From 18e341d650c6cdb0637464608e23cb185130eaf5 Mon Sep 17 00:00:00 2001
From: Pavel Yakunin <pyakunin@gmail.com>
Date: Sun, 5 Jun 2016 22:28:30 +0300
Subject: [PATCH] epub uploading

---
 cps/book_formats.py | 24 ++++++++++++----
 cps/epub.py         | 67 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 86 insertions(+), 5 deletions(-)
 create mode 100644 cps/epub.py

diff --git a/cps/book_formats.py b/cps/book_formats.py
index b656fa02..4e797113 100644
--- a/cps/book_formats.py
+++ b/cps/book_formats.py
@@ -9,19 +9,33 @@ try:
     from wand.image import Image
     use_generic_pdf_cover = False
 except ImportError, e:
-    logger.warning('cannot import Image, generating pdf covers for pdf uploads will not work')
+    logger.warning('cannot import Image, generating pdf covers for pdf uploads will not work: %s', e)
     use_generic_pdf_cover = True
 try:
     from PyPDF2 import PdfFileReader
     use_pdf_meta = True
 except ImportError, e:
-    logger.warning('cannot import PyPDF2, extracting pdf metadata will not work')
+    logger.warning('cannot import PyPDF2, extracting pdf metadata will not work: %s', e)
     use_pdf_meta = False
 
+try:
+    import epub
+    use_epub_meta = True
+except ImportError, e:
+    logger.warning('cannot import PyPDF2, extracting pdf metadata will not work: %s', e)
+    use_epub_meta = False
+
+
 def process(tmp_file_path, original_file_name, original_file_extension):
-    if (".PDF" == original_file_extension.upper()):
-        return pdf_meta(tmp_file_path, original_file_name, original_file_extension)
-    else: return default_meta(tmp_file_path, original_file_name, original_file_extension)
+    try:
+        if ".PDF" == original_file_extension.upper():
+            return pdf_meta(tmp_file_path, original_file_name, original_file_extension)
+        if ".EPUB" == original_file_extension.upper() and use_pdf_meta == True:
+            return epub.get_epub_info(tmp_file_path, original_file_name, original_file_extension)
+    except Exception, e:
+        logger.warning('cannot parse metadata, using default: %s', e)
+
+    return default_meta(tmp_file_path, original_file_name, original_file_extension)
 
 
 
diff --git a/cps/epub.py b/cps/epub.py
new file mode 100644
index 00000000..03fb30bb
--- /dev/null
+++ b/cps/epub.py
@@ -0,0 +1,67 @@
+import zipfile
+from lxml import etree
+import os
+import uploader
+
+def extractCover(zip, coverFile, tmp_file_name):
+    if (coverFile is None):
+        return None
+    else:
+        cf = zip.read("OPS/" + coverFile)
+        prefix = os.path.splitext(tmp_file_name)[0]
+        tmp_cover_name = prefix + "." + coverFile
+        image = open(tmp_cover_name, 'wb')
+        image.write(cf)
+        image.close()
+        return tmp_cover_name
+
+
+
+def get_epub_info(tmp_file_path, original_file_name, original_file_extension):
+    ns = {
+        'n':'urn:oasis:names:tc:opendocument:xmlns:container',
+        'pkg':'http://www.idpf.org/2007/opf',
+        'dc':'http://purl.org/dc/elements/1.1/'
+    }
+
+    zip = zipfile.ZipFile(tmp_file_path)
+
+    txt = zip.read('META-INF/container.xml')
+    tree = etree.fromstring(txt)
+    cfname = tree.xpath('n:rootfiles/n:rootfile/@full-path',namespaces=ns)[0]
+
+    cf = zip.read(cfname)
+    tree = etree.fromstring(cf)
+
+    p = tree.xpath('/pkg:package/pkg:metadata',namespaces=ns)[0]
+
+    epub_metadata = {}
+    for s in ['title', 'description', 'creator']:
+        tmp = p.xpath('dc:%s/text()'%(s),namespaces=ns)
+        if (len(tmp) > 0):
+            epub_metadata[s] = p.xpath('dc:%s/text()'%(s),namespaces=ns)[0]
+        else:
+            epub_metadata[s] = "Unknown"
+
+    coversection = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='cover']/@href",namespaces=ns)
+    if (len(coversection) > 0):
+        coverfile = extractCover(zip, coversection[0], tmp_file_path)
+    else:
+        coverfile = None
+    if epub_metadata['title'] is None:
+        title = original_file_name
+    else:
+        title = epub_metadata['title']
+
+
+    return uploader.BookMeta(
+        file_path = tmp_file_path,
+        extension = original_file_extension,
+        title = title,
+        author = epub_metadata['creator'],
+        cover = coverfile,
+        description = epub_metadata['description'],
+        tags = "",
+        series = "",
+        series_id="")
+