I'm trying to select just one account using SQL Server but am getting the following error:
ERROR: The text data type cannot be selected as DISTINCT because
it is not comparable. Error Code: 421
with the following statement:
select DISTINCT ad.*,
acc.companyname,
acc.accountnumber
from address ad
join AddressLink al on al.AddressID = ad.id
join account acc on acc.ID = al.ParentID
where acc.accountnumber like '11227'
What have I done wrong?
Edit:
New query:
select address.ID,
address.StreetAddress1,
address.StreetAddress2,
address.City,
Address.State,
Address.PostalCode,
Address.ClassTypeID,
account.companyname,
account.accountnumber,
addresslink.ID as addressLinkID,
addresslink.addresstypeid
from address
join AddressLink on address.id = addresslink.AddressID
join account on addresslink.ParentID = account.ID
where account.CompanyName like 'company name'
All the company names that I've had to blur are identical.
Try:
select ad.*,
l.companyname,
l.accountnumber
from address ad
join (select DISTINCT al.AddressID,
acc.companyname,
acc.accountnumber
from account acc
join AddressLink al on acc.ID = al.ParentID
where acc.accountnumber like '11227') l
on l.AddressID = ad.id
"Distinct", in the context you have is trying to do distinct on ALL columns. That said, there are some data types that are NOT converable, such as TEXT. So, if your table has some of these non "Distinctable" column types exists, that is what is crashing your query.
However, to get around this, if you do something like
CONVERT( char(60), YourTextColumn ) as YourTextColumn,
It should get that for you... at least its now thinking the final column type is "char"acter and CAN compare it.
You should check the data types of the columns in the address table. My guess is that one or more of them has the data type text, ntext or image.
One of the restrictions of using text, ntext or image data types is that columns defined of these data types cannot be used as part of a SELECT statement that includes the DISTINCT clause.
For what it's worth, the MSDN article for ntext, text, and image (Transact-SQL) recommends avoiding these data types and use nvarchar(max), varchar(max), and varbinary(max) instead. You may want to consider changing how that table is defined.
The accepted answer from Mark B shows a subquery (good idea to limit the domain of the DISTINCT) on AddressLink.AddressId, Account.CompanyName, and Account.AccountNumber.
Let me ask this: Does AddressLink allow more than one record to have the same value in the ParentId and AddressId fields?
If not, and assuming that Mark B's answer works, then just remove the DISTINCT because you're never going to get any duplicates inside of that subquery.
Leaving the DISTINCT in causes a performance hit because the DB has to create a temporary table that is either indexed with a btree or a hash and it has to insert every value returned by the subquery into that table to check if it invalidates the uniqueness constraint on those three fields. Note that the "optimizer" doesn't know that there won't be any dupes... if you tell it to check for DISTINCT, it will check it... With a btree index this is going to cause O(n log n) work on the number of rows returned; with a hash it would cause O(n) work but who knows how big the constant factor is in relation to the other work you're doing (it's probably larger than everything else you're doing meaning this could make this run half as fast as without the DISTINCT).
So my answer is Mark B's answer without the DISTINCT in the subquery. Let me know if AddressLink does allow repeats (can't imagine why it would).
Related
I have an order system. Users with can be attached to different orders as a type of different user. They can download documents associated with an order. Documents are only given to certain types of users on the order. I'm having trouble writing the query to check a user's permission to view a document and select the info about the document.
I have the following tables and (applicable) fields:
Docs: DocNo, FileNo
DocAccess: DocNo, UserTypeWithAccess
FileUsers: FileNo, UserType, UserNo
I have the following query:
SELECT Docs.*
FROM Docs
WHERE DocNo = 1000
AND EXISTS (
SELECT * FROM DocAccess
LEFT JOIN FileUsers
ON FileUsers.UserType = DocAccess.UserTypeWithAccess
AND FileUsers.FileNo = Docs.FileNo /* Errors here */
WHERE DocAccess.UserNo = 2000 )
The trouble is that in the Exists Select, it does not recognize Docs (at Docs.FileNo) as a valid table. If I move the second on argument to the where clause it works, but I would rather limit the initial join rather than filter them out after the fact.
I can get around this a couple ways, but this seems like it would be best. Anything I'm missing here? Or is it simply not allowed?
I think this is a limitation of your database engine. In most databases, docs would be in scope for the entire subquery -- including both the where and in clauses.
However, you do not need to worry about where you put the particular clause. SQL is a descriptive language, not a procedural language. The purpose of SQL is to describe the output. The SQL engine, parser, and compiler should be choosing the most optimal execution path. Not always true. But, move the condition to the where clause and don't worry about it.
I am not clear why do you need to join with FileUsers at all in your subquery?
What is the purpose and idea of the query (in plain English)?
In any case, if you do need to join with FileUsers then I suggest to use the inner join and move second filter to the WHERE condition. I don't think you can use it in JOIN condition in subquery - at least I've never seen it used this way before. I believe you can only correlate through WHERE clause.
You have to use aliases to get this working:
SELECT
doc.*
FROM
Docs doc
WHERE
doc.DocNo = 1000
AND EXISTS (
SELECT
*
FROM
DocAccess acc
LEFT OUTER JOIN
FileUsers usr
ON
usr.UserType = acc.UserTypeWithAccess
AND usr.FileNo = doc.FileNo
WHERE
acc.UserNo = 2000
)
This also makes it more clear which table each field belongs to (think about using the same table twice or more in the same query with different aliases).
If you would only like to limit the output to one row you can use TOP 1:
SELECT TOP 1
doc.*
FROM
Docs doc
INNER JOIN
FileUsers usr
ON
usr.FileNo = doc.FileNo
INNER JOIN
DocAccess acc
ON
acc.UserTypeWithAccess = usr.UserType
WHERE
doc.DocNo = 1000
AND acc.UserNo = 2000
Of course the second query works a bit different than the first one (both JOINS are INNER). Depeding on your data model you might even leave the TOP 1 out of that query.
Say I have a select statement that goes..
select * from animals
That gives a a query result of all the columns in the table.
Now, if the 42nd column of the table animals is is_parent, and I want to return that in my results, just after gender, so I can see it more easily. But I also want all the other columns.
select is_parent, * from animals
This returns ORA-00936: missing expression.
The same statement will work fine in Sybase, and I know that you need to add a table alias to the animals table to get it to work ( select is_parent, a.* from animals ani), but why must Oracle need a table alias to be able to work out the select?
Actually, it's easy to solve the original problem. You just have to qualify the *.
select is_parent, animals.* from animals;
should work just fine. Aliases for the table names also work.
There is no merit in doing this in production code. We should explicitly name the columns we want rather than using the SELECT * construct.
As for ad hoc querying, get yourself an IDE - SQL Developer, TOAD, PL/SQL Developer, etc - which allows us to manipulate queries and result sets without needing extensions to SQL.
Good question, I've often wondered this myself but have then accepted it as one of those things...
Similar problem is this:
sql>select geometrie.SDO_GTYPE from ngg_basiscomponent
ORA-00904: "GEOMETRIE"."SDO_GTYPE": invalid identifier
where geometrie is a column of type mdsys.sdo_geometry.
Add an alias and the thing works.
sql>select a.geometrie.SDO_GTYPE from ngg_basiscomponent a;
Lots of good answers so far on why select * shouldn't be used and they're all perfectly correct. However, don't think any of them answer the original question on why the particular syntax fails.
Sadly, I think the reason is... "because it doesn't".
I don't think it's anything to do with single-table vs. multi-table queries:
This works fine:
select *
from
person p inner join user u on u.person_id = p.person_id
But this fails:
select p.person_id, *
from
person p inner join user u on u.person_id = p.person_id
While this works:
select p.person_id, p.*, u.*
from
person p inner join user u on u.person_id = p.person_id
It might be some historical compatibility thing with 20-year old legacy code.
Another for the "buy why!!!" bucket, along with why can't you group by an alias?
The use case for the alias.* format is as follows
select parent.*, child.col
from parent join child on parent.parent_id = child.parent_id
That is, selecting all the columns from one table in a join, plus (optionally) one or more columns from other tables.
The fact that you can use it to select the same column twice is just a side-effect. There is no real point to selecting the same column twice and I don't think laziness is a real justification.
Select * in the real world is only dangerous when referring to columns by index number after retrieval rather than by name, the bigger problem is inefficiency when not all columns are required in the resultset (network traffic, cpu and memory load).
Of course if you're adding columns from other tables (as is the case in this example it can be dangerous as these tables may over time have columns with matching names, select *, x in that case would fail if a column x is added to the table that previously didn't have it.
why must Oracle need a table alias to be able to work out the select
Teradata is requiring the same. As both are quite old (maybe better call it mature :-) DBMSes this might be historical reasons.
My usual explanation is: an unqualified * means everything/all columns and the parser/optimizer is simply confused because you request more than everything.
I've just learned ( yesterday ) to use "exists" instead of "in".
BAD
select * from table where nameid in (
select nameid from othertable where otherdesc = 'SomeDesc' )
GOOD
select * from table t where exists (
select nameid from othertable o where t.nameid = o.nameid and otherdesc = 'SomeDesc' )
And I have some questions about this:
1) The explanation as I understood was: "The reason why this is better is because only the matching values will be returned instead of building a massive list of possible results". Does that mean that while the first subquery might return 900 results the second will return only 1 ( yes or no )?
2) In the past I have had the RDBMS complainin: "only the first 1000 rows might be retrieved", this second approach would solve that problem?
3) What is the scope of the alias in the second subquery?... does the alias only lives in the parenthesis?
for example
select * from table t where exists (
select nameid from othertable o where t.nameid = o.nameid and otherdesc = 'SomeDesc' )
AND
select nameid from othertable o where t.nameid = o.nameid and otherdesc = 'SomeOtherDesc' )
That is, if I use the same alias ( o for table othertable ) In the second "exist" will it present any problem with the first exists? or are they totally independent?
Is this something Oracle only related or it is valid for most RDBMS?
Thanks a lot
It's specific to each DBMS and depends on the query optimizer. Some optimizers detect IN clause and translate it.
In all DBMSes I tested, alias is only valid inside the ( )
BTW, you can rewrite the query as:
select t.*
from table t
join othertable o on t.nameid = o.nameid
and o.otherdesc in ('SomeDesc','SomeOtherDesc');
And, to answer your questions:
Yes
Yes
Yes
You are treading into complicated territory, known as 'correlated sub-queries'. Since we don't have detailed information about your tables and the key structures, some of the answers can only be 'maybe'.
In your initial IN query, the notation would be valid whether or not OtherTable contains a column NameID (and, indeed, whether OtherDesc exists as a column in Table or OtherTable - which is not clear in any of your examples, but presumably is a column of OtherTable). This behaviour is what makes a correlated sub-query into a correlated sub-query. It is also a routine source of angst for people when they first run into it - invariably by accident. Since the SQL standard mandates the behaviour of interpreting a name in the sub-query as referring to a column in the outer query if there is no column with the relevant name in the tables mentioned in the sub-query but there is a column with the relevant name in the tables mentioned in the outer (main) query, no product that wants to claim conformance to (this bit of) the SQL standard will do anything different.
The answer to your Q1 is "it depends", but given plausible assumptions (NameID exists as a column in both tables; OtherDesc only exists in OtherTable), the results should be the same in terms of the data set returned, but may not be equivalent in terms of performance.
The answer to your Q2 is that in the past, you were using an inferior if not defective DBMS. If it supported EXISTS, then the DBMS might still complain about the cardinality of the result.
The answer to your Q3 as applied to the first EXISTS query is "t is available as an alias throughout the statement, but o is only available as an alias inside the parentheses". As applied to your second example box - with AND connecting two sub-selects (the second of which is missing the open parenthesis when I'm looking at it), then "t is available as an alias throughout the statement and refers to the same table, but there are two different aliases both labelled 'o', one for each sub-query". Note that the query might return no data if OtherDesc is unique for a given NameID value in OtherTable; otherwise, it requires two rows in OtherTable with the same NameID and the two OtherDesc values for each row in Table with that NameID value.
Oracle-specific: When you write a query using the IN clause, you're telling the rule-based optimizer that you want the inner query to drive the outer query. When you write EXISTS in a where clause, you're telling the optimizer that you want the outer query to be run first, using each value to fetch a value from the inner query. See "Difference between IN and EXISTS in subqueries".
Probably.
Alias declared inside subquery lives inside subquery. By the way, I don't think your example with 2 ANDed subqueries is valid SQL. Did you mean UNION instead of AND?
Personally I would use a join, rather than a subquery for this.
SELECT t.*
FROM yourTable t
INNER JOIN otherTable ot
ON (t.nameid = ot.nameid AND ot.otherdesc = 'SomeDesc')
It is difficult to generalize that EXISTS is always better than IN. Logically if that is the case, then SQL community would have replaced IN with EXISTS...
Also, please note that IN and EXISTS are not same, the results may be different when you use the two...
With IN, usually its a Full Table Scan of the inner table once without removing NULLs (so if you have NULLs in your inner table, IN will not remove NULLS by default)... While EXISTS removes NULL and in case of correlated subquery, it runs inner query for every row from outer query.
Assuming there are no NULLS and its a simple query (with no correlation), EXIST might perform better if the row you are finding is not the last row. If it happens to be the last row, EXISTS may need to scan till the end like IN.. so similar performance...
But IN and EXISTS are not interchangeable...
I've been trying to come up with a good design pattern for mapping data contained in relational databases to the business objects I've created but I keep hitting a wall.
Consider the following tables:
TYPE: typeid, description
USER: userid, username, usertypeid->TYPE.typeid, imageid->IMAGE.imageid
IMAGE: imageid, location, imagetypeid->TYPE.typeid
I would like to gather all the information regarding a specific user. Creating a query for this isn't too difficult.
SELECT u.*, ut.*, i.*, it.* FROM user u
INNER JOIN type ut ON ut.typeid = u.usertypeid
INNER JOIN image i ON i.imageid = u.imageid
INNER JOIN type it ON it.typeid = i.imagetypeid
WHERE u.userid = #userid
The problem is that the field names collide and then I'm forced to alias every single field which gets out of hand very quickly.
Does anyone have a decent design pattern for this kind of thing?
I've thought about retrieving multiple results from a single stored procedure and then using a dataset to iterate through each one but I'm worried that some performance issues might bite me in the butt later. For example instead of the above query something like:
SELECT u.*, t.* FROM user u
INNER JOIN type t ON t.typeid = u.usertypeid
WHERE u.userid = #userid;
SELECT i.*, t.* FROM image i
INNER JOIN type t ON t.typeid = i.imagetypeid
INNER JOIN user u ON u.imageid = i.imageid
WHERE u.userid = #userid;
Does that seem like a decent solution? Can anyone foresee any issues with this approach?
Never use the SQL * wildcard in production code. Always spell out all the columns you want to retrieve.
Then aliasing some of them doesn't seem like such a huge amount of extra work.
Re your comment asking for background and reasoning:
Sometimes you don't really need every column from all tables, and fetching them can be needlessly costly (especially for large strings and blobs). There is no SQL syntax for "all columns except the following exceptions."
You can't alias columns that you fetch using the wildcard. Once you need to alias any of the columns, you need to expand the wildcard to list all the columns explicitly.
If the table structure changes, e.g. columns are renamed, reordered, dropped, or added, then the wildcard fetches them all, by position as defined in the tables. This may seem like a convenience, but not when your application depends on columns being in the result set by a given name or in a given position. You can get mysterious bugs where your application displays columns in the wrong order (if referencing columns by position), or shows them as blank (if referencing columns by name).
However, if the SQL query names columns explicitly, you can employ the "Fail Early" principle. This helps debugging, because it leads you directly to the SQL query that needs to be edited to account for the schema change.
My boss found a bug in a query I created, and I don't understand the reasoning behind the bug, although the query results prove he's correct. Here's the query (simplified version) before the fix:
select PTNO,PTNM,CATCD
from PARTS
left join CATEGORIES on (CATEGORIES.CATCD=PARTS.CATCD);
and here it is after the fix:
select PTNO,PTNM,PARTS.CATCD
from PARTS
left join CATEGORIES on (CATEGORIES.CATCD=PARTS.CATCD);
The bug was, that null values were being shown for column CATCD, i.e. the query results included results from table CATEGORIES instead of PARTS.
Here's what I don't understand: if there was ambiguity in the original query, why didn't Oracle throw an error? As far as I understood, in the case of left joins, the "main" table in the query (PARTS) has precedence in ambiguity.
Am I wrong, or just not thinking about this problem correctly?
Update:
Here's a revised example, where the ambiguity error is not thrown:
CREATE TABLE PARTS (PTNO NUMBER, CATCD NUMBER, SECCD NUMBER);
CREATE TABLE CATEGORIES(CATCD NUMBER);
CREATE TABLE SECTIONS(SECCD NUMBER, CATCD NUMBER);
select PTNO,CATCD
from PARTS
left join CATEGORIES on (CATEGORIES.CATCD=PARTS.CATCD)
left join SECTIONS on (SECTIONS.SECCD=PARTS.SECCD) ;
Anybody have a clue?
Here's the query (simplified version)
I think by simplifying the query you removed the real cause of the bug :-)
What oracle version are you using? Oracle 10g ( 10.2.0.1.0 ) gives:
create table parts (ptno number , ptnm number , catcd number);
create table CATEGORIES (catcd number);
select PTNO,PTNM,CATCD from PARTS
left join CATEGORIES on (CATEGORIES.CATCD=PARTS.CATCD);
I get ORA-00918: column ambiguously defined
Interesting in SQL server that throws an error (as it should)
select id
from sysobjects s
left join syscolumns c on s.id = c.id
Server: Msg 209, Level 16, State 1, Line 1
Ambiguous column name 'id'.
select id
from sysobjects
left join syscolumns on sysobjects.id = syscolumns.id
Server: Msg 209, Level 16, State 1, Line 1
Ambiguous column name 'id'.
From my experience if you create a query like this the data result will pull CATCD from the right side of the join not the left when there is a field overlap like this.
So since this join will have all records from PARTS with only some pull through from CATEGORIES you will have NULL in the CATCD field any time there is no data on the right side.
By explicitly defining the column as from PARTS (ie left side) you will get a non null value assuming that the field has data in PARTS.
Remember that with LEFT JOIN you are only guarantied data in fields from the left table, there may well be empty columns to the right.
This may be a bug in the Oracle optimizer. I can reproduce the same behavior on the query with 3 tables. Intuitively it does seem that it should produce an error. If I rewrite it in either of the following ways, it does generate an error:
(1) Using old-style outer join
select ptno, catcd
from parts, categories, sections
where categories.catcd (+) = parts.catcd
and sections.seccd (+) = parts.seccd
(2) Explicitly isolating the two joins
select ptno, catcd
from (
select ptno, seccd, catcd
from parts
left join categories on (categories.CATCD=parts.CATCD)
)
left join sections on (sections.SECCD=parts.SECCD)
I used DBMS_XPLAN to get details on the execution of the query, which did show something interesting. The plan is basically to outer join PARTS and CATEGORIES, project that result set, then outer join it to SECTIONS. The interesting part is that in the projection of the first outer join, it is only including PTNO and SECCD -- it is NOT including the CATCD from either of the first two tables. Therefore the final result is getting CATCD from the third table.
But I don't know whether this is a cause or an effect.
I'm afraid I can't tell you why you're not getting an exception, but I can postulate as to why it chose CATEGORIES' version of the column over PARTS' version.
As far as I understood, in the case of left joins, the "main" table in the query (PARTS) has precedence in ambiguity
It's not clear whether by "main" you mean simply the left table in a left join, or the "driving" table, as you see the query conceptually... But in either case, what you see as the "main" table in the query as you've written it will not necessarily be the "main" table in the actual execution of that query.
My guess is that Oracle is simply using the column from the first table it hits in executing the query. And since most individual operations in SQL do not require one table to be hit before the other, the DBMS will decide at parse time which is the most efficient one to scan first. Try getting an execution plan for the query. I suspect it may reveal that it's hitting CATEGORIES first and then PARTS.
I am using Oracle 9.2.0.8.0. and it does give the error "ORA-00918: column ambiguously defined".
This is a known bug with some Oracle versions when using ANSI-style joins. The correct behavior would be to get an ORA-00918 error.
It's always best to specify your table names anyway; that way your queries don't break when you happen to add a new column with a name that is also used in another table.
It is generally advised to be specific and fully qualify all column names anyway, as it saves the optimizer a little work. Certainly in SQL Server.
From what I can gleen from the Oracle docs, it seems it will only throw if you select the column name twice in the select list, or once in the select list and then again elsewhere like an order by clause.
Perhaps you have uncovered an 'undocumented feature' :)
Like HollyStyles, I cannot find anything in the Oracle docs which can explain what you are seeing.
PostgreSQL, DB2, MySQL and MSSQL all refuse to run the first query, as it's ambiguous.
#Pat: I get the same error here for your query. My query is just a little bit more complicated than what I originally posted. I'm working on a reproducible simple example now.
A bigger question you should be asking yourself is - why do I have a category code in the parts table that doesn't exist in the categories table?
This is a bug in Oracle 9i. If you join more than 2 tables using ANSI notation, it will not detect ambiguities in column names, and can return the wrong column if an alias isn't used.
As has been mentioned already, it is fixed in 10g, so if an alias isn't used, an error will be returned.