HCE Project Python language Distributed Tasks Manager Application, Distributed Crawler Application and client API bindings.  2.0.0-chaika
Hierarchical Cluster Engine Python language binding
ProcessorTask.py File Reference

Go to the source code of this file.

Classes

class  dc_processor.ProcessorTask.ProcessorTask
 
class  dc_processor.ProcessorTask.ProcessorTask.Meta
 

Namespaces

 dc_processor.ProcessorTask
 

Variables

string dc_processor.ProcessorTask.APP_NAME = "processor-task"
 
string dc_processor.ProcessorTask.DC_URLS_DB_NAME = "dc_urls"
 
string dc_processor.ProcessorTask.DC_URLS_TABLE_PREFIX = "urls_"
 
string dc_processor.ProcessorTask.DC_SITES_DB_NAME = "dc_sites"
 
string dc_processor.ProcessorTask.DC_SITES_TABLE_NAME = "sites"
 
string dc_processor.ProcessorTask.DC_URLS_TABLE_NAME = "urls"
 
string dc_processor.ProcessorTask.DC_SITES_PROPERTIES_TABLE_NAME = "sites_properties"
 
string dc_processor.ProcessorTask.MSG_ERROR_PROCESS_BATCH_ITEM = "Error process batch item "
 
string dc_processor.ProcessorTask.MSG_ERROR_PROCESS_BATCH = "Error process batch. "
 
string dc_processor.ProcessorTask.MSG_ERROR_LOAD_CONFIG = "Error loading config file."
 
string dc_processor.ProcessorTask.MSG_ERROR_EMPTY_CONFIG_FILE_NAME = "Config file name is empty."
 
string dc_processor.ProcessorTask.MSG_ERROR_LOAD_LOG_CONFIG_FILE = "Error loading logging config file. Exiting."
 
string dc_processor.ProcessorTask.MSG_ERROR_LOAD_URL_DATA = "Can't load url data: "
 
string dc_processor.ProcessorTask.MSG_ERROR_LOAD_SITE_DATA = "Error load site data: "
 
string dc_processor.ProcessorTask.MSG_ERROR_READ_SITE_FROM_DB = "Error read site data from db"
 
string dc_processor.ProcessorTask.MSG_ERROR_PROCESS_TASK = "Can't process task "
 
string dc_processor.ProcessorTask.MSG_ERROR_SERIALISE_RESULT = "Error serialize result "
 
string dc_processor.ProcessorTask.MSG_ERROR_GET_SITE_FILE_DB = "Error get site file db "
 
string dc_processor.ProcessorTask.MSG_ERROR_UPDATE_RECORD = "Error update record "
 
string dc_processor.ProcessorTask.MSG_ERROR_UPDATE_PROCESSED_URL = "Error update processed url "
 
string dc_processor.ProcessorTask.MSG_ERROR_UPDATE_URL_CHARSET = "Error update url charset "
 
string dc_processor.ProcessorTask.MSG_ERROR_GET_RAW_CONTENT_FROM_DB = "Error get raw content from disk "
 
string dc_processor.ProcessorTask.MSG_ERROR_PROCESS = "Error process "
 
string dc_processor.ProcessorTask.MSG_ERROR_LOAD_SITE_PROPERTIES = "Error load site properties "
 
string dc_processor.ProcessorTask.MSG_ERROR_CHECK_SITE = "Site check is not passed. "
 
string dc_processor.ProcessorTask.MSG_ERROR_LOAD_OPTIONS = "Error load options. "
 
string dc_processor.ProcessorTask.MSG_ERROR_CONVERT_RAW_CONTENT_CHARSET = "Cannot convert raw content charset. "
 
string dc_processor.ProcessorTask.MSG_ERROR_UPDATE_SITE_RESOURCES = "Error update site resources. "
 
string dc_processor.ProcessorTask.MSG_ERROR_EMPTY_BATCH = "Error read input pickle from stdin."
 
string dc_processor.ProcessorTask.MSG_ERROR_CHECK_CONTENT_HASH = "Fail to check content hash"
 
string dc_processor.ProcessorTask.MSG_ERROR_CALC_CONTENT_HASH = "Fail to calc content hash"
 
string dc_processor.ProcessorTask.MSG_ERROR_CHECK_CONTENT_HASH_DUPLICATE = "Can't check content hash duplicate"
 
string dc_processor.ProcessorTask.MSG_INFO_PROCESSOR_CMD = "Processor cmd: "
 
string dc_processor.ProcessorTask.MSG_INFO_LOAD_SITE_PROPERTIES = "Mismatch load site properties "
 
string dc_processor.ProcessorTask.MSG_INFO_PROCESS_BATCH = "Skipped process batch. "
 
string dc_processor.ProcessorTask.MSG_INFO_PROCESS_BATCH_ITEM = "Skipped process batch item "
 
string dc_processor.ProcessorTask.MSG_INFO_PROCESSOR_EXIT_CODE = "Scraper exit_code: "
 
string dc_processor.ProcessorTask.MSG_INFO_PROCESSOR_OUTPUT = "Scraper output: "
 
string dc_processor.ProcessorTask.MSG_INFO_PROCESSOR_ERROR = "Scraper err: "
 
int dc_processor.ProcessorTask.EXIT_SUCCESS = 0
 
int dc_processor.ProcessorTask.EXIT_FAILURE = 1
 
int dc_processor.ProcessorTask.ERROR_MASK_NO_ERRORS = 0
 
int dc_processor.ProcessorTask.ERROR_MASK_SITE_OK = 0
 
int dc_processor.ProcessorTask.URLS_OF_MEDIA_CONTENT = 1
 
string dc_processor.ProcessorTask.ENV_PROCESSOR_STORE_PATH = "ENV_PROCESSOR_STORE_PATH"
 
string dc_processor.ProcessorTask.SCRAPER_RESPONSE_ATTR_NAME = 'scraperResponse'
 
string dc_processor.ProcessorTask.DEFSULT_CHAIN_DELIMITER = ' '
 
 dc_processor.ProcessorTask.Results = namedtuple("Results", "exit_code, output, err, scraperResponse")