diff options
Diffstat (limited to 'parsers')
| -rw-r--r-- | parsers/QMs.py | 10 | ||||
| -rw-r--r-- | parsers/caves.py | 9 | ||||
| -rw-r--r-- | parsers/cavetab.py | 2 | ||||
| -rw-r--r-- | parsers/logbooks.py | 39 | ||||
| -rw-r--r-- | parsers/people.py | 10 | ||||
| -rw-r--r-- | parsers/subcaves.py | 2 | ||||
| -rw-r--r-- | parsers/survex.py | 64 | ||||
| -rw-r--r-- | parsers/surveys.py | 28 |
8 files changed, 83 insertions, 81 deletions
diff --git a/parsers/QMs.py b/parsers/QMs.py index 47e6bc7..a5ecd2f 100644 --- a/parsers/QMs.py +++ b/parsers/QMs.py @@ -38,7 +38,7 @@ def parseCaveQMs(cave,inputFile): dialect=csv.Sniffer().sniff(qmCSVContents.read()) qmCSVContents.seek(0,0) qmReader = csv.reader(qmCSVContents,dialect=dialect) - qmReader.next() # Skip header row + next(qmReader) # Skip header row for line in qmReader: try: year=int(line[0][1:5]) @@ -48,7 +48,7 @@ def parseCaveQMs(cave,inputFile): elif cave=='hauch': placeholder, hadToCreate = LogbookEntry.objects.get_or_create(date__year=year, title="placeholder for QMs in 234", text="QMs temporarily attached to this should be re-attached to their actual trips", defaults={"date": date(year, 1, 1),"cave":hauchHl}) if hadToCreate: - print(cave + " placeholder logbook entry for " + str(year) + " added to database") + print((cave + " placeholder logbook entry for " + str(year) + " added to database")) QMnum=re.match(r".*?-\d*?-X?(?P<numb>\d*)",line[0]).group("numb") newQM = QM() newQM.found_by=placeholder @@ -71,9 +71,9 @@ def parseCaveQMs(cave,inputFile): if preexistingQM.new_since_parsing==False: #if the pre-existing QM has not been modified, overwrite it preexistingQM.delete() newQM.save() - print("overwriting " + str(preexistingQM) +"\r") + print(("overwriting " + str(preexistingQM) +"\r")) else: # otherwise, print that it was ignored - print("preserving " + str(preexistingQM) + ", which was edited in admin \r") + print(("preserving " + str(preexistingQM) + ", which was edited in admin \r")) except QM.DoesNotExist: #if there is no pre-existing QM, save the new one newQM.save() @@ -82,7 +82,7 @@ def parseCaveQMs(cave,inputFile): except KeyError: #check on this one continue except IndexError: - print("Index error in " + str(line)) + print(("Index error in " + str(line))) continue def parse_KH_QMs(kh, inputFile): diff --git a/parsers/caves.py b/parsers/caves.py index 4f65675..745b119 100644 --- a/parsers/caves.py +++ b/parsers/caves.py @@ -1,9 +1,10 @@ # -*- coding: utf-8 -*- -import troggle.core.models as models -from django.conf import settings import os import re +from django.conf import settings + +import troggle.core.models as models def readcaves(): @@ -14,11 +15,11 @@ def readcaves(): area_1626 = models.Area.objects.update_or_create(short_name = "1626", parent = None) print(" - Reading Entrances") #print "list of <Slug> <Filename>" - for filename in os.walk(settings.ENTRANCEDESCRIPTIONS).next()[2]: #Should be a better way of getting a list of files + for filename in next(os.walk(settings.ENTRANCEDESCRIPTIONS))[2]: #Should be a better way of getting a list of files if filename.endswith('.html'): readentrance(filename) print (" - Reading Caves") - for filename in os.walk(settings.CAVEDESCRIPTIONS).next()[2]: #Should be a better way of getting a list of files + for filename in next(os.walk(settings.CAVEDESCRIPTIONS))[2]: #Should be a better way of getting a list of files if filename.endswith('.html'): readcave(filename) diff --git a/parsers/cavetab.py b/parsers/cavetab.py index 99202d5..8d257a7 100644 --- a/parsers/cavetab.py +++ b/parsers/cavetab.py @@ -58,7 +58,7 @@ def LoadCaveTab(): cavetab = open(os.path.join(settings.EXPOWEB, "noinfo", "CAVETAB2.CSV"),'rU') caveReader = csv.reader(cavetab) - caveReader.next() # Strip out column headers + next(caveReader) # Strip out column headers logging.info("Beginning to import caves from "+str(cavetab)+"\n"+"-"*60+"\n") diff --git a/parsers/logbooks.py b/parsers/logbooks.py index 01800a1..ded90e4 100644 --- a/parsers/logbooks.py +++ b/parsers/logbooks.py @@ -40,7 +40,7 @@ def GetTripPersons(trippeople, expedition, logtime_underground): tripperson = re.sub(round_bracket_regex, "", tripperson).strip() personyear = GetPersonExpeditionNameLookup(expedition).get(tripperson.lower()) if not personyear: - print(" - No name match for: '%s'" % tripperson) + print((" - No name match for: '%s'" % tripperson)) message = "No name match for: '%s' in year '%s'" % (tripperson, expedition.year) models.DataIssue.objects.create(parser='logbooks', message=message) res.append((personyear, logtime_underground)) @@ -72,11 +72,11 @@ def GetTripCave(place): #need to be fuzzier about matching here. Already a very return tripCaveRes elif len(tripCaveRes)>1: - print("Ambiguous place " + str(place) + " entered. Choose from " + str(tripCaveRes)) - correctIndex=input("type list index of correct cave") + print(("Ambiguous place " + str(place) + " entered. Choose from " + str(tripCaveRes))) + correctIndex=eval(input("type list index of correct cave")) return tripCaveRes[correctIndex] else: - print("No cave found for place " , place) + print(("No cave found for place " , place)) return logentries = [] # the entire logbook is a single object: a list of entries @@ -92,7 +92,7 @@ def EnterLogIntoDbase(date, place, title, text, trippeople, expedition, logtime_ trippersons, author = GetTripPersons(trippeople, expedition, logtime_underground) if not author: - print(" - Skipping logentry: " + title + " - no author for entry") + print((" - Skipping logentry: " + title + " - no author for entry")) message = "Skipping logentry: %s - no author for entry in year '%s'" % (title, expedition.year) models.DataIssue.objects.create(parser='logbooks', message=message) return @@ -175,7 +175,7 @@ def Parseloghtmltxt(year, expedition, txt): ''', trippara) if not s: if not re.search(r"Rigging Guide", trippara): - print("can't parse: ", trippara) # this is 2007 which needs editing + print(("can't parse: ", trippara)) # this is 2007 which needs editing #assert s, trippara continue tripid, tripid1, tripdate, trippeople, triptitle, triptext, tu = s.groups() @@ -203,7 +203,7 @@ def Parseloghtmltxt(year, expedition, txt): def Parseloghtml01(year, expedition, txt): tripparas = re.findall(r"<hr[\s/]*>([\s\S]*?)(?=<hr)", txt) for trippara in tripparas: - s = re.match(u"(?s)\s*(?:<p>)?(.*?)</?p>(.*)$(?i)", trippara) + s = re.match("(?s)\s*(?:<p>)?(.*?)</?p>(.*)$(?i)", trippara) assert s, trippara[:300] tripheader, triptext = s.group(1), s.group(2) mtripid = re.search(r'<a id="(.*?)"', tripheader) @@ -251,7 +251,7 @@ def Parseloghtml01(year, expedition, txt): def Parseloghtml03(year, expedition, txt): tripparas = re.findall(r"<hr\s*/>([\s\S]*?)(?=<hr)", txt) for trippara in tripparas: - s = re.match(u"(?s)\s*<p>(.*?)</p>(.*)$", trippara) + s = re.match("(?s)\s*<p>(.*?)</p>(.*)$", trippara) assert s, trippara tripheader, triptext = s.group(1), s.group(2) tripheader = re.sub(r" ", " ", tripheader) @@ -261,7 +261,7 @@ def Parseloghtml03(year, expedition, txt): if re.match("T/U|Time underwater", sheader[-1]): tu = sheader.pop() if len(sheader) != 3: - print("header not three pieces", sheader) + print(("header not three pieces", sheader)) tripdate, triptitle, trippeople = sheader ldate = ParseDate(tripdate.strip(), year) triptitles = triptitle.split(" , ") @@ -325,35 +325,36 @@ def LoadLogbookForExpedition(expedition): #print " - Cache is more than 30 days old." bad_cache= True if bad_cache: - print " - Cache is either stale or more than 30 days old. Deleting it." + print(" - Cache is either stale or more than 30 days old. Deleting it.") os.remove(cache_filename) logentries=[] raise - print(" - Reading cache: " + cache_filename ) + print((" - Reading cache: " + cache_filename )) try: with open(cache_filename, "rb") as f: logentries = pickle.load(f) - print " - Loaded ", len(logentries), " objects" + print(" - Loaded ", len(logentries), " objects") logbook_cached = True except: - print " - Failed to load corrupt cache. Deleting it.\n" + print(" - Failed to load corrupt cache. Deleting it.\n") os.remove(cache_filename) logentries=[] + raise except: print(" - Opening logbook: ") - file_in = open(os.path.join(expowebbase, year_settings[0])) + file_in = open(os.path.join(expowebbase, year_settings[0]),'rb') txt = file_in.read().decode("latin1") file_in.close() parsefunc = year_settings[1] logbook_parseable = True - print(" - Parsing logbook: " + year_settings[0] + "\n - Using parser: " + year_settings[1]) + print((" - Parsing logbook: " + year_settings[0] + "\n - Using parser: " + year_settings[1])) if logbook_parseable: parser = globals()[parsefunc] parser(expedition.year, expedition, txt) SetDatesFromLogbookEntries(expedition) # and this has also stored all the objects in logentries[] - print " - Storing " , len(logentries), " log entries" + print(" - Storing " , len(logentries), " log entries") cache_filename = os.path.join(expowebbase, year_settings[0])+".cache" with open(cache_filename, "wb") as f: pickle.dump(logentries, f, 2) @@ -370,7 +371,7 @@ def LoadLogbookForExpedition(expedition): i +=1 else: try: - file_in = open(os.path.join(expowebbase, expedition.year, settings.DEFAULT_LOGBOOK_FILE)) + file_in = open(os.path.join(expowebbase, expedition.year, settings.DEFAULT_LOGBOOK_FILE),'rb') txt = file_in.read().decode("latin1") file_in.close() logbook_parseable = True @@ -378,7 +379,7 @@ def LoadLogbookForExpedition(expedition): parsefunc = settings.DEFAULT_LOGBOOK_PARSER except (IOError): logbook_parseable = False - print("Couldn't open default logbook file and nothing in settings for expo " + expedition.year) + print(("Couldn't open default logbook file and nothing in settings for expo " + expedition.year)) #return "TOLOAD: " + year + " " + str(expedition.personexpedition_set.all()[1].logbookentry_set.count()) + " " + str(models.PersonTrip.objects.filter(personexpedition__expedition=expedition).count()) @@ -391,7 +392,7 @@ def LoadLogbooks(): # Fetch all expos expos = models.Expedition.objects.all() for expo in expos: - print("\nLoading Logbook for: " + expo.year) + print(("\nLoading Logbook for: " + expo.year)) # Load logbook for expo LoadLogbookForExpedition(expo) diff --git a/parsers/people.py b/parsers/people.py index 265dacc..e05c5a3 100644 --- a/parsers/people.py +++ b/parsers/people.py @@ -4,7 +4,7 @@ from django.conf import settings import troggle.core.models as models import csv, re, datetime, os, shutil from utils import save_carefully -from HTMLParser import HTMLParser +from html.parser import HTMLParser from unidecode import unidecode # def saveMugShot(mugShotPath, mugShotFilename, person): @@ -45,7 +45,7 @@ def parseMugShotAndBlurb(personline, header, person): #Only finds the first image, not all of them person.blurb=re.search('<body>.*<hr',personPageOld,re.DOTALL).group() else: - print "ERROR: --------------- Broken link or Blurb parse error in ", mugShotFilename + print("ERROR: --------------- Broken link or Blurb parse error in ", mugShotFilename) #for mugShotFilename in re.findall('i/.*?jpg',personPageOld,re.DOTALL): # mugShotPath = os.path.join(settings.EXPOWEB, "folk", mugShotFilename) # saveMugShot(mugShotPath=mugShotPath, mugShotFilename=mugShotFilename, person=person) @@ -55,8 +55,8 @@ def LoadPersonsExpos(): persontab = open(os.path.join(settings.EXPOWEB, "folk", "folk.csv")) personreader = csv.reader(persontab) - headers = personreader.next() - header = dict(zip(headers, range(len(headers)))) + headers = next(personreader) + header = dict(list(zip(headers, list(range(len(headers)))))) # make expeditions print(" - Loading expeditions") @@ -100,7 +100,7 @@ def LoadPersonsExpos(): parseMugShotAndBlurb(personline=personline, header=header, person=person) # make person expedition from table - for year, attended in zip(headers, personline)[5:]: + for year, attended in list(zip(headers, personline))[5:]: expedition = models.Expedition.objects.get(year=year) if attended == "1" or attended == "-1": lookupAttribs = {'person':person, 'expedition':expedition} diff --git a/parsers/subcaves.py b/parsers/subcaves.py index 739af44..5889a91 100644 --- a/parsers/subcaves.py +++ b/parsers/subcaves.py @@ -34,7 +34,7 @@ def importSubcaves(cave): nonLookupAttribs={'description':description} newSubcave=save_carefully(Subcave,lookupAttribs=lookupAttribs,nonLookupAttribs=nonLookupAttribs) - logging.info("Added " + unicode(newSubcave) + " to " + unicode(cave)) + logging.info("Added " + str(newSubcave) + " to " + str(cave)) except IOError: logging.info("Subcave import couldn't open "+subcaveFilePath) diff --git a/parsers/survex.py b/parsers/survex.py index 38cae62..907b183 100644 --- a/parsers/survex.py +++ b/parsers/survex.py @@ -33,27 +33,27 @@ def LoadSurvexLineLeg(survexblock, stardata, sline, comment, cave): try: survexleg.tape = float(ls[stardata["tape"]]) except ValueError: - print("! Tape misread in", survexblock.survexfile.path) - print(" Stardata:", stardata) - print(" Line:", ls) + print(("! Tape misread in", survexblock.survexfile.path)) + print((" Stardata:", stardata)) + print((" Line:", ls)) message = ' ! Value Error: Tape misread in line %s in %s' % (ls, survexblock.survexfile.path) models.DataIssue.objects.create(parser='survex', message=message) survexleg.tape = 1000 try: lclino = ls[stardata["clino"]] except: - print("! Clino misread in", survexblock.survexfile.path) - print(" Stardata:", stardata) - print(" Line:", ls) + print(("! Clino misread in", survexblock.survexfile.path)) + print((" Stardata:", stardata)) + print((" Line:", ls)) message = ' ! Value Error: Clino misread in line %s in %s' % (ls, survexblock.survexfile.path) models.DataIssue.objects.create(parser='survex', message=message) lclino = error try: lcompass = ls[stardata["compass"]] except: - print("! Compass misread in", survexblock.survexfile.path) - print(" Stardata:", stardata) - print(" Line:", ls) + print(("! Compass misread in", survexblock.survexfile.path)) + print((" Stardata:", stardata)) + print((" Line:", ls)) message = ' ! Value Error: Compass misread in line %s in %s' % (ls, survexblock.survexfile.path) models.DataIssue.objects.create(parser='survex', message=message) lcompass = error @@ -67,9 +67,9 @@ def LoadSurvexLineLeg(survexblock, stardata, sline, comment, cave): try: survexleg.compass = float(lcompass) except ValueError: - print("! Compass misread in", survexblock.survexfile.path) - print(" Stardata:", stardata) - print(" Line:", ls) + print(("! Compass misread in", survexblock.survexfile.path)) + print((" Stardata:", stardata)) + print((" Line:", ls)) message = ' ! Value Error: line %s in %s' % (ls, survexblock.survexfile.path) models.DataIssue.objects.create(parser='survex', message=message) survexleg.compass = 1000 @@ -143,7 +143,7 @@ def RecursiveLoad(survexblock, survexfile, fin, textlines): global insp # uncomment to print out all files during parsing - print(insp+" - Reading file: " + survexblock.survexfile.path + " <> " + survexfile.path) + print((insp+" - Reading file: " + survexblock.survexfile.path + " <> " + survexfile.path)) stamp = datetime.now() lineno = 0 @@ -196,7 +196,7 @@ def RecursiveLoad(survexblock, survexfile, fin, textlines): # print(insp+' - Wallet ; ref - %s - found in survexscansfolders' % refscan) else: message = ' ! Wallet ; ref - %s - NOT found in survexscansfolders %s-%s-%s' % (refscan,yr,letterx,wallet) - print(insp+message) + print((insp+message)) models.DataIssue.objects.create(parser='survex', message=message) # This whole section should be moved if we can have *QM become a proper survex command @@ -268,7 +268,7 @@ def RecursiveLoad(survexblock, survexfile, fin, textlines): # print(insp+' - Wallet *REF - %s - found in survexscansfolders' % refscan) else: message = ' ! Wallet *REF - %s - NOT found in survexscansfolders %s-%s-%s' % (refscan,yr,letterx,wallet) - print(insp+message) + print((insp+message)) models.DataIssue.objects.create(parser='survex', message=message) continue @@ -293,7 +293,7 @@ def RecursiveLoad(survexblock, survexfile, fin, textlines): cmd = cmd.lower() if re.match("include$(?i)", cmd): includepath = os.path.join(os.path.split(survexfile.path)[0], re.sub(r"\.svx$", "", line)) - print(insp+' - Include path found including - ' + includepath) + print((insp+' - Include path found including - ' + includepath)) # Try to find the cave in the DB if not use the string as before path_match = re.search(r"caves-(\d\d\d\d)/(\d+|\d\d\d\d-?\w+-\d+)/", includepath) if path_match: @@ -303,7 +303,7 @@ def RecursiveLoad(survexblock, survexfile, fin, textlines): if cave: survexfile.cave = cave else: - print(insp+' - No match in DB (i) for %s, so loading..' % includepath) + print((insp+' - No match in DB (i) for %s, so loading..' % includepath)) includesurvexfile = models.SurvexFile(path=includepath) includesurvexfile.save() includesurvexfile.SetDirectory() @@ -326,10 +326,10 @@ def RecursiveLoad(survexblock, survexfile, fin, textlines): if cave: survexfile.cave = cave else: - print(insp+' - No match (b) for %s' % newsvxpath) + print((insp+' - No match (b) for %s' % newsvxpath)) name = line.lower() - print(insp+' - Begin found for: ' + name) + print((insp+' - Begin found for: ' + name)) # print(insp+'Block cave: ' + str(survexfile.cave)) survexblockdown = models.SurvexBlock(name=name, begin_char=fin.tell(), parent=survexblock, survexpath=survexblock.survexpath+"."+name, cave=survexfile.cave, survexfile=survexfile, totalleglength=0.0) survexblockdown.save() @@ -420,7 +420,7 @@ def RecursiveLoad(survexblock, survexfile, fin, textlines): if cmd not in ["sd", "include", "units", "entrance", "data", "flags", "title", "export", "instrument", "calibrate", "set", "infer", "alias", "cs", "declination", "case"]: message = "! Bad svx command in line:%s %s %s %s" % (cmd, line, survexblock, survexblock.survexfile.path) - print(insp+message) + print((insp+message)) models.DataIssue.objects.create(parser='survex', message=message) endstamp = datetime.now() @@ -482,7 +482,7 @@ def LoadPos(): If we don't have it in the database, print an error message and discard it. """ topdata = settings.SURVEX_DATA + settings.SURVEX_TOPNAME - print(' - Generating a list of Pos from %s.svx and then loading...' % (topdata)) + print((' - Generating a list of Pos from %s.svx and then loading...' % (topdata))) # Be careful with the cache file. # If LoadPos has been run before, @@ -498,39 +498,39 @@ def LoadPos(): updtsvx = os.path.getmtime(topdata + ".svx") updtcache = os.path.getmtime(cachefile) age = updtcache - updtsvx - print(' svx: %s cache: %s not-found cache is fresher by: %s' % (updtsvx, updtcache, str(timedelta(seconds=age) ))) + print((' svx: %s cache: %s not-found cache is fresher by: %s' % (updtsvx, updtcache, str(timedelta(seconds=age) )))) now = time.time() if now - updtcache > 3*24*60*60: - print " cache is more than 3 days old. Deleting." + print(" cache is more than 3 days old. Deleting.") os.remove(cachefile) elif age < 0 : - print " cache is stale. Deleting." + print(" cache is stale. Deleting.") os.remove(cachefile) else: - print " cache is fresh. Reading..." + print(" cache is fresh. Reading...") try: with open(cachefile, "r") as f: for line in f: l = line.rstrip() if l in notfoundbefore: notfoundbefore[l] +=1 # should not be duplicates - print " DUPLICATE ", line, notfoundbefore[l] + print(" DUPLICATE ", line, notfoundbefore[l]) else: notfoundbefore[l] =1 except: - print " FAILURE READ opening cache file %s" % (cachefile) + print(" FAILURE READ opening cache file %s" % (cachefile)) raise notfoundnow =[] found = 0 skip = {} - print "\n" # extra line because cavern overwrites the text buffer somehow + print("\n") # extra line because cavern overwrites the text buffer somehow # cavern defaults to using same cwd as supplied input file call([settings.CAVERN, "--output=%s.3d" % (topdata), "%s.svx" % (topdata)]) call([settings.THREEDTOPOS, '%s.3d' % (topdata)], cwd = settings.SURVEX_DATA) - print " - This next bit takes a while. Matching ~32,000 survey positions. Be patient..." + print(" - This next bit takes a while. Matching ~32,000 survey positions. Be patient...") posfile = open("%s.pos" % (topdata)) posfile.readline() #Drop header @@ -550,7 +550,7 @@ def LoadPos(): found += 1 except: notfoundnow.append(name) - print " - %s stations not found in lookup of SurvexStation.objects. %s found. %s skipped." % (len(notfoundnow),found, len(skip)) + print(" - %s stations not found in lookup of SurvexStation.objects. %s found. %s skipped." % (len(notfoundnow),found, len(skip))) if found > 10: # i.e. a previous cave import has been done try: @@ -560,8 +560,8 @@ def LoadPos(): f.write("%s\n" % i) for j in skip: f.write("%s\n" % j) # NB skip not notfoundbefore - print(' Not-found cache file written: %s entries' % c) + print((' Not-found cache file written: %s entries' % c)) except: - print " FAILURE WRITE opening cache file %s" % (cachefile) + print(" FAILURE WRITE opening cache file %s" % (cachefile)) raise diff --git a/parsers/surveys.py b/parsers/surveys.py index 942c0a5..2f0ff90 100644 --- a/parsers/surveys.py +++ b/parsers/surveys.py @@ -10,7 +10,7 @@ import csv import re import datetime -#from PIL import Image +from PIL import Image from utils import save_carefully from functools import reduce @@ -82,14 +82,14 @@ def get_or_create_placeholder(year): # logging.info("added survey " + survey[header['Year']] + "#" + surveyobj.wallet_number + "\r") # dead -# def listdir(*directories): - # try: - # return os.listdir(os.path.join(settings.SURVEYS, *directories)) - # except: - # import urllib.request, urllib.parse, urllib.error - # url = settings.SURVEYS + reduce(lambda x, y: x + "/" + y, ["listdir"] + list(directories)) - # folders = urllib.request.urlopen(url.replace("#", "%23")).readlines() - # return [folder.rstrip(r"/") for folder in folders] +def listdir(*directories): + try: + return os.listdir(os.path.join(settings.SURVEYS, *directories)) + except: + import urllib.request, urllib.parse, urllib.error + url = settings.SURVEYS + reduce(lambda x, y: x + "/" + y, ["listdir"] + list(directories)) + folders = urllib.request.urlopen(url.replace("#", "%23")).readlines() + return [folder.rstrip(r"/") for folder in folders] # add survey scans # def parseSurveyScans(expedition, logfile=None): @@ -252,7 +252,7 @@ def LoadListScans(): def FindTunnelScan(tunnelfile, path): scansfolder, scansfile = None, None - mscansdir = re.search(r"(\d\d\d\d#X?\d+\w?|1995-96kh|92-94Surveybookkh|1991surveybook|smkhs)/(.*?(?:png|jpg|pdf|jpeg))$", path) + mscansdir = re.search(rb"(\d\d\d\d#X?\d+\w?|1995-96kh|92-94Surveybookkh|1991surveybook|smkhs)/(.*?(?:png|jpg|pdf|jpeg))$", path) if mscansdir: scansfolderl = SurvexScansFolder.objects.filter(walletname=mscansdir.group(1)) if len(scansfolderl): @@ -273,7 +273,7 @@ def FindTunnelScan(tunnelfile, path): if scansfile: tunnelfile.survexscans.add(scansfile) - elif path and not re.search(r"\.(?:png|jpg|pdf|jpeg)$(?i)", path): + elif path and not re.search(rb"\.(?:png|jpg|pdf|jpeg)$(?i)", path): name = os.path.split(path)[1] #print("debug-tunnelfileobjects ", tunnelfile.tunnelpath, path, name) rtunnelfilel = TunnelFile.objects.filter(tunnelname=name) @@ -295,16 +295,16 @@ def SetTunnelfileInfo(tunnelfile): if tunnelfile.filesize <= 0: print("DEBUG - zero length xml file", ff) return - mtype = re.search(r"<(fontcolours|sketch)", ttext) + mtype = re.search(rb"<(fontcolours|sketch)", ttext) assert mtype, ff tunnelfile.bfontcolours = (mtype.group(1)=="fontcolours") - tunnelfile.npaths = len(re.findall(r"<skpath", ttext)) + tunnelfile.npaths = len(re.findall(rb"<skpath", ttext)) tunnelfile.save() # <tunnelxml tunnelversion="version2009-06-21 Matienzo" tunnelproject="ireby" tunneluser="goatchurch" tunneldate="2009-06-29 23:22:17"> # <pcarea area_signal="frame" sfscaledown="12.282584" sfrotatedeg="-90.76982" sfxtrans="11.676667377221136" sfytrans="-15.677173422877454" sfsketch="204description/scans/plan(38).png" sfstyle="" nodeconnzsetrelative="0.0"> - for path, style in re.findall(r'<pcarea area_signal="frame".*?sfsketch="([^"]*)" sfstyle="([^"]*)"', ttext): + for path, style in re.findall(rb'<pcarea area_signal="frame".*?sfsketch="([^"]*)" sfstyle="([^"]*)"', ttext): FindTunnelScan(tunnelfile, path) # should also scan and look for survex blocks that might have been included |