/* This file is part of Pazpar2.
- Copyright (C) 2006-2008 Index Data
+ Copyright (C) 2006-2012 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
#include <config.h>
#endif
+#include <assert.h>
#include <math.h>
#include <stdlib.h>
#include "relevance.h"
-#include "pazpar2.h"
-
-#define USE_TRIE 0
+#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_charset_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];
+struct word_entry {
+ const char *norm_str;
+ int termno;
+ char *ccl_field;
+ struct word_entry *next;
};
-static struct word_trie *create_word_trie_node(NMEM nmem)
+int word_entry_match(struct word_entry *entries, const char *norm_str)
{
- struct word_trie *res = nmem_malloc(nmem, sizeof(struct word_trie));
- int i;
- for (i = 0; i < 26; i++)
+ for (; entries; entries = entries->next)
{
- res->list[i].child = 0;
- res->list[i].termno = -1;
+ if (!strcmp(norm_str, entries->norm_str))
+ return entries->termno;
}
- return res;
+ return 0;
}
-static void word_trie_addterm(NMEM nmem, struct word_trie *n, const char *term, int num)
+void relevance_countwords(struct relevance *r, struct record_cluster *cluster,
+ const char *words, int multiplier, const char *name)
{
+ int *mult = cluster->term_frequency_vec_tmp;
+ const char *norm_str;
+ int i, length = 0;
- while (*term) {
- int c = tolower(*term);
- if (c < 'a' || c > 'z')
- term++;
- else
+ pp2_charset_token_first(r->prt, words, 0);
+ for (i = 1; i < r->vec_len; i++)
+ mult[i] = 0;
+
+ while ((norm_str = pp2_charset_token_next(r->prt)))
+ {
+ int res = word_entry_match(r->entries, norm_str);
+ if (res)
{
- 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;
+ assert(res < r->vec_len);
+ mult[res] += multiplier;
}
+ length++;
}
-}
-
-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
+ for (i = 1; i < r->vec_len; i++)
{
- if (t->list[c].child)
- {
- return word_trie_match(t->list[c].child, word, skipped);
- }
- else
- return 0;
+ 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;
}
-
-static struct word_trie *build_word_trie(NMEM nmem, const char **terms)
+static void pull_terms(struct relevance *res, struct ccl_rpn_node *n)
{
- struct word_trie *res = create_word_trie_node(nmem);
- const char **p;
+ char **words;
+ int numwords;
+ char *ccl_field;
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)
+ switch (n->kind)
{
- 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)
+ case CCL_RPN_AND:
+ case CCL_RPN_OR:
+ case CCL_RPN_NOT:
+ case CCL_RPN_PROX:
+ pull_terms(res, n->u.p[0]);
+ pull_terms(res, n->u.p[1]);
+ break;
+ case CCL_RPN_TERM:
+ nmem_strsplit(res->nmem, " ", n->u.t.term, &words, &numwords);
+ for (i = 0; i < numwords; i++)
{
- words += skipped;
- cluster->term_frequency_vec[res] += multiplier;
- }
- else
- {
- while (*words && (c = raw_char(tolower(*words))) >= 0)
- words++;
- }
- cluster->term_frequency_vec[0]++;
- }
-}
+ const char *norm_str;
+
+ ccl_field = nmem_strdup_null(res->nmem, n->u.t.qual);
-#else
-
-struct word_entry {
- const char *norm_str;
- int termno;
- struct word_entry *next;
-};
-
-static void add_word_entry(NMEM nmem,
- struct word_entry **entries,
- const char *norm_str,
- int term_no)
-{
- struct word_entry *ne = nmem_malloc(nmem, sizeof(*ne));
- ne->norm_str = nmem_strdup(nmem, norm_str);
- ne->termno = term_no;
-
- ne->next = *entries;
- *entries = ne;
-}
-
-
-int word_entry_match(struct word_entry *entries, const char *norm_str)
-{
- for (; entries; entries = entries->next)
- {
- if (!strcmp(norm_str, entries->norm_str))
- return entries->termno;
+ pp2_charset_token_first(res->prt, words[i], 0);
+ while ((norm_str = pp2_charset_token_next(res->prt)))
+ {
+ struct word_entry **e = &res->entries;
+ while (*e)
+ e = &(*e)->next;
+ *e = nmem_malloc(res->nmem, sizeof(**e));
+ (*e)->norm_str = nmem_strdup(res->nmem, norm_str);
+ (*e)->ccl_field = ccl_field;
+ (*e)->termno = res->vec_len++;
+ (*e)->next = 0;
+ }
+ }
+ break;
+ default:
+ break;
}
- return 0;
}
-static struct word_entry *build_word_entries(pp2_charset_t pct, NMEM nmem,
- const char **terms)
+struct relevance *relevance_create_ccl(pp2_charset_fact_t pft,
+ NMEM nmem, struct ccl_rpn_node *query)
{
- int termno = 1; /* >0 signals THERE is an entry */
- struct word_entry *entries = 0;
- const char **p = terms;
-
- for (; *p; p++)
- {
- pp2_relevance_token_t prt = pp2_relevance_tokenize(pct, *p);
- const char *norm_str;
-
- while ((norm_str = pp2_relevance_token_next(prt)))
- add_word_entry(nmem, &entries, norm_str, termno);
+ struct relevance *res = nmem_malloc(nmem, sizeof(*res));
+ int i;
- pp2_relevance_token_destroy(prt);
+ res->nmem = nmem;
+ res->entries = 0;
+ res->vec_len = 1;
+ res->prt = pp2_charset_token_create(pft, "relevance");
+
+ pull_terms(res, query);
- termno++;
- }
- return entries;
+ res->doc_frequency_vec = nmem_malloc(nmem, res->vec_len * sizeof(int));
+ for (i = 0; i < res->vec_len; i++)
+ res->doc_frequency_vec[i] = 0;
+ return res;
}
-void relevance_countwords(struct relevance *r, struct record_cluster *cluster,
- const char *words, int multiplier)
+void relevance_destroy(struct relevance **rp)
{
- pp2_relevance_token_t prt = pp2_relevance_tokenize(r->pct, words);
-
- const char *norm_str;
-
- while ((norm_str = pp2_relevance_token_next(prt)))
+ if (*rp)
{
- int res = word_entry_match(r->entries, norm_str);
- if (res)
- cluster->term_frequency_vec[res] += multiplier;
- cluster->term_frequency_vec[0]++;
+ pp2_charset_token_destroy((*rp)->prt);
+ *rp = 0;
}
- pp2_relevance_token_destroy(prt);
-}
-
-#endif
-
-
-
-struct relevance *relevance_create(pp2_charset_t pct,
- NMEM nmem, const char **terms, int numrecs)
-{
- struct relevance *res = nmem_malloc(nmem, sizeof(struct relevance));
- const char **p;
- int i;
-
- for (p = terms, i = 0; *p; p++, i++)
- ;
- res->vec_len = ++i;
- 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
- return res;
}
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));
}
}
-
void relevance_donerecord(struct relevance *r, struct record_cluster *cluster)
{
int i;
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++)
{
}
}
// 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];
+ float termfreq = (float) rec->term_frequency_vecf[t];
+ 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
*/
+
projects / pazpar2-moved-to-github.git / blobdiff