def test_huge_postfile():
with TempStorage("hugeindex") as st:
pf = st.create_file("test.pst")
gb5 = 5 * 1024 * 1024 * 1024
pf.seek(gb5)
pf.write("\x00\x00\x00\x00")
assert_equal(pf.tell(), gb5 + 4)
fpw = FilePostingWriter(pf)
format = formats.Frequency(None)
offset = fpw.start(format)
for i in xrange(10):
fpw.write(i, float(i), struct.pack("!I", i), 10)
posttotal = fpw.finish()
assert_equal(posttotal, 10)
fpw.close()
pf = st.open_file("test.pst")
pfr = FilePostingReader(pf, offset, format)
i = 0
while pfr.is_active():
assert_equal(pfr.id(), i)
assert_equal(pfr.weight(), float(i))
assert_equal(pfr.value(), struct.pack("!I", i))
pfr.next()
i += 1
pf.close()
def roundtrip(postings, format, astype):
with TempStorage("roundtrip") as st:
postfile = st.create_file(astype)
getweight = format.decoder("weight")
fpw = FilePostingWriter(postfile, blocklimit=8)
fpw.start(format)
for id, value in postings:
v = format.encode(value)
fpw.write(id, getweight(v), v, 0)
fpw.finish()
fpw.close()
postfile = st.open_file(astype)
fpr = FilePostingReader(postfile, 0, format)
readback = list(fpr.items_as(astype))
postfile.close()
return readback
def test_readwrite():
with TempStorage("readwrite") as st:
format = Frequency()
postings = make_postings()
postfile = st.create_file("readwrite")
fpw = FilePostingWriter(postfile, blocklimit=8)
fpw.start(format)
for id, freq in postings:
fpw.write(id, float(freq), format.encode(freq), 0)
fpw.finish()
fpw.close()
postfile = st.open_file("readwrite")
fpr = FilePostingReader(postfile, 0, format)
assert_equal(postings, list(fpr.items_as("frequency")))
postfile.close()
def roundtrip(self, postings, format, astype):
postfile = self.make_file(astype)
readback = None
try:
fpw = FilePostingWriter(postfile, blocklimit=8)
fpw.start(format)
for id, value in postings:
fpw.write(id, format.encode(value))
fpw.close()
postfile = self.open_file(astype)
fpr = FilePostingReader(postfile, 0, format)
readback = list(fpr.all_as(astype))
fpr.close()
finally:
self.delete_file(astype)
return readback
def roundtrip(self, postings, format, astype):
postfile = self.make_file(astype)
readback = None
try:
fpw = FilePostingWriter(postfile, blocklimit=8)
fpw.start(format)
for id, value in postings:
fpw.write(id, format.encode(value))
fpw.close()
postfile = self.open_file(astype)
fpr = FilePostingReader(postfile, 0, format)
readback = list(fpr.all_as(astype))
fpr.close()
finally:
self.delete_file(astype)
return readback
def roundtrip(postings, format, astype):
with TempStorage("roundtrip") as st:
postfile = st.create_file(astype)
getweight = format.decoder("weight")
fpw = FilePostingWriter(postfile, blocklimit=8)
fpw.start(format)
for id, value in postings:
v = format.encode(value)
fpw.write(id, getweight(v), v, 0)
fpw.finish()
fpw.close()
postfile = st.open_file(astype)
fpr = FilePostingReader(postfile, 0, format)
readback = list(fpr.items_as(astype))
postfile.close()
return readback
def test_readwrite():
with TempStorage("readwrite") as st:
format = Frequency()
postings = make_postings()
postfile = st.create_file("readwrite")
fpw = FilePostingWriter(postfile, blocklimit=8)
fpw.start(format)
for id, freq in postings:
fpw.write(id, float(freq), format.encode(freq), 0)
fpw.finish()
fpw.close()
postfile = st.open_file("readwrite")
fpr = FilePostingReader(postfile, 0, format)
assert_equal(postings, list(fpr.items_as("frequency")))
postfile.close()
def test_readwrite(self):
format = Frequency(None)
postings = self.make_postings()
postfile = self.make_file("readwrite")
try:
fpw = FilePostingWriter(postfile, blocklimit=8)
fpw.start(format)
for id, freq in postings:
fpw.write(id, format.encode(freq))
fpw.close()
postfile = self.open_file("readwrite")
fpr = FilePostingReader(postfile, 0, format)
#self.assertEqual(postings, list(fpr.items_as("frequency")))
fpr.close()
finally:
self.delete_file("readwrite")
def test_readwrite(self):
format = Frequency(None)
postings = self.make_postings()
postfile = self.make_file("readwrite")
try:
fpw = FilePostingWriter(postfile, blocklimit=8)
fpw.start(format)
for id, freq in postings:
fpw.write(id, format.encode(freq))
fpw.close()
postfile = self.open_file("readwrite")
fpr = FilePostingReader(postfile, 0, format)
#self.assertEqual(postings, list(fpr.items_as("frequency")))
fpr.close()
finally:
self.delete_file("readwrite")
def test_lowlevel_block_writing():
st = RamStorage()
f = st.create_file("postfile")
fpw = FilePostingWriter(f, blocklimit=4)
fmt = formats.Frequency()
fpw.start(fmt)
fpw.write(0, 1.0, fmt.encode(1.0), 1)
fpw.write(1, 2.0, fmt.encode(2.0), 2)
fpw.write(2, 12.0, fmt.encode(12.0), 6)
fpw.write(5, 6.5, fmt.encode(6.5), 420)
fpw.write(11, 1.5, fmt.encode(1.5), 1)
fpw.write(12, 2.5, fmt.encode(2.5), 2)
fpw.write(26, 100.5, fmt.encode(100.5), 21)
fpw.write(50, 8.0, fmt.encode(8.0), 1020)
ti = fpw.finish()
assert_equal(ti.weight(), 134.0)
assert_equal(ti.doc_frequency(), 8)
assert_equal(ti.min_length(), 1)
assert_equal(ti.max_length(), byte_to_length(length_to_byte(1020)))
assert_equal(ti.max_weight(), 100.5)
assert_equal(ti.max_wol(), 100.5 / byte_to_length(length_to_byte(21)))
