2
0
mirror of https://expo.survex.com/repositories/troggle/.git synced 2024-11-22 15:21:52 +00:00
troggle/core/unused.py
2021-04-13 22:27:01 +01:00

130 lines
4.9 KiB
Python

import sys
import re
from django.conf import settings
from django.shortcuts import render
"""Oddball mixture of apparently now superfluous functions which should
be deleted
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
re_body = re.compile(r"\<body[^>]*\>(.*)\</body\>", re.DOTALL)
re_title = re.compile(r"\<title[^>]*\>(.*)\</title\>", 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"\<b[^>]*\>(.*?)\</b\>", re.DOTALL), r"'''\1'''"),
(re.compile(r"\<i\>(.*?)\</i\>", re.DOTALL), r"''\1''"),
(re.compile(r"\<h1[^>]*\>(.*?)\</h1\>", re.DOTALL), r"=\1="),
(re.compile(r"\<h2[^>]*\>(.*?)\</h2\>", re.DOTALL), r"==\1=="),
(re.compile(r"\<h3[^>]*\>(.*?)\</h3\>", re.DOTALL), r"===\1==="),
(re.compile(r"\<h4[^>]*\>(.*?)\</h4\>", re.DOTALL), r"====\1===="),
(re.compile(r"\<h5[^>]*\>(.*?)\</h5\>", re.DOTALL), r"=====\1====="),
(re.compile(r"\<h6[^>]*\>(.*?)\</h6\>", re.DOTALL), r"======\1======"),
(re.compile(r'(<a href="?(?P<target>.*)"?>)?<img class="?(?P<class>\w*)"? src="?t/?(?P<source>[\w/\.]*)"?(?P<rest>></img>|\s/>(</a>)?)', re.DOTALL),r'[[display:\g<class> photo:\g<source>]]'), #
(re.compile(r"\<a\s+id=['\"]([^'\"]*)['\"]\s*\>(.*?)\</a\>", re.DOTALL), r"[[subcave:\1|\2]]"), #assumes that all links with id attributes are subcaves. Not great.
#interpage link needed
(re.compile(r"\<a\s+href=['\"]#([^'\"]*)['\"]\s*\>(.*?)\</a\>", re.DOTALL), r"[[cavedescription:\1|\2]]"), #assumes that all links with target ids are cave descriptions. Not great.
(re.compile(r"\[\<a\s+href=['\"][^'\"]*['\"]\s+id=['\"][^'\"]*['\"]\s*\>([^\s]*).*?\</a\>\]", re.DOTALL), r"[[qm:\1]]"),
# (re.compile(r'<a\shref="?(?P<target>.*)"?>(?P<text>.*)</a>'),href_to_wikilinks),
]
def html_to_wiki(text, codec = "utf-8"):
if isinstance(text, str):
text = str(text, codec)
text = re.sub("</p>", r"", text)
text = re.sub("<p>$", r"", text)
text = re.sub("<p>", r"\n\n", text)
out = ""
lists = ""
#lists
while text:
mstar = re.match(r"^(.*?)<ul[^>]*>\s*<li[^>]*>(.*?)</li>(.*)$", text, re.DOTALL)
munstar = re.match(r"^(\s*)</ul>(.*)$", text, re.DOTALL)
mhash = re.match(r"^(.*?)<ol[^>]*>\s*<li[^>]*>(.*?)</li>(.*)$", text, re.DOTALL)
munhash = re.match(r"^(\s*)</ol>(.*)$", text, re.DOTALL)
mitem = re.match(r"^(\s*)<li[^>]*>(.*?)</li>(.*)$", 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