Merge branch 'wip-martin-review-cleanup' into 'master'

review notes and some cleanup

See merge request webgroup/fuzzycat!7

5 files changed, 82 insertions, 9 deletions

diff --git a/fuzzycat/config.py b/fuzzycat/config.py
index 61050d1..d6989cf 100644
--- a/fuzzycat/config.py
+++ b/fuzzycat/config.py
@@ -1,4 +1,3 @@
-
 from dynaconf import Dynaconf
 
 settings = Dynaconf(envvar_prefix="FUZZYCAT")
diff --git a/fuzzycat/matching.py b/fuzzycat/matching.py
index c94a308..310dfc2 100644
--- a/fuzzycat/matching.py
+++ b/fuzzycat/matching.py
@@ -10,9 +10,9 @@ import requests
 from fatcat_openapi_client import ContainerEntity, DefaultApi, ReleaseEntity
 from fatcat_openapi_client.rest import ApiException
 
+from fuzzycat.config import settings
 from fuzzycat.entities import entity_from_dict, entity_from_json
 from fuzzycat.utils import es_compat_hits_total
-from fuzzycat.config import settings
 
 FATCAT_API_URL = settings.get("FATCAT_API_URL", "https://api.fatcat.wiki/v0")
 
@@ -73,12 +73,83 @@ def match_release_fuzzy(
         if r:
             return [r]
 
+
+    if release.title is not None and release.contribs is not None:
+        names = " ".join([c.raw_name for c in release.contribs])
+        body = {
+            "track_total_hits": True,
+            "query": {
+                "bool": {
+                    "must": [
+                        {
+                            "match": {
+                                "title": {
+                                    "query": release.title,
+                                    "operator": "AND",
+                                    "fuzziness": "AUTO",
+                                },
+                            }
+                        },
+                        {
+                            "match": {
+                                "contrib_names": {
+                                    "query": names,
+                                    "operator": "AND",
+                                    "fuzziness": "AUTO",
+                                }
+                            }
+                        },
+                    ],
+                },
+            },
+            "size": size,
+        }
+        resp = es.search(body=body, index="fatcat_release")
+        if es_compat_hits_total(resp) > 0:
+            return response_to_entity_list(resp, entity_type=ReleaseEntity, size=size, api=api)
+
+        body = {
+            "track_total_hits": True,
+            "query": {
+                "bool": {
+                    "should": [
+                        {
+                            "match": {
+                                "title": {
+                                    "query": release.title,
+                                    "operator": "AND",
+                                    "fuzziness": "AUTO",
+                                },
+                            }
+                        },
+                        {
+                            "match": {
+                                "contrib_names": {
+                                    "query": names,
+                                    "operator": "AND",
+                                    "fuzziness": "AUTO",
+                                }
+                            }
+                        },
+                    ],
+                },
+            },
+            "size": size,
+        }
+        resp = es.search(body=body, index="fatcat_release")
+        if es_compat_hits_total(resp) > 0:
+            return response_to_entity_list(resp, entity_type=ReleaseEntity, size=size, api=api)
+
+    # Note: If the title is short, we will get lots of results here; do we need
+    # to check for title length or result set length length or result set
+    # length here?
     body = {
+        "track_total_hits": True,
         "query": {
             "match": {
                 "title": {
                     "query": release.title,
-                    "operator": "AND"
+                    "operator": "AND",
                 }
             }
         },
@@ -91,6 +162,7 @@ def match_release_fuzzy(
     # Get fuzzy.
     # https://www.elastic.co/guide/en/elasticsearch/reference/current/common-options.html#fuzziness
     body = {
+        "track_total_hits": True,
         "query": {
             "match": {
                 "title": {
@@ -106,6 +178,7 @@ def match_release_fuzzy(
     if es_compat_hits_total(resp) > 0:
         return response_to_entity_list(resp, entity_type=ReleaseEntity, size=size, api=api)
 
+
     # TODO: perform more queries on other fields.
     return []
 
diff --git a/fuzzycat/simple.py b/fuzzycat/simple.py
index 8b206b1..ff59ba2 100644
--- a/fuzzycat/simple.py
+++ b/fuzzycat/simple.py
@@ -25,8 +25,8 @@ from fuzzycat.common import Reason, Status
 from fuzzycat.entities import entity_to_dict
 from fuzzycat.grobid_unstructured import grobid_parse_unstructured
 from fuzzycat.matching import match_release_fuzzy
-from fuzzycat.verify import verify
 from fuzzycat.utils import clean_doi
+from fuzzycat.verify import verify
 
 
 @dataclass
diff --git a/fuzzycat/utils.py b/fuzzycat/utils.py
index a1c5124..303daf6 100644
--- a/fuzzycat/utils.py
+++ b/fuzzycat/utils.py
@@ -81,6 +81,7 @@ def dict_key_exists(doc, path):
     else:
         return True
 
+
 def clean_doi(raw: Optional[str]) -> Optional[str]:
     if not raw:
         return None
@@ -95,6 +96,7 @@ def clean_doi(raw: Optional[str]) -> Optional[str]:
         raw = raw[:8] + raw[9:]
     return raw
 
+
 def doi_prefix(v):
     """
     Return the prefix of a DOI.
diff --git a/fuzzycat/verify.py b/fuzzycat/verify.py
index 1eeea40..5b90c47 100644
--- a/fuzzycat/verify.py
+++ b/fuzzycat/verify.py
@@ -90,9 +90,9 @@ from fuzzycat.common import Reason, Status
 from fuzzycat.data import (CONTAINER_NAME_BLACKLIST, PUBLISHER_BLACKLIST, TITLE_BLACKLIST,
                            TITLE_FRAGMENT_BLACKLIST)
 from fuzzycat.entities import entity_to_dict
-from fuzzycat.utils import (author_similarity_score, contains_chemical_formula, dict_key_exists,
-                            doi_prefix, has_doi_prefix, jaccard, num_project, parse_page_string,
-                            slugify_string, clean_doi)
+from fuzzycat.utils import (author_similarity_score, clean_doi, contains_chemical_formula,
+                            dict_key_exists, doi_prefix, has_doi_prefix, jaccard, num_project,
+                            parse_page_string, slugify_string)
 
 Verify = collections.namedtuple("Verify", "status reason")
 
@@ -597,8 +597,7 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]:
     try:
         a_parsed_pages = parse_page_string(glom(a, "pages"))
         b_parsed_pages = parse_page_string(glom(b, "pages"))
-        if (a_parsed_pages.count != None
-                and b_parsed_pages.count != None
+        if (a_parsed_pages.count != None and b_parsed_pages.count != None
                 and abs(a_parsed_pages.count - b_parsed_pages.count) > 5):
             return Verify(Status.DIFFERENT, Reason.PAGE_COUNT)
     except (ValueError, PathAccessError):