Hi,

I've written a windows script which works very similar to the standard nutch shell script.  Please have a look.  I'm sure some changes will be made as I've only tested it on a couple of machines.  Make sure it goes in the bin directory but access it from the root (probably something that should be fixed in the script).

I tried to attach it as a zip file but it got kicked back to me.  I'll paste the text in below

Matt



REM Developed for Windows XP using Delayed Environment Variable Expansion.
REM To enable Delayed Env Var Expansion use cmd /V:ON prior to running
REM this command.
REM
REM Copyright (c) 2004 The Nutch Organization.  All rights reserved.  
REM Use subject to the conditions in http://www.nutch.org/LICENSE.txt.
REM
REM Matt Tencati


@echo off
setlocal


if "%1" == "" (
 echo Usage: nutch COMMAND
 echo where COMMAND is one of:
 echo   crawl             one-step crawler for intranets
 echo   admin             database administration, including creation
 echo   inject            inject new urls into the database
 echo   generate          generate new segments to fetch
 echo   fetchlist         print the fetchlist of a segment
 echo   fetch             fetch a segment's pages
 echo   index             run the indexer on a segment's fetcher output
 echo   merge             merge several segment indexes
 echo   dedup             remove duplicates from a set of segment indexes
 echo   updatedb          update database from a segment's fetcher output
 echo   readdb            examine arbitrary fields of the database
 echo   analyze           adjust database link-analysis scoring
 echo   server            run a search server
 echo  or
 echo   CLASSNAME         run the class named CLASSNAME
 echo Most commands print help when invoked w/o parameters.
 goto done

)

set COMMAND=%1
shift
set ARGS=%1 %2 %3 %4 %5 %6 %7 %8 %9


set THIS_DIR=%CD%
set NUTCH_HOME=%THIS_DIR%


if "%JAVA_HOME%" == "" (
 echo You must specify JAVA_HOME.
 goto done
)


set JAVA=%JAVA_HOME%\bin\java
set JAVA_HEAP_MAX=-Xmx1500m


if NOT "%NUTCH_HEAPSIZE%" == "" (
 set JAVA_HEAP_MAX=-Xmx%NUTCH_HEAPSIZE%m
)


if "%NUTCH_CONF_DIR%" == "" (
 set CLASSPATH=%NUTCH_HOME%\conf
) else (
 set CLASSPATH=%NUTCH_CONF_DIR%
)


if EXIST %NUTCH_HOME%\build\classes (
 set CLASSPATH=%CLASSPATH%;%NUTCH_HOME%\build\classes
)


if EXIST %NUTCH_HOME%\build\test\classes (
 set CLASSPATH=%CLASSPATH%;%NUTCH_HOME%\build\test\classes
)


for %%i in (%NUTCH_HOME%\nutch-*.jar) do set CLASSPATH=!CLASSPATH!;%%i
for %%i in (%NUTCH_HOME%\lib\*.jar) do set CLASSPATH=!CLASSPATH!;%%i


if "%COMMAND%" == "crawl" set CLASS=net.nutch.tools.CrawlTool
if "%COMMAND%" == "admin" set CLASS=net.nutch.tools.WebDBAdminTool
if "%COMMAND%" == "inject" set CLASS=net.nutch.db.WebDBInjector
if "%COMMAND%" == "generate" set CLASS=net.nutch.tools.FetchListTool
if "%COMMAND%" == "fetchlist" set CLASS=net.nutch.pagedb.FetchListEntry
if "%COMMAND%" == "fetch" set CLASS=net.nutch.fetcher.Fetcher
if "%COMMAND%" == "index" set CLASS=net.nutch.indexer.IndexSegment
if "%COMMAND%" == "merge" set CLASS=net.nutch.indexer.IndexMerger
if "%COMMAND%" == "dedup" set CLASS=net.nutch.indexer.DeleteDuplicates
if "%COMMAND%" == "updatedb" set CLASS=net.nutch.tools.UpdateDatabaseTool
if "%COMMAND%" == "readdb" set CLASS=net.nutch.db.WebDBReader
if "%COMMAND%" == "analyze" set CLASS=net.nutch.tools.LinkAnalysisTool
if "%COMMAND%" == "server" set CLASS='net.nutch.searcher.DistributedSearch$Server'
if "%COMMAND%" == "" set CLASS=$COMMAND


%JAVA% %JAVA_HEAP_MAX% %NUTCH_OPTS% -classpath %CLASSPATH% %CLASS% %ARGS%

:done
endlocal

Reply via email to