Merge remote-tracking branch 'origin/devel' into devel

docs/conf.py

@@ -20,6 +20,7 @@ import os
 # add these directories to sys.path here. If the directory is relative to the
 # documentation root, use os.path.abspath to make it absolute, like shown here.
 sys.path.insert(0, '/home/timo/projects/estnltk')
+sys.path.insert(0, '/home/keeletehnoloogia/estnltk')
 
 # -- General configuration ------------------------------------------------
 

docs/tutorials/database.rst

 .. _database_tutorial:
 
-===========================================================
-Handling large text collections with ElasticSearch database
-===========================================================
+=====================================================
+Handling large text collections with Elastic database
+=====================================================
 
 .. content ..
 
-Mention elasticsearch visualization plugin ES view
+The activate Elastic (formerly Elasticsearch) carry out the guide from the Elastic team
+at webpage `https://www.elastic.co/guide/en/elasticsearch/reference/current/_installation.html`_.
 
-Mention that simply for testing purposes one can increase memory using --ES_MAX_MEM switch
-./elasticsearch --ES_MAX_MEM=4g
+.. _https://www.elastic.co/guide/en/elasticsearch/reference/current/_installation.html: https://www.elastic.co/guide/en/elasticsearch/reference/current/_installation.html/
+
+When the installation is complete you can run Elastic (from Elastic folder) with the command::
+
+    ./elasticsearch
+
+Elastic has a visualization plugin that can be accessed through a browser of your choosing.
+To do this you need to write  `http://localhost:9200/_plugin/head/`_ to the URL bar in your browser.
+
+.. _http://localhost:9200/_plugin/head/: http://localhost:9200/_plugin/head/
+
+For simple testing purposes one can increase the memory by using --ES_MAX_MEM switch.
+Example of using the memory switch::
+
+    ./elasticsearch --ES_MAX_MEM=4g
 
 Bulk importing data
 ===================
@@ -35,3 +49,40 @@ Eesti Koondkorpus, you can insert them using commands::
     python3 -m estnltk.database.importer koond corpora/koond
     python3 -m estnltk.database.importer eesti corpora/eesti
 
+
+Insert Text object to database
+==============================
+
+Estnltk has a python function for inserting Text objects to Elastic database for further analysis.
+
+It is important that you create a database before inserting. In the example there is a database created named 'test'.
+
+After that the Text object is created with a sentence. Then the insert() function is being called.
+
+Example for using the text insert::
+
+    from ..database import Database
+    from ...text import Text
+
+    db = Database('test')
+
+    text = Text('Mees, keda seal kohtasime, oli tuttav ja ta teretas meid.')
+
+    db.insert(text)
+
+
+Searching the database for keywords
+===================================
+
+To search from the Elastic database you need to specify the name of the database and the keywords that you need
+to start the search for. The function to do the search with is query_documents().
+
+The example search is from the 'test' database and the search word is 'aegna'::
+
+    from ..database import Database
+
+    db = Database('test')
+
+    search = Database.query_documents(db, "aegna")
+
+The search will return a json format query with the full text of the successful search result.
\ No newline at end of file

estnltk/database/tests/test_insert.py

@@ -31,13 +31,14 @@ class InsertTest(unittest.TestCase):
 
     def test_insert_default_ids(self):
         # see pole warningu eemaldamiseks sobiv viis, sest warning lihtsalt peidetakse. Pigem las ta olla nähtav.
-        # TODO: delete me: warnings.simplefilter("ignore")
         self.db.refresh()
         db = self.db
 
         # insert the documents
         id_first = db.insert(first())
+        print(id_first)
         id_second = db.insert(second())
+        print(id_second)
 
         # check the count
         self.assertEqual(2, db.count())
@@ -51,19 +52,12 @@ class BulkInsertTest(unittest.TestCase):
 
     def setUp(self):
         self.db = Database(TEST_INDEX)
-        self.db.delete()
+        #self.db.delete()
 
     def test_bulk_insert(self):
         db = self.db
         db.refresh()
 
-        # parem on tõsta first ja second InsertTestist lihtsalt välja (tegin juba selle ära).
-        # uue instantsi tegemine on ebavajalik.
-        # TODO: delete me.
-        # insert many (bulk) into db bulk_test
-        # it = InsertTest()
-        # text_lists = [it.first, it.second]
-
         text_lists = [first(), second()]
         id_bulk = db.bulk_insert(text_lists)
 
@@ -74,7 +68,6 @@ class BulkInsertTest(unittest.TestCase):
 class SearchTest(unittest.TestCase):
 
     def test_search_keyword_documents(self):
-        # TODO: move Database setup and initialization to def setUp() method
         self.db = Database(TEST_INDEX)
         keywords = ["aegna"]
         search = Database.query_documents(self.db, query=keywords)