Finalize ‘exec’ migration and make it backward compatibility for now

ocrmypdf/__init__.py

@@ -1,4 +1,3 @@
-import os
 import pkg_resources
 
 PROGRAM_NAME = 'ocrmypdf'
@@ -6,5 +5,11 @@ PROGRAM_NAME = 'ocrmypdf'
 VERSION = pkg_resources.get_distribution('ocrmypdf').version
 
 
-def page_number(input_file):
-    return int(os.path.basename(input_file)[0:6])
+# These imports are for v4.x backward compatibility for consumers of ocrmypdf
+# (if any). They are deprecated and will be removed in v5.x.
+from .exec import ghostscript, qpdf, tesseract, unpaper, get_program
+from .exceptions import ExitCode
+from .helpers import page_number, is_iterable_notstr
+
+
+

ocrmypdf/exec/tesseract.py

@@ -7,7 +7,7 @@ import re
 import shutil
 from functools import lru_cache
 from ..exceptions import MissingDependencyError
-from .. import page_number
+from ..helpers import page_number
 from . import get_program
 from collections import namedtuple
 from textwrap import dedent

ocrmypdf/helpers.py

@@ -49,3 +49,7 @@ def re_symlink(input_file, soft_link_name, log=None):
 
 def is_iterable_notstr(thing):
     return isinstance(thing, Iterable) and not isinstance(thing, str)
+
+
+def page_number(input_file):
+    return int(os.path.basename(input_file)[0:6])

ocrmypdf/pipeline.py

@@ -24,11 +24,11 @@ from ruffus import formatter, regex, Pipeline, suffix
 from .hocrtransform import HocrTransform
 from .pageinfo import pdf_get_all_pageinfo
 from .pdfa import generate_pdfa_def, file_claims_pdfa
-from .helpers import re_symlink, is_iterable_notstr
+from .helpers import re_symlink, is_iterable_notstr, page_number
 from .exec import ghostscript, tesseract, qpdf
 from .exceptions import *
 from . import leptonica
-from . import page_number, PROGRAM_NAME, VERSION
+from . import PROGRAM_NAME, VERSION
 
 
 VECTOR_PAGE_DPI = 400