Python getStopWords Examples

Example #1

def tempSearchQuery(index, query, settings, lang):
	if not lang:
		lang = settings.get('lang')

	searchEngine = SearchEngine(index, getStopWords(lang))
	fca = FCASearchEngine(searchEngine, index, settings)
	searchResults = fca.search(query, lang)
	return searchResults

Example #2

File: statistics.py Project: havrlant/fca-search

	def search(self, query):
		database = DATABASES_FOLDER + self.databaseName + '/'
		settings = Settings(database + SETTINGS_FILE)
		index = Index(database, settings)
		searchEngine = SearchEngine(index, getStopWords())
		fca = FCASearchEngine(searchEngine, index, settings)
		searchResults = fca.search(query, True) # nostemsearch
		return [tuple(map(self.normalizeQuery, x['words'])) for x in searchResults['specialization']][:self.maxSpec]

Example #3

def searchQuery(databaseName, query, lang, stopwatch = None):
	index, settings = getIndexAndSettings(databaseName)
	if not lang:
		lang = settings.get('lang')

	searchEngine = SearchEngine(index, getStopWords(lang))
	fca = FCASearchEngine(searchEngine, index, settings)
	searchResults = fca.search(query, lang)
	return searchResults

Example #4

def tempSearch(path):
	content = readfile(path)
	data = loads(content);
	options = data.get('options', {})
	lang = options.get('lang', 'en')
	tempIndex = TempSearch()
	index = tempIndex.build(data, getStopWords(lang))
	res=tempSearchQuery(index, options.get('query', 'lion'), {}, lang)
	return getJson(res)

Example #5

def buildIndex(databaseName, linksSourcePath, currSettings, lang):
	settings = Settings(DATA_FOLDER + SETTINGS_FILE)
	for key, value in currSettings.items():
		settings.set(key, value)

	database = DATABASES_FOLDER + databaseName + '/'
	links = readfile(linksSourcePath).splitlines()
	indexManager = IndexManager(settings)
	indexManager.shutUp = False
	indexManager.build(links, database, getStopWords(lang), lang)

Example #6

 def search(self, query):
     database = DATABASES_FOLDER + self.databaseName + '/'
     settings = Settings(database + SETTINGS_FILE)
     index = Index(database, settings)
     searchEngine = SearchEngine(index, getStopWords())
     fca = FCASearchEngine(searchEngine, index, settings)
     searchResults = fca.search(query, True)  # nostemsearch
     return [
         tuple(map(self.normalizeQuery, x['words']))
         for x in searchResults['specialization']
     ][:self.maxSpec]

Example #7

File: preprocess_test.py Project: KGerring/fca_search

    def test_toIndex(self):
        urls = self.getURLs()
        sites = downloads(urls)
        sites = [{'type': 'html', 'content': x, 'url': 'url'} for x in sites]

        # savefile(repr(toIndex(sites, [], 1)), TEST_FOLDER + 'index1.txt')
        # savefile(repr(toIndex(sites, getStopWords(), 1)), TEST_FOLDER + 'index2.txt')
        # savefile(repr(toIndex(sites, getStopWords(), 2)), TEST_FOLDER + 'index3.txt')

        result = toIndex(sites, [], 1)
        desired = readfile(TEST_FOLDER + 'index1.txt')
        self.assertEqual(repr(result), desired)

        result = toIndex(sites, getStopWords(), 1)
        desired = readfile(TEST_FOLDER + 'index2.txt')
        self.assertEqual(repr(result), desired)

        result = toIndex(sites, getStopWords(), 2)
        desired = readfile(TEST_FOLDER + 'index3.txt')
        self.assertEqual(repr(result), desired)