Better parser guessing when grabbing plain text from a webserver.

Also fix a typo in an error message

diff --git a/htsworkflow/util/rdfhelp.py b/htsworkflow/util/rdfhelp.py
index 7f8902a7615969c71e17ec2a2b6574a6dc65d742..9f4a1074376f34c30ca4075e5f374af91585c9f9 100644 (file)
--- a/htsworkflow/util/rdfhelp.py
+++ b/htsworkflow/util/rdfhelp.py
@@ -277,6 +277,7 @@ def load_into_model(model, parser_name, path, ns=None):
 
     rdf_parser = RDF.Parser(name=parser_name)
 
+    statements = []
     retries = 3
     while retries > 0:
         try:
@@ -285,7 +286,7 @@ def load_into_model(model, parser_name, path, ns=None):
             retries = 0
         except RDF.RedlandError, e:
             errmsg = "RDF.RedlandError: {0} {1} tries remaining"
-            logger.error(errmsg.format(str(e), tries))
+            logger.error(errmsg.format(str(e), retries))
 
     for s in statements:
         conditionally_add_statement(model, s, ns)
@@ -355,16 +356,16 @@ def guess_parser(content_type, pathname):
         return 'turtle'
     elif content_type in ('text/html',):
         return 'rdfa'
-    elif content_type is None:
+    elif content_type is None or content_type in ('text/plain',):
         return guess_parser_by_extension(pathname)
 
 def guess_parser_by_extension(pathname):
     _, ext = os.path.splitext(pathname)
     if ext in ('.xml', '.rdf'):
         return 'rdfxml'
-    elif ext in ('.html'):
+    elif ext in ('.html',):
         return 'rdfa'
-    elif ext in ('.turtle'):
+    elif ext in ('.turtle',):
         return 'turtle'
     return 'guess'
 

diff --git a/htsworkflow/util/test/test_rdfhelp.py b/htsworkflow/util/test/test_rdfhelp.py
index d331416ebc0225688fbe53ae6921ed260640aa34..61cc1dc3d84106f758be2d4973f099982372ea27 100644 (file)
--- a/htsworkflow/util/test/test_rdfhelp.py
+++ b/htsworkflow/util/test/test_rdfhelp.py
@@ -202,7 +202,8 @@ _:a owl:imports "{loc}extra.turtle" .
                 ('/a/b/c.rdf', 'rdfxml'),
                 ('/a/b/c.xml', 'rdfxml'),
                 ('/a/b/c.html', 'rdfa'),
-                ('/a/b/c.turtle', 'turtle')]
+                ('/a/b/c.turtle', 'turtle'),
+                ('http://foo.bar/bleem.turtle', 'turtle')]
             for path, parser in DATA:
                 self.assertEqual(guess_parser_by_extension(path), parser)
                 self.assertEqual(guess_parser(None, path), parser)
@@ -210,7 +211,10 @@ _:a owl:imports "{loc}extra.turtle" .
             DATA = [
                 ('application/rdf+xml', 'http://a.org/b/c', 'rdfxml'),
                 ('application/x-turtle', 'http://a.org/b/c', 'turtle'),
-                ('text/html', 'http://a.org/b/c', 'rdfa')
+                ('text/html', 'http://a.org/b/c', 'rdfa'),
+                ('text/html', 'http://a.org/b/c.html', 'rdfa'),
+                ('text/plain', 'http://a.org/b/c.turtle', 'turtle'),
+                ('text/plain', 'http://a.org/b/c', 'guess')
             ]
             for contenttype, url, parser in DATA:
                 self.assertEqual(guess_parser(contenttype, url), parser)