workflows: only use matcher on help

.dockerignore

@@ -32,3 +32,6 @@
 Procfile*
 docker*
 gun
+
+**/__pycache__
+**/*.pyc

inspirehep/modules/workflows/tasks/actions.py

@@ -78,7 +78,6 @@
     extract_references_from_text,
     extract_references_from_text_data,
 )
-from inspirehep.modules.refextract.matcher import match_references
 from inspirehep.modules.workflows.utils import _get_headers_for_hep_root_table_request, create_error
 from inspirehep.modules.workflows.errors import BadGatewayError, MissingRecordControlNumber
 from inspirehep.modules.workflows.utils import (
@@ -474,10 +473,6 @@ def match_references_hep(references):
     create_error(response)
 
 
-def match_references_based_on_flag(references):
-    return match_references(references)
-
-
 @with_debug_logging
 def refextract(obj, eng):
     """Extract references from various sources and add them to the workflow.
@@ -497,7 +492,7 @@ def refextract(obj, eng):
     if 'references' in obj.data:
         extracted_raw_references = dedupe_list(extract_references_from_raw_refs(obj.data['references']))
         obj.log.info('Extracted %d references from raw refs.', len(extracted_raw_references))
-        obj.data['references'] = match_references_based_on_flag(extracted_raw_references)
+        obj.data['references'] = match_references_hep(extracted_raw_references)
         return
 
     matched_pdf_references, matched_text_references = [], []
@@ -511,12 +506,12 @@ def refextract(obj, eng):
                 url, source=source, custom_kbs_file=journal_kb_dict
             )
         )
-        matched_pdf_references = match_references_based_on_flag(pdf_references)
+        matched_pdf_references = match_references_hep(pdf_references)
     else:
         with get_document_in_workflow(obj) as tmp_document:
             if tmp_document:
                 pdf_references = dedupe_list(extract_references_from_pdf(tmp_document, source))
-                matched_pdf_references = match_references_based_on_flag(pdf_references)
+                matched_pdf_references = match_references_hep(pdf_references)
 
     text = get_value(obj.extra_data, 'formdata.references')
     if text and current_app.config.get("FEATURE_FLAG_ENABLE_REFEXTRACT_SERVICE"):
@@ -525,10 +520,10 @@ def refextract(obj, eng):
                 text, source=source, custom_kbs_file=journal_kb_dict
             )
         )
-        matched_text_references = match_references_based_on_flag(text_references)
+        matched_text_references = match_references_hep(text_references)
     elif text:
         text_references = dedupe_list(extract_references_from_text(text, source))
-        matched_text_references = match_references_based_on_flag(text_references)
+        matched_text_references = match_references_hep(text_references)
 
     if not matched_pdf_references and not matched_text_references:
         obj.log.info('No references extracted.')

setup.cfg

@@ -46,8 +46,6 @@ omit =
   inspirehep/wsgi.py
   inspirehep/wsgi_with_coverage.py
 
-[tool:pytest]
-addopts = --cov=inspirehep --cov-report=term-missing:skip-covered
 
 [flake8]
 ignore = *.py E501 FI12 FI14 FI15 FI16 FI17 FI18 FI50 FI51 FI53 W504 W605 W743 W503

tests/integration/workflows/conftest.py

@@ -289,6 +289,13 @@ def mocked_external_services(workflow_app):
             headers=_get_headers_for_hep_root_table_request(),
             status_code=200,
         )
+        requests_mocker.register_uri(
+            "POST",
+            "http://web:8000/api/matcher/linked_references/",
+            json={"references": []},
+            headers=_get_headers_for_hep_root_table_request(),
+            status_code=200,
+        )
         if "INSPIREHEP_URL" in workflow_app.config:
             # HEP record upload
             requests_mocker.register_uri(