X-Git-Url: http://git.indexdata.com/?a=blobdiff_plain;f=src%2Frelevance.c;h=35b7d8312c040b677350d28a3485addcea460f7a;hb=2ebf0b250fd141b7a3e186e7e99bfc76e29e39d7;hp=b35adce4470ad8de78a8a2937cfa87b7a092cce2;hpb=f89a08d579f270d78b6e48a04ec63cef23539c88;p=pazpar2-moved-to-github.git diff --git a/src/relevance.c b/src/relevance.c index b35adce..35b7d83 100644 --- a/src/relevance.c +++ b/src/relevance.c @@ -1,5 +1,5 @@ /* This file is part of Pazpar2. - Copyright (C) 2006-2008 Index Data + Copyright (C) 2006-2010 Index Data Pazpar2 is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free @@ -17,156 +17,26 @@ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ -#include -#include -#include - #if HAVE_CONFIG_H #include #endif -#include "relevance.h" -#include "pazpar2.h" +#include +#include +#include -#define USE_TRIE 0 +#include "relevance.h" +#include "session.h" struct relevance { int *doc_frequency_vec; int vec_len; -#if USE_TRIE - struct word_trie *wt; -#else struct word_entry *entries; - pp2_charset_t pct; -#endif + pp2_relevance_token_t prt; NMEM nmem; }; -#if USE_TRIE -#define raw_char(c) (((c) >= 'a' && (c) <= 'z') ? (c) - 'a' : -1) - - -// We use this data structure to recognize terms in input records, -// and map them to record term vectors for counting. -struct word_trie -{ - struct - { - struct word_trie *child; - int termno; - } list[26]; -}; - -static struct word_trie *create_word_trie_node(NMEM nmem) -{ - struct word_trie *res = nmem_malloc(nmem, sizeof(struct word_trie)); - int i; - for (i = 0; i < 26; i++) - { - res->list[i].child = 0; - res->list[i].termno = -1; - } - return res; -} - -static void word_trie_addterm(NMEM nmem, struct word_trie *n, const char *term, int num) -{ - - while (*term) { - int c = tolower(*term); - if (c < 'a' || c > 'z') - term++; - else - { - c -= 'a'; - if (!*(++term)) - n->list[c].termno = num; - else - { - if (!n->list[c].child) - { - struct word_trie *new = create_word_trie_node(nmem); - n->list[c].child = new; - } - word_trie_addterm(nmem, n->list[c].child, term, num); - } - break; - } - } -} - -static int word_trie_match(struct word_trie *t, const char *word, int *skipped) -{ - int c = raw_char(tolower(*word)); - - if (!*word) - return 0; - - word++; - (*skipped)++; - if (!*word || raw_char(*word) < 0) - { - if (t->list[c].termno > 0) - return t->list[c].termno; - else - return 0; - } - else - { - if (t->list[c].child) - { - return word_trie_match(t->list[c].child, word, skipped); - } - else - return 0; - } - -} - - -static struct word_trie *build_word_trie(NMEM nmem, const char **terms) -{ - struct word_trie *res = create_word_trie_node(nmem); - const char **p; - int i; - - for (i = 1, p = terms; *p; p++, i++) - word_trie_addterm(nmem, res, *p, i); - return res; -} - - -// FIXME. The definition of a word is crude here.. should support -// some form of localization mechanism? -void relevance_countwords(struct relevance *r, struct record_cluster *cluster, - const char *words, int multiplier) -{ - while (*words) - { - char c; - int res; - int skipped = 0; - while (*words && (c = raw_char(tolower(*words))) < 0) - words++; - if (!*words) - break; - res = word_trie_match(r->wt, words, &skipped); - if (res) - { - words += skipped; - cluster->term_frequency_vec[res] += multiplier; - } - else - { - while (*words && (c = raw_char(tolower(*words))) >= 0) - words++; - } - cluster->term_frequency_vec[0]++; - } -} - -#else struct word_entry { const char *norm_str; @@ -198,7 +68,8 @@ int word_entry_match(struct word_entry *entries, const char *norm_str) return 0; } -static struct word_entry *build_word_entries(pp2_charset_t pct, NMEM nmem, +static struct word_entry *build_word_entries(pp2_relevance_token_t prt, + NMEM nmem, const char **terms) { int termno = 1; /* >0 signals THERE is an entry */ @@ -207,42 +78,50 @@ static struct word_entry *build_word_entries(pp2_charset_t pct, NMEM nmem, for (; *p; p++) { - pp2_relevance_token_t prt = pp2_relevance_tokenize(pct, *p); const char *norm_str; + pp2_relevance_first(prt, *p, 0); while ((norm_str = pp2_relevance_token_next(prt))) add_word_entry(nmem, &entries, norm_str, termno); - - pp2_relevance_token_destroy(prt); - termno++; } return entries; } void relevance_countwords(struct relevance *r, struct record_cluster *cluster, - const char *words, int multiplier) + const char *words, int multiplier, const char *name) { - pp2_relevance_token_t prt = pp2_relevance_tokenize(r->pct, words); - + int *mult = cluster->term_frequency_vec_tmp; const char *norm_str; - - while ((norm_str = pp2_relevance_token_next(prt))) + int i, length = 0; + + pp2_relevance_first(r->prt, words, 0); + for (i = 1; i < r->vec_len; i++) + mult[i] = 0; + + while ((norm_str = pp2_relevance_token_next(r->prt))) { int res = word_entry_match(r->entries, norm_str); if (res) - cluster->term_frequency_vec[res] += multiplier; - cluster->term_frequency_vec[0]++; + { + assert(res < r->vec_len); + mult[res] += multiplier; + } + length++; } - pp2_relevance_token_destroy(prt); -} - -#endif + for (i = 1; i < r->vec_len; i++) + { + if (length > 0) /* only add if non-empty */ + cluster->term_frequency_vecf[i] += (double) mult[i] / length; + cluster->term_frequency_vec[i] += mult[i]; + } + cluster->term_frequency_vec[0] += length; +} struct relevance *relevance_create(pp2_charset_t pct, - NMEM nmem, const char **terms, int numrecs) + NMEM nmem, const char **terms) { struct relevance *res = nmem_malloc(nmem, sizeof(struct relevance)); const char **p; @@ -254,21 +133,44 @@ struct relevance *relevance_create(pp2_charset_t pct, res->doc_frequency_vec = nmem_malloc(nmem, res->vec_len * sizeof(int)); memset(res->doc_frequency_vec, 0, res->vec_len * sizeof(int)); res->nmem = nmem; -#if USE_TRIE - res->wt = build_word_trie(nmem, terms); -#else - res->entries = build_word_entries(pct, nmem, terms); - res->pct = pct; -#endif + res->prt = pp2_relevance_tokenize(pct); + res->entries = build_word_entries(res->prt, nmem, terms); return res; } +void relevance_destroy(struct relevance **rp) +{ + if (*rp) + { + pp2_relevance_token_destroy((*rp)->prt); + *rp = 0; + } +} + 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)); - memset(rec->term_frequency_vec, 0, r->vec_len * sizeof(int)); + int i; + + // term frequency [1,..] . [0] is total length of all fields + rec->term_frequency_vec = + nmem_malloc(r->nmem, + r->vec_len * sizeof(*rec->term_frequency_vec)); + for (i = 0; i < r->vec_len; i++) + rec->term_frequency_vec[i] = 0; + + // term frequency divided by length of field [1,...] + rec->term_frequency_vecf = + nmem_malloc(r->nmem, + r->vec_len * sizeof(*rec->term_frequency_vecf)); + for (i = 0; i < r->vec_len; i++) + rec->term_frequency_vecf[i] = 0.0; + + // for relevance_countwords (so we don't have to xmalloc/xfree) + rec->term_frequency_vec_tmp = + nmem_malloc(r->nmem, + r->vec_len * sizeof(*rec->term_frequency_vec_tmp)); } } @@ -290,6 +192,7 @@ void relevance_prepare_read(struct relevance *rel, struct reclist *reclist) int i; float *idfvec = xmalloc(rel->vec_len * sizeof(float)); + reclist_enter(reclist); // Calculate document frequency vector for each term. for (i = 1; i < rel->vec_len; i++) { @@ -309,30 +212,42 @@ void relevance_prepare_read(struct relevance *rel, struct reclist *reclist) } } // Calculate relevance for each document - for (i = 0; i < reclist->num_records; i++) + + while (1) { int t; - struct record_cluster *rec = reclist->flatlist[i]; - float relevance; - relevance = 0; + int relevance = 0; + struct record_cluster *rec = reclist_read_record(reclist); + if (!rec) + break; for (t = 1; t < rel->vec_len; t++) { float termfreq; - if (!rec->term_frequency_vec[0]) - break; - termfreq = (float) rec->term_frequency_vec[t] / rec->term_frequency_vec[0]; - relevance += termfreq * idfvec[t]; +#if 1 + termfreq = (float) rec->term_frequency_vecf[t]; +#else + if (rec->term_frequency_vec[0]) + { + termfreq = (float) + rec->term_frequency_vec[t] / rec->term_frequency_vec[0] ; + } + else + termfreq = 0.0; +#endif + relevance += 100000 * (termfreq * idfvec[t] + 0.0000005); } - rec->relevance = (int) (relevance * 100000); + rec->relevance_score = relevance; } - reclist->pointer = 0; + reclist_leave(reclist); xfree(idfvec); } /* * Local variables: * c-basic-offset: 4 + * c-file-style: "Stroustrup" * indent-tabs-mode: nil * End: * vim: shiftwidth=4 tabstop=8 expandtab */ +