'''
Created on Apr 24, 2013
@author: inesmeya
'''
import unittest
from wiki_knows import wiki_knowledge
from io_test_utils import getOutputFile, getInputFile
from model.stemmers import PorterStemmer
from model.semantic_interpreter import SemanticComparer
from model.logger import getTestLogger
_log = getTestLogger("wiki_exec")
"""
Articles
--------
Politics, Technology, Computer, Nature, Art,
Busyness, Internet, Biology, Physics, Law, Economics, History,
Education, War, Love, Emotion, Medicine, Research, Sociology,
Wealth, Science
Code to download articles
-------------------------
articles_titles = '''Politics, Technology, Computer, Nature, Art,
Busyness, Internet, Biology, Physics, Law, Economics, History,
Education, War, Love, Emotion, Medicine, Research, Sociology,
import unittest
import wiki_knows.wiki_knowledge as wn
import io_test_utils as io_tu
from model.stemmers import StopWordsStemmer
from model.semantic_interpreter import SemanticComparer
import test.test_utils as test_utils
from io_test_utils import getOutputFile, getInputFile
import os
from model.logger import getTestLogger
_log = getTestLogger("Test")
class Test(unittest.TestCase):
def setUp(self):
pass
def tearDown(self):
pass
def test__parse_dump(self):
wiki_dump_path = io_tu.getInputFile(io_tu.FilesList.test__parse_tools)
wiki_parsed_dump_path = io_tu.getOutputFile(
io_tu.FilesList.test__parse_tools)
wn.parse_dump(wiki_dump_path, wiki_parsed_dump_path)
def test_number_of_concepts(self):
""" db builder reads parsed xml properly"""
'''
Created on Apr 24, 2013
@author: inesmeya
'''
import unittest
from wiki_knows import wiki_knowledge
from io_test_utils import getOutputFile, getInputFile
from model.stemmers import PorterStemmer
from model.semantic_interpreter import SemanticComparer
from model.logger import getTestLogger
_log = getTestLogger("wiki_exec")
"""
Articles
--------
Politics, Technology, Computer, Nature, Art,
Busyness, Internet, Biology, Physics, Law, Economics, History,
Education, War, Love, Emotion, Medicine, Research, Sociology,
Wealth, Science
Code to download articles
-------------------------
articles_titles = '''Politics, Technology, Computer, Nature, Art,
Busyness, Internet, Biology, Physics, Law, Economics, History,
Education, War, Love, Emotion, Medicine, Research, Sociology,
Wealth, Science'''
import xml.etree.ElementTree as etree
import gzip
import WikiExtractor
from parsers.wikitext_processor import WikiTextProcessor
from model.wiki_doc import WikiDocument
from model.wiki_doc import doc_from_xml, WdNames
from model.logger import getTestLogger
_log = getTestLogger(__name__)
#==================================================================================================
WIKIPEDIA_NAMESPACE = 'http://www.mediawiki.org/xml/export-0.8/'
def make_wikipedia_tag(tag):
'''Creates tag full name according to wikipedia namespace
@param tag: string. Tag in wikipedia xml dump file, such as 'page'
@return: tag with namespace: {WIKIPEDIA_NAMESPACE}{tag}"
'''
return "{%s}%s" % (WIKIPEDIA_NAMESPACE, tag)
# wikipedia page tag
PAGE_TAG = make_wikipedia_tag('page')
# parsed doc tag
DOC_TAG = 'doc'
import unittest
import wiki_knows.wiki_knowledge as wn
import io_test_utils as io_tu
from model.stemmers import StopWordsStemmer
from model.semantic_interpreter import SemanticComparer
import test.test_utils as test_utils
from io_test_utils import getOutputFile, getInputFile
import os
from model.logger import getTestLogger
_log = getTestLogger("Test")
class Test(unittest.TestCase):
def setUp(self):
pass
def tearDown(self):
pass
def test__parse_dump(self):
wiki_dump_path = io_tu.getInputFile(io_tu.FilesList.test__parse_tools)
wiki_parsed_dump_path = io_tu.getOutputFile(io_tu.FilesList.test__parse_tools)
wn.parse_dump(wiki_dump_path, wiki_parsed_dump_path)
import xml.etree.ElementTree as etree
import gzip
import WikiExtractor
from parsers.wikitext_processor import WikiTextProcessor
from model.wiki_doc import WikiDocument
from model.wiki_doc import doc_from_xml, WdNames
from model.logger import getTestLogger
_log = getTestLogger(__name__)
#==================================================================================================
WIKIPEDIA_NAMESPACE = 'http://www.mediawiki.org/xml/export-0.8/'
def make_wikipedia_tag(tag):
'''Creates tag full name according to wikipedia namespace
@param tag: string. Tag in wikipedia xml dump file, such as 'page'
@return: tag with namespace: {WIKIPEDIA_NAMESPACE}{tag}"
'''
return "{%s}%s" % (WIKIPEDIA_NAMESPACE, tag)
# wikipedia page tag
PAGE_TAG = make_wikipedia_tag('page')
# parsed doc tag
DOC_TAG = 'doc'
