setup script + doc improvement + tsv exporter

dbpediakit/postgres.py

@@ -169,5 +169,12 @@ def check_text_table(archive_name, table, database=DATABASE, **extract_params):
     copy(tuples, table, database=database)
     logging.info("Creating index on column '%s' in table '%s'",
                  "id", table)
-    execute(CREATE_INDEX.format(table=table, column="id"))
+    execute(CREATE_INDEX.format(table=table, column="id"), database=database)
     return True
+
+
+def export_as_tsv(table, columns, filename, database=DATABASE):
+    """Export the content of a SQL table as tab separated values file"""
+    sql = "copy (select %s from %s) TO '%s';" % (
+        ', '.join(columns), table, filename)
+    execute(sql, database=database)

examples/topics/README.md

@@ -20,11 +20,9 @@ To initialize the PostgreSQL under Ubuntu / Debian::
 Then switch to the postgres admin user to create a role and DB for your unix
 user and your dbpediakit usage. For instance my unix account is `ogrisel`:
 
-    $ sudo su - postgres
-    $ createuser ogrisel
+    $ sudo -u postgres createuser ogrisel
     Shall the new role be a superuser? (y/n) y
-    $ createdb -O ogrisel -E UTF8 dbpediakit
-    $ ^D
+    $ sudo -u postgres createdb -O ogrisel -E UTF8 dbpediakit
 
 You can check that database dbpediakit has been created successfully and that
 your unix account as access to it with::

setup.py

@@ -0,0 +1,38 @@
+#! /usr/bin/env python
+
+DISTNAME = 'dbpediakit'
+DESCRIPTION = """Python / SQL utilities to work with the DBpedia dumps"""
+LONG_DESCRIPTION = open('README.md').read()
+MAINTAINER = 'Olivier Grisel'
+MAINTAINER_EMAIL = 'olivier.grisel@ensta.org'
+URL = 'https://github.com/ogrisel/dbpediakit'
+LICENSE = 'MIT'
+VERSION = '0.1-git'
+
+from distutils.core import setup
+
+
+if __name__ == "__main__":
+
+    setup(name=DISTNAME,
+          maintainer=MAINTAINER,
+          maintainer_email=MAINTAINER_EMAIL,
+          description=DESCRIPTION,
+          license=LICENSE,
+          url=URL,
+          version=VERSION,
+          long_description=LONG_DESCRIPTION,
+          classifiers=[
+              'Intended Audience :: Science/Research',
+              'Intended Audience :: Developers',
+              'License :: OSI Approved',
+              'Programming Language :: Python',
+              'Programming Language :: SQL',
+              'Topic :: Software Development',
+              'Topic :: Scientific/Engineering',
+              'Operating System :: Microsoft :: Windows',
+              'Operating System :: POSIX',
+              'Operating System :: Unix',
+              'Operating System :: MacOS'
+             ]
+    )