def test_makeContext0(self):
f1_name = 'test_f1.txt'
f2_name = 'test_f2.txt'
f1 = open(f1_name, 'w')
f1.write('Ляляля маму. Мррррррр. Бебебе!')
f1.close()
f2 = open(f2_name, 'w')
f2.write('мамами мыла раму. М')
f2.close()
db_name = 'testdb'
makeDB([f1_name, f2_name], db_name)
ass = "[(['Ляляля маму'], [[(7, 11)]]), (['мамами мыла раму'], [[(0, 6)]])]"
db = shelve.open(db_name)
qres = query('маме', db_name)
res = str(list(makeContexts(qres).values()))
db.close()
self.assertEqual(ass, res)
os.unlink(f1_name)
os.unlink(f2_name)
if os.path.exists(db_name): os.unlink(db_name)
if os.path.exists(db_name + '.dat'): os.unlink(db_name + '.dat')
if os.path.exists(db_name + '.bak'): os.unlink(db_name + '.bak')
if os.path.exists(db_name + '.dir'): os.unlink(db_name + '.dir')
def test_makeContexts(self):
f1 = open('f1.txt', 'w')
f1.write('foo bar')
f1.close()
f1 = open('f2.txt', 'w')
f1.write('egg foo ham')
f1.close()
makeDB.makeDB(['f1.txt', 'f2.txt'], 'testdb')
ass = "OrderedDict([('f2.txt', ['egg foo ham'])])"
res = getQuery.query('foo ham', 'testdb')
res = str(getQuery.makeContexts(res))
os.unlink('f1.txt')
os.unlink('f2.txt')
if os.path.exists('testdb'):
os.unlink('testdb')
if os.path.exists('testdb.dat'):
os.unlink('testdb.dat')
if os.path.exists('testdb.bak'):
os.unlink('testdb.bak')
if os.path.exists('testdb.dir'):
os.unlink('testdb.dir')
self.assertEqual(ass, res)
def do_POST(self):
form = cgi.FieldStorage(fp=self.rfile,
headers=self.headers,
environ={
'REQUEST_METHOD': 'POST',
'CONTENT_TYPE':
self.headers['Content-Type']
})
self.send_response(200)
self.send_header('Content-type', 'text/html; charset=utf-8')
self.end_headers()
inputWords = form.getvalue('query').lower()
doc_count = form.getvalue('doc_count')
try:
doc_count = int(doc_count)
if doc_count < 0: doc_count = 2
except:
doc_count = 2
if form.getvalue('begin'):
myHandler.DOC_START = 1
elif form.getvalue('back'):
sh = doc_count
if myHandler.DOC_START - sh < 1:
sh = myHandler.DOC_START - 1
myHandler.DOC_START -= sh
elif form.getfirst('forward'):
myHandler.DOC_START += doc_count
result_line = ''
if inputWords != None:
if myHandler.QUERY == inputWords and \
myHandler.DOC_COUNT == doc_count:
for i in range(len(myHandler.QUTES_COUNTS)):
countQuote = form.getvalue('countQuote' + str(i))
try:
countQuote = int(countQuote)
except:
countQuote = 10
if form.getvalue('beginQuote' + str(i)):
myHandler.QUTES_COUNTS[i] = [countQuote, 0]
elif form.getvalue('backQuote' + str(i)):
sh = countQuote
if myHandler.QUTES_COUNTS[i][1] - sh < 0:
sh = mmyHandler.QUTES_COUNTS[i][1]
myHandler.QUTES_COUNTS[i][1] -= sh
elif form.getfirst('forwardQuote' + str(i)):
myHandler.QUTES_COUNTS[i][1] += countQuote
myHandler.QUTES_COUNTS[i][0] = countQuote
else:
myHandler.DOC_START = 1
myHandler.DOC_COUNT = 2
myHandler.QUERY = inputWords
myHandler.QUTES_COUNTS = []
for i in range(myHandler.DOC_COUNT):
myHandler.QUTES_COUNTS.append([5, 0])
qres = getQuery.query(inputWords, config.DATABASE_NAME,
myHandler.lemma, doc_count,
myHandler.DOC_START, myHandler.QUTES_COUNTS)
#resDict - { 'path' : ( [ 'context' ], [ [ (stBoldWord_1 , endBoldWord_1), (stBoldWord_2 , endBoldWord_2) ] ] ) }
resDict = getQuery.makeContexts(qres, myHandler.QUTES_COUNTS)
newQuotes = myHandler.QUTES_COUNTS == None
if newQuotes: myHandler.QUTES_COUNTS = []
for i, path in enumerate(resDict):
if newQuotes: myHandler.QUTES_COUNTS.append([5, 0])
#list for documents
result_line += r'<li>' + r'<b>' + path + r'</b>' + r'<ul>'
tup = resDict[path]
for context, positions in zip(tup[0], tup[1]):
#list for contexts
result_line += r'<li>'
result_line += context[:positions[0][0]]
for j in range(len(positions) - 1):
pos = positions[j]
result_line += r'<b>'
result_line += context[pos[0]:pos[1]]
result_line += r'</b>'
result_line += context[pos[1]:positions[j + 1][0]]
#code for last bold word in context
last_pos = positions[-1]
result_line += r'<b>'
result_line += context[last_pos[0]:last_pos[1]]
result_line += r'</b>'
result_line += context[last_pos[1]:]
result_line += r'</li>'
result_line += r'</ul><p>'
result_line += r'<input type="submit" name="beginQuote' + str(
i) + '" value="В начало"> '
result_line += r'<input type="submit" name="backQuote' + str(
i) + '" value="Назад"> '
result_line += r'<input type="submit" name="forwardQuote' + str(
i) + '" value="Вперед"> '
result_line += r'<input type="text" name="countQuote' + str(
i) + r'" value="'
countQuote = myHandler.QUTES_COUNTS[i][0]
result_line += str(countQuote) + r'"></li></p>'
if len(result_line) != 0:
result_line = r'<ol type="I">' + result_line + r'</ol>'
else:
result_line = r'<p>Ничего не найдено. Искать в Яндекс, Google, Mail.ru</p>'
else:
result_line = r'<p><p><p>Задан пустой поисковый запрос</p></p></p>'
inputWords = ''
myHandler.QUERY = inputWords
myHandler.DOC_COUNT = doc_count
self.wfile.write(
bytes(myHandler.HTML_DOC_1 + '"' + myHandler.QUERY + '"' +
myHandler.HTML_DOC_2 + '"' + str(myHandler.DOC_COUNT) +
myHandler.HTML_DOC_3 + result_line + myHandler.HTML_DOC_4,
encoding='utf-8'))
def test_doc_count_0(self):
lemma = lemmatizer()
qres = getQuery.query('смотреть', config.DATABASE_NAME, lemma, 2, 1, None)
#resDict - { 'path' : ( [ 'context' ], [ [ (stBoldWord_1 , endBoldWord_1), (stBoldWord_2 , endBoldWord_2) ] ] ) }
resDict = getQuery.makeContexts(qres, None)
self.assertEqual(len(resDict.keys()), 2)
def test_doc_names(self):
lemma = lemmatizer()
qres = getQuery.query('смотреть', config.DATABASE_NAME, lemma, 2, 1, None)
resDict = getQuery.makeContexts(qres, None)
self.assertEqual(sorted(resDict.keys()), ['mid_text_1.txt', 'mid_text_2.txt'])
def test_doc_count_4(self):
lemma = lemmatizer()
qres = getQuery.query('смотреть', config.DATABASE_NAME, lemma, 1, 3, None)
resDict = getQuery.makeContexts(qres, None)
self.assertEqual(len(resDict.keys()), 0)