unnest.c

harvest是一个下载html网页得机器人

static char rcsid[] = "unnest.c,v 1.55 1996/03/26 04:12:12 wessels Exp";
/*
 *  unnest.c - Presentation Unnesting for the Essence system.
 *
 *  DEBUG: section  65, level 1         Gatherer essence object unnesting
 *
 *  Darren Hardy, [e-mail], February 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 <stdlib.h>
#include <unistd.h>
#include <string.h>
#include <memory.h>
#include <errno.h>
#include <sys/param.h>
#include <sys/types.h>
#include <fcntl.h>
#include <dirent.h>
#include <time.h>
#include "util.h"
#include "essence.h"

/* Local functions */
static int default_extract();	/* extraction routines */
static int extract_BZIP2Compressed();
static int extract_BZIP2CompressedTar();
static int extract_Compressed();
static int extract_CompressedTar();
static int extract_GNUCompressed();
static int extract_GNUCompressedTar();
static int extract_ShellArchive();
static int extract_Tar();
static int extract_Uuencoded();
static int extract_PCZipped();
static int extract_MacBinHex();
static char *filename_to_url();

/* recursion routines */
static DataObjectList *recurse_unix_directory();
static DataObjectList *recurse_external();

static int mk_timestamp();

/* Local variables */
static char extracted_filename[MAXPATHLEN + 1];
static char unnestdir[MAXPATHLEN + 1];
static time_t timestamp;

/*
 *  README for adding new Presentation Unnesting routines:
 *
 *  Methods for unnesting various types.  To add unnesting for a new type,
 *  write a new extraction routine and add (type, proc) to this table.
 *
 *  If extract is NULL, then the nested type is treated as an exploder.
 *  The program type.unnest is run with the URL as the first argument,
 *  and the filename that contains the data as the second argument.
 *  The program generates a stream of SOIF templates that contain
 *  manual information about the data.  To add a new exploder, add
 *  the type to this table, and set the extract field to NULL, then
 *  write a SOIF generated and install it as type.unnest.
 */
struct nested_type {
	char *type;		/* Nested file type */
	int (*extract) ();	/* how to extract the data */
	int do_timestamp;	/* timestamp to determine extracted files */
} nested_types[] = {

/* normal unnesting that generates new objects to process */
	{
		"BZIP2Compressed", extract_BZIP2Compressed, 0
	},
	{
		"BZIP2CompressedTar", extract_BZIP2CompressedTar, 1
	},
	{
		"Compressed", extract_Compressed, 0
	},
	{
		"CompressedTar", extract_CompressedTar, 1
	},
	{
		"GNUCompressed", extract_GNUCompressed, 0
	},
	{
		"GNUCompressedTar", extract_GNUCompressedTar, 1
	},
	{
		"ShellArchive", extract_ShellArchive, 1
	},
	{
		"Tar", extract_Tar, 1
	},
	{
		"Uuencoded", extract_Uuencoded, 1
	},
	{
		"PCZipped", extract_PCZipped, 1
	},
/* exploders that generate a stream of SOIF tmpls to use as manual info */
	{
		"Exploder", NULL, 0
	},
	{
		"IAFA", NULL, 0
	},
	{
		"LSM", NULL, 0
	},
#ifdef USE_PCINDEX
	{
		"PCIndex", NULL, 0
	},
	{
		"Cica-PCIndex", NULL, 0
	},
	{
		"Garbo-PCIndex", NULL, 0
	},
	{
		"Garbo-Win-PCIndex", NULL, 0
	},
	{
		"Hobbes-PCIndex", NULL, 0
	},
	{
		"Lowell-PCIndex", NULL, 0
	},
	{
		"Oakland-PCIndex", NULL, 0
	},
	{
		"Umich-PCIndex", NULL, 0
	},
#endif
	{
		"MacBinHex", extract_MacBinHex, 1
	},
/* currently unsupported */
	{
		"PCCompressed", default_extract, 0
	},
	{
		NULL, default_extract, 0
	}
};

/*
 *  presentation_unnest() - Determines if the given object is has
 *  any presentation nesting.  If the object is nested, then it
 *  unnests the object until no more nesting is uncovered.  Returns
 *  the list of unnested objects when the object is successfully unnested;
 *  otherwise, returns NULL.
 */
DataObjectList *presentation_unnest(object)
     DataObject *object;
{
	static DataObjectList *dol = NULL;
	DataObjectList *walker = NULL, *tdol = NULL;
	int cur;
	DIR *dirp;
	struct dirent *dp;
	struct stat sb;
	char buf[MAXPATHLEN + 1], *s;
#if 0
	/* we don't need a new directory for each nested item, use a
	 * temporary directory for all nested objects. kjl/3oct2000
	 */
	static char unnestsubdir[MAXPATHLEN + 1];
	static int count = 0;
#endif

	Debug(65, 1, ("Unnesting: %s\n", object->url->url));

	/* Check to see if we simply need to recurse to unnest */
	if (object->url->type == URL_FILE &&
	    !strcmp(object->type, "Directory")) {
		return (recurse_unix_directory(object));
	}
	/* Locate the object's type in the unnesting configuration table */
	for (cur = 0; nested_types[cur].type != NULL; cur++) {
		if (!strcmp(nested_types[cur].type, object->type)) {
			break;
		}
	}
	if (nested_types[cur].type == NULL) {
		errorlog("pn: %s not a unnestable type\n", object->type);
		return (NULL);
	}
	if (nested_types[cur].extract == NULL) {
		char cmd[BUFSIZ];

		if (object_retrieve(object)) {
			return (NULL);
		}
		sprintf(cmd, "%s.unnest '%s' '%s'", nested_types[cur].type,
		    object->url->url, object->url->filename);
		return (recurse_external(object, cmd));
	}
	if (object->flags & F_NO_ACCESS)
		return (NULL);

	/*
	 *  We check for the newly created files, two ways: 1) we generate
	 *  the new filenames based on the old filename (eg. foo.Z -> foo),
	 *  or we check stat(2) to see which files were created recently.
	 */
	if (nested_types[cur].do_timestamp && mk_timestamp())
		return (NULL);

#if 0
	/* we don't need subdirectory. kjl/10oct2000 */
	sprintf(unnestsubdir, "%s/%05d", unnestdir, ++count);
	if (mkdir(unnestsubdir, 0775) < 0) {
		log_errno2(__FILE__, __LINE__, unnestsubdir);
		return (NULL);
	}
#endif
#if 0
	/* We'll need to create new file(s) in the unnestdir, so first cd */
	Debug(65, 1, ("presentation_unnest: chdir %s\n", unnestsubdir));
	if (chdir(unnestsubdir) < 0) {
		log_errno2(__FILE__, __LINE__, unnestsubdir);
		return (NULL);
	}
#endif
	/* We'll need to create new file(s) in the unnestdir, so first cd */
	Debug(65, 1, ("presentation_unnest: chdir %s\n", unnestdir));
	if (chdir(unnestdir) < 0) {
		log_errno2(__FILE__, __LINE__, unnestdir);
		return (NULL);
	}
	/*
	 *  Run the Extraction process, then gather the extracted
	 *  files and return as DataObjectList
	 */
	if ((*nested_types[cur].extract) (object)) {
		if (chdir(topdir) < 0) {	/* go back to previous directory */
			log_errno2(__FILE__, __LINE__, topdir);
		}
		return (NULL);	/* extraction failed */
	}
	/* Go back to previous directory */
	Debug(65, 1, ("presentation_unnest: chdir %s\n", topdir));
	if (chdir(topdir) < 0) {
		log_errno2(__FILE__, __LINE__, topdir);
	}
	/* We already know the extracted file */
	if (nested_types[cur].do_timestamp == 0) {
		char *s = filename_to_url(extracted_filename);
		dol = create_dol(s, object->flags | F_TEMPORARY | F_NESTED);
		xfree(s);
		if (dol == NULL)
			return (NULL);
		if (object->parent_url)
			dol->object->parent_url = strdup(object->parent_url);
		else
			dol->object->parent_url = strdup(object->url->url);
		return (dol);
	}
	/*
	 *  We need to check the creation times to discover all of the
	 *  files generated.
	 */
	dol = walker = NULL;
#if 0
	if ((dirp = opendir(unnestsubdir)) == NULL) {
		log_errno2(__FILE__, __LINE__, unnestsubdir);
		errorlog("presentation_unnest: Cannot open directory: %s\n",
		    unnestsubdir);
		return (NULL);
	}
	while ((dp = readdir(dirp)) != NULL) {
		if (!strcmp(dp->d_name, ".") || !strcmp(dp->d_name, ".."))
			continue;
		sprintf(buf, "%s/%s", unnestsubdir, dp->d_name);
#endif
	if ((dirp = opendir(unnestdir)) == NULL) {
		log_errno2(__FILE__, __LINE__, unnestdir);
		errorlog("presentation_unnest: Cannot open directory: %s\n",
		    unnestdir);
		return (NULL);
	}
	while ((dp = readdir(dirp)) != NULL) {
		if (!strcmp(dp->d_name, ".") || !strcmp(dp->d_name, ".."))
			continue;
		sprintf(buf, "%s/%s", unnestdir, dp->d_name);
		if (lstat(buf, &sb) < 0) {
			log_errno2(__FILE__, __LINE__, buf);
			errorlog("presentation_unnest: Cannot stat: %s\n", buf);
			continue;
		}
		if (timestamp > sb.st_ctime)	/* old file */
			continue;
		if (!strcmp(object->basename, dp->d_name))	/* same file */
			continue;

		s = filename_to_url(buf);
		tdol = create_dol(s, object->flags | F_TEMPORARY | F_NESTED);