1c0cd03712f95fb5966968abc2a39313175594c6,src/fonduer/parser/preprocessors/doc_preprocessor.py,DocPreprocessor,__len__,#DocPreprocessor#,44

Before Change

    def __len__(self):
        Provide a len attribute based on max_docs and number of files in folder.
        num_docs = min(len(self.all_files), self.max_docs)
        return num_docs

    def __iter__(self):

After Change

        return [doc for doc in self.get_docs_for_path(fp)]

    def __len__(self):
        raise NotImplementedError(
            "One generec file can yield more than one Document objects, "
            "so length can not be yielded before we process all files"
        )

    def __iter__(self):
        return self.generate()

Instances