From a862ff2be6c4af21aa0fc9a5f0943fabbe888f23 Mon Sep 17 00:00:00 2001
From: MDW <mdeweerd@users.noreply.github.com>
Date: Fri, 19 May 2023 01:04:42 +0200
Subject: [PATCH] Add fallback for plain elm #294 #290

---
 ingest.py | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/ingest.py b/ingest.py
index 47b5192..f226102 100644
--- a/ingest.py
+++ b/ingest.py
@@ -31,7 +31,7 @@ LOADER_MAPPING = {
     ".doc": (UnstructuredWordDocumentLoader, {}),
     ".docx": (UnstructuredWordDocumentLoader, {}),
     ".enex": (EverNoteLoader, {}),
-    ".eml": (UnstructuredEmailLoader, {}),
+    ".eml": (MyElmLoader, {}),
     ".epub": (UnstructuredEPubLoader, {}),
     ".html": (UnstructuredHTMLLoader, {}),
     ".md": (UnstructuredMarkdownLoader, {}),
@@ -47,6 +47,24 @@ LOADER_MAPPING = {
 load_dotenv()
 
 
+class MyElmLoader(UnstructuredEmailLoader):
+    """Wrapper to fallback to text/plain when default does not work"""
+
+    def load(self) -> List[Document]:
+        """Wrapper adding fallback for elm without html"""
+        try:
+            doc = UnstructuredEmailLoader.load()
+        except ValueError as e:
+            if 'text/html content not found in email' in str(e):
+                # Try plain text
+                self.unstructured_kwargs["content_source"]="text/plain"
+                doc = UnstructuredEmailLoader.load()
+            else:
+                raise
+
+        return doc
+
+
 def load_single_document(file_path: str) -> Document:
     ext = "." + file_path.rsplit(".", 1)[-1]
     if ext in LOADER_MAPPING: