|
@@ -105,7 +105,7 @@ class TikaLoader:
|
|
|
|
|
|
if r.ok:
|
|
if r.ok:
|
|
raw_metadata = r.json()
|
|
raw_metadata = r.json()
|
|
- text = raw_metadata.get("X-TIKA:content", "<No text content found>")
|
|
|
|
|
|
+ text = raw_metadata.get("X-TIKA:content", "<No text content found>").strip()
|
|
|
|
|
|
if "Content-Type" in raw_metadata:
|
|
if "Content-Type" in raw_metadata:
|
|
headers["Content-Type"] = raw_metadata["Content-Type"]
|
|
headers["Content-Type"] = raw_metadata["Content-Type"]
|