def testIndexDocument(self):
text = u"""Le tartuffe, de Jean-Baptiste Poquelin, dit Molière.
Le petit chat est mort."""
text = normalizeText(text)
digest = sha.sha(text).hexdigest()
cursor = self.cnx.cursor()
# At this point, database should be emtpy, so no document
# should match <digest>
title = 'Le Tartuffe'
matchingDocs = Document.selectWhere(cursor, document_id=digest)
self.assertEquals(len(matchingDocs), 0)
self.querier.indexDocument('0'*40, FutureDocument(
filename='/tmp/Tartuffe.txt',
title=title,
text=text,
fileSize=len(text),
lastModificationTime=30000,
content_hash=digest,
mime_type='text',
state=Document.PUBLISHED_STATE,
file_state=FileInfo.CREATED_FILE_STATE))
matchingDocs = Document.selectWhere(cursor, document_id=digest)
self.assertEquals(len(matchingDocs), 1)
self.assertEquals(matchingDocs[0].text, '%s %s' % (title, text))
def testIndexDocument(self):
text = u"""Le tartuffe, de Jean-Baptiste Poquelin, dit Molière.
Le petit chat est mort."""
text = normalizeText(text)
digest = sha.sha(text).hexdigest()
cursor = self.cnx.cursor()
# At this point, database should be emtpy, so no document
# should match <digest>
title = 'Le Tartuffe'
matchingDocs = Document.selectWhere(cursor, document_id=digest)
self.assertEquals(len(matchingDocs), 0)
self.querier.indexDocument('0'*40, FutureDocument(
filename='/tmp/Tartuffe.txt',
title=title,
text=text,
fileSize=len(text),
lastModificationTime=30000,
content_hash=digest,
mime_type='text',
state=Document.PUBLISHED_STATE,
file_state=FileInfo.CREATED_FILE_STATE))
matchingDocs = Document.selectWhere(cursor, document_id=digest)
self.assertEquals(len(matchingDocs), 1)
self.assertEquals(matchingDocs[0].text, '%s %s' % (title, text))
def testIndexDocument(self):
text = u"""Le tartuffe, de Jean-Baptiste Poquelin, dit Molière.
Le petit chat est mort."""
text = normalizeText(text)
digest = sha.sha(text).hexdigest()
cursor = self.cnx.cursor()
# At this point, database should be emtpy, so no document
# should match <digest>
matchingDocs = Document.selectWhere(cursor, document_id=digest)
self.assertEquals(len(matchingDocs), 0)
self.querier.indexDocument('/tmp/Tartuffe.txt', 'Le Tartuffe', text,
len(text), 30000, digest, 'text',
Document.PUBLISHED_STATE,
FileInfo.CREATED_FILE_STATE)
matchingDocs = Document.selectWhere(cursor, document_id=digest)
self.assertEquals(len(matchingDocs), 1)
self.assertEquals(matchingDocs[0].text, text)
def testIndexDocument(self):
text = u"""Le tartuffe, de Jean-Baptiste Poquelin, dit Molière.
Le petit chat est mort."""
text = normalizeText(text)
digest = sha.sha(text).hexdigest()
cursor = self.cnx.cursor()
# At this point, database should be emtpy, so no document
# should match <digest>
matchingDocs = Document.selectWhere(cursor, document_id=digest)
self.assertEquals(len(matchingDocs), 0)
self.querier.indexDocument('/tmp/Tartuffe.txt',
'Le Tartuffe',
text,
len(text),
30000,
digest,
'text',
Document.PUBLISHED_STATE,
FileInfo.CREATED_FILE_STATE)
matchingDocs = Document.selectWhere(cursor, document_id=digest)
self.assertEquals(len(matchingDocs), 1)
self.assertEquals(matchingDocs[0].text, text)
def test_normalizeText(self):
self.assertEquals(normalizeText(u"ÉtùïÄç"), "etuiac")
def test_normalizeText(self):
self.assertEquals(normalizeText(u"ÉtùïÄç"), "etuiac")
