3 posts tagged with "python"

Improving Apache's canonical hostname rewrite rules

March 25, 2009 · 2 min read

According to the Apache URL rewriting guide, the way to handle Canonical Hostnames is like this:

RewriteCond %{HTTP_HOST}   !^fully\.qualified\.domain\.name [NC]
RewriteCond %{HTTP_HOST}   !^$
RewriteRule ^/(.*)         http://fully.qualified.domain.name/$1 [L,R]

Well, those rules are not always sufficient. Specifically, what if you also owned the www.example.com.au domain, and wished to redirect it also to the primary www.example.com domain? The solution is simple - we just need to add a single $ character to the end of the match-pattern of the first RewriteCond like this:

RewriteCond %{HTTP_HOST}   !^fully\.qualified\.domain\.name$ [NC]
RewriteCond %{HTTP_HOST}   !^$
RewriteRule ^/(.*)         http://fully.qualified.domain.name/$1 [L,R]

Now that will work nicely as long as the hosts use standard ports (ie 80 for HTTP, and 443 for HTTPS). However, some Python versions unnecessarily append the standard HTTPS port number to the Host HTTP header. Also I discovered today (after some Apache debug logging) that Adobe AIR applications have the exact same misbehavior for HTTPS, but only when running under Mac OS X.

Using PyODConverter with non-default ports

February 10, 2009 · 2 min read

Paul Colby

I've been using the excellent PyODConverter (aka Python OpenDocument Converter) for quite some time now. It's a very small Python script that uses OpenOffice's Python-UNO bridge to convert documents between formats. For example, to convert test.doc to a PDF file, you could execute:

python DocumentConverter.py test.doc test.pdf

tip

For the Python-UNO bridge (and thus PyODConverter) to work, you do need to use the python binary that installs with OpenOffice, so you will most likely need to full-qualify the python command like:

/opt/openoffice.org3/program/python DocumentConverter.py test.doc test.pdf

Anyway, PyODConverter always tries to talk to OpenOffice via (the somewhat arbitrary) port 8100. But today I found myself needing to able to tell PyODConverter which port to use via the command line. So, I went about modifying the PyODConverter code - which was very easy, thanks to it being already very well written.

Memory leak in ibm_db.fetch_assoc

August 8, 2008 · One min read

Paul Colby

I had a really frustrating time yesterday, trying to sort out some bugs in IBM's ibm_db DB2 driver for Python. Unfortunately I don't know Python well enough to know whether the bugs are in the ibm_db driver, Python, or my misuse if either or both :( But what I can tell you, is that the following Python / ibm_db code results in a definite memory leak.

sql = "SELECT filename, data FROM files WHERE id = ... ";
stmt = ibm_db.exec_immediate(conn,sql);
row = ibm_db.fetch_assoc(stmt);
row.clear(); # Just to be sure.
ibm_db.free_result(stmt);