Hypertext "Anchor" Object

/*
**	(c) COPYRIGHT MIT 1995.
**	Please first read the full copyright statement in the file COPYRIGH.
*/
An anchor represents a region of a hypertext document which is linked to another anchor in the same or a different document. As always we must emulate the fancy features of C++ by hand :-(. In this module you find: This module is implemented by HTAnchor.c, and it is a part of the W3C Reference Library.

History

#ifndef HTANCHOR_H
#define HTANCHOR_H

#include "HTList.h"
#include "HTAtom.h"
#include "HTMethod.h"

Types for Atoms

 This is a set of videly used type definitions used through out the Library: 
typedef HTAtom * HTFormat;
typedef HTAtom * HTLevel;		       /* Used to specify HTML level */
typedef HTAtom * HTEncoding;				 /* Content Encoding */
typedef HTAtom * HTCte;				/* Content transfer encoding */
typedef HTAtom * HTCharset;
typedef HTAtom * HTLanguage;

Anchor data structures

 We have to do this in order to make forward references. 
typedef struct _HyperDoc HyperDoc;  /* Ready for forward references */
typedef struct _HTAnchor HTAnchor;
typedef struct _HTParentAnchor HTParentAnchor;
typedef struct _HTChildAnchor HTChildAnchor;
Must be AFTER definition of HTAnchor: 
typedef HTAtom HTLinkType;

typedef enum _HTLinkResult
{
    HT_LINK_INVALID = -1,
    HT_LINK_NONE = 0,
    HT_LINK_ERROR,
    HT_LINK_OK
} HTLinkResult;

typedef struct {
    HTAnchor *		dest;		   /* The anchor to which this leads */
    HTLinkType *	type;		           /* Semantics of this link */
    HTMethod		method;		   /* Method for this link, e.g. PUT */
    HTLinkResult	result;    /* Result of any attempt to get this link */
} HTLink;

Generic Anchor type

 This is the super class of anchors. We often use this as an argument to the functions that both accept parent anchors and child anchors. We separate the first link from the others to avoid too many small mallocs involved by a list creation. Most anchors only point to one place. 
struct _HTAnchor {
  HTLink	mainLink;	/* Main (or default) destination of this */
  HTList *	links;  	/* List of extra links from this, if any */
  HTParentAnchor * parent;	/* Parent of this anchor (self for adults) */
};

Anchor for a Parent Object

 These anchors points to the whole contents of a graphic object (document). The parent anchor of a parent anchor is itself. The parent anchor now contains all meta information about the object. This is largely the entity headers in the HTTP specification. 
struct _HTParentAnchor {
  /* Common part from the generic anchor structure */
  HTLink	mainLink;	/* Main (or default) destination of this */
  HTList *	links;  	/* List of extra links from this, if any */
  HTParentAnchor * parent;	/* Parent of this anchor (self) */

  /* ParentAnchor-specific information */
  HTList *	children;	/* Subanchors of this, if any */
  HTList *	sources;	/* List of anchors pointing to this, if any */
  HyperDoc *	document;	/* The document within this is an anchor */
  char *	physical;	/* Physical address */
  BOOL		cacheHit;	/* Yes, if cached object found */
  char * 	address;	/* Absolute address of this node */
  BOOL		isIndex;	/* Acceptance of a keyword search */

  /* Entity header fields */
  BOOL		header_parsed;	/* Are we done parsing? */

  char *	title;
  int		methods;	/* Allowed methods (bit-flag) */

  HTEncoding	content_encoding;
  HTLanguage	content_language;	/* @@@ SHOULD BE LIST @@@ */
  long int	content_length;
  HTCte		cte;		/* Content-Transfer-Encoding */
  HTFormat	content_type;
  HTCharset	charset;	/* Parameter to content-type */
  HTLevel	level;		/* Parameter to content-type `text/html' */

  time_t	date;		/* When was the request issued */  
  time_t	expires;	/* When does the copy expire */
  time_t	last_modified;

  char *	derived_from;	/* Opaque string */
  char *	version;	/* Opaque string */

  /* List of unknown headers coming in from the network. Use the field in the
     request structure for sending test headers. */
  HTList *	extra_headers;
};

Anchor for a Child Object

 A child anchor is a anchor object that points to a subpart of a graphic object (document) 
struct _HTChildAnchor {
  /* Common part from the generic anchor structure */
  HTLink	mainLink;	/* Main (or default) destination of this */
  HTList *	links;  	/* List of extra links from this, if any */
  HTParentAnchor * parent;	/* Parent of this anchor */

  /* ChildAnchor-specific information */
  char * 	tag;		/* Address of this anchor relative to parent */
};

Creation and Deletion Methods

 After we have defined the data structures we must define the methods that can be used on them. All anchors are kept in an internal hash table so that they are easier to find again.

Find/Create a Parent Anchor

This one is for a reference (link) which is found in a document, and might not be already loaded. The parent anchor returned can either be created on the spot or is already in the hash table. 
extern HTAnchor * HTAnchor_findAddress		(CONST char * address);

Find/Create a Child Anchor

This one is for a new child anchor being edited into an existing document. The parent anchor must already exist but the child returned can either be created on the spot or is already in the hash table. The tag is the part that's after the '#' sign in a URI. 
extern HTChildAnchor * HTAnchor_findChild	(HTParentAnchor *parent,
						 CONST char *	tag);

Find/Create a Child Anchor and Link to Another Parent

Find a child anchor anchor with a given parent and possibly a tag, and (if passed) link this child to the URI given in the href. As we really want typed links to the caller should also indicate what the type of the link is (see HTTP spec for more information). The link is relative to the address of the parent anchor. 
extern HTChildAnchor * HTAnchor_findChildAndLink
		(HTParentAnchor * parent,		/* May not be 0 */
		CONST char * tag,			/* May be "" or 0 */
		CONST char * href,			/* May be "" or 0 */
		HTLinkType * ltype);			/* May be 0 */

Delete an Anchor

All outgoing links from parent and children are deleted, and this anchor is removed from the sources list of all its targets. We also delete the targets. If this anchor's source list is empty, we delete it and its children. 
extern BOOL HTAnchor_delete	(HTParentAnchor *me);

Delete all Anchors

Deletes all anchors and return a list of all the HyperDocs found while doing it. The application may keep its own list of HyperDocs, but this function returns it anyway. It is always for the application to delete any HyperDocs. If NULL then no hyperdocs are returned. Return YES if OK, else NO.

Note: This function is different from cleaning up the history list! 

extern BOOL HTAnchor_deleteAll	(HTList * objects);

The Link Object

 Anchors are bound together using link objects. Each anchor can be the source or destination of zero, one, or more links from and to other anchors.

Link this Anchor to another given one

A single anchor may have many outgoing links of which the default is the main link. If one already exists then this new link is simply added to the list. 
extern BOOL HTAnchor_link	(HTAnchor *	source,
				 HTAnchor *	destination,
				 HTLinkType *	type,
				 HTMethod	method);

Find the Link Object that Binds two Anchors

If the destination anchor is a target of a link from the source anchor then return the link object, else NULL. 
extern HTLink *HTAnchor_findLink (HTAnchor *src, HTAnchor *dest);
#define HTAnchor_findMainLink(me) ((me) ? &((me)->mainLink) : NULL)

Find The Method of a Link

The method used in a link can be PUT, or POST, for example 
#define HTAnchor_linkMethod(me)	((me) ? (me)->method : METHOD_INVALID)

Find destination of a Link

Find the anchor which is the main target of this anchor. 
extern HTAnchor * HTAnchor_followMainLink (HTAnchor *me);
#define HTAnchor_linkDest(me) ((me) ? (me)->dest : NULL)

Find destination with given relationship

Return the anchor with a given typed link. 
extern HTAnchor * HTAnchor_followTypedLink (HTAnchor *me, HTLinkType *type);

Result of a Link

When a link has been used for posting an object from a source to a destination link, the result of the operation is stored as part of the link information. 
#define HTAnchor_linkResult(me)	((me) ? me->result : HT_LINK_INVALID)
extern BOOL HTAnchor_setLinkResult	(HTLink * link, HTLinkResult result);

Make a particular link the main link

Any outgoing link can at any time be the main destination. 
extern BOOL HTAnchor_makeMainLink	(HTAnchor *me, HTLink *movingLink);

Move Link Information

Move all link information form one anchor to another. This is useful when we get a redirection on a request and want to inherit the link information to the new anchor and change the link information in the old one to "redirect". 
extern BOOL HTAnchor_moveAllLinks	(HTAnchor *src, HTAnchor *dest);

Remove Link Information

Delete link information between two or more anchors 
extern BOOL HTAnchor_removeLink		(HTAnchor *src, HTAnchor *dest);
extern BOOL HTAnchor_removeAllLinks	(HTAnchor * me);

Move a child anchor to the head of the list of its siblings

This is to ensure that an anchor which might have already existed is put in the correct order as we load the document. 
extern void HTAnchor_makeLastChild	(HTChildAnchor *me);

Access Methods of an Anchor

 These functions should be used to access information within the anchor structures.

Relations to Other Anchors

Who is Parent?

For parent anchors this returns the anchor itself 
extern HTParentAnchor * HTAnchor_parent	(HTAnchor *me);

Does it have any Anchors within it?

extern BOOL HTAnchor_hasChildren	(HTParentAnchor *me);

Graphic Object (HyperDoc)

HyperDoc is the application defined data structure that contains a graphic object in memory.

Assign a HyperDoc to an Anchor

extern void HTAnchor_setDocument	(HTParentAnchor *me, HyperDoc *	doc);

Return the HyperDoc of an anchor (if any)

extern HyperDoc * HTAnchor_document	(HTParentAnchor *me);

URI Information of Anchors

There are two addresses of an anchor. The URI that was passed when the anchor was crated and the physical address that's used when the URI is going to be requested. The two addresses may be different if the request is going through a proxy or a gateway.

Get URI Address

Returns the full URI of the anchor, child or parent as a malloc'd string to be freed by the caller as when th eanchor was created. 
extern char * HTAnchor_address		(HTAnchor *me);

Cache Information

If the cache manager finds a cached obejct, it is registered in the anchor object. This way the file loader knows that it is a MIME data object. The cache manager does not know whether the data object is out of date (for example if a Expires: header is in the MIME header. This is for the MIME parser to find out. 
extern BOOL HTAnchor_cacheHit		(HTParentAnchor	*me);
extern void HTAnchor_setCacheHit	(HTParentAnchor	*me, BOOL cacheHit);

Physical address

Contains the physical address after we haved looked for proxies etc. 
extern char * HTAnchor_physical		(HTParentAnchor * me);

extern void HTAnchor_setPhysical	(HTParentAnchor * me, char * protocol);

Is the Anchor searchable?

extern void HTAnchor_clearIndex		(HTParentAnchor *me);
extern void HTAnchor_setIndex		(HTParentAnchor *me);
extern BOOL HTAnchor_isIndex		(HTParentAnchor *me);

What Protocol should be Used

extern void * HTAnchor_protocol		(HTParentAnchor * me);
extern void HTAnchor_setProtocol	(HTParentAnchor * me, void* protocol);

Title handling

We keep the title in the anchor as we then can refer to it later in the history list etc. We can also obtain the title element if it is passed as a HTTP header in the response. Any title element found in an HTML document will overwrite a title given in a HTTP header. 
extern CONST char * HTAnchor_title	(HTParentAnchor *me);

extern void HTAnchor_setTitle		(HTParentAnchor *me,
					 CONST char *	title);

extern void HTAnchor_appendTitle	(HTParentAnchor *me,
					 CONST char *	title);

Media Types (Content-Type)

extern HTFormat HTAnchor_format		(HTParentAnchor *me);
extern void HTAnchor_setFormat		(HTParentAnchor *me,
					 HTFormat	form);

Charset parameter to Content-Type

extern HTCharset HTAnchor_charset	(HTParentAnchor *me);
extern void HTAnchor_setCharset		(HTParentAnchor *me,
					 HTCharset	charset);

Level parameter to Content-Type

extern HTLevel HTAnchor_level		(HTParentAnchor * me);
extern void HTAnchor_setLevel		(HTParentAnchor * me,
					 HTLevel	level);

Content Language

extern HTLanguage HTAnchor_language	(HTParentAnchor *me);
extern void HTAnchor_setLanguage	(HTParentAnchor *me,
					 HTLanguage	language);

Content Encoding

extern HTEncoding HTAnchor_encoding	(HTParentAnchor *me);
extern void HTAnchor_setEncoding	(HTParentAnchor *me,
					 HTEncoding	encoding);

Content Transfer Encoding

extern HTCte HTAnchor_cte		(HTParentAnchor *me);
extern void HTAnchor_setCte		(HTParentAnchor *me,
					 HTCte		cte);

Content Length

extern long int HTAnchor_length		(HTParentAnchor *me);
extern void HTAnchor_setLength		(HTParentAnchor *me,
					 long int	length);

Allowed methods (Allow)

extern int HTAnchor_methods		(HTParentAnchor *me);
extern void HTAnchor_setMethods		(HTParentAnchor *me,
					 int		methodset);
extern void HTAnchor_appendMethods	(HTParentAnchor *me,
					 int		methodset);

Version

extern CONST char * HTAnchor_version	(HTParentAnchor *me);
extern void HTAnchor_setVersion		(HTParentAnchor *me,
					 CONST char *	version);

Date

Returns the date that was registered in the RFC822 header "Date" 
#define HTAnchor_date(me)		((me) ? (me)->date : -1)
extern void HTAnchor_setDate		(HTParentAnchor	*me,
					 CONST time_t	*date);

Last Modified Date

Returns the date that was registered in the RFC822 header "Last-Modified" 
#define HTAnchor_lastModified(me)	((me) ? (me)->last_modified : -1)
extern void HTAnchor_setLastModified	(HTParentAnchor	*me,
					 CONST time_t	*lm);

Expires Date

#define HTAnchor_expires(me)		((me) ? (me)->expires : -1)
extern void HTAnchor_setExpires		(HTParentAnchor	*me,
					 CONST time_t	*expires);

Derived from

extern CONST char * HTAnchor_derived	(HTParentAnchor *me);
extern void HTAnchor_setDerived		(HTParentAnchor *me,
					 CONST char *	derived_from);

Extra Headers

List of unknown headers coming in from the network. Do not use the HTAnchor_addExtra() function to extra headers here, but use the field in the request structure for sending test headers. 
extern HTList * HTAnchor_Extra		(HTParentAnchor *me);
extern void HTAnchor_addExtra		(HTParentAnchor *me,
					 CONST char *	header);

Status of Header Parsing

These are primarily for internal use 
extern BOOL HTAnchor_headerParsed	(HTParentAnchor *me);
extern void HTAnchor_setHeaderParsed	(HTParentAnchor *me);

We want to clear the header information...

extern void HTAnchor_clearHeader	(HTParentAnchor *me);

#endif /* HTANCHOR_H */