Improve debug message in RecordCds, RecordHepPubli and friends

modules/store_tools/recordcdspubli.py

@@ -15,7 +15,7 @@ from .base import (ARXIV,
                    search_synonym,
                    REG_DOI,
                    REG_OAI,
-                   T6)
+                   T4, T6)
 from .exception import CheckException
 from filters import CLEAN_COLLABORATION
 from pandas import concat, DataFrame
@@ -238,6 +238,8 @@ class RecordCdsPubli(dict, AuthorsMixin, PublicationInfoMixin):
             field does not exist.
 
         """
+        self.logger.debug(f"{T4}process authors")
+
         if "authors" not in self:
             cols = ["affiliation",
                     "first_name",
@@ -313,6 +315,8 @@ class RecordCdsPubli(dict, AuthorsMixin, PublicationInfoMixin):
               and volume.
 
         """
+        self.logger.debug(f"{T4}process publication info")
+
         if "publication_info" not in self:
             cols = ["title",
                     "volume",

modules/store_tools/recordhepconfpaper.py

@@ -3,6 +3,7 @@
 """
 import requests
 
+from .base import T4, T6
 from datetime import datetime
 from plugin_dbui import CLEAN_SPACES
 from .recordheppubli import RecordHepPubli
@@ -20,6 +21,15 @@ class RecordHepConfPaper(RecordHepPubli):
             Schema for conference metadata is document here:
             https://inspire-schemas.readthedocs.io/en/latest/schemas/
 
+            Main information are:
+                * addresses: [{cities: [], country: str, ...}, ...]
+                * cnum: str
+                * control_number: int
+                * closing_date: str
+                * opening_date: str
+                * titles: [{value: str}, ...]
+                * urls: [{value: str}, ...]
+
     """
 
     def __init__(self, recjson):
@@ -30,12 +40,16 @@ class RecordHepConfPaper(RecordHepPubli):
         self._process_conference_data()
 
     def _process_conference_data(self):
-        """Append the conference record.
+        """Append the conference data to the record.
 
         """
+        logger = self.logger
+        logger.debug(f"{T4}process conference data")
+
         # get the URL of the conference record in inspirehep.net
         publication_info = self.get("publication_info", None)
         if publication_info is None:
+            logger.debug(f"{T6}no 'publication_info' field")
             return
 
         urlins = None
@@ -44,6 +58,7 @@ class RecordHepConfPaper(RecordHepPubli):
                 urlins = elt.get("conference_record", {}).get("$ref", None)
 
         if urlins is None:
+            logger.debug(f"{T6}no 'conference_record.$ref' information")
             return
 
         # get conference metadata
@@ -53,6 +68,7 @@ class RecordHepConfPaper(RecordHepPubli):
             obj = r.json()
 
         except(requests.RequestException, ValueError):
+            logger.debug(f"{T6}failed to retrieve conference data")
             return
 
         self.conference = obj.get("metadata", None)

modules/store_tools/recordheppubli.py

@@ -9,7 +9,7 @@ from .base import (search_synonym,
                    MSG_UNKNOWN_COLLABORATION,
                    MSG_WELL_FORMED_DATE,
                    REG_DATE_YYYYMM,
-                   T6)
+                   T4, T6)
 from .exception import CheckException
 from filters import CLEAN_COLLABORATION
 from pandas import DataFrame
@@ -98,7 +98,7 @@ class RecordHepPubli(dict, AuthorsMixin, PublicationInfoMixin):
             is not defined.
 
         """
-        self.logger.debug("    process authors")
+        self.logger.debug(f"{T4}process authors")
 
         authors = self.get("authors", None)
 
@@ -176,7 +176,7 @@ class RecordHepPubli(dict, AuthorsMixin, PublicationInfoMixin):
               and volume.
 
         """
-        self.logger.debug("    process publication info")
+        self.logger.debug(f"{T4}process publication info")
 
         cols = ["title",
                 "volume",