From cab654e58b46b7a29f867a5caa076f07130b60cd Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Thu, 7 May 2020 19:58:08 -0700
Subject: nice simple hack for config loading

---
 chocula/config.py | 43 +++++++++++++++++--------------------------
 1 file changed, 17 insertions(+), 26 deletions(-)

(limited to 'chocula')

diff --git a/chocula/config.py b/chocula/config.py
index 1835478..2237404 100644
--- a/chocula/config.py
+++ b/chocula/config.py
@@ -1,30 +1,21 @@
 
-class ChoculaConfig:
+from types import SimpleNamespace
+import toml
 
-    ISSNL_FILE = 'data/20200323.ISSN-to-ISSN-L.txt'
+class ChoculaConfig(SimpleNamespace):
 
-    ENTREZ_FILE = 'data/entrez-journals.csv'
-    ROAD_FILE = 'data/road-2018-01-24.tsv'
-    ROAD_DATE = '2018-01-24'
-    DOAJ_FILE = 'data/journalcsv__doaj_20191221_0135_utf8.csv'
-    DOAJ_DATE = '2019-12-21'
-    CROSSREF_FILE = 'data/doi_titles_file_2019-12-20.csv'
-    SHERPA_ROMEO_JOURNAL_FILE = 'data/romeo-journals.csv'
-    SHERPA_ROMEO_POLICY_FILE = 'data/romeo-policies.csv'
-    NORWEGIAN_FILE = 'data/2019-12-21 Norwegian Register for Scientific Journals and Series.csv'
-    NORWEGIAN_DATE = '2019-12-21'
-    LOCKSS_FILE = 'data/kbart_LOCKSS.txt'
-    CLOCKSS_FILE = 'data/kbart_CLOCKSS.txt'
-    PORTICO_FILE = 'data/Portico_Holding_KBart.txt'
-    JSTOR_FILE = 'data/JSTOR_Global_AllArchiveTitles_2019-12-21.txt'
-    SIM_FILE = 'data/MASTER TITLE_METADATA_LIST_20171019.converted.csv'
-    SZCZEPANSKI_DATE = '2018'
-    SZCZEPANSKI_FILE = 'data/Jan-Szczepanski-Open-Access-Journals-2018_0.fixed.json'
-    EZB_FILE = 'data/ezb_metadata.json'
-    GOLD_OA_FILE = 'data/ISSN_Gold-OA_3.0.csv'
-    WIKIDATA_SPARQL_FILE = 'data/wikidata_journals_sparql.2019-12-20.tsv'
-    OPENAPC_FILE = 'data/apc_de.2019-12-20.csv'
-    FATCAT_CONTAINER_FILE = 'data/container_export.2019-12-13.json'
+    @classmethod
+    def from_file(cls, file_path="sources.toml", sources_dir="data/"):
 
-    IA_CRAWL_FILE = 'data/url_status.20191223.json'
-    FATCAT_STATS_FILE = 'data/container_stats.20191213.json'
+        # TODO: can we just pass _dict=SimpleNamespace here?
+        sources = toml.load(file_path)
+
+        # convert all sub-tables to SimpleNamespace
+        for k in list(sources.keys()):
+            if isinstance(sources[k], dict):
+                if "filename" in sources[k]:
+                    sources[k]["filepath"] = sources_dir + sources[k]["filename"]
+                sources[k] = SimpleNamespace(**sources[k])
+
+        # conver the whole thing to SimpleNamespace
+        return ChoculaConfig(**sources)
-- 
cgit v1.2.3