Merge pull request #124 from bmartin5692/master

Added a density setting

paperless.conf.example

@@ -61,6 +61,17 @@ PAPERLESS_SHARED_SECRET=""
 # the web for "MAGICK_MEMORY_LIMIT".
 #PAPERLESS_CONVERT_MEMORY_LIMIT=0
 
+# By default the conversion density setting for documents is 300DPI, in some
+# cases it has proven useful to configure a lesser value.
+# This setting has a high impact on the physical size of tmp page files,
+# the speed of document conversion, and can affect the accuracy of OCR
+# results. Individual results can vary and this setting should be tested 
+# thoroughly against the documents you are importing to see if it has any 
+# impacts either negative or positive. Testing on limited document sets has
+# shown a setting of 200 can cut the size of tmp files by 1/3, and speed up
+# conversion by up to 4x with little impact to OCR accuracy.
+#PAPERLESS_CONVERT_DENSITY=300
+
 # Similar to the memory limit, if you've got a small system and your OS mounts
 # /tmp as tmpfs, you should set this to a path that's on a physical disk, like
 # /home/your_user/tmp or something.  ImageMagick will use this as scratch space

src/documents/consumer.py

@@ -53,6 +53,7 @@ class Consumer(object):
     UNPAPER = settings.UNPAPER_BINARY
     CONSUME = settings.CONSUMPTION_DIR
     THREADS = int(settings.OCR_THREADS) if settings.OCR_THREADS else None
+    DENSITY = settings.CONVERT_DENSITY if settings.CONVERT_DENSITY else 300
 
     DEFAULT_OCR_LANGUAGE = settings.OCR_LANGUAGE
 
@@ -158,7 +159,7 @@ class Consumer(object):
         pnm = os.path.join(tempdir, "convert-%04d.pnm")
         run_convert(
             self.CONVERT,
-            "-density", "300",
+            "-density", str(self.DENSITY),
             "-depth", "8",
             "-type", "grayscale",
             doc, pnm,

src/paperless/settings.py

@@ -191,6 +191,7 @@ GNUPG_HOME = os.getenv("HOME", "/tmp")
 CONVERT_BINARY = os.getenv("PAPERLESS_CONVERT_BINARY")
 CONVERT_TMPDIR = os.getenv("PAPERLESS_CONVERT_TMPDIR")
 CONVERT_MEMORY_LIMIT = os.getenv("PAPERLESS_CONVERT_MEMORY_LIMIT")
+CONVERT_DENSITY = os.getenv("PAPERLESS_CONVERT_DENSITY")
 
 # Unpaper
 UNPAPER_BINARY = os.getenv("PAPERLESS_UNPAPER_BINARY", "unpaper")