X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/a8e0e65bd0f444c69d7199f7e3c5ebce0d206b09..30aeb8412da3bb4d9dfc7f659f94fd64f5e26876:/librarian/__init__.py diff --git a/librarian/__init__.py b/librarian/__init__.py index 9c48a02..8a69d00 100644 --- a/librarian/__init__.py +++ b/librarian/__init__.py @@ -9,7 +9,7 @@ import os import re import shutil -class ParseError(Exception): +class UnicodeException(Exception): def __str__(self): """ Dirty workaround for Python Unicode handling problems. """ return self.message @@ -18,14 +18,17 @@ class ParseError(Exception): """ Dirty workaround for Python Unicode handling problems. """ return self.message -class ValidationError(Exception): +class ParseError(UnicodeException): + pass + +class ValidationError(UnicodeException): pass class NoDublinCore(ValidationError): """There's no DublinCore section, and it's required.""" pass -class NoProvider(Exception): +class NoProvider(UnicodeException): """There's no DocProvider specified, and it's needed.""" pass @@ -66,20 +69,45 @@ WLNS = EmptyNamespace() class WLURI(object): - """Represents a WL URI. Extracts slug and language from it.""" - + """Represents a WL URI. Extracts slug from it.""" slug = None - language = None - _re_wl_uri = re.compile('http://wolnelektury.pl/katalog/lektura/' - '(?P[-a-z]+)(/(?P[a-z]{3})/?)?') + example = 'http://wolnelektury.pl/katalog/lektura/template/' + _re_wl_uri = re.compile(r'http://(www\.)?wolnelektury.pl/katalog/lektura/' + '(?P[-a-z0-9]+)/?$') def __init__(self, uri): + uri = unicode(uri) self.uri = uri - match = self._re_wl_uri.match(uri) - assert match - self.slug = match.group('slug') - self.language = match.group('lang') + self.slug = uri.rstrip('/').rsplit('/', 1)[-1] + + @classmethod + def strict(cls, uri): + match = cls._re_wl_uri.match(uri) + if not match: + raise ValidationError(u'Invalid URI (%s). Should match: %s' % ( + uri, cls._re_wl_uri.pattern)) + return cls(uri) + + @classmethod + def from_slug(cls, slug): + """Contructs an URI from slug. + + >>> WLURI.from_slug('a-slug').uri + u'http://wolnelektury.pl/katalog/lektura/a-slug/' + + """ + uri = 'http://wolnelektury.pl/katalog/lektura/%s/' % slug + return cls(uri) + + def __unicode__(self): + return self.uri + + def __str__(self): + return self.uri + + def __eq__(self, other): + return self.slug == other.slug class DocProvider(object): @@ -88,18 +116,14 @@ class DocProvider(object): Used for generating joined files, like EPUBs. """ - def by_slug_and_lang(self, slug, lang=None): - """Should return a file-like object with a WL document XML.""" - raise NotImplementedError - def by_slug(self, slug): """Should return a file-like object with a WL document XML.""" - return self.by_slug_and_lang(slug) + raise NotImplementedError - def by_uri(self, uri): + def by_uri(self, uri, wluri=WLURI): """Should return a file-like object with a WL document XML.""" - wluri = WLURI(uri) - return self.by_slug_and_lang(wluri.slug, wluri.language) + wluri = wluri(uri) + return self.by_slug(wluri.slug) class DirDocProvider(DocProvider): @@ -108,10 +132,9 @@ class DirDocProvider(DocProvider): def __init__(self, dir_): self.dir = dir_ self.files = {} - return super(DirDocProvider, self).__init__() - def by_slug_and_lang(self, slug, lang=None): - fname = "%s%s.xml" % (slug, ".%s" % lang if lang else "") + def by_slug(self, slug): + fname = slug + '.xml' return open(os.path.join(self.dir, fname)) @@ -134,8 +157,7 @@ DEFAULT_BOOKINFO = dcparser.BookInfo( Wolne Lektury (http://wolnelektury.pl). Reprodukcja cyfrowa wykonana przez Bibliotekę Narodową z egzemplarza pochodzącego ze zbiorów BN."""], - DCNS('identifier.url'): - [u"http://wolnelektury.pl/katalog/lektura/template"], + DCNS('identifier.url'): [WLURI.example], DCNS('rights'): [u"Domena publiczna - zm. [OPIS STANU PRAWNEGO TEKSTU]"] })