⚡ changing output CSV to hespi-results.csv and appending subsequent r…

…esults to this file

hespi/hespi.py

@@ -148,7 +148,7 @@ def detect(
                         output_dir=output_dir / stub,
                     )
 
-        df = ocr_data_df(ocr_data, output_path=output_dir/"ocr_results.csv")
+        df = ocr_data_df(ocr_data, output_path=output_dir/"hespi-results.csv")
 
         # Write report
         if report:

hespi/main.py

@@ -48,6 +48,7 @@ def detect(
     ),
     institutional_label_classifier_weights: str = typer.Option(
         DEFAULT_INSTITUTIONAL_LABEL_CLASSIFIER_WEIGHTS,
+        envvar="HESPI_INSTITUTIONAL_LABEL_CLASSIFIER_WEIGHTS",
         help="The path to the institutional label classifier weights.",
     ),
     force_download:bool = typer.Option(False, help="Whether or not to force download model weights even if a weights file is present."),

hespi/util.py

@@ -70,6 +70,15 @@ def ocr_data_df(data: dict, output_path: Path=None) -> pd.DataFrame:
     if output_path:
         output_path = Path(output_path)
         output_path.parent.mkdir(exist_ok=True, parents=True)
+
+        # If the file already exists, then concatenate it
+        if output_path.exists():
+            old_df = pd.read_csv(output_path)
+            df = pd.concat([old_df, df])
+            console.print(f"Appending Hespi results to: '{output_path}'")
+        else:
+            console.print(f"Writing Hespi results to: '{output_path}'")
+
         df.to_csv(output_path, index=False)
 
     return df