pegasust
/
tantivy-py
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

CR: Adding trailing lines and removing some trailing spaces.

master
Paul Masurel 2019-08-29 09:55:36 +09:00
parent 6dc2b943b4
commit ccd8021ff9
3 changed files with 61 additions and 54 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
src/index.rs
View File

@ -144,7 +144,6 @@ impl Index {
}; };
let reader = index.reader().map_err(to_pyerr)?; let reader = index.reader().map_err(to_pyerr)?;
println!("reader {}", reader.searcher().segment_readers().len());
obj.init(Index { index, reader }); obj.init(Index { index, reader });
Ok(()) Ok(())
} }
@ -215,6 +214,16 @@ impl Index {
Ok(()) Ok(())
} }
/// Acquires a Searcher from the searcher pool.
///
/// If no searcher is available during the call, note that
/// this call will block until one is made available.
///
/// Searcher are automatically released back into the pool when
/// they are dropped. If you observe this function to block forever
/// you probably should configure the Index to have a larger
/// searcher pool, or you are holding references to previous searcher
/// for ever.
fn searcher(&self) -> Searcher { fn searcher(&self) -> Searcher {
Searcher { Searcher {
inner: self.reader.searcher(), inner: self.reader.searcher(),

100
tests/tantivy_test.py
View File

@ -3,57 +3,56 @@ import pytest
from tantivy import Document, Index, SchemaBuilder, Schema from tantivy import Document, Index, SchemaBuilder, Schema
def schema(): def schema():
return SchemaBuilder()\ return SchemaBuilder() \
.add_text_field("title", stored=True)\ .add_text_field("title", stored=True) \
.add_text_field("body")\ .add_text_field("body") \
.build() .build()
@pytest.fixture(scope="class") @pytest.fixture(scope="class")
def ram_index(): def ram_index():
# assume all tests will use the same documents for now # assume all tests will use the same documents for now
# other methods may set up function-local indexes # other methods may set up function-local indexes
index = Index(schema()) index = Index(schema())
writer = index.writer() writer = index.writer()
# 2 ways of adding documents # 2 ways of adding documents
# 1 # 1
doc = Document() doc = Document()
# create a document instance # create a document instance
# add field-value pairs # add field-value pairs
doc.add_text("title", "The Old Man and the Sea") doc.add_text("title", "The Old Man and the Sea")
doc.add_text("body", ("He was an old man who fished alone in a skiff in" doc.add_text("body", ("He was an old man who fished alone in a skiff in"
"the Gulf Stream and he had gone eighty-four days " "the Gulf Stream and he had gone eighty-four days "
"now without taking a fish.")) "now without taking a fish."))
writer.add_document(doc) writer.add_document(doc)
# 2 use the built-in json support # 2 use the built-in json support
# keys need to coincide with field names # keys need to coincide with field names
doc = Document.from_dict({ doc = Document.from_dict({
"title": "Of Mice and Men", "title": "Of Mice and Men",
"body": ("A few miles south of Soledad, the Salinas River drops " "body": ("A few miles south of Soledad, the Salinas River drops "
"in close to the hillside bank and runs deep and " "in close to the hillside bank and runs deep and "
"green. The water is warm too, for it has slipped " "green. The water is warm too, for it has slipped "
"twinkling over the yellow sands in the sunlight " "twinkling over the yellow sands in the sunlight "
"before reaching the narrow pool. On one side of the " "before reaching the narrow pool. On one side of the "
"river the golden foothill slopes curve up to the " "river the golden foothill slopes curve up to the "
"strong and rocky Gabilan Mountains, but on the valley " "strong and rocky Gabilan Mountains, but on the valley "
"side the water is lined with trees—willows fresh and " "side the water is lined with trees—willows fresh and "
"green with every spring, carrying in their lower leaf " "green with every spring, carrying in their lower leaf "
"junctures the debris of the winter’s flooding; and " "junctures the debris of the winter’s flooding; and "
"sycamores with mottled, white, recumbent limbs and " "sycamores with mottled, white, recumbent limbs and "
"branches that arch over the pool") "branches that arch over the pool")
}) })
writer.add_document(doc) writer.add_document(doc)
writer.add_json("""{
writer.add_json("""{
"title": ["Frankenstein", "The Modern Prometheus"], "title": ["Frankenstein", "The Modern Prometheus"],
"body": "You will rejoice to hear that no disaster has accompanied the commencement of an enterprise which you have regarded with such evil forebodings. I arrived here yesterday, and my first task is to assure my dear sister of my welfare and increasing confidence in the success of my undertaking." "body": "You will rejoice to hear that no disaster has accompanied the commencement of an enterprise which you have regarded with such evil forebodings. I arrived here yesterday, and my first task is to assure my dear sister of my welfare and increasing confidence in the success of my undertaking."
}""") }""")
writer.commit()
writer.commit() index.reload()
index.reload() return index
return index
class TestClass(object): class TestClass(object):
@ -86,7 +85,6 @@ class TestClass(object):
assert len(result) == 1 assert len(result) == 1
def test_and_query_parser_default_fields(self, ram_index): def test_and_query_parser_default_fields(self, ram_index):
query = ram_index.parse_query("winter", default_field_names=["title"]) query = ram_index.parse_query("winter", default_field_names=["title"])
assert repr(query) == """Query(TermQuery(Term(field=0,bytes=[119, 105, 110, 116, 101, 114])))""" assert repr(query) == """Query(TermQuery(Term(field=0,bytes=[119, 105, 110, 116, 101, 114])))"""
@ -98,7 +96,6 @@ class TestClass(object):
"(Should, TermQuery(Term(field=1,bytes=[119, 105, 110, 116, 101, 114])))] " \ "(Should, TermQuery(Term(field=1,bytes=[119, 105, 110, 116, 101, 114])))] " \
"})" "})"
def test_query_errors(self, ram_index): def test_query_errors(self, ram_index):
index = ram_index index = ram_index
# no "bod" field # no "bod" field
@ -106,9 +103,9 @@ class TestClass(object):
index.parse_query("bod:men", ["title", "body"]) index.parse_query("bod:men", ["title", "body"])
PATH_TO_INDEX = "tests/test_index/" PATH_TO_INDEX = "tests/test_index/"
class TestFromDiskClass(object): class TestFromDiskClass(object):
def test_exists(self): def test_exists(self):
@ -123,29 +120,30 @@ class TestFromDiskClass(object):
def test_create_readers(self): def test_create_readers(self):
# not sure what is the point of this test. # not sure what is the point of this test.
idx = Index(schema()) idx = Index(schema())
assert idx.searcher().num_docs == 0 assert idx.searcher().num_docs == 0
# by default this is manual mode # by default this is manual mode
writer = idx.writer(30000000, 1) writer = idx.writer(30000000, 1)
writer.add_document(Document(title="mytitle",body="mybody")) writer.add_document(Document(title="mytitle", body="mybody"))
writer.commit() writer.commit()
assert idx.searcher().num_docs == 0 assert idx.searcher().num_docs == 0
# Manual is the default setting. # Manual is the default setting.
# In this case, change are reflected only when # In this case, change are reflected only when
# the index is manually reloaded. # the index is manually reloaded.
idx.reload() idx.reload()
assert idx.searcher().num_docs == 1 assert idx.searcher().num_docs == 1
idx.config_reader("OnCommit", 4) idx.config_reader("OnCommit", 4)
writer.add_document(Document(title="mytitle2",body="mybody2")) writer.add_document(Document(title="mytitle2", body="mybody2"))
writer.commit() writer.commit()
import time import time
for i in range(50): for i in range(50):
# The index should be automatically reloaded. # The index should be automatically reloaded.
# Wait for at most 5s for it to happen. # Wait for at most 5s for it to happen.
time.sleep(0.1) time.sleep(0.1)
if idx.searcher().num_docs == 2: if idx.searcher().num_docs == 2:
return return
assert False assert False
class TestSearcher(object): class TestSearcher(object):
def test_searcher_repr(self, ram_index): def test_searcher_repr(self, ram_index):
assert repr(ram_index.searcher()) == "Searcher(num_docs=3, num_segments=1)" assert repr(ram_index.searcher()) == "Searcher(num_docs=3, num_segments=1)"