Drop remnants of support for Tesseract without has_textonly_pdf

Also improve Tesseract version checking so it can compare all of their
weird conventions.

src/ocrmypdf/_exec/tesseract.py

@@ -9,8 +9,10 @@
 
 import logging
 import os
+import re
 import shutil
 from collections import namedtuple
+from distutils.version import StrictVersion
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired
@@ -53,31 +55,29 @@ class TesseractLoggerAdapter(logging.LoggerAdapter):
         return '[tesseract] %s' % (msg), kwargs
 
 
+class TesseractVersion(StrictVersion):
+    version_re = re.compile(
+        r'''
+        ^(\d+) \. (\d+) (\. (\d+))?  # groups: 1/major, 2/minor, 3/[skip], 4/patch
+        [-]?  # optional hyphen separator
+        (?:(alpha|beta|rc|dev)[.\-\ ]?(\d+)?)?  # 5/prerelease, 6/prerelease_num
+        $
+        ''',
+        re.VERBOSE | re.ASCII,
+    )
+
+    def parse(self, vstring):
+        try:
+            super().parse(vstring)
+        except TypeError as e:
+            if 'int() argument must be a string' in str(e):
+                super().parse(vstring + '0')
+
+
 def version():
     return get_version('tesseract', regex=r'tesseract\s(.+)')
 
 
-def has_textonly_pdf(langs=None):
-    """Does Tesseract have textonly_pdf capability?
-
-    Available in v4.00.00alpha since January 2017. Best to
-    parse the parameter list.
-    """
-    args_tess = tess_base_args(langs, engine_mode=None) + ['--print-parameters', 'pdf']
-    params = ''
-    try:
-        proc = run(args_tess, check=True, stdout=PIPE, stderr=STDOUT)
-        params = proc.stdout
-    except CalledProcessError as e:
-        raise MissingDependencyError(
-            "Could not --print-parameters from tesseract. This can happen if the "
-            "TESSDATA_PREFIX environment is not set to a valid tessdata folder. "
-        ) from e
-    if b'textonly_pdf' in params:
-        return True
-    return False
-
-
 def has_user_words():
     """Does Tesseract have --user-words capability?
 

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -81,19 +81,13 @@ def check_options(options):
         package={'linux': 'tesseract-ocr'},
         version_checker=tesseract.version,
         need_version='4.0.0',  # using backport for Travis CI
+        version_parser=tesseract.TesseractVersion,
     )
 
     # Decide on what renderer to use
     if options.pdf_renderer == 'auto':
         options.pdf_renderer = 'sandwich'
 
-    if options.pdf_renderer == 'sandwich' and not tesseract.has_textonly_pdf(
-        set(options.languages)
-    ):
-        raise MissingDependencyError(
-            "You are using an alpha version of Tesseract 4.0 that does not support "
-            "the textonly_pdf parameter. We don't support versions this old."
-        )
     if not tesseract.has_user_words() and (options.user_words or options.user_patterns):
         log.warning(
             "Tesseract 4.0 ignores --user-words and --user-patterns, so these "

src/ocrmypdf/subprocess/__init__.py

@@ -13,14 +13,17 @@ import re
 import sys
 from collections.abc import Mapping
 from contextlib import suppress
-from distutils.version import LooseVersion
+from distutils.version import LooseVersion, Version
 from functools import lru_cache
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, CompletedProcess, Popen
 from subprocess import run as subprocess_run
+from typing import Callable, Optional, Type, Union
 
 from ocrmypdf.exceptions import MissingDependencyError
 
+# pylint: disable=logging-format-interpolation
+
 log = logging.getLogger(__name__)
 
 
@@ -264,13 +267,30 @@ def _error_old_version(program, package, need_version, found_version, required_f
 
 def check_external_program(
     *,
-    program,
-    package,
-    version_checker,
-    need_version,
-    required_for=None,
+    program: str,
+    package: str,
+    version_checker: Union[str, Callable],
+    need_version: str,
+    required_for: Optional[str] = None,
     recommended=False,
+    version_parser: Type[Version] = LooseVersion,
 ):
+    """Check for required version of external program and raise exception if not.
+
+    Args:
+        program: The name of the program to test.
+        package: The name of a software package that typically supplies this program.
+            Usually the same as program.
+        version_check: A callable without arguments that retrieves the installed
+            version of program.
+        need_version: The minimum required version.
+        required_for: The name of an argument of feature that requires this program.
+        recommended: If this external program is recommended, instead of raising
+            an exception, log a warning and allow execution to continue.
+        version_parser: A class that should be used to parse and compare version
+            numbers. Used when version numbers do not follow standard conventions.
+    """
+
     try:
         if callable(version_checker):
             found_version = version_checker()
@@ -279,7 +299,7 @@ def check_external_program(
     except (CalledProcessError, FileNotFoundError, MissingDependencyError):
         _error_missing_program(program, package, required_for, recommended)
         if not recommended:
-            raise MissingDependencyError()
+            raise MissingDependencyError(program)
         return
 
     def remove_leading_v(s):
@@ -290,9 +310,9 @@ def check_external_program(
     found_version = remove_leading_v(found_version)
     need_version = remove_leading_v(need_version)
 
-    if found_version and LooseVersion(found_version) < LooseVersion(need_version):
+    if found_version and version_parser(found_version) < version_parser(need_version):
         _error_old_version(program, package, need_version, found_version, required_for)
         if not recommended:
-            raise MissingDependencyError()
+            raise MissingDependencyError(program)
 
     log.debug('Found %s %s', program, found_version)

tests/test_validation.py

@@ -13,6 +13,7 @@ import pytest
 
 from ocrmypdf import _validation as vd
 from ocrmypdf._concurrent import NullProgressBar, SerialExecutor
+from ocrmypdf._exec.tesseract import TesseractVersion
 from ocrmypdf._plugin_manager import get_plugin_manager
 from ocrmypdf.api import create_options
 from ocrmypdf.cli import get_parser
@@ -52,29 +53,23 @@ def test_hocr_notlatin_warning(caplog):
 
 
 def test_old_ghostscript(caplog):
-    with patch('ocrmypdf._exec.ghostscript.version', return_value='9.19'), patch(
-        'ocrmypdf._exec.tesseract.has_textonly_pdf', return_value=True
-    ):
+    with patch('ocrmypdf._exec.ghostscript.version', return_value='9.19'):
         vd._check_options(
             *make_opts_pm(language='chi_sim', output_type='pdfa'), {'chi_sim'}
         )
         assert 'does not work correctly' in caplog.text
 
-    with patch('ocrmypdf._exec.ghostscript.version', return_value='9.18'), patch(
-        'ocrmypdf._exec.tesseract.has_textonly_pdf', return_value=True
-    ):
+    with patch('ocrmypdf._exec.ghostscript.version', return_value='9.18'):
         with pytest.raises(MissingDependencyError):
             vd._check_options(*make_opts_pm(output_type='pdfa-3'), set())
 
-    with patch('ocrmypdf._exec.ghostscript.version', return_value='9.24'), patch(
-        'ocrmypdf._exec.tesseract.has_textonly_pdf', return_value=True
-    ):
+    with patch('ocrmypdf._exec.ghostscript.version', return_value='9.24'):
         with pytest.raises(MissingDependencyError):
             vd._check_options(*make_opts_pm(), set())
 
 
 def test_old_tesseract_error():
-    with patch('ocrmypdf._exec.tesseract.has_textonly_pdf', return_value=False):
+    with patch('ocrmypdf._exec.tesseract.version', return_value='4.00.00alpha'):
         with pytest.raises(MissingDependencyError):
             opts = make_opts(pdf_renderer='sandwich', language='eng')
             plugin_manager = get_plugin_manager(opts.plugins)
@@ -227,17 +222,20 @@ def test_version_comparison():
         version_checker=lambda: '10.0',
         need_version='8.0.2',
     )
-    vd.check_external_program(
-        program="tesseract",
-        package="tesseract",
-        version_checker=lambda: '4.0.0-beta.1',
-        need_version='4.0.0',
-    )
+    with pytest.raises(MissingDependencyError):
+        vd.check_external_program(
+            program="tesseract",
+            package="tesseract",
+            version_checker=lambda: '4.0.0-beta.1',
+            need_version='4.0.0',
+            version_parser=TesseractVersion,
+        )
     vd.check_external_program(
         program="tesseract",
         package="tesseract",
         version_checker=lambda: 'v5.0.0-alpha.20200201',
         need_version='4.0.0',
+        version_parser=TesseractVersion,
     )
     with pytest.raises(MissingDependencyError):
         vd.check_external_program(
@@ -277,11 +275,9 @@ def test_pagesegmode_warning(caplog):
 
 
 def test_two_languages():
-    with patch('ocrmypdf._exec.tesseract.has_textonly_pdf', return_value=True) as mock:
-        vd._check_options(
-            *make_opts_pm(language='fakelang1+fakelang2'), {'fakelang1', 'fakelang2'}
-        )
-        mock.assert_called()
+    vd._check_options(
+        *make_opts_pm(language='fakelang1+fakelang2'), {'fakelang1', 'fakelang2'}
+    )
 
 
 def test_sidecar_equals_output(resources, no_outpdf):