opensubsdata.py 文件源码

def loadConversations(self, dirName):
        """
        Args:
            dirName (str): folder to load
        Return:
            array(question, answer): the extracted QA pairs
        """
        conversations = []
        dirList = self.filesInDir(dirName)
        for filepath in tqdm(dirList, "OpenSubtitles data files"):
            if filepath.endswith('gz'):
                try:
                    doc = self.getXML(filepath)
                    conversations.extend(self.genList(doc))
                except ValueError:
                    tqdm.write("Skipping file %s with errors." % filepath)
                except:
                    print("Unexpected error:", sys.exc_info()[0])
                    raise
        return conversations