trustgraph-base 2.2.6__tar.gz → 2.2.8__tar.gz

{trustgraph_base-2.2.6 → trustgraph_base-2.2.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: trustgraph-base
-Version: 2.2.6
+Version: 2.2.8
 Summary: TrustGraph provides a means to run a pipeline of flexible AI processing components in a flexible means to achieve a processing pipeline.
 Author-email: "trustgraph.ai" <security@trustgraph.ai>
 Project-URL: Homepage, https://github.com/trustgraph-ai/trustgraph

trustgraph_base-2.2.8/trustgraph/base_version.py

@@ -0,0 +1 @@
+__version__ = "2.2.8"

{trustgraph_base-2.2.6 → trustgraph_base-2.2.8}/trustgraph/messaging/translators/document_loading.py

@@ -4,6 +4,29 @@ from ...schema import Document, TextDocument, Chunk, DocumentEmbeddings, ChunkEm
 from .base import SendTranslator
 
 
+def _decode_text_payload(payload: str | bytes, charset: str) -> str:
+    """
+    Decode text-load payloads.
+
+    Historical clients send base64-encoded text, but direct REST callers may
+    send raw UTF-8 text. Support both so Unicode text-load requests do not fail
+    at the gateway translation layer.
+    """
+    if isinstance(payload, bytes):
+        if not payload.isascii():
+            return payload.decode(charset)
+        candidate = payload.decode("ascii")
+    else:
+        if not payload.isascii():
+            return payload
+        candidate = payload
+
+    try:
+        return base64.b64decode(candidate, validate=True).decode(charset)
+    except (ValueError, UnicodeDecodeError):
+        return candidate
+
+
 class DocumentTranslator(SendTranslator):
     """Translator for Document schema objects (PDF docs etc.)"""
 
@@ -49,8 +72,7 @@ class TextDocumentTranslator(SendTranslator):
     def to_pulsar(self, data: Dict[str, Any]) -> TextDocument:
         charset = data.get("charset", "utf-8")
 
-        # Text is base64 encoded in input
-        text = base64.b64decode(data["text"]).decode(charset)
+        text = _decode_text_payload(data["text"], charset)
 
         from ...schema import Metadata
         return TextDocument(
@@ -169,4 +191,4 @@ class DocumentEmbeddingsTranslator(SendTranslator):
 
             result["metadata"] = metadata_dict
 
-        return result
+        return result

{trustgraph_base-2.2.6 → trustgraph_base-2.2.8}/trustgraph_base.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: trustgraph-base
-Version: 2.2.6
+Version: 2.2.8
 Summary: TrustGraph provides a means to run a pipeline of flexible AI processing components in a flexible means to achieve a processing pipeline.
 Author-email: "trustgraph.ai" <security@trustgraph.ai>
 Project-URL: Homepage, https://github.com/trustgraph-ai/trustgraph

trustgraph_base-2.2.6/trustgraph/base_version.py

@@ -1 +0,0 @@
-__version__ = "2.2.6"