- primary key
-- dist key
|| nvl(d.distkey,'')
--sort key
|| nvl((select
' sortkey(' ||substr(array_to_string(
array( select ','||cast(column_name as varchar(100)) as str from
(select column_name from information_schema.columns col where col.table_schema= tm.schemaname and col.table_name=tm.tablename) c2
join
(-- gives sort cols
select attrelid as tableid, attname as colname, attsortkeyord as sort_col_order from pg_attribute pa where
pa.attnum > 0 AND NOT pa.attisdropped AND pa.attsortkeyord > 0
) st on tm.tableid=st.tableid and c2.column_name=st.colname order by sort_col_order
)
,'')
,2,10000) || ')'
)
,'') ||';'
from
-- t master table list
(
SELECT substring(n.nspname,1,100) as schemaname, substring(c.relname,1,100) as tablename, c.oid as tableid
FROM pg_namespace n, pg_class c
WHERE n.oid = c.relnamespace
AND nspname NOT IN ('pg_catalog', 'pg_toast', 'information_schema')
) tm
-- cp creates the col params for the create string
join
(select
substr(str,(charindex('QQQ',str)+3),(charindex('ZZZ',str))-(charindex('QQQ',str)+3)) as tableid
,substr(replace(replace(str,'ZZZ',''),'QQQ'||substr(str,(charindex('QQQ',str)+3),(charindex('ZZZ',str))-(charindex('QQQ',str)+3)),''),2,10000) as coldef
from
( select array_to_string(array(
SELECT 'QQQ'||cast(t.tableid as varchar(10))||'ZZZ'|| ','||column_name||' '|| decode(udt_name,'bpchar','char',udt_name) || decode(character_maximum_length,null,'', '('||cast(character_maximum_length as varchar(9))||')' )
-- default
|| decode(substr(column_default,2,8),'identity','',null,'',' default '||column_default||' ')
-- nullable
|| decode(is_nullable,'YES',' NULL ','NO',' NOT NULL ')
-- identity
|| decode(substr(column_default,2,8),'identity',' identity('||substr(column_default,(charindex('''',column_default)+1), (length(column_default)-charindex('''',reverse(column_default))-charindex('''',column_default) ) ) ||') ', '') as str
from
-- ci all the col info
(
select cast(t.tableid as int), cast(table_schema as varchar(100)), cast(table_name as varchar(100)), cast(column_name as varchar(100)),
cast(ordinal_position as int), cast(column_default as varchar(100)), cast(is_nullable as varchar(20)) , cast(udt_name as varchar(50)) ,cast(character_maximum_length as int),
sort_col_order , decode(d.colname,null,0,1) dist_key
from (select * from information_schema.columns c where c.table_schema= t.schemaname and c.table_name=t.tablename) c
left join
(-- gives sort cols
select attrelid as tableid, attname as colname, attsortkeyord as sort_col_order from pg_attribute a where
a.attnum > 0 AND NOT a.attisdropped AND a.attsortkeyord > 0
) s on t.tableid=s.tableid and c.column_name=s.colname
left join
-- gives dist col
(select attrelid as tableid, attname as colname from pg_attribute a where
a.attnum > 0 AND NOT a.attisdropped AND a.attisdistkey = 't'
) d on t.tableid=d.tableid and c.column_name=d.colname
order by ordinal_position
) ci
-- for the working array funct
), '') as str
from
(-- need tableid
SELECT substring(n.nspname,1,100) as schemaname, substring(c.relname,1,100) as tablename, c.oid as tableid
FROM pg_namespace n, pg_class c
WHERE n.oid = c.relnamespace
AND nspname NOT IN ('pg_catalog', 'pg_toast', 'information_schema')
) t
)) cp on tm.tableid=cp.tableid
-- add in primary key query here
-- dist key
left join
( select
-- close off the col defs after the primary key
')' ||
' distkey('|| cast(column_name as varchar(100)) ||')' as distkey, t.tableid
from information_schema.columns c
join
(-- need tableid
SELECT substring(n.nspname,1,100) as schemaname, substring(c.relname,1,100) as tablename, c.oid as tableid
FROM pg_namespace n, pg_class c
WHERE n.oid = c.relnamespace
AND nspname NOT IN ('pg_catalog', 'pg_toast', 'information_schema')
) t on c.table_schema= t.schemaname and c.table_name=t.tablename
join
-- gives dist col
(select attrelid as tableid, attname as colname from pg_attribute a where
a.attnum > 0 AND NOT a.attisdropped AND a.attisdistkey = 't'
) d on t.tableid=d.tableid and c.column_name=d.colname
) d on tm.tableid=d.tableid
