detecting mismatched entrance slugs and filenames

parsers/caves.py

@@ -52,6 +52,8 @@ entrances_xslug = {}
 caves_xslug = {}
 areas_xslug = {}
 
+LETTERS = list(string.ascii_lowercase)
+
 
 def dummy_entrance(k, slug, msg="DUMMY"):
     """Returns an empty entrance object for either a PENDING cave or a DUMMY entrance if
@@ -450,6 +452,10 @@ def read_entrance(filename, ent=None):
 
       If not called as part of initial import, then the global lists will not be correct
       but this is OK, a search will find them in the db.
+      
+      EDIT href examples
+      /1623-1:1623-1a_entrance_edit
+      /1623/1/1623-1_cave_edit/
 
       Args:
         filename: The name of the .html file.
@@ -474,13 +480,31 @@ def read_entrance(filename, ent=None):
     ent_area = filename[:4]
     if ent_area not in AREACODES:
         message = f'! BAD AREA CODE in "{filename}". Not recognised.'
-        DataIssue.objects.create(parser="entrances", message=message, url=f"/entrance_data/{filename}_edit")
+        DataIssue.objects.create(parser="entrances", message=message, url=ent_edit_url)
         print(message)
+        
+    
+    
+    # Derive the letter, entrance slug and cave slug fromthe filename
+    entslug_fn = filename[:-5]
+    if entslug_fn[-1] in LETTERS:
+        caveslug_fn = entslug_fn[:-1]
+        letter_fn = entslug_fn[-1]
+    else:
+        caveslug_fn = entslug_fn
+        letter_fn = ""
+        
+    cave_name_fn = caveslug_fn[5:] # remove initial "1623-"
+    
+    ent_edit_url = f"/{caveslug_fn}:{entslug_fn}_entrance_edit"
+    cave_edit_url = f"/{ent_area}/{cave_name_fn}/{caveslug_fn}_cave_edit"
+    
+
     
     entrancecontentslist = getXML(contents, "entrance", maxItems=1, context=context)
     if len(entrancecontentslist) != 1:
         message = f'! BAD ENTRANCE DATA in "{filename}". More than one entrance. Edit file manually, click.'
-        DataIssue.objects.create(parser="entrances", message=message, url=f"/entrance_data/{filename}_edit")
+        DataIssue.objects.create(parser="entrances", message=message, url=ent_edit_url)
         print(message)
         return None
 
@@ -491,12 +515,17 @@ def read_entrance(filename, ent=None):
     if len(slugs) >1:
         # Only ever one of these per entrance in the expo dataset
         message = f" ! - More than one slug for an entrance: {entrance}, slugs: {slugs}. Ignoring all except first."
-        DataIssue.objects.create(parser="entrances", message=message, url=f"/cave/{slug}/edit/")
+        DataIssue.objects.create(parser="entrances", message=message, url=cave_edit_url)
         print(message)
         
-    lastvisit = getXML(entrancecontents, "lastvisit", maxItems=1, minItems=0, context=f"/cave/{slug}/edit/")
-    lat_wgs84 = getXML(entrancecontents, "lat_wgs84", maxItems=1, minItems=0, context=f"/cave/{slug}/edit/")
-    long_wgs84 = getXML(entrancecontents, "long_wgs84", maxItems=1, minItems=0, context=f"/cave/{slug}/edit/")
+    if slug != entslug_fn:
+        message = f" ! - Warning, mismatch between entrance slug and filename:  {slug=} {filename=}. "
+        DataIssue.objects.create(parser="xEntrances", message=message, url=cave_edit_url)
+        print(message)
+    
+    lastvisit = getXML(entrancecontents, "lastvisit", maxItems=1, minItems=0, context=cave_edit_url)
+    lat_wgs84 = getXML(entrancecontents, "lat_wgs84", maxItems=1, minItems=0, context=cave_edit_url)
+    long_wgs84 = getXML(entrancecontents, "long_wgs84", maxItems=1, minItems=0, context=cave_edit_url)
 
     alt = getXMLmax1("alt")
     approach = getXMLmax1("approach")
@@ -551,7 +580,7 @@ def read_entrance(filename, ent=None):
         except:
             message = f" ! BAD ENTRANCE TAG '{st}' in '{filename}'. Must format like '1623.p204'. Edit file manually, click."
             #http://localhost:8000/1623/2023-EBH-01/1623-2023-EBH-01:1623-2023-EBH-01_entrance_edit
-            DataIssue.objects.create(parser="entrances", message=message, url=f"/1623/{slug}/{slug}:{slug}_entrance_edit")
+            DataIssue.objects.create(parser="entrances", message=message, url=ent_edit_url) # url=f"/1623/{slug}/{slug}:{slug}_entrance_edit")
             print(message)
     ent.save()
     return ent
@@ -923,7 +952,7 @@ def readcaves():
 
     with transaction.atomic():
         print(" - Reading Entrances from entrance descriptions xml files")
-        for filename in next(os.walk(ENTRANCEDESCRIPTIONS))[2]:  # Should be a better way of getting a list of files
+        for filename in next(os.walk(ENTRANCEDESCRIPTIONS))[2]:  # Should be a better way of getting a list of files, use pathlib !
             read_entrance(filename)
 
     # Why is this needed ? Without it, we lose these DataIssues!