diff options
Diffstat (limited to 'parsers/caves.py')
| -rw-r--r-- | parsers/caves.py | 34 |
1 files changed, 23 insertions, 11 deletions
diff --git a/parsers/caves.py b/parsers/caves.py index f1c8c4f..808c2c0 100644 --- a/parsers/caves.py +++ b/parsers/caves.py @@ -556,10 +556,12 @@ def read_entrance(filename, ent=None): ent.save() return ent -def read_cave(filename, cave=None): +def read_cave(filename, mvf, cave=None): """Reads an entrance description from the .html file Convoluted. Sorry. Needs rewriting + mvf is a file handle for misnamed files + 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. @@ -685,18 +687,25 @@ def read_cave(filename, cave=None): if kataster_number: if slug == f"{areacode}-{kataster_number}": return slug - message = f" ! Cave Slug mismatch (kataster): '{slug}' != '{areacode}-{kataster_number}' {url=} in file {filename}. Adjusting.." + message = f" ! Cave Slug mismatch (kataster): '{slug}' != '{areacode}-{kataster_number}' {url=} in file {filename}. CHANGE caveslug field in the .html file." correctslug = f"{areacode}-{kataster_number}" + else: if slug == f"{areacode}-{unofficial_number}": return slug if slug.lower() == f"{areacode}-{unofficial_number.lower()}": - message = f" ! Cave Slug capitalisation incorrect (unofficial): '{slug}' != '{areacode}-{unofficial_number}' {url=} in file {filename}" + message = f" ! Cave Slug capitalisation incorrect (unofficial): '{slug}' != '{areacode}-{unofficial_number}' {url=} in file {filename}." correctslug = slug.lower() else: - message = f" ! Cave Slug mismatch (unofficial): '{slug}' != '{areacode}-{unofficial_number}' {url=} in file {filename}" + message = f" ! Cave Slug mismatch (unofficial): '{slug}' != '{areacode}-{unofficial_number}' {url=} in file {filename} CHANGE caveslug field in the .html file." correctslug = slug # hack to stopit crashing - DataIssue.objects.create(parser="caves", message=message, url=f"{cave.slug}_cave_edit/") + DataIssue.objects.create(parser="caves", message=message, url=f"{slug}_cave_edit/") # url here is for where the file actually is, for editing + mvtext = f"mv {filename} {correctslug}.html" + #print(mvtext) + if filename != f"{correctslug}.html" : + message = f" ! Filename is not the same as the cave slug '{slug}' != '{areacode}-{unofficial_number}' {url=} in file {filename} so use troggle/mvscript.sh to fix." + DataIssue.objects.create(parser="caves", message=message, url=f"{slug}_cave_edit/") # url here is for where the file actually is, for editing + mvf.write(mvtext + "\n") print(message) return correctslug @@ -716,7 +725,7 @@ def read_cave(filename, cave=None): DataIssue.objects.create(parser="caves", message=message, url=context) print(message) return None - + with open(fn) as f: contents = f.read() cavecontentslist = getXML(contents, "cave", maxItems=1, context=context) @@ -814,8 +823,8 @@ def read_cave(filename, cave=None): cave.url = f"{cave.areacode}/{cave.number()}/{cave.number()}.html" check_directory(cave.areacode, cave.number(), cave.url, cave) - # This next line has no effect because the cave slug is not actually a field on the Cave object so we can't fix it here. to-do. - slug = check_slug(cave.areacode,cave.kataster_number, cave.unofficial_number, cave.url) + # This next line has no effect because the cave slug is not actually a field on the Cave object so we can't fix it here. to-do! + slug = check_slug(cave.areacode, cave.kataster_number, cave.unofficial_number, cave.url) entrances = getXML(cavecontents, "entrance", context=context) do_entrances() @@ -905,9 +914,12 @@ def readcaves(): with transaction.atomic(): print(" - Reading Caves from cave descriptions xml files") - for filename in next(os.walk(CAVEDESCRIPTIONS))[2]: # Should be a better way of getting a list of files - if filename.endswith(".html"): - read_cave(filename) + mvscript = "mvscript.sh" + with open(mvscript, "w") as mvf: # overwrite + mvf.write(f"cd {CAVEDESCRIPTIONS}\n") + for filename in next(os.walk(CAVEDESCRIPTIONS))[2]: # Should be a better way of getting a list of files + if filename.endswith(".html"): + read_cave(filename, mvf) print(" - Setting up all the variously useful alias names") GetCaveLookup() |