X-Git-Url: http://jsfdemo.indexdata.com/?a=blobdiff_plain;f=src%2Frelevance.c;h=bc841e4e5e18396ee988824eb57343ca545a0205;hb=c7b8fb38d1cd3568301aabac00c5627bd6f510ca;hp=d689e7b16a579a48307f6dfbbeb8f000e9737af8;hpb=dde4a5914bbb5511a91e73d8ab45210b48637596;p=pazpar2-moved-to-github.git diff --git a/src/relevance.c b/src/relevance.c index d689e7b..bc841e4 100644 --- a/src/relevance.c +++ b/src/relevance.c @@ -1,11 +1,15 @@ /* - * $Id: relevance.c,v 1.3 2007-01-03 06:23:44 quinn Exp $ + * $Id: relevance.c,v 1.8 2007-01-15 04:34:28 quinn Exp $ */ #include #include #include +#if HAVE_CONFIG_H +#include +#endif + #include "relevance.h" #include "pazpar2.h" @@ -117,25 +121,25 @@ struct relevance *relevance_create(NMEM nmem, const char **terms, int numrecs) ; res->vec_len = ++i; res->doc_frequency_vec = nmem_malloc(nmem, res->vec_len * sizeof(int)); - bzero(res->doc_frequency_vec, res->vec_len * sizeof(int)); + memset(res->doc_frequency_vec, 0, res->vec_len * sizeof(int)); res->nmem = nmem; res->wt = build_word_trie(nmem, terms); return res; } -void relevance_newrec(struct relevance *r, struct record *rec) +void relevance_newrec(struct relevance *r, struct record_cluster *rec) { if (!rec->term_frequency_vec) { rec->term_frequency_vec = nmem_malloc(r->nmem, r->vec_len * sizeof(int)); - bzero(rec->term_frequency_vec, r->vec_len * sizeof(int)); + memset(rec->term_frequency_vec, 0, r->vec_len * sizeof(int)); } } // FIXME. The definition of a word is crude here.. should support // some form of localization mechanism? -void relevance_countwords(struct relevance *r, struct record *head, +void relevance_countwords(struct relevance *r, struct record_cluster *cluster, const char *words, int multiplier) { while (*words) @@ -151,28 +155,29 @@ void relevance_countwords(struct relevance *r, struct record *head, if ((res = word_trie_match(r->wt, words, &skipped))) { words += skipped; - head->term_frequency_vec[res] += multiplier; + cluster->term_frequency_vec[res] += multiplier; } else { while (*words && (c = raw_char(tolower(*words))) >= 0) words++; } - head->term_frequency_vec[0]++; + cluster->term_frequency_vec[0]++; } } -void relevance_donerecord(struct relevance *r, struct record *head) +void relevance_donerecord(struct relevance *r, struct record_cluster *cluster) { int i; for (i = 1; i < r->vec_len; i++) - if (head->term_frequency_vec[i] > 0) + if (cluster->term_frequency_vec[i] > 0) r->doc_frequency_vec[i]++; r->doc_frequency_vec[0]++; } +#ifdef GAGA #ifdef FLOAT_REL static int comp(const void *p1, const void *p2) { @@ -190,13 +195,14 @@ static int comp(const void *p1, const void *p2) #else static int comp(const void *p1, const void *p2) { - struct record **r1 = (struct record **) p1; - struct record **r2 = (struct record **) p2; + struct record_cluster **r1 = (struct record_cluster **) p1; + struct record_cluster **r2 = (struct record_cluster **) p2; return (*r2)->relevance - (*r1)->relevance; } #endif +#endif -// Prepare for a relevance-sorted read of up to num entries +// Prepare for a relevance-sorted read void relevance_prepare_read(struct relevance *rel, struct reclist *reclist) { int i; @@ -214,7 +220,7 @@ void relevance_prepare_read(struct relevance *rel, struct reclist *reclist) for (i = 0; i < reclist->num_records; i++) { int t; - struct record *rec = reclist->flatlist[i]; + struct record_cluster *rec = reclist->flatlist[i]; float relevance; relevance = 0; for (t = 1; t < rel->vec_len; t++) @@ -227,7 +233,9 @@ void relevance_prepare_read(struct relevance *rel, struct reclist *reclist) } rec->relevance = (int) (relevance * 100000); } +#ifdef GAGA qsort(reclist->flatlist, reclist->num_records, sizeof(struct record*), comp); +#endif reclist->pointer = 0; xfree(idfvec); }