def search(dbpath, querystring, offset=0, pagesize=10):
# offset - defines starting point within result set
# pagesize - defines number of records to retrieve
# Open the database we're going to search.
db = xapian.Database(dbpath)
# Set up a QueryParser with a stemmer and suitable prefixes
queryparser = xapian.QueryParser()
queryparser.set_stemmer(xapian.Stem("en"))
queryparser.set_stemming_strategy(queryparser.STEM_SOME)
queryparser.add_prefix("title", "S")
queryparser.add_prefix("description", "XD")
# And parse the query
query = queryparser.parse_query(querystring)
# Use an Enquire object on the database to run the query
enquire = xapian.Enquire(db)
enquire.set_query(query)
# Start of example code.
class DistanceKeyMaker(xapian.KeyMaker):
def __call__(self, doc):
# we want to return a sortable string which represents
# the distance from Washington, DC to the middle of this
# state.
value = doc.get_value(4).decode('utf8')
x, y = map(float, value.split(','))
washington = (38.012, -77.037)
return xapian.sortable_serialise(
support.distance_between_coords((x, y), washington))
enquire.set_sort_by_key_then_relevance(DistanceKeyMaker(), False)
# End of example code.
# And print out something about each match
matches = []
for match in enquire.get_mset(offset, pagesize):
fields = json.loads(match.document.get_data().decode('utf8'))
print(
u"%(rank)i: #%(docid)3.3i %(name)s %(date)s\n Population %(pop)s"
% {
'rank': match.rank + 1,
'docid': match.docid,
'name': fields.get('name', u''),
'date': support.format_date(fields.get('admitted', u'')),
'pop': support.format_numeral(int(fields.get('population',
0))),
'lat': fields.get('latitude', u''),
'lon': fields.get('longitude', u''),
})
matches.append(match.docid)
# Finally, make sure we log the query and displayed results
support.log_matches(querystring, offset, pagesize, matches)
def search(dbpath, querystring, offset=0, pagesize=10):
# offset - defines starting point within result set
# pagesize - defines number of records to retrieve
# Open the database we're going to search.
db = xapian.Database(dbpath)
# Set up a QueryParser with a stemmer and suitable prefixes
queryparser = xapian.QueryParser()
queryparser.set_stemmer(xapian.Stem("en"))
queryparser.set_stemming_strategy(queryparser.STEM_SOME)
queryparser.add_prefix("title", "S")
queryparser.add_prefix("description", "XD")
# And parse the query
query = queryparser.parse_query(querystring)
# Use an Enquire object on the database to run the query
enquire = xapian.Enquire(db)
enquire.set_query(query)
# Start of example code.
class DistanceKeyMaker(xapian.KeyMaker):
def __call__(self, doc):
# we want to return a sortable string which represents
# the distance from Washington, DC to the middle of this
# state.
coords = map(float, doc.get_value(4).split(","))
washington = (38.012, -77.037)
return xapian.sortable_serialise(support.distance_between_coords(coords, washington))
enquire.set_sort_by_key_then_relevance(DistanceKeyMaker(), False)
# End of example code.
# And print out something about each match
matches = []
for match in enquire.get_mset(offset, pagesize):
fields = json.loads(match.document.get_data())
print(
u"%(rank)i: #%(docid)3.3i %(name)s %(date)s\n Population %(pop)s"
% {
"rank": match.rank + 1,
"docid": match.docid,
"name": fields.get("name", u""),
"date": support.format_date(fields.get("admitted", u"")),
"pop": support.format_numeral(int(fields.get("population", 0))),
"lat": fields.get("latitude", u""),
"lon": fields.get("longitude", u""),
}
)
matches.append(match.docid)
# Finally, make sure we log the query and displayed results
support.log_matches(querystring, offset, pagesize, matches)
def search(dbpath, querystring, offset=0, pagesize=10):
# offset - defines starting point within result set
# pagesize - defines number of records to retrieve
# Open the database we're going to search.
db = xapian.Database(dbpath)
# Set up a QueryParser with a stemmer and suitable prefixes
queryparser = xapian.QueryParser()
queryparser.set_stemmer(xapian.Stem("en"))
queryparser.set_stemming_strategy(queryparser.STEM_SOME)
queryparser.add_prefix("title", "S")
queryparser.add_prefix("description", "XD")
# And parse the query
query = queryparser.parse_query(querystring)
# Use an Enquire object on the database to run the query
enquire = xapian.Enquire(db)
enquire.set_query(query)
# Start of example code.
keymaker = xapian.MultiValueKeyMaker()
keymaker.add_value(1, False)
keymaker.add_value(3, True)
enquire.set_sort_by_key_then_relevance(keymaker, False)
# End of example code.
# And print out something about each match
matches = []
for match in enquire.get_mset(offset, pagesize):
fields = json.loads(match.document.get_data().decode('utf8'))
print(
u"%(rank)i: #%(docid)3.3i %(name)s %(date)s\n Population %(pop)s"
% {
'rank': match.rank + 1,
'docid': match.docid,
'name': fields.get('name', u''),
'date': support.format_date(fields.get('admitted', u'')),
'pop': support.format_numeral(int(fields.get('population',
0))),
'lat': fields.get('latitude', u''),
'lon': fields.get('longitude', u''),
})
matches.append(match.docid)
# Finally, make sure we log the query and displayed results
support.log_matches(querystring, offset, pagesize, matches)
def search(dbpath, querystring, offset=0, pagesize=10):
# offset - defines starting point within result set
# pagesize - defines number of records to retrieve
# Open the database we're going to search.
db = xapian.Database(dbpath)
# Set up a QueryParser with a stemmer and suitable prefixes
queryparser = xapian.QueryParser()
queryparser.set_stemmer(xapian.Stem("en"))
queryparser.set_stemming_strategy(queryparser.STEM_SOME)
queryparser.add_prefix("title", "S")
queryparser.add_prefix("description", "XD")
# And parse the query
query = queryparser.parse_query(querystring)
# Use an Enquire object on the database to run the query
enquire = xapian.Enquire(db)
enquire.set_query(query)
# Start of example code.
keymaker = xapian.MultiValueKeyMaker()
keymaker.add_value(1, False)
keymaker.add_value(3, True)
enquire.set_sort_by_key_then_relevance(keymaker, False)
# End of example code.
# And print out something about each match
matches = []
for index, match in enumerate(enquire.get_mset(offset, pagesize)):
fields = json.loads(match.document.get_data())
print u"%(rank)i: #%(docid)3.3i %(name)s %(date)s\n Population %(pop)s" % {
'rank': offset + index + 1,
'docid': match.docid,
'name': fields.get('name', u''),
'date': support.format_date(fields.get('admitted', u'')),
'pop': support.format_numeral(fields.get('population', 0)),
'lat': fields.get('latitude', u''),
'lon': fields.get('longitude', u''),
}
matches.append(match.docid)
# Finally, make sure we log the query and displayed results
support.log_matches(querystring, offset, pagesize, matches)
def search(dbpath, querystring, offset=0, pagesize=10):
# offset - defines starting point within result set
# pagesize - defines number of records to retrieve
# Open the database we're going to search.
db = xapian.Database(dbpath)
# Set up a QueryParser with a stemmer and suitable prefixes
queryparser = xapian.QueryParser()
queryparser.set_stemmer(xapian.Stem("en"))
queryparser.set_stemming_strategy(queryparser.STEM_SOME)
queryparser.add_prefix("title", "S")
queryparser.add_prefix("description", "XD")
# and add in range processors
# Start of custom RP code
class PopulationRangeProcessor(xapian.RangeProcessor):
def __init__(self, slot, low, high):
super(PopulationRangeProcessor, self).__init__()
self.nrp = xapian.NumberRangeProcessor(slot)
self.low = low
self.high = high
def __call__(self, begin, end):
if len(begin) > 0:
try:
_begin = int(begin)
if _begin < self.low or _begin > self.high:
raise ValueError()
except:
return xapian.Query(xapian.Query.OP_INVALID)
if len(end) > 0:
try:
_end = int(end)
if _end < self.low or _end > self.high:
raise ValueError()
except:
return xapian.Query(xapian.Query.OP_INVALID)
return self.nrp(begin, end)
queryparser.add_rangeprocessor(
PopulationRangeProcessor(3, 500000, 50000000)
)
# End of custom RP code
# Start of date example code
queryparser.add_rangeprocessor(
xapian.DateRangeProcessor(2, xapian.RP_DATE_PREFER_MDY, 1860)
)
queryparser.add_rangeprocessor(
xapian.NumberRangeProcessor(1)
)
# End of date example code
# And parse the query
query = queryparser.parse_query(querystring)
# Use an Enquire object on the database to run the query
enquire = xapian.Enquire(db)
enquire.set_query(query)
# And print out something about each match
matches = []
for match in enquire.get_mset(offset, pagesize):
fields = json.loads(match.document.get_data().decode('utf8'))
population = support.format_numeral(int(fields.get('population', 0)))
date = support.format_date(fields.get('admitted'))
print(u"""\
%(rank)i: #%(docid)3.3i %(name)s %(date)s
Population %(pop)s""" % {
'rank': match.rank + 1,
'docid': match.docid,
'name': fields.get('name', u''),
'date': date,
'pop': population,
'lat': fields.get('latitude', u''),
'lon': fields.get('longitude', u''),
})
matches.append(match.docid)
# Finally, make sure we log the query and displayed results
support.log_matches(querystring, offset, pagesize, matches)
def search(dbpath, querystring, offset=0, pagesize=10):
# offset - defines starting point within result set
# pagesize - defines number of records to retrieve
# Open the database we're going to search.
db = xapian.Database(dbpath)
# Set up a QueryParser with a stemmer and suitable prefixes
queryparser = xapian.QueryParser()
queryparser.set_stemmer(xapian.Stem("en"))
queryparser.set_stemming_strategy(queryparser.STEM_SOME)
queryparser.add_prefix("title", "S")
queryparser.add_prefix("description", "XD")
# and add in range processors
# Start of custom RP code
class PopulationRangeProcessor(xapian.RangeProcessor):
def __init__(self, slot, low, high):
super(PopulationRangeProcessor, self).__init__()
self.nrp = xapian.NumberRangeProcessor(slot)
self.low = low
self.high = high
def __call__(self, begin, end):
if len(begin) > 0:
try:
_begin = int(begin)
if _begin < self.low or _begin > self.high:
raise ValueError()
except:
return xapian.Query(xapian.Query.OP_INVALID)
if len(end) > 0:
try:
_end = int(end)
if _end < self.low or _end > self.high:
raise ValueError()
except:
return xapian.Query(xapian.Query.OP_INVALID)
return self.nrp(begin, end)
queryparser.add_rangeprocessor(
PopulationRangeProcessor(3, 500000, 50000000)
)
# End of custom RP code
# Start of date example code
queryparser.add_rangeprocessor(
xapian.DateRangeProcessor(2, xapian.RP_DATE_PREFER_MDY, 1860)
)
queryparser.add_rangeprocessor(
xapian.NumberRangeProcessor(1)
)
# End of date example code
# And parse the query
query = queryparser.parse_query(querystring)
# Use an Enquire object on the database to run the query
enquire = xapian.Enquire(db)
enquire.set_query(query)
# And print out something about each match
matches = []
for match in enquire.get_mset(offset, pagesize):
fields = json.loads(match.document.get_data())
population = support.format_numeral(int(fields.get('population', 0)))
date = support.format_date(fields.get('admitted'))
print(u"""\
%(rank)i: #%(docid)3.3i %(name)s %(date)s
Population %(pop)s""" % {
'rank': match.rank + 1,
'docid': match.docid,
'name': fields.get('name', u''),
'date': date,
'pop': population,
'lat': fields.get('latitude', u''),
'lon': fields.get('longitude', u''),
})
matches.append(match.docid)
# Finally, make sure we log the query and displayed results
support.log_matches(querystring, offset, pagesize, matches)