feat: adds extractor for epub

.devcontainer/Dockerfile

@@ -4,7 +4,7 @@ ARG DEBIAN_FRONTEND=noninteractive
 ARG USER=vscode
 
 RUN DEBIAN_FRONTEND=noninteractive \
-    && apt-get update \ 
+    && apt-get update \
     && apt-get install -y build-essential --no-install-recommends make \
         ca-certificates \
         git \
@@ -27,7 +27,7 @@ RUN DEBIAN_FRONTEND=noninteractive \
 # Python and poetry installation
 USER $USER
 ARG HOME="/home/$USER"
-ARG PYTHON_VERSION=3.11
+ARG PYTHON_VERSION=3.13
 
 ENV PYENV_ROOT="${HOME}/.pyenv"
 ENV PATH="${PYENV_ROOT}/shims:${PYENV_ROOT}/bin:${HOME}/.local/bin:$PATH"
@@ -40,4 +40,4 @@ RUN echo "done 0" \
     && pyenv global ${PYTHON_VERSION} \
     && echo "done 3" \
     && curl -sSL https://install.python-poetry.org | python3 - \
-    && poetry config virtualenvs.in-project true
+    && poetry config virtualenvs.in-project true

libs/extractor-api-lib/pyproject.toml

@@ -100,6 +100,7 @@ markdownify = "^1.1.0"
 langchain-core = "0.3.63"
 camelot-py = {extras = ["cv"], version = "^1.0.0"}
 fake-useragent = "^2.2.0"
+pypandoc-binary = "^1.15"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.3.5"

libs/extractor-api-lib/src/extractor_api_lib/dependency_container.py

@@ -5,6 +5,7 @@
 
 from extractor_api_lib.impl.api_endpoints.general_source_extractor import GeneralSourceExtractor
 from extractor_api_lib.impl.extractors.confluence_extractor import ConfluenceExtractor
+from extractor_api_lib.impl.extractors.file_extractors.epub_extractor import EpubExtractor
 from extractor_api_lib.impl.extractors.file_extractors.ms_docs_extractor import MSDocsExtractor
 from extractor_api_lib.impl.extractors.file_extractors.pdf_extractor import PDFExtractor
 from extractor_api_lib.impl.extractors.file_extractors.xml_extractor import XMLExtractor
@@ -46,7 +47,9 @@ class DependencyContainer(DeclarativeContainer):
     intern2external = Singleton(Internal2ExternalInformationPiece)
     langchain_document2information_piece = Singleton(ConfluenceLangchainDocument2InformationPiece)
     sitemap_document2information_piece = Singleton(SitemapLangchainDocument2InformationPiece)
-    file_extractors = List(pdf_extractor, ms_docs_extractor, xml_extractor)
+    epub_extractor = Singleton(EpubExtractor, file_service, langchain_document2information_piece)
+
+    file_extractors = List(pdf_extractor, ms_docs_extractor, xml_extractor, epub_extractor)
 
     general_file_extractor = Singleton(GeneralFileExtractor, file_service, file_extractors, intern2external)
     confluence_extractor = Singleton(ConfluenceExtractor, mapper=langchain_document2information_piece)

libs/extractor-api-lib/src/extractor_api_lib/impl/extractors/file_extractors/epub_extractor.py

@@ -0,0 +1,71 @@
+"""Module containing the EpubExtractor class."""
+
+import logging
+from pathlib import Path
+
+
+from extractor_api_lib.impl.mapper.confluence_langchain_document2information_piece import (
+    ConfluenceLangchainDocument2InformationPiece,
+)
+from langchain_community.document_loaders import UnstructuredEPubLoader
+
+
+from extractor_api_lib.file_services.file_service import FileService
+from extractor_api_lib.extractors.information_file_extractor import InformationFileExtractor
+from extractor_api_lib.impl.types.file_type import FileType
+from extractor_api_lib.models.dataclasses.internal_information_piece import InternalInformationPiece
+
+logger = logging.getLogger(__name__)
+
+
+class EpubExtractor(InformationFileExtractor):
+    """Extractor for Epub documents using unstructured library."""
+
+    def __init__(
+        self,
+        file_service: FileService,
+        mapper: ConfluenceLangchainDocument2InformationPiece,
+    ):
+        """Initialize the EpubExtractor.
+
+        Parameters
+        ----------
+        file_service : FileService
+            Handler for downloading the file to extract content from and upload results to if required.
+        mapper : ConfluenceLangchainDocument2InformationPiece
+            An instance of ConfluenceLangchainDocument2InformationPiece used for mapping langchain documents
+            to information pieces.
+        """
+        super().__init__(file_service=file_service)
+        self._mapper = mapper
+
+    @property
+    def compatible_file_types(self) -> list[FileType]:
+        """
+        List of compatible file types for the XML extractor.
+
+        Returns
+        -------
+        list[FileType]
+            A list containing the compatible file types, which in this case is XML.
+        """
+        return [FileType.EPUB]
+
+    async def aextract_content(self, file_path: Path, name: str) -> list[InternalInformationPiece]:
+        """
+        Extract content from an epub file and processes the elements.
+
+        Parameters
+        ----------
+        file_path : Path
+            The path to the epub file to be processed.
+        name : str
+            Name of the document.
+
+        Returns
+        -------
+        list[InformationPiece]
+            A list of processed information pieces extracted from the epub file.
+        """
+        elements = UnstructuredEPubLoader(file_path.as_posix()).load()
+        return [self._mapper.map_document2informationpiece(x, name) for x in elements]

libs/extractor-api-lib/src/extractor_api_lib/impl/types/file_type.py

@@ -11,3 +11,4 @@ class FileType(StrEnum):
     DOCX = "DOCX"
     PPTX = "PPTX"
     XML = "XML"
+    EPUB = "EPUB"