From 2a1710596a48ce0dbd2b4aa5f510f0c79bd57b99 Mon Sep 17 00:00:00 2001 From: Philip Sargent Date: Tue, 13 Apr 2021 00:11:08 +0100 Subject: moving save_carefully() --- utils.py | 173 --------------------------------------------------------------- 1 file changed, 173 deletions(-) delete mode 100644 utils.py (limited to 'utils.py') diff --git a/utils.py b/utils.py deleted file mode 100644 index b667e09..0000000 --- a/utils.py +++ /dev/null @@ -1,173 +0,0 @@ -import sys -import random -import re -import logging - -from django.conf import settings -from django.shortcuts import render - -"""Oddball mixture of critical, superfluous and useful functions which should -be re-located more sensibly to other modules: - - -various HTML/wiki functions presumably for logbooks? - -Use unknown: -weighted_choice(lst) -randomLogbookSentence() -""" - - -def weighted_choice(lst): - n = random.uniform(0,1) - for item, weight in lst: - if n < weight: - break - n = n - weight - return item - -def randomLogbookSentence(): - from troggle.core.models import LogbookEntry - randSent={} - - # needs to handle empty logbooks without crashing - - #Choose a random logbook entry - randSent['entry']=LogbookEntry.objects.order_by('?')[0] - - #Choose again if there are no sentances (this happens if it is a placeholder entry) - while len(re.findall('[A-Z].*?\.',randSent['entry'].text))==0: - randSent['entry']=LogbookEntry.objects.order_by('?')[0] - - #Choose a random sentence from that entry. Store the sentence as randSent['sentence'], and the number of that sentence in the entry as randSent['number'] - sentenceList=re.findall('[A-Z].*?\.',randSent['entry'].text) - randSent['number']=random.randrange(0,len(sentenceList)) - randSent['sentence']=sentenceList[randSent['number']] - - return randSent - - -def save_carefully(objectType, lookupAttribs={}, nonLookupAttribs={}): - """Looks up instance using lookupAttribs and carries out the following: - -if instance does not exist in DB: add instance to DB, return (new instance, True) - -if instance exists in DB and was modified using Troggle: do nothing, return (existing instance, False) - -if instance exists in DB and was not modified using Troggle: overwrite instance, return (instance, False) - - The checking is accomplished using Django's get_or_create and the new_since_parsing boolean field - defined in core.models.TroggleModel. - - """ - try: - instance, created = objectType.objects.get_or_create(defaults=nonLookupAttribs, **lookupAttribs) - except: - print(" !! - SAVE CAREFULLY ===================", objectType) - print(" !! - -- objects.get_or_create()") - print(" !! - lookupAttribs:{}\n !! - nonLookupAttribs:{}".format(lookupAttribs,nonLookupAttribs)) - raise - if not created and not instance.new_since_parsing: - for k, v in list(nonLookupAttribs.items()): #overwrite the existing attributes from the logbook text (except date and title) - setattr(instance, k, v) - try: - instance.save() - except: - print(" !! - SAVE CAREFULLY ===================", objectType) - print(" !! - -- instance.save()") - print(" !! - lookupAttribs:{}\n !! - nonLookupAttribs:{}".format(lookupAttribs,nonLookupAttribs)) - raise - try: - msg = str(instance) - except: - msg = "FAULT getting __str__ for instance with lookupattribs: {}:".format(lookupAttribs) - if created: - logging.info(str(instance) + ' was just added to the database for the first time. \n') - - if not created and instance.new_since_parsing: - logging.info(str(instance) + " has been modified using Troggle, so the current script left it as is. \n") - - if not created and not instance.new_since_parsing: - logging.info(str(instance) + " existed in the database unchanged since last parse. It was overwritten by the current script. \n") - return (instance, created) - -re_body = re.compile(r"\]*\>(.*)\", re.DOTALL) -re_title = re.compile(r"\]*\>(.*)\", re.DOTALL) - -def get_html_body(text): - return get_single_match(re_body, text) - -def get_html_title(text): - return get_single_match(re_title, text) - -def get_single_match(regex, text): - match = regex.search(text) - - if match: - return match.groups()[0] - else: - return None - -re_subs = [(re.compile(r"\]*\>(.*?)\", re.DOTALL), r"'''\1'''"), - (re.compile(r"\(.*?)\", re.DOTALL), r"''\1''"), - (re.compile(r"\]*\>(.*?)\", re.DOTALL), r"=\1="), - (re.compile(r"\]*\>(.*?)\", re.DOTALL), r"==\1=="), - (re.compile(r"\]*\>(.*?)\", re.DOTALL), r"===\1==="), - (re.compile(r"\]*\>(.*?)\", re.DOTALL), r"====\1===="), - (re.compile(r"\]*\>(.*?)\", re.DOTALL), r"=====\1====="), - (re.compile(r"\]*\>(.*?)\", re.DOTALL), r"======\1======"), - (re.compile(r'()?>|\s/>()?)', re.DOTALL),r'[[display:\g photo:\g]]'), # - (re.compile(r"\(.*?)\", re.DOTALL), r"[[subcave:\1|\2]]"), #assumes that all links with id attributes are subcaves. Not great. - #interpage link needed - (re.compile(r"\(.*?)\", re.DOTALL), r"[[cavedescription:\1|\2]]"), #assumes that all links with target ids are cave descriptions. Not great. - (re.compile(r"\[\([^\s]*).*?\\]", re.DOTALL), r"[[qm:\1]]"), -# (re.compile(r'.*)"?>(?P.*)'),href_to_wikilinks), - ] - -def html_to_wiki(text, codec = "utf-8"): - if isinstance(text, str): - text = str(text, codec) - text = re.sub("

", r"", text) - text = re.sub("

$", r"", text) - text = re.sub("

", r"\n\n", text) - out = "" - lists = "" - #lists - while text: - mstar = re.match("^(.*?)]*>\s*]*>(.*?)(.*)$", text, re.DOTALL) - munstar = re.match("^(\s*)(.*)$", text, re.DOTALL) - mhash = re.match("^(.*?)]*>\s*]*>(.*?)(.*)$", text, re.DOTALL) - munhash = re.match("^(\s*)(.*)$", text, re.DOTALL) - mitem = re.match("^(\s*)]*>(.*?)(.*)$", text, re.DOTALL) - ms = [len(m.groups()[0]) for m in [mstar, munstar, mhash, munhash, mitem] if m] - def min_(i, l): - try: - v = i.groups()[0] - l.remove(len(v)) - return len(v) < min(l, 1000000000) - except: - return False - if min_(mstar, ms): - lists += "*" - pre, val, post = mstar.groups() - out += pre + "\n" + lists + " " + val - text = post - elif min_(mhash, ms): - lists += "#" - pre, val, post = mhash.groups() - out += pre + "\n" + lists + " " + val - text = post - elif min_(mitem, ms): - pre, val, post = mitem.groups() - out += "\n" + lists + " " + val - text = post - elif min_(munstar, ms): - lists = lists[:-1] - text = munstar.groups()[1] - elif min_(munhash, ms): - lists.pop() - text = munhash.groups()[1] - else: - out += text - text = "" - #substitutions - for regex, repl in re_subs: - out = regex.sub(repl, out) - return out \ No newline at end of file -- cgit v1.2.3