From 4a52a71956a8d46fcb7294ac71734504bb09bcc2 Mon Sep 17 00:00:00 2001
From: S. Solomon Darnell
Date: Fri, 28 Mar 2025 21:52:21 -0500
Subject: two version of R2R are here

---
 R2R/r2r/parsers/media/docx_parser.py | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)
 create mode 100755 R2R/r2r/parsers/media/docx_parser.py

(limited to 'R2R/r2r/parsers/media/docx_parser.py')

diff --git a/R2R/r2r/parsers/media/docx_parser.py b/R2R/r2r/parsers/media/docx_parser.py
new file mode 100755
index 00000000..9edced81
--- /dev/null
+++ b/R2R/r2r/parsers/media/docx_parser.py
@@ -0,0 +1,28 @@
+from io import BytesIO
+from typing import AsyncGenerator
+
+from r2r.base.abstractions.document import DataType
+from r2r.base.parsers.base_parser import AsyncParser
+
+
+class DOCXParser(AsyncParser[DataType]):
+    """A parser for DOCX data."""
+
+    def __init__(self):
+        try:
+            from docx import Document
+
+            self.Document = Document
+        except ImportError:
+            raise ValueError(
+                "Error, `python-docx` is required to run `DOCXParser`. Please install it using `pip install python-docx`."
+            )
+
+    async def ingest(self, data: DataType) -> AsyncGenerator[str, None]:
+        """Ingest DOCX data and yield text from each paragraph."""
+        if isinstance(data, str):
+            raise ValueError("DOCX data must be in bytes format.")
+
+        doc = self.Document(BytesIO(data))
+        for paragraph in doc.paragraphs:
+            yield paragraph.text
-- 
cgit v1.2.3