Environment variables can now override default programs

RELEASE_NOTES.rst

@@ -6,6 +6,18 @@ Please always read this file before installing the package
 Download software here: https://github.com/jbarlow83/OCRmyPDF/tags
 
 
+Latest:
+=====
+
+Changes
+-------
+
+-  Fixed bug where successful repair of PDF files errors led to abort (thanks to @shemgp)
+-  You can now override the location of external programs OCRmyPDF uses by setting
+   environmental variables of the form OCRMYPDF_PROGRAMNAME, e.g. OCRMYPDF_TESSERACT will
+   override system Tesseract.
+
+
 v3.1:
 =====
 

ocrmypdf/__init__.py

@@ -1,4 +1,5 @@
 from enum import IntEnum
+import os
 
 
 class ExitCode(IntEnum):
@@ -10,3 +11,8 @@ class ExitCode(IntEnum):
     file_access_error = 5
     already_done_ocr = 6
     other_error = 15
+
+
+def get_program(name):
+    envvar = 'OCRMYPDF_' + name.upper()
+    return os.environ.get(envvar, name)

ocrmypdf/ghostscript.py

@@ -4,12 +4,13 @@
 from tempfile import NamedTemporaryFile
 from subprocess import Popen, PIPE, check_call
 from shutil import copy
+from . import get_program
 
 
 def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log):
     with NamedTemporaryFile(delete=True) as tmp:
         args_gs = [
-            'gs',
+            get_program('gs'),
             '-dQUIET',
             '-dBATCH',
             '-dNOPAUSE',
@@ -36,7 +37,7 @@ def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log):
 def generate_pdfa(pdf_pages, output_file, threads=1):
     with NamedTemporaryFile(delete=True) as gs_pdf:
         args_gs = [
-            "gs",
+            get_program("gs"),
             "-dQUIET",
             "-dBATCH",
             "-dNOPAUSE",

ocrmypdf/pdfa.py

@@ -8,6 +8,7 @@ from string import Template
 from subprocess import Popen, PIPE
 import os
 import codecs
+from . import get_program
 
 
 # This is a template written in PostScript which is needed to create PDF/A
@@ -95,7 +96,8 @@ def _get_pdfa_def(icc_profile, icc_identifier, pdfmark):
 def _get_postscript_icc_path():
     "Parse Ghostscript's help message to find where iccprofiles are stored"
 
-    p_gs = Popen(['gs', '--help'], close_fds=True, universal_newlines=True,
+    p_gs = Popen([get_program('gs'), '--help'], close_fds=True,
+                 universal_newlines=True,
                  stdout=PIPE, stderr=PIPE)
     out, _ = p_gs.communicate()
     lines = out.splitlines()

ocrmypdf/qpdf.py

@@ -5,12 +5,12 @@ from subprocess import CalledProcessError, check_output, STDOUT, check_call
 import sys
 import os
 
-from . import ExitCode
+from . import ExitCode, get_program
 
 
 def check(input_file, log):
     args_qpdf = [
-        'qpdf',
+        get_program('qpdf'),
         '--check',
         input_file
     ]
@@ -34,7 +34,7 @@ def check(input_file, log):
 
 def repair(input_file, output_file, log):
     args_qpdf = [
-        'qpdf', input_file, output_file
+        get_program('qpdf'), input_file, output_file
     ]
     try:
         check_output(args_qpdf, stderr=STDOUT, universal_newlines=True)
@@ -60,7 +60,7 @@ def repair(input_file, output_file, log):
 
 def get_npages(input_file):
     pages = check_output(
-        ['qpdf', '--show-npages', input_file],
+        [get_program('qpdf'), '--show-npages', input_file],
          universal_newlines=True, close_fds=True)
     return int(pages)
 
@@ -73,7 +73,7 @@ def split_pages(input_file, work_folder, npages):
     """
     for n in range(int(npages)):
         args_qpdf = [
-            'qpdf', input_file,
+            get_program('qpdf'), input_file,
             '--pages', input_file, '{0}'.format(n + 1), '--',
             os.path.join(work_folder, '{0:06d}.page.pdf'.format(n + 1))
         ]

ocrmypdf/tesseract.py

@@ -6,7 +6,7 @@ import os
 import re
 import shutil
 from functools import lru_cache
-from . import ExitCode
+from . import ExitCode, get_program
 
 from subprocess import Popen, PIPE, CalledProcessError, \
     TimeoutExpired, check_output, STDOUT
@@ -42,7 +42,7 @@ HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?>
 @lru_cache(maxsize=1)
 def version():
     args_tess = [
-        'tesseract',
+        get_program('tesseract'),
         '--version'
     ]
     try:
@@ -60,7 +60,7 @@ def version():
 @lru_cache(maxsize=1)
 def languages():
     args_tess = [
-        'tesseract',
+        get_program('tesseract'),
         '--list-langs'
     ]
     try:
@@ -82,7 +82,7 @@ def generate_hocr(input_file, output_hocr, language: list, tessconfig: list,
     badxml = os.path.splitext(output_hocr)[0] + '.badxml'
 
     args_tesseract = [
-        'tesseract',
+        get_program('tesseract'),
         '-l', '+'.join(language),
         input_file,
         badxml,
@@ -147,7 +147,7 @@ def generate_pdf(input_image, skip_pdf, output_pdf, language: list,
     '''
 
     args_tesseract = [
-        'tesseract',
+        get_program('tesseract'),
         '-l', '+'.join(language),
         input_image,
         os.path.splitext(output_pdf)[0],  # Tesseract appends suffix

ocrmypdf/unpaper.py

@@ -8,13 +8,13 @@ from tempfile import NamedTemporaryFile
 import sys
 import os
 from functools import lru_cache
-from . import ExitCode
+from . import ExitCode, get_program
 
 
 @lru_cache(maxsize=1)
 def version():
     args_unpaper = [
-        'unpaper',
+        get_program('unpaper'),
         '--version'
     ]
     p_unpaper = Popen(args_unpaper, close_fds=True, universal_newlines=True,
@@ -33,7 +33,7 @@ except ImportError:
 
 def run(input_file, output_file, dpi, log, mode_args):
     args_unpaper = [
-        'unpaper',
+        get_program('unpaper'),
         '-v',
         '--dpi', str(dpi)
     ] + mode_args