code cleanup

src/paperless_tesseract/parsers.py

@@ -50,7 +50,10 @@ class RasterisedDocumentParser(DocumentParser):
         except ParseError:
             # if convert fails, fall back to extracting
             # the first PDF page as a PNG using Ghostscript
-            self.log('warning', 'Thumbnail generation with ImageMagick failed, falling back to ghostscript. Check your /etc/ImageMagick-x/policy.xml!')
+            self.log(
+                'warning',
+                "Thumbnail generation with ImageMagick failed, falling back "
+                "to ghostscript. Check your /etc/ImageMagick-x/policy.xml!")
             gs_out_path = os.path.join(self.tempdir, "gs_out.png")
             cmd = [settings.GS_BINARY,
                    "-q",
@@ -98,24 +101,38 @@ class RasterisedDocumentParser(DocumentParser):
         try:
 
             sample_page_index = int(len(images) / 2)
-            self.log("debug", "Attempting language detection on page {} of {}...".format(sample_page_index + 1, len(images)))
-            sample_page_text = self._ocr([images[sample_page_index]], settings.OCR_LANGUAGE)[0]
+            self.log(
+                "debug",
+                f"Attempting language detection on page "
+                f"{sample_page_index + 1} of {len(images)}...")
+
+            sample_page_text = self._ocr([images[sample_page_index]],
+                                         settings.OCR_LANGUAGE)[0]
             guessed_language = self._guess_language(sample_page_text)
 
             if not guessed_language or guessed_language not in ISO639:
                 self.log("warning", "Language detection failed.")
-                ocr_pages = self._complete_ocr_default_language(images, sample_page_index, sample_page_text)
+                ocr_pages = self._complete_ocr_default_language(
+                    images, sample_page_index, sample_page_text)
 
             elif ISO639[guessed_language] == settings.OCR_LANGUAGE:
-                self.log("debug", "Detected language: {} (default language)".format(guessed_language))
-                ocr_pages = self._complete_ocr_default_language(images, sample_page_index, sample_page_text)
+                self.log(
+                    "debug",
+                    f"Detected language: {guessed_language} "
+                    f"(default language)")
+                ocr_pages = self._complete_ocr_default_language(
+                    images, sample_page_index, sample_page_text)
 
             elif not ISO639[guessed_language] in pyocr.get_available_tools()[0].get_available_languages():
-                self.log("warning", "Detected language {} is not available on this system.".format(guessed_language))
-                ocr_pages = self._complete_ocr_default_language(images, sample_page_index, sample_page_text)
+                self.log(
+                    "warning",
+                    f"Detected language {guessed_language} is not available "
+                    f"on this system.")
+                ocr_pages = self._complete_ocr_default_language(
+                    images, sample_page_index, sample_page_text)
 
             else:
-                self.log("debug", "Detected language: {}".format(guessed_language))
+                self.log("debug", f"Detected language: {guessed_language}")
                 ocr_pages = self._ocr(images, ISO639[guessed_language])
 
             self.log("debug", "OCR completed.")
@@ -130,7 +147,9 @@ class RasterisedDocumentParser(DocumentParser):
         Greyscale images are easier for Tesseract to OCR
         """
 
-        self.log("debug", "Converting document {} into greyscale images...".format(self.document_path))
+        self.log(
+            "debug",
+            f"Converting document {self.document_path} into greyscale images")
 
         # Convert PDF to multiple PNMs
         pnm = os.path.join(self.tempdir, "convert-%04d.pnm")
@@ -148,7 +167,7 @@ class RasterisedDocumentParser(DocumentParser):
             if f.endswith(".pnm"):
                 pnms.append(os.path.join(self.tempdir, f))
 
-        self.log("debug", "Running unpaper on {} pages...".format(len(pnms)))
+        self.log("debug", f"Running unpaper on {len(pnms)} pages...")
 
         # Run unpaper in parallel on converted images
         with ThreadPool(processes=settings.THREADS_PER_WORKER) as pool:
@@ -161,26 +180,25 @@ class RasterisedDocumentParser(DocumentParser):
             guess = langdetect.detect(text)
             return guess
         except Exception as e:
-            self.log('warning', "Language detection failed with: {}".format(e))
+            self.log('warning', f"Language detection failed with: {e}")
             return None
 
     def _ocr(self, imgs, lang):
-        self.log("debug", "Performing OCR on {} page(s) with language {}".format(len(imgs), lang))
+        self.log(
+            "debug",
+            f"Performing OCR on {len(imgs)} page(s) with language {lang}")
         with ThreadPool(processes=settings.THREADS_PER_WORKER) as pool:
             r = pool.map(image_to_string, itertools.product(imgs, [lang]))
             return r
 
-    def _complete_ocr_default_language(self, images, sample_page_index, sample_page):
-        """
-        Given a `middle` value and the text that middle page represents, we OCR
-        the remainder of the document and return the whole thing.
-        """
-        # text = self._ocr(imgs[:middle], settings.OCR_LANGUAGE) + text
-        # text += self._ocr(imgs[middle + 1:], settings.OCR_LANGUAGE)
+    def _complete_ocr_default_language(self,
+                                       images,
+                                       sample_page_index,
+                                       sample_page):
         images_copy = list(images)
         del images_copy[sample_page_index]
         if images_copy:
-            self.log('debug', 'Continuing ocr with default language.')
+            self.log('debug', "Continuing ocr with default language.")
             ocr_pages = self._ocr(images_copy, settings.OCR_LANGUAGE)
             ocr_pages.insert(sample_page_index, sample_page)
             return ocr_pages