feat: add hwp/hwpx support and fixtures for testing

README.md

@@ -105,6 +105,7 @@ At the moment, the following optional dependencies are available:
 * `[xls]` Installs dependencies for older Excel files
 * `[pdf]` Installs dependencies for PDF files
 * `[outlook]` Installs dependencies for Outlook messages
+* `[hwp]` Installs dependencies for HWP and HWPX files
 * `[az-doc-intel]` Installs dependencies for Azure Document Intelligence
 * `[az-content-understanding]` Installs dependencies for Azure Content Understanding
 * `[audio-transcription]` Installs dependencies for audio transcription of wav and mp3 files

packages/markitdown/pyproject.toml

@@ -50,13 +50,15 @@ all = [
   "azure-ai-documentintelligence",
   "azure-ai-contentunderstanding>=1.2.0b1",
   "azure-identity",
+  "rhwp-python>=0.8.1",
 ]
 pptx = ["python-pptx"]
 docx = ["mammoth~=1.11.0", "lxml"]
 xlsx = ["pandas", "openpyxl"]
 xls = ["pandas", "xlrd"]
 pdf = ["pdfminer.six>=20251230", "pdfplumber>=0.11.9"]
 outlook = ["olefile"]
+hwp = ["rhwp-python>=0.8.1"]
 audio-transcription = ["pydub", "SpeechRecognition"]
 youtube-transcription = ["youtube-transcript-api~=1.2.3"]
 az-doc-intel = ["azure-ai-documentintelligence", "azure-identity"]

packages/markitdown/src/markitdown/_markitdown.py

@@ -42,6 +42,7 @@
     DocumentIntelligenceConverter,
     ContentUnderstandingConverter,
     CsvConverter,
+    HwpConverter,
 )
 
 from ._base_converter import DocumentConverter, DocumentConverterResult
@@ -250,6 +251,7 @@ def enable_builtins(self, **kwargs) -> None:
             self.register_converter(OutlookMsgConverter())
             self.register_converter(EpubConverter())
             self.register_converter(CsvConverter())
+            self.register_converter(HwpConverter())
 
             # Register Document Intelligence converter at the top of the stack if endpoint is provided
             docintel_endpoint = kwargs.get("docintel_endpoint")

packages/markitdown/src/markitdown/converters/__init__.py

@@ -27,6 +27,7 @@
 )
 from ._epub_converter import EpubConverter
 from ._csv_converter import CsvConverter
+from ._hwp_converter import HwpConverter
 
 __all__ = [
     "PlainTextConverter",
@@ -51,4 +52,5 @@
     "ContentUnderstandingFileType",
     "EpubConverter",
     "CsvConverter",
+    "HwpConverter",
 ]

packages/markitdown/src/markitdown/converters/_hwp_converter.py

@@ -0,0 +1,83 @@
+import os
+from pathlib import Path
+import tempfile
+from typing import Any, BinaryIO
+
+from .._base_converter import DocumentConverter, DocumentConverterResult
+from .._exceptions import MissingDependencyException, MISSING_DEPENDENCY_MESSAGE
+from .._stream_info import StreamInfo
+
+_dependency_exc_info = None
+rhwp: Any = None
+try:
+    import rhwp
+except ImportError:
+    import sys
+
+    _dependency_exc_info = sys.exc_info()
+
+ACCEPTED_MIME_TYPE_PREFIXES = [
+    "application/x-hwp",
+    "application/vnd.hancom.hwp",
+    "application/x-hwp-v5",
+    "application/haansofthwp",
+    "application/vnd.hancom.hwpx",
+    "application/hwpx",
+    "application/x-hwpx",
+]
+
+ACCEPTED_FILE_EXTENSIONS = [".hwp", ".hwpx"]
+
+
+class HwpConverter(DocumentConverter):
+    """Converts HWP and HWPX files to Markdown with rhwp-python."""
+
+    def accepts(
+        self,
+        file_stream: BinaryIO,
+        stream_info: StreamInfo,
+        **kwargs: Any,
+    ) -> bool:
+        mimetype = (stream_info.mimetype or "").lower()
+        extension = (stream_info.extension or "").lower()
+
+        if extension in ACCEPTED_FILE_EXTENSIONS:
+            return True
+
+        return any(
+            mimetype.startswith(prefix) for prefix in ACCEPTED_MIME_TYPE_PREFIXES
+        )
+
+    def convert(
+        self,
+        file_stream: BinaryIO,
+        stream_info: StreamInfo,
+        **kwargs: Any,
+    ) -> DocumentConverterResult:
+        if _dependency_exc_info is not None:
+            raise MissingDependencyException(
+                MISSING_DEPENDENCY_MESSAGE.format(
+                    converter=type(self).__name__,
+                    extension=".hwp or .hwpx",
+                    feature="hwp",
+                )
+            ) from _dependency_exc_info[1].with_traceback(  # type: ignore[union-attr]
+                _dependency_exc_info[2]
+            )
+
+        extension = (stream_info.extension or "").lower()
+        if extension not in ACCEPTED_FILE_EXTENSIONS:
+            extension = ".hwp"
+
+        with tempfile.TemporaryDirectory(prefix="markitdown-rhwp-") as temp_dir:
+            temp_path = Path(temp_dir)
+            input_path = temp_path / f"input{extension}"
+
+            current_position = file_stream.tell()
+            try:
+                input_path.write_bytes(file_stream.read())
+            finally:
+                file_stream.seek(current_position)
+
+            document = rhwp.parse(os.fspath(input_path))
+            return DocumentConverterResult(markdown=document.to_ir().to_markdown())