The process to get pdf2htmlEX installed on beta

diff --git a/fabfile.py b/fabfile.py
index 6d9bd8fa952b778e45151dd1e3848ffd3accb773..f903dc5de01233f8cf4824246f639cf35b3c348b 100644 (file)
--- a/fabfile.py
+++ b/fabfile.py
@@ -280,6 +280,38 @@ def import_usde():
     virtenv_exec('{0}/manage.py import_usde_csv {1}'.format(env.code_root, env.usde_csv))
     virtenv_exec('{0}/manage.py sanitize_usde_schools'.format(env.code_root))
 
+@task
+def install_pdf2htmlEX():
+    """
+    # Some things we need:
+    sudo apt-get install cmake libpng-dev libjpeg-dev libgtk2.0-dev pkg-config libfontconfig1-dev autoconf libtool
+
+    # Ubuntu 12.04 comes with a version of poppler that is too
+    # old, so compile our own
+    wget http://poppler.freedesktop.org/poppler-0.24.4.tar.xz
+    tar xf poppler-0.24.4.tar.gz
+    ./configure --prefix=/usr --enable-xpdf-headers
+    make
+    sudo make install
+
+    # Ubuntu 12.04 comes with a version of fontforge that is too
+    # old, so compile our own
+    git clone https://github.com/fontforge/fontforge.git
+    ./autogen.sh
+    ./configure --prefix=/usr
+    make
+    sudo make install
+
+    # Compile pdf2htmlEX
+    wget https://github.com/coolwanglu/pdf2htmlEX/archive/v0.10.tar.gz
+    tar xf x0.10.tar.gz
+    cd pdf2htmlEX
+    cmake .
+    make
+    sudo make install
+    """
+    print "not implemented yet!"
+
 @task
 def first_deploy():
     """

diff --git a/karmaworld/apps/notes/gdrive.py b/karmaworld/apps/notes/gdrive.py
index ec450094808f89e4c3e23096956e13d8ff8b8910..a58b743d45383c04eff1fc3bc7f03c491ea2eb47 100644 (file)
--- a/karmaworld/apps/notes/gdrive.py
+++ b/karmaworld/apps/notes/gdrive.py
@@ -74,7 +74,7 @@ def pdf2html(content):
     pdf_file.flush()
     tmp_dir = tempfile.gettempdir()
     html_file_name = uuid.uuid4().hex
-    html_file_path = tmp_dir + os.sep + html_file_name
+    html_file_path = os.path.join(tmp_dir, html_file_name)
 
     command = ['pdf2htmlEX', pdf_file.name, html_file_name]
     call = subprocess.Popen(command, shell=False, cwd=tmp_dir)
@@ -82,6 +82,8 @@ def pdf2html(content):
     if call.returncode != 0:
         raise ValueError("PDF file could not be processed")
 
+    pdf_file.close()
+
     try:
         html_file = open(html_file_path, 'r')
         html = html_file.read()