xml parser attmpt retract

1 files changed, 13 insertions, 67 deletions

diff --git a/parsers/caves.py b/parsers/caves.py
index 5389a8e..e1ec8dc 100644
--- a/parsers/caves.py
+++ b/parsers/caves.py
@@ -1,5 +1,7 @@
 import os
 import re
+
+
 from pathlib import Path
 
 from django.conf import settings
@@ -426,6 +428,14 @@ def read_cave(filename, cave=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.
+    
+    Attempted to use standard python3.11 xml library but fails on HTML entities (2023-04-23)
+    import xml.etree.ElementTree as ET
+    tree = ET.parse(fn)
+    xml_root = tree.getroot()
+    for t in ["html", "head", "body", "cave","non_public", "caveslug", "official_name","entrance"]:
+        elements = xml_root.findall(t)
+
     """
     def getXMLmax1(field):
         return getXML(cavecontents, field, maxItems=1, context=context)
@@ -492,6 +502,8 @@ def read_cave(filename, cave=None):
     
     # Note: these are HTML files in the EXPOWEB repo, not from the loser repo.
     fn = settings.CAVEDESCRIPTIONS / filename
+    context = filename
+    
     # print(f" - Reading Cave from cave descriptions file {fn}")
     if not fn.exists():
         message = f" ! Cave_data file reading problem filename:'cave_data/{filename}'"
@@ -501,7 +513,6 @@ def read_cave(filename, cave=None):
 
     with open(fn) as f:
         contents = f.read()
-    context = filename
     cavecontentslist = getXML(contents, "cave", maxItems=1, context=context)
 
     if len(cavecontentslist) != 1:
@@ -580,7 +591,7 @@ def read_cave(filename, cave=None):
     cave.url=url[0]
             
     areas = getXML(cavecontents, "area", context=context)
-    # cave.area_set.clear() # Need to find correct syntax. Does not delete previously loaded areas.. WARNING
+    cave.area.clear() # Deletes all links to areas in db
     for area_slug in areas:
         if area_slug in areas_xslug:
             newArea = areas_xslug[area_slug]
@@ -630,70 +641,6 @@ def read_cave(filename, cave=None):
     cave.save()
     return cave
 
-
-# ChatGPT replacement attempt 2023-04-21. Obviously very incomplete, but some useful ideas
-# import os
-# import xml.etree.ElementTree as ET
-
-# class BadCaveException(Exception):
-    # pass
-
-# class FailedCaveUpdateException(Exception):
-    # pass
-
-# def read_cave_chatgpt(filename, entrances_xslug, caves_xslug, areas_xslug):
-    # """Reads an entrance description from the .html file and updates the corresponding Cave object"""
-    # tree = ET.parse(os.path.join(CAVEDESCRIPTIONS, filename))
-    # root = tree.getroot()
-
-    # cavecontents = root.find("cave")
-    # if cavecontents is None:
-        # raise BadCaveException(f'! BAD CAVE at "{filename}"')
-
-    # non_public = cavecontents.findtext("non_public")
-    # slugs = cavecontents.findtext("caveslug")
-    # official_name = cavecontents.findtext("official_name")
-    # kataster_code = cavecontents.findtext("kataster_code")
-    # kataster_number = cavecontents.findtext("kataster_number")
-    # unofficial_number = cavecontents.findtext("unofficial_number")
-    # explorers = cavecontents.findtext("explorers")
-    # underground_description = cavecontents.findtext("underground_description")
-    # equipment = cavecontents.findtext("equipment")
-    # references = cavecontents.findtext("references")
-    # survey = cavecontents.findtext("survey")
-    # kataster_status = cavecontents.findtext("kataster_status")
-    # underground_centre_line = cavecontents.findtext("underground_centre_line")
-    # notes = cavecontents.findtext("notes")
-    # length = cavecontents.findtext("length")
-    # depth = cavecontents.findtext("depth")
-    # extent = cavecontents.findtext("extent")
-    # survex_file = cavecontents.findtext("survex_file")
-    # description_file = cavecontents.findtext("description_file")
-    # url = cavecontents.findtext("url")
-
-    # areas = cavecontents.findall("area")
-    # entrances = cavecontents.findall("entrance")
-
-    # if (
-        # non_public is not None
- # # etc.
- # # wrong, some of these should be ==1 and some >=1 
-    # ):
-        # try:
-            # cave = caves_xslug.get(kataster_number)
-            # if cave is None:
-                # cave = Cave.objects.create(
-                    # non_public={
-                        # "True": True,
-                        # "False": False,
-                        # "true": True,
-                        # "false": False,
-                    # }[non_public],
-                    # official_name=official_name,
-                    # # kataster [truncated]
-
-
-
 def readcaves():
     """Called from databaseReset mass importer.
     Reads the xml-format HTML 'cave' files in the EXPOWEB repo, the survex files from the loser repo.
@@ -732,7 +679,6 @@ def readcaves():
     with transaction.atomic():
         area = get_area("1623")
 
-        print(" - settings.CAVEDESCRIPTIONS: ", CAVEDESCRIPTIONS)
         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
             read_entrance(filename)