[英]Parsing T-SQL To Extract Part of WHERE Clause
我有一個包含“曲線”的大型SQL數據庫。 每條曲線都有一個ID(曲線)。 我正在嘗試確定每個曲線的主要用戶以及是否使用了所有曲線。 為此,DBA提供了針對數據庫執行的所有語句的日志。
這些陳述可能非常復雜。 我要做的就是提取要查詢的curveid。
示例語句如下:
WITH G AS ( SELECT [Timevalue] FROM [mc].[GranularityLookup]
WHERE [TimeValue] BETWEEN '19-Jul-2017 00:00' AND '30-Sep-2017 00:00'
AND [1 Hr] = 1),
D AS ( SELECT [CurveID], [DeliveryDate], [PublishDate], AVG([Value]) Value, MAX([PeriodNumber]) PeriodNumber
FROM mc.CURVEID_6657_1_LATEST data
JOIN
(SELECT CurveID ID, DeliveryDate dDate, MAX(PublishDate) pDate
FROM mc.CURVEID_6657_1_LATEST
WHERE CurveID = 90564
AND DeliveryDate >= '19-Jul-2017 00:00' AND DeliveryDate <= '30-Sep-2017 00:00'
GROUP BY DeliveryDate, CurveID ) Dates
ON data.DeliveryDate = dates.dDate AND data.PublishDate = dates.pDate
WHERE data.CurveID = 90564
AND data.DeliveryDate >= '19-Jul-2017 00:00' AND data.DeliveryDate <= '30-Sep-2017 00:00'
GROUP BY [CurveID], [PublishDate], [DeliveryDate] )
SELECT
G.[TimeValue] [Deliver
yDate] , D.[PublishDate], D.[Value], D.[PeriodNumber]
FROM
G
LEFT JOIN
D
ON
G.[TimeValue] = D.[DeliveryDate]
ORDER BY DeliveryDate ASC, PeriodNumber ASC, publishDate DESC
從此語句中,我感興趣的只是提取用戶查詢的curveid 90564。
該語句也可能類似於以下之一:
SELECT * FROM anytable WHERE curveid = 123 AND deliverydate BETWEEN '2017-01-01' AND 2017-02-01'
要么
SELECT * FROM mc.anytable WHERE curveid IN (1,2,3,4,5,6,7)
同樣,我只想知道曲線ID。 我不在乎其他任何條款。
我正在使用Microsoft.SqlServer.TransactSql.ScriptDom命名空間來解析SQL,現在我可以使用類似於以下代碼(與其他一些示例組合在一起)識別所有WHERE語句:
string sql = @"WITH
G AS ( SELECT [Timevalue] FROM [mc].[GranularityLookup]
WHERE [TimeValue] BETWEEN '19-Jul-2017 00:00' AND '30-Sep-2017 00:00'
AND [1 Hr] = 1),
D AS ( SELECT [CurveID], [DeliveryDate], [PublishDate], AVG([Value]) Value, MAX([PeriodNumber]) PeriodNumber
FROM mc.CURVEID_6657_1_LATEST data
JOIN
(SELECT CurveID ID, DeliveryDate dDate, MAX(PublishDate) pDate
FROM mc.CURVEID_6657_1_LATEST
WHERE CurveID = 90564
AND DeliveryDate >= '19-Jul-2017 00:00' AND DeliveryDate <= '30-Sep-2017 00:00'
GROUP BY DeliveryDate, CurveID ) Dates
ON data.DeliveryDate = dates.dDate AND data.PublishDate = dates.pDate
WHERE data.CurveID = 90564
AND data.DeliveryDate >= '19-Jul-2017 00:00' AND data.DeliveryDate <= '30-Sep-2017 00:00'
GROUP BY [CurveID], [PublishDate], [DeliveryDate] )
SELECT
G.[TimeValue] [Deliver
yDate] , D.[PublishDate], D.[Value], D.[PeriodNumber]
FROM
G
LEFT JOIN
D
ON
G.[TimeValue] = D.[DeliveryDate]
ORDER BY DeliveryDate ASC, PeriodNumber ASC, publishDate DESC";
var parser = new TSql120Parser(false);
IList<ParseError> errors;
var fragment = parser.Parse(new StringReader(sql), out errors);
var whereVisitor = new WhereVisitor();
fragment.Accept(whereVisitor);
// I now have all WHERE clauses in whereVisitor.WhereStatements
class WhereVisitor : TSqlConcreteFragmentVisitor
{
public readonly List<WhereClause> WhereStatements = new List<WhereClause>();
public override void Visit(WhereClause node)
{
WhereStatements.Add(node);
}
}
whereVisitor.WhereStatements(此示例中為3)中的每個子句都公開了一個稱為SearchCondition的屬性。 不幸的是,這是我沒有想法的地方。 我要實現的是如下邏輯:
foreach (var clause in whereVisitor.WhereStatements)
{
// IF any part of the clause filters based on curveid THEN
// Capture curveIDs
// END IF
}
其他詳情:
編輯1
一些其他信息:
編輯2(部分解決方案)
在子句類似於curveid = 123的情況下,請以下訪問者幫助:
class CurveIdVisitor : TSqlConcreteFragmentVisitor
{
public readonly List<int> CurveIds = new List<int>();
public override void Visit(BooleanComparisonExpression exp)
{
if (exp.FirstExpression is ColumnReferenceExpression && exp.SecondExpression is IntegerLiteral )
{
// there is a possibility that this is of the ilk 'curveid = 123'
// we will look for the 'identifier'
// we take the last if there are multiple. Example:
// alias.curveid
// goives two identifiers: alias and curveid
if (
((ColumnReferenceExpression) exp.FirstExpression).MultiPartIdentifier.Identifiers.Last().Value.ToLower() ==
"curveid")
{
// this is definitely a curveid filter
// Now to find the curve id
int curveid = int.Parse(((IntegerLiteral) exp.SecondExpression).Value);
CurveIds.Add(curveid);
}
}
終於解決了這個問題,希望以后對其他人有所幫助。 也許其他人可能會花些時間閱讀並提供更好的解決方案。
public class SqlParser
{
public List<int> GetQueriedCurveIds(string sql)
{
var parser = new TSql120Parser(false);
IList<ParseError> errors;
var fragment = parser.Parse(new StringReader(sql), out errors);
List<int> curveIds = new List<int>();
CurveIdVisitor cidv = new CurveIdVisitor();
InPredicateVisitor inpv = new InPredicateVisitor();
fragment.AcceptChildren(cidv);
fragment.AcceptChildren(inpv);
curveIds.AddRange(cidv.CurveIds);
curveIds.AddRange(inpv.CurveIds);
return curveIds.Distinct().ToList();
}
}
class CurveIdVisitor : TSqlConcreteFragmentVisitor
{
public readonly List<int> CurveIds = new List<int>();
public override void Visit(BooleanComparisonExpression exp)
{
if (exp.FirstExpression is ColumnReferenceExpression && exp.SecondExpression is IntegerLiteral )
{
// there is a possibility that this is of the ilk 'curveid = 123'
// we will look for the 'identifier'
// we take the last if there are multiple. Example:
// alias.curveid
// goives two identifiers: alias and curveid
if (
((ColumnReferenceExpression) exp.FirstExpression).MultiPartIdentifier.Identifiers.Last().Value.ToLower() ==
"curveid")
{
// this is definitely a curveid filter
// Now to find the curve id
int curveid = int.Parse(((IntegerLiteral) exp.SecondExpression).Value);
CurveIds.Add(curveid);
}
}
}
}
class InPredicateVisitor : TSqlConcreteFragmentVisitor
{
public readonly List<int> CurveIds = new List<int>();
public override void Visit(InPredicate exp)
{
if (exp.Expression is ColumnReferenceExpression)
{
if (
((ColumnReferenceExpression) exp.Expression).MultiPartIdentifier.Identifiers.Last().Value.ToLower() ==
"curveid")
{
foreach (var value in exp.Values)
{
if (value is IntegerLiteral)
{
CurveIds.Add(int.Parse(((IntegerLiteral)value).Value));
}
}
}
}
}
}
這是縮減代碼以示答案。 在現實生活中,您將需要檢查ParseError集合並添加一些錯誤處理!
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.