From 901cf998ce7d8f896cf5d609719b1defd96d01d4 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 29 Jan 2020 16:00:03 -0800
Subject: first implementation of ES file schema

Includes a trivial test and transform, but not any workers or doc
updates.
---
 extra/elasticsearch/file_schema.json            | 46 +++++++++++++++++++++++++
 python/fatcat_tools/transforms/__init__.py      |  2 +-
 python/fatcat_tools/transforms/elasticsearch.py | 45 ++++++++++++++++++++++++
 python/tests/transform_tests.py                 | 25 ++++++++++++--
 4 files changed, 115 insertions(+), 3 deletions(-)
 create mode 100644 extra/elasticsearch/file_schema.json

diff --git a/extra/elasticsearch/file_schema.json b/extra/elasticsearch/file_schema.json
new file mode 100644
index 00000000..66d81e0b
--- /dev/null
+++ b/extra/elasticsearch/file_schema.json
@@ -0,0 +1,46 @@
+{
+"settings": {
+    "index": {
+        "analysis": {
+            "analyzer": {
+                "default": {
+                    "type": "custom",
+                    "tokenizer": "standard",
+                    "filter": [ "lowercase", "asciifolding" ]
+                }
+            }
+        }
+    }
+},
+"mappings": {
+    "changelog": {
+        "properties": {
+            "ident":            { "type": "keyword", "doc_values": false },
+            "state":            { "type": "keyword" },
+            "revision":         { "type": "keyword", "doc_values": false },
+
+            "release_ids":      { "type": "keyword", "doc_values": false },
+            "release_count":    { "type": "integer" },
+            "mimetype":         { "type": "keyword" },
+            "size_bytes":       { "type": "integer" },
+            "sha1":             { "type": "keyword", "doc_values": false },
+            "sha256":           { "type": "keyword", "doc_values": false },
+            "md5":              { "type": "keyword", "doc_values": false },
+
+            "domains":          { "type": "keyword" },
+            "hosts":            { "type": "keyword" },
+            "rels":             { "type": "keyword" },
+            "in_ia":            { "type": "boolean" },
+
+            "release_id":       { "type": "alias", "path": "release_ids" },
+            "sha1hex":          { "type": "alias", "path": "sha1hex" },
+            "sha256hex":        { "type": "alias", "path": "sha256hex" },
+            "md5hex":           { "type": "alias", "path": "md5hex" },
+            "size":             { "type": "alias", "path": "size_bytes" },
+            "domain":           { "type": "alias", "path": "domains" },
+            "host":             { "type": "alias", "path": "host" },
+            "rel":              { "type": "alias", "path": "rel" }
+        }
+    }
+}
+}
diff --git a/python/fatcat_tools/transforms/__init__.py b/python/fatcat_tools/transforms/__init__.py
index 6a4b1bba..3f4700ff 100644
--- a/python/fatcat_tools/transforms/__init__.py
+++ b/python/fatcat_tools/transforms/__init__.py
@@ -1,5 +1,5 @@
 
 from .entities import entity_to_dict, entity_from_json, entity_from_dict
-from .elasticsearch import release_to_elasticsearch, container_to_elasticsearch, changelog_to_elasticsearch
+from .elasticsearch import release_to_elasticsearch, container_to_elasticsearch, changelog_to_elasticsearch, file_to_elasticsearch
 from .csl import release_to_csl, citeproc_csl
 from .ingest import release_ingest_request
diff --git a/python/fatcat_tools/transforms/elasticsearch.py b/python/fatcat_tools/transforms/elasticsearch.py
index 3a53db4d..8141a8b9 100644
--- a/python/fatcat_tools/transforms/elasticsearch.py
+++ b/python/fatcat_tools/transforms/elasticsearch.py
@@ -357,3 +357,48 @@ def changelog_to_elasticsearch(entity):
     #t['deleted'] = deleted
     #t['total'] = created + updated + deleted
     return t
+
+
+def file_to_elasticsearch(entity):
+    """
+    Converts from an entity model/schema to elasticsearch oriented schema.
+
+    Returns: dict
+    Raises exception on error (never returns None)
+    """
+
+    if entity.state in ('redirect', 'deleted'):
+        return dict(
+            ident = entity.ident,
+            state = entity.state,
+        )
+    elif entity.state != 'active':
+        raise ValueError("Unhandled entity state: {}".format(entity.state))
+
+    # First, the easy ones (direct copy)
+    t = dict(
+        ident = entity.ident,
+        state = entity.state,
+        revision = entity.revision,
+        release_ids = entity.release_ids,
+        release_count = len(entity.release_ids),
+        mimetype = entity.mimetype,
+        size_bytes = entity.size,
+        sha1 = entity.sha1,
+        sha256 = entity.sha256,
+        md5 = entity.md5,
+        rel = [u.rel for u in entity.urls],
+    )
+
+    # TODO: domain, hosts (from urls; use proper urlcanon)
+    t['rel'] = list(set([u.rel for u in entity.urls]))
+    t['host'] = []
+    t['domain'] = []
+
+    in_ia = False
+    for u in entity.urls:
+        if '://archive.org/' in u.url or '://web.archive.org/' in u.url:
+            in_ia = True
+    t['in_ia'] = bool(in_ia)
+
+    return t
diff --git a/python/tests/transform_tests.py b/python/tests/transform_tests.py
index f254e117..7b583ac4 100644
--- a/python/tests/transform_tests.py
+++ b/python/tests/transform_tests.py
@@ -7,6 +7,7 @@ from fixtures import api
 from import_journal_metadata import journal_metadata_importer
 
 from import_crossref import crossref_importer
+from import_matched import matched_importer
 
 def test_basic_elasticsearch_convert(crossref_importer):
     with open('tests/files/crossref-works.single.json', 'r') as f:
@@ -72,14 +73,34 @@ def test_rich_elasticsearch_convert():
     assert es['ref_count'] == 2
     assert es['ref_linked_count'] == 1
 
-def test_elasticsearch_from_json():
+def test_elasticsearch_release_from_json():
     r = entity_from_json(open('./tests/files/math_universe.json', 'r').read(), ReleaseEntity)
     release_to_elasticsearch(r)
 
-def test_elasticsearch_container_convert(journal_metadata_importer):
+def test_elasticsearch_container_transform(journal_metadata_importer):
     with open('tests/files/journal_metadata.sample.json', 'r') as f:
         raw = json.loads(f.readline())
         c = journal_metadata_importer.parse_record(raw)
     c.state = 'active'
     es = container_to_elasticsearch(c)
     assert es['publisher'] == c.publisher
+
+def test_elasticsearch_file_transform(matched_importer):
+    with open('tests/files/example_matched.json', 'r') as f:
+        raw = json.loads(f.readline())
+        f = matched_importer.parse_record(raw)
+
+    f.state = 'active'
+    es = file_to_elasticsearch(f)
+    assert es['sha1'] == f.sha1
+    assert es['sha256'] == f.sha256
+    assert es['md5'] == f.md5
+    assert es['size_bytes'] == f.size
+    assert es['mimetype'] == f.mimetype
+    assert es['in_ia'] == True
+    assert 'publisher' in es['rel']
+
+    # XXX: implement hosts and domain parsing with urlcanon
+    #assert 'journals.plos.org' in es['host']
+    #assert 'plos.org' in es['domain']
+
-- 
cgit v1.2.3


From 8e8b447a1d142b7815498ffa02263c34207973b4 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 29 Jan 2020 16:21:13 -0800
Subject: container ES schema changes

---
 extra/elasticsearch/container_schema.json       | 33 ++++++++++++++----------
 python/fatcat_tools/transforms/elasticsearch.py | 34 +++++++++++++------------
 2 files changed, 38 insertions(+), 29 deletions(-)

diff --git a/extra/elasticsearch/container_schema.json b/extra/elasticsearch/container_schema.json
index b0a47e85..3be261a2 100644
--- a/extra/elasticsearch/container_schema.json
+++ b/extra/elasticsearch/container_schema.json
@@ -27,13 +27,17 @@
 "mappings": {
     "container": {
         "properties": {
-            "ident":          { "type": "keyword" },
+            "ident":          { "type": "keyword", "doc_values": false },
             "state":          { "type": "keyword" },
-            "revision":       { "type": "keyword" },
-            "name":           { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" },
-            "publisher":      { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" },
+            "revision":       { "type": "keyword", "doc_values": false },
+            "name":           { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
+            "original_name":  { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
+            "publisher":      { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
+            "abbrev":         { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
+            "aliases":        { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
             "container_type": { "type": "keyword" },
             "issnl":          { "type": "keyword" },
+            "issns":          { "type": "keyword" },
             "wikidata_qid":   { "type": "keyword" },
             "country":        { "type": "keyword" },
             "region":         { "type": "keyword" },
@@ -43,15 +47,17 @@
             "first_year":     { "type": "integer" },
             "last_year":      { "type": "integer" },
 
-            "in_doaj":        { "type": "boolean" },
-            "in_road":        { "type": "boolean" },
-            "in_doi":         { "type": "boolean" },
-            "in_sherpa_romeo":{ "type": "boolean" },
-            "is_oa":          { "type": "boolean" },
-            "is_longtail_oa": { "type": "boolean" },
-            "any_kbart":      { "type": "boolean" },
-            "any_jstor":      { "type": "boolean" },
-            "any_ia_sim":        { "type": "boolean" },
+
+            "biblio":         { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" },
+
+            "in_doaj":              { "type": "boolean" },
+            "in_road":              { "type": "boolean" },
+            "is_oa":                { "type": "boolean" },
+            "is_longtail_oa":       { "type": "boolean" },
+            "any_kbart":            { "type": "boolean" },
+            "any_jstor":            { "type": "boolean" },
+            "any_ia_sim":           { "type": "boolean" },
+            "sherpa_romeo_color":   { "type": "keyword" },
 
             "releases_total": { "type": "integer" },
             "releases_kbart": { "type": "integer" },
@@ -64,6 +70,7 @@
 
             "year":           { "type": "alias", "path": "first_year" },
             "type":           { "type": "alias", "path": "container_type" },
+            "issn":           { "type": "alias", "path": "issns" },
             "oa":             { "type": "alias", "path": "is_oa" },
             "longtail":       { "type": "alias", "path": "is_longtail_oa" }
         }
diff --git a/python/fatcat_tools/transforms/elasticsearch.py b/python/fatcat_tools/transforms/elasticsearch.py
index 8141a8b9..edc68748 100644
--- a/python/fatcat_tools/transforms/elasticsearch.py
+++ b/python/fatcat_tools/transforms/elasticsearch.py
@@ -257,23 +257,24 @@ def container_to_elasticsearch(entity, force_bool=True):
         wikidata_qid = entity.wikidata_qid,
     )
 
-    # TODO: region, discipline
-    # TODO: single primary language?
     if not entity.extra:
         entity.extra = dict()
-    for key in ('country', 'languages', 'mimetypes', 'first_year', 'last_year'):
+    for key in ('country', 'languages', 'mimetypes', 'original_name',
+                'first_year', 'last_year', 'aliases', 'abbrev', 'region',
+                'discipline'):
         if entity.extra.get(key):
             t[key] = entity.extra[key]
 
+    t['issns'] = []
+    if entity.issnl:
+        t['issns'].append(entity.issnl)
+    for key in ('issnp', 'issne'):
+        if entity.extra.get(key):
+            t['issns'].append(entity.extra[key])
+
     in_doaj = None
     in_road = None
-    # TODO: not currently implemented
-    in_doi = None
-    # TODO: would be nice to have 'in_doaj_works', or maybe just "any_pid"
-    #in_doaj_works = None
-    in_sherpa_romeo = None
     is_oa = None
-    # TODO: not actually set/stored anywhere?
     is_longtail_oa = None
     any_kbart = None
     any_jstor = None
@@ -295,8 +296,9 @@ def container_to_elasticsearch(entity, force_bool=True):
     if extra.get('default_license'):
         if extra['default_license'].startswith('CC-'):
             is_oa = True
+    t['sherpa_romeo_color'] = None
     if extra.get('sherpa_romeo'):
-        in_sherpa_romeo = True
+        t['sherpa_romeo_color'] = extra['sherpa_romeo'].get('color')
         if extra['sherpa_romeo'].get('color') == 'white':
             is_oa = False
     if extra.get('kbart'):
@@ -306,21 +308,21 @@ def container_to_elasticsearch(entity, force_bool=True):
     if extra.get('ia'):
         if extra['ia'].get('sim'):
             any_ia_sim = True
+        if extra['ia'].get('longtail_oa'):
+            is_longtail_oa = True
     t['is_superceded'] = bool(extra.get('superceded'))
 
     t['in_doaj'] = bool(in_doaj)
     t['in_road'] = bool(in_road)
-    t['in_sherpa_romeo'] = bool(in_sherpa_romeo)
     t['any_kbart'] = bool(any_kbart)
-    t['is_longtail_oa'] = bool(is_longtail_oa)
     if force_bool:
-        t['in_doi'] = bool(in_doi)
-        t['is_oa'] = bool(in_doaj or in_road or is_longtail_oa or is_oa)
+        t['is_oa'] = bool(in_doaj or in_road or is_oa)
+        t['is_longtail_oa'] = bool(is_longtail_oa)
         t['any_jstor'] = bool(any_jstor)
         t['any_ia_sim'] = bool(any_ia_sim)
     else:
-        t['in_doi'] = in_doi
-        t['is_oa'] = in_doaj or in_road or is_longtail_oa or is_oa
+        t['is_oa'] = in_doaj or in_road or is_oa
+        t['is_longtail_oa'] = is_longtail_oa
         t['any_jstor'] = any_jstor
         t['any_ia_sim'] = any_ia_sim
     return t
-- 
cgit v1.2.3


From e047fbe1a9c495e86a6757d44eb32c9109a1b753 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 29 Jan 2020 20:39:22 -0800
Subject: ES release schema updates

---
 extra/elasticsearch/release_schema.json         | 69 ++++++++++++++-------
 python/fatcat_tools/transforms/elasticsearch.py | 81 +++++++++++++++++++++++--
 2 files changed, 122 insertions(+), 28 deletions(-)

diff --git a/extra/elasticsearch/release_schema.json b/extra/elasticsearch/release_schema.json
index 85026060..98a1c28e 100644
--- a/extra/elasticsearch/release_schema.json
+++ b/extra/elasticsearch/release_schema.json
@@ -27,48 +27,62 @@
 "mappings": {
     "release": {
         "properties": {
-            "ident":          { "type": "keyword" },
+            "ident":          { "type": "keyword", "doc_values": false },
             "state":          { "type": "keyword" },
-            "revision":       { "type": "keyword" },
-            "work_id":        { "type": "keyword" },
-            "title":          { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" },
-            "subtitle":       { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" },
-            "original_title": { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" },
+            "revision":       { "type": "keyword", "doc_values": false },
+            "work_id":        { "type": "keyword", "doc_values": false },
+            "title":          { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
+            "subtitle":       { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
+            "original_title": { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
             "release_date":   { "type": "date" },
-            "release_year":   { "type": "integer" },
-            "release_type":   { "type": "keyword" },
+            "release_year":   { "type": "integer", "copy_to": "biblio" },
+            "release_type":   { "type": "keyword", "copy_to": "biblio" },
             "release_stage":  { "type": "keyword" },
-            "withdrawn_status": { "type": "keyword" },
+            "withdrawn_status": { "type": "keyword", "copy_to": "biblio" },
             "language":       { "type": "keyword" },
-            "doi":            { "type": "keyword" },
-            "pmid":           { "type": "keyword" },
-            "pmcid":          { "type": "keyword" },
-            "isbn13":         { "type": "keyword" },
-            "wikidata_qid":   { "type": "keyword" },
-            "core_id":        { "type": "keyword" },
-            "axiv_id":        { "type": "keyword" },
-            "jstor_id":       { "type": "keyword" },
-            "ark_id":         { "type": "keyword" },
-            "mag_id":         { "type": "keyword" },
+            "volume":         { "type": "keyword", "copy_to": "biblio" },
+            "issue":          { "type": "keyword", "copy_to": "biblio" },
+            "pages":          { "type": "keyword", "copy_to": "biblio" },
+            "first_page":     { "type": "keyword" },
+            "number":         { "type": "keyword", "copy_to": "biblio" },
+            "doi":            { "type": "keyword", "doc_values": false },
+            "doi_prefix":     { "type": "keyword" },
+            "doi_registrar":  { "type": "keyword" },
+            "pmid":           { "type": "keyword", "doc_values": false },
+            "pmcid":          { "type": "keyword", "doc_values": false },
+            "isbn13":         { "type": "keyword", "doc_values": false },
+            "wikidata_qid":   { "type": "keyword", "doc_values": false },
+            "core_id":        { "type": "keyword", "doc_values": false },
+            "axiv_id":        { "type": "keyword", "doc_values": false },
+            "jstor_id":       { "type": "keyword", "doc_values": false },
+            "ark_id":         { "type": "keyword", "doc_values": false },
+            "mag_id":         { "type": "keyword", "doc_values": false },
             "license":        { "type": "keyword" },
             "publisher":            { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" },
-            "container_name":       { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" },
+            "container_name":       { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
             "container_id":         { "type": "keyword" },
             "container_issnl":      { "type": "keyword" },
             "container_type":       { "type": "keyword" },
             "contrib_count":        { "type": "integer" },
-            "contrib_names":        { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" },
+            "contrib_names":        { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
+            "affiliations":         { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" },
+            "affiliation_rors":     { "type": "keyword" },
             "creator_ids":          { "type": "keyword" },
             "ref_count":            { "type": "integer" },
             "ref_linked_count":     { "type": "integer" },
+            "ref_release_ids":      { "type": "keyword" },
             "file_count":           { "type": "integer" },
             "fileset_count":        { "type": "integer" },
             "webcapture_count":     { "type": "integer" },
             "any_abstract":         { "type": "boolean" },
 
-            "best_pdf_url":         { "type": "keyword" },
-            "ia_pdf_url":           { "type": "keyword" },
+            "biblio":               { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" },
+
+            "best_pdf_url":         { "type": "keyword", "doc_values": false },
+            "ia_pdf_url":           { "type": "keyword", "doc_values": false },
+            "ia_microfilm_url":     { "type": "keyword", "doc_values": false },
             "is_oa":                { "type": "boolean" },
+            "oa_color":             { "type": "keyword" },
             "is_longtail_oa":       { "type": "boolean" },
             "is_preserved":         { "type": "boolean" },
             "in_kbart":             { "type": "boolean" },
@@ -79,7 +93,13 @@
             "in_ia_sim":            { "type": "boolean" },
             "in_shadows":           { "type": "boolean" },
             "is_superceded":        { "type": "boolean" },
+            "is_retracted":         { "type": "boolean" },
+            "preservation":         { "type": "keyword" },
 
+            "affilation":     { "type": "alias", "path": "affiliations" },
+            "ror":            { "type": "alias", "path": "affiliation_rors" },
+            "creator_id":     { "type": "alias", "path": "creator_id" },
+            "ref_release_id": { "type": "alias", "path": "ref_release_ids" },
             "author":         { "type": "alias", "path": "contrib_names" },
             "journal":        { "type": "alias", "path": "container_name" },
             "date":           { "type": "alias", "path": "release_date" },
@@ -90,6 +110,9 @@
             "lang":           { "type": "alias", "path": "language" },
             "file_pdf_url":   { "type": "alias", "path": "best_pdf_url" },
             "release_status": { "type": "alias", "path": "release_stage" },
+            "stage":          { "type": "alias", "path": "release_stage" },
+            "type":           { "type": "alias", "path": "release_type" },
+            "retracted":      { "type": "alias", "path": "is_retracted" },
             "is_kept":        { "type": "alias", "path": "in_kbart" }
         }
     }
diff --git a/python/fatcat_tools/transforms/elasticsearch.py b/python/fatcat_tools/transforms/elasticsearch.py
index edc68748..b997796d 100644
--- a/python/fatcat_tools/transforms/elasticsearch.py
+++ b/python/fatcat_tools/transforms/elasticsearch.py
@@ -50,6 +50,10 @@ def release_to_elasticsearch(entity, force_bool=True):
         release_stage = release.release_stage,
         withdrawn_status = release.withdrawn_status,
         language = release.language,
+        volume = release.volume,
+        issue = release.issue,
+        pages = release.pages,
+        number = release.number,
         license = release.license_slug,
         doi = release.ext_ids.doi,
         pmid = release.ext_ids.pmid,
@@ -72,7 +76,7 @@ def release_to_elasticsearch(entity, force_bool=True):
     in_dweb = False
     in_ia = False
     in_ia_sim = False
-    in_shadow = False
+    in_shadows = False
 
     release_year = release.release_year
     if release.release_date:
@@ -85,11 +89,15 @@ def release_to_elasticsearch(entity, force_bool=True):
 
     t['any_abstract'] = len(release.abstracts or []) > 0
     t['ref_count'] = len(release.refs or [])
-    t['ref_linked_count'] = 0
-    if release.refs:
-        t['ref_linked_count'] = len([1 for ref in release.refs if ref.target_release_id])
+    ref_release_ids = []
+    for r in (release.refs or []):
+        if r.target_release_id:
+            ref_release_ids.append(r.target_release_id)
+    t['ref_release_ids'] = ref_release_ids
+    t['ref_linked_count'] = len(ref_release_ids)
     t['contrib_count'] = len(release.contribs or [])
     contrib_names = []
+    contrib_affiliations = []
     creator_ids = []
     for c in (release.contribs or []):
         if c.raw_name:
@@ -98,8 +106,14 @@ def release_to_elasticsearch(entity, force_bool=True):
             contrib_names.append(c.surname)
         if c.creator_id:
             creator_ids.append(c.creator_id)
+        if c.raw_affiliation:
+            contrib_affiliations.append(c.raw_affiliation)
     t['contrib_names'] = contrib_names
     t['creator_ids'] = creator_ids
+    t['affiliations'] = contrib_affiliations
+
+    # TODO: mapping... probably by lookup?
+    t['affiliation_rors'] = None
 
     container = release.container
     if container:
@@ -140,8 +154,13 @@ def release_to_elasticsearch(entity, force_bool=True):
             if c_extra.get('szczepanski'):
                 if c_extra['szczepanski'].get('as_of'):
                     is_oa = True
-    else:
+
+    # fall back to release-level container metadata if container not linked or
+    # missing context
+    if not t.get('publisher'):
         t['publisher'] = release.publisher
+    if not t.get('container_name') and release.extra:
+        t['container_name'] = release.extra.get('container_name')
 
     if release.ext_ids.jstor or (release.ext_ids.doi and release.ext_ids.doi.startswith('10.2307/')):
         in_jstor = True
@@ -203,6 +222,46 @@ def release_to_elasticsearch(entity, force_bool=True):
             if extra['crossref'].get('archive'):
                 # all crossref archives are KBART, I believe
                 in_kbart = True
+        # backwards compatible subtitle fetching
+        if not t['subtitle'] and extra.get('subtitle'):
+            if type(extra['subtitle']) == list:
+                t['subtitle'] = extra['subtitle'][0]
+            else:
+                t['subtitle'] = extra['subtitle']
+
+    t['first_page'] = None
+    if release.pages:
+        first = release.pages.split('-')[0]
+        first = first.replace('p', '')
+        if release.pages.isdigit():
+            t['first_page'] = release.pages
+        # TODO: non-numerical first pages
+
+    t['ia_microfilm_url'] = None
+    if in_ia_sim:
+        # TODO: determine URL somehow? I think this is in flux. Will probably
+        # need extra metadata in the container extra field.
+        # special case as a demo for now.
+        if release.container_id == "hl5g6d5msjcl7hlbyyvcsbhc2u" \
+                and release.year in (2011, 2013) \
+                and release.volume.isdigit() \
+                and t['first_page']:
+            t['ia_microfilm_url'] = "https://archive.org/details/sim_bjog_{}-{:02d}/page/n{}".format(
+                release.year,
+                release.volume - 1,
+                t['first_page'],
+            )
+
+    t['doi_registrar'] = None
+    if extra and t['doi']:
+        for k in ('crossref', 'datacite', 'jalc'):
+            if k in extra:
+                t['doi_registrar'] = k
+        if not 'doi_registrar' in t:
+            t['doi_registrar'] = 'crossref'
+
+    if t['doi']:
+        t['doi_prefix'] = t['doi'].split('/')[0]
 
     if is_longtail_oa:
         is_oa = True
@@ -215,6 +274,7 @@ def release_to_elasticsearch(entity, force_bool=True):
         t['in_jstor'] = bool(in_jstor)
         t['in_web'] = bool(in_web)
         t['in_dweb'] = bool(in_dweb)
+        t['in_shadows'] = bool(in_shadows)
     else:
         t['is_oa'] = is_oa
         t['is_longtail_oa'] = is_longtail_oa
@@ -223,9 +283,20 @@ def release_to_elasticsearch(entity, force_bool=True):
         t['in_jstor'] = in_jstor
         t['in_web'] = in_web
         t['in_dweb'] = in_dweb
+        t['in_shadows'] = in_shadows
 
     t['in_ia'] = bool(in_ia)
     t['is_preserved'] = bool(is_preserved or in_ia or in_kbart or in_jstor)
+
+    if in_ia:
+        t['preservation'] = 'bright'
+    elif in_kbart or in_jstor:
+        t['preservation'] = 'dark_only'
+    elif in_shadows:
+        t['preservation'] = 'shadows_only'
+    else:
+        t['preservation'] = 'none'
+
     return t
 
 def container_to_elasticsearch(entity, force_bool=True):
-- 
cgit v1.2.3


From 5d458a3df7e58e6551d8ec72979e376c62fdd2f7 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 29 Jan 2020 21:52:33 -0800
Subject: fix some transform bugs, add some tests

---
 python/fatcat_tools/transforms/elasticsearch.py    |  14 +--
 python/fatcat_transform.py                         |  26 ++++-
 python/tests/files/changelog_3469683.json          |   1 +
 .../files/file_bcah4zp5tvdhjl5bqci2c2lgfa.json     |   1 +
 .../files/release_etodop5banbndg3faecnfm6ozi.json  |   1 +
 python/tests/transform_elasticsearch.py            | 114 +++++++++++++++++++++
 python/tests/transform_tests.py                    | 106 -------------------
 7 files changed, 149 insertions(+), 114 deletions(-)
 create mode 100644 python/tests/files/changelog_3469683.json
 create mode 100644 python/tests/files/file_bcah4zp5tvdhjl5bqci2c2lgfa.json
 create mode 100644 python/tests/files/release_etodop5banbndg3faecnfm6ozi.json
 create mode 100644 python/tests/transform_elasticsearch.py
 delete mode 100644 python/tests/transform_tests.py

diff --git a/python/fatcat_tools/transforms/elasticsearch.py b/python/fatcat_tools/transforms/elasticsearch.py
index b997796d..812cd1fd 100644
--- a/python/fatcat_tools/transforms/elasticsearch.py
+++ b/python/fatcat_tools/transforms/elasticsearch.py
@@ -20,6 +20,7 @@ def test_check_kbart():
     assert check_kbart(1950, dict(year_spans=[[1900, 1920], [1990, 2000]])) == False
     assert check_kbart(1950, dict(year_spans=[[1900, 1920], [1930, 2000]])) == True
 
+
 def release_to_elasticsearch(entity, force_bool=True):
     """
     Converts from an entity model/schema to elasticsearch oriented schema.
@@ -233,8 +234,8 @@ def release_to_elasticsearch(entity, force_bool=True):
     if release.pages:
         first = release.pages.split('-')[0]
         first = first.replace('p', '')
-        if release.pages.isdigit():
-            t['first_page'] = release.pages
+        if first.isdigit():
+            t['first_page'] = first
         # TODO: non-numerical first pages
 
     t['ia_microfilm_url'] = None
@@ -243,12 +244,12 @@ def release_to_elasticsearch(entity, force_bool=True):
         # need extra metadata in the container extra field.
         # special case as a demo for now.
         if release.container_id == "hl5g6d5msjcl7hlbyyvcsbhc2u" \
-                and release.year in (2011, 2013) \
-                and release.volume.isdigit() \
+                and release.release_year in (2011, 2013) \
+                and release.issue.isdigit() \
                 and t['first_page']:
             t['ia_microfilm_url'] = "https://archive.org/details/sim_bjog_{}-{:02d}/page/n{}".format(
-                release.year,
-                release.volume - 1,
+                release.release_year,
+                int(release.issue) - 1,
                 t['first_page'],
             )
 
@@ -299,6 +300,7 @@ def release_to_elasticsearch(entity, force_bool=True):
 
     return t
 
+
 def container_to_elasticsearch(entity, force_bool=True):
     """
     Converts from an entity model/schema to elasticsearch oriented schema.
diff --git a/python/fatcat_transform.py b/python/fatcat_transform.py
index ccb13871..42d2ea99 100755
--- a/python/fatcat_transform.py
+++ b/python/fatcat_transform.py
@@ -1,6 +1,8 @@
 #!/usr/bin/env python3
 
 """
+Utility script for doing bulk conversion/tranforms of entity JSON schema to
+other formats
 """
 
 import sys
@@ -15,10 +17,11 @@ from citeproc_styles import get_style_filepath
 
 import fatcat_openapi_client
 from fatcat_openapi_client.rest import ApiException
-from fatcat_openapi_client import ReleaseEntity, ContainerEntity, ChangelogEntry
+from fatcat_openapi_client import ReleaseEntity, ContainerEntity, FileEntity, ChangelogEntry
 from fatcat_tools import uuid2fcid, entity_from_json, entity_to_dict, \
     release_to_elasticsearch, container_to_elasticsearch, \
-    changelog_to_elasticsearch, public_api, release_to_csl, citeproc_csl
+    file_to_elasticsearch, changelog_to_elasticsearch, public_api, \
+    release_to_csl, citeproc_csl
 
 
 def run_elasticsearch_releases(args):
@@ -39,6 +42,15 @@ def run_elasticsearch_containers(args):
         args.json_output.write(
             json.dumps(container_to_elasticsearch(entity)) + '\n')
 
+def run_elasticsearch_files(args):
+    for line in args.json_input:
+        line = line.strip()
+        if not line:
+            continue
+        entity = entity_from_json(line, FileEntity, api_client=args.api.api_client)
+        args.json_output.write(
+            json.dumps(file_to_elasticsearch(entity)) + '\n')
+
 def run_elasticsearch_changelogs(args):
     for line in args.json_input:
         line = line.strip()
@@ -87,6 +99,16 @@ def main():
         help="where to send output",
         default=sys.stdout, type=argparse.FileType('w'))
 
+    sub_elasticsearch_files = subparsers.add_parser('elasticsearch-files',
+        help="convert fatcat file JSON schema to elasticsearch file schema")
+    sub_elasticsearch_files.set_defaults(func=run_elasticsearch_files)
+    sub_elasticsearch_files.add_argument('json_input',
+        help="JSON-per-line of file entities",
+        default=sys.stdin, type=argparse.FileType('r'))
+    sub_elasticsearch_files.add_argument('json_output',
+        help="where to send output",
+        default=sys.stdout, type=argparse.FileType('w'))
+
     sub_elasticsearch_changelogs = subparsers.add_parser('elasticsearch-changelogs',
         help="convert fatcat changelog JSON schema to elasticsearch changelog schema")
     sub_elasticsearch_changelogs.set_defaults(func=run_elasticsearch_changelogs)
diff --git a/python/tests/files/changelog_3469683.json b/python/tests/files/changelog_3469683.json
new file mode 100644
index 00000000..7a847b16
--- /dev/null
+++ b/python/tests/files/changelog_3469683.json
@@ -0,0 +1 @@
+{"index":3469683,"editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","timestamp":"2020-01-30T05:04:39.738601Z","editgroup":{"editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","editor_id":"scmbogxw25evtcesfcab5qaboa","editor":{"editor_id":"scmbogxw25evtcesfcab5qaboa","username":"crawl-bot","is_admin":true,"is_bot":true,"is_active":true},"changelog_index":3469683,"created":"2020-01-30T05:04:39.738601Z","description":"Files crawled from web using sandcrawler ingest tool","extra":{"agent":"fatcat_tools.IngestFileResultImporter","git_rev":"v0.3.1-280-ga889f32"},"edits":{"containers":[],"creators":[],"files":[{"edit_id":"ba819a2b-a4d0-43e6-9e5c-505284c8ae42","ident":"e3lmbzqyjjam3a5nqnccc6d654","revision":"7a606095-9d07-41ee-898a-bcf8b6bc0004","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.1080/23802359.2020.1715878"}},{"edit_id":"a71c4b91-d599-4422-a7a6-527562161278","ident":"e62h2fa6fba6ve3lukv7n635fq","revision":"1374f1bd-684a-48b9-aaff-65b9e90083b5","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.1186/s13071-020-3909-6"}},{"edit_id":"82e4d65d-0335-4a40-b9c9-bf38f9bd7b19","ident":"fam7ii245zasvnesikw7bhmoii","revision":"327e3358-2b2b-4919-9613-449bdbb76c55","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.23917/jjr.v9i1.8294"}},{"edit_id":"49e987dc-fc6f-4391-8b75-33176f03b5cb","ident":"fa6sljsebjapfojqapxd3dj4um","revision":"7f51f4fa-e448-410a-b7d5-7ae9cdf9fcb8","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.33536/jcpe.v4i1.293"}},{"edit_id":"e62ed1ca-3961-423b-ab05-967694e32f70","ident":"fhhzbabf3zcx7p2tor2omqveyq","revision":"d40c3f8c-255f-4913-ace8-06db6af66697","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.5802/smai-jcm.59"}},{"edit_id":"337b8ed6-1248-4872-81da-d16f6db021e6","ident":"fllcoo4smfdyrh5q5lmu72e7cq","revision":"724b26cd-6ab1-46a1-bc88-a87410fdf102","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.1080/1343943x.2020.1717970"}},{"edit_id":"43a0c9d5-692e-4c73-b154-d8769854d268","ident":"fzshcc6sfzegbduum2763o3lgy","revision":"a8f5e34b-fbf4-4d52-987e-887455e6bd50","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.23917/jjr.v9i1.8099"}},{"edit_id":"48767850-1141-47e3-80ef-556605e3588c","ident":"grdztt2vwjd65ovcifeo3ysbam","revision":"12dceb74-6333-4a17-b1e8-4afac9df1888","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.26565/2220-8089-2019-36-02"}},{"edit_id":"4b3b92ac-c250-4b78-9e91-43fc893c935e","ident":"hgpzsozky5amvcts45qb6nhqum","revision":"b5951fd6-dd36-422c-9770-8cdfb7e6d82d","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.33549/physiolres.934410"}},{"edit_id":"dabff0df-6f52-4adb-a63f-1965f30d8bd2","ident":"hpxdh7mykng77jyfoolpixzw2y","revision":"0e06e57c-0756-4ee5-8102-0d96478aa23f","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.26452/ijrps.v11i1.1916"}},{"edit_id":"b757f2b5-5f97-45b8-bfcd-9c9fb08047b8","ident":"htorhznxdfdppbvpf57nrz536q","revision":"034f4640-fbb6-4123-9ad8-f934220ab820","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.1039/c9ra09196c"}},{"edit_id":"5662469f-a4d3-4339-88a0-4d27ef3f5f58","ident":"if6a63p7rnaxbjkcr4egtihj74","revision":"08d384cf-396c-41e1-a14d-6bde24b47323","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.1192/bjb.2019.92"}},{"edit_id":"540a1ec1-7879-42f4-b749-d3287eb26ef7","ident":"i76ou5g2jndo7gyjrxdhoks3bm","revision":"eddbf701-59c3-4f33-b26b-87ad29297f65","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.33549/physiolres.934355"}},{"edit_id":"04a0b805-b09f-4ff6-80b3-77cb643c72d7","ident":"jl2z2az4sjfpdigdts3xjm24vy","revision":"a541e130-07be-43ae-8fbf-b0295d5b576f","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.1080/23802359.2020.1719936"}},{"edit_id":"3e4566b9-7e3f-4e02-aa81-b6299545b150","ident":"jsrgx72devbadbyyiqwm2bl4aa","revision":"f51f164e-0e96-4245-973b-3408250ebc3b","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.24193/ed21.2019.17.09"}},{"edit_id":"80c2f0ca-ba43-4481-b5a5-c15d87d4d7b4","ident":"kijz6wlf25dito3av5snrz345a","revision":"fa1b5279-2221-4063-853e-070ca2d5954b","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.1017/s2045796020000037"}},{"edit_id":"c0f44f12-e4c7-45d4-a79a-a3ce2d628e78","ident":"ky3cjfbzejecxaa5tjaaucurb4","revision":"0e227663-f825-42e8-bf57-ba50fea60bf5","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.1017/s204579602000013x"}},{"edit_id":"92093947-7ff5-48ad-bc47-b26d4c0959c8","ident":"llfciusk6jf6rd35ofpuufmgfe","revision":"ed89f8b0-98cd-4886-b99e-b5d276b2ac9f","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.33549/physiolres.934349"}},{"edit_id":"4cb0e042-4298-4d0b-98b8-3c0c808642ea","ident":"mdw33cq7svdfnlaevnpih7bsyu","revision":"4a0ed3ce-56f2-4299-861c-051e7c06499d","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.23917/jjr.v9i2.8073"}},{"edit_id":"611fc1e1-79e1-4e10-a702-0420919407f6","ident":"mwghms3u2zecdf2x5zk7tzs4mq","revision":"101d7d0f-6aca-4df3-a08a-f4a3f26d3cd4","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.1186/s12864-020-6509-0"}},{"edit_id":"b9a350bd-3497-4c83-97c1-0a20a420a287","ident":"ooejwh3g35cfrmmk4bvjcqxrai","revision":"8a4e8a05-3fb4-4d83-a545-35f152e24f58","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.6018/cpd.340501"}},{"edit_id":"aeab2a58-ec4e-4a2a-82ee-a0d2428eca50","ident":"pepmo2ajfzh7ldtqdugj4p5zvy","revision":"7d13f42d-ce94-4537-8c56-0158d9bf99e9","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.6018/cpd.347981"}},{"edit_id":"f3cd1575-fcfd-4f6b-ab48-28b06592df85","ident":"qcw5h7c5uncbbphtrp3zibn5y4","revision":"fa7b2868-777e-4046-98ca-b146c0056180","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.1017/s1742170519000425"}},{"edit_id":"3c0ffa45-7f39-4393-a73c-0615bf9543f6","ident":"qfmufcdlrbfyhcjemvut5om23i","revision":"fac63461-4790-49a8-9b75-b23e9a369529","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.34225/jidc.2019.14.2.57"}},{"edit_id":"4ad40f3a-55f4-4aa8-9016-d04f904b2163","ident":"qrpp45vopfbvzanalh4lmpiz24","revision":"2ac1355f-cba9-49ed-b260-9eea5ec09473","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.24193/ed21.2019.17.19"}},{"edit_id":"1ec3a67b-796c-4393-93c2-ddac4ea66e0f","ident":"q7cv6lezvjalpg5xd4tckkbmsi","revision":"702adc9f-9ecb-4030-a095-936f15839c31","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.33549/physiolres.934359"}},{"edit_id":"a8ab2cf7-8aad-4060-b281-371d41df32cf","ident":"rqcd44zbfvcovipfpnqpowiq2e","revision":"bd51fd60-438a-42fe-80e9-104705b0580f","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.33549/physiolres.934350"}},{"edit_id":"6d626d5c-1c7c-42e3-8d00-c313a91fc7c1","ident":"ruzbactehngbrlyx4vq3zlaqlu","revision":"5da34289-7da0-42ad-98bb-1c0b21bb6e69","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.5802/smai-jcm.55"}},{"edit_id":"4651ac6b-228c-4918-ac74-0757ce64c031","ident":"rvbhhfvwc5dkhdpxekutlew7di","revision":"53b088f6-653c-4e6d-974a-8e5e6e154f12","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.31616/asj.2019.0190"}},{"edit_id":"156b4a96-af8b-4c01-a8ec-6aa53736450f","ident":"r6j7ad7vmvg75lvel6v4e4gbb4","revision":"46647620-a36a-482b-a651-492a4e6ca1bb","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.5802/smai-jcm.53"}},{"edit_id":"67e6f76f-859d-422d-8c90-715b3173e24c","ident":"scajd3ykrjatbjmifvxwcl3yhu","revision":"d99f1da3-484a-4977-bc14-6e952d007acd","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.24193/ed21.2019.17.11"}},{"edit_id":"22395a5e-2a2e-4bf2-9547-0fb5122f8a7f","ident":"sk22wngc3fh23b74nmkbgeeyya","revision":"7423067d-3a18-4305-98b4-5cee8127e24a","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.31616/asj.2019.0300"}},{"edit_id":"4ea1f9dd-d85e-450b-bc2a-995364fcf3fe","ident":"tma3dvw77bghjfaqrdoiwquuge","revision":"c86364bf-501b-42b4-a3ed-ef334ff26e0a","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.36447/estudios2014.v33-34.art3"}},{"edit_id":"87d158ff-b0e0-4944-88d9-017dcef70d6e","ident":"tvuumx4n75dorebv7bu7imyiym","revision":"ae17166e-43ce-4d5a-95de-4befeeb76fa6","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.35236/jots.663726"}},{"edit_id":"2114c75b-ac23-471a-83d9-c76ae5f6bf42","ident":"twnql5u4mbfqffal2atv5qucoq","revision":"cb73ac6c-bc2b-422b-bc27-7032d14cac4d","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.31616/asj.2019.0162"}},{"edit_id":"2f1d20fd-e69e-4490-9f70-f2b043f53634","ident":"tzwyuimcgrepvhide2sj3lovjm","revision":"b9cf9229-db47-4fa0-a8f6-45320b5af440","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.33549/physiolres.934348"}},{"edit_id":"fdb6c388-9b22-45ff-8db1-1531eac43bbf","ident":"vfwz3fuvbbgcxek2hi6vjo525q","revision":"6c57ecb2-a870-4078-af17-a779ca3ceb28","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.4197/eco.29-1.8"}},{"edit_id":"3b8cf6fa-75e7-4b15-a83c-784552ff76e9","ident":"vtq5tvfltbfv3pizvux32ek5hi","revision":"7c0b5d64-6d20-407b-9de3-482a9c75f40e","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.23917/jurisprudence.v8i2.6977"}},{"edit_id":"899303e8-ce86-4f53-909f-249ef45d9a3b","ident":"vuneewh3fncxpb7bzviptx6kze","revision":"3fd4ff1c-1855-41e2-9bae-7edbae86783a","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.3846/jcem.2020.11826"}},{"edit_id":"c0595f10-72dc-4144-b243-5b344912842f","ident":"v2i53kwtnbea7kfhsnvcpkvixe","revision":"09891662-3d67-4d7f-a4ed-7f9bfa3f426f","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.33549/physiolres.934347"}},{"edit_id":"80f26273-d243-4dcf-af4a-e05226ba679c","ident":"wtish6c32randpuucjxq5byjo4","revision":"a69cd59a-52bf-4c48-9323-62a4070b2440","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.29261/pakvetj/2019.033"}},{"edit_id":"79f1bdc1-2627-4328-97ff-71731295fcad","ident":"xkf7a4cavnhahnfsjj5w5aoopu","revision":"b826cb89-efcc-427f-a378-0829bb2b871c","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.36447/estudios2014.v33-34.art6"}},{"edit_id":"695feb37-ab8e-4ecd-8c9e-fae06ff63e39","ident":"yx24fslfafb6dgx7gvjbmoma5m","revision":"4109aeb1-fcc1-47f3-9d2c-8e3abfbc697e","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.1039/c9ra10366j"}},{"edit_id":"48f2eb73-a5a3-440a-8bd1-c581797a82ca","ident":"3p5rah3wbfftdht7rabkpjfcrm","revision":"df754aec-4750-45eb-97e6-943928dad661","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.24193/ed21.2019.17.01"}},{"edit_id":"7a937ed3-5362-40ed-8f96-e6c6231e0adf","ident":"4r3madqhfzb5jb7jd7xmv55em4","revision":"6feccd54-38bd-4d51-8f42-fe211baf5ba3","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.35236/jots.668781"}},{"edit_id":"3beaa94e-c4e1-4a6b-96a7-d455ad13b7aa","ident":"53ooeweri5efjm5vhl2bwjcfze","revision":"a9d318ad-eb2a-4590-a463-8d6016e2e887","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.1017/s2045796020000049"}},{"edit_id":"8a0b80e2-c8b2-4457-ac89-2fc7ad7548f7","ident":"546k37iji5bfffakw2egl2azxy","revision":"3a4d93d0-c59e-4f81-8fbb-40ce21b11b1e","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.1039/c9ra08019h"}},{"edit_id":"15fa5e34-9829-483e-bfa5-a4011b974c6b","ident":"6cy3aonbdfgxbjxnujg3hsqx7q","revision":"021fed8f-5109-4389-9e7f-13a70cbaf4a3","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.2478/joim-2019-0023"}},{"edit_id":"6bc507c8-ceea-49a5-8c1f-9c652463588e","ident":"6rxwlcytwzeopgrhidvi236b2q","revision":"60307cd5-28a3-4063-9111-d5e90e1cb346","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.3846/aviation.2019.11913"}},{"edit_id":"283013c6-4400-4fdc-b2b2-1dbd1a262332","ident":"7j4w24plxzc3nnrkorbowmnra4","revision":"0fa4112c-a596-49a2-9d36-82c213db3fb8","editgroup_id":"jebmpiqsjja7jozze7hoy3bir4","extra":{"ingest_request_source":"fatcat-changelog","link_source":"doi","link_source_id":"10.24193/ed21.2019.17.22"}}],"filesets":[],"webcaptures":[],"releases":[],"works":[]}}}
\ No newline at end of file
diff --git a/python/tests/files/file_bcah4zp5tvdhjl5bqci2c2lgfa.json b/python/tests/files/file_bcah4zp5tvdhjl5bqci2c2lgfa.json
new file mode 100644
index 00000000..bed8977d
--- /dev/null
+++ b/python/tests/files/file_bcah4zp5tvdhjl5bqci2c2lgfa.json
@@ -0,0 +1 @@
+{"release_ids":["5tbuas2e4vd6jaowbgzmmhhqxe"],"mimetype":"application/pdf","urls":[{"url":"https://web.archive.org/web/20200130042753/https://www.zhros.ru/jour/article/download/811/542","rel":"webarchive"},{"url":"https://www.zhros.ru/jour/article/download/811/542","rel":"web"}],"sha256":"1665cdb90b73c684233038601c52995acef77bb37aefc6e63ae13e4194d48261","sha1":"3ad4df99ff1354ec0b5a333a59fba9a3a5d9812a","md5":"39159f9c8e98a245f954c9000b0f2810","size":739980,"revision":"dcc7a975-725d-4bc9-8c3f-cd0476cd485e","ident":"bcah4zp5tvdhjl5bqci2c2lgfa","state":"active"}
\ No newline at end of file
diff --git a/python/tests/files/release_etodop5banbndg3faecnfm6ozi.json b/python/tests/files/release_etodop5banbndg3faecnfm6ozi.json
new file mode 100644
index 00000000..1204c95d
--- /dev/null
+++ b/python/tests/files/release_etodop5banbndg3faecnfm6ozi.json
@@ -0,0 +1 @@
+{"abstracts":[],"refs":[{"index":0,"extra":{"issue":"Suppl 1","volume":"118"},"key":"10.1111/j.1471-0528.2011.03098.x-BIB1|cit1","year":2011,"container_name":"BJOG","title":"Saving Mothers' Lives: reviewing maternal deaths to make motherhood safer-2006-2008. The Eighth Report of the Confidential Enquiries into Maternal Deaths in the United Kingdom"}],"contribs":[{"index":0,"raw_name":"Philip Steer","role":"author","extra":{"seq":"first"}}],"language":"en","publisher":"Wiley","pages":"1404-1404","issue":"11","volume":"118","ext_ids":{"doi":"10.1111/j.1471-0528.2011.03098.x"},"release_year":2011,"release_date":"2011-09-09","release_stage":"published","release_type":"article-journal","container_id":"hl5g6d5msjcl7hlbyyvcsbhc2u","webcaptures":[],"filesets":[],"files":[],"container":{"wikidata_qid":"Q15724571","issnl":"1470-0328","publisher":"Wiley (Blackwell Publishing)","container_type":"journal","name":"BJOG: an International Journal of Obstetrics and Gynaecology","extra":{"abbrev":"BJOG","country":"gb","ia":{"sim":{"year_spans":[[1902,1915],[1921,2015]]}},"issne":"1471-0528","issnp":"1470-0328","kbart":{"clockss":{"year_spans":[[1989,1989],[1993,1993],[2002,2003],[2009,2017]]},"portico":{"year_spans":[[1902,2019]]}},"languages":["en"],"sherpa_romeo":{"color":"yellow"},"urls":["http://www.bjog.org/view/0/index.html"]},"revision":"ec26766c-c1fe-453b-837d-087cc254fe07","ident":"hl5g6d5msjcl7hlbyyvcsbhc2u","state":"active"},"work_id":"wmwe5wwkzfcs7gyjfgdeanksha","title":"Saving Mothers' Lives. Reviewing maternal deaths to make motherhood safer: 2006-2008","state":"active","ident":"etodop5banbndg3faecnfm6ozi","revision":"deb7e050-6df6-42ed-9704-788a0e30facf","extra":{"crossref":{"type":"journal-article"},"subtitle":["Correpondence"]}}
\ No newline at end of file
diff --git a/python/tests/transform_elasticsearch.py b/python/tests/transform_elasticsearch.py
new file mode 100644
index 00000000..ab613a0a
--- /dev/null
+++ b/python/tests/transform_elasticsearch.py
@@ -0,0 +1,114 @@
+
+import json
+import pytest
+from fatcat_tools import *
+from fatcat_openapi_client import *
+from fixtures import api
+from import_journal_metadata import journal_metadata_importer
+
+from import_crossref import crossref_importer
+from import_matched import matched_importer
+
+def test_basic_elasticsearch_convert(crossref_importer):
+    with open('tests/files/crossref-works.single.json', 'r') as f:
+        # not a single line
+        raw = json.loads(f.read())
+        r = crossref_importer.parse_record(raw)
+    r.state = 'active'
+    release_to_elasticsearch(r)
+
+def test_rich_elasticsearch_convert():
+    r = ReleaseEntity(
+        title="something",
+        release_year=1234,
+        license_slug="CC-BY-NC",
+        ext_ids=ReleaseExtIds(),
+        refs=[
+            ReleaseRef(),
+            ReleaseRef(target_release_id="iznnn644szdwva7khyxqzc73bi"),
+        ],
+    )
+    r.state = 'active'
+    r.container = ContainerEntity(
+        name="dummy journal",
+        extra={
+            "ia": {
+                "sim": {
+                    "year_spans": [[1000, 1100]],
+                },
+            },
+            "kbart": {
+                "lockss": {
+                    "year_spans": [[1200, 1300]],
+                },
+                "jstor": {
+                    "year_spans": [[1950, 1960], [1980, 2005]],
+                },
+            },
+            "sherpa_romeo": {"color": "blue"},
+            "doaj": {"as_of": "2010-02-03"},
+        },
+    )
+    r.files = [FileEntity(
+        mimetype="application/pdf",
+        urls=[
+            FileUrl(rel="dweb", url="dat://a954329dlk/thingie"),
+            FileUrl(rel="webarchive", url="https://web.archive.org/web/20001122030405/http://example.com"),
+            FileUrl(rel="web", url="https://archive.org/details/blah/file.pdf"),
+        ],
+        extra={
+            "shadows": {},
+        },
+    )]
+    es = release_to_elasticsearch(r)
+    assert es['release_year'] == r.release_year
+    assert es['in_ia'] == True
+    assert es['in_jstor'] == False
+    assert es['in_ia_sim'] == False
+    assert es['in_ia'] == True
+    assert es['in_web'] == True
+    assert es['in_dweb'] == True
+    assert es['is_oa'] == True
+    assert es['is_longtail_oa'] == False
+    assert es['ref_count'] == 2
+    assert es['ref_linked_count'] == 1
+
+def test_elasticsearch_release_from_json():
+    r = entity_from_json(open('./tests/files/release_etodop5banbndg3faecnfm6ozi.json', 'r').read(), ReleaseEntity)
+    es = release_to_elasticsearch(r)
+
+    assert es['subtitle'] == "Correpondence"
+    assert es['ident'] == "etodop5banbndg3faecnfm6ozi"
+    assert es['container_name'] == "BJOG: an International Journal of Obstetrics and Gynaecology"
+    assert es['first_page'] == "1404"
+    assert es['issue'] == "11"
+    assert es['volume'] == "118"
+    assert es['number'] == None
+    assert es['in_ia_sim'] == True
+    assert es['in_kbart'] == True
+
+def test_elasticsearch_container_transform(journal_metadata_importer):
+    with open('tests/files/journal_metadata.sample.json', 'r') as f:
+        raw = json.loads(f.readline())
+        c = journal_metadata_importer.parse_record(raw)
+    c.state = 'active'
+    es = container_to_elasticsearch(c)
+    assert es['publisher'] == c.publisher
+
+def test_elasticsearch_file_transform(matched_importer):
+    f = entity_from_json(open('./tests/files/file_bcah4zp5tvdhjl5bqci2c2lgfa.json', 'r').read(), FileEntity)
+
+    f.state = 'active'
+    es = file_to_elasticsearch(f)
+    assert es['sha1'] == f.sha1
+    assert es['sha256'] == f.sha256
+    assert es['md5'] == f.md5
+    assert es['size_bytes'] == f.size
+    assert es['mimetype'] == f.mimetype
+    assert es['in_ia'] == True
+    assert 'publisher' in es['rel']
+
+    # XXX: implement hosts and domain parsing with urlcanon
+    #assert 'journals.plos.org' in es['host']
+    #assert 'plos.org' in es['domain']
+
diff --git a/python/tests/transform_tests.py b/python/tests/transform_tests.py
deleted file mode 100644
index 7b583ac4..00000000
--- a/python/tests/transform_tests.py
+++ /dev/null
@@ -1,106 +0,0 @@
-
-import json
-import pytest
-from fatcat_tools import *
-from fatcat_openapi_client import *
-from fixtures import api
-from import_journal_metadata import journal_metadata_importer
-
-from import_crossref import crossref_importer
-from import_matched import matched_importer
-
-def test_basic_elasticsearch_convert(crossref_importer):
-    with open('tests/files/crossref-works.single.json', 'r') as f:
-        # not a single line
-        raw = json.loads(f.read())
-        r = crossref_importer.parse_record(raw)
-    r.state = 'active'
-    release_to_elasticsearch(r)
-
-def test_rich_elasticsearch_convert():
-    r = ReleaseEntity(
-        title="something",
-        release_year=1234,
-        license_slug="CC-BY-NC",
-        ext_ids=ReleaseExtIds(),
-        refs=[
-            ReleaseRef(),
-            ReleaseRef(target_release_id="iznnn644szdwva7khyxqzc73bi"),
-        ],
-    )
-    r.state = 'active'
-    r.container = ContainerEntity(
-        name="dummy journal",
-        extra={
-            "ia": {
-                "sim": {
-                    "year_spans": [[1000, 1100]],
-                },
-            },
-            "kbart": {
-                "lockss": {
-                    "year_spans": [[1200, 1300]],
-                },
-                "jstor": {
-                    "year_spans": [[1950, 1960], [1980, 2005]],
-                },
-            },
-            "sherpa_romeo": {"color": "blue"},
-            "doaj": {"as_of": "2010-02-03"},
-        },
-    )
-    r.files = [FileEntity(
-        mimetype="application/pdf",
-        urls=[
-            FileUrl(rel="dweb", url="dat://a954329dlk/thingie"),
-            FileUrl(rel="webarchive", url="https://web.archive.org/web/20001122030405/http://example.com"),
-            FileUrl(rel="web", url="https://archive.org/details/blah/file.pdf"),
-        ],
-        extra={
-            "shadows": {},
-        },
-    )]
-    es = release_to_elasticsearch(r)
-    assert es['release_year'] == r.release_year
-    assert es['in_ia'] == True
-    assert es['in_jstor'] == False
-    assert es['in_ia_sim'] == False
-    assert es['in_ia'] == True
-    assert es['in_web'] == True
-    assert es['in_dweb'] == True
-    assert es['is_oa'] == True
-    assert es['is_longtail_oa'] == False
-    assert es['ref_count'] == 2
-    assert es['ref_linked_count'] == 1
-
-def test_elasticsearch_release_from_json():
-    r = entity_from_json(open('./tests/files/math_universe.json', 'r').read(), ReleaseEntity)
-    release_to_elasticsearch(r)
-
-def test_elasticsearch_container_transform(journal_metadata_importer):
-    with open('tests/files/journal_metadata.sample.json', 'r') as f:
-        raw = json.loads(f.readline())
-        c = journal_metadata_importer.parse_record(raw)
-    c.state = 'active'
-    es = container_to_elasticsearch(c)
-    assert es['publisher'] == c.publisher
-
-def test_elasticsearch_file_transform(matched_importer):
-    with open('tests/files/example_matched.json', 'r') as f:
-        raw = json.loads(f.readline())
-        f = matched_importer.parse_record(raw)
-
-    f.state = 'active'
-    es = file_to_elasticsearch(f)
-    assert es['sha1'] == f.sha1
-    assert es['sha256'] == f.sha256
-    assert es['md5'] == f.md5
-    assert es['size_bytes'] == f.size
-    assert es['mimetype'] == f.mimetype
-    assert es['in_ia'] == True
-    assert 'publisher' in es['rel']
-
-    # XXX: implement hosts and domain parsing with urlcanon
-    #assert 'journals.plos.org' in es['host']
-    #assert 'plos.org' in es['domain']
-
-- 
cgit v1.2.3


From d58c3891ac2122dac53ced606568108f543f2d80 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 29 Jan 2020 21:52:58 -0800
Subject: actually implement changelog transform

---
 extra/elasticsearch/changelog_schema.json       | 11 ++++-
 python/fatcat_tools/transforms/elasticsearch.py | 62 ++++++++++++++++++-------
 python/tests/transform_elasticsearch.py         | 24 +++++++++-
 3 files changed, 78 insertions(+), 19 deletions(-)

diff --git a/extra/elasticsearch/changelog_schema.json b/extra/elasticsearch/changelog_schema.json
index f3211e99..77c77238 100644
--- a/extra/elasticsearch/changelog_schema.json
+++ b/extra/elasticsearch/changelog_schema.json
@@ -16,20 +16,29 @@
     "changelog": {
         "properties": {
             "index":            { "type": "integer" },
-            "editgroup_id":     { "type": "keyword" },
+            "editgroup_id":     { "type": "keyword", "doc_values": false },
             "timestamp":        { "type": "date" },
             "editor_id":        { "type": "keyword" },
             "username":         { "type": "keyword" },
             "is_bot":           { "type": "boolean" },
             "is_admin":         { "type": "boolean" },
             "agent":            { "type": "keyword" },
+
             "containers":       { "type": "integer" },
+            "new_containers":   { "type": "integer" },
             "creators":         { "type": "integer" },
+            "new_creators":     { "type": "integer" },
             "files":            { "type": "integer" },
+            "new_files":        { "type": "integer" },
             "filessets":        { "type": "integer" },
+            "new_filessets":    { "type": "integer" },
             "webcaptures":      { "type": "integer" },
+            "new_webcaptures":  { "type": "integer" },
             "releases":         { "type": "integer" },
+            "new_releases":     { "type": "integer" },
             "works":            { "type": "integer" },
+            "new_works":        { "type": "integer" },
+
             "created":          { "type": "integer" },
             "updated":          { "type": "integer" },
             "deleted":          { "type": "integer" },
diff --git a/python/fatcat_tools/transforms/elasticsearch.py b/python/fatcat_tools/transforms/elasticsearch.py
index 812cd1fd..c8547b27 100644
--- a/python/fatcat_tools/transforms/elasticsearch.py
+++ b/python/fatcat_tools/transforms/elasticsearch.py
@@ -401,36 +401,64 @@ def container_to_elasticsearch(entity, force_bool=True):
     return t
 
 
+def _type_of_edit(edit):
+    if edit.revision == None and edit.redirect_ident == None:
+        return 'delete'
+    elif edit.redirect_ident:
+        # redirect
+        return 'update'
+    elif edit.prev_revision == None and edit.redirect_ident == None and edit.revision:
+        return 'create'
+    else:
+        return 'update'
+
+
 def changelog_to_elasticsearch(entity):
 
     editgroup = entity.editgroup
     t = dict(
         index=entity.index,
         editgroup_id=entity.editgroup_id,
-        timestamp=entity.timestamp,
+        timestamp=entity.timestamp.isoformat(),
         editor_id=editgroup.editor_id,
+        username=editgroup.editor.username,
+        is_bot=editgroup.editor.is_bot,
+        is_admin=editgroup.editor.is_admin,
     )
 
     extra = editgroup.extra or dict()
     if extra.get('agent'):
         t['agent'] = extra['agent']
 
-    t['containers'] = len(editgroup.edits.containers)
-    t['creators'] = len(editgroup.edits.containers)
-    t['files'] = len(editgroup.edits.containers)
-    t['filesets'] = len(editgroup.edits.containers)
-    t['webcaptures'] = len(editgroup.edits.containers)
-    t['releases'] = len(editgroup.edits.containers)
-    t['works'] = len(editgroup.edits.containers)
-
-    # TODO: parse and pull out counts
-    #created = 0
-    #updated = 0
-    #deleted = 0
-    #t['created'] = created
-    #t['updated'] = updated
-    #t['deleted'] = deleted
-    #t['total'] = created + updated + deleted
+    containers = [_type_of_edit(e) for e in editgroup.edits.containers]
+    creators = [_type_of_edit(e) for e in editgroup.edits.creators]
+    files = [_type_of_edit(e) for e in editgroup.edits.files]
+    filesets = [_type_of_edit(e) for e in editgroup.edits.filesets]
+    webcaptures = [_type_of_edit(e) for e in editgroup.edits.webcaptures]
+    releases = [_type_of_edit(e) for e in editgroup.edits.releases]
+    works = [_type_of_edit(e) for e in editgroup.edits.works]
+
+    t['containers'] = len(containers)
+    t['new_containers'] = len([e for e in containers if e == 'create'])
+    t['creators'] = len(creators)
+    t['new_creators'] = len([e for e in creators if e == 'create'])
+    t['files'] = len(files)
+    t['new_files'] = len([e for e in files if e == 'create'])
+    t['filesets'] = len(filesets)
+    t['new_filesets'] = len([e for e in filesets if e == 'create'])
+    t['webcaptures'] = len(webcaptures)
+    t['new_webcaptures'] = len([e for e in webcaptures if e == 'create'])
+    t['releases'] = len(releases)
+    t['new_releases'] = len([e for e in releases if e == 'create'])
+    t['works'] = len(works)
+    t['new_works'] = len([e for e in works if e == 'create'])
+
+    all_edits = containers + creators + files + filesets + webcaptures + releases + works
+
+    t['created'] = len([e for e in all_edits if e == 'create'])
+    t['updated'] = len([e for e in all_edits if e == 'update'])
+    t['deleted'] = len([e for e in all_edits if e == 'delete'])
+    t['total'] = len(all_edits)
     return t
 
 
diff --git a/python/tests/transform_elasticsearch.py b/python/tests/transform_elasticsearch.py
index ab613a0a..89a4eef8 100644
--- a/python/tests/transform_elasticsearch.py
+++ b/python/tests/transform_elasticsearch.py
@@ -106,9 +106,31 @@ def test_elasticsearch_file_transform(matched_importer):
     assert es['size_bytes'] == f.size
     assert es['mimetype'] == f.mimetype
     assert es['in_ia'] == True
-    assert 'publisher' in es['rel']
+    assert 'web' in es['rel']
 
     # XXX: implement hosts and domain parsing with urlcanon
     #assert 'journals.plos.org' in es['host']
     #assert 'plos.org' in es['domain']
 
+def test_elasticsearch_changelog_transform(matched_importer):
+    ce = entity_from_json(open('./tests/files/changelog_3469683.json', 'r').read(), ChangelogEntry)
+
+    es = changelog_to_elasticsearch(ce)
+    assert es['index'] == 3469683
+    # len("2020-01-30T05:04:39") => 19
+    assert es['timestamp'][:19] == "2020-01-30T05:04:39.738601Z"[:19]
+    assert es['editor_id'] == "scmbogxw25evtcesfcab5qaboa"
+    assert es['username'] == "crawl-bot"
+    assert es['is_bot'] == True
+    assert es['is_admin'] == True
+    assert es['agent'] == "fatcat_tools.IngestFileResultImporter"
+
+    assert es['total'] == 50
+    assert es['files'] == 50
+    assert es['new_files'] == 50
+    assert es['created'] == 50
+
+    assert es['releases'] == 0
+    assert es['new_releases'] == 0
+    assert es['updated'] == 0
+    assert es['deleted'] == 0
-- 
cgit v1.2.3


From d5d83762063b8ec7f512c20567f46c03f2e6b542 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 29 Jan 2020 21:57:32 -0800
Subject: update ES docs and proposal

---
 extra/elasticsearch/README.md           | 2 ++
 proposals/2020_elasticsearch_schemas.md | 8 ++++----
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/extra/elasticsearch/README.md b/extra/elasticsearch/README.md
index 3a48a178..3e0857b4 100644
--- a/extra/elasticsearch/README.md
+++ b/extra/elasticsearch/README.md
@@ -40,9 +40,11 @@ Drop and rebuild the schema:
 
     http delete :9200/fatcat_release
     http delete :9200/fatcat_container
+    http delete :9200/fatcat_file
     http delete :9200/fatcat_changelog
     http put :9200/fatcat_release < release_schema.json
     http put :9200/fatcat_container < container_schema.json
+    http put :9200/fatcat_file < file_schema.json
     http put :9200/fatcat_changelog < changelog_schema.json
 
 Put a single object (good for debugging):
diff --git a/proposals/2020_elasticsearch_schemas.md b/proposals/2020_elasticsearch_schemas.md
index 83db884f..5fb28d19 100644
--- a/proposals/2020_elasticsearch_schemas.md
+++ b/proposals/2020_elasticsearch_schemas.md
@@ -14,8 +14,6 @@ Simple additions:
 - pages
 - `first_page` (parsed from pages) (?)
 - number
-- `in_shadow`
-- OA license slug (?)
 - `doi_prefix`
 - `doi_registrar` (based on extra)
 - `first_author` (surname; for matching)
@@ -25,6 +23,8 @@ Simple additions:
 - referenced releases idents
 - contrib creator idents
 
+Add affiliations, both as raw strings and ROR identifiers.
+
 
 ## Preservation Summary Field
 
@@ -128,8 +128,8 @@ hit does not}").
 
 ## Container Fields
 
-- `all_issns`
-- `release_count`
+- `issn` (all issns)
+- `original_name`
 
 The `release_count` would not be indexed (left null) by default, and would be
 "patched" in to entities by a separate script (periodically?).
-- 
cgit v1.2.3


From bf718fd076476c1a54e80ca88cd02ede606ab6f3 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 29 Jan 2020 23:23:39 -0800
Subject: add country to v03b release schema

---
 extra/elasticsearch/release_schema.json         | 1 +
 python/fatcat_tools/transforms/elasticsearch.py | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/extra/elasticsearch/release_schema.json b/extra/elasticsearch/release_schema.json
index 98a1c28e..2b67c5f5 100644
--- a/extra/elasticsearch/release_schema.json
+++ b/extra/elasticsearch/release_schema.json
@@ -40,6 +40,7 @@
             "release_stage":  { "type": "keyword" },
             "withdrawn_status": { "type": "keyword", "copy_to": "biblio" },
             "language":       { "type": "keyword" },
+            "country":        { "type": "keyword" },
             "volume":         { "type": "keyword", "copy_to": "biblio" },
             "issue":          { "type": "keyword", "copy_to": "biblio" },
             "pages":          { "type": "keyword", "copy_to": "biblio" },
diff --git a/python/fatcat_tools/transforms/elasticsearch.py b/python/fatcat_tools/transforms/elasticsearch.py
index c8547b27..f0146d01 100644
--- a/python/fatcat_tools/transforms/elasticsearch.py
+++ b/python/fatcat_tools/transforms/elasticsearch.py
@@ -155,6 +155,8 @@ def release_to_elasticsearch(entity, force_bool=True):
             if c_extra.get('szczepanski'):
                 if c_extra['szczepanski'].get('as_of'):
                     is_oa = True
+            if c_extra.get('country'):
+                t['country'] = c_extra['country']
 
     # fall back to release-level container metadata if container not linked or
     # missing context
-- 
cgit v1.2.3


From e98f389a53d886b4fa8f0237b90b086999770f78 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 29 Jan 2020 23:26:58 -0800
Subject: elastic schema fixes

---
 extra/elasticsearch/file_schema.json            | 12 ++++++------
 extra/elasticsearch/release_schema.json         |  2 +-
 python/fatcat_tools/transforms/elasticsearch.py |  5 +++++
 3 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/extra/elasticsearch/file_schema.json b/extra/elasticsearch/file_schema.json
index 66d81e0b..2a7e5be0 100644
--- a/extra/elasticsearch/file_schema.json
+++ b/extra/elasticsearch/file_schema.json
@@ -13,7 +13,7 @@
     }
 },
 "mappings": {
-    "changelog": {
+    "file": {
         "properties": {
             "ident":            { "type": "keyword", "doc_values": false },
             "state":            { "type": "keyword" },
@@ -33,13 +33,13 @@
             "in_ia":            { "type": "boolean" },
 
             "release_id":       { "type": "alias", "path": "release_ids" },
-            "sha1hex":          { "type": "alias", "path": "sha1hex" },
-            "sha256hex":        { "type": "alias", "path": "sha256hex" },
-            "md5hex":           { "type": "alias", "path": "md5hex" },
+            "sha1hex":          { "type": "alias", "path": "sha1" },
+            "sha256hex":        { "type": "alias", "path": "sha256" },
+            "md5hex":           { "type": "alias", "path": "md5" },
             "size":             { "type": "alias", "path": "size_bytes" },
             "domain":           { "type": "alias", "path": "domains" },
-            "host":             { "type": "alias", "path": "host" },
-            "rel":              { "type": "alias", "path": "rel" }
+            "host":             { "type": "alias", "path": "hosts" },
+            "rel":              { "type": "alias", "path": "rels" }
         }
     }
 }
diff --git a/extra/elasticsearch/release_schema.json b/extra/elasticsearch/release_schema.json
index 2b67c5f5..3d301dba 100644
--- a/extra/elasticsearch/release_schema.json
+++ b/extra/elasticsearch/release_schema.json
@@ -99,7 +99,7 @@
 
             "affilation":     { "type": "alias", "path": "affiliations" },
             "ror":            { "type": "alias", "path": "affiliation_rors" },
-            "creator_id":     { "type": "alias", "path": "creator_id" },
+            "creator_id":     { "type": "alias", "path": "creator_ids" },
             "ref_release_id": { "type": "alias", "path": "ref_release_ids" },
             "author":         { "type": "alias", "path": "contrib_names" },
             "journal":        { "type": "alias", "path": "container_name" },
diff --git a/python/fatcat_tools/transforms/elasticsearch.py b/python/fatcat_tools/transforms/elasticsearch.py
index f0146d01..42669bbf 100644
--- a/python/fatcat_tools/transforms/elasticsearch.py
+++ b/python/fatcat_tools/transforms/elasticsearch.py
@@ -416,6 +416,11 @@ def _type_of_edit(edit):
 
 
 def changelog_to_elasticsearch(entity):
+    """
+    Note that this importer requires expanded fill info to work. Calling code
+    may need to re-fetch editgroup from API to get the 'editor' field. Some of
+    the old kafka feed content doesn't includes editor in particular.
+    """
 
     editgroup = entity.editgroup
     t = dict(
-- 
cgit v1.2.3


From 749295a16dd18aa64b87f6b7c3e0e6052931161a Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 29 Jan 2020 23:54:17 -0800
Subject: new biblio-only general search

The other fields are now "copy_to" the merged biblio field.
---
 python/fatcat_web/search.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/python/fatcat_web/search.py b/python/fatcat_web/search.py
index 7c60a6dd..6b2b9cc1 100644
--- a/python/fatcat_web/search.py
+++ b/python/fatcat_web/search.py
@@ -77,7 +77,7 @@ def do_release_search(q, limit=30, fulltext_only=True, offset=0):
                 "default_operator": "AND",
                 "analyze_wildcard": True,
                 "lenient": True,
-                "fields": ["title^5", "contrib_names^2", "container_title"],
+                "fields": ["biblio"],
             },
         },
     }
@@ -106,7 +106,7 @@ def do_container_search(q, limit=30, offset=0):
                 "default_operator": "AND",
                 "analyze_wildcard": True,
                 "lenient": True,
-                "fields": ["name^5", "publisher"],
+                "fields": ["biblio"],
             },
         },
     }
-- 
cgit v1.2.3


From ade1eb9ff955ca5ba58acdc8b76e344c9cc54790 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 29 Jan 2020 23:56:27 -0800
Subject: fix ES file schema plural field names

---
 python/fatcat_tools/transforms/elasticsearch.py | 7 +++----
 python/tests/transform_elasticsearch.py         | 2 +-
 2 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/python/fatcat_tools/transforms/elasticsearch.py b/python/fatcat_tools/transforms/elasticsearch.py
index 42669bbf..5a492fb4 100644
--- a/python/fatcat_tools/transforms/elasticsearch.py
+++ b/python/fatcat_tools/transforms/elasticsearch.py
@@ -497,13 +497,12 @@ def file_to_elasticsearch(entity):
         sha1 = entity.sha1,
         sha256 = entity.sha256,
         md5 = entity.md5,
-        rel = [u.rel for u in entity.urls],
     )
 
     # TODO: domain, hosts (from urls; use proper urlcanon)
-    t['rel'] = list(set([u.rel for u in entity.urls]))
-    t['host'] = []
-    t['domain'] = []
+    t['rels'] = list(set([u.rel for u in entity.urls]))
+    t['hosts'] = []
+    t['domains'] = []
 
     in_ia = False
     for u in entity.urls:
diff --git a/python/tests/transform_elasticsearch.py b/python/tests/transform_elasticsearch.py
index 89a4eef8..c247e745 100644
--- a/python/tests/transform_elasticsearch.py
+++ b/python/tests/transform_elasticsearch.py
@@ -106,7 +106,7 @@ def test_elasticsearch_file_transform(matched_importer):
     assert es['size_bytes'] == f.size
     assert es['mimetype'] == f.mimetype
     assert es['in_ia'] == True
-    assert 'web' in es['rel']
+    assert 'web' in es['rels']
 
     # XXX: implement hosts and domain parsing with urlcanon
     #assert 'journals.plos.org' in es['host']
-- 
cgit v1.2.3


From 461376e6c6107da9a1c0a41c379465ef1c39f051 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 29 Jan 2020 23:56:47 -0800
Subject: pipenv: add tldextract (url parser) and update deps

---
 python/Pipfile      |   1 +
 python/Pipfile.lock | 294 ++++++++++++++++++++++++++++------------------------
 2 files changed, 159 insertions(+), 136 deletions(-)

diff --git a/python/Pipfile b/python/Pipfile
index 1a19a145..a5389e4f 100644
--- a/python/Pipfile
+++ b/python/Pipfile
@@ -51,6 +51,7 @@ dateparser = ">=0.7"
 langdetect = "*"
 pathlib2 = "*"
 pycountry = "*"
+tldextract = "*"
 
 [requires]
 # Python 3.5 is the bundled (system) version of python for Ubuntu 16.04
diff --git a/python/Pipfile.lock b/python/Pipfile.lock
index d813dd32..f3cbfbd6 100644
--- a/python/Pipfile.lock
+++ b/python/Pipfile.lock
@@ -1,7 +1,7 @@
 {
     "_meta": {
         "hash": {
-            "sha256": "edac46fb8a4b49aea89946621337abba881fff6f6768107d2529c752bcf702ac"
+            "sha256": "8288b1a7102a0a34644ef56817d60e936dc57695604208036f229e96bc14c42f"
         },
         "pipfile-spec": 6,
         "requires": {
@@ -235,6 +235,7 @@
         },
         "flask-misaka": {
             "hashes": [
+                "sha256:bcfdacc0803ccea75d377737e82c83489b2153d922c9d9f9eabc5148d216ed70",
                 "sha256:d0cfb0efd9e5afacda76defd4a605a68390f4fb1bef283c71534fd3ce0d3efb5",
                 "sha256:f423c3beb5502742a57330a272f81d53223f6f99d45cc45b03926e3a3034f589"
             ],
@@ -292,10 +293,10 @@
         },
         "jinja2": {
             "hashes": [
-                "sha256:74320bb91f31270f9551d46522e33af46a80c3d619f4a4bf42b3164d30b5911f",
-                "sha256:9fe95f19286cfefaa917656583d020be14e7859c6b0252588391e47db34527de"
+                "sha256:6e7a3c2934694d59ad334c93dd1b6c96699cf24c53fdb8ec848ac6b23e685734",
+                "sha256:d6609ae5ec3d56212ca7d802eda654eaf2310000816ce815361041465b108be4"
             ],
-            "version": "==2.10.3"
+            "version": "==2.11.0"
         },
         "kazoo": {
             "hashes": [
@@ -321,34 +322,35 @@
         },
         "lxml": {
             "hashes": [
-                "sha256:00ac0d64949fef6b3693813fe636a2d56d97a5a49b5bbb86e4cc4cc50ebc9ea2",
-                "sha256:0571e607558665ed42e450d7bf0e2941d542c18e117b1ebbf0ba72f287ad841c",
-                "sha256:0e3f04a7615fdac0be5e18b2406529521d6dbdb0167d2a690ee328bef7807487",
-                "sha256:13cf89be53348d1c17b453867da68704802966c433b2bb4fa1f970daadd2ef70",
-                "sha256:217262fcf6a4c2e1c7cb1efa08bd9ebc432502abc6c255c4abab611e8be0d14d",
-                "sha256:223e544828f1955daaf4cefbb4853bc416b2ec3fd56d4f4204a8b17007c21250",
-                "sha256:277cb61fede2f95b9c61912fefb3d43fbd5f18bf18a14fae4911b67984486f5d",
-                "sha256:3213f753e8ae86c396e0e066866e64c6b04618e85c723b32ecb0909885211f74",
-                "sha256:4690984a4dee1033da0af6df0b7a6bde83f74e1c0c870623797cec77964de34d",
-                "sha256:4fcc472ef87f45c429d3b923b925704aa581f875d65bac80f8ab0c3296a63f78",
-                "sha256:61409bd745a265a742f2693e4600e4dbd45cc1daebe1d5fad6fcb22912d44145",
-                "sha256:678f1963f755c5d9f5f6968dded7b245dd1ece8cf53c1aa9d80e6734a8c7f41d",
-                "sha256:6c6d03549d4e2734133badb9ab1c05d9f0ef4bcd31d83e5d2b4747c85cfa21da",
-                "sha256:6e74d5f4d6ecd6942375c52ffcd35f4318a61a02328f6f1bd79fcb4ffedf969e",
-                "sha256:7b4fc7b1ecc987ca7aaf3f4f0e71bbfbd81aaabf87002558f5bc95da3a865bcd",
-                "sha256:7ed386a40e172ddf44c061ad74881d8622f791d9af0b6f5be20023029129bc85",
-                "sha256:8f54f0924d12c47a382c600c880770b5ebfc96c9fd94cf6f6bdc21caf6163ea7",
-                "sha256:ad9b81351fdc236bda538efa6879315448411a81186c836d4b80d6ca8217cdb9",
-                "sha256:bbd00e21ea17f7bcc58dccd13869d68441b32899e89cf6cfa90d624a9198ce85",
-                "sha256:c3c289762cc09735e2a8f8a49571d0e8b4f57ea831ea11558247b5bdea0ac4db",
-                "sha256:cf4650942de5e5685ad308e22bcafbccfe37c54aa7c0e30cd620c2ee5c93d336",
-                "sha256:cfcbc33c9c59c93776aa41ab02e55c288a042211708b72fdb518221cc803abc8",
-                "sha256:e301055deadfedbd80cf94f2f65ff23126b232b0d1fea28f332ce58137bcdb18",
-                "sha256:ebbfe24df7f7b5c6c7620702496b6419f6a9aa2fd7f005eb731cc80d7b4692b9",
-                "sha256:eff69ddbf3ad86375c344339371168640951c302450c5d3e9936e98d6459db06",
-                "sha256:f6ed60a62c5f1c44e789d2cf14009423cb1646b44a43e40a9cf6a21f077678a1"
-            ],
-            "version": "==4.4.2"
+                "sha256:06d4e0bbb1d62e38ae6118406d7cdb4693a3fa34ee3762238bcb96c9e36a93cd",
+                "sha256:0701f7965903a1c3f6f09328c1278ac0eee8f56f244e66af79cb224b7ef3801c",
+                "sha256:1f2c4ec372bf1c4a2c7e4bb20845e8bcf8050365189d86806bad1e3ae473d081",
+                "sha256:4235bc124fdcf611d02047d7034164897ade13046bda967768836629bc62784f",
+                "sha256:5828c7f3e615f3975d48f40d4fe66e8a7b25f16b5e5705ffe1d22e43fb1f6261",
+                "sha256:585c0869f75577ac7a8ff38d08f7aac9033da2c41c11352ebf86a04652758b7a",
+                "sha256:5d467ce9c5d35b3bcc7172c06320dddb275fea6ac2037f72f0a4d7472035cea9",
+                "sha256:63dbc21efd7e822c11d5ddbedbbb08cd11a41e0032e382a0fd59b0b08e405a3a",
+                "sha256:7bc1b221e7867f2e7ff1933165c0cec7153dce93d0cdba6554b42a8beb687bdb",
+                "sha256:8620ce80f50d023d414183bf90cc2576c2837b88e00bea3f33ad2630133bbb60",
+                "sha256:8a0ebda56ebca1a83eb2d1ac266649b80af8dd4b4a3502b2c1e09ac2f88fe128",
+                "sha256:90ed0e36455a81b25b7034038e40880189169c308a3df360861ad74da7b68c1a",
+                "sha256:95e67224815ef86924fbc2b71a9dbd1f7262384bca4bc4793645794ac4200717",
+                "sha256:afdb34b715daf814d1abea0317b6d672476b498472f1e5aacbadc34ebbc26e89",
+                "sha256:b4b2c63cc7963aedd08a5f5a454c9f67251b1ac9e22fd9d72836206c42dc2a72",
+                "sha256:d068f55bda3c2c3fcaec24bd083d9e2eede32c583faf084d6e4b9daaea77dde8",
+                "sha256:d5b3c4b7edd2e770375a01139be11307f04341ec709cf724e0f26ebb1eef12c3",
+                "sha256:deadf4df349d1dcd7b2853a2c8796593cc346600726eff680ed8ed11812382a7",
+                "sha256:df533af6f88080419c5a604d0d63b2c33b1c0c4409aba7d0cb6de305147ea8c8",
+                "sha256:e4aa948eb15018a657702fee0b9db47e908491c64d36b4a90f59a64741516e77",
+                "sha256:e5d842c73e4ef6ed8c1bd77806bf84a7cb535f9c0cf9b2c74d02ebda310070e1",
+                "sha256:ebec08091a22c2be870890913bdadd86fcd8e9f0f22bcb398abd3af914690c15",
+                "sha256:edc15fcfd77395e24543be48871c251f38132bb834d9fdfdad756adb6ea37679",
+                "sha256:f2b74784ed7e0bc2d02bd53e48ad6ba523c9b36c194260b7a5045071abbb1012",
+                "sha256:fa071559f14bd1e92077b1b5f6c22cf09756c6de7139370249eb372854ce51e6",
+                "sha256:fd52e796fee7171c4361d441796b64df1acfceb51f29e545e812f16d023c4bbc",
+                "sha256:fe976a0f1ef09b3638778024ab9fb8cde3118f203364212c198f71341c0715ca"
+            ],
+            "version": "==4.5.0"
         },
         "markupsafe": {
             "hashes": [
@@ -356,13 +358,16 @@
                 "sha256:09027a7803a62ca78792ad89403b1b7a73a01c8cb65909cd876f7fcebd79b161",
                 "sha256:09c4b7f37d6c648cb13f9230d847adf22f8171b1ccc4d5682398e77f40309235",
                 "sha256:1027c282dad077d0bae18be6794e6b6b8c91d58ed8a8d89a89d59693b9131db5",
+                "sha256:13d3144e1e340870b25e7b10b98d779608c02016d5184cfb9927a9f10c689f42",
                 "sha256:24982cc2533820871eba85ba648cd53d8623687ff11cbb805be4ff7b4c971aff",
                 "sha256:29872e92839765e546828bb7754a68c418d927cd064fd4708fab9fe9c8bb116b",
                 "sha256:43a55c2930bbc139570ac2452adf3d70cdbb3cfe5912c71cdce1c2c6bbd9c5d1",
                 "sha256:46c99d2de99945ec5cb54f23c8cd5689f6d7177305ebff350a58ce5f8de1669e",
                 "sha256:500d4957e52ddc3351cabf489e79c91c17f6e0899158447047588650b5e69183",
                 "sha256:535f6fc4d397c1563d08b88e485c3496cf5784e927af890fb3c3aac7f933ec66",
+                "sha256:596510de112c685489095da617b5bcbbac7dd6384aeebeda4df6025d0256a81b",
                 "sha256:62fe6c95e3ec8a7fad637b7f3d372c15ec1caa01ab47926cfdf7a75b40e0eac1",
+                "sha256:6788b695d50a51edb699cb55e35487e430fa21f1ed838122d722e0ff0ac5ba15",
                 "sha256:6dd73240d2af64df90aa7c4e7481e23825ea70af4b4922f8ede5b9e35f78a3b1",
                 "sha256:717ba8fe3ae9cc0006d7c451f0bb265ee07739daf76355d06366154ee68d221e",
                 "sha256:79855e1c5b8da654cf486b830bd42c06e8780cea587384cf6545b7d9ac013a0b",
@@ -379,7 +384,9 @@
                 "sha256:ba59edeaa2fc6114428f1637ffff42da1e311e29382d81b339c1817d37ec93c6",
                 "sha256:c8716a48d94b06bb3b2524c2b77e055fb313aeb4ea620c8dd03a105574ba704f",
                 "sha256:cd5df75523866410809ca100dc9681e301e3c27567cf498077e8551b6d20e42f",
-                "sha256:e249096428b3ae81b08327a63a485ad0878de3fb939049038579ac0ef61e17e7"
+                "sha256:cdb132fc825c38e1aeec2c8aa9338310d29d337bebbd7baa06889d09a60a1fa2",
+                "sha256:e249096428b3ae81b08327a63a485ad0878de3fb939049038579ac0ef61e17e7",
+                "sha256:e8313f01ba26fbbe36c7be1966a7b7424942f670f38e666995b88d012765b9be"
             ],
             "version": "==1.1.1"
         },
@@ -442,6 +449,7 @@
         },
         "pykafka": {
             "hashes": [
+                "sha256:6b075909a52cb0c95325bc16ab797bbcdbb37386652ea460705ed4472ce91459",
                 "sha256:f0bbd394ae6970042a587c99fe4dc0966e67787249d963d4ce2f810dc9490577"
             ],
             "index": "pypi",
@@ -498,11 +506,11 @@
         },
         "python-dotenv": {
             "hashes": [
-                "sha256:debd928b49dbc2bf68040566f55cdb3252458036464806f4094487244e2a4093",
-                "sha256:f157d71d5fec9d4bd5f51c82746b6344dffa680ee85217c123f4a0c8117c4544"
+                "sha256:440c7c23d53b7d352f9c94d6f70860242c2f071cf5c029dd661ccb22d64ae42b",
+                "sha256:f254bfd0c970d64ccbb6c9ebef3667ab301a71473569c991253a481f1c98dddc"
             ],
             "index": "pypi",
-            "version": "==0.10.3"
+            "version": "==0.10.5"
         },
         "python-magic": {
             "hashes": [
@@ -528,9 +536,6 @@
             "version": "==2019.3"
         },
         "raven": {
-            "extras": [
-                "flask"
-            ],
             "hashes": [
                 "sha256:3fa6de6efa2493a7c827472e984ce9b020797d0da16f1db67197bcc23c8fae54",
                 "sha256:44a13f87670836e153951af9a3c80405d36b43097db869a36e92809673692ce4"
@@ -572,27 +577,35 @@
             "index": "pypi",
             "version": "==2.22.0"
         },
+        "requests-file": {
+            "hashes": [
+                "sha256:75c175eed739270aec3c5279ffd74e6527dada275c5c0d76b5817e9c86bb7dea",
+                "sha256:8f04aa6201bacda0567e7ac7f677f1499b0fc76b22140c54bc06edf1ba92e2fa"
+            ],
+            "version": "==1.4.3"
+        },
         "requests-oauthlib": {
             "hashes": [
                 "sha256:7f71572defaecd16372f9006f33c2ec8c077c3cfa6f5911a9a90202beb513f3d",
-                "sha256:b4261601a71fd721a8bd6d7aa1cc1d6a8a93b4a9f5e96626f8e4d91e8beeaa6a"
+                "sha256:b4261601a71fd721a8bd6d7aa1cc1d6a8a93b4a9f5e96626f8e4d91e8beeaa6a",
+                "sha256:fa6c47b933f01060936d87ae9327fead68768b69c6c9ea2109c48be30f2d4dbc"
             ],
             "version": "==1.3.0"
         },
         "sickle": {
             "hashes": [
-                "sha256:76d66ed4607af2cd36ee15568a98e7f147d4ec3dd227bd047664a1ca88b21944",
-                "sha256:b0aaa41d97a0c355aa6099b4dfa46c03f0bf828e6171960a15d68bd0548215ec"
+                "sha256:c0841b4df5edea33d2da01e893b3feadb1a8eacd2ca4dab9248e6047455ba14a",
+                "sha256:efdfa46c40cd34b3550f11b59c607ff0bd63adbc074efaa8b4dd662108269a2f"
             ],
             "index": "pypi",
-            "version": "==0.6.4"
+            "version": "==0.6.5"
         },
         "six": {
             "hashes": [
-                "sha256:1f1b7d42e254082a9db6279deae68afb421ceba6158efa6131de7b3003ee93fd",
-                "sha256:30f610279e8b2578cab6db20741130331735c781b56053c59c4076da27f06b66"
+                "sha256:236bdbdce46e6e6a3d61a337c0f8b763ca1e8717c03b369e87a7ec7ce1319c0a",
+                "sha256:8f3cd2e254d8f793e7f3d6d9df77b92252b52637291d0f0da013c76ea2724b6c"
             ],
-            "version": "==1.13.0"
+            "version": "==1.14.0"
         },
         "soupsieve": {
             "hashes": [
@@ -607,6 +620,14 @@
             ],
             "version": "==0.8.6"
         },
+        "tldextract": {
+            "hashes": [
+                "sha256:16b2f7e81d89c2a5a914d25bdbddd3932c31a6b510db886c3ce0764a195c0ee7",
+                "sha256:9aa21a1f7827df4209e242ec4fc2293af5940ec730cde46ea80f66ed97bfc808"
+            ],
+            "index": "pypi",
+            "version": "==2.2.2"
+        },
         "tzlocal": {
             "hashes": [
                 "sha256:11c9f16e0a633b4b60e1eede97d8a46340d042e67b670b290ca526576e039048",
@@ -616,10 +637,10 @@
         },
         "urllib3": {
             "hashes": [
-                "sha256:a8a318824cc77d1fd4b2bec2ded92646630d7fe8619497b142c84a9e6f5a7293",
-                "sha256:f3c5fd51747d450d4dcf6f923c81f78f811aab8205fda64b0aba34a4e48b0745"
+                "sha256:2f3db8b19923a873b3e5256dc9c2dedfa883e33d87c690d9c7913e1f40673cdc",
+                "sha256:87716c2d2a7121198ebcb7ce7cccf6ce5e9ba539041cfbaeecfb641dc0bf6acc"
             ],
-            "version": "==1.25.7"
+            "version": "==1.25.8"
         },
         "wcwidth": {
             "hashes": [
@@ -630,10 +651,10 @@
         },
         "werkzeug": {
             "hashes": [
-                "sha256:7280924747b5733b246fe23972186c6b348f9ae29724135a6dfc1e53cea433e7",
-                "sha256:e5f4a1f98b52b18a93da705a7458e55afb26f32bff83ff5d19189f92462d65c4"
+                "sha256:1e0dedc2acb1f46827daa2e399c1485c8fa17c0d8e70b6b875b4e7f54bf408d2",
+                "sha256:b353856d37dec59d6511359f97f6a4b2468442e454bd1c98298ddce53cac1f04"
             ],
-            "version": "==0.16.0"
+            "version": "==0.16.1"
         },
         "wtforms": {
             "hashes": [
@@ -682,39 +703,39 @@
         },
         "coverage": {
             "hashes": [
-                "sha256:189aac76d6e0d7af15572c51892e7326ee451c076c5a50a9d266406cd6c49708",
-                "sha256:1bf7ba2af1d373a1750888724f84cffdfc697738f29a353c98195f98fc011509",
-                "sha256:1f4ee8e2e4243971618bc16fcc4478317405205f135e95226c2496e2a3b8dbbf",
-                "sha256:225e79a5d485bc1642cb7ba02281419c633c216cdc6b26c26494ba959f09e69f",
-                "sha256:23688ff75adfa8bfa2a67254d889f9bdf9302c27241d746e17547c42c732d3f4",
-                "sha256:28f7f73b34a05e23758e860a89a7f649b85c6749e252eff60ebb05532d180e86",
-                "sha256:2d0cb9b1fe6ad0d915d45ad3d87f03a38e979093a98597e755930db1f897afae",
-                "sha256:47874b4711c5aeb295c31b228a758ce3d096be83dc37bd56da48ed99efb8813b",
-                "sha256:511ec0c00840e12fb4e852e4db58fa6a01ca4da72f36a9766fae344c3d502033",
-                "sha256:53e7438fef0c97bc248f88ba1edd10268cd94d5609970aaf87abbe493691af87",
-                "sha256:569f9ee3025682afda6e9b0f5bb14897c0db03f1a1dc088b083dd36e743f92bb",
-                "sha256:593853aa1ac6dcc6405324d877544c596c9d948ef20d2e9512a0f5d2d3202356",
-                "sha256:5b0a07158360d22492f9abd02a0f2ee7981b33f0646bf796598b7673f6bbab14",
-                "sha256:7ca3db38a61f3655a2613ee2c190d63639215a7a736d3c64cc7bbdb002ce6310",
-                "sha256:7d1cc7acc9ce55179616cf72154f9e648136ea55987edf84addbcd9886ffeba2",
-                "sha256:88b51153657612aea68fa684a5b88037597925260392b7bb4509d4f9b0bdd889",
-                "sha256:955ec084f549128fa2702f0b2dc696392001d986b71acd8fd47424f28289a9c3",
-                "sha256:b251c7092cbb6d789d62dc9c9e7c4fb448c9138b51285c36aeb72462cad3600e",
-                "sha256:bd82b684bb498c60ef47bb1541a50e6d006dde8579934dcbdbc61d67d1ea70d9",
-                "sha256:bfe102659e2ec13b86c7f3b1db6c9a4e7beea4255058d006351339e6b342d5d2",
-                "sha256:c1e4e39e43057396a5e9d069bfbb6ffeee892e40c5d2effbd8cd71f34ee66c4d",
-                "sha256:cb2b74c123f65e8166f7e1265829a6c8ed755c3cd16d7f50e75a83456a5f3fd7",
-                "sha256:cca38ded59105f7705ef6ffe1e960b8db6c7d8279c1e71654a4775ab4454ca15",
-                "sha256:cf908840896f7aa62d0ec693beb53264b154f972eb8226fb864ac38975590c4f",
-                "sha256:d095a7b473f8a95f7efe821f92058c8a2ecfb18f8db6677ae3819e15dc11aaae",
-                "sha256:d22b4297e7e4225ccf01f1aa55e7a96412ea0796b532dd614c3fcbafa341128e",
-                "sha256:d4a2b578a7a70e0c71f662705262f87a456f1e6c1e40ada7ea699abaf070a76d",
-                "sha256:ddeb42a3d5419434742bf4cc71c9eaa22df3b76808e23a82bd0b0bd360f1a9f1",
-                "sha256:e65a5aa1670db6263f19fdc03daee1d7dbbadb5cb67fd0a1f16033659db13c1d",
-                "sha256:eaad65bd20955131bcdb3967a4dea66b4e4d4ca488efed7c00d91ee0173387e8",
-                "sha256:f45fba420b94165c17896861bb0e8b27fb7abdcedfeb154895d8553df90b7b00"
-            ],
-            "version": "==5.0.2"
+                "sha256:15cf13a6896048d6d947bf7d222f36e4809ab926894beb748fc9caa14605d9c3",
+                "sha256:1daa3eceed220f9fdb80d5ff950dd95112cd27f70d004c7918ca6dfc6c47054c",
+                "sha256:1e44a022500d944d42f94df76727ba3fc0a5c0b672c358b61067abb88caee7a0",
+                "sha256:25dbf1110d70bab68a74b4b9d74f30e99b177cde3388e07cc7272f2168bd1477",
+                "sha256:3230d1003eec018ad4a472d254991e34241e0bbd513e97a29727c7c2f637bd2a",
+                "sha256:3dbb72eaeea5763676a1a1efd9b427a048c97c39ed92e13336e726117d0b72bf",
+                "sha256:5012d3b8d5a500834783689a5d2292fe06ec75dc86ee1ccdad04b6f5bf231691",
+                "sha256:51bc7710b13a2ae0c726f69756cf7ffd4362f4ac36546e243136187cfcc8aa73",
+                "sha256:527b4f316e6bf7755082a783726da20671a0cc388b786a64417780b90565b987",
+                "sha256:722e4557c8039aad9592c6a4213db75da08c2cd9945320220634f637251c3894",
+                "sha256:76e2057e8ffba5472fd28a3a010431fd9e928885ff480cb278877c6e9943cc2e",
+                "sha256:77afca04240c40450c331fa796b3eab6f1e15c5ecf8bf2b8bee9706cd5452fef",
+                "sha256:7afad9835e7a651d3551eab18cbc0fdb888f0a6136169fbef0662d9cdc9987cf",
+                "sha256:9bea19ac2f08672636350f203db89382121c9c2ade85d945953ef3c8cf9d2a68",
+                "sha256:a8b8ac7876bc3598e43e2603f772d2353d9931709345ad6c1149009fd1bc81b8",
+                "sha256:b0840b45187699affd4c6588286d429cd79a99d509fe3de0f209594669bb0954",
+                "sha256:b26aaf69713e5674efbde4d728fb7124e429c9466aeaf5f4a7e9e699b12c9fe2",
+                "sha256:b63dd43f455ba878e5e9f80ba4f748c0a2156dde6e0e6e690310e24d6e8caf40",
+                "sha256:be18f4ae5a9e46edae3f329de2191747966a34a3d93046dbdf897319923923bc",
+                "sha256:c312e57847db2526bc92b9bfa78266bfbaabac3fdcd751df4d062cd4c23e46dc",
+                "sha256:c60097190fe9dc2b329a0eb03393e2e0829156a589bd732e70794c0dd804258e",
+                "sha256:c62a2143e1313944bf4a5ab34fd3b4be15367a02e9478b0ce800cb510e3bbb9d",
+                "sha256:cc1109f54a14d940b8512ee9f1c3975c181bbb200306c6d8b87d93376538782f",
+                "sha256:cd60f507c125ac0ad83f05803063bed27e50fa903b9c2cfee3f8a6867ca600fc",
+                "sha256:d513cc3db248e566e07a0da99c230aca3556d9b09ed02f420664e2da97eac301",
+                "sha256:d649dc0bcace6fcdb446ae02b98798a856593b19b637c1b9af8edadf2b150bea",
+                "sha256:d7008a6796095a79544f4da1ee49418901961c97ca9e9d44904205ff7d6aa8cb",
+                "sha256:da93027835164b8223e8e5af2cf902a4c80ed93cb0909417234f4a9df3bcd9af",
+                "sha256:e69215621707119c6baf99bda014a45b999d37602cb7043d943c76a59b05bf52",
+                "sha256:ea9525e0fef2de9208250d6c5aeeee0138921057cd67fcef90fbed49c4d62d37",
+                "sha256:fca1669d464f0c9831fd10be2eef6b86f5ebd76c724d1e0706ebdff86bb4adf0"
+            ],
+            "version": "==5.0.3"
         },
         "decorator": {
             "hashes": [
@@ -732,11 +753,11 @@
         },
         "importlib-metadata": {
             "hashes": [
-                "sha256:073a852570f92da5f744a3472af1b61e28e9f78ccf0c9117658dc32b15de7b45",
-                "sha256:d95141fbfa7ef2ec65cfd945e2af7e5a6ddbd7c8d9a25e66ff3be8e3daf9f60f"
+                "sha256:06f5b3a99029c7134207dd882428a66992a9de2bef7c2b699b5641f9886c3302",
+                "sha256:b97607a1a18a5100839aec1dc26a1ea17ee0d93b20b0f008d80a5a050afb200b"
             ],
             "markers": "python_version < '3.8'",
-            "version": "==1.3.0"
+            "version": "==1.5.0"
         },
         "ipython": {
             "hashes": [
@@ -762,10 +783,10 @@
         },
         "jedi": {
             "hashes": [
-                "sha256:1349c1e8c107095a55386628bb3b2a79422f3a2cab8381e34ce19909e0cf5064",
-                "sha256:e909527104a903606dd63bea6e8e888833f0ef087057829b89a18364a856f807"
+                "sha256:b4f4052551025c6b0b0b193b29a6ff7bdb74c52450631206c262aef9f7159ad2",
+                "sha256:d5c871cb9360b414f981e7072c52c33258d598305280fef91c6cae34739d65d5"
             ],
-            "version": "==0.15.2"
+            "version": "==0.16.0"
         },
         "lazy-object-proxy": {
             "hashes": [
@@ -802,24 +823,24 @@
         },
         "more-itertools": {
             "hashes": [
-                "sha256:b84b238cce0d9adad5ed87e745778d20a3f8487d0f0cb8b8a586816c7496458d",
-                "sha256:c833ef592a0324bcc6a60e48440da07645063c453880c9477ceb22490aec1564"
+                "sha256:5dd8bcf33e5f9513ffa06d5ad33d78f31e1931ac9a18f33d37e77a180d393a7c",
+                "sha256:b1ddb932186d8a6ac451e1d95844b382f55e12686d51ca0c68b6f61f2ab7a507"
             ],
-            "version": "==8.0.2"
+            "version": "==8.2.0"
         },
         "packaging": {
             "hashes": [
-                "sha256:aec3fdbb8bc9e4bb65f0634b9f551ced63983a529d6a8931817d52fdd0816ddb",
-                "sha256:fe1d8331dfa7cc0a883b49d75fc76380b2ab2734b220fbb87d774e4fd4b851f8"
+                "sha256:170748228214b70b672c581a3dd610ee51f733018650740e98c7df862a583f73",
+                "sha256:e665345f9eef0c621aa0bf2f8d78cf6d21904eef16a93f020240b704a57f1334"
             ],
-            "version": "==20.0"
+            "version": "==20.1"
         },
         "parso": {
             "hashes": [
-                "sha256:55cf25df1a35fd88b878715874d2c4dc1ad3f0eebd1e0266a67e1f55efccfbe1",
-                "sha256:5c1f7791de6bd5dbbeac8db0ef5594b36799de198b3f7f7014643b0c5536b9d3"
+                "sha256:1376bdc8cb81377ca481976933773295218a2df47d3e1182ba76d372b1acb128",
+                "sha256:597f36de5102a8db05ffdf7ecdc761838b86565a4a111604c6e78beaedf1b045"
             ],
-            "version": "==0.5.2"
+            "version": "==0.6.0"
         },
         "pathlib2": {
             "hashes": [
@@ -831,11 +852,11 @@
         },
         "pexpect": {
             "hashes": [
-                "sha256:2094eefdfcf37a1fdbfb9aa090862c1a4878e5c7e0e7e7088bdb511c558e5cd1",
-                "sha256:9e2c1fd0e6ee3a49b28f95d4b33bc389c89b20af6a1255906e90ff1262ce62eb"
+                "sha256:0b48a55dcb3c05f3329815901ea4fc1537514d6ba867a152b581d69ae3710937",
+                "sha256:fc65a43959d153d0114afe13997d439c22823a27cefceb5ff35c2178c6784c0c"
             ],
             "markers": "sys_platform != 'win32'",
-            "version": "==4.7.0"
+            "version": "==4.8.0"
         },
         "pg-view": {
             "hashes": [
@@ -922,11 +943,11 @@
         },
         "pytest": {
             "hashes": [
-                "sha256:6b571215b5a790f9b41f19f3531c53a45cf6bb8ef2988bc1ff9afb38270b25fa",
-                "sha256:e41d489ff43948babd0fad7ad5e49b8735d5d55e26628a58673c39ff61d95de4"
+                "sha256:0d5fe9189a148acc3c3eb2ac8e1ac0742cb7618c084f3d228baaec0c254b318d",
+                "sha256:ff615c761e25eb25df19edddc0b970302d2a9091fbce0e7213298d85fb61fef6"
             ],
             "index": "pypi",
-            "version": "==5.3.2"
+            "version": "==5.3.5"
         },
         "pytest-cov": {
             "hashes": [
@@ -984,10 +1005,10 @@
         },
         "six": {
             "hashes": [
-                "sha256:1f1b7d42e254082a9db6279deae68afb421ceba6158efa6131de7b3003ee93fd",
-                "sha256:30f610279e8b2578cab6db20741130331735c781b56053c59c4076da27f06b66"
+                "sha256:236bdbdce46e6e6a3d61a337c0f8b763ca1e8717c03b369e87a7ec7ce1319c0a",
+                "sha256:8f3cd2e254d8f793e7f3d6d9df77b92252b52637291d0f0da013c76ea2724b6c"
             ],
-            "version": "==1.13.0"
+            "version": "==1.14.0"
         },
         "traitlets": {
             "hashes": [
@@ -998,36 +1019,37 @@
         },
         "typed-ast": {
             "hashes": [
-                "sha256:1170afa46a3799e18b4c977777ce137bb53c7485379d9706af8a59f2ea1aa161",
-                "sha256:18511a0b3e7922276346bcb47e2ef9f38fb90fd31cb9223eed42c85d1312344e",
-                "sha256:262c247a82d005e43b5b7f69aff746370538e176131c32dda9cb0f324d27141e",
-                "sha256:2b907eb046d049bcd9892e3076c7a6456c93a25bebfe554e931620c90e6a25b0",
-                "sha256:354c16e5babd09f5cb0ee000d54cfa38401d8b8891eefa878ac772f827181a3c",
-                "sha256:48e5b1e71f25cfdef98b013263a88d7145879fbb2d5185f2a0c79fa7ebbeae47",
-                "sha256:4e0b70c6fc4d010f8107726af5fd37921b666f5b31d9331f0bd24ad9a088e631",
-                "sha256:630968c5cdee51a11c05a30453f8cd65e0cc1d2ad0d9192819df9978984529f4",
-                "sha256:66480f95b8167c9c5c5c87f32cf437d585937970f3fc24386f313a4c97b44e34",
-                "sha256:71211d26ffd12d63a83e079ff258ac9d56a1376a25bc80b1cdcdf601b855b90b",
-                "sha256:7954560051331d003b4e2b3eb822d9dd2e376fa4f6d98fee32f452f52dd6ebb2",
-                "sha256:838997f4310012cf2e1ad3803bce2f3402e9ffb71ded61b5ee22617b3a7f6b6e",
-                "sha256:95bd11af7eafc16e829af2d3df510cecfd4387f6453355188342c3e79a2ec87a",
-                "sha256:bc6c7d3fa1325a0c6613512a093bc2a2a15aeec350451cbdf9e1d4bffe3e3233",
-                "sha256:cc34a6f5b426748a507dd5d1de4c1978f2eb5626d51326e43280941206c209e1",
-                "sha256:d755f03c1e4a51e9b24d899561fec4ccaf51f210d52abdf8c07ee2849b212a36",
-                "sha256:d7c45933b1bdfaf9f36c579671fec15d25b06c8398f113dab64c18ed1adda01d",
-                "sha256:d896919306dd0aa22d0132f62a1b78d11aaf4c9fc5b3410d3c666b818191630a",
-                "sha256:fdc1c9bbf79510b76408840e009ed65958feba92a88833cdceecff93ae8fff66",
-                "sha256:ffde2fbfad571af120fcbfbbc61c72469e72f550d676c3342492a9dfdefb8f12"
+                "sha256:0666aa36131496aed8f7be0410ff974562ab7eeac11ef351def9ea6fa28f6355",
+                "sha256:0c2c07682d61a629b68433afb159376e24e5b2fd4641d35424e462169c0a7919",
+                "sha256:249862707802d40f7f29f6e1aad8d84b5aa9e44552d2cc17384b209f091276aa",
+                "sha256:24995c843eb0ad11a4527b026b4dde3da70e1f2d8806c99b7b4a7cf491612652",
+                "sha256:269151951236b0f9a6f04015a9004084a5ab0d5f19b57de779f908621e7d8b75",
+                "sha256:4083861b0aa07990b619bd7ddc365eb7fa4b817e99cf5f8d9cf21a42780f6e01",
+                "sha256:498b0f36cc7054c1fead3d7fc59d2150f4d5c6c56ba7fb150c013fbc683a8d2d",
+                "sha256:4e3e5da80ccbebfff202a67bf900d081906c358ccc3d5e3c8aea42fdfdfd51c1",
+                "sha256:6daac9731f172c2a22ade6ed0c00197ee7cc1221aa84cfdf9c31defeb059a907",
+                "sha256:715ff2f2df46121071622063fc7543d9b1fd19ebfc4f5c8895af64a77a8c852c",
+                "sha256:73d785a950fc82dd2a25897d525d003f6378d1cb23ab305578394694202a58c3",
+                "sha256:8c8aaad94455178e3187ab22c8b01a3837f8ee50e09cf31f1ba129eb293ec30b",
+                "sha256:8ce678dbaf790dbdb3eba24056d5364fb45944f33553dd5869b7580cdbb83614",
+                "sha256:aaee9905aee35ba5905cfb3c62f3e83b3bec7b39413f0a7f19be4e547ea01ebb",
+                "sha256:bcd3b13b56ea479b3650b82cabd6b5343a625b0ced5429e4ccad28a8973f301b",
+                "sha256:c9e348e02e4d2b4a8b2eedb48210430658df6951fa484e59de33ff773fbd4b41",
+                "sha256:d205b1b46085271b4e15f670058ce182bd1199e56b317bf2ec004b6a44f911f6",
+                "sha256:d43943ef777f9a1c42bf4e552ba23ac77a6351de620aa9acf64ad54933ad4d34",
+                "sha256:d5d33e9e7af3b34a40dc05f498939f0ebf187f07c385fd58d591c533ad8562fe",
+                "sha256:fc0fea399acb12edbf8a628ba8d2312f583bdbdb3335635db062fa98cf71fca4",
+                "sha256:fe460b922ec15dd205595c9b5b99e2f056fd98ae8f9f56b888e7a17dc2b757e7"
             ],
             "markers": "implementation_name == 'cpython' and python_version < '3.8'",
-            "version": "==1.4.0"
+            "version": "==1.4.1"
         },
         "urllib3": {
             "hashes": [
-                "sha256:a8a318824cc77d1fd4b2bec2ded92646630d7fe8619497b142c84a9e6f5a7293",
-                "sha256:f3c5fd51747d450d4dcf6f923c81f78f811aab8205fda64b0aba34a4e48b0745"
+                "sha256:2f3db8b19923a873b3e5256dc9c2dedfa883e33d87c690d9c7913e1f40673cdc",
+                "sha256:87716c2d2a7121198ebcb7ce7cccf6ce5e9ba539041cfbaeecfb641dc0bf6acc"
             ],
-            "version": "==1.25.7"
+            "version": "==1.25.8"
         },
         "wcwidth": {
             "hashes": [
@@ -1044,10 +1066,10 @@
         },
         "zipp": {
             "hashes": [
-                "sha256:3718b1cbcd963c7d4c5511a8240812904164b7f381b647143a89d3b98f9bcd8e",
-                "sha256:f06903e9f1f43b12d371004b4ac7b06ab39a44adc747266928ae6debfa7b3335"
+                "sha256:ccc94ed0909b58ffe34430ea5451f07bc0c76467d7081619a454bf5c98b89e28",
+                "sha256:feae2f18633c32fc71f2de629bfb3bd3c9325cd4419642b1f1da42ee488d9b98"
             ],
-            "version": "==0.6.0"
+            "version": "==2.1.0"
         }
     }
 }
-- 
cgit v1.2.3


From 4cbee44529dd967c966ed3f2cc2bb80176be4e43 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Thu, 30 Jan 2020 00:08:41 -0800
Subject: implement host+domain parsing for file ES transform

---
 python/fatcat_tools/transforms/elasticsearch.py | 14 +++++---------
 python/tests/transform_elasticsearch.py         |  7 +++----
 2 files changed, 8 insertions(+), 13 deletions(-)

diff --git a/python/fatcat_tools/transforms/elasticsearch.py b/python/fatcat_tools/transforms/elasticsearch.py
index 5a492fb4..e1980d90 100644
--- a/python/fatcat_tools/transforms/elasticsearch.py
+++ b/python/fatcat_tools/transforms/elasticsearch.py
@@ -1,6 +1,6 @@
 
-
 import collections
+import tldextract
 from fatcat_openapi_client import ApiClient
 
 
@@ -499,15 +499,11 @@ def file_to_elasticsearch(entity):
         md5 = entity.md5,
     )
 
-    # TODO: domain, hosts (from urls; use proper urlcanon)
+    parsed_urls = [tldextract.extract(u.url) for u in entity.urls]
+    t['hosts'] = list(set(['.'.join(pu) for pu in parsed_urls]))
+    t['domains'] = list(set([pu.registered_domain for pu in parsed_urls]))
     t['rels'] = list(set([u.rel for u in entity.urls]))
-    t['hosts'] = []
-    t['domains'] = []
 
-    in_ia = False
-    for u in entity.urls:
-        if '://archive.org/' in u.url or '://web.archive.org/' in u.url:
-            in_ia = True
-    t['in_ia'] = bool(in_ia)
+    t['in_ia'] = bool('archive.org' in t['domains'])
 
     return t
diff --git a/python/tests/transform_elasticsearch.py b/python/tests/transform_elasticsearch.py
index c247e745..e67681c6 100644
--- a/python/tests/transform_elasticsearch.py
+++ b/python/tests/transform_elasticsearch.py
@@ -106,11 +106,10 @@ def test_elasticsearch_file_transform(matched_importer):
     assert es['size_bytes'] == f.size
     assert es['mimetype'] == f.mimetype
     assert es['in_ia'] == True
-    assert 'web' in es['rels']
 
-    # XXX: implement hosts and domain parsing with urlcanon
-    #assert 'journals.plos.org' in es['host']
-    #assert 'plos.org' in es['domain']
+    assert 'web' in es['rels']
+    assert 'www.zhros.ru' in es['hosts']
+    assert 'zhros.ru' in es['domains']
 
 def test_elasticsearch_changelog_transform(matched_importer):
     ce = entity_from_json(open('./tests/files/changelog_3469683.json', 'r').read(), ChangelogEntry)
-- 
cgit v1.2.3


From 59912583926077260d99a9bf77a938c2215eb6c8 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Thu, 30 Jan 2020 00:20:34 -0800
Subject: tweak file ES archive.org domain tracking

---
 extra/elasticsearch/file_schema.json            | 1 +
 python/fatcat_tools/transforms/elasticsearch.py | 6 ++++++
 2 files changed, 7 insertions(+)

diff --git a/extra/elasticsearch/file_schema.json b/extra/elasticsearch/file_schema.json
index 2a7e5be0..a0ac3346 100644
--- a/extra/elasticsearch/file_schema.json
+++ b/extra/elasticsearch/file_schema.json
@@ -31,6 +31,7 @@
             "hosts":            { "type": "keyword" },
             "rels":             { "type": "keyword" },
             "in_ia":            { "type": "boolean" },
+            "in_ia_petabox":    { "type": "boolean" },
 
             "release_id":       { "type": "alias", "path": "release_ids" },
             "sha1hex":          { "type": "alias", "path": "sha1" },
diff --git a/python/fatcat_tools/transforms/elasticsearch.py b/python/fatcat_tools/transforms/elasticsearch.py
index e1980d90..9aa3cece 100644
--- a/python/fatcat_tools/transforms/elasticsearch.py
+++ b/python/fatcat_tools/transforms/elasticsearch.py
@@ -505,5 +505,11 @@ def file_to_elasticsearch(entity):
     t['rels'] = list(set([u.rel for u in entity.urls]))
 
     t['in_ia'] = bool('archive.org' in t['domains'])
+    t['in_ia_petabox'] = bool('archive.org' in t['hosts'])
+
+    # ok, but actually remove archive.org hosts, because they make other
+    # aggregations hard and are a waste of storage
+    t['hosts'] = [h for h in t['hosts'] if h not in ('archive.org', 'web.archive.org')]
+    t['domains'] = [h for h in t['hosts'] if h not in ('archive.org')]
 
     return t
-- 
cgit v1.2.3


From b7404fb0f696807db3a92bc2c4c73c2d208e59ef Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Thu, 30 Jan 2020 00:51:56 -0800
Subject: ES schemas: make keywords case-insensitive by default

But not applying asciifolding; don't see any need to do so?
---
 extra/elasticsearch/changelog_schema.json | 20 +++++--
 extra/elasticsearch/container_schema.json | 38 ++++++++-----
 extra/elasticsearch/file_schema.json      | 34 ++++++++----
 extra/elasticsearch/release_schema.json   | 89 ++++++++++++++++++-------------
 4 files changed, 115 insertions(+), 66 deletions(-)

diff --git a/extra/elasticsearch/changelog_schema.json b/extra/elasticsearch/changelog_schema.json
index 77c77238..d958fed9 100644
--- a/extra/elasticsearch/changelog_schema.json
+++ b/extra/elasticsearch/changelog_schema.json
@@ -8,6 +8,18 @@
                     "tokenizer": "standard",
                     "filter": [ "lowercase", "asciifolding" ]
                 }
+            },
+            "normalizer": {
+                "default": {
+                    "type": "custom",
+                    "char_filter": [],
+                    "filter": ["lowercase"]
+                },
+                "caseSensitive": {
+                    "type": "custom",
+                    "char_filter": [],
+                    "filter": []
+                }
             }
         }
     }
@@ -16,13 +28,13 @@
     "changelog": {
         "properties": {
             "index":            { "type": "integer" },
-            "editgroup_id":     { "type": "keyword", "doc_values": false },
+            "editgroup_id":     { "type": "keyword", "normalizer": "default", "doc_values": false },
             "timestamp":        { "type": "date" },
-            "editor_id":        { "type": "keyword" },
-            "username":         { "type": "keyword" },
+            "editor_id":        { "type": "keyword", "normalizer": "default" },
+            "username":         { "type": "keyword", "normalize": "caseSensitive" },
             "is_bot":           { "type": "boolean" },
             "is_admin":         { "type": "boolean" },
-            "agent":            { "type": "keyword" },
+            "agent":            { "type": "keyword", "normalize": "caseSensitive" },
 
             "containers":       { "type": "integer" },
             "new_containers":   { "type": "integer" },
diff --git a/extra/elasticsearch/container_schema.json b/extra/elasticsearch/container_schema.json
index 3be261a2..be3a408e 100644
--- a/extra/elasticsearch/container_schema.json
+++ b/extra/elasticsearch/container_schema.json
@@ -20,6 +20,18 @@
                     "char_filter": [ "icu_normalizer" ],
                     "filter": [ "icu_folding" ]
                 }
+            },
+            "normalizer": {
+                "default": {
+                    "type": "custom",
+                    "char_filter": [],
+                    "filter": ["lowercase"]
+                },
+                "caseSensitive": {
+                    "type": "custom",
+                    "char_filter": [],
+                    "filter": []
+                }
             }
         }
     }
@@ -27,23 +39,23 @@
 "mappings": {
     "container": {
         "properties": {
-            "ident":          { "type": "keyword", "doc_values": false },
-            "state":          { "type": "keyword" },
-            "revision":       { "type": "keyword", "doc_values": false },
+            "ident":          { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "state":          { "type": "keyword", "normalizer": "default" },
+            "revision":       { "type": "keyword", "normalizer": "default", "doc_values": false },
             "name":           { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
             "original_name":  { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
             "publisher":      { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
             "abbrev":         { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
             "aliases":        { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
-            "container_type": { "type": "keyword" },
-            "issnl":          { "type": "keyword" },
-            "issns":          { "type": "keyword" },
-            "wikidata_qid":   { "type": "keyword" },
-            "country":        { "type": "keyword" },
-            "region":         { "type": "keyword" },
-            "discipline":     { "type": "keyword" },
-            "languages":      { "type": "keyword" },
-            "mimetypes":      { "type": "keyword" },
+            "container_type": { "type": "keyword", "normalizer": "default" },
+            "issnl":          { "type": "keyword", "normalizer": "default" },
+            "issns":          { "type": "keyword", "normalizer": "default" },
+            "wikidata_qid":   { "type": "keyword", "normalizer": "default" },
+            "country":        { "type": "keyword", "normalizer": "default" },
+            "region":         { "type": "keyword", "normalizer": "default" },
+            "discipline":     { "type": "keyword", "normalizer": "default" },
+            "languages":      { "type": "keyword", "normalizer": "default" },
+            "mimetypes":      { "type": "keyword", "normalizer": "default" },
             "first_year":     { "type": "integer" },
             "last_year":      { "type": "integer" },
 
@@ -57,7 +69,7 @@
             "any_kbart":            { "type": "boolean" },
             "any_jstor":            { "type": "boolean" },
             "any_ia_sim":           { "type": "boolean" },
-            "sherpa_romeo_color":   { "type": "keyword" },
+            "sherpa_romeo_color":   { "type": "keyword", "normalizer": "default" },
 
             "releases_total": { "type": "integer" },
             "releases_kbart": { "type": "integer" },
diff --git a/extra/elasticsearch/file_schema.json b/extra/elasticsearch/file_schema.json
index a0ac3346..9c8ee64c 100644
--- a/extra/elasticsearch/file_schema.json
+++ b/extra/elasticsearch/file_schema.json
@@ -8,6 +8,18 @@
                     "tokenizer": "standard",
                     "filter": [ "lowercase", "asciifolding" ]
                 }
+            },
+            "normalizer": {
+                "default": {
+                    "type": "custom",
+                    "char_filter": [],
+                    "filter": ["lowercase"]
+                },
+                "caseSensitive": {
+                    "type": "custom",
+                    "char_filter": [],
+                    "filter": []
+                }
             }
         }
     }
@@ -15,21 +27,21 @@
 "mappings": {
     "file": {
         "properties": {
-            "ident":            { "type": "keyword", "doc_values": false },
-            "state":            { "type": "keyword" },
-            "revision":         { "type": "keyword", "doc_values": false },
+            "ident":            { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "state":            { "type": "keyword", "normalizer": "default" },
+            "revision":         { "type": "keyword", "normalizer": "default", "doc_values": false },
 
-            "release_ids":      { "type": "keyword", "doc_values": false },
+            "release_ids":      { "type": "keyword", "normalizer": "default", "doc_values": false },
             "release_count":    { "type": "integer" },
-            "mimetype":         { "type": "keyword" },
+            "mimetype":         { "type": "keyword", "normalizer": "default" },
             "size_bytes":       { "type": "integer" },
-            "sha1":             { "type": "keyword", "doc_values": false },
-            "sha256":           { "type": "keyword", "doc_values": false },
-            "md5":              { "type": "keyword", "doc_values": false },
+            "sha1":             { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "sha256":           { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "md5":              { "type": "keyword", "normalizer": "default", "doc_values": false },
 
-            "domains":          { "type": "keyword" },
-            "hosts":            { "type": "keyword" },
-            "rels":             { "type": "keyword" },
+            "domains":          { "type": "keyword", "normalizer": "default" },
+            "hosts":            { "type": "keyword", "normalizer": "default" },
+            "rels":             { "type": "keyword", "normalizer": "default" },
             "in_ia":            { "type": "boolean" },
             "in_ia_petabox":    { "type": "boolean" },
 
diff --git a/extra/elasticsearch/release_schema.json b/extra/elasticsearch/release_schema.json
index 3d301dba..f983a703 100644
--- a/extra/elasticsearch/release_schema.json
+++ b/extra/elasticsearch/release_schema.json
@@ -20,58 +20,71 @@
                     "char_filter": [ "icu_normalizer" ],
                     "filter": [ "icu_folding" ]
                 }
+            },
+            "normalizer": {
+                "default": {
+                    "type": "custom",
+                    "char_filter": [],
+                    "filter": ["lowercase"]
+                },
+                "caseSensitive": {
+                    "type": "custom",
+                    "char_filter": [],
+                    "filter": []
+                }
             }
         }
     }
+}
 },
 "mappings": {
     "release": {
         "properties": {
-            "ident":          { "type": "keyword", "doc_values": false },
-            "state":          { "type": "keyword" },
-            "revision":       { "type": "keyword", "doc_values": false },
-            "work_id":        { "type": "keyword", "doc_values": false },
+            "ident":          { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "state":          { "type": "keyword", "normalizer": "default" },
+            "revision":       { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "work_id":        { "type": "keyword", "normalizer": "default", "doc_values": false },
             "title":          { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
             "subtitle":       { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
             "original_title": { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
             "release_date":   { "type": "date" },
             "release_year":   { "type": "integer", "copy_to": "biblio" },
-            "release_type":   { "type": "keyword", "copy_to": "biblio" },
-            "release_stage":  { "type": "keyword" },
-            "withdrawn_status": { "type": "keyword", "copy_to": "biblio" },
-            "language":       { "type": "keyword" },
-            "country":        { "type": "keyword" },
-            "volume":         { "type": "keyword", "copy_to": "biblio" },
-            "issue":          { "type": "keyword", "copy_to": "biblio" },
-            "pages":          { "type": "keyword", "copy_to": "biblio" },
-            "first_page":     { "type": "keyword" },
-            "number":         { "type": "keyword", "copy_to": "biblio" },
-            "doi":            { "type": "keyword", "doc_values": false },
-            "doi_prefix":     { "type": "keyword" },
-            "doi_registrar":  { "type": "keyword" },
-            "pmid":           { "type": "keyword", "doc_values": false },
-            "pmcid":          { "type": "keyword", "doc_values": false },
-            "isbn13":         { "type": "keyword", "doc_values": false },
-            "wikidata_qid":   { "type": "keyword", "doc_values": false },
-            "core_id":        { "type": "keyword", "doc_values": false },
-            "axiv_id":        { "type": "keyword", "doc_values": false },
-            "jstor_id":       { "type": "keyword", "doc_values": false },
-            "ark_id":         { "type": "keyword", "doc_values": false },
-            "mag_id":         { "type": "keyword", "doc_values": false },
-            "license":        { "type": "keyword" },
+            "release_type":   { "type": "keyword", "normalizer": "default", "copy_to": "biblio" },
+            "release_stage":  { "type": "keyword", "normalizer": "default" },
+            "withdrawn_status": { "type": "keyword", "normalizer": "default", "copy_to": "biblio" },
+            "language":       { "type": "keyword", "normalizer": "default" },
+            "country":        { "type": "keyword", "normalizer": "default" },
+            "volume":         { "type": "keyword", "normalizer": "default", "copy_to": "biblio" },
+            "issue":          { "type": "keyword", "normalizer": "default", "copy_to": "biblio" },
+            "pages":          { "type": "keyword", "normalizer": "default", "copy_to": "biblio" },
+            "first_page":     { "type": "keyword", "normalizer": "default" },
+            "number":         { "type": "keyword", "normalizer": "default", "copy_to": "biblio" },
+            "doi":            { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "doi_prefix":     { "type": "keyword", "normalizer": "default" },
+            "doi_registrar":  { "type": "keyword", "normalizer": "default" },
+            "pmid":           { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "pmcid":          { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "isbn13":         { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "wikidata_qid":   { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "core_id":        { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "axiv_id":        { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "jstor_id":       { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "ark_id":         { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "mag_id":         { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "license":        { "type": "keyword", "normalizer": "default" },
             "publisher":            { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" },
             "container_name":       { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
-            "container_id":         { "type": "keyword" },
-            "container_issnl":      { "type": "keyword" },
-            "container_type":       { "type": "keyword" },
+            "container_id":         { "type": "keyword", "normalizer": "default" },
+            "container_issnl":      { "type": "keyword", "normalizer": "default" },
+            "container_type":       { "type": "keyword", "normalizer": "default" },
             "contrib_count":        { "type": "integer" },
             "contrib_names":        { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
             "affiliations":         { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" },
-            "affiliation_rors":     { "type": "keyword" },
-            "creator_ids":          { "type": "keyword" },
+            "affiliation_rors":     { "type": "keyword", "normalizer": "default" },
+            "creator_ids":          { "type": "keyword", "normalizer": "default" },
             "ref_count":            { "type": "integer" },
             "ref_linked_count":     { "type": "integer" },
-            "ref_release_ids":      { "type": "keyword" },
+            "ref_release_ids":      { "type": "keyword", "normalizer": "default" },
             "file_count":           { "type": "integer" },
             "fileset_count":        { "type": "integer" },
             "webcapture_count":     { "type": "integer" },
@@ -79,11 +92,11 @@
 
             "biblio":               { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" },
 
-            "best_pdf_url":         { "type": "keyword", "doc_values": false },
-            "ia_pdf_url":           { "type": "keyword", "doc_values": false },
-            "ia_microfilm_url":     { "type": "keyword", "doc_values": false },
+            "best_pdf_url":         { "type": "keyword", "normalizer": "caseSensitive", "doc_values": false },
+            "ia_pdf_url":           { "type": "keyword", "normalizer": "caseSensitive", "doc_values": false },
+            "ia_microfilm_url":     { "type": "keyword", "normalizer": "caseSensitive", "doc_values": false },
             "is_oa":                { "type": "boolean" },
-            "oa_color":             { "type": "keyword" },
+            "oa_color":             { "type": "keyword", "normalizer": "default" },
             "is_longtail_oa":       { "type": "boolean" },
             "is_preserved":         { "type": "boolean" },
             "in_kbart":             { "type": "boolean" },
@@ -95,7 +108,7 @@
             "in_shadows":           { "type": "boolean" },
             "is_superceded":        { "type": "boolean" },
             "is_retracted":         { "type": "boolean" },
-            "preservation":         { "type": "keyword" },
+            "preservation":         { "type": "keyword", "normalizer": "default" },
 
             "affilation":     { "type": "alias", "path": "affiliations" },
             "ror":            { "type": "alias", "path": "affiliation_rors" },
-- 
cgit v1.2.3


From ca283a45cc151f3346e403c8d57f55ec75f40672 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Thu, 30 Jan 2020 01:00:12 -0800
Subject: JSON typo in release mapping

---
 extra/elasticsearch/release_schema.json | 1 -
 1 file changed, 1 deletion(-)

diff --git a/extra/elasticsearch/release_schema.json b/extra/elasticsearch/release_schema.json
index f983a703..07601f36 100644
--- a/extra/elasticsearch/release_schema.json
+++ b/extra/elasticsearch/release_schema.json
@@ -35,7 +35,6 @@
             }
         }
     }
-}
 },
 "mappings": {
     "release": {
-- 
cgit v1.2.3


From caa588612b91181950697756eace8fda270fd092 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Thu, 30 Jan 2020 01:03:08 -0800
Subject: add upper-case work-around from kibana map join

---
 extra/elasticsearch/release_schema.json         | 1 +
 python/fatcat_tools/transforms/elasticsearch.py | 1 +
 2 files changed, 2 insertions(+)

diff --git a/extra/elasticsearch/release_schema.json b/extra/elasticsearch/release_schema.json
index 07601f36..c0bbda22 100644
--- a/extra/elasticsearch/release_schema.json
+++ b/extra/elasticsearch/release_schema.json
@@ -53,6 +53,7 @@
             "withdrawn_status": { "type": "keyword", "normalizer": "default", "copy_to": "biblio" },
             "language":       { "type": "keyword", "normalizer": "default" },
             "country":        { "type": "keyword", "normalizer": "default" },
+            "country_upper":  { "type": "keyword", "normalizer": "caseSensitive" },
             "volume":         { "type": "keyword", "normalizer": "default", "copy_to": "biblio" },
             "issue":          { "type": "keyword", "normalizer": "default", "copy_to": "biblio" },
             "pages":          { "type": "keyword", "normalizer": "default", "copy_to": "biblio" },
diff --git a/python/fatcat_tools/transforms/elasticsearch.py b/python/fatcat_tools/transforms/elasticsearch.py
index 9aa3cece..ded239d3 100644
--- a/python/fatcat_tools/transforms/elasticsearch.py
+++ b/python/fatcat_tools/transforms/elasticsearch.py
@@ -157,6 +157,7 @@ def release_to_elasticsearch(entity, force_bool=True):
                     is_oa = True
             if c_extra.get('country'):
                 t['country'] = c_extra['country']
+                t['country_upper'] = c_extra['country'].upper()
 
     # fall back to release-level container metadata if container not linked or
     # missing context
-- 
cgit v1.2.3


From 8aac86c4484f0376c46cdd51c69d5ada478b7f72 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Thu, 30 Jan 2020 01:12:51 -0800
Subject: fix json typos in changelog schema

---
 extra/elasticsearch/changelog_schema.json | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/extra/elasticsearch/changelog_schema.json b/extra/elasticsearch/changelog_schema.json
index d958fed9..d8342549 100644
--- a/extra/elasticsearch/changelog_schema.json
+++ b/extra/elasticsearch/changelog_schema.json
@@ -31,10 +31,10 @@
             "editgroup_id":     { "type": "keyword", "normalizer": "default", "doc_values": false },
             "timestamp":        { "type": "date" },
             "editor_id":        { "type": "keyword", "normalizer": "default" },
-            "username":         { "type": "keyword", "normalize": "caseSensitive" },
+            "username":         { "type": "keyword", "normalizer": "caseSensitive" },
             "is_bot":           { "type": "boolean" },
             "is_admin":         { "type": "boolean" },
-            "agent":            { "type": "keyword", "normalize": "caseSensitive" },
+            "agent":            { "type": "keyword", "normalizer": "caseSensitive" },
 
             "containers":       { "type": "integer" },
             "new_containers":   { "type": "integer" },
-- 
cgit v1.2.3


From 5ba91951bb4ebc59cb59340e82cba2a7d763dc59 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Thu, 30 Jan 2020 13:22:45 -0800
Subject: fix release es transform missing 'issue'

---
 python/fatcat_tools/transforms/elasticsearch.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/python/fatcat_tools/transforms/elasticsearch.py b/python/fatcat_tools/transforms/elasticsearch.py
index ded239d3..b5abe2ae 100644
--- a/python/fatcat_tools/transforms/elasticsearch.py
+++ b/python/fatcat_tools/transforms/elasticsearch.py
@@ -248,6 +248,7 @@ def release_to_elasticsearch(entity, force_bool=True):
         # special case as a demo for now.
         if release.container_id == "hl5g6d5msjcl7hlbyyvcsbhc2u" \
                 and release.release_year in (2011, 2013) \
+                and release.issue \
                 and release.issue.isdigit() \
                 and t['first_page']:
             t['ia_microfilm_url'] = "https://archive.org/details/sim_bjog_{}-{:02d}/page/n{}".format(
-- 
cgit v1.2.3


From 0d037d0d2f73b18014d8d98a06fa3f7bc2c9b794 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Thu, 30 Jan 2020 16:52:29 -0800
Subject: pipenv: lock zipp version to work around python3.6 requirement

---
 python/Pipfile      |  4 ++++
 python/Pipfile.lock | 23 ++++++++++++++++-------
 2 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/python/Pipfile b/python/Pipfile
index a5389e4f..838cc2c0 100644
--- a/python/Pipfile
+++ b/python/Pipfile
@@ -53,6 +53,10 @@ pathlib2 = "*"
 pycountry = "*"
 tldextract = "*"
 
+# this is only to lock to a python3.5-compatible version. needed by an
+# importlib-metadata, under pytest
+zipp = "<2.0.0"
+
 [requires]
 # Python 3.5 is the bundled (system) version of python for Ubuntu 16.04
 # (Xenial), currently the default on Internet Archive production VMs, as well
diff --git a/python/Pipfile.lock b/python/Pipfile.lock
index f3cbfbd6..05894aee 100644
--- a/python/Pipfile.lock
+++ b/python/Pipfile.lock
@@ -1,7 +1,7 @@
 {
     "_meta": {
         "hash": {
-            "sha256": "8288b1a7102a0a34644ef56817d60e936dc57695604208036f229e96bc14c42f"
+            "sha256": "0ce2be10751676f4bc5c6f411825efad087a7576cae7cf09e8540aefe321c53b"
         },
         "pipfile-spec": 6,
         "requires": {
@@ -293,10 +293,10 @@
         },
         "jinja2": {
             "hashes": [
-                "sha256:6e7a3c2934694d59ad334c93dd1b6c96699cf24c53fdb8ec848ac6b23e685734",
-                "sha256:d6609ae5ec3d56212ca7d802eda654eaf2310000816ce815361041465b108be4"
+                "sha256:93187ffbc7808079673ef52771baa950426fd664d3aad1d0fa3e95644360e250",
+                "sha256:b0eaf100007721b5c16c1fc1eecb87409464edc10469ddc9a22a27a99123be49"
             ],
-            "version": "==2.11.0"
+            "version": "==2.11.1"
         },
         "kazoo": {
             "hashes": [
@@ -663,6 +663,14 @@
             ],
             "index": "pypi",
             "version": "==2.2.1"
+        },
+        "zipp": {
+            "hashes": [
+                "sha256:15428d652e993b6ce86694c3cccf0d71aa7afdc6ef1807fa25a920e9444e0281",
+                "sha256:d9d2efe11d3a3fb9184da550d35bd1319dc8e30a63255927c82bb42fca1f4f7c"
+            ],
+            "index": "pypi",
+            "version": "==1.1.0"
         }
     },
     "develop": {
@@ -1066,10 +1074,11 @@
         },
         "zipp": {
             "hashes": [
-                "sha256:ccc94ed0909b58ffe34430ea5451f07bc0c76467d7081619a454bf5c98b89e28",
-                "sha256:feae2f18633c32fc71f2de629bfb3bd3c9325cd4419642b1f1da42ee488d9b98"
+                "sha256:15428d652e993b6ce86694c3cccf0d71aa7afdc6ef1807fa25a920e9444e0281",
+                "sha256:d9d2efe11d3a3fb9184da550d35bd1319dc8e30a63255927c82bb42fca1f4f7c"
             ],
-            "version": "==2.1.0"
+            "index": "pypi",
+            "version": "==1.1.0"
         }
     }
 }
-- 
cgit v1.2.3


From 741c7b1efae5e39f3ee2c082e3ca28c6c5c85b76 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Fri, 31 Jan 2020 13:31:59 -0800
Subject: ES releases: host/domain fixes

---
 python/fatcat_tools/transforms/elasticsearch.py | 4 ++--
 python/tests/transform_elasticsearch.py         | 3 +++
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/python/fatcat_tools/transforms/elasticsearch.py b/python/fatcat_tools/transforms/elasticsearch.py
index b5abe2ae..f8bc05fb 100644
--- a/python/fatcat_tools/transforms/elasticsearch.py
+++ b/python/fatcat_tools/transforms/elasticsearch.py
@@ -502,7 +502,7 @@ def file_to_elasticsearch(entity):
     )
 
     parsed_urls = [tldextract.extract(u.url) for u in entity.urls]
-    t['hosts'] = list(set(['.'.join(pu) for pu in parsed_urls]))
+    t['hosts'] = list(set(['.'.join([seg for seg in pu if seg]) for pu in parsed_urls]))
     t['domains'] = list(set([pu.registered_domain for pu in parsed_urls]))
     t['rels'] = list(set([u.rel for u in entity.urls]))
 
@@ -512,6 +512,6 @@ def file_to_elasticsearch(entity):
     # ok, but actually remove archive.org hosts, because they make other
     # aggregations hard and are a waste of storage
     t['hosts'] = [h for h in t['hosts'] if h not in ('archive.org', 'web.archive.org')]
-    t['domains'] = [h for h in t['hosts'] if h not in ('archive.org')]
+    t['domains'] = [h for h in t['domains'] if h not in ('archive.org')]
 
     return t
diff --git a/python/tests/transform_elasticsearch.py b/python/tests/transform_elasticsearch.py
index e67681c6..c94ab375 100644
--- a/python/tests/transform_elasticsearch.py
+++ b/python/tests/transform_elasticsearch.py
@@ -110,6 +110,9 @@ def test_elasticsearch_file_transform(matched_importer):
     assert 'web' in es['rels']
     assert 'www.zhros.ru' in es['hosts']
     assert 'zhros.ru' in es['domains']
+    assert not '.archive.org' in (es['hosts'] + es['domains'])
+    assert not 'archive.org' in (es['hosts'] + es['domains'])
+    assert not 'web.archive.org' in (es['hosts'] + es['domains'])
 
 def test_elasticsearch_changelog_transform(matched_importer):
     ce = entity_from_json(open('./tests/files/changelog_3469683.json', 'r').read(), ChangelogEntry)
-- 
cgit v1.2.3


From fbd79c7315cad4789eb0e92c136c59da8f38c4f3 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Fri, 31 Jan 2020 13:33:38 -0800
Subject: ES release schema: fix typo

---
 extra/elasticsearch/release_schema.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/extra/elasticsearch/release_schema.json b/extra/elasticsearch/release_schema.json
index c0bbda22..2cc9169c 100644
--- a/extra/elasticsearch/release_schema.json
+++ b/extra/elasticsearch/release_schema.json
@@ -110,7 +110,7 @@
             "is_retracted":         { "type": "boolean" },
             "preservation":         { "type": "keyword", "normalizer": "default" },
 
-            "affilation":     { "type": "alias", "path": "affiliations" },
+            "affiliation":     { "type": "alias", "path": "affiliations" },
             "ror":            { "type": "alias", "path": "affiliation_rors" },
             "creator_id":     { "type": "alias", "path": "creator_ids" },
             "ref_release_id": { "type": "alias", "path": "ref_release_ids" },
-- 
cgit v1.2.3


From 8007cdfc4e06753a9bbba56d1fa7f9686775e5e8 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Tue, 4 Feb 2020 15:10:26 -0800
Subject: fix axiv/arxiv typo in release schema

---
 extra/elasticsearch/release_schema.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/extra/elasticsearch/release_schema.json b/extra/elasticsearch/release_schema.json
index 2cc9169c..607bacf1 100644
--- a/extra/elasticsearch/release_schema.json
+++ b/extra/elasticsearch/release_schema.json
@@ -67,7 +67,7 @@
             "isbn13":         { "type": "keyword", "normalizer": "default", "doc_values": false },
             "wikidata_qid":   { "type": "keyword", "normalizer": "default", "doc_values": false },
             "core_id":        { "type": "keyword", "normalizer": "default", "doc_values": false },
-            "axiv_id":        { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "arxiv_id":       { "type": "keyword", "normalizer": "default", "doc_values": false },
             "jstor_id":       { "type": "keyword", "normalizer": "default", "doc_values": false },
             "ark_id":         { "type": "keyword", "normalizer": "default", "doc_values": false },
             "mag_id":         { "type": "keyword", "normalizer": "default", "doc_values": false },
-- 
cgit v1.2.3


From 3655bbe6c539fdeccfbfaa19b6fc93a4859e0ca7 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 5 Feb 2020 15:42:43 -0800
Subject: ES release: actually do want doc_values for work_id

Eg, for fast "unique count"
---
 extra/elasticsearch/release_schema.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/extra/elasticsearch/release_schema.json b/extra/elasticsearch/release_schema.json
index 607bacf1..b85fc8a4 100644
--- a/extra/elasticsearch/release_schema.json
+++ b/extra/elasticsearch/release_schema.json
@@ -42,7 +42,7 @@
             "ident":          { "type": "keyword", "normalizer": "default", "doc_values": false },
             "state":          { "type": "keyword", "normalizer": "default" },
             "revision":       { "type": "keyword", "normalizer": "default", "doc_values": false },
-            "work_id":        { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "work_id":        { "type": "keyword", "normalizer": "default" },
             "title":          { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
             "subtitle":       { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
             "original_title": { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
-- 
cgit v1.2.3


From 83387210e6775751e5eb690a7d8b56fe99dbe380 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Fri, 7 Feb 2020 14:38:13 -0800
Subject: ES files: don't remove archive.org domains/hosts

---
 python/fatcat_tools/transforms/elasticsearch.py | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/python/fatcat_tools/transforms/elasticsearch.py b/python/fatcat_tools/transforms/elasticsearch.py
index f8bc05fb..e00d7830 100644
--- a/python/fatcat_tools/transforms/elasticsearch.py
+++ b/python/fatcat_tools/transforms/elasticsearch.py
@@ -509,9 +509,4 @@ def file_to_elasticsearch(entity):
     t['in_ia'] = bool('archive.org' in t['domains'])
     t['in_ia_petabox'] = bool('archive.org' in t['hosts'])
 
-    # ok, but actually remove archive.org hosts, because they make other
-    # aggregations hard and are a waste of storage
-    t['hosts'] = [h for h in t['hosts'] if h not in ('archive.org', 'web.archive.org')]
-    t['domains'] = [h for h in t['domains'] if h not in ('archive.org')]
-
     return t
-- 
cgit v1.2.3


From 2f8788152ff740d049d11e2e263cac978d526e2a Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Thu, 13 Feb 2020 14:22:59 -0800
Subject: release schema: do doc_value on DOIs

Because DOIs are pseudo-structured (prefix, and often structure within
the publisher-controlled area), I suspect we will in fact be wanting to
do analytics over these strings.
---
 extra/elasticsearch/release_schema.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/extra/elasticsearch/release_schema.json b/extra/elasticsearch/release_schema.json
index b85fc8a4..1b91696c 100644
--- a/extra/elasticsearch/release_schema.json
+++ b/extra/elasticsearch/release_schema.json
@@ -59,7 +59,7 @@
             "pages":          { "type": "keyword", "normalizer": "default", "copy_to": "biblio" },
             "first_page":     { "type": "keyword", "normalizer": "default" },
             "number":         { "type": "keyword", "normalizer": "default", "copy_to": "biblio" },
-            "doi":            { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "doi":            { "type": "keyword", "normalizer": "default" },
             "doi_prefix":     { "type": "keyword", "normalizer": "default" },
             "doi_registrar":  { "type": "keyword", "normalizer": "default" },
             "pmid":           { "type": "keyword", "normalizer": "default", "doc_values": false },
-- 
cgit v1.2.3


From ed38bfde4e1eaddd6d710802b6f372c7b0aab26b Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Fri, 14 Feb 2020 00:07:56 -0800
Subject: ES updates: fix tests to accept archive.org in host/domain

---
 python/tests/transform_elasticsearch.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/python/tests/transform_elasticsearch.py b/python/tests/transform_elasticsearch.py
index c94ab375..a954fc4d 100644
--- a/python/tests/transform_elasticsearch.py
+++ b/python/tests/transform_elasticsearch.py
@@ -110,9 +110,10 @@ def test_elasticsearch_file_transform(matched_importer):
     assert 'web' in es['rels']
     assert 'www.zhros.ru' in es['hosts']
     assert 'zhros.ru' in es['domains']
+    assert 'archive.org' in (es['hosts'] + es['domains'])
+    assert 'web.archive.org' in (es['hosts'] + es['domains'])
+    # old regression
     assert not '.archive.org' in (es['hosts'] + es['domains'])
-    assert not 'archive.org' in (es['hosts'] + es['domains'])
-    assert not 'web.archive.org' in (es['hosts'] + es['domains'])
 
 def test_elasticsearch_changelog_transform(matched_importer):
     ce = entity_from_json(open('./tests/files/changelog_3469683.json', 'r').read(), ChangelogEntry)
-- 
cgit v1.2.3


From 0450f22006c9b991cdc4695458fc3b3e3e97bfbb Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 26 Feb 2020 11:22:30 -0800
Subject: ES release: last minor tweaks

---
 extra/elasticsearch/release_schema.json         | 8 +++++---
 python/fatcat_tools/transforms/elasticsearch.py | 4 ++--
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/extra/elasticsearch/release_schema.json b/extra/elasticsearch/release_schema.json
index 1b91696c..666a672f 100644
--- a/extra/elasticsearch/release_schema.json
+++ b/extra/elasticsearch/release_schema.json
@@ -52,8 +52,8 @@
             "release_stage":  { "type": "keyword", "normalizer": "default" },
             "withdrawn_status": { "type": "keyword", "normalizer": "default", "copy_to": "biblio" },
             "language":       { "type": "keyword", "normalizer": "default" },
-            "country":        { "type": "keyword", "normalizer": "default" },
-            "country_upper":  { "type": "keyword", "normalizer": "caseSensitive" },
+            "country_code":        { "type": "keyword", "normalizer": "default" },
+            "country_code_upper":  { "type": "keyword", "normalizer": "caseSensitive" },
             "volume":         { "type": "keyword", "normalizer": "default", "copy_to": "biblio" },
             "issue":          { "type": "keyword", "normalizer": "default", "copy_to": "biblio" },
             "pages":          { "type": "keyword", "normalizer": "default", "copy_to": "biblio" },
@@ -71,8 +71,10 @@
             "jstor_id":       { "type": "keyword", "normalizer": "default", "doc_values": false },
             "ark_id":         { "type": "keyword", "normalizer": "default", "doc_values": false },
             "mag_id":         { "type": "keyword", "normalizer": "default", "doc_values": false },
+            "s2_id":          { "type": "keyword", "normalizer": "default", "doc_values": false },
             "license":        { "type": "keyword", "normalizer": "default" },
             "publisher":            { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" },
+            "publisher_type":       { "type": "keyword", "normalizer": "default" },
             "container_name":       { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
             "container_id":         { "type": "keyword", "normalizer": "default" },
             "container_issnl":      { "type": "keyword", "normalizer": "default" },
@@ -110,7 +112,7 @@
             "is_retracted":         { "type": "boolean" },
             "preservation":         { "type": "keyword", "normalizer": "default" },
 
-            "affiliation":     { "type": "alias", "path": "affiliations" },
+            "affiliation":    { "type": "alias", "path": "affiliations" },
             "ror":            { "type": "alias", "path": "affiliation_rors" },
             "creator_id":     { "type": "alias", "path": "creator_ids" },
             "ref_release_id": { "type": "alias", "path": "ref_release_ids" },
diff --git a/python/fatcat_tools/transforms/elasticsearch.py b/python/fatcat_tools/transforms/elasticsearch.py
index e00d7830..cbafca7e 100644
--- a/python/fatcat_tools/transforms/elasticsearch.py
+++ b/python/fatcat_tools/transforms/elasticsearch.py
@@ -156,8 +156,8 @@ def release_to_elasticsearch(entity, force_bool=True):
                 if c_extra['szczepanski'].get('as_of'):
                     is_oa = True
             if c_extra.get('country'):
-                t['country'] = c_extra['country']
-                t['country_upper'] = c_extra['country'].upper()
+                t['country_code'] = c_extra['country']
+                t['country_code_upper'] = c_extra['country'].upper()
 
     # fall back to release-level container metadata if container not linked or
     # missing context
-- 
cgit v1.2.3


From 4e6bc246d01183f4c7ffad7d0d474e683f04c07f Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 26 Feb 2020 11:28:05 -0800
Subject: ES container last tweaks

---
 extra/elasticsearch/container_schema.json       | 7 ++++---
 python/fatcat_tools/transforms/elasticsearch.py | 3 +++
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/extra/elasticsearch/container_schema.json b/extra/elasticsearch/container_schema.json
index be3a408e..5cd85b04 100644
--- a/extra/elasticsearch/container_schema.json
+++ b/extra/elasticsearch/container_schema.json
@@ -47,11 +47,12 @@
             "publisher":      { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
             "abbrev":         { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
             "aliases":        { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch", "copy_to": "biblio" },
+            "publisher_type": { "type": "keyword", "normalizer": "default" },
             "container_type": { "type": "keyword", "normalizer": "default" },
             "issnl":          { "type": "keyword", "normalizer": "default" },
             "issns":          { "type": "keyword", "normalizer": "default" },
             "wikidata_qid":   { "type": "keyword", "normalizer": "default" },
-            "country":        { "type": "keyword", "normalizer": "default" },
+            "country_code":   { "type": "keyword", "normalizer": "default" },
             "region":         { "type": "keyword", "normalizer": "default" },
             "discipline":     { "type": "keyword", "normalizer": "default" },
             "languages":      { "type": "keyword", "normalizer": "default" },
@@ -74,8 +75,8 @@
             "releases_total": { "type": "integer" },
             "releases_kbart": { "type": "integer" },
             "releases_ia":    { "type": "integer" },
-            "releases_sim":   { "type": "integer" },
-            "releases_shadow":          { "type": "integer" },
+            "releases_ia_sim":          { "type": "integer" },
+            "releases_shadows":         { "type": "integer" },
             "releases_any_file":        { "type": "integer" },
             "releases_any_fileset":     { "type": "integer" },
             "releases_any_webcapture":  { "type": "integer" },
diff --git a/python/fatcat_tools/transforms/elasticsearch.py b/python/fatcat_tools/transforms/elasticsearch.py
index cbafca7e..8581febd 100644
--- a/python/fatcat_tools/transforms/elasticsearch.py
+++ b/python/fatcat_tools/transforms/elasticsearch.py
@@ -342,6 +342,9 @@ def container_to_elasticsearch(entity, force_bool=True):
         if entity.extra.get(key):
             t[key] = entity.extra[key]
 
+    if 'country' in t:
+        t['country_code'] = t.pop('country')
+
     t['issns'] = []
     if entity.issnl:
         t['issns'].append(entity.issnl)
-- 
cgit v1.2.3


From c57a743cb8b774750c99c6f079438666a87f6476 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 26 Feb 2020 11:38:51 -0800
Subject: bulk ES transform: skip non-active entities

---
 python/fatcat_transform.py | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/python/fatcat_transform.py b/python/fatcat_transform.py
index 42d2ea99..9ddbaa4d 100755
--- a/python/fatcat_transform.py
+++ b/python/fatcat_transform.py
@@ -30,6 +30,8 @@ def run_elasticsearch_releases(args):
         if not line:
             continue
         entity = entity_from_json(line, ReleaseEntity, api_client=args.api.api_client)
+        if entity['state'] != 'active':
+            continue
         args.json_output.write(
             json.dumps(release_to_elasticsearch(entity)) + '\n')
 
@@ -39,6 +41,8 @@ def run_elasticsearch_containers(args):
         if not line:
             continue
         entity = entity_from_json(line, ContainerEntity, api_client=args.api.api_client)
+        if entity['state'] != 'active':
+            continue
         args.json_output.write(
             json.dumps(container_to_elasticsearch(entity)) + '\n')
 
@@ -48,6 +52,8 @@ def run_elasticsearch_files(args):
         if not line:
             continue
         entity = entity_from_json(line, FileEntity, api_client=args.api.api_client)
+        if entity['state'] != 'active':
+            continue
         args.json_output.write(
             json.dumps(file_to_elasticsearch(entity)) + '\n')
 
@@ -66,6 +72,8 @@ def run_citeproc_releases(args):
         if not line:
             continue
         entity = entity_from_json(line, ReleaseEntity, api_client=args.api.api_client)
+        if entity['state'] != 'active':
+            continue
         csl_json = release_to_csl(entity)
         csl_json['id'] = "release:" + (entity.ident or "unknown")
         out = citeproc_csl(csl_json, args.style, args.html)
-- 
cgit v1.2.3


From 21239503ddd71c69ddf651260f2953c93f227dfc Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 26 Feb 2020 12:16:22 -0800
Subject: fix fatcat_transform state filters

---
 python/fatcat_transform.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/python/fatcat_transform.py b/python/fatcat_transform.py
index 9ddbaa4d..23a56109 100755
--- a/python/fatcat_transform.py
+++ b/python/fatcat_transform.py
@@ -30,7 +30,7 @@ def run_elasticsearch_releases(args):
         if not line:
             continue
         entity = entity_from_json(line, ReleaseEntity, api_client=args.api.api_client)
-        if entity['state'] != 'active':
+        if entity.state != 'active':
             continue
         args.json_output.write(
             json.dumps(release_to_elasticsearch(entity)) + '\n')
@@ -41,7 +41,7 @@ def run_elasticsearch_containers(args):
         if not line:
             continue
         entity = entity_from_json(line, ContainerEntity, api_client=args.api.api_client)
-        if entity['state'] != 'active':
+        if entity.state != 'active':
             continue
         args.json_output.write(
             json.dumps(container_to_elasticsearch(entity)) + '\n')
@@ -52,7 +52,7 @@ def run_elasticsearch_files(args):
         if not line:
             continue
         entity = entity_from_json(line, FileEntity, api_client=args.api.api_client)
-        if entity['state'] != 'active':
+        if entity.state != 'active':
             continue
         args.json_output.write(
             json.dumps(file_to_elasticsearch(entity)) + '\n')
@@ -72,7 +72,7 @@ def run_citeproc_releases(args):
         if not line:
             continue
         entity = entity_from_json(line, ReleaseEntity, api_client=args.api.api_client)
-        if entity['state'] != 'active':
+        if entity.state != 'active':
             continue
         csl_json = release_to_csl(entity)
         csl_json['id'] = "release:" + (entity.ident or "unknown")
-- 
cgit v1.2.3


From 0ab3f66664fd4cc63cf9040e351d725c6a5c22b9 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 26 Feb 2020 12:27:28 -0800
Subject: update ES transform README

- smaller batch sizes to prevent esbulk errors
- file transform/index
---
 extra/elasticsearch/README.md | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/extra/elasticsearch/README.md b/extra/elasticsearch/README.md
index 3e0857b4..df4cb918 100644
--- a/extra/elasticsearch/README.md
+++ b/extra/elasticsearch/README.md
@@ -59,8 +59,9 @@ Bulk insert from a file on disk:
 Or, in a bulk production live-stream conversion:
 
     export LC_ALL=C.UTF-8
-    time zcat /srv/fatcat/snapshots/release_export_expanded.json.gz | pv -l | parallel -j20 --linebuffer --round-robin --pipe ./fatcat_transform.py elasticsearch-releases - - | esbulk -verbose -size 20000 -id ident -w 8 -index fatcat_release -type release
-    time zcat /srv/fatcat/snapshots/container_export.json.gz | pv -l | ./fatcat_transform.py elasticsearch-containers - - | esbulk -verbose -size 20000 -id ident -w 8 -index fatcat_container -type container
+    time zcat /srv/fatcat/snapshots/release_export_expanded.json.gz | pv -l | parallel -j20 --linebuffer --round-robin --pipe ./fatcat_transform.py elasticsearch-releases - - | esbulk -verbose -size 2000 -id ident -w 8 -index fatcat_release -type release
+    time zcat /srv/fatcat/snapshots/container_export.json.gz | pv -l | ./fatcat_transform.py elasticsearch-containers - - | esbulk -verbose -size 2000 -id ident -w 8 -index fatcat_container -type container
+    time zcat /srv/fatcat/snapshots/file_export.json.gz | pv -l | parallel -j20 --linebuffer --round-robin --pipe ./fatcat_transform.py elasticsearch-files - - | esbulk -verbose -size 2000 -id ident -w 8 -index fatcat_file -type file
 
 ## Index Aliases
 
-- 
cgit v1.2.3


From 81e0784813500a39955c20278140e25d7940d9c6 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 26 Feb 2020 22:04:35 -0800
Subject: improve is_oa flag accuracy

Particularly, the ezb=green match seems mostly incorrect.

Note that pmcid being assigned could still be in an embargo window?
---
 proposals/2020_elasticsearch_schemas.md         |  4 ++--
 python/fatcat_tools/transforms/elasticsearch.py | 12 ++++--------
 2 files changed, 6 insertions(+), 10 deletions(-)

diff --git a/proposals/2020_elasticsearch_schemas.md b/proposals/2020_elasticsearch_schemas.md
index 5fb28d19..c3e79073 100644
--- a/proposals/2020_elasticsearch_schemas.md
+++ b/proposals/2020_elasticsearch_schemas.md
@@ -33,8 +33,8 @@ status (from `in_kbart`, `in_ia`, etc) to a `preservation_status` flag which
 is:
 
 - `bright`
-- `dark_only`
-- `shadow_only`
+- `dark`
+- `shadows_only`
 - `none`
 
 Note that these don't align with OA color or work-level preservation (aka, no
diff --git a/python/fatcat_tools/transforms/elasticsearch.py b/python/fatcat_tools/transforms/elasticsearch.py
index 8581febd..87e054ec 100644
--- a/python/fatcat_tools/transforms/elasticsearch.py
+++ b/python/fatcat_tools/transforms/elasticsearch.py
@@ -149,9 +149,6 @@ def release_to_elasticsearch(entity, force_bool=True):
             if c_extra.get('road'):
                 if c_extra['road'].get('as_of'):
                     is_oa = True
-            if c_extra.get('ezb'):
-                if c_extra['ezb'].get('color') == 'green':
-                    is_oa = True
             if c_extra.get('szczepanski'):
                 if c_extra['szczepanski'].get('as_of'):
                     is_oa = True
@@ -210,6 +207,8 @@ def release_to_elasticsearch(entity, force_bool=True):
         # TODO: more/better checks here, particularly strict *not* OA licenses
         if release.license_slug.startswith("CC-"):
             is_oa = True
+        if release.license_slug.startswith("ARXIV-"):
+            is_oa = True
 
     extra = release.extra or dict()
     if extra:
@@ -293,10 +292,10 @@ def release_to_elasticsearch(entity, force_bool=True):
     t['in_ia'] = bool(in_ia)
     t['is_preserved'] = bool(is_preserved or in_ia or in_kbart or in_jstor)
 
-    if in_ia:
+    if in_ia or t.get('pmcid') or t.get('arxiv_id'):
         t['preservation'] = 'bright'
     elif in_kbart or in_jstor:
-        t['preservation'] = 'dark_only'
+        t['preservation'] = 'dark'
     elif in_shadows:
         t['preservation'] = 'shadows_only'
     else:
@@ -367,9 +366,6 @@ def container_to_elasticsearch(entity, force_bool=True):
     if extra.get('road'):
         if extra['road'].get('as_of'):
             in_road = True
-    if extra.get('ezb'):
-        if extra['ezb'].get('color') == 'green':
-            is_oa = True
     if extra.get('szczepanski'):
         if extra['szczepanski'].get('as_of'):
             is_oa = True
-- 
cgit v1.2.3