wn.h

一个与传统电子字典不同的字典

/*
   
   wn.h - header file needed to use WordNet Run Time Library

   $Id: wn.h,v 1.60 2005/03/02 16:36:39 wn Exp $

*/

#ifdef HAVE_CONFIG_H
#include "config.h"
#endif

#ifndef _WN_
#define _WN_

#include <stdio.h>

/* Platform specific path and filename specifications */

#ifdef _WINDOWS
#define DICTDIR         "\\dict"
#define DEFAULTPATH	"C:\\Program Files\\WordNet\\2.1\\dict"
#define DATAFILE	"%s\\data.%s"
#define INDEXFILE	"%s\\index.%s"
#define SENSEIDXFILE	"%s\\index.sense"
#define KEYIDXFILE	"%s\\index.key"
#define REVKEYIDXFILE	"%s\\index.key.rev"
#define VRBSENTFILE  	"%s\\sents.vrb"
#define VRBIDXFILE	"%s\\sentidx.vrb"
#define CNTLISTFILE     "%s\\cntlist.rev"
#else
#define DICTDIR         "/dict"
#define DEFAULTPATH	"/usr/local/WordNet-2.1/dict"
#define DATAFILE	"%s/data.%s"
#define INDEXFILE	"%s/index.%s"
#define SENSEIDXFILE	"%s/index.sense"
#define KEYIDXFILE	"%s/index.key"
#define REVKEYIDXFILE	"%s/index.key.rev"
#define VRBSENTFILE     "%s/sents.vrb"
#define VRBIDXFILE	"%s/sentidx.vrb"
#define CNTLISTFILE     "%s/cntlist.rev"
#endif

/* Various buffer sizes */

#define SEARCHBUF	((long)(200*(long)1024))
#define LINEBUF		(15*1024) /* 15K buffer to read index & data files */
#define SMLINEBUF	(3*1024) /* small buffer for output lines */
#define WORDBUF		(256)	/* buffer for one word or collocation */

#define ALLSENSES	0	/* pass to findtheinfo() if want all senses */
#define MAXID		15	/* maximum id number in lexicographer file */
#define MAXDEPTH	20	/* maximum tree depth - used to find cycles */
#define MAXSENSE	75	/* maximum number of senses in database */
#define MAX_FORMS	5	/* max # of different 'forms' word can have */
#define MAXFNUM		44	/* maximum number of lexicographer files */

/* Pointer type and search type counts */

/* Pointers */

#define ANTPTR           1	/* ! */
#define HYPERPTR         2	/* @ */
#define HYPOPTR          3	/* ~ */
#define ENTAILPTR        4	/* * */
#define SIMPTR           5	/* & */

#define ISMEMBERPTR      6	/* #m */
#define ISSTUFFPTR       7	/* #s */
#define ISPARTPTR        8	/* #p */

#define HASMEMBERPTR     9	/* %m */
#define HASSTUFFPTR     10	/* %s */
#define HASPARTPTR      11	/* %p */

#define MERONYM         12	/* % (not valid in lexicographer file) */
#define HOLONYM         13	/* # (not valid in lexicographer file) */
#define CAUSETO         14	/* > */
#define PPLPTR	        15	/* < */
#define SEEALSOPTR	16	/* ^ */
#define PERTPTR		17	/* \ */
#define ATTRIBUTE	18	/* = */
#define VERBGROUP	19	/* $ */
#define DERIVATION      20	/* + */
#define CLASSIFICATION  21	/* ; */
#define CLASS           22	/* - */

#define LASTTYPE	CLASS

/* Misc searches */

#define SYNS            (LASTTYPE + 1)
#define FREQ            (LASTTYPE + 2)
#define FRAMES          (LASTTYPE + 3)
#define COORDS          (LASTTYPE + 4)
#define RELATIVES	(LASTTYPE + 5)
#define HMERONYM        (LASTTYPE + 6)
#define HHOLONYM	(LASTTYPE + 7)
#define WNGREP		(LASTTYPE + 8)
#define OVERVIEW	(LASTTYPE + 9)

#define MAXSEARCH       OVERVIEW

#define CLASSIF_START    (MAXSEARCH + 1)

#define CLASSIF_CATEGORY (CLASSIF_START)        /* ;c */
#define CLASSIF_USAGE    (CLASSIF_START + 1)    /* ;u */
#define CLASSIF_REGIONAL (CLASSIF_START + 2)    /* ;r */

#define CLASSIF_END      CLASSIF_REGIONAL

#define CLASS_START      (CLASSIF_END + 1)

#define CLASS_CATEGORY   (CLASS_START)          /* -c */
#define CLASS_USAGE      (CLASS_START + 1)      /* -u */
#define CLASS_REGIONAL   (CLASS_START + 2)      /* -r */

#define CLASS_END        CLASS_REGIONAL

#define INSTANCE         (CLASS_END + 1)        /* @i */
#define INSTANCES        (CLASS_END + 2)        /* ~i */

#define MAXPTR          INSTANCES

/* WordNet part of speech stuff */

#define NUMPARTS	4	/* number of parts of speech */
#define NUMFRAMES	35	/* number of verb frames */

/* Generic names for part of speech */

#define NOUN		1
#define VERB		2
#define ADJ		3
#define ADV		4
#define SATELLITE	5	/* not really a part of speech */
#define ADJSAT		SATELLITE

#define ALL_POS		0	/* passed to in_wn() to check all POS */

#define bit(n) ((unsigned int)((unsigned int)1<<((unsigned int)n)))

/* Adjective markers */

#define PADJ		1	/* (p) */
#define NPADJ		2	/* (a) */
#define IPADJ		3	/* (ip) */

#define UNKNOWN_MARKER		0
#define ATTRIBUTIVE		NPADJ
#define PREDICATIVE		PADJ
#define IMMED_POSTNOMINAL	IPADJ

extern char *wnrelease;		/* WordNet release/version number */

extern char *lexfiles[];	/* names of lexicographer files */
extern char *ptrtyp[];		/* pointer characters */
extern char *partnames[];	/* POS strings */
extern char partchars[];	/* single chars for each POS */
extern char *adjclass[];	/* adjective class strings */
extern char *frametext[];	/* text of verb frames */

/* Data structures used by search code functions. */

/* Structure for index file entry */
typedef struct {
    long idxoffset;		/* byte offset of entry in index file */
    char *wd;			/* word string */
    char *pos;			/* part of speech */
    int sense_cnt;		/* sense (collins) count */
    int off_cnt;		/* number of offsets */
    int tagged_cnt;		/* number senses that are tagged */
    unsigned long *offset;	/* offsets of synsets containing word */
    int ptruse_cnt;		/* number of pointers used */
    int *ptruse;		/* pointers used */
} Index;

typedef Index *IndexPtr;

/* Structure for data file synset */
typedef struct ss {
    long hereiam;		/* current file position */
    int sstype;			/* type of ADJ synset */
    int fnum;			/* file number that synset comes from */
    char *pos;			/* part of speech */
    int wcount;			/* number of words in synset */
    char **words;		/* words in synset */
    int *lexid;			/* unique id in lexicographer file */
    int *wnsns;			/* sense number in wordnet */
    int whichword;		/* which word in synset we're looking for */
    int ptrcount;		/* number of pointers */
    int *ptrtyp;		/* pointer types */
    long *ptroff;		/* pointer offsets */
    int *ppos;			/* pointer part of speech */
    int *pto;			/* pointer 'to' fields */
    int *pfrm;			/* pointer 'from' fields */
    int fcount;			/* number of verb frames */
    int *frmid;			/* frame numbers */
    int *frmto;			/* frame 'to' fields */
    char *defn;			/* synset gloss (definition) */
    unsigned int key;		/* unique synset key */

    /* these fields are used if a data structure is returned
       instead of a text buffer */

    struct ss *nextss;		/* ptr to next synset containing searchword */
    struct ss *nextform;	/* ptr to list of synsets for alternate
				   spelling of wordform */
    int searchtype;		/* type of search performed */
    struct ss *ptrlist;		/* ptr to synset list result of search */
    char *headword;		/* if pos is "s", this is cluster head word */
    short headsense;		/* sense number of headword */
} Synset;

typedef Synset *SynsetPtr;

typedef struct si {
    char *sensekey;		/* sense key */
    char *word;			/* word string */
    long loc;			/* synset offset */
    int wnsense;		/* WordNet sense number */
    int tag_cnt;		/* number of semantic tags to sense */
    struct si *nextsi;		/* ptr to next sense index entry */
} SnsIndex;

typedef SnsIndex *SnsIndexPtr;
    
typedef struct {
    int SenseCount[MAX_FORMS];	/* number of senses word form has */
    int OutSenseCount[MAX_FORMS]; /* number of senses printed for word form */
    int numforms;		/* number of word forms searchword has */
    int printcnt;		/* number of senses printed by search */
    char *searchbuf;		/* buffer containing formatted results */
    SynsetPtr searchds;		/* data structure containing search results */
} SearchResults;

typedef SearchResults *SearchResultsPtr;

/* Global variables and flags */

extern SearchResults wnresults;	/* structure containing results of search */
extern int fnflag;		/* if set, print lex filename after sense */
extern int dflag;		/* if set, print definitional glosses */
extern int saflag;		/* if set, print SEE ALSO pointers */
extern int fileinfoflag;	/* if set, print lex file info on synsets */
extern int frflag;		/* if set, print verb frames after synset */
extern int abortsearch;		/* if set, stop search algorithm */
extern int offsetflag;		/* if set, print byte offset of each synset */
extern int wnsnsflag;		/* if set, print WN sense # for each word */

/* File pointers for database files */

extern int OpenDB;		/* if non-zero, database file are open */
extern FILE *datafps[NUMPARTS + 1], 
            *indexfps[NUMPARTS + 1],
            *sensefp,
            *cntlistfp,
            *keyindexfp, *revkeyindexfp,
            *vidxfilefp, *vsentfilefp;

/* Method for interface to check for events while search is running */