template.h

harvest是一个下载html网页得机器人

/*
 *  template.h - SOIF template processing support
 *
 *  Darren Hardy, [e-mail], July 1994
 *
 *  template.h,v 1.11 1995/09/05 19:09:33 hardy Exp
 *
 *  ----------------------------------------------------------------------
 *  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.
 *
 */
#ifndef _TEMPLATE_H_
#define _TEMPLATE_H_

#include <stdio.h>
#include "config.h"

/* Attribute-Value pair */
struct attr_value {
	char *attribute;	/* Attribute string; '\0' terminated */
	char *value;		/* Value data; not '\0' terminated */
	size_t vsize;		/* # of bytes in the value data */
	size_t offset;		/* Starting byte of the value data in input */
};
typedef struct attr_value AVPair;

/* List of Attribute-Value pairs */
struct attr_value_list {
	AVPair *data;
	struct attr_value_list *next;
};
typedef struct attr_value_list AVList;

/* SOIF Template structure */
struct template {
	char *template_type;	/* type of template */
	char *url;		/* URL for template */
	AVList *list;		/* List of Attribute-Value pairs */
	size_t offset;		/* Starting byte of the template; the @ */
	size_t length;		/* # of bytes that the template covers */
};
typedef struct template Template;


/* Common Attribute Tags */
#define T_ABSTRACT	"Abstract"
#define T_AUTHOR	"Author"
#define T_DESCRIPTION	"Description"
#define T_FILESIZE	"File-Size"
#define T_FULLTEXT	"Full-Text"
#define T_GENERATION	"Generation-Time"
#define T_GHOST		"Gatherer-Host"
#define T_GNAME		"Gatherer-Name"
#define T_GVERSION	"Gatherer-Version"
#define T_HEADINGS	"Headings"               /* hw */
#define T_KEYS		"Keywords"
#define T_LMT		"Last-Modification-Time"
#define T_MD5		"MD5"
#define T_NESTED	"Nested-Filename"
#define T_PARTTEXT	"Partial-Text"
#define T_REFERENCE	"References"
#define T_REFRESH	"Refresh-Rate"
#define T_RELATED	"Related"
#define T_TITLE		"Title"
#define T_TTL		"Time-to-Live"
#define T_TYPE		"Type"
#define T_UPDATE	"Update-Time"
#ifdef USE_T_URI
#define T_URI		"URI"
#endif
#if 0
#define T_URL		"URL"
#endif
#define T_UREFS		"URL-References"

/* Backwards compatibility */
#define T_FILETYPE	T_TYPE
#define T_TIMESTAMP	T_LMT

/* Common time_t numbers */
#define HOUR	((time_t) 60 * 60)
#define DAY	((time_t) HOUR * 24)
#define WEEK    ((time_t) DAY * 7)
#define MONTH	((time_t) WEEK * 4)
#define YEAR	((time_t) MONTH * 12)

#ifndef _PARAMS
#if defined(__STDC__) || defined(__cplusplus) || defined(__STRICT_ANSI__)
#define _PARAMS(ARGS) ARGS
#else /* Traditional C */
#define _PARAMS(ARGS) ()
#endif /* __STDC__ */
#endif /* _PARAMS */

/* Templates */
Template *create_template _PARAMS((char *, char *));
Template *embed_template _PARAMS((Template *, Template *));
void free_template _PARAMS((Template *));

/* Attribute-Value pairs */
AVList *create_AVList _PARAMS((char *, char *, int));
void add_AVList _PARAMS((AVList *, char *, char *, int));
void FAST_add_AVList _PARAMS((AVList *, char *, char *, int));
void append_AVList _PARAMS((AVList *, char *, char *, int));
AVPair *extract_AVPair _PARAMS((AVList *, char *));
AVList *merge_AVList _PARAMS((AVList *, AVList *));
AVList *sort_AVList _PARAMS((AVList *));
AVList *sink_embedded _PARAMS((AVList *));
int exists_AVList _PARAMS((AVList *, char *));
void free_AVPair _PARAMS((AVPair *));
void free_AVList _PARAMS((AVList *));

/* Printing Templates */
Buffer *init_print_template _PARAMS((FILE *));
void print_template _PARAMS((Template *));
void print_template_header _PARAMS((Template *));
void print_template_body _PARAMS((Template *));
void print_template_trailer _PARAMS((Template *));
void finish_print_template _PARAMS(());

/* Parsing Templates */
void init_parse_template_file _PARAMS((FILE *));
void init_parse_template_string _PARAMS((char *, int));
Template *parse_template _PARAMS(());
void finish_parse_template _PARAMS(());
int is_parse_end_of_input _PARAMS(());

#endif /* _TEMPLATE_H_ */