Rename ‘tesstop’ to ‘tess4’

There’s no reason text-only PDF shouldn’t become the default for
tesseract 4.

ocrmypdf/__main__.py

@@ -222,14 +222,15 @@ advanced.add_argument(
          "3 - default.")
     )
 advanced.add_argument(
-    '--pdf-renderer', choices=['auto', 'tesseract', 'hocr', 'tesstop'], default='auto',
+    '--pdf-renderer', choices=['auto', 'tesseract', 'hocr', 'tess4'], default='auto',
     help="choose OCR PDF renderer - the default option is to let OCRmyPDF "
          "choose.  The 'tesseract' PDF renderer is more accurate and does a "
          "better job and document structure such as recognizing columns. It "
          "also does a better job on non-Latin languages. However, it does "
          "not work as well when older versions of Tesseract or Ghostscript "
          "are installed, and some combinations of arguments to do not work "
-         "with --pdf-renderer tesseract.")
+         "with --pdf-renderer tesseract.  The 'tess4' PDF renderer is similar "
+         "to 'tesseract', requires tesseract 4, and gives superior results.")
 advanced.add_argument(
     '--tesseract-timeout', default=180.0, type=float, metavar='SECONDS',
     help='give up on OCR after the timeout, but copy the preprocessed page '

ocrmypdf/pipeline.py

@@ -970,7 +970,7 @@ def build_pipeline(options, work_folder, log, context):
     task_select_image_layer.graphviz(
         fillcolor='"#00cc66"', shape='diamond')
     task_select_image_layer.active_if(
-        options.pdf_renderer == 'hocr' or options.pdf_renderer == 'tesstop')
+        options.pdf_renderer == 'hocr' or options.pdf_renderer == 'tess4')
 
     task_render_hocr_page = main_pipeline.transform(
         task_func=render_hocr_page,
@@ -999,7 +999,7 @@ def build_pipeline(options, work_folder, log, context):
         output=os.path.join(work_folder, r'\1.text.pdf'),
         extras=[log, context])
     task_ocr_tesseract_textonly_pdf.graphviz(fillcolor='"#ff69b4"')
-    task_ocr_tesseract_textonly_pdf.active_if(options.pdf_renderer == 'tesstop')
+    task_ocr_tesseract_textonly_pdf.active_if(options.pdf_renderer == 'tess4')
     if tesseract.v4():
         task_ocr_tesseract_textonly_pdf.jobs_limit(1)
 
@@ -1012,7 +1012,7 @@ def build_pipeline(options, work_folder, log, context):
         output=os.path.join(work_folder, r'\1.rendered.pdf'),
         extras=[log, context])
     task_combine_layers.graphviz(fillcolor='"#00cc66"')
-    task_combine_layers.active_if(options.pdf_renderer == 'hocr' or options.pdf_renderer == 'tesstop')
+    task_combine_layers.active_if(options.pdf_renderer == 'hocr' or options.pdf_renderer == 'tess4')
 
     # Tesseract OCR+PDF
     task_ocr_tesseract_and_render_pdf = main_pipeline.collate(

tests/test_tess4.py

@@ -0,0 +1,88 @@
+#!/usr/bin/env python3
+# © 2017 James R. Barlow: github.com/jbarlow83
+
+from __future__ import print_function
+from subprocess import Popen, PIPE, check_output, check_call, DEVNULL
+import os
+import shutil
+from contextlib import suppress
+import sys
+import pytest
+from ocrmypdf.pageinfo import pdf_get_all_pageinfo
+import PyPDF2 as pypdf
+from ocrmypdf.exceptions import ExitCode
+from ocrmypdf import leptonica
+from ocrmypdf.pdfa import file_claims_pdfa
+from ocrmypdf.exec import tesseract
+import platform
+
+
+if sys.version_info.major < 3:
+    print("Requires Python 3.4+")
+    sys.exit(1)
+
+TESTS_ROOT = os.path.abspath(os.path.dirname(__file__))
+SPOOF_PATH = os.path.join(TESTS_ROOT, 'spoof')
+PROJECT_ROOT = os.path.dirname(TESTS_ROOT)
+TEST_RESOURCES = os.path.join(PROJECT_ROOT, 'tests', 'resources')
+OCRMYPDF = [sys.executable, '-m', 'ocrmypdf']
+
+
+# Skip all tests in this file if not tesseract 4
+pytestmark = pytest.mark.skipif(not tesseract.v4(),
+                                reason="tesseract 4.0 required")
+
+
+def running_in_docker():
+    # Docker creates a file named /.dockerinit
+    return os.path.exists('/.dockerinit')
+
+
+def is_linux():
+    return platform.system() == 'Linux'
+
+
+def _infile(input_basename):
+    return os.path.join(TEST_RESOURCES, input_basename)
+
+
+def check_ocrmypdf(input_basename, output, *args, env=None):
+    "Run ocrmypdf and confirmed that a valid file was created"
+    input_file = _infile(input_basename)
+
+    p, out, err = run_ocrmypdf(input_basename, output, *args, env=env)
+    print(err)  # ensure py.test collects the output, use -s to view
+    assert p.returncode == 0
+    assert os.path.exists(output), "Output file not created"
+    assert os.stat(output).st_size > 100, "PDF too small or empty"
+    assert out == "", \
+        "The following was written to stdout and should not have been: \n" + \
+        "<stdout>\n" + out + "\n</stdout>"
+    return output
+
+
+def run_ocrmypdf(input_basename, output, *args, env=None):
+    "Run ocrmypdf and let caller deal with results"
+    input_file = _infile(input_basename)
+
+    if env is None:
+        env = os.environ
+
+    p_args = OCRMYPDF + list(args) + [input_file, output]
+    p = Popen(
+        p_args, close_fds=True, stdout=PIPE, stderr=PIPE,
+        universal_newlines=True, env=env)
+    out, err = p.communicate()
+    print(err)
+
+    return p, out, err
+
+
+@pytest.mark.skipif(not tesseract.has_textonly_pdf(),
+                    reason="requires textonly_pdf parameter")
+def test_textonly_pdf(self, tmpdir):
+    output = str(tmpdir.join("linn_textonly.pdf"))
+    check_ocrmypdf('linn.pdf', output, '--pdf-renderer', 'tess4')
+
+
+