main.c

这是用C写的中文分词程序

#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#include "pws.h"

int main( int argc, char ** argv )
{
	char buf[256];
	FILE * fp = 0;
	const char * p_dict = "./dict.dat";
	long total = 0, i = 0, * wordid = 0;
	const char ** words = 0;

	if ( argc < 2 )
	{
		fprintf( stdout, "usage:\n\tunit_t <content file>\n\n" );
		return 0;
	}

	fp = fopen( argv[1], "r" );
	if ( fp == 0 )
	{
		fprintf( stderr, "open content file failed.\n" );
		return 3;
	}

	/* create a word segmentor result object with pws_res_create() */
	pws_result_t * pws_res = pws_res_create();
	if ( pws_res == 0 )
	{
		fclose( fp );
		fprintf( stderr, "create word splitter object failed.\n" );
		return 1;
	}

	if ( pws_initialize(p_dict) != 0 )
	{
		fclose( fp );
		pws_res_free( &pws_res );
		fprintf( stderr, "wordsplitter initialization failed.\n" );
		return 2;
	}

	while ( fgets(buf,256,fp) != 0 )
	{
		pws_segment_full( buf, strlen(buf), pws_res );
		total = pws_res_words( pws_res, &wordid, &words );
		fprintf( stdout, "%s:", buf );
		for ( i=0; i<total; i++ )
			fprintf( stdout, "%s(%ld) ", *(words+i), *(wordid+i) );
		fprintf( stdout, "\n" );
		pws_res_clean( pws_res );
	}
	
	pws_res_free( &pws_res );

	fclose( fp );

	pws_release();
	return 0;
}