From 853f6cdc0c02338bca4bb55448a5cd4975889f1e Mon Sep 17 00:00:00 2001
From: j <j@mailb.org>
Date: Fri, 1 Feb 2019 16:43:05 +0530
Subject: [PATCH 1/6] only scan once per day

---
 oml/tasks.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/oml/tasks.py b/oml/tasks.py
index 3f97379..93d3b45 100644
--- a/oml/tasks.py
+++ b/oml/tasks.py
@@ -36,7 +36,10 @@ class Tasks(Thread):
 
     def run(self):
         self.load_tasks()
-        self.queue('scan')
+        if time.mktime(time.gmtime()) - settings.server.get('last_scan', 0) > 24*60*60:
+            settings.server['last_scan'] = time.mktime(time.gmtime())
+            self.queue('scan')
+
         import item.scan
         from item.models import sync_metadata, get_preview, get_cover
         from user.models import (

From 1421e402e13e07a4c426dd0430b7c16a1afa01a4 Mon Sep 17 00:00:00 2001
From: j <j@mailb.org>
Date: Fri, 1 Feb 2019 16:43:20 +0530
Subject: [PATCH 2/6] PEP8

---
 oml/media/epub.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/oml/media/epub.py b/oml/media/epub.py
index cd5a6f0..552a134 100644
--- a/oml/media/epub.py
+++ b/oml/media/epub.py
@@ -153,7 +153,7 @@ def info(epub):
                             contents.append(txt)
                 if contents:
                     data['tableofcontents'] = '\n'.join(contents).strip()
-        if not 'tableofcontents' in data:
+        if 'tableofcontents' not in data:
             guide = info.find('{http://www.idpf.org/2007/opf}guide')
             if guide:
                 for ref in guide.findall('{http://www.idpf.org/2007/opf}reference'):
@@ -169,7 +169,7 @@ def info(epub):
         data['description'] = strip_tags(decode_html(data['description']))
     text = extract_text(epub)
     data['textsize'] = len(text)
-    if not 'isbn' in data:
+    if 'isbn' not in data:
         isbn = extract_isbn(text)
         if isbn:
             data['isbn'] = isbn

From e623307d190bea5e8110b44aa5bf8cc9a145f088 Mon Sep 17 00:00:00 2001
From: j <j@mailb.org>
Date: Fri, 1 Feb 2019 16:43:30 +0530
Subject: [PATCH 3/6] paths with spaces

---
 ctl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ctl b/ctl
index da49820..8195061 100755
--- a/ctl
+++ b/ctl
@@ -56,7 +56,7 @@ else
             ARCH="_armv7l"
         fi
         PLATFORM="linux$ARCH"
-        if [ -e $BASE/platform_${PLATFORM}/lib/libunrar.so ]; then
+        if [ -e "$BASE/platform_${PLATFORM}/lib/libunrar.so" ]; then
             export UNRAR_LIB_PATH="$BASE/platform_${PLATFORM}/lib/libunrar.so"
         fi
     fi

From debe3823e2a83ef5d624786a8dc34d222c0cf475 Mon Sep 17 00:00:00 2001
From: j <j@mailb.org>
Date: Fri, 1 Feb 2019 16:43:55 +0530
Subject: [PATCH 4/6] only try to download if we have a url

---
 oml/item/models.py | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/oml/item/models.py b/oml/item/models.py
index a2b200a..72d6b8e 100644
--- a/oml/item/models.py
+++ b/oml/item/models.py
@@ -843,15 +843,17 @@ def download_cover(id):
             url = i.meta.get('cover')
         else:
             url = None
+            cover = None
 
     logger.debug('download cover %s %s', id, url)
     ratio = None
-    try:
-        cover = ox.net.read_url(url)
-        ratio = get_ratio(cover)
-    except:
-        logger.debug('unable to read cover url %s', url)
-        cover = None
+    if url:
+        try:
+            cover = ox.net.read_url(url)
+            ratio = get_ratio(cover)
+        except:
+            logger.debug('unable to read cover url %s', url)
+            cover = None
     with db.session():
         i = Item.get(id, for_update=True)
         if i:

From c38d3a8b3523b0fff74d9a4456887f22f5087671 Mon Sep 17 00:00:00 2001
From: j <j@mailb.org>
Date: Fri, 1 Feb 2019 17:36:03 +0530
Subject: [PATCH 5/6] use pdftotext if available

---
 oml/media/pdf.py | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/oml/media/pdf.py b/oml/media/pdf.py
index bc342d0..75313b2 100644
--- a/oml/media/pdf.py
+++ b/oml/media/pdf.py
@@ -237,10 +237,13 @@ def info(pdf):
 def extract_text(pdf):
     if sys.platform == 'win32':
         pdf = get_short_path_name(pdf)
+    cmd = ['pdftotext', pdf, '-']
     if sys.platform == 'darwin':
-        cmd = ['/usr/bin/mdimport', '-d2', pdf]
-    else:
-        cmd = ['pdftotext', pdf, '-']
+        pdftotext = ['/usr/local/bin/pdftotext', pdf, '-']
+        if os.path.exists(pdftotext[0]):
+            cmd = pdftotext
+        else:
+            cmd = ['/usr/bin/mdimport', '-d2', pdf]
     if sys.platform == 'win32':
         startupinfo = subprocess.STARTUPINFO()
         startupinfo.dwFlags |= subprocess.STARTF_USESHOWWINDOW
@@ -251,7 +254,7 @@ def extract_text(pdf):
     stdout, stderr = p.communicate()
     stdout = stdout.decode()
     stderr = stderr.decode()
-    if sys.platform == 'darwin':
+    if sys.platform == 'darwin' and cmd[0] == '/usr/bin/mdimport':
         if 'kMDItemTextContent' in stderr:
             stdout = stderr.split('kMDItemTextContent = "')[-1].split('\n')[0][:-2]
         else:

From 4e4b853416b5899dbad5e8cb38610cdca7547a45 Mon Sep 17 00:00:00 2001
From: j <j@mailb.org>
Date: Fri, 1 Feb 2019 17:53:17 +0530
Subject: [PATCH 6/6] fix cbz

---
 oml/media/cbz.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/oml/media/cbz.py b/oml/media/cbz.py
index b08c972..60f0672 100644
--- a/oml/media/cbz.py
+++ b/oml/media/cbz.py
@@ -1,9 +1,14 @@
 # -*- coding: utf-8 -*-
 import os
 import zipfile
+import logging
 
 import ox
 
+
+logger = logging.getLogger(__name__)
+
+
 def cover(path):
     data = None
     logger.debug('cover %s', path)