def lambda_handler(event, context):
print("Comprehend Event: {}".format(event))
bucketName = event['Records'][0]['s3']['bucket']['name']
objectName = urllib.parse.unquote_plus(
event['Records'][0]['s3']['object']['key'])
callerId = context.invoked_function_arn
assert (FileHelper().getFileNameAndExtension(objectName.lower()) == (
'fullresponse', 'json'
)), "File detected does not match expected format: 'fullresponse.json'"
runComprehend(bucketName, objectName, callerId)
def processRequest(request):
output = ""
logger.info("request: {}".format(request))
up = urlparse(request["s3uri"], allow_fragments=False)
accountid = request["accountId"]
jobid = request["jobId"]
bucketName = up.netloc
objectkey = up.path.lstrip('/')
basePrefixPath = objectkey + accountid + "-TranslateText-" + jobid + "/"
languageCode = request["langCode"]
logger.debug("Base Prefix Path:{}".format(basePrefixPath))
captions = Captions()
#filter only the delimited files with .delimited suffix
objs = S3Helper().getFilteredFileNames(bucketName, basePrefixPath,
["delimited"])
for obj in objs:
try:
#Read the Delimited file contents
content = S3Helper().readFromS3(bucketName, obj)
fileName = FileHelper().getFileName(obj)
sourceFileName = FileHelper().getFileName(
obj.replace("{}.".format(languageCode), ""))
logger.debug("SourceFileKey:{}.processed".format(sourceFileName))
soureFileKey = "input/{}.processed".format(sourceFileName)
vttObject = {}
vttObject["Bucket"] = bucketName
vttObject["Key"] = soureFileKey
captions_list = []
#Based on the file format, call the right method to load the file as python object
if (fileName.endswith("vtt")):
captions_list = captions.vttToCaptions(vttObject)
elif (fileName.endswith("srt")):
captions_list = captions.srtToCaptions(vttObject)
# Replace the text captions with the translated content
translatedCaptionsList = captions.DelimitedToWebCaptions(
captions_list, content, "<span>", 15)
translatedText = ""
# Recreate the Caption files in VTT or SRT format
if (fileName.endswith("vtt")):
translatedText = captions.captionsToVTT(translatedCaptionsList)
elif (fileName.endswith("srt")):
translatedText = captions.captionsToSRT(translatedCaptionsList)
logger.debug(translatedText)
logger.debug(content)
newObjectKey = "output/{}".format(fileName)
# Write the VTT or SRT file into the output S3 folder
S3Helper().writeToS3(str(translatedText), bucketName, newObjectKey)
output = "Output Object: {}/{}".format(bucketName, newObjectKey)
logger.debug(output)
except ClientError as e:
logger.error("An error occured with S3 bucket operations: %s" % e)
except:
e = sys.exc_info()[0]
logger.error("Error occured processing the captions file: %s" % e)
objs = S3Helper().getFilteredFileNames(bucketName, "captions-in/",
["delimited"])
if (request["delete_captionsin"]
and request["delete_captionsin"] == "true"):
for obj in objs:
try:
logger.debug(
"Deleting temp delimited caption files {}".format(obj))
S3Helper().deleteObject(bucketName, obj)
except ClientError as e:
logger.error("An error occured with S3 bucket operations: %s" %
e)
except:
e = sys.exc_info()[0]
logger.error(
"Error occured in deleting the delimited captions file: %s"
% e)
