Internet Publisher's Toolbox 2.0

home *** CD-ROM | disk | FTP | other *** search

/ Internet Publisher's Toolbox 2.0 / Internet Publisher's Toolbox.iso / internet / ntserver / wtsource / stoplist.c < prev next >

Wrap

C/C++ Source or Header | 1994-02-16 | 7.7 KB | 487 lines

/* WIDE AREA INFORMATION SERVER SOFTWARE: No guarantees or restrictions. See the readme file for the full standard disclaimer. */ /* Copyright (c) CNIDR (see ../COPYRIGHT) */ /* this is a set of utilities for maintaining a stoplist * kind of a kludge. * * -brewster */ #ifndef lint static char *RCSid = "$Header: /usr/users/freewais/FreeWAIS-0.1/ir/stoplist.c,v 1.1 1993/02/16 15:05:35 freewais Exp $"; #endif /* Change log: * $Log: stoplist.c,v $ * Revision 1.1 1993/02/16 15:05:35 freewais * Initial revision * * Revision 1.2 92/02/12 13:50:01 jonathan * Added "$Log" so RCS will put the log message in the header * * */ #include "stoplist.h" #include "cutil.h" #include <string.h> static char stoplist_filename[MAX_FILENAME_LEN];/* dgg */ long stoplist_pointer = 0; char *stoplist[] = { "a", "about", "above", "according", "across", "actually", "adj", "after", "afterwards", "again", "against", "all", "almost", "alone", "along", "already", "also", "although", "always", "among", "amongst", "an", "and", "another", "any", "anyhow", "anyone", "anything", "anywhere", "are", "aren't", "around", "as", "at", "b", "be", "became", "because", "become", "becomes", "becoming", "been", "before", "beforehand", "begin", "beginning", "behind", "being", "below", "beside", "besides", "between", "beyond", "billion", "both", "but", "by", "c", "can", "can't", "cannot", "caption", "co", "co.", "could", "couldn't", "d", "did", "didn't", "do", "does", "doesn't", "don't", "down", "during", "e", "each", "eg", "eight", "eighty", "either", "else", "elsewhere", "end", "ending", "enough", "etc", "even", "ever", "every", "everyone", "everything", "everywhere", "except", "f", "few", "fifty", "first", "five", "for", "former", "formerly", "forty", "found", "", "four", "from", "further", "g", "h", "had", "has", "hasn't", "have", "haven't", "he", "he'd", "he'll", "he's", "hence", "her", "here", "here's", "hereafter", "hereby", "herein", "hereupon", "hers", "herself", "him", "himself", "his", "how", "however", "hundred", "i", "i'd", "i'll", "i'm", "i've", "ie", "if", "in", "inc.", "indeed", "instead", "into", "is", "isn't", "it", "it's", "its", "itself", "j", "k", "l", "last", "later", "latter", "latterly", "least", "less", "let", "let's", "like", "likely", "ltd", "m", "made", "make", "makes", "many", "maybe", "me", "meantime", "meanwhile", "might", "million", "miss", "more", "moreover", "most", "mostly", "mr", "mrs", "much", "must", "my", "myself", "n", "namely", "neither", "never", "nevertheless", "next", "nine", "ninety", "no", "nobody", "none", "nonetheless", "noone", "nor", "not", "nothing", "now", "nowhere", "o", "of", "off", "often", "on", "once", "one", "one's", "only", "onto", "or", "other", "others", "otherwise", "our", "ours", "ourselves", "out", "over", "overall", "own", "p", "per", "perhaps", "q", "r", "rather", "recent", "recently", "s", "same", "seem", "seemed", "seeming", "seems", "seven", "seventy", "several", "she", "she'd", "she'll", "she's", "should", "shouldn't", "since", "six", "sixty", "so", "some", "somehow", "someone", "something", "sometime", "sometimes", "somewhere", "still", "stop", "such", "t", "taking", "ten", "than", "that", "that'll", "that's", "that've", "the", "their", "them", "themselves", "then", "thence", "there", "there'd", "there'll", "there're", "there's", "there've", "thereafter", "thereby", "therefore", "therein", "thereupon", "these", "they", "they'd", "they'll", "they're", "they've", "thirty", "this", "those", "though", "thousand", "three", "through", "throughout", "thru", "thus", "to", "together", "too", "toward", "towards", "trillion", "twenty", "two", "u", "under", "unless", "unlike", "unlikely", "until", "up", "upon", "us", "used", "using", "v", "very", "via", "w", "was", "wasn't", "we", "we'd", "we'll", "we're", "we've", "well", "were", "weren't", "what", "what'll", "what's", "what've", "whatever", "when", "whence", "whenever", "where", "where's", "whereafter", "whereas", "whereby", "wherein", "whereupon", "wherever", "whether", "which", "while", "whither", "who", "who'd", "who'll", "who's", "whoever", "whole", "whom", "whomever", "whose", "why", "will", "with", "within", "without", "won't", "would", "wouldn't", "x", "y", "yes", "yet", "you", "you'd", "you'll", "you're", "you've", "your", "yours", "yourself", "yourselves", "z", NULL }; long nstops = 0; char **stop_from_file = NULL; /* dgg */ char **stop_ptr; /* dgg */ typedef char (*charptr); void stop_list_file (filename) char *filename; { strcpy (stoplist_filename, filename); } void init_stop_list () { #ifdef BIO if (nstops > 0 && stop_from_file != NULL) {/* dgg */ int i; for (i = 0; i < nstops; i++) free (stop_from_file[i]); free (stop_from_file); nstops = 0; } /* printf("init_stop_list: stoplist file is '%s'\n", stoplist_filename); */ if (stoplist_filename[0] != '\0') { char word[256]; FILE * fp; fp = fopen (stoplist_filename, "r"); nstops = 1; (void *) stop_from_file = malloc (nstops * sizeof (charptr)); while (fgets (word, 255, fp)) { char *cp = strstr (word, "\n"); if (cp != NULL) *cp = '\0'; stop_from_file[nstops - 1] = malloc (strlen (word) + 1); strcpy (stop_from_file[nstops - 1], word); /* printf("init_stop_list: word %d is '%s'\n", nstops, stop_from_file[nstops-1]); */ nstops++; (void *) stop_from_file = realloc (stop_from_file, nstops * sizeof (charptr)); } fclose (fp); stop_from_file[nstops - 1] = NULL; stop_ptr = stop_from_file; /* printf("init_stop_list: read %d stop words from '%s'\n", nstops-1, stoplist_filename); */ } else #endif stop_ptr = stoplist; stoplist_pointer = 0; } char *next_stop_word () { /* returns NULL if all out */ if (stop_ptr[stoplist_pointer] == NULL) return (NULL); else return (stop_ptr[stoplist_pointer++]); }