Add DataCite's schema and update relationships between databases

docs/datacite.rst

@@ -0,0 +1,158 @@
+DataCite publication data
+=========================
+
+.. Automatically generated file. Do not modify by hand.
+
+.. code:: py
+
+   from alexandria3k.data_sources import datacite
+
+.. autoclass:: data_sources.datacite.Datacite
+   :members: query, populate
+
+Generated schema
+----------------
+
+.. code:: sql
+
+    CREATE TABLE dc_works(
+      id,
+      container_id,
+      identifier,
+      identifier_type,
+      doi,
+      publisher,
+      publication_year,
+      resource_type,
+      resource_type_general,
+      language,
+      sizes,
+      formats,
+      schema_version,
+      metadata_version,
+      url,
+      created,
+      registered,
+      published,
+      updated
+    );
+
+    CREATE TABLE dc_work_creators(
+      id,
+      container_id,
+      work_id,
+      name,
+      name_type,
+      given_name,
+      family_name
+    );
+
+    CREATE TABLE dc_creator_name_identifiers(
+      creator_id,
+      container_id,
+      name_identifier,
+      name_identifier_scheme,
+      scheme_uri
+    );
+
+    CREATE TABLE dc_creator_affiliations(
+      creator_id,
+      container_id,
+      name
+    );
+
+    CREATE TABLE dc_work_titles(
+      work_id,
+      container_id,
+      title,
+      title_type
+    );
+
+    CREATE TABLE dc_work_subjects(
+      work_id,
+      container_id,
+      subject,
+      subject_scheme,
+      scheme_uri,
+      value_uri
+    );
+
+    CREATE TABLE dc_work_contributors(
+      id,
+      container_id,
+      work_id,
+      contributor_type,
+      name,
+      family_name,
+      given_name
+    );
+
+    CREATE TABLE dc_contributor_name_identifiers(
+      contributor_id,
+      container_id,
+      name_identifier,
+      name_identifier_scheme,
+      scheme_uri
+    );
+
+    CREATE TABLE dc_contributor_affiliations(
+      contributor_id,
+      container_id,
+      name
+    );
+
+    CREATE TABLE dc_work_dates(
+      work_id,
+      container_id,
+      date,
+      date_type
+    );
+
+    CREATE TABLE dc_work_related_identifiers(
+      work_id,
+      container_id,
+      related_identifier,
+      related_identifier_type,
+      relation_type,
+      related_metadata_scheme,
+      scheme_uri,
+      scheme_type
+    );
+
+    CREATE TABLE dc_work_rights(
+      work_id,
+      container_id,
+      rights,
+      lang,
+      rights_uri,
+      rights_identifier,
+      rights_identifier_scheme,
+      scheme_uri
+    );
+
+    CREATE TABLE dc_work_descriptions(
+      work_id,
+      container_id,
+      description,
+      description_type
+    );
+
+    CREATE TABLE dc_work_geo_locations(
+      work_id,
+      container_id,
+      geo_location_place,
+      geo_location_point,
+      geo_location_box
+    );
+
+    CREATE TABLE dc_work_funding_references(
+      work_id,
+      container_id,
+      funder_name,
+      funder_identifier,
+      funder_identifier_type,
+      award_number,
+      award_uri,
+      award_title
+    );
+

docs/dev.rst

@@ -180,7 +180,7 @@ Adding a new data source plugin to *alexandria3k* involves the following steps.
   downloading its data.
   The data source's name for the CLI is all lowercase (e.g. ``datacite``),
   for the class name with an initial capital (e.g. ``Datacite``), and in
-  the documentation and schema's as formally spelled (e.g. ``DataCtire``).
+  the documentation and schema's as formally spelled (e.g. ``DataCite``).
   All table rows have an ``id`` field, with a unique identifier for that
   table across all table rows.
   As detail table indices are reset for each record, the identifier

docs/issn_subject_codes.rst

@@ -0,0 +1,23 @@
+ISSN Subject Codes data processing
+==================================
+
+.. Automatically generated file. Do not modify by hand.
+
+.. code:: py
+
+   from alexandria3k.data_sources import issn_subject_codes
+
+.. autoclass:: data_sources.issn_subject_codes.IssnSubjectCodes
+   :members: query, populate
+
+Generated schema
+----------------
+
+.. code:: sql
+
+    CREATE TABLE issn_subject_codes(
+      id INTEGER PRIMARY KEY,
+      issn,
+      subject_code INTEGER
+    );
+

docs/schema/.gitignore

@@ -5,3 +5,4 @@ other.pdf
 ror.pdf
 uspto.pdf
 pubmed.pdf
+datacite.pdf

docs/schema/datacite.dot

@@ -1,18 +1,21 @@
 	node [fillcolor="#00b0e1", fontcolor="#000000"];
 	dc_works;
-	dc_work_geo_locations;
-	dc_work_funding_references;
-	dc_work_titles;
-	dc_creator_name_identifiers;
-	dc_work_contributors;
-	dc_work_sizes;
-	dc_work_subjects;
-	dc_work_descriptions;
-	dc_contributor_name_identifiers;
-	dc_work_formats;
-	dc_work_related_identifiers;
-	dc_work_dates;
-	dc_work_rights;
-	dc_contributor_affiliations;
 	dc_work_creators;
-	dc_creator_affiliations;
+	dc_work_contributors;
+
+	dc_works -> dc_work_creators [headlabel="1…N", taillabel="1"];
+	dc_works -> dc_work_titles [headlabel="1…N", taillabel="1"];
+
+	edge [headlabel="0…N", taillabel="1"];
+	dc_work_creators -> dc_creator_name_identifiers;
+	dc_work_creators -> dc_creator_affiliations;
+	dc_works -> dc_work_subjects;
+	dc_works -> dc_work_contributors;
+	dc_work_contributors -> dc_contributor_name_identifiers;
+	dc_work_contributors -> dc_contributor_affiliations;
+	dc_works -> dc_work_dates;
+	dc_works -> dc_work_related_identifiers;
+	dc_works -> dc_work_rights;
+	dc_works -> dc_work_geo_locations;
+	dc_works -> dc_work_descriptions; 
+	dc_works -> dc_work_funding_references;