Implement —user-words, —user-patterns

ocrmypdf/__main__.py

@@ -255,6 +255,15 @@ advanced.add_argument(
          "are applied to all pages, including those for which OCR was "
          "skipped.  Not supported for --output-type=pdf ; that setting "
          "preserves the original compression of all images.")
+advanced.add_argument(
+    '--user-words', metavar='FILE',
+    help="Specify the location of the Tesseract user words file. This is a "
+         "list of words Tesseract should consider while performing OCR in "
+         "addition to its standard language dictionaries. This can improve "
+         "OCR quality especially for specialized and technical documents.")
+advanced.add_argument(
+    '--user-patterns', metavar='FILE',
+    help="Specify the location of the Tesseract user patterns file.")
 
 debugging = parser.add_argument_group(
     "Debugging",

ocrmypdf/exec/tesseract.py

@@ -214,7 +214,8 @@ def _generate_null_hocr(output_hocr, image):
 
 def generate_hocr(input_file, output_hocr, language: list, engine_mode,
                   tessconfig: list,
-                  timeout: float, pagesegmode: int, log):
+                  timeout: float, pagesegmode: int, user_words, user_patterns,
+                  log):
 
     badxml = os.path.splitext(output_hocr)[0] + '.badxml'
 
@@ -223,6 +224,12 @@ def generate_hocr(input_file, output_hocr, language: list, engine_mode,
     if pagesegmode is not None:
         args_tesseract.extend([psm(), str(pagesegmode)])
 
+    if user_words:
+        args_tesseract.extend(['--user-words', user_words])
+
+    if user_patterns:
+        args_tesseract.extend(['--user-patterns', user_patterns])
+
     args_tesseract.extend([
         input_file,
         badxml,
@@ -293,7 +300,8 @@ def use_skip_page(text_only, skip_pdf, output_pdf):
 
 def generate_pdf(input_image, skip_pdf, output_pdf, language: list,
                  engine_mode, text_only: bool,
-                 tessconfig: list, timeout: float, pagesegmode: int, log):
+                 tessconfig: list, timeout: float, pagesegmode: int,
+                 user_words, user_patterns, log):
     '''Use Tesseract to render a PDF.
 
     input_image -- image to analyze
@@ -315,6 +323,12 @@ def generate_pdf(input_image, skip_pdf, output_pdf, language: list,
     if text_only:
         args_tesseract.extend(['-c', 'textonly_pdf=1'])
 
+    if user_words:
+        args_tesseract.extend(['--user-words', user_words])
+
+    if user_patterns:
+        args_tesseract.extend(['--user-patterns', user_patterns])
+
     args_tesseract.extend([
         input_image,
         os.path.splitext(output_pdf)[0],  # Tesseract appends suffix

ocrmypdf/pipeline.py

@@ -495,6 +495,8 @@ def ocr_tesseract_hocr(
         tessconfig=options.tesseract_config,
         timeout=options.tesseract_timeout,
         pagesegmode=options.tesseract_pagesegmode,
+        user_words=options.user_words,
+        user_patterns=options.user_patterns,
         log=log
         )
 
@@ -703,6 +705,8 @@ def ocr_tesseract_and_render_pdf(
         tessconfig=options.tesseract_config,
         timeout=options.tesseract_timeout,
         pagesegmode=options.tesseract_pagesegmode,
+        user_words=options.user_words,
+        user_patterns=options.user_patterns,
         log=log)