supply file_name for tika parser

src/documents/consumer.py

@@ -1,6 +1,5 @@
 import datetime
 import hashlib
-import logging
 import os
 
 import magic
@@ -130,7 +129,7 @@ class Consumer(LoggingMixin):
 
         try:
             self.log("debug", "Parsing {}...".format(self.filename))
-            document_parser.parse(self.path, mime_type)
+            document_parser.parse(self.path, mime_type, self.filename)
 
             self.log("debug", f"Generating thumbnail for {self.filename}...")
             thumbnail = document_parser.get_optimised_thumbnail(

src/documents/parsers.py

@@ -267,7 +267,7 @@ class DocumentParser(LoggingMixin):
     def extract_metadata(self, document_path, mime_type):
         return []
 
-    def parse(self, document_path, mime_type):
+    def parse(self, document_path, mime_type, file_name=None):
         raise NotImplementedError()
 
     def get_archive_path(self):

src/documents/tests/test_consumer.py

@@ -177,7 +177,7 @@ class DummyParser(DocumentParser):
     def get_optimised_thumbnail(self, document_path, mime_type):
         return self.fake_thumb
 
-    def parse(self, document_path, mime_type):
+    def parse(self, document_path, mime_type, file_name=None):
         self.text = "The Text"
 
 
@@ -194,7 +194,7 @@ class FaultyParser(DocumentParser):
     def get_optimised_thumbnail(self, document_path, mime_type):
         return self.fake_thumb
 
-    def parse(self, document_path, mime_type):
+    def parse(self, document_path, mime_type, file_name=None):
         raise ParseError("Does not compute.")
 
 

src/paperless_tesseract/parsers.py

@@ -88,7 +88,7 @@ class RasterisedDocumentParser(DocumentParser):
                 f"Error while calculating DPI for image {image}: {e}")
             return None
 
-    def parse(self, document_path, mime_type):
+    def parse(self, document_path, mime_type, file_name=None):
         mode = settings.OCR_MODE
 
         text_original = get_text_from_pdf(document_path)

src/paperless_text/parsers.py

@@ -32,6 +32,6 @@ class TextDocumentParser(DocumentParser):
 
         return out_path
 
-    def parse(self, document_path, mime_type):
+    def parse(self, document_path, mime_type, file_name=None):
         with open(document_path, 'r') as f:
             self.text = f.read()

src/paperless_tika/parsers.py

@@ -39,7 +39,7 @@ class TikaDocumentParser(DocumentParser):
             } for key in parsed['metadata']
         ]
 
-    def parse(self, document_path, mime_type):
+    def parse(self, document_path, mime_type, file_name=None):
         self.log("info", f"Sending {document_path} to Tika server")
         tika_server = settings.PAPERLESS_TIKA_ENDPOINT
 
@@ -60,15 +60,15 @@ class TikaDocumentParser(DocumentParser):
             self.log("warning", f"Unable to extract date for document "
                                 f"{document_path}: {e}")
 
-        self.archive_path = self.convert_to_pdf(document_path)
+        self.archive_path = self.convert_to_pdf(document_path, file_name)
 
-    def convert_to_pdf(self, document_path):
+    def convert_to_pdf(self, document_path, file_name):
         pdf_path = os.path.join(self.tempdir, "convert.pdf")
         gotenberg_server = settings.PAPERLESS_TIKA_GOTENBERG_ENDPOINT
         url = gotenberg_server + "/convert/office"
 
         self.log("info", f"Converting {document_path} to PDF as {pdf_path}")
-        files = {"files": open(document_path, "rb")}
+        files = {"files": (file_name, open(document_path, "rb"))}
         headers = {}
 
         try: