Index *index_new(Store *store, Analyzer *analyzer, HashSet *def_fields,
bool create)
{
Index *self = ALLOC_AND_ZERO(Index);
HashSetEntry *hse;
/* FIXME: need to add these to the query parser */
self->config = default_config;
mutex_init(&self->mutex, NULL);
self->has_writes = false;
if (store) {
REF(store);
self->store = store;
} else {
self->store = open_ram_store();
create = true;
}
if (analyzer) {
self->analyzer = analyzer;
REF(analyzer);
} else {
self->analyzer = mb_standard_analyzer_new(true);
}
if (create) {
FieldInfos *fis = fis_new(STORE_YES, INDEX_YES,
TERM_VECTOR_WITH_POSITIONS_OFFSETS);
index_create(self->store, fis);
fis_deref(fis);
}
/* options */
self->key = NULL;
self->id_field = intern("id");
self->def_field = intern("id");
self->auto_flush = false;
self->check_latest = true;
REF(self->analyzer);
self->qp = qp_new(self->analyzer);
for (hse = def_fields->first; hse; hse = hse->next) {
qp_add_field(self->qp, (Symbol)hse->elem, true, true);
}
/* Index is a convenience class so set qp convenience options */
self->qp->allow_any_fields = true;
self->qp->clean_str = true;
self->qp->handle_parse_errors = true;
return self;
}
static void sort_test_setup(Store *store)
{
int i;
IndexWriter *iw;
FieldInfos *fis = fis_new(STORE_YES, INDEX_YES, TERM_VECTOR_YES);
index_create(store, fis);
fis_deref(fis);
iw = iw_open(store, whitespace_analyzer_new(false), NULL);
for (i = 0; i < NELEMS(data); i++) {
add_sort_test_data(&data[i], iw);
}
iw_close(iw);
}
void prepare_filter_index(Store *store)
{
int i;
IndexWriter *iw;
FieldInfos *fis = fis_new(STORE_YES, INDEX_YES, TERM_VECTOR_NO);
num = intern("num");
date = intern("date");
flipflop = intern("flipflop");
struct FilterData data[FILTER_DOCS_SIZE] = {
{"0", "20040601", "on"},
{"1", "20041001", "off"},
{"2", "20051101", "on"},
{"3", "20041201", "off"},
{"4", "20051101", "on"},
{"5", "20041201", "off"},
{"6", "20050101", "on"},
{"7", "20040701", "off"},
{"8", "20050301", "on"},
{"9", "20050401", "off"}
};
index_create(store, fis);
fis_deref(fis);
iw = iw_open(store, whitespace_analyzer_new(false), NULL);
for (i = 0; i < FILTER_DOCS_SIZE; i++) {
Document *doc = doc_new();
doc->boost = (float)(i+1);
doc_add_field(doc, df_add_data(df_new(num), data[i].num));
doc_add_field(doc, df_add_data(df_new(date), data[i].date));
doc_add_field(doc, df_add_data(df_new(flipflop), data[i].flipflop));
iw_add_doc(iw, doc);
doc_destroy(doc);
}
iw_close(iw);
return;
}
static void sort_multi_test_setup(Store *store1, Store *store2)
{
int i;
FieldInfos *fis = fis_new(STORE_YES, INDEX_YES, TERM_VECTOR_YES);
IndexWriter *iw;
SortTestData data[] = { /* len mod */
{"findall","a","6","0.01"}, /* 4 0 */
{"findall","c","5","0.1"}, /* 3 3 */
{"findall","e","2","0.001"}, /* 5 1 */
{"findall","g","1","1.0"}, /* 3 3 */
{"findall","i","3","0.0001"}, /* 6 2 */
{"findall","", "4","10.0"}, /* 4 0 */
{"findall","h","5","0.00001"}, /* 7 3 */
{"findall","f","2","100.0"}, /* 5 1 */
{"findall","d","3","1000.0"}, /* 6 2 */
{"findall","b","4","0.000001"} /* 8 0 */
};
index_create(store1, fis);
index_create(store2, fis);
fis_deref(fis);
iw = iw_open(store1, whitespace_analyzer_new(false), NULL);
for (i = 0; i < NELEMS(data)/2; i++) {
add_sort_test_data(&data[i], iw);
}
iw_close(iw);
iw = iw_open(store2, whitespace_analyzer_new(false), NULL);
for (i = NELEMS(data)/2; i < NELEMS(data); i++) {
add_sort_test_data(&data[i], iw);
}
iw_close(iw);
}
static FieldInfos *create_fis()
{
FieldInfos *fis = fis_new(STORE_YES, INDEX_YES,
TERM_VECTOR_WITH_POSITIONS_OFFSETS);
return fis;
}
IndexWriter *
frjs_iw_init(bool create, bool create_if_missing, Store *store,
Analyzer *analyzer, FieldInfos *fis) {
IndexWriter *iw = NULL;
Config config = default_config;
// rb_scan_args(argc, argv, "01", &roptions);
/*if (argc > 0) {
Check_Type(roptions, T_HASH);
if ((rval = rb_hash_aref(roptions, sym_dir)) != Qnil) {
Check_Type(rval, T_DATA);
store = DATA_PTR(rval);
} else if ((rval = rb_hash_aref(roptions, sym_path)) != Qnil) {
StringValue(rval);
frb_create_dir(rval);
store = open_fs_store(rs2s(rval));
DEREF(store);
}
// Let ruby's garbage collector handle the closing of the store
// if (!close_dir) {
// close_dir = RTEST(rb_hash_aref(roptions, sym_close_dir));
// }
// use_compound_file defaults to true
config.use_compound_file =
(rb_hash_aref(roptions, sym_use_compound_file) == Qfalse)
? false
: true;
if ((rval = rb_hash_aref(roptions, sym_analyzer)) != Qnil) {
analyzer = frb_get_cwrapped_analyzer(rval);
}
create = RTEST(rb_hash_aref(roptions, sym_create));
if ((rval = rb_hash_aref(roptions, sym_create_if_missing)) != Qnil) {
create_if_missing = RTEST(rval);
}
SET_INT_ATTR(chunk_size);
SET_INT_ATTR(max_buffer_memory);
SET_INT_ATTR(index_interval);
SET_INT_ATTR(skip_interval);
SET_INT_ATTR(merge_factor);
SET_INT_ATTR(max_buffered_docs);
SET_INT_ATTR(max_merge_docs);
SET_INT_ATTR(max_field_length);
}*/
if (NULL == store) {
store = open_ram_store();
DEREF(store);
}
if (!create && create_if_missing && !store->exists(store, "segments")) {
create = true;
}
if (create) {
if (fis != NULL) {
index_create(store, fis);
} else {
fis = fis_new(STORE_YES, INDEX_YES,
TERM_VECTOR_WITH_POSITIONS_OFFSETS);
index_create(store, fis);
fis_deref(fis);
}
}
iw = iw_open(store, analyzer, &config);
return iw;
}
