More refactoring - helpers.py

ocrmypdf/__init__.py

@@ -1,6 +1,5 @@
 from enum import IntEnum
 import os
-from collections.abc import Iterable
 import pkg_resources
 
 PROGRAM_NAME = 'ocrmypdf'
@@ -31,6 +30,3 @@ def page_number(input_file):
     return int(os.path.basename(input_file)[0:6])
 
 
-def is_iterable_notstr(thing):
-    return isinstance(thing, Iterable) and not isinstance(thing, str)
-

ocrmypdf/__main__.py

@@ -25,17 +25,15 @@ import ruffus.proxy_logger as proxy_logger
 from .pipeline import JobContext, JobContextManager, re_symlink, \
     cleanup_working_files, build_pipeline
 from .pdfa import file_claims_pdfa
+from .helpers import is_iterable_notstr, re_symlink
 from . import tesseract
 from . import qpdf
-from . import ExitCode, is_iterable_notstr, PROGRAM_NAME, VERSION
+from . import ExitCode, PROGRAM_NAME, VERSION
 from collections.abc import Sequence
 
 warnings.simplefilter('ignore', pypdf.utils.PdfReadWarning)
 
 
-BASEDIR = os.path.dirname(os.path.realpath(__file__))
-
-
 # -------------
 # External dependencies
 

ocrmypdf/helpers.py

@@ -0,0 +1,52 @@
+#!/usr/bin/env python3
+# © 2016 James R. Barlow: github.com/jbarlow83
+
+from functools import partial
+from collections.abc import Iterable
+import sys
+import os
+
+
+def re_symlink(input_file, soft_link_name, log=None):
+    """
+    Helper function: relinks soft symbolic link if necessary
+    """
+
+    if log is None:
+        prdebug = partial(print, file=sys.stderr)
+    else:
+        prdebug = log.debug
+
+    # Guard against soft linking to oneself
+    if input_file == soft_link_name:
+        prdebug("Warning: No symbolic link made. You are using " +
+                "the original data directory as the working directory.")
+        return
+
+    # Soft link already exists: delete for relink?
+    if os.path.lexists(soft_link_name):
+        # do not delete or overwrite real (non-soft link) file
+        if not os.path.islink(soft_link_name):
+            raise FileExistsError(
+                "%s exists and is not a link" % soft_link_name)
+        try:
+            os.unlink(soft_link_name)
+        except:
+            prdebug("Can't unlink %s" % (soft_link_name))
+
+    if not os.path.exists(input_file):
+        raise FileNotFoundError(
+            "trying to create a broken symlink to %s" % input_file)
+
+    prdebug("os.symlink(%s, %s)" % (input_file, soft_link_name))
+
+    # Create symbolic link using absolute path
+    os.symlink(
+        os.path.abspath(input_file),
+        soft_link_name
+    )
+
+
+def is_iterable_notstr(thing):
+    return isinstance(thing, Iterable) and not isinstance(thing, str)
+

ocrmypdf/pipeline.py

@@ -24,12 +24,12 @@ 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 . import ghostscript
 from . import tesseract
 from . import qpdf
 from . import leptonica
-from . import ExitCode, page_number, is_iterable_notstr, PROGRAM_NAME, \
-    VERSION
+from . import ExitCode, page_number, PROGRAM_NAME, VERSION
 
 
 VECTOR_PAGE_DPI = 400
@@ -78,43 +78,6 @@ class JobContextManager(BaseManager):
     pass
 
 
-
-def re_symlink(input_file, soft_link_name, log):
-    """
-    Helper function: relinks soft symbolic link if necessary
-    """
-
-    # Guard against soft linking to oneself
-    if input_file == soft_link_name:
-        log.debug("Warning: No symbolic link made. You are using " +
-                  "the original data directory as the working directory.")
-        return
-
-    # Soft link already exists: delete for relink?
-    if os.path.lexists(soft_link_name):
-        # do not delete or overwrite real (non-soft link) file
-        if not os.path.islink(soft_link_name):
-            raise FileExistsError(
-                "%s exists and is not a link" % soft_link_name)
-        try:
-            os.unlink(soft_link_name)
-        except:
-            log.debug("Can't unlink %s" % (soft_link_name))
-
-    if not os.path.exists(input_file):
-        raise FileNotFoundError(
-            "trying to create a broken symlink to %s" % input_file)
-
-    log.debug("os.symlink(%s, %s)" % (input_file, soft_link_name))
-
-    # Create symbolic link using absolute path
-    os.symlink(
-        os.path.abspath(input_file),
-        soft_link_name
-    )
-
-
-
 def cleanup_working_files(work_folder, options):
     if options.keep_temporary_files:
         print("Temporary working files saved at:\n{0}".format(work_folder),
@@ -869,7 +832,7 @@ def build_pipeline(options, work_folder, log, context):
         output_dir=work_folder,
         extras=[log, context])
 
-    # Split
+    # Split (kwargs for split seems to be broken, so pass plain args)
     task_split_pages = main_pipeline.split(
         split_pages,
         task_repair_pdf,