From fda2bfbea7ce44a66fe2ee45381ce8b59accde9d Mon Sep 17 00:00:00 2001
From: jonaswinkler <17569239+jonaswinkler@users.noreply.github.com>
Date: Mon, 22 Mar 2021 23:00:15 +0100
Subject: [PATCH] better exception logging

---
 src/documents/consumer.py          | 16 ++++++++++------
 src/paperless_tesseract/parsers.py |  6 +++---
 2 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/src/documents/consumer.py b/src/documents/consumer.py
index 3fd62fabc..3d7d98198 100755
--- a/src/documents/consumer.py
+++ b/src/documents/consumer.py
@@ -64,9 +64,9 @@ class Consumer(LoggingMixin):
                                                      {'type': 'status_update',
                                                       'data': payload})
 
-    def _fail(self, message, log_message=None):
+    def _fail(self, message, log_message=None, exc_info=None):
         self._send_progress(100, 100, 'FAILED', message)
-        self.log("error", log_message or message)
+        self.log("error", log_message or message, exc_info=exc_info)
         raise ConsumerError(f"{self.filename}: {log_message or message}")
 
     def __init__(self):
@@ -120,7 +120,8 @@ class Consumer(LoggingMixin):
         except Exception as e:
             self._fail(
                 MESSAGE_PRE_CONSUME_SCRIPT_ERROR,
-                f"Error while executing pre-consume script: {e}"
+                f"Error while executing pre-consume script: {e}",
+                exc_info=True
             )
 
     def run_post_consume_script(self, document):
@@ -150,7 +151,8 @@ class Consumer(LoggingMixin):
         except Exception as e:
             self._fail(
                 MESSAGE_POST_CONSUME_SCRIPT_ERROR,
-                f"Error while executing post-consume script: {e}"
+                f"Error while executing post-consume script: {e}",
+                exc_info=True
             )
 
     def try_consume_file(self,
@@ -255,7 +257,8 @@ class Consumer(LoggingMixin):
             document_parser.cleanup()
             self._fail(
                 str(e),
-                f"Error while consuming document {self.filename}: {e}"
+                f"Error while consuming document {self.filename}: {e}",
+                exc_info=True
             )
 
         # Prepare the document classifier.
@@ -326,7 +329,8 @@ class Consumer(LoggingMixin):
             self._fail(
                 str(e),
                 f"The following error occured while consuming "
-                f"{self.filename}: {e}"
+                f"{self.filename}: {e}",
+                exc_info=True
             )
         finally:
             document_parser.cleanup()
diff --git a/src/paperless_tesseract/parsers.py b/src/paperless_tesseract/parsers.py
index 944bda601..d381ed94f 100644
--- a/src/paperless_tesseract/parsers.py
+++ b/src/paperless_tesseract/parsers.py
@@ -246,9 +246,9 @@ class RasterisedDocumentParser(DocumentParser):
             if original_has_text:
                 self.text = text_original
         except (NoTextFoundException, InputFileError) as e:
-            self.log("exception",
-                     f"Encountered the following error while running OCR, "
-                     f"attempting force OCR to get the text.")
+            self.log("warning",
+                     f"Encountered an error while running OCR: {str(e)}. "
+                     f"Attempting force OCR to get the text.")
 
             archive_path_fallback = os.path.join(
                 self.tempdir, "archive-fallback.pdf")