[RFC PATCH 2/2] lib: add date range search

[Jani Nikula]

Add a custom value range processor to enable date and time searches of
the form date:since..until, where "since" and "until" are expressions
understood by parse_time_string().

If "since" or "until" describes date/time at an accuracy of days or
less, the values are rounded according to the accuracy, towards past
for "since" and towards future for "until". For example,
date:november..yesterday would match from the beginning of November
until the end of yesterday. Expressions such as date:today..today
means since the beginning of today until the end of today.

Open-ended ranges are supported (since Xapian 1.2.1), i.e. you can
specify date:..until or date:since.. to not limit the start or end
date, respectively.

CAVEATS:

Xapian does not support spaces in range expressions. You can replace
the spaces with '_' or (in most cases) '-' or (in some cases) leave
the spaces out altogether.

Entering date:expr without ".." (for example date:yesterday) won't
work. You can achieve the expected result by duplicating the expr both
sides of ".." (for example date:yesterday..yesterday).

Signed-off-by: Jani Nikula <jani at nikula.org>
---
 lib/Makefile.local     |    1 +
 lib/database-private.h |    1 +
 lib/database.cc        |    4 ++++
 lib/getdate-proc.cc    |   34 ++++++++++++++++++++++++++++++++++
 lib/getdate-proc.h     |   21 +++++++++++++++++++++
 5 files changed, 61 insertions(+), 0 deletions(-)
 create mode 100644 lib/getdate-proc.cc
 create mode 100644 lib/getdate-proc.h

diff --git a/lib/Makefile.local b/lib/Makefile.local
index 803a284..7dd1f7d 100644
--- a/lib/Makefile.local
+++ b/lib/Makefile.local
@@ -59,6 +59,7 @@ libnotmuch_c_srcs =		\
 
 libnotmuch_cxx_srcs =		\
 	$(dir)/database.cc	\
+	$(dir)/getdate-proc.cc	\
 	$(dir)/directory.cc	\
 	$(dir)/index.cc		\
 	$(dir)/message.cc	\
diff --git a/lib/database-private.h b/lib/database-private.h
index 88532d5..ba13dc7 100644
--- a/lib/database-private.h
+++ b/lib/database-private.h
@@ -52,6 +52,7 @@ struct _notmuch_database {
     Xapian::QueryParser *query_parser;
     Xapian::TermGenerator *term_gen;
     Xapian::ValueRangeProcessor *value_range_processor;
+    Xapian::ValueRangeProcessor *getdate_proc;
 };
 
 /* Return the list of terms from the given iterator matching a prefix.
diff --git a/lib/database.cc b/lib/database.cc
index c928d02..a3f8adb 100644
--- a/lib/database.cc
+++ b/lib/database.cc
@@ -19,6 +19,7 @@
  */
 
 #include "database-private.h"
+#include "getdate-proc.h"
 
 #include <iostream>
 
@@ -682,12 +683,14 @@ notmuch_database_open (const char *path,
 	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->getdate_proc = new GetDateValueRangeProcessor (NOTMUCH_VALUE_TIMESTAMP, "date:", true);
 
 	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->getdate_proc);
 
 	for (i = 0; i < ARRAY_SIZE (BOOLEAN_PREFIX_EXTERNAL); i++) {
 	    prefix_t *prefix = &BOOLEAN_PREFIX_EXTERNAL[i];
@@ -729,6 +732,7 @@ notmuch_database_close (notmuch_database_t *notmuch)
     delete notmuch->query_parser;
     delete notmuch->xapian_db;
     delete notmuch->value_range_processor;
+    delete notmuch->getdate_proc;
     talloc_free (notmuch);
 }
 
diff --git a/lib/getdate-proc.cc b/lib/getdate-proc.cc
new file mode 100644
index 0000000..31f8f03
--- /dev/null
+++ b/lib/getdate-proc.cc
@@ -0,0 +1,34 @@
+
+#include "database-private.h"
+#include "getdate-proc.h"
+#include "parse-time-string.h"
+
+/* see *ValueRangeProcessor in xapian-core/api/valuerangeproc.cc */
+Xapian::valueno
+GetDateValueRangeProcessor::operator() (std::string &begin, std::string &end)
+{
+    time_t t, now;
+
+    if (Xapian::StringValueRangeProcessor::operator() (begin, end) == Xapian::BAD_VALUENO)
+	return Xapian::BAD_VALUENO;
+
+    /* use the same 'now' for begin and end */
+    if (time (&now) == (time_t) -1)
+	return Xapian::BAD_VALUENO;
+
+    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 (!end.empty ()) {
+	if (parse_time_string (end.c_str (), &t, &now, PARSE_TIME_ROUND_UP))
+	    return Xapian::BAD_VALUENO;
+
+	end.assign (Xapian::sortable_serialise ((double) t));
+    }
+
+    return valno;
+}
diff --git a/lib/getdate-proc.h b/lib/getdate-proc.h
new file mode 100644
index 0000000..351d06e
--- /dev/null
+++ b/lib/getdate-proc.h
@@ -0,0 +1,21 @@
+
+#ifndef NOTMUCH_GETDATE_PROC_H
+#define NOTMUCH_GETDATE_PROC_H
+
+#include <xapian.h>
+
+/* see *ValueRangeProcessor in xapian-core/include/xapian/queryparser.h */
+class GetDateValueRangeProcessor : public Xapian::StringValueRangeProcessor {
+public:
+    GetDateValueRangeProcessor (Xapian::valueno slot_)
+	: StringValueRangeProcessor (slot_) { }
+
+    GetDateValueRangeProcessor (Xapian::valueno slot_,
+				const std::string &str_,
+				bool prefix_ = true)
+	: StringValueRangeProcessor (slot_, str_, prefix_) { }
+
+    Xapian::valueno operator() (std::string &begin, std::string &end);
+};
+
+#endif /* NOTMUCH_GETDATE_PROC_H */
-- 
1.7.5.4