From 63de7e1677819b187923dcce7628ae5209cd6e4a Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <jim@purplerock.ca>
Date: Mon, 30 Dec 2019 16:14:52 -0800
Subject: [PATCH] Improve error message for unreadable input files

---
 src/ocrmypdf/_pipeline.py   | 8 +++++---
 src/ocrmypdf/_sync.py       | 8 ++++++--
 src/ocrmypdf/_validation.py | 4 ++--
 tests/test_main.py          | 9 +++++++++
 4 files changed, 22 insertions(+), 7 deletions(-)

diff --git a/src/ocrmypdf/_pipeline.py b/src/ocrmypdf/_pipeline.py
index 2705b2ab..cad9d74b 100644
--- a/src/ocrmypdf/_pipeline.py
+++ b/src/ocrmypdf/_pipeline.py
@@ -19,6 +19,7 @@ import os
 import re
 import sys
 from datetime import datetime, timezone
+from pathlib import Path
 from shutil import copyfileobj
 
 import img2pdf
@@ -123,7 +124,7 @@ def _pdf_guess_version(input_file, search_window=1024):
     return ''
 
 
-def triage(input_file, output_file, options, log):
+def triage(original_filename, input_file, output_file, options, log):
     try:
         if _pdf_guess_version(input_file):
             if options.image_dpi:
@@ -135,8 +136,9 @@ def triage(input_file, output_file, options, log):
             safe_symlink(input_file, output_file)
             return output_file
     except EnvironmentError as e:
-        log.error(e)
-        raise InputFileError() from e
+        log.debug(f"Temporary file was at: {input_file}")
+        msg = str(e).replace(input_file, original_filename)
+        raise InputFileError(msg) from e
 
     triage_image_file(input_file, output_file, options, log)
     return output_file
diff --git a/src/ocrmypdf/_sync.py b/src/ocrmypdf/_sync.py
index 5b27a8f0..87546049 100644
--- a/src/ocrmypdf/_sync.py
+++ b/src/ocrmypdf/_sync.py
@@ -332,11 +332,15 @@ def run_pipeline(options, api=False):
     work_folder = mkdtemp(prefix="com.github.ocrmypdf.")
     try:
         check_requested_output_file(options)
-        start_input_file = create_input_file(options, work_folder)
+        start_input_file, original_filename = create_input_file(options, work_folder)
 
         # Triage image or pdf
         origin_pdf = triage(
-            start_input_file, os.path.join(work_folder, 'origin.pdf'), options, log
+            original_filename,
+            start_input_file,
+            os.path.join(work_folder, 'origin.pdf'),
+            options,
+            log,
         )
 
         # Gather pdfinfo and create context
diff --git a/src/ocrmypdf/_validation.py b/src/ocrmypdf/_validation.py
index b53f0fc4..1ebd422c 100644
--- a/src/ocrmypdf/_validation.py
+++ b/src/ocrmypdf/_validation.py
@@ -380,12 +380,12 @@ def create_input_file(options, work_folder):
         target = os.path.join(work_folder, 'stdin')
         with open(target, 'wb') as stream_buffer:
             copyfileobj(sys.stdin.buffer, stream_buffer)
-        return target
+        return target, "<stdin>"
     else:
         try:
             target = os.path.join(work_folder, 'origin')
             safe_symlink(options.input_file, target)
-            return target
+            return target, os.fspath(options.input_file)
         except FileNotFoundError:
             raise InputFileError(f"File not found - {options.input_file}")
 
diff --git a/tests/test_main.py b/tests/test_main.py
index 0380508b..0e336d80 100644
--- a/tests/test_main.py
+++ b/tests/test_main.py
@@ -270,6 +270,15 @@ def test_input_file_not_found(caplog, no_outpdf):
     assert input_file in caplog.text
 
 
+def test_input_file_not_readable(caplog, resources, outdir, no_outpdf):
+    input_file = outdir / 'trivial.pdf'
+    shutil.copy(resources / 'trivial.pdf', input_file)
+    input_file.chmod(0o000)
+    result = run_ocrmypdf_api(input_file, no_outpdf)
+    assert result == ExitCode.input_file
+    assert input_file in caplog.text
+
+
 def test_input_file_not_a_pdf(caplog, no_outpdf):
     input_file = __file__  # Try to OCR this file
     result = run_ocrmypdf_api(input_file, no_outpdf)