lib: migrate from Xapian ValueRangeProcessor to RangeProcessor

This will be mandatory as of Xapian 1.5.  The API is also more
consistent with the FieldProcessor API, which helps code re-use a bit.

Note that this switches to using the built-in Xapian support for
prefixes on ranges (i.e. deleted code at beginning of
ParseTimeRangeProcessor::operator(), added prefix to constructor).

Another side effect of the migration is that we are generating smaller
queries, using one OP_VALUE_RANGE instead of an AND of two OP_VALUE_*
queries.
This commit is contained in:
David Bremner 2020-07-07 07:56:46 -03:00
parent a1b7cc834b
commit b90d852a2f
4 changed files with 56 additions and 58 deletions

View file

@ -218,9 +218,9 @@ struct _notmuch_database {
unsigned long view;
Xapian::QueryParser *query_parser;
Xapian::TermGenerator *term_gen;
Xapian::ValueRangeProcessor *value_range_processor;
Xapian::ValueRangeProcessor *date_range_processor;
Xapian::ValueRangeProcessor *last_mod_range_processor;
Xapian::RangeProcessor *value_range_processor;
Xapian::RangeProcessor *date_range_processor;
Xapian::RangeProcessor *last_mod_range_processor;
/* XXX it's slightly gross to use two parallel string->string maps
* here, but at least they are small */

View file

@ -385,8 +385,8 @@ _setup_query_field (const prefix_t *prefix, notmuch_database_t *notmuch)
Xapian::FieldProcessor *fp;
if (STRNCMP_LITERAL (prefix->name, "date") == 0)
fp = (new DateFieldProcessor ())->release ();
else if (STRNCMP_LITERAL (prefix->name, "query") == 0)
fp = (new DateFieldProcessor(NOTMUCH_VALUE_TIMESTAMP))->release ();
else if (STRNCMP_LITERAL(prefix->name, "query") == 0)
fp = (new QueryFieldProcessor (*notmuch->query_parser, notmuch))->release ();
else if (STRNCMP_LITERAL (prefix->name, "thread") == 0)
fp = (new ThreadFieldProcessor (*notmuch->query_parser, notmuch))->release ();
@ -1036,17 +1036,16 @@ notmuch_database_open_verbose (const char *path,
notmuch->query_parser = new Xapian::QueryParser;
notmuch->term_gen = new Xapian::TermGenerator;
notmuch->term_gen->set_stemmer (Xapian::Stem ("english"));
notmuch->value_range_processor = new Xapian::NumberValueRangeProcessor (NOTMUCH_VALUE_TIMESTAMP);
notmuch->date_range_processor = new ParseTimeValueRangeProcessor (NOTMUCH_VALUE_TIMESTAMP);
notmuch->last_mod_range_processor = new Xapian::NumberValueRangeProcessor (NOTMUCH_VALUE_LAST_MOD, "lastmod:");
notmuch->value_range_processor = new Xapian::NumberRangeProcessor (NOTMUCH_VALUE_TIMESTAMP);
notmuch->date_range_processor = new ParseTimeRangeProcessor (NOTMUCH_VALUE_TIMESTAMP, "date:");
notmuch->last_mod_range_processor = new Xapian::NumberRangeProcessor (NOTMUCH_VALUE_LAST_MOD, "lastmod:");
notmuch->query_parser->set_default_op (Xapian::Query::OP_AND);
notmuch->query_parser->set_database (*notmuch->xapian_db);
notmuch->query_parser->set_stemmer (Xapian::Stem ("english"));
notmuch->query_parser->set_stemming_strategy (Xapian::QueryParser::STEM_SOME);
notmuch->query_parser->add_valuerangeprocessor (notmuch->value_range_processor);
notmuch->query_parser->add_valuerangeprocessor (notmuch->date_range_processor);
notmuch->query_parser->add_valuerangeprocessor (notmuch->last_mod_range_processor);
notmuch->query_parser->add_rangeprocessor (notmuch->value_range_processor);
notmuch->query_parser->add_rangeprocessor (notmuch->date_range_processor);
notmuch->query_parser->add_rangeprocessor (notmuch->last_mod_range_processor);
for (i = 0; i < ARRAY_SIZE (prefix_table); i++) {
const prefix_t *prefix = &prefix_table[i];
@ -1401,7 +1400,7 @@ handle_sigalrm (unused (int signal))
*/
notmuch_status_t
notmuch_database_upgrade (notmuch_database_t *notmuch,
void (*progress_notify)(void *closure,
void (*progress_notify) (void *closure,
double progress),
void *closure)
{

View file

@ -24,64 +24,63 @@
#include "parse-time-vrp.h"
#include "parse-time-string.h"
#define PREFIX "date:"
/* See *ValueRangeProcessor in xapian-core/api/valuerangeproc.cc */
Xapian::valueno
ParseTimeValueRangeProcessor::operator() (std::string &begin, std::string &end)
Xapian::Query
ParseTimeRangeProcessor::operator() (const std::string &begin, const std::string &end)
{
time_t t, now;
std::string b;
/* Require date: prefix in start of the range... */
if (STRNCMP_LITERAL (begin.c_str (), PREFIX))
return Xapian::BAD_VALUENO;
/* ...and remove it. */
begin.erase (0, sizeof (PREFIX) - 1);
b = begin;
double from = DBL_MIN, to = DBL_MAX;
time_t parsed_time, now;
std::string str;
/* Use the same 'now' for begin and end. */
if (time (&now) == (time_t) -1)
return Xapian::BAD_VALUENO;
throw Xapian::QueryParserError ("unable to get current time");
if (! begin.empty ()) {
if (parse_time_string (begin.c_str (), &t, &now, PARSE_TIME_ROUND_DOWN))
return Xapian::BAD_VALUENO;
begin.assign (Xapian::sortable_serialise ((double) t));
if (!begin.empty ()) {
if (parse_time_string (begin.c_str (), &parsed_time, &now, PARSE_TIME_ROUND_DOWN))
throw Xapian::QueryParserError ("Didn't understand date specification '" + begin + "'");
else
from = (double) parsed_time;
}
if (! end.empty ()) {
if (end == "!" && ! b.empty ())
end = b;
if (!end.empty ()) {
if (end == "!" && ! begin.empty ())
str = begin;
else
str = end;
if (parse_time_string (end.c_str (), &t, &now, PARSE_TIME_ROUND_UP_INCLUSIVE))
return Xapian::BAD_VALUENO;
end.assign (Xapian::sortable_serialise ((double) t));
if (parse_time_string (str.c_str (), &parsed_time, &now, PARSE_TIME_ROUND_UP_INCLUSIVE))
throw Xapian::QueryParserError ("Didn't understand date specification '" + str + "'");
else
to = (double) parsed_time;
}
return valno;
return Xapian::Query (Xapian::Query::OP_VALUE_RANGE, slot,
Xapian::sortable_serialise (from),
Xapian::sortable_serialise (to));
}
/* XXX TODO: is throwing an exception the right thing to do here? */
Xapian::Query
DateFieldProcessor::operator() (const std::string & str)
{
time_t from, to, now;
double from = DBL_MIN, to = DBL_MAX;
time_t parsed_time, now;
/* Use the same 'now' for begin and end. */
if (time (&now) == (time_t) -1)
throw Xapian::QueryParserError ("Unable to get current time");
if (parse_time_string (str.c_str (), &from, &now, PARSE_TIME_ROUND_DOWN))
if (parse_time_string (str.c_str (), &parsed_time, &now, PARSE_TIME_ROUND_DOWN))
throw Xapian::QueryParserError ("Didn't understand date specification '" + str + "'");
else
from = (double) parsed_time;
if (parse_time_string (str.c_str (), &to, &now, PARSE_TIME_ROUND_UP_INCLUSIVE))
if (parse_time_string (str.c_str (), &parsed_time, &now, PARSE_TIME_ROUND_UP_INCLUSIVE))
throw Xapian::QueryParserError ("Didn't understand date specification '" + str + "'");
else
to = (double) parsed_time;
return Xapian::Query (Xapian::Query::OP_AND,
Xapian::Query (Xapian::Query::OP_VALUE_GE, 0, Xapian::sortable_serialise ((double) from)),
Xapian::Query (Xapian::Query::OP_VALUE_LE, 0, Xapian::sortable_serialise ((double) to)));
return Xapian::Query (Xapian::Query::OP_VALUE_RANGE, slot,
Xapian::sortable_serialise (from),
Xapian::sortable_serialise (to));
}

View file

@ -26,21 +26,21 @@
#include <xapian.h>
/* see *ValueRangeProcessor in xapian-core/include/xapian/queryparser.h */
class ParseTimeValueRangeProcessor : public Xapian::ValueRangeProcessor {
protected:
Xapian::valueno valno;
class ParseTimeRangeProcessor : public Xapian::RangeProcessor {
public:
ParseTimeValueRangeProcessor (Xapian::valueno slot_)
: valno (slot_)
{
}
ParseTimeRangeProcessor (Xapian::valueno slot_, const std::string prefix_)
: Xapian::RangeProcessor(slot_, prefix_, 0) { }
Xapian::valueno operator() (std::string &begin, std::string &end);
Xapian::Query operator() (const std::string &begin, const std::string &end);
};
class DateFieldProcessor : public Xapian::FieldProcessor {
Xapian::Query operator() (const std::string & str);
private:
Xapian::valueno slot;
public:
DateFieldProcessor(Xapian::valueno slot_) : slot(slot_) { };
Xapian::Query operator()(const std::string & str);
};
#endif /* NOTMUCH_PARSE_TIME_VRP_H */