def createByOcr(self, filePath, lang, options = None):
'''
Submitting picture, containing textual content, to plagiarism scan
'''
assert filePath, 'Missing filePath'
assert os.path.exists(filePath), 'filePath is not exists!'
assert os.path.getsize(filePath) <= Consts.MAX_FILE_SIZE_BYTES, 'Exceed max file size (max allowed: %s bytes)' % (Consts.MAX_FILE_SIZE_BYTES)
assert lang, 'Missing lang'
assert lang.value in eOcrLanguage.__members__ , 'Unknown language'
serviceUrl = "%s%s/%s/create-by-file-ocr?language=%s" % (Consts.SERVICE_ENTRY_POINT, Consts.SERVICE_VERSION, self.product, lang.value)
headers = {
Consts.AUTHORIZATION_HEADER: self.token.generateAuthrizationHeader()
}
if options != None:
headers = headers.copy()
headers.update(options.getHeaders())
theFile = {'file': (os.path.basename(filePath), open(filePath, 'rb'))}
response = requests.post(serviceUrl, headers=headers, files=theFile)
if (response.status_code == Consts.HTTP_SUCCESS):
return CopyleaksProcess(self.getProduct(), self.token, response.json())
else:
raise CommandFailedError(response)
def createByUrl(self, url, options = None):
'''
Submitting URL to plagiarism scan
'''
assert url, 'Missing URL'
assert bool(re.match('http://|https://', url, re.I)), 'url must starts with "http://" or "https://"'
serviceUrl = "%s%s/%s/create-by-url" % (Consts.SERVICE_ENTRY_POINT, Consts.SERVICE_VERSION, self.product)
payload = {
'url': url
}
headers = {
Consts.AUTHORIZATION_HEADER: self.token.generateAuthrizationHeader(),
Consts.CONTENT_TYPE_HEADER: Consts.CONTENT_TYPE_JSON
}
if options != None:
headers = headers.copy()
headers.update(options.getHeaders())
response = requests.post(serviceUrl, headers=headers, data=json.dumps(payload))
if (response.status_code == Consts.HTTP_SUCCESS):
return CopyleaksProcess(self.getProduct(), self.token, response.json())
else:
raise CommandFailedError(response)
def createByText(self, utf8text, options=None):
'''
Submitting text for scan.
The input text encoding must be UTF-8 encoded.
'''
assert utf8text, 'Missing text'
assert utf8text.strip() != '', 'Text cannot be empty'
serviceUrl = "%s%s/%s/create-by-text" % (
Consts.SERVICE_ENTRY_POINT, Consts.SERVICE_VERSION, self.product)
headers = {
Consts.AUTHORIZATION_HEADER:
self.token.generateAuthrizationHeader()
}
if options != None:
headers = headers.copy()
headers.update(options.getHeaders())
response = requests.post(serviceUrl, headers=headers, data=utf8text)
if (response.status_code == Consts.HTTP_SUCCESS):
return CopyleaksProcess(self.getProduct(), self.token,
response.json())
else:
raise CommandFailedError(response)
def createByFile(self, filePath, options=None):
'''
Submitting local file to plagiarism scan
'''
assert filePath, 'Missing filePath'
assert os.path.exists(filePath), 'filePath is not exists!'
assert os.path.getsize(
filePath
) <= Consts.MAX_FILE_SIZE_BYTES, 'Exceed max file size (max allowed: %s bytes)' % (
Consts.MAX_FILE_SIZE_BYTES)
serviceUrl = "%sv2/%s/create-by-file" % (Consts.SERVICE_ENTRY_POINT,
self.product)
headers = {
Consts.AUTHORIZATION_HEADER:
self.token.generateAuthrizationHeader()
}
if options != None:
headers = headers.copy()
headers.update(options.getHeaders())
theFile = {'file': (os.path.basename(filePath), open(filePath, 'rb'))}
response = requests.post(serviceUrl, headers=headers, files=theFile)
if (response.status_code == Consts.HTTP_SUCCESS):
return CopyleaksProcess(self.getProduct(), self.token,
response.json())
else:
raise CommandFailedError(response)
def getProcesses(self):
'''
Get your active processes
'''
url = "%s%s/%s/list" % (Consts.SERVICE_ENTRY_POINT, Consts.SERVICE_VERSION, self.product)
headers = {
Consts.AUTHORIZATION_HEADER: self.token.generateAuthrizationHeader()
}
response = requests.get(url, headers=headers)
if (response.status_code == Consts.HTTP_SUCCESS):
return CopyleaksProcess.parseProcesses(self.login, response.json())
else:
raise CommandFailedError(response)
def getProcesses(self):
'''
Get your active processes
'''
url = "%s%s/%s/list" % (Consts.SERVICE_ENTRY_POINT, Consts.SERVICE_VERSION, self.product)
headers = {
Consts.AUTHORIZATION_HEADER: self.token.generateAuthrizationHeader()
}
response = requests.get(url, headers=headers)
if (response.status_code == Consts.HTTP_SUCCESS):
return CopyleaksProcess.parseProcesses(self.login, response.json())
else:
raise CommandFailedError(response)
def createByFiles(self, filePaths, options=None):
'''
Submitting local files to plagiarism scan. The files are being submitted
together on same HTTP request.
Args:
filePaths - list of file paths (string)
options - Process options
'''
assert filePaths, 'Missing filePath'
for i in range(len(filePaths)):
assert os.path.exists(filePaths[i]), 'filePath is not exists!'
assert os.path.getsize(
filePaths[i]
) <= Consts.MAX_FILE_SIZE_BYTES, 'Exceed max file size (max allowed: %s bytes)' % (
Consts.MAX_FILE_SIZE_BYTES)
assert len(filePaths) <= 100, 'Too many files'
serviceUrl = "%sv2/%s/create-by-file" % (Consts.SERVICE_ENTRY_POINT,
self.product)
headers = {
Consts.AUTHORIZATION_HEADER:
self.token.generateAuthrizationHeader()
}
if options != None:
headers = headers.copy()
headers.update(options.getHeaders())
theFiles = {}
for i in range(len(filePaths)):
theFiles['file%s' % (i)] = (os.path.basename(filePaths[i]),
open(filePaths[i], 'rb'))
response = requests.post(serviceUrl, headers=headers, files=theFiles)
if (response.status_code == Consts.HTTP_SUCCESS):
lstProcesses = []
returnedObj = response.json()
for i in range(len(returnedObj["Success"])):
lstProcesses.append(
CopyleaksProcess(self.getProduct(), self.token,
returnedObj["Success"][i]))
return lstProcesses, returnedObj["Errors"]
else:
raise CommandFailedError(response)