Add support for using pre-existing text from PDFs

src/paperless/settings.py

@@ -210,6 +210,9 @@ OCR_LANGUAGE = os.getenv("PAPERLESS_OCR_LANGUAGE", "eng")
 # The amount of threads to use for OCR
 OCR_THREADS = os.getenv("PAPERLESS_OCR_THREADS")
 
+# OCR all documents?
+OCR_ALWAYS = bool(os.getenv("PAPERLESS_OCR_ALWAYS", "NO").lower() in ("yes", "y", "1", "t", "true"))
+
 # If this is true, any failed attempts to OCR a PDF will result in the PDF
 # being indexed anyway, with whatever we could get.  If it's False, the file
 # will simply be left in the CONSUMPTION_DIR.

src/paperless_tesseract/parsers.py

@@ -4,6 +4,7 @@ import re
 import subprocess
 from multiprocessing.pool import Pool
 import dateparser
+import pdftotext
 
 import langdetect
 import pyocr
@@ -33,6 +34,7 @@ class RasterisedDocumentParser(DocumentParser):
     UNPAPER = settings.UNPAPER_BINARY
     DATE_ORDER = settings.DATE_ORDER
     DEFAULT_OCR_LANGUAGE = settings.OCR_LANGUAGE
+    OCR_ALWAYS = settings.OCR_ALWAYS
 
     def get_thumbnail(self):
         """
@@ -48,7 +50,21 @@ class RasterisedDocumentParser(DocumentParser):
 
         return os.path.join(self.tempdir, "convert-0000.png")
 
+    def _is_ocred(self):
+        # Extract text from PDF using pdftotext
+        text = get_text_from_pdf(self.document_path)
+
+        # We assume, that a PDF with at least 50 characters contains text
+        # (so no OCR required)
+        if len(text) > 50:
+            return True
+
+        return False
+
     def get_text(self):
+        if not self.OCR_ALWAYS and self._is_ocred():
+            self.log("info", "Skipping OCR, using Text from PDF")
+            return get_text_from_pdf(self.document_path)
 
         images = self._get_greyscale()
 
@@ -237,3 +253,13 @@ def image_to_string(args):
             except (TesseractError, OtherTesseractError):
                 pass
         return ocr.image_to_string(f, lang=lang)
+
+
+def get_text_from_pdf(pdf_file):
+    with open(pdf_file, "rb") as f:
+        try:
+            pdf = pdftotext.PDF(f)
+        except pdftotext.Error:
+            return False
+
+    return "\n".join(pdf)