ccache_hash.c

harvest是一个下载html网页得机器人

static char rcsid[] = "ccache_hash.c,v 1.14 1995/11/29 00:48:30 duane Exp";
/******************************************************************************
**
** FILE
**      hash.c
**
** DESCRIPTION
**      This file contains the socket control algorithms and structures.
**	It manages the hash table and expirations of sockets.
**
** FUNCTIONS
**      SockInit()
**	free_url()
**	Compare_URL()
**	StripFileName()
**	SearchList()
**	GetConnection()
**	DisconnectOne()
**	TouchDate()
**	SockRetrieve()
**	SockGetData()
**	ExpireSocket()
**	ShutDownCache()
**	DestroyDataReturn()
**	DumpHash()
**
**  David Merkel & Mark Peterson, University of Colorado - Boulder, July 1994
 *
 *  ----------------------------------------------------------------------
 *  Copyright (c) 1994, 1995.  All rights reserved.
 *  
 *    The Harvest software was developed by the Internet Research Task
 *    Force Research Group on Resource Discovery (IRTF-RD):
 *  
 *          Mic Bowman of Transarc Corporation.
 *          Peter Danzig of the University of Southern California.
 *          Darren R. Hardy of the University of Colorado at Boulder.
 *          Udi Manber of the University of Arizona.
 *          Michael F. Schwartz of the University of Colorado at Boulder.
 *          Duane Wessels of the University of Colorado at Boulder.
 *  
 *    This copyright notice applies to software in the Harvest
 *    ``src/'' directory only.  Users should consult the individual
 *    copyright notices in the ``components/'' subdirectories for
 *    copyright information about other software bundled with the
 *    Harvest source code distribution.
 *  
 *  TERMS OF USE
 *    
 *    The Harvest software may be used and re-distributed without
 *    charge, provided that the software origin and research team are
 *    cited in any use of the system.  Most commonly this is
 *    accomplished by including a link to the Harvest Home Page
 *    (http://harvest.cs.colorado.edu/) from the query page of any
 *    Broker you deploy, as well as in the query result pages.  These
 *    links are generated automatically by the standard Broker
 *    software distribution.
 *    
 *    The Harvest software is provided ``as is'', without express or
 *    implied warranty, and with no support nor obligation to assist
 *    in its use, correction, modification or enhancement.  We assume
 *    no liability with respect to the infringement of copyrights,
 *    trade secrets, or any patents, and are not responsible for
 *    consequential damages.  Proper use of the Harvest software is
 *    entirely the responsibility of the user.
 *  
 *  DERIVATIVE WORKS
 *  
 *    Users may make derivative works from the Harvest software, subject 
 *    to the following constraints:
 *  
 *      - You must include the above copyright notice and these 
 *        accompanying paragraphs in all forms of derivative works, 
 *        and any documentation and other materials related to such 
 *        distribution and use acknowledge that the software was 
 *        developed at the above institutions.
 *  
 *      - You must notify IRTF-RD regarding your distribution of 
 *        the derivative work.
 *  
 *      - You must clearly notify users that your are distributing 
 *        a modified version and not the original Harvest software.
 *  
 *      - Any derivative product is also subject to these copyright 
 *        and use restrictions.
 *  
 *    Note that the Harvest software is NOT in the public domain.  We
 *    retain copyright, as specified above.
 *  
 *  HISTORY OF FREE SOFTWARE STATUS
 *  
 *    Originally we required sites to license the software in cases
 *    where they were going to build commercial products/services
 *    around Harvest.  In June 1995 we changed this policy.  We now
 *    allow people to use the core Harvest software (the code found in
 *    the Harvest ``src/'' directory) for free.  We made this change
 *    in the interest of encouraging the widest possible deployment of
 *    the technology.  The Harvest software is really a reference
 *    implementation of a set of protocols and formats, some of which
 *    we intend to standardize.  We encourage commercial
 *    re-implementations of code complying to this set of standards.  
 *  
******************************************************************************/
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <unistd.h>
#include <signal.h>
#include <sys/types.h>
#include <netdb.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include "ccache.h"
#include "time_it.h"
#include "util.h"

/* Allow differnet passwords on the same socket */
#define ALLOW_DIFFERENT_PASSWORDS

/* Hash function is last 8 bits of the IP number of the destination host. */
#define GetHKey(theIP) ((int) ((theIP) & 0xff))

/* Flag to prevent non-initialized hash from being used. */
static Boolean initialized = FALSE;

/* The hash table. */
static SockCntlRec *SockHash[HASH_SLOTS];

/* The expiration queue. */
static SockCntlRec *TimeOutListNew = NULL;
static SockCntlRec *TimeOutListOld = NULL;

/* Current number of connections being maintained.  */
static int currConnections = 0;

/* Default values. */
static int maxConnections = 10;
static long timeOut = 300;

/* Called on timer expiration. */
int ExpireSocket(int whichTimer);

/* Called on SIGUSR1 to dump the hash table to stdout. */
static void DumpHash();


/****************************************************************************
** function:  void SockInit()
**
** parameters: InitConfigRec sets the initialization parameters to the
**             library package.  If NULL, we use the defaults.
**
** postcondistions:  The structures are initialized and ready to accept
**                   connections.
**
** other: This function should only be called once, and must be called before
**        any other related function call.
*****************************************************************************/
void SockInit(InitConfigRec * initParam)
{
	if (initialized)	/* If we've already initialed, don't do it again. */
		return;

	initialized = TRUE;	/* Set initialization to TRUE */

	signal(SIGUSR1, DumpHash);	/* On this interrupt the Hash table */
	/* spills its guts. */

	/* Initialize the Hash Table to NULL's */
	memset((char *) SockHash, '\0', (sizeof(SockCntlRec *) * HASH_SLOTS));

	/* Initialize the timer package. */
	InitTimer();

	/* If no initailization was given use default values. */
	if (!initParam)
		return;

	/* Set the maximum number of connections to maintain. */
	if (initParam->maxConnections > MIN_CONNECTIONS)
		maxConnections = initParam->maxConnections;

	/* Set the timeOut for inactive connections. */
	if (initParam->timeOut > MIN_TIMEOUT)
		timeOut = initParam->timeOut;
}

/***************************************************************************
**  function: free_url()
**
**  parameters: An allocated URL structure.
**
**  postconditions:  The URL is deallocated.
****************************************************************************/
static void free_url(URL * toFree)
{
	if (toFree->url)
		xfree(toFree->url);
	if (toFree->pathname)
		xfree(toFree->pathname);
	if (toFree->host)
		xfree(toFree->host);
	if (toFree->user)
		xfree(toFree->user);
	if (toFree->password)
		xfree(toFree->password);
	if (toFree->raw_pathname)
		xfree(toFree->raw_pathname);
	xfree((char *) toFree);
	toFree = NULL;
}

/*************************************************************************
** function: CompareURL()
**
** parameters: Two preallocated URL structures.
**
** postconditions:  Returns TRUE if these to connections have the same
**                  hostname and port number.
*************************************************************************/
static int CompareURL(URL * ua, URL * ub)
{
#ifdef DEBUG
	printf("inside of CompareURL\n");
	printf("ub->host: %s\n", ub->host);
	printf("ua->host: %s\n", ua->host);
#endif


	if (strcmp(ua->host, ub->host) != 0)
		return FALSE;
	if (ua->port != ub->port)
		return FALSE;

	return TRUE;
}


/******************************************************************************
** function name: StripFileName()
**
** preconditions: Buffer must be an empty pre-allocated string.
**		  Path must contain a unix pathname.
**
** postconditions: The last unit of the pathname is placed into the buffer.
**
******************************************************************************/
static void StripFileName(buffer, path)
     char *buffer;
     char *path;
{
	int i;

	for (i = strlen(path); i >= 0; i--) {
		if (path[i] == '/')
			break;
	}

	strcpy(buffer, &path[i + 1]);
}


/**********************************************************************
**  function: SearchList()
**
**  parameters: An allocated SockCntlRec and a URL.  The SockCntrlRec *
**  should point to the beginning of the hash to search.
**
**  postconditions: A socket with a matching URL is returned if an
**  INACTIVE one is available.
**********************************************************************/
static SockCntlRec *SearchList(SockCntlRec * theRec, URL * theURL)
{
	SockCntlRec *tmpPtr;
	char errorReply[SERV_REPLY_LENGTH];
	URL *newURL;
	int errNum;

	/* Make sure we've initizlized and the URL is valid */
	if (!initialized || theURL == NULL)
		return (NULL);

	newURL = dup_url(theURL);
	tmpPtr = theRec;
	/* Go until we've checked all in the list. */
	while (tmpPtr != NULL) {

		/* See if this one is inactive and matches our URL. */
		if ((tmpPtr->sockStateStor == INACTIVE) &&
		    (CompareURL(tmpPtr->socketInfo, theURL))) {
			/* If the user or password is different relogin in. */
			if ((strcmp(tmpPtr->socketInfo->user, theURL->user) != 0)
#ifndef ALLOW_DIFFERENT_PASSWORDS
			    || (strcmp(tmpPtr->socketInfo->password, theURL->password) != 0)
#endif
			    ) {
				free_url(tmpPtr->socketInfo);
				tmpPtr->socketInfo = newURL;
				if ((errNum = Login(tmpPtr->socketInfo->user,
					    tmpPtr->socketInfo->password, tmpPtr->theSocket, FALSE,
					    errorReply)) < 0) {
					CancelTimer(tmpPtr->timerid);
					ExpireSocket(tmpPtr->timerid);
					DoError(errNum, errorReply);
					return (NULL);
				}
				return (tmpPtr);
			}
			free_url(tmpPtr->socketInfo);
			tmpPtr->socketInfo = newURL;
			return (tmpPtr);
		}
		/* Look at the next one. */
		tmpPtr = tmpPtr->hashNext;
	}
	return (NULL);
}

/****************************************************************************
** function: GetConnection()
**
** parameters:  An allocated URL and the IP number of the host to connect
** to.
**
** postconditions:  The socket is returned to the structure.
****************************************************************************/
static SockCntlRec *GetConnection(URL * theURL, long theIPnum)
{
	SockCntlRec *locSockRec;
	int errNum;
	char errorReply[SERV_REPLY_LENGTH];
	char errorIgnore[SERV_REPLY_LENGTH];

	locSockRec = (SockCntlRec *) malloc(sizeof(SockCntlRec));

	if (!locSockRec) {
		DoError(MEMORY_ERROR, NULL);
		return NULL;
	}
	/* Configure a new socket. */
	locSockRec->socketInfo = theURL;
	locSockRec->theHostIP = theIPnum;
	locSockRec->timerid = SetTimer(timeOut, ExpireSocket);
	locSockRec->incomDataBuf = NULL;
	locSockRec->incomDataFile = NULL;
	locSockRec->incomDataSize = 0;
	locSockRec->listPrev = NULL;
	locSockRec->listNext = NULL;
	locSockRec->hashPrev = NULL;
	locSockRec->hashNext = NULL;
	locSockRec->theSocket = FTPInit(theIPnum, theURL->port, errorReply);


	if (locSockRec->theSocket < 0) {
		DoError(locSockRec->theSocket, errorReply);
		free_url(theURL);
		theURL = NULL;
		free((char *) locSockRec);
		return NULL;
	}
	/* Try to Login, if not successful, close the connection. */
	if ((errNum = Login(theURL->user, theURL->password,
		    locSockRec->theSocket, TRUE, errorReply)) < 0) {
		CancelTimer(locSockRec->timerid);
		Disconnect(locSockRec->theSocket, errorIgnore);
		free_url(locSockRec->socketInfo);
		theURL = NULL;
		free((char *) locSockRec);
		locSockRec = NULL;

		if (errNum != SERV_REPLY_ERROR)
			DoError(errNum, NULL);
		else
			DoError(errNum, errorReply);
	}
	return (locSockRec);
}

/*********************************************************************
** function: DisconnectOne()
**
** parameters: None
**
** postconditions: Attempts to disconnect the oldest inactive connection.
*********************************************************************/
Boolean DisconnectOne()
{
	SockCntlRec *locSockRec;