Forward --oem argument to tesseract 4

ocrmypdf/__main__.py

@@ -212,6 +212,15 @@ advanced.add_argument(
     '--tesseract-pagesegmode', action='store', type=int, metavar='PSM',
     choices=range(0, 14),
     help="set Tesseract page segmentation mode (see tesseract --help)")
+advanced.add_argument(
+    '--tesseract-oem', action='store', type=int, metavar='MODE',
+    choices=range(0, 4),
+    help=("set Tesseract 4.0 OCR engine mode: "
+         "0 - original Tesseract only; "
+         "1 - neural nets LSTM only; "
+         "2 - Tesseract + LSTM; "
+         "3 - default.")
+    )
 advanced.add_argument(
     '--pdf-renderer', choices=['auto', 'tesseract', 'hocr'], default='auto',
     help="choose OCR PDF renderer - the default option is to let OCRmyPDF "
@@ -316,12 +325,22 @@ def check_options_ocr_behavior(options, log):
             "    ocrmypdf --pdf-renderer tesseract --output-type pdf")
 
 
+def check_options_advanced(options, log):
+    if tesseract.v4():
+        log.info(
+            "Tesseract v4.x.alpha found. OCRmyPDF support is experimental.")
+    if options.tesseract_oem and not tesseract.v4():
+        log.warning(
+            "--tesseract-oem requires Tesseract 4.x -- argument ignored")
+
+
 def check_options(options, log):
     try:
         check_options_languages(options, log)
         check_options_output(options, log)
         check_options_preprocessing(options, log)
         check_options_ocr_behavior(options, log)
+        check_options_advanced(options, log)
     except argparse.ArgumentError as e:
         log.error(e)
         sys.exit(ExitCode.bad_args)
@@ -462,6 +481,7 @@ def run_pipeline():
     _log, _log_mutex = proxy_logger.make_shared_logger_and_proxy(
         logging_factory, __name__, [None, options.verbose])
     _log.debug('ocrmypdf ' + VERSION)
+    _log.debug('tesseract ' + tesseract.version())
 
     check_options(options, _log)
 

ocrmypdf/exec/tesseract.py

@@ -93,10 +93,20 @@ def languages():
     return set(lang.strip() for lang in langs.splitlines()[1:])
 
 
-def get_orientation(input_file, language: list, timeout: float, log):
-    args_tesseract = [
+def tess_base_args(languages, engine_mode):
+    args = [
         get_program('tesseract'),
-        '-l', '+'.join(language),
+    ]
+    if languages:
+        args.extend(['-l', '+'.join(languages)])
+    if engine_mode is not None and v4():
+        args.extend(['--oem', str(engine_mode)])
+    return args
+
+
+def get_orientation(input_file, language: list, engine_mode, timeout: float,
+                    log):
+    args_tesseract = tess_base_args(language, engine_mode) + [
         psm(), '0',
         input_file,
         'stdout'
@@ -175,15 +185,13 @@ def _generate_null_hocr(output_hocr, image):
         f.write(HOCR_TEMPLATE.format(w, h))
 
 
-def generate_hocr(input_file, output_hocr, language: list, tessconfig: list,
-                  timeout: float, pageinfo_getter, pagesegmode: int, log):
+def generate_hocr(input_file, output_hocr, language: list, engine_mode,
+                  tessconfig: list,
+                  timeout: float, pagesegmode: int, log):
 
     badxml = os.path.splitext(output_hocr)[0] + '.badxml'
 
-    args_tesseract = [
-        get_program('tesseract'),
-        '-l', '+'.join(language)
-    ]
+    args_tesseract = tess_base_args(language, engine_mode)
 
     if pagesegmode is not None:
         args_tesseract.extend([psm(), str(pagesegmode)])
@@ -194,6 +202,7 @@ def generate_hocr(input_file, output_hocr, language: list, tessconfig: list,
         'hocr'
     ] + tessconfig)
     try:
+        log.debug(args_tesseract)
         stdout = check_output(
             args_tesseract, close_fds=True, stderr=STDOUT,
             universal_newlines=True, timeout=timeout)
@@ -235,6 +244,7 @@ def generate_hocr(input_file, output_hocr, language: list, tessconfig: list,
 
 
 def generate_pdf(input_image, skip_pdf, output_pdf, language: list,
+                 engine_mode,
                  tessconfig: list, timeout: float, pagesegmode: int, log):
     '''Use Tesseract to render a PDF.
 
@@ -246,10 +256,7 @@ def generate_pdf(input_image, skip_pdf, output_pdf, language: list,
     log -- logger object
     '''
 
-    args_tesseract = [
-        get_program('tesseract'),
-        '-l', '+'.join(language)
-    ]
+    args_tesseract = tess_base_args(language, engine_mode)
 
     if pagesegmode is not None:
         args_tesseract.extend([psm(), str(pagesegmode)])
@@ -261,6 +268,7 @@ def generate_pdf(input_image, skip_pdf, output_pdf, language: list,
     ] + tessconfig)
 
     try:
+        log.debug(args_tesseract)
         stdout = check_output(
             args_tesseract, close_fds=True, stderr=STDOUT,
             universal_newlines=True, timeout=timeout)

ocrmypdf/pipeline.py

@@ -332,6 +332,7 @@ def orient_page(
     orient_conf = tesseract.get_orientation(
         preview,
         language=options.language,
+        engine_mode=options.tesseract_oem,
         timeout=options.tesseract_timeout,
         log=log)
 
@@ -476,9 +477,9 @@ def ocr_tesseract_hocr(
         input_file=input_file,
         output_hocr=output_file,
         language=options.language,
+        engine_mode=options.tesseract_oem,
         tessconfig=options.tesseract_config,
         timeout=options.tesseract_timeout,
-        pageinfo_getter=partial(get_pageinfo, input_file, context),
         pagesegmode=options.tesseract_pagesegmode,
         log=log
         )
@@ -669,6 +670,7 @@ def tesseract_ocr_and_render_pdf(
         skip_pdf=input_pdf,
         output_pdf=output_file,
         language=options.language,
+        engine_mode=options.tesseract_oem,
         tessconfig=options.tesseract_config,
         timeout=options.tesseract_timeout,
         pagesegmode=options.tesseract_pagesegmode,