Merge pull request #123 from nulib/fix

fixes ingest script

nulrdcscripts/ingest/Ingest_Sheet_Maker.py

@@ -9,7 +9,6 @@
 import nulrdcscripts.ingest.inventory_helpers as inv_helpers
 import nulrdcscripts.ingest.ingest_helpers as ing_helpers
 
-
 class Ingest_Sheet_Maker:
     """
     a class for creating ingest sheet csv files
@@ -21,8 +20,12 @@ class Ingest_Sheet_Maker:
     :var list[dict] ingest_dictlist: contains ingest sheet data
     :var str work_type: type of work ingest sheet is for
     """
-
-    def __init__(self, indir: str, outfile: str, x_parse: str):
+    def __init__(
+            self, 
+            indir: str, 
+            outfile: str, 
+            x_parse: str
+        ):
         """
         Initializes Ingest_Sheet_Maker input, output, and role assignment rules.
 
@@ -35,7 +38,10 @@ def __init__(self, indir: str, outfile: str, x_parse: str):
         """fullpath to input directory"""
         self.outfile: str
         """fullpath to output csv file"""
-        self.indir, self.outfile = helpers.init_io(indir, outfile)
+        self.indir, self.outfile = helpers.init_io(
+            indir,
+            outfile
+        )
         self.inventory_dictlist: list[dict[str, str]] = None
         """contains inventory data"""
 
@@ -85,9 +91,15 @@ def run(self, skip: list[str], prepend: str):
             # files and subdirs are "cleaned" in separate functions before analyzing
             for file in helpers.clean_files(files, skip):
                 self.analyze_file(
-                    file, helpers.clean_subdir(subdir, self.indir), prepend
+                    file, 
+                    helpers.clean_subdir(subdir, self.indir), 
+                    prepend
                 )
-        helpers.write_csv(self.outfile, ing_helpers.get_fields(), self.ingest_dictlist)
+        helpers.write_csv(
+            self.outfile, 
+            ing_helpers.get_fields(), 
+            self.ingest_dictlist
+        )
         print("Process complete!")
         print("Meadow inventory located at: " + self.outfile)
 
@@ -109,34 +121,34 @@ def analyze_file(self, filename: str, parent_dir: str, prepend: str = ""):
             u_file: str = helpers.get_unix_fullpath(filename, parent_dir)
             work_accession_number: str = item["work_accession_number"]
             description: str = ing_helpers.get_ingest_description(item, filename)
-
-            # options for image or AV
+            
+            #options for image or AV
             if self.work_type == "IMAGE":
                 role = item["role"]
+                label = item["label"]
                 file_accession_number = item["file_accession_number"]
             else:
-                label, role, file_builder = self.get_ingest_LRF(filename, item["label"])
+                label, role, file_builder = self.get_ingest_LRF(
+                    filename, item["label"]
+                )
                 if item["filename"] in self.ingest_dictlist:
                     role_count = 1 + sum(
-                        x.get("role") == role
-                        for x in self.ingest_dictlist[item["filename"]]
+                        x.get("role") == role for x in self.ingest_dictlist[item["filename"]]
                     )
                 else:
                     role_count = 1
-                file_accession_number = (
-                    item["filename"] + file_builder + f"{role_count:03d}"
-                )
+                file_accession_number = item["filename"] + file_builder + f"{role_count:03d}"
             # prepend to file_accession_number
             if prepend:
                 file_accession_number = prepend + file_accession_number
             # create meadow dict for file
-            meadow_file_dict: dict[str, str] = {
+            meadow_file_dict: dict[str, str]= {
                 "work_type": self.work_type,
                 "work_accession_number": work_accession_number,
                 "file_accession_number": file_accession_number,
                 "filename": u_file,
                 "description": description,
-                "label": "",
+                "label": label,
                 "role": role,
                 "work_image": None,
                 "structure": None,
@@ -152,9 +164,8 @@ def analyze_file(self, filename: str, parent_dir: str, prepend: str = ""):
         # allow user to add the file anyway
         # only gets here if file isnt found
         print(
-            "+++ WARNING: No entry matching "
-            + filename
-            + " was found in your inventory +++"
+            "+++ WARNING: No entry matching " + filename + 
+            " was found in your inventory +++"
         )
 
     def get_ingest_LRF(self, filename: str, inventory_label: str):
@@ -182,11 +193,11 @@ def get_ingest_LRF(self, filename: str, inventory_label: str):
             role = "S"
             file_builder = "_supplementary_"
         else:
-            role = self.role_dict[role_index]["role"]
-            file_builder = self.role_dict[role_index]["file_builder"]
+            role  = self.role_dict[role_index]["role"]
+            file_builder  = self.role_dict[role_index]["file_builder"]
             label = ing_helpers.ingest_label_creator(filename, inventory_label)
 
-            # append label if role has extra info
+            #append label if role has extra info
             if self.role_dict[role_index]["label"]:
                 label += " " + self.role_dict[role_index]["label"]
-        return label, role, file_builder
+        return label, role, file_builder

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "nul-rdc-scripts"
-version = "0.3.1"
+version = "0.4.0"
 description = "Scripts for NUL RDC Digitization Team"
 authors = [
     "Northwestern University Libraries <[email protected]>",