From 5d111a3c04d1c1fb6d0f1e8cf5a7475b66252539 Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <jim@purplerock.ca>
Date: Wed, 16 Dec 2015 17:48:26 -0800
Subject: [PATCH] Refactor tesseract --pdfrenderer calls to tesseract.py

---
 ocrmypdf/main.py      | 28 ++++++++--------------------
 ocrmypdf/tesseract.py | 33 +++++++++++++++++++++++++++++++++
 2 files changed, 41 insertions(+), 20 deletions(-)

diff --git a/ocrmypdf/main.py b/ocrmypdf/main.py
index 6ce98907..7483c8bb 100755
--- a/ocrmypdf/main.py
+++ b/ocrmypdf/main.py
@@ -654,26 +654,14 @@ def tesseract_ocr_and_render_pdf(
         re_symlink(input_pdf, output_file)
         return
 
-    args_tesseract = [
-        'tesseract',
-        '-l', '+'.join(options.language),
-        input_image,
-        os.path.splitext(output_file)[0],  # Tesseract appends suffix
-        'pdf'
-    ] + options.tesseract_config
-    p = Popen(args_tesseract, close_fds=True, stdout=PIPE, stderr=PIPE,
-              universal_newlines=True)
-
-    try:
-        stdout, stderr = p.communicate(timeout=options.tesseract_timeout)
-        if stdout:
-            log.info(stdout)
-        if stderr:
-            log.error(stderr)
-    except TimeoutExpired:
-        p.kill()
-        log.info("Tesseract - page timed out")
-        re_symlink(input_pdf, output_file)
+    tesseract.generate_pdf(
+        input_image=input_image,
+        skip_pdf=input_pdf,
+        output_pdf=output_file,
+        language=options.language,
+        tessconfig=options.tesseract_config,
+        timeout=options.tesseract_timeout,
+        log=log)
 
 
 @transform(
diff --git a/ocrmypdf/tesseract.py b/ocrmypdf/tesseract.py
index 1505476a..38a29f98 100644
--- a/ocrmypdf/tesseract.py
+++ b/ocrmypdf/tesseract.py
@@ -134,3 +134,36 @@ def generate_hocr(input_file, output_hocr, language: list, tessconfig: list,
                 f_out.write(line)
 
 
+def generate_pdf(input_image, skip_pdf, output_pdf, language: list,
+                 tessconfig: list, timeout: float, log):
+    '''Use Tesseract to render a PDF.
+
+    input_image -- image to analyze
+    skip_pdf -- if we time out, use this file as output
+    language -- list of languages to consider
+    tessconfig -- tesseract configuration
+    timeout -- timeout (seconds)
+    log -- logger object
+    '''
+
+    args_tesseract = [
+        'tesseract',
+        '-l', '+'.join(language),
+        input_image,
+        os.path.splitext(output_pdf)[0],  # Tesseract appends suffix
+        'pdf'
+    ] + tessconfig
+    p = Popen(args_tesseract, close_fds=True, stdout=PIPE, stderr=PIPE,
+              universal_newlines=True)
+
+    try:
+        stdout, stderr = p.communicate(timeout=timeout)
+        if stdout:
+            log.info(stdout)
+        if stderr:
+            log.error(stderr)
+    except TimeoutExpired:
+        p.kill()
+        log.info("Tesseract - page timed out")
+        shutil.copy(skip_pdf, output_pdf)
+