Lucene 避免lucence QueryParser解析异常？
在第三行，我得到了一些异常，比如“IOException:read over eof”和“LookaheadSuccess:Error in the application” 有没有办法避免这种情况？我讨厌每次执行搜索时中断并按两次继续 注意：我只在告诉visual Studio显示即使捕获也会抛出的异常时才注意到这一点。我没有得到异常，我只是看到每次搜索时都会抛出两个（或三个）断点。应用程序运行良好 var searcher=newindexsearcher（目录，true）； var parser=newqueryparser（Lucene.Net.Util.Version.Lucene_29，“全部”，分析器）；Lucene 避免lucence QueryParser解析异常？,lucene,lucene.net,Lucene,Lucene.net,在第三行，我得到了一些异常，比如“IOException:read over eof”和“LookaheadSuccess:Error in the application” 有没有办法避免这种情况？我讨厌每次执行搜索时中断并按两次继续 注意：我只在告诉visual Studio显示即使捕获也会抛出的异常时才注意到这一点。我没有得到异常，我只是看到每次搜索时都会抛出两个（或三个）断点。应用程序运行良好 var searcher=newindexsearcher（目录，true）； var par
var query=parser.Parse（文本）//这里这些是Lucene中发生并被捕获的第一次机会异常。您已经将VisualStudio配置为在所有异常上中断，而不仅仅是那些未处理的异常。使用异常对话框（ctrl-alt-e iirc）并更改您的设置。Lucene.NET（在版本3.0.3时）使用IOExceptions来管理解析器流的几个部分。这对性能有不良影响（在我的开发机器上长达90毫秒）
好消息是，目前位于的源代码存储库中的版本似乎已经删除了导致这种情况的特定异常。当然对我来说，这大大提高了性能。希望这有帮助。Lucene 3.0.3中QueryParser的补丁，以避免LookaheadSuccess异常抛出：
--- a/src/core/QueryParser/QueryParser.cs
+++ b/src/core/QueryParser/QueryParser.cs
@@ -1708,16 +1708,13 @@ namespace Lucene.Net.QueryParsers
}
private bool Jj_2_1(int xla)
- {
+ {
+ bool lookaheadSuccess = false;
jj_la = xla;
jj_lastpos = jj_scanpos = token;
try
{
- return !Jj_3_1();
- }
- catch (LookaheadSuccess)
- {
- return true;
+ return !Jj_3_1(out lookaheadSuccess);
}
finally
{
@@ -1725,29 +1722,31 @@ namespace Lucene.Net.QueryParsers
}
}
- private bool Jj_3R_2()
- {
- if (jj_scan_token(TermToken)) return true;
- if (jj_scan_token(ColonToken)) return true;
+ private bool Jj_3R_2(out bool lookaheadSuccess)
+ {
+ if (jj_scan_token(TermToken, out lookaheadSuccess)) return true;
+ if (lookaheadSuccess) return false;
+ if (jj_scan_token(ColonToken, out lookaheadSuccess)) return true;
return false;
}
- private bool Jj_3_1()
+ private bool Jj_3_1(out bool lookaheadSuccess)
{
Token xsp;
xsp = jj_scanpos;
- if (Jj_3R_2())
+ if (Jj_3R_2(out lookaheadSuccess))
{
jj_scanpos = xsp;
- if (Jj_3R_3()) return true;
+ if (Jj_3R_3(out lookaheadSuccess)) return true;
}
return false;
}
- private bool Jj_3R_3()
- {
- if (jj_scan_token(StarToken)) return true;
- if (jj_scan_token(ColonToken)) return true;
+ private bool Jj_3R_3(out bool lookaheadSuccess)
+ {
+ if (jj_scan_token(StarToken, out lookaheadSuccess)) return true;
+ if (lookaheadSuccess) return false;
+ if (jj_scan_token(ColonToken, out lookaheadSuccess)) return true;
return false;
}
@@ -1861,14 +1860,9 @@ namespace Lucene.Net.QueryParsers
throw GenerateParseException();
}
- [Serializable]
- private sealed class LookaheadSuccess : System.Exception
- {
- }
-
- private LookaheadSuccess jj_ls = new LookaheadSuccess();
- private bool jj_scan_token(int kind)
- {
+ private bool jj_scan_token(int kind, out bool lookaheadSuccess)
+ {
+ lookaheadSuccess = false;
if (jj_scanpos == jj_lastpos)
{
jj_la--;
@@ -1896,8 +1890,8 @@ namespace Lucene.Net.QueryParsers
}
if (tok != null) Jj_add_error_token(kind, i);
}
- if (jj_scanpos.kind != kind) return true;
- if (jj_la == 0 && jj_scanpos == jj_lastpos) throw jj_ls;
+ if (jj_scanpos.kind != kind) return true;
+ if (jj_la == 0 && jj_scanpos == jj_lastpos) lookaheadSuccess = true;
return false;
}
@@ -2029,32 +2023,34 @@ namespace Lucene.Net.QueryParsers
}
private void Jj_rescan_token()
- {
+ {
+ bool lookaheadSuccess = false;
jj_rescan = true;
for (int i = 0; i < 1; i++)
{
- try
+ JJCalls p = jj_2_rtns[i];
+ do
{
- JJCalls p = jj_2_rtns[i];
- do
+ if (p.gen > jj_gen)
{
- if (p.gen > jj_gen)
+ jj_la = p.arg;
+ jj_lastpos = jj_scanpos = p.first;
+ switch (i)
{
- jj_la = p.arg;
- jj_lastpos = jj_scanpos = p.first;
- switch (i)
- {
- case 0:
- Jj_3_1();
- break;
- }
+ case 0:
+ Jj_3_1(out lookaheadSuccess);
+ if (lookaheadSuccess)
+ {
+ goto Jj_rescan_token_after_while_label;
+ }
+ break;
}
- p = p.next;
- } while (p != null);
- }
- catch (LookaheadSuccess)
- {
- }
+ }
+ p = p.next;
+ } while (p != null);
+
+ Jj_rescan_token_after_while_label:
+ lookaheadSuccess = false;
}
jj_rescan = false;
}
--
文本是什么样子的？这里不可能说什么有用，但听起来像是一个格式不好的查询。
--- CharStream.cs
+++ CharStream.cs
@@ -44,6 +44,7 @@
/// implementing this interface. Can throw any java.io.IOException.
/// </summary>
char ReadChar();
+ char ReadChar(ref bool? systemIoException);
/// <summary> Returns the column position of the character last read.</summary>
/// <deprecated>
@@ -93,6 +94,7 @@
/// to this method to implement backup correctly.
/// </summary>
char BeginToken();
+ char BeginToken(ref bool? systemIoException);
/// <summary> Returns a string made up of characters from the marked token beginning
/// to the current buffer position. Implementations have the choice of returning
--- FastCharStream.cs
+++ FastCharStream.cs
@@ -48,12 +48,35 @@
public char ReadChar()
{
+ bool? systemIoException = null;
if (bufferPosition >= bufferLength)
- Refill();
+ {
+ Refill(ref systemIoException);
+ }
+ return buffer[bufferPosition++];
+ }
+
+ public char ReadChar(ref bool? systemIoException)
+ {
+ if (bufferPosition >= bufferLength)
+ {
+ Refill(ref systemIoException);
+ // If using this Nullable as System.IO.IOException signal and is signaled.
+ if (systemIoException.HasValue && systemIoException.Value == true)
+ {
+ return '\0';
+ }
+ }
return buffer[bufferPosition++];
}
- private void Refill()
+ // You may ask to be signaled of a System.IO.IOException through the systemIoException parameter.
+ // Set it to false if you are interested, it will be set to true to signal a System.IO.IOException.
+ // Set it to null if you are not interested.
+ // This is used to avoid having a lot of System.IO.IOExceptions thrown while running the code under a debugger.
+ // Having a lot of exceptions thrown under a debugger causes the code to execute a lot more slowly.
+ // So use this if you are experimenting a lot of slow parsing at runtime under a debugger.
+ private void Refill(ref bool? systemIoException)
{
int newPosition = bufferLength - tokenStart;
@@ -86,7 +109,18 @@
int charsRead = input.Read(buffer, newPosition, buffer.Length - newPosition);
if (charsRead <= 0)
- throw new System.IO.IOException("read past eof");
+ {
+ // If interested in using this Nullable to signal a System.IO.IOException
+ if (systemIoException.HasValue)
+ {
+ systemIoException = true;
+ return;
+ }
+ else
+ {
+ throw new System.IO.IOException("read past eof");
+ }
+ }
else
bufferLength += charsRead;
}
@@ -96,6 +130,12 @@
tokenStart = bufferPosition;
return ReadChar();
}
+
+ public char BeginToken(ref bool? systemIoException)
+ {
+ tokenStart = bufferPosition;
+ return ReadChar(ref systemIoException);
+ }
public void Backup(int amount)
{
@@ -156,4 +196,4 @@
get { return 1; }
}
}
-}
\ No newline at end of file
+}
--- QueryParserTokenManager.cs
+++ QueryParserTokenManager.cs
@@ -1341,9 +1341,16 @@
for (; ; )
{
+ bool? systemIoException = false;
try
{
- curChar = input_stream.BeginToken();
+ curChar = input_stream.BeginToken(ref systemIoException);
+ if (systemIoException != null && systemIoException.HasValue && systemIoException.Value == true)
+ {
+ jjmatchedKind = 0;
+ matchedToken = JjFillToken();
+ return matchedToken;
+ }
}
catch (System.IO.IOException)
{
@@ -1459,4 +1466,4 @@
while (start++ != end);
}
}
-}
\ No newline at end of file
+}