Documents: COinS and Dublin Core tags

1 files changed, 155 insertions, 0 deletions

diff --git a/ishtar_common/models.py b/ishtar_common/models.py
index a5e8e6341..df9fe0c20 100644
--- a/ishtar_common/models.py
+++ b/ishtar_common/models.py
@@ -43,6 +43,8 @@ from ooopy.Transformer import Transformer as OOTransformer
 import ooopy.Transforms as OOTransforms
 import uuid
 import zipfile
+from urllib.parse import urlencode
+from xml.etree import ElementTree as ET
 
 from django import forms
 from django.apps import apps
@@ -4616,6 +4618,10 @@ class Person(Address, Merge, OwnPerms, ValueGetter, MainItem):
         return (self.uuid,)
 
     @property
+    def first_name(self):
+        return self.surname
+
+    @property
     def full_title(self):
         return " ".join(
             [str(getattr(self, attr))
@@ -6014,6 +6020,155 @@ class Document(BaseHistorizedItem, QRCodeItem, OwnPerms, ImageModel,
     def import_get_next_index(cls, context, value):
         context["index"] = cls.get_next_index()
 
+    @property
+    def dublin_core_identifier(self):
+        identifier = None
+        if self.isbn:
+            identifier = self.isbn
+        elif self.issn:
+            identifier = self.issn
+        elif self.associated_url:
+            identifier = self.associated_url
+        elif Site.objects.count():
+            identifier = "http://{}{}".format(
+                Site.objects.all()[0].domain, self.get_absolute_url())
+        return identifier
+
+    def dublin_core_tags(self):
+        if not self.title:
+            return ""
+        tags = [
+            ("link",
+             {"rel": "schema.DC", "href": "http://purl.org/dc/elements/1.1/"}),
+            ("link",
+             {"rel": "schema.DCTERMS", "href": "http://purl.org/dc/terms/"}),
+        ]
+        title = {"name": "DC.title", "content": self.title}
+        tags.append(("meta", title))
+        if self.creation_date:
+            date = {"name": "DC.date", "scheme": "DCTERMS.W3CDTF",
+                    "content": self.creation_date.strftime("%Y-%m-%d")}
+            tags.append(("meta", date))
+        if self.tags.count():
+            content = ", ".join([str(t) for t in self.tags.all()])
+            tg = {"name": "DC.subject", "content": content}
+            tags.append(("meta", tg))
+        if self.description:
+            tags.append(
+                ("meta", {"name": "DC.description",
+                          "content": self.description}))
+        if self.publisher:
+            tags.append(
+                ("meta", {"name": "DC.publisher",
+                          "content": self.publisher.name}))
+        if self.authors.count():
+            content = ", ".join([str(t.person.raw_name) for t in
+                                 self.authors.all()])
+            tags.append(
+                ("meta", {"name": "DC.creator",
+                          "content": content}))
+        if self.source_type:
+            tags.append(
+                ("meta", {"name": "DC.type",
+                          "content": str(self.source_type)}))
+        if self.format_type:
+            tags.append(
+                ("meta", {"name": "DC.format",
+                          "content": str(self.format_type)}))
+        identifier = self.dublin_core_identifier
+        if identifier:
+            tags.append(
+                ("meta", {"name": "DC.identifier",
+                          "content": identifier}))
+        if self.language:
+            lang = self.language.iso_code
+            tags.append(
+                ("meta", {"name": "DC.language",
+                          "content": lang}))
+        if self.licenses.count():
+            licences = ", ".join([str(l) for l in self.licenses.all()])
+            tags.append(
+                ("meta", {"name": "DC.rights",
+                          "content": licences}))
+        src = None
+        if self.source:
+            src = self.source.dublin_core_identifier
+        if src:
+            tags.append(
+                ("meta", {"name": "DC.relation",
+                          "content": src}))
+            tags.append(
+                ("meta", {"name": "DC.source",
+                          "content": src}))
+        elif self.source_free_input:
+            tags.append(
+                ("meta", {"name": "DC.source",
+                          "content": self.source_free_input}))
+        html = ""
+        for tag, attrs in tags:
+            et = ET.Element(tag, attrib=attrs)
+            html += ET.tostring(et, encoding="unicode", method="html")
+        return html
+
+    @property
+    def extra_meta(self):
+        return self.dublin_core_tags()
+
+    def coins_tag(self):
+        if not self.title:
+            return
+        info = [
+            ("url_ver", "Z39.88-2004"),
+            ("ctx_ver", "Z39.88-2004"),
+            ("rft_val_fmt", "info:ofi/fmt:kev:mtx:dc"),
+            ("rft.title", self.title),
+            ("rft.btitle", self.title)
+        ]
+        if self.associated_url:
+            info.append(("rft.identifier", self.associated_url))
+        elif Site.objects.count():
+            info.append(("rft.identifier", "http://{}{}".format(
+                Site.objects.all()[0].domain, self.get_absolute_url())))
+        for author in self.authors.all():
+            person = author.person
+            if not person.raw_name:
+                continue
+            if person.first_name and person.name:
+                info.append(("rft.aulast", person.name))
+                info.append(("rft.aufirst", person.first_name))
+                info.append(("rft.au", "{}+{}".format(person.first_name,
+                                                      person.name)))
+            else:
+                info.append(("rft.au", person.raw_name))
+        if self.source_type:
+            info.append(("rft.type", self.source_type.coins_type))
+            if self.source_type.coins_genre:
+                info.append(("rft.genre", self.source_type.coins_genre))
+        if self.description:
+            info.append(("rft.description", self.description))
+        if self.publisher:
+            info.append(("rft.publisher", self.publisher.name))
+        if self.creation_date:
+            if self.creation_date.day == 1 and self.creation_date.month == 1:
+                info.append(("rft.date", self.creation_date.year))
+            else:
+                info.append(("rft.date",
+                             self.creation_date.strftime("%Y-%m-%d")))
+        if self.source and self.source.title:
+            info.append(("rft.source", self.source.title))
+        elif self.source_free_input:
+            info.append(("rft.source", self.source_free_input))
+        if self.issn:
+            info.append(("rft.issn", self.issn))
+        if self.isbn:
+            info.append(("rft.isbn", self.isbn))
+        if self.licenses.count():
+            licenses = ";".join([str(l) for l in self.licenses.all()])
+            info.append(("rft.rights", licenses))
+        if self.language:
+            info.append(("rft.language", self.language.iso_code))
+        return '<span class="Z3988" title="{}">'.format(urlencode(info))
+
     def save(self, *args, **kwargs):
         no_path_change = 'no_path_change' in kwargs \
                          and kwargs.pop('no_path_change')