HDXDSYS-898 Refactor org code (#134)

* Add uncleaned names as keys to lookups
Remove intersectoral check
dict() to {}
Move branches that have continue higher up in loops in operational presence

* Some rearrangement of operational presence and comments to help me understand the org processing

* Small reorg of org type if code

* store normalised keys as well as non normalised

* Use already normalised key

* Simplify org lookup code and operational presence

* Add to lookup to reduce need to keep normalising

* Pass around normalise variables

* Remove org lookup only used in test

* Remove unnecessary variable

* Update CHANGELOG

* Can just return value here

* Combine ifs

* Use named tuples for clarity

* Rename value to org_info

* Use org_data in populate_multiple

* Use OrgData in tests

* Make OrgInfo into a data class
Add used and complete bools to OrgInfo
Correct OrgInfo objects in org_map with corrections from looking up in data member variable

* Make separate function

* Add debug option to command line
Add org_map debug

CHANGELOG.md

@@ -4,6 +4,13 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
+## [0.9.36] - 2024-07-19
+
+### Changed
+
+- Refactor org code
+- Also add uncleaned names as keys to lookups
+
 ## [0.9.35] - 2024-07-18
 
 ### Fixed

pyproject.toml

@@ -36,7 +36,7 @@ requires-python = ">=3.8"
 dependencies = [
     "hapi-schema>=0.8.14",
     "hdx-python-api>= 6.3.1",
-    "hdx-python-country>= 3.7.6",
+    "hdx-python-country>= 3.7.7",
     "hdx-python-database[postgresql]>= 1.3.1",
     "hdx-python-scraper>= 2.4.0",
     "hdx-python-utilities>= 3.7.2",

requirements.txt

@@ -26,7 +26,7 @@ click==8.1.7
     # via typer
 coverage==7.6.0
     # via pytest-cov
-cryptography==42.0.8
+cryptography==43.0.0
     # via pyopenssl
 defopt==6.4.0
     # via hdx-python-api
@@ -64,7 +64,7 @@ hdx-python-api==6.3.1
     # via
     #   hapi-pipelines (pyproject.toml)
     #   hdx-python-scraper
-hdx-python-country==3.7.6
+hdx-python-country==3.7.7
     # via
     #   hapi-pipelines (pyproject.toml)
     #   hdx-python-api
@@ -172,13 +172,13 @@ pydantic-core==2.20.1
     # via pydantic
 pygments==2.18.0
     # via rich
-pyopenssl==24.1.0
+pyopenssl==24.2.1
     # via
     #   hdx-python-api
     #   ndg-httpsclient
 pyphonetics==0.5.3
     # via hdx-python-country
-pytest==8.2.2
+pytest==8.3.1
     # via
     #   hapi-pipelines (pyproject.toml)
     #   pytest-check
@@ -242,7 +242,7 @@ ruamel-yaml==0.18.6
     # via hdx-python-utilities
 ruamel-yaml-clib==0.2.8
     # via ruamel-yaml
-setuptools==70.3.0
+setuptools==71.1.0
     # via ckanapi
 shellingham==1.5.4
     # via typer

src/hapi/pipelines/app/__main__.py

@@ -84,6 +84,13 @@ def parse_args():
         action="store_true",
         help="Use saved data",
     )
+    parser.add_argument(
+        "-dbg",
+        "--debug",
+        default=False,
+        action="store_true",
+        help="Debug",
+    )
     return parser.parse_args()
 
 
@@ -95,6 +102,7 @@ def main(
     basic_auths: Optional[Dict[str, str]] = None,
     save: bool = False,
     use_saved: bool = False,
+    debug: bool = False,
     **ignore,
 ) -> None:
     """Run HAPI. Either a database connection string (db_uri) or database
@@ -110,6 +118,7 @@ def main(
         basic_auths (Optional[Dict[str, str]]): Basic authorisations
         save (bool): Whether to save state for testing. Defaults to False.
         use_saved (bool): Whether to use saved state for testing. Defaults to False.
+        debug (bool): Whether to output debug info. Defaults to False.
 
     Returns:
         None
@@ -156,6 +165,8 @@ def main(
                 )
                 pipelines.run()
                 pipelines.output()
+                if debug:
+                    pipelines.debug("debug")
     logger.info("HAPI pipelines completed!")
 
 
@@ -233,4 +244,5 @@ def main(
         basic_auths=basic_auths,
         save=args.save,
         use_saved=args.use_saved,
+        debug=args.debug,
     )

src/hapi/pipelines/app/pipelines.py

@@ -96,7 +96,7 @@ def __init__(
             errors_on_exit=errors_on_exit,
             scrapers_to_run=scrapers_to_run,
         )
-        self.configurable_scrapers = dict()
+        self.configurable_scrapers = {}
         self.create_configurable_scrapers()
         self.metadata = Metadata(
             runner=self.runner, session=session, today=today
@@ -333,3 +333,6 @@ def output(self):
             self.wfp_commodity.populate()
             self.wfp_market.populate()
             self.food_price.populate()
+
+    def debug(self, folder: str) -> None:
+        self.org.output_org_map(folder)

src/hapi/pipelines/database/conflict_event.py

@@ -103,7 +103,7 @@ def populate(self):
             batch_populate(conflict_event_rows, self._session, DBConflictEvent)
 
         for dataset, msg in self._config.get(
-            "conflict_event_error_messages", dict()
+            "conflict_event_error_messages", {}
         ).items():
             add_message(errors, dataset, msg)
         for error in sorted(errors):