accept missing dc tags

[librarian.git] / librarian / parser.py

diff --git a/librarian/parser.py b/librarian/parser.py
index 9300aa6..12fffb3 100644 (file)
--- a/librarian/parser.py
+++ b/librarian/parser.py
@@ -3,7 +3,7 @@
 # This file is part of Librarian, licensed under GNU Affero GPLv3 or later.
 # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
 #
 # This file is part of Librarian, licensed under GNU Affero GPLv3 or later.
 # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
 #

-from librarian import ValidationError, NoDublinCore,  ParseError, NoProvider
+from librarian import ValidationError, NoDublinCore,  ParseError

 from librarian import RDFNS, IOFile
 from librarian import dcparser
 
 from librarian import RDFNS, IOFile
 from librarian import dcparser
 


@@ -15,11 +15,13 @@ import os
 import re
 from StringIO import StringIO
 
 import re
 from StringIO import StringIO
 

+

 class WLDocument(object):
     LINE_SWAP_EXPR = re.compile(r'/\s', re.MULTILINE | re.UNICODE)
     provider = None
 
     _edoc = None
 class WLDocument(object):
     LINE_SWAP_EXPR = re.compile(r'/\s', re.MULTILINE | re.UNICODE)
     provider = None
 
     _edoc = None

+

     @property
     def edoc(self):
         if self._edoc is None:
     @property
     def edoc(self):
         if self._edoc is None:


@@ -28,13 +30,14 @@ class WLDocument(object):
                 data = data.decode('utf-8')
             data = data.replace(u'\ufeff', '')
             try:
                 data = data.decode('utf-8')
             data = data.replace(u'\ufeff', '')
             try:

-                parser = etree.XMLParser(remove_blank_text=False)
+                parser = etree.XMLParser()

                 self._edoc = etree.parse(StringIO(data.encode('utf-8')), parser)
             except (ExpatError, XMLSyntaxError, XSLTApplyError), e:
                 raise ParseError(e)
         return self._edoc
 
     _rdf_elem = None
                 self._edoc = etree.parse(StringIO(data.encode('utf-8')), parser)
             except (ExpatError, XMLSyntaxError, XSLTApplyError), e:
                 raise ParseError(e)
         return self._edoc
 
     _rdf_elem = None

+

     @property
     def rdf_elem(self):
         if self._rdf_elem is None:
     @property
     def rdf_elem(self):
         if self._rdf_elem is None:


@@ -45,6 +48,7 @@ class WLDocument(object):
         return self._rdf_elem
 
     _book_info = None
         return self._rdf_elem
 
     _book_info = None

+

     @property
     def book_info(self):
         if not self.parse_dublincore:
     @property
     def book_info(self):
         if not self.parse_dublincore:


@@ -54,17 +58,16 @@ class WLDocument(object):
                     self.rdf_elem, fallbacks=self.meta_fallbacks, strict=self.strict)
         return self._book_info
 
                     self.rdf_elem, fallbacks=self.meta_fallbacks, strict=self.strict)
         return self._book_info
 

-    def __init__(self, iofile, provider=None, 
-            parse_dublincore=True, # shouldn't it be in a subclass?
-            strict=False, # ?
-            meta_fallbacks=None # ?
-            ):
+    def __init__(self, iofile, provider=None, parse_dublincore=True,  # shouldn't it be in a subclass?
+                 strict=False,  # ?
+                 meta_fallbacks=None):  # ?

         self.source = iofile
         self.provider = provider
         self.parse_dublincore = parse_dublincore
         self.strict = strict
         self.meta_fallbacks = meta_fallbacks
         self.source = iofile
         self.provider = provider
         self.parse_dublincore = parse_dublincore
         self.strict = strict
         self.meta_fallbacks = meta_fallbacks

-        if self.edoc.getroot().tag != 'utwor':
+        root_elem = self.edoc.getroot()
+        if root_elem.tag != 'utwor':

             raise ValidationError("Invalid root element. Found '%s', should be 'utwor'" % root_elem.tag)
         if parse_dublincore:
             self.book_info
             raise ValidationError("Invalid root element. Found '%s', should be 'utwor'" % root_elem.tag)
         if parse_dublincore:
             self.book_info


@@ -78,7 +81,6 @@ class WLDocument(object):
         iofile = IOFile.from_filename(xmlfile)
         return cls(iofile, *args, **kwargs)
 
         iofile = IOFile.from_filename(xmlfile)
         return cls(iofile, *args, **kwargs)
 

-

     def swap_endlines(self):
         """Converts line breaks in stanzas into <br/> tags."""
         # only swap inside stanzas
     def swap_endlines(self):
         """Converts line breaks in stanzas into <br/> tags."""
         # only swap inside stanzas


@@ -119,7 +121,7 @@ class WLDocument(object):
                 parts.append(part)
             else:
                 tag, n = match.groups()
                 parts.append(part)
             else:
                 tag, n = match.groups()

-                parts.append("*[%d][name() = '%s']" % (int(n)+1, tag) )
+                parts.append("*[%d][name() = '%s']" % (int(n)+1, tag))

 
         if parts[0] == '.':
             parts[0] = ''
 
         if parts[0] == '.':
             parts[0] = ''


@@ -132,7 +134,7 @@ class WLDocument(object):
     def update_dc(self):
         if self.book_info:
             parent = self.rdf_elem.getparent()
     def update_dc(self):
         if self.book_info:
             parent = self.rdf_elem.getparent()

-            parent.replace( self.rdf_elem, self.book_info.to_etree(parent) )
+            parent.replace(self.rdf_elem, self.book_info.to_etree(parent))

 
     def serialize(self):
         self.update_dc()
 
     def serialize(self):
         self.update_dc()


@@ -145,18 +147,19 @@ class WLDocument(object):
             try:
                 xpath = self.path_to_xpath(key)
                 node = self.edoc.xpath(xpath)[0]
             try:
                 xpath = self.path_to_xpath(key)
                 node = self.edoc.xpath(xpath)[0]

-                repl = etree.fromstring(u"<%s>%s</%s>" %(node.tag, data, node.tag) )
+                repl = etree.fromstring(u"<%s>%s</%s>" % (node.tag, data, node.tag))

                 node.getparent().replace(node, repl)
             except Exception, e:
                 node.getparent().replace(node, repl)
             except Exception, e:

-                unmerged.append( repr( (key, xpath, e) ) )
+                # WTF xpath may be unused; also: too broad except
+                unmerged.append(repr((key, xpath, e)))

 
         return unmerged
 
     def clean_ed_note(self):
         """ deletes forbidden tags from nota_red """
 
 
         return unmerged
 
     def clean_ed_note(self):
         """ deletes forbidden tags from nota_red """
 

-        for node in self.edoc.xpath('|'.join('//nota_red//%s' % tag for tag in
-                    ('pa', 'pe', 'pr', 'pt', 'begin', 'end', 'motyw'))):
+        forbidden_tags = ('pa', 'pe', 'pr', 'pt', 'begin', 'end', 'motyw')
+        for node in self.edoc.xpath('|'.join('//nota_red//%s' % tag for tag in forbidden_tags)):

             tail = node.tail
             node.clear()
             node.tag = 'span'
             tail = node.tail
             node.clear()
             node.tag = 'span'


@@ -194,15 +197,12 @@ class WLDocument(object):
             cover_class = WLCover
         return cover_class(self.book_info, *args, **kwargs).output_file()
 
             cover_class = WLCover
         return cover_class(self.book_info, *args, **kwargs).output_file()
 

-    def save_output_file(self, output_file, output_path=None,
-            output_dir_path=None, make_author_dir=False, ext=None):
+    def save_output_file(self, output_file, output_path=None, output_dir_path=None, make_author_dir=False, ext=None):

         if output_dir_path:
             save_path = output_dir_path
             if make_author_dir:
         if output_dir_path:
             save_path = output_dir_path
             if make_author_dir:

-                save_path = os.path.join(save_path,
-                        unicode(self.book_info.author).encode('utf-8'))
-            save_path = os.path.join(save_path,
-                                self.book_info.uri.slug)
+                save_path = os.path.join(save_path, unicode(self.book_info.author).encode('utf-8'))
+            save_path = os.path.join(save_path, self.book_info.uri.slug)

             if ext:
                 save_path += '.%s' % ext
         else:
             if ext:
                 save_path += '.%s' % ext
         else: