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/README.md

@@ -1,7 +1,7 @@
 # RAG Core Libraries
 
 This directory contains the core libraries of the STACKIT RAG template.
-These libraries provide comprehensive document extraction capabilities including support for files (PDF, DOCX, XML), web sources via sitemaps, and Confluence pages.
+These libraries provide comprehensive document extraction capabilities including support for files (PDF, DOCX, XML, EPUB), web sources via sitemaps, and Confluence pages.
 It consists of the following python packages:
 
 - [`1. Rag Core API`](#1-rag-core-api)
@@ -230,7 +230,8 @@ Technically, all parameters of the `SitemapLoader` from LangChain can be provide
 | pdf_extractor | [`extractor_api_lib.extractors.information_extractor.InformationExtractor`](./extractor-api-lib/src/extractor_api_lib/extractors/information_extractor.py) |[`extractor_api_lib.impl.extractors.file_extractors.pdf_extractor.PDFExtractor`](./extractor-api-lib/src/extractor_api_lib/impl/extractors/file_extractors/pdf_extractor.py) | Extractor used for extracting information from PDF documents. |
 | ms_docs_extractor |  [`extractor_api_lib.extractors.information_extractor.InformationExtractor`](./extractor-api-lib/src/extractor_api_lib/extractors/information_extractor.py) |[`extractor_api_lib.extractors.file_extractors.ms_docs_extractor.MSDocsExtractor`](./extractor-api-lib/src/extractor_api_lib/impl/extractors/file_extractors/ms_docs_extractor.py) | Extractor used for extracting information from Microsoft Documents like *.docx, etc. |
 | xml_extractor |  [`extractor_api_lib.extractors.information_extractor.InformationExtractor`](./extractor-api-lib/src/extractor_api_lib/extractors/information_extractor.py) | [`extractor_api_lib.extractors.file_extractors.xml_extractor.XMLExtractor`](./extractor-api-lib/src/extractor_api_lib/impl/extractors/file_extractors/xml_extractor.py) | Extractor used for extracting content from XML documents. |
-| all_extractors | `dependency_injector.providers.List[extractor_api_lib.extractors.information_extractor.InformationExtractor]` | `dependency_injector.providers.List(pdf_extractor, ms_docs_extractor, xml_extractor)` | List of all available extractors. If you add a new type of extractor you would have to add it to this list. |
+| epub_extractor |  [`extractor_api_lib.extractors.information_file_extractor.InformationFileExtractor`](./extractor-api-lib/src/extractor_api_lib/extractors/information_file_extractor.py) | [`extractor_api_lib.extractors.file_extractors.epub_extractor.EPUBExtractor`](./extractor-api-lib/src/extractor_api_lib/impl/extractors/file_extractors/epub_extractor.py) | Extractor used for extracting content from EPUB documents. |
+| file_extractors | `dependency_injector.providers.List[extractor_api_lib.extractors.information_file_extractor.InformationFileExtractor]` | `dependency_injector.providers.List(pdf_extractor, ms_docs_extractor, xml_extractor, epub_extractor)` | List of all available extractors. If you add a new type of extractor you would have to add it to this list. |
 | general_file_extractor | [`extractor_api_lib.api_endpoints.file_extractor.FileExtractor`](./extractor-api-lib/src/extractor_api_lib/api_endpoints/file_extractor.py) |[`extractor_api_lib.impl.api_endpoints.general_file_extractor.GeneralFileExtractor`](./extractor-api-lib/src/extractor_api_lib/impl/api_endpoints/general_file_extractor.py) | Combines multiple file extractors and decides which one to use for the given file format. |
 | general_source_extractor | [`extractor_api_lib.api_endpoints.source_extractor.SourceExtractor`](./extractor-api-lib/src/extractor_api_lib/api_endpoints/source_extractor.py) | [`extractor_api_lib.impl.api_endpoints.general_source_extractor.GeneralSourceExtractor`](./extractor-api-lib/src/extractor_api_lib/impl/api_endpoints/general_source_extractor.py) | Implementation of the `/extract_from_source` endpoint.  Will decide the correct extractor for the source. |
 | confluence_extractor | [`extractor_api_lib.extractors.information_extractor.InformationExtractor`](./extractor-api-lib/src/extractor_api_lib/extractors/information_extractor.py) | [`extractor_api_lib.impl.extractors.confluence_extractor.ConfluenceExtractor`](./extractor-api-lib/src/extractor_api_lib/impl/extractors/confluence_extractor.py) | Implementation of an extractor for the source `confluence`. |

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

@@ -3,12 +3,21 @@
 from dependency_injector.containers import DeclarativeContainer
 from dependency_injector.providers import Factory, List, Singleton  # noqa: WOT001
 
-from extractor_api_lib.impl.api_endpoints.general_source_extractor import GeneralSourceExtractor
+from extractor_api_lib.impl.api_endpoints.general_file_extractor import (
+    GeneralFileExtractor,
+)
+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.ms_docs_extractor import MSDocsExtractor
+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
-from extractor_api_lib.impl.api_endpoints.general_file_extractor import GeneralFileExtractor
 from extractor_api_lib.impl.extractors.sitemap_extractor import SitemapExtractor
 from extractor_api_lib.impl.file_services.s3_service import S3Service
 from extractor_api_lib.impl.mapper.confluence_langchain_document2information_piece import (
@@ -17,7 +26,12 @@
 from extractor_api_lib.impl.mapper.internal2external_information_piece import (
     Internal2ExternalInformationPiece,
 )
-from extractor_api_lib.impl.mapper.sitemap_document2information_piece import SitemapLangchainDocument2InformationPiece
+from extractor_api_lib.impl.mapper.langchain_document2information_piece import (
+    LangchainDocument2InformationPiece,
+)
+from extractor_api_lib.impl.mapper.sitemap_document2information_piece import (
+    SitemapLangchainDocument2InformationPiece,
+)
 from extractor_api_lib.impl.settings.pdf_extractor_settings import PDFExtractorSettings
 from extractor_api_lib.impl.settings.s3_settings import S3Settings
 from extractor_api_lib.impl.table_converter.dataframe2markdown import DataFrame2Markdown
@@ -44,12 +58,15 @@ class DependencyContainer(DeclarativeContainer):
     xml_extractor = Singleton(XMLExtractor, file_service)
 
     intern2external = Singleton(Internal2ExternalInformationPiece)
-    langchain_document2information_piece = Singleton(ConfluenceLangchainDocument2InformationPiece)
+    confluence_langchain_document2information_piece = Singleton(ConfluenceLangchainDocument2InformationPiece)
+    langchain_document2information_piece = Singleton(LangchainDocument2InformationPiece)
     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)
+    confluence_extractor = Singleton(ConfluenceExtractor, mapper=confluence_langchain_document2information_piece)
 
     sitemap_extractor = Singleton(
         SitemapExtractor,

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

@@ -0,0 +1,73 @@
+"""Module containing the EpubExtractor class."""
+
+import logging
+from pathlib import Path
+
+from langchain_community.document_loaders import UnstructuredEPubLoader
+
+from extractor_api_lib.extractors.information_file_extractor import (
+    InformationFileExtractor,
+)
+from extractor_api_lib.file_services.file_service import FileService
+from extractor_api_lib.impl.mapper.langchain_document2information_piece import (
+    LangchainDocument2InformationPiece,
+)
+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: LangchainDocument2InformationPiece,
+    ):
+        """Initialize the EpubExtractor.
+
+        Parameters
+        ----------
+        file_service : FileService
+            Handler for downloading the file to extract content from and upload results to if required.
+        mapper : LangchainDocument2InformationPiece
+            An instance of LangchainDocument2InformationPiece 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 EPUB extractor.
+
+        Returns
+        -------
+        list[FileType]
+            A list containing the compatible file types, which in this case is EPUB.
+        """
+        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(document=x, document_name=name) for x in elements]

libs/extractor-api-lib/src/extractor_api_lib/impl/mapper/langchain_document2information_piece.py

@@ -0,0 +1,12 @@
+"""Module for the LangchainDocument2InformationPiece class."""
+
+from extractor_api_lib.mapper.source_langchain_document2information_piece import (
+    SourceLangchainDocument2InformationPiece,
+)
+
+
+class LangchainDocument2InformationPiece(SourceLangchainDocument2InformationPiece):
+    """A class to map a LangchainDocument to an InformationPiece."""
+
+    def _map_meta(self, internal: dict, document_name: str) -> dict:
+        return internal

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"

libs/extractor-api-lib/tests/epub_extractor_test.py

@@ -0,0 +1,50 @@
+"""Comprehensive test suite for SitemapExtractor class."""
+
+from pathlib import Path
+
+import pytest
+
+from extractor_api_lib.impl.extractors.file_extractors.epub_extractor import (
+    EpubExtractor,
+)
+from extractor_api_lib.impl.mapper.langchain_document2information_piece import (
+    LangchainDocument2InformationPiece,
+)
+from extractor_api_lib.impl.types.file_type import FileType
+from extractor_api_lib.models.content_type import ContentType
+
+
+class TestEpubExtractor:
+    """Test class for EpubExtractor."""
+
+    @pytest.fixture
+    def mapper(self) -> LangchainDocument2InformationPiece:
+        return LangchainDocument2InformationPiece()
+
+    @pytest.fixture
+    def epub_extractor(self, mock_file_service, mapper):
+        """Create a EpubExtractor instance for testing."""
+        return EpubExtractor(file_service=mock_file_service, mapper=mapper)
+
+    def test_init(self, mock_file_service, mapper):
+        """Test EpubExtractor initialization."""
+        extractor = EpubExtractor(file_service=mock_file_service, mapper=mapper)
+        assert extractor._mapper == mapper
+        assert extractor._file_service == mock_file_service
+
+    def test_file_type(self, epub_extractor):
+        """Test that extractor_type returns EPUB."""
+        assert epub_extractor.compatible_file_types == [FileType.EPUB]
+
+    @pytest.mark.asyncio
+    async def test_extract_content_success(self, epub_extractor):
+        page_content = "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam"
+
+        test_data_dir = Path(__file__).parent / "test_data"
+
+        file_path = test_data_dir / "LoremIpsum.epub"
+        result = await epub_extractor.aextract_content(file_path, file_path.name)
+
+        assert len(result) == 1
+        assert result[0].type == ContentType.TEXT
+        assert result[0].page_content == page_content