CRLF in epub

[librarian.git] / librarian / dcparser.py

diff --git a/librarian/dcparser.py b/librarian/dcparser.py
index 12bb24f..f8dfaf9 100644 (file)
--- a/librarian/dcparser.py
+++ b/librarian/dcparser.py
@@ -12,13 +12,14 @@ from librarian.util import roman_to_int
 from librarian import (ValidationError, NoDublinCore, ParseError, DCNS, RDFNS,
                        XMLNS, WLURI, WLNS, PLMETNS)
 
 from librarian import (ValidationError, NoDublinCore, ParseError, DCNS, RDFNS,
                        XMLNS, WLURI, WLNS, PLMETNS)
 

-import lxml.etree as etree # ElementTree API using libxml2
+import lxml.etree as etree  # ElementTree API using libxml2

 from lxml.etree import XMLSyntaxError
 
 
 class TextPlus(unicode):
     pass
 
 from lxml.etree import XMLSyntaxError
 
 
 class TextPlus(unicode):
     pass
 

+

 class DatePlus(date):
     pass
 
 class DatePlus(date):
     pass
 


@@ -34,18 +35,18 @@ class Person(object):
 
     @classmethod
     def from_text(cls, text):
 
     @classmethod
     def from_text(cls, text):

-        parts = [ token.strip() for token in text.split(',') ]
+        parts = [token.strip() for token in text.split(',')]

         if len(parts) == 1:
             surname = parts[0]
             names = []
         elif len(parts) != 2:
         if len(parts) == 1:
             surname = parts[0]
             names = []
         elif len(parts) != 2:

-            raise ValueError("Invalid person name. There should be at most one comma: \"%s\"." % text)
+            raise ValueError("Invalid person name. There should be at most one comma: \"%s\"." % text.encode('utf-8'))

         else:
             surname = parts[0]
             if len(parts[1]) == 0:
                 # there is no non-whitespace data after the comma
                 raise ValueError("Found a comma, but no names given: \"%s\" -> %r." % (text, parts))
         else:
             surname = parts[0]
             if len(parts[1]) == 0:
                 # there is no non-whitespace data after the comma
                 raise ValueError("Found a comma, but no names given: \"%s\" -> %r." % (text, parts))

-            names = [ name for name in parts[1].split() if len(name) ] # all non-whitespace tokens
+            names = parts[1].split()

         return cls(surname, *names)
 
     def readable(self):
         return cls(surname, *names)
 
     def readable(self):


@@ -69,6 +70,7 @@ class Person(object):
     def __repr__(self):
         return 'Person(last_name=%r, first_names=*%r)' % (self.last_name, self.first_names)
 
     def __repr__(self):
         return 'Person(last_name=%r, first_names=*%r)' % (self.last_name, self.first_names)
 

+

 def as_date(text):
     """Dates for digitization of pictures. It seems we need the following:
 ranges:                '1350-1450',
 def as_date(text):
     """Dates for digitization of pictures. It seems we need the following:
 ranges:                '1350-1450',


@@ -81,7 +83,8 @@ for now we will translate this to some single date losing information of course.
     """
     try:
         # check out the "N. poł X w." syntax
     """
     try:
         # check out the "N. poł X w." syntax

-        if isinstance(text, str): text = text.decode("utf-8")
+        if isinstance(text, str):
+            text = text.decode("utf-8")

 
         century_format = u"(?:([12]) *poł[.]? +)?([MCDXVI]+) *w[.,]*(?: *l[.]? *([0-9]+))?"
         vague_format = u"(?:po *|ok. *)?([0-9]{4})(-[0-9]{2}-[0-9]{2})?"
 
         century_format = u"(?:([12]) *poł[.]? +)?([MCDXVI]+) *w[.,]*(?: *l[.]? *([0-9]+))?"
         vague_format = u"(?:po *|ok. *)?([0-9]{4})(-[0-9]{2}-[0-9]{2})?"


@@ -114,18 +117,22 @@ for now we will translate this to some single date losing information of course.
     except ValueError, e:
         raise ValueError("Unrecognized date format. Try YYYY-MM-DD or YYYY.")
 
     except ValueError, e:
         raise ValueError("Unrecognized date format. Try YYYY-MM-DD or YYYY.")
 

+

 def as_person(text):
     return Person.from_text(text)
 
 def as_person(text):
     return Person.from_text(text)
 

+

 def as_unicode(text):
     if isinstance(text, unicode):
         return text
     else:
         return TextPlus(text.decode('utf-8'))
 
 def as_unicode(text):
     if isinstance(text, unicode):
         return text
     else:
         return TextPlus(text.decode('utf-8'))
 

+

 def as_wluri_strict(text):
     return WLURI.strict(text)
 
 def as_wluri_strict(text):
     return WLURI.strict(text)
 

+

 class Field(object):
     def __init__(self, uri, attr_name, validator=as_unicode, strict=None, multiple=False, salias=None, **kwargs):
         self.uri = uri
 class Field(object):
     def __init__(self, uri, attr_name, validator=as_unicode, strict=None, multiple=False, salias=None, **kwargs):
         self.uri = uri


@@ -135,7 +142,7 @@ class Field(object):
         self.multiple = multiple
         self.salias = salias
 
         self.multiple = multiple
         self.salias = salias
 

-        self.required = kwargs.get('required', True) and not kwargs.has_key('default')
+        self.required = kwargs.get('required', True) and 'default' not in kwargs

         self.default = kwargs.get('default', [] if multiple else [None])
 
     def validate_value(self, val, strict=False):
         self.default = kwargs.get('default', [] if multiple else [None])
 
     def validate_value(self, val, strict=False):


@@ -173,7 +180,7 @@ class Field(object):
     def validate(self, fdict, fallbacks=None, strict=False):
         if fallbacks is None:
             fallbacks = {}
     def validate(self, fdict, fallbacks=None, strict=False):
         if fallbacks is None:
             fallbacks = {}

-        if not fdict.has_key(self.uri):
+        if self.uri not in fdict:

             if not self.required:
                 # Accept single value for single fields and saliases.
                 if self.name in fallbacks:
             if not self.required:
                 # Accept single value for single fields and saliases.
                 if self.name in fallbacks:


@@ -199,7 +206,7 @@ class Field(object):
 
 
 class DCInfo(type):
 
 
 class DCInfo(type):

-    def __new__(meta, classname, bases, class_dict):
+    def __new__(mcs, classname, bases, class_dict):

         fields = list(class_dict['FIELDS'])
 
         for base in bases[::-1]:
         fields = list(class_dict['FIELDS'])
 
         for base in bases[::-1]:


@@ -211,40 +218,40 @@ class DCInfo(type):
                         fields.insert(0, field)
 
         class_dict['FIELDS'] = tuple(fields)
                         fields.insert(0, field)
 
         class_dict['FIELDS'] = tuple(fields)

-        return super(DCInfo, meta).__new__(meta, classname, bases, class_dict)
+        return super(DCInfo, mcs).__new__(mcs, classname, bases, class_dict)

 
 
 class WorkInfo(object):
     __metaclass__ = DCInfo
 
     FIELDS = (
 
 
 class WorkInfo(object):
     __metaclass__ = DCInfo
 
     FIELDS = (

-        Field( DCNS('creator'), 'authors', as_person, salias='author', multiple=True),
-        Field( DCNS('title'), 'title'),
-        Field( DCNS('type'), 'type', required=False, multiple=True),
-
-        Field( DCNS('contributor.editor'), 'editors', \
-            as_person, salias='editor', multiple=True, default=[]),
-        Field( DCNS('contributor.technical_editor'), 'technical_editors',
-            as_person, salias='technical_editor', multiple=True, default=[]),
-        Field( DCNS('contributor.funding'), 'funders',
-            salias='funder', multiple=True, default=[]),
-        Field( DCNS('contributor.thanks'), 'thanks', required=False),
-
-        Field( DCNS('date'), 'created_at', as_date),
-        Field( DCNS('date.pd'), 'released_to_public_domain_at', as_date, required=False),
-        Field( DCNS('publisher'), 'publisher'),
-
-        Field( DCNS('language'), 'language'),
-        Field( DCNS('description'), 'description', required=False),
-
-        Field( DCNS('source'), 'source_name', required=False),
-        Field( DCNS('source.URL'), 'source_url', required=False),
-        Field( DCNS('identifier.url'), 'url', WLURI, strict=as_wluri_strict),
-        Field( DCNS('rights.license'), 'license', required=False),
-        Field( DCNS('rights'), 'license_description'),
-
-        Field( PLMETNS('digitisationSponsor'), 'sponsors', multiple=True, default=[]),
-        Field( WLNS('digitisationSponsorNote'), 'sponsor_note', required=False),
+        Field(DCNS('creator'), 'authors', as_person, salias='author', multiple=True),
+        Field(DCNS('title'), 'title'),
+        Field(DCNS('type'), 'type', required=False, multiple=True),
+
+        Field(DCNS('contributor.editor'), 'editors',
+              as_person, salias='editor', multiple=True, required=False),
+        Field(DCNS('contributor.technical_editor'), 'technical_editors',
+              as_person, salias='technical_editor', multiple=True, required=False),
+        Field(DCNS('contributor.funding'), 'funders', salias='funder', multiple=True, required=False),
+        Field(DCNS('contributor.thanks'), 'thanks', required=False),
+
+        Field(DCNS('date'), 'created_at'),
+        Field(DCNS('date.pd'), 'released_to_public_domain_at', as_date, required=False),
+        Field(DCNS('publisher'), 'publisher', multiple=True),
+
+        Field(DCNS('language'), 'language'),
+        Field(DCNS('description'), 'description', required=False),
+
+        Field(DCNS('source'), 'source_name', required=False),
+        Field(DCNS('source.URL'), 'source_url', required=False),
+        Field(DCNS('identifier.url'), 'url', WLURI, strict=as_wluri_strict),
+        Field(DCNS('rights.license'), 'license', required=False),
+        Field(DCNS('rights'), 'license_description'),
+
+        Field(PLMETNS('digitisationSponsor'), 'sponsors', multiple=True, required=False),
+        Field(WLNS('digitisationSponsorNote'), 'sponsor_note', required=False),
+        Field(WLNS('developmentStage'), 'stage', required=False),

     )
 
     @classmethod
     )
 
     @classmethod


@@ -303,6 +310,10 @@ class WorkInfo(object):
                     text = text.decode('utf-8')
                 val = TextPlus(text)
                 val.lang = e.attrib.get(XMLNS('lang'), lang)
                     text = text.decode('utf-8')
                 val = TextPlus(text)
                 val.lang = e.attrib.get(XMLNS('lang'), lang)

+                if e.tag == 'meta':
+                    meta_id = e.attrib.get('id')
+                    if meta_id and meta_id.endswith('-id'):
+                        field_dict[meta_id] = [val.replace('ISBN-', 'ISBN ')]

             else:
                 val = e.text
             fv.append(val)
             else:
                 val = e.text
             fv.append(val)


@@ -319,11 +330,11 @@ class WorkInfo(object):
         self.fmap = {}
 
         for field in self.FIELDS:
         self.fmap = {}
 
         for field in self.FIELDS:

-            value = field.validate(dc_fields, fallbacks=fallbacks,
-                            strict=strict)
+            value = field.validate(dc_fields, fallbacks=fallbacks, strict=strict)

             setattr(self, 'prop_' + field.name, value)
             self.fmap[field.name] = field
             setattr(self, 'prop_' + field.name, value)
             self.fmap[field.name] = field

-            if field.salias: self.fmap[field.salias] = field
+            if field.salias:
+                self.fmap[field.salias] = field

 
     def __getattribute__(self, name):
         try:
 
     def __getattribute__(self, name):
         try:


@@ -331,7 +342,7 @@ class WorkInfo(object):
             value = object.__getattribute__(self, 'prop_'+field.name)
             if field.name == name:
                 return value
             value = object.__getattribute__(self, 'prop_'+field.name)
             if field.name == name:
                 return value

-            else: # singular alias
+            else:  # singular alias

                 if not field.multiple:
                     raise "OUCH!! for field %s" % name
 
                 if not field.multiple:
                     raise "OUCH!! for field %s" % name
 


@@ -344,7 +355,7 @@ class WorkInfo(object):
             field = object.__getattribute__(self, 'fmap')[name]
             if field.name == name:
                 object.__setattr__(self, 'prop_'+field.name, newvalue)
             field = object.__getattribute__(self, 'fmap')[name]
             if field.name == name:
                 object.__setattr__(self, 'prop_'+field.name, newvalue)

-            else: # singular alias
+            else:  # singular alias

                 if not field.multiple:
                     raise "OUCH! while setting field %s" % name
 
                 if not field.multiple:
                     raise "OUCH! while setting field %s" % name
 


@@ -356,13 +367,13 @@ class WorkInfo(object):
         """Update using field_dict. Verify correctness, but don't check if all
         required fields are present."""
         for field in self.FIELDS:
         """Update using field_dict. Verify correctness, but don't check if all
         required fields are present."""
         for field in self.FIELDS:

-            if field_dict.has_key(field.name):
+            if field.name in field_dict:

                 setattr(self, field.name, field_dict[field.name])
 
                 setattr(self, field.name, field_dict[field.name])
 

-    def to_etree(self, parent = None):
+    def to_etree(self, parent=None):

         """XML representation of this object."""
         """XML representation of this object."""

-        #etree._namespace_map[str(self.RDF)] = 'rdf'
-        #etree._namespace_map[str(self.DC)] = 'dc'
+        # etree._namespace_map[str(self.RDF)] = 'rdf'
+        # etree._namespace_map[str(self.DC)] = 'dc'

 
         if parent is None:
             root = etree.Element(RDFNS('RDF'))
 
         if parent is None:
             root = etree.Element(RDFNS('RDF'))


@@ -378,7 +389,8 @@ class WorkInfo(object):
             v = getattr(self, field.name, None)
             if v is not None:
                 if field.multiple:
             v = getattr(self, field.name, None)
             if v is not None:
                 if field.multiple:

-                    if len(v) == 0: continue
+                    if len(v) == 0:
+                        continue

                     for x in v:
                         e = etree.Element(field.uri)
                         if x is not None:
                     for x in v:
                         e = etree.Element(field.uri)
                         if x is not None:


@@ -392,16 +404,16 @@ class WorkInfo(object):
         return root
 
     def serialize(self):
         return root
 
     def serialize(self):

-        rdf = {}
-        rdf['about'] = { 'uri': RDFNS('about'), 'value': self.about }
+        rdf = {'about': {'uri': RDFNS('about'), 'value': self.about}}

 
         dc = {}
         for field in self.FIELDS:
             v = getattr(self, field.name, None)
             if v is not None:
                 if field.multiple:
 
         dc = {}
         for field in self.FIELDS:
             v = getattr(self, field.name, None)
             if v is not None:
                 if field.multiple:

-                    if len(v) == 0: continue
-                    v = [ unicode(x) for x in v if x is not None ]
+                    if len(v) == 0:
+                        continue
+                    v = [unicode(x) for x in v if x is not None]

                 else:
                     v = unicode(v)
 
                 else:
                     v = unicode(v)
 


@@ -416,44 +428,48 @@ class WorkInfo(object):
 
             if v is not None:
                 if field.multiple:
 
             if v is not None:
                 if field.multiple:

-                    if len(v) == 0: continue
-                    v = [ unicode(x) for x in v if x is not None ]
+                    if len(v) == 0:
+                        continue
+                    v = [unicode(x) for x in v if x is not None]

                 else:
                     v = unicode(v)
                 result[field.name] = v
 
             if field.salias:
                 v = getattr(self, field.salias)
                 else:
                     v = unicode(v)
                 result[field.name] = v
 
             if field.salias:
                 v = getattr(self, field.salias)

-                if v is not None: result[field.salias] = unicode(v)
+                if v is not None:
+                    result[field.salias] = unicode(v)

 
         return result
 
 
 class BookInfo(WorkInfo):
     FIELDS = (
 
         return result
 
 
 class BookInfo(WorkInfo):
     FIELDS = (

-        Field( DCNS('audience'), 'audiences', salias='audience', multiple=True,
-                required=False),
-
-        Field( DCNS('subject.period'), 'epochs', salias='epoch', multiple=True,
-                required=False),
-        Field( DCNS('subject.type'), 'kinds', salias='kind', multiple=True,
-                required=False),
-        Field( DCNS('subject.genre'), 'genres', salias='genre', multiple=True,
-                required=False),
-                
-        Field( DCNS('contributor.translator'), 'translators', \
-            as_person,  salias='translator', multiple=True, default=[]),
-        Field( DCNS('relation.hasPart'), 'parts', 
-            WLURI, strict=as_wluri_strict, multiple=True, required=False),
-        Field( DCNS('relation.isVariantOf'), 'variant_of', 
-            WLURI, strict=as_wluri_strict, required=False),
-
-        Field( DCNS('relation.coverImage.url'), 'cover_url', required=False),
-        Field( DCNS('relation.coverImage.attribution'), 'cover_by', required=False),
-        Field( DCNS('relation.coverImage.source'), 'cover_source', required=False),
+        Field(DCNS('audience'), 'audiences', salias='audience', multiple=True, required=False),
+
+        Field(DCNS('subject.period'), 'epochs', salias='epoch', multiple=True, required=False),
+        Field(DCNS('subject.type'), 'kinds', salias='kind', multiple=True, required=False),
+        Field(DCNS('subject.genre'), 'genres', salias='genre', multiple=True, required=False),
+
+        Field(DCNS('subject.location'), 'location', required=False),
+
+        Field(DCNS('contributor.translator'), 'translators',
+              as_person,  salias='translator', multiple=True, required=False),
+        Field(DCNS('relation.hasPart'), 'parts', WLURI, strict=as_wluri_strict, multiple=True, required=False),
+        Field(DCNS('relation.isVariantOf'), 'variant_of', WLURI, strict=as_wluri_strict, required=False),
+
+        Field(DCNS('relation.coverImage.url'), 'cover_url', required=False),
+        Field(DCNS('relation.coverImage.attribution'), 'cover_by', required=False),
+        Field(DCNS('relation.coverImage.source'), 'cover_source', required=False),

         # WLCover-specific.
         # WLCover-specific.

-        Field( WLNS('coverBarColor'), 'cover_bar_color', required=False),
-        Field( WLNS('coverBoxPosition'), 'cover_box_position', required=False),
+        Field(WLNS('coverBarColor'), 'cover_bar_color', required=False),
+        Field(WLNS('coverBoxPosition'), 'cover_box_position', required=False),
+        Field(WLNS('coverClass'), 'cover_class', default=['default']),
+        Field('pdf-id',  'isbn_pdf',  required=False),
+        Field('epub-id', 'isbn_epub', required=False),
+        Field('mobi-id', 'isbn_mobi', required=False),
+        Field('txt-id',  'isbn_txt',  required=False),
+        Field('html-id', 'isbn_html', required=False),

     )
 
 
     )