chore(repo): Move references to reference data dir

Begin restructuring data dir by separating out references into their own
data sub-dir containing only references and bibtex files.

src/globals.py

@@ -1,11 +1,12 @@
-from pathlib import Path
 import os
+from pathlib import Path
 
-PROJECT_DIR=Path(os.getenv("QUARTO_PROJECT_DIR", "."))
+PROJECT_DIR = Path(os.getenv("QUARTO_PROJECT_DIR", "."))
 
-DATA_DIR=PROJECT_DIR.joinpath("data")
+DATA_DIR = PROJECT_DIR.joinpath("data")
 
-RAW_DATA=DATA_DIR.joinpath("raw")
-WORKING_DATA=DATA_DIR.joinpath("intermediate")
-PROCESSED_DATA=DATA_DIR.joinpath("processed")
-SUPPLEMENTARY_DATA=DATA_DIR.joinpath("supplementary")
+WORKING_DATA = DATA_DIR.joinpath("intermediate")
+PROCESSED_DATA = DATA_DIR.joinpath("processed")
+SUPPLEMENTARY_DATA = DATA_DIR.joinpath("supplementary")
+
+REFERENCE_DATA = DATA_DIR.joinpath("references")

src/model/prisma.py

@@ -1,8 +1,4 @@
-from src.process import add_metadata as meta
-from src import globals as g
-
-bib_sample_raw_db = meta.bib_library_from_dir(g.RAW_DATA)
-bib_sample = meta.bib_library_from_dir(g.WORKING_DATA)
+from src.process.generate_dataframes import bib_sample_raw_db, bib_sample
 
 class PrismaNumbers:
     nr_database_query_raw = len(bib_sample_raw_db.entries)

src/process/add_metadata.py

@@ -31,6 +31,19 @@ def bib_library_from_dir(
         return bibtexparser.parse_string(bib_string)
 
 
+def bib_library_from_file(
+    file: Path, disable_warnings: bool = True
+) -> bibtexparser.Library:
+    with open(file) as f:
+        bib_string = f.read()
+    if disable_warnings:
+        cm = all_logging_disabled
+    else:
+        cm = nullcontext
+    with cm():
+        return bibtexparser.parse_string(bib_string)
+
+
 def bib_metadata_df(sample: bibtexparser.Library) -> pd.DataFrame:
     """Returns dataframe with relevant metadata extracted from a bibtex library.
 

src/process/generate_dataframes.py

@@ -11,9 +11,9 @@ import src.globals as g
 from src.process import add_metadata as meta
 
 # raw database-search results
-bib_sample_raw_db = meta.bib_library_from_dir(g.RAW_DATA)
+bib_sample_raw_db = meta.bib_library_from_dir(g.REFERENCE_DATA)
 # the complete library of sampled (and working) literature
-bib_sample = meta.bib_library_from_dir(g.WORKING_DATA)
+bib_sample = meta.bib_library_from_file(g.REFERENCE_DATA.joinpath("zotero-library.bib"))
 
 # load relevant studies
 from src.extract import load_data as load