url.h

Larbin互联网蜘蛛索引系统

// Larbin
// Sebastien Ailleret
// 15-11-99 -> 02-12-99

/* This class describes an URL */

#ifndef URL_H
#define URL_H

#include <stdlib.h>

#include "types.h"
#include "xutils/string.h"

struct global;

class url {
 private:
  char *host;
  uint port;
  char *file;
  uint depth;
  /* parse the url */
  void parse (char *s);
  /** parse a file with base */
  void parseWithBase (char *u, char *base);
  /* normalize file name */
  bool normalize (char *file);
  /* Does this url starts with a protocol name */
  bool isProtocol (char *s);

 public:
  /* Constructor : Parses an url (u is deleted) */
  url (char *u, uint depth, char *base = NULL);

  /* Constructor : read the url from a file (cf serialize) */
  url (String *line);

  /* Destructor */
  ~url ();

  /* Is it a valid url ? */
  int isValid ();

  /* print an URL */
  void print ();

  /* return the host */
  char *getHost ();

  /* return the port */
  uint getPort ();

  /* return the file */
  char *getFile ();

  /** Depth in the Site */
  uint getDepth ();

  /** Set depth to one if we are at an entry point in the site */
  void setDepth (char *fromHost);

  /** return the base of the url
   * give means that you have to delete the string yourself
   */
  char *giveBase ();

  /** return a char * representation of the url
   * give means that you have to delete the string yourself
   */
  char *giveUrl ();

  /* return a hashcode for the host of this url */
  uint hostHashCode ();

  /* return a hashcode for this url */
  uint hashCode ();

  /* serialize the url */
  char *serialize (int fds);
};

#endif // URL_H