Update RVK processing (#24)

The RVK URI prefix has been defined http://rvk.uni-regensburg.de/nt/
and underscore was chosen as replacement character for whitespace.

This commit adds native support of RVK processing and a new option to
set whitespace replacement character.

Author: nichtich

README.rst

@@ -91,8 +91,9 @@ URIs can be also be generated on the fly from an URI template specified with opt
   is to use 010 or 016 if defined, otherwise 001. If you find examples where this approach
   fails, please add them to [#42](https://github.com/scriptotek/mc2skos/issues/42).
 * ``{collection}`` is "class", "table" or "scheme"
-* ``{object}`` is a member of the classification scheme (with spaces replaced by
-  hyphens) and part of a ``{collection}``, such as a specific class or table.
+* ``{object}`` is a member of the classification scheme and part of a ``{collection}``, such
+  as a specific class or table. Spaces in the URI are replaced by hyphens or another character
+  configured with option `--whitespace`.
 * ``{edition}`` is taken from ``084 $c`` (with language code stripped)
 
 

examples/rvk.ttl

@@ -8,31 +8,29 @@
 @prefix xml: <http://www.w3.org/XML/1998/namespace> .
 @prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
 
-# RVK has no official URIs yet. Use example.org for testing
-
-<http://example.org/rvk/A> a skos:Concept ;
+<http://rvk.uni-regensburg.de/nt/A> a skos:Concept ;
     dcterms:created "2012-07-05"^^xsd:date ;
     dcterms:identifier "1:" ;
     dcterms:modified "2017-09-12"^^xsd:date ;
     skos:notation "A" ;
     skos:prefLabel "Allgemeines"@de ;
-    skos:topConceptOf <http://example.org/rvk> .
+    skos:topConceptOf <http://rvk.uni-regensburg.de/nt/> .
 
-<http://example.org/rvk/AA> a skos:Concept ;
+<http://rvk.uni-regensburg.de/nt/AA> a skos:Concept ;
     dcterms:created "2012-07-05"^^xsd:date ;
     dcterms:identifier "2:" ;
     dcterms:modified "2017-09-12"^^xsd:date ;
-    skos:broader <http://example.org/rvk/A> ;
-    skos:inScheme <http://example.org/rvk> ;
+    skos:broader <http://rvk.uni-regensburg.de/nt/A> ;
+    skos:inScheme <http://rvk.uni-regensburg.de/nt/> ;
     skos:notation "AA" ;
     skos:prefLabel "Bibliographien der Bibliographien, Universalbibliographien, Bibliothekskataloge, Nationalbibliographien"@de .
 
-<http://example.org/rvk/AA-09900> a skos:Concept ;
+<http://rvk.uni-regensburg.de/nt/AA_09900> a skos:Concept ;
     dcterms:created "2012-07-05"^^xsd:date ;
     dcterms:identifier "3:" ;
     dcterms:modified "2017-09-12"^^xsd:date ;
-    skos:broader <http://example.org/rvk/AA> ;
+    skos:broader <http://rvk.uni-regensburg.de/nt/AA> ;
     skos:editorialNote "Erläuterungen zur Notationsvergabe s. RVK-Online - Nutzunghinweise"@de ;
-    skos:inScheme <http://example.org/rvk> ;
+    skos:inScheme <http://rvk.uni-regensburg.de/nt/> ;
     skos:notation "AA 09900" ;
     skos:prefLabel "Bibliographische Zeitschriften"@de .

mc2skos/mc2skos.py

@@ -217,6 +217,8 @@ def main():
     parser.add_argument('--uri', dest='base_uri', help='URI template')
     parser.add_argument('--scheme', dest='scheme_uri', help='SKOS scheme for all records, use {edition} to specify edition.')
 #    parser.add_argument('--table_scheme', dest='table_scheme_uri', help='SKOS scheme for table records, use {edition} to specify edition.')
+    parser.add_argument('--whitespace', dest='whitespace', metavar='STRING',
+                        help='Replace whitespaces in URI templates with this.')
 
     parser.add_argument('--altlabels', '--indexterms', dest='altlabels', action='store_true',
                         help='Include altlabels (from 7XX or 4XX).')
@@ -293,6 +295,7 @@ def main():
     options = {
         'base_uri': args.base_uri,
         'scheme_uri': args.scheme_uri,
+        'whitespace': args.whitespace,
         'include_altlabels': args.altlabels,
         'exclude_notes': args.exclude_notes,
         'include_components': args.components,

mc2skos/record.py

@@ -67,6 +67,7 @@ def get_config(self, concept_type, code, options):
             return {
                 'concept': options.get('base_uri'),
                 'scheme': options.get('scheme_uri') or options.get('base_uri'),
+                'whitespace': options.get('whitespace', '-'),
             }
 
         try:
@@ -122,10 +123,6 @@ def get_uri(self, uri_type='concept', **kwargs):
             # Remove organization prefix in parenthesis:
             kwargs['control_number'] = re.sub(r'^\(.+\)(.+)$', '\\1', kwargs['control_number'])
 
-        if 'object' in kwargs:
-            # replace spaces by hyphens
-            kwargs['object'] = kwargs['object'].replace(' ', '-')
-
         if uri_type not in self.config:
             raise UnknownSchemeError(scheme_code=self.code, **kwargs)
 
@@ -156,7 +153,10 @@ def process_formatter(matches):
             uri_template
         )
 
-        return uri_template.format(**kwargs)
+        uri = uri_template.format(**kwargs)
+
+        # replace whitespaces in URI
+        return uri.replace(' ', self.config.get('whitespace', '-'))
 
 
 class Record(object):

mc2skos/vocabularies.yml

@@ -1,11 +1,15 @@
 ---
 classification_schemes:
-    ddc: http://dewey.info/{collection}/{object}/e{edition}/
+    asb: http://uri.gbv.de/terminology/asb/{object}
     bkl: http://uri.gbv.de/terminology/bk/{object}
+    ddc: http://dewey.info/{collection}/{object}/e{edition}/
+    rvk:
+        concept: http://rvk.uni-regensburg.de/nt/{object}
+        scheme: http://rvk.uni-regensburg.de/nt/
+        whitespace: _
     utklklass:
         concept: http://data.ub.uio.no/lklass/L{object[2:]}
         scheme: http://data.ub.uio.no/lklass/
-    asb: http://uri.gbv.de/terminology/asb/{object}
 subject_schemes:
     a:
         concept: http://id.loc.gov/authorities/subjects/{control_number}

test/test_process_examples.py

@@ -75,8 +75,6 @@ def test_rvk_example(marc, match):
 
     options = {
         'include_altlabels': True,
-        'scheme_uri': 'http://example.org/rvk',
-        'base_uri': 'http://example.org/rvk/{object}'
     }
 
     check_processing(marc, Graph(), **options)