From dd0fcc28ddc4768fb8fa3edcec32ee205d77101b Mon Sep 17 00:00:00 2001 From: Philip Sargent Date: Wed, 27 Jul 2022 23:24:40 +0300 Subject: update todo strings --- parsers/survex.py | 1 - 1 file changed, 1 deletion(-) (limited to 'parsers/survex.py') diff --git a/parsers/survex.py b/parsers/survex.py index 7b94005..615019d 100644 --- a/parsers/survex.py +++ b/parsers/survex.py @@ -37,7 +37,6 @@ todo = '''Also walk the entire tree in the :loser: repo looking for unconnected - LoadSurvexFile() Creates a new current survexfile and valid .survexdirectory The survexblock passed-in is not necessarily the parent. FIX THIS. -- rx_qm recognises only simple survey point ids. EXTEND to cover more naming formats and test fully for 2023 ''' survexblockroot = None ROOTBLOCK = "rootblock" -- cgit v1.2.3 From 93622b111f4a7136033ccf844a7e03a4093cb336 Mon Sep 17 00:00:00 2001 From: Philip Sargent Date: Thu, 28 Jul 2022 15:15:11 +0300 Subject: obscure bug fixed for lines ;*include --- core/models/survex.py | 2 +- parsers/survex.py | 25 ++++++++++++------------- 2 files changed, 13 insertions(+), 14 deletions(-) (limited to 'parsers/survex.py') diff --git a/core/models/survex.py b/core/models/survex.py index 29241f9..d8a5fb5 100644 --- a/core/models/survex.py +++ b/core/models/survex.py @@ -20,7 +20,7 @@ class SurvexDirectory(models.Model): verbose_name_plural = "Survex directories" def __str__(self): - return "[SurvexDirectory:"+str(self.path) + "-" + str(self.primarysurvexfile.path) + "-" + str(self.cave)+"]" + return "[SurvexDirectory:"+str(self.path) + " | Primary svx:" + str(self.primarysurvexfile.path) +".svx ]" class SurvexFile(models.Model): diff --git a/parsers/survex.py b/parsers/survex.py index 615019d..5eee625 100644 --- a/parsers/survex.py +++ b/parsers/survex.py @@ -130,8 +130,8 @@ class LoadingSurvex(): rx_cave = re.compile(r'(?i)caves-(\d\d\d\d)/([-\d\w]+|\d\d\d\d-?\w+-\d+)') rx_comment = re.compile(r'([^;]*?)\s*(?:;\s*(.*))?\n?$') - rx_comminc = re.compile(r'(?i)^\*include[\s]*([-\w/]*).*$') # inserted by linear collate ;*include - rx_commcni = re.compile(r'(?i)^\*edulcni[\s]*([-\w/]*).*$') # inserted by linear collate ;*edulcni + rx_comminc = re.compile(r'(?i)^\|\*include[\s]*([-\w/]*).*$') # inserted by linear collate ;*include + rx_commcni = re.compile(r'(?i)^\|\*edulcni[\s]*([-\w/]*).*$') # inserted by linear collate ;*edulcni rx_include = re.compile(r'(?i)^\s*(\*include[\s].*)$') rx_commref = re.compile(r'(?i)^\s*ref(?:erence)?[\s.:]*(\d+)\s*#\s*(X)?\s*(\d+)') rx_wallet = re.compile(r'(?i)^\s*wallet[\s.:]*(\d+)\s*#\s*(X)?\s*(\d+)') @@ -177,7 +177,7 @@ class LoadingSurvex(): callcount = 0 caverncount = 0 ignoreprefix = ["surface", "kataster", "fixedpts", "gpx"] - ignorenoncave = ["caves-1623", "caves-1623/2007-neu"] + ignorenoncave = ["caves-1623", "caves-1626", "caves-1623/2007-neu"] includedfilename ="" currentsurvexblock = None currentsurvexfile = None @@ -689,9 +689,7 @@ class LoadingSurvex(): def IdentifyCave(self, cavepath): if cavepath.lower() in self.caveslist: return self.caveslist[cavepath.lower()] - # TO DO - some of this is already done in generating self.caveslist so simplify this - # esp. as it is in a loop. - # TO DO recognise cave if different name, e.g. gruenstein == 281 + # TO DO - this predates the big revision to Gcavelookup so look at this again carefully path_match = self.rx_cave.search(cavepath) if path_match: sluggy = '{}-{}'.format(path_match.group(1), path_match.group(2)) @@ -724,17 +722,17 @@ class LoadingSurvex(): """Ignore surface, kataser and gpx *include survex files """ if headpath in self.ignorenoncave: - #message = f" - {headpath} is (while creating '{includelabel}' sfile & sdirectory)" + message = f" - {headpath} is (while creating '{includelabel}' sfile & sdirectory)" #print("\n"+message) #print("\n"+message,file=sys.stderr) return for i in self.ignoreprefix: if headpath.startswith(i): message = f" - {headpath} starts with (while creating '{includelabel}' sfile & sdirectory)" - #print("\n"+message) - #print("\n"+message,file=sys.stderr) + # print("\n"+message) + # print("\n"+message,file=sys.stderr) return - message = f" ! Error: FAILURE '{headpath}' while creating '{includelabel}' at depth:[{depth}]. Not a cave or in the ignore list:'{self.ignoreprefix}'" + message = f" ! Error: not a cave nor ignorable. headpath:'{headpath}' while creating '{includelabel=}' at depth:[{len(depth)}]. ignore prefix list:'{self.ignoreprefix}'" # getting this triggered for gpx/2018 (cavern error) but not for gpx/2017 (no content). print("\n"+message) print("\n"+message,file=sys.stderr) @@ -779,7 +777,7 @@ class LoadingSurvex(): if cave: newdirectory.cave = cave newfile.cave = cave - # print(f"\n - New directory {newdirectory} for cave {newdirectory.cave}",file=sys.stderr) + # print(f"\n - New directory '{newdirectory}' for cave '{cave}'",file=sys.stderr) else: # probably a surface survey, or a cave in a new area e.g. 1624 not previously managed, and not in the pending list self.ReportNonCaveIncludes(headpath, svxid, depth) @@ -861,6 +859,7 @@ class LoadingSurvex(): included = self.rx_comminc.match(comment) # ;*include means 'we have been included'; whereas *include means 'proceed to include' + # bug, If the original survex file contians the line ;*include then we pick it up ! So fix our special code to be ;|*include if included: self.ProcessIncludeLine(included) @@ -1210,7 +1209,7 @@ class LoadingSurvex(): #-------------------------------------------------------- self.depthinclude += 1 fininclude = open(fullpath,'r') - fcollate.write(";*include {}\n".format(includepath)) + fcollate.write(";|*include {}\n".format(includepath)) flinear.write("{:2} {} *include {}\n".format(self.depthinclude, indent, includepath)) push = includepath.lower() self.includestack.append(push) @@ -1225,7 +1224,7 @@ class LoadingSurvex(): print(message,file=sys.stderr) DataIssue.objects.create(parser='survex', message=message, url=get_offending_filename(path)) flinear.write("{:2} {} *edulcni {}\n".format(self.depthinclude, indent, pop)) - fcollate.write(";*edulcni {}\n".format(pop)) + fcollate.write(";|*edulcni {}\n".format(pop)) fininclude.close() self.depthinclude -= 1 #-------------------------------------------------------- -- cgit v1.2.3 From 7872e98cb2a8f8b087afab4c7a93d5ba71624fd2 Mon Sep 17 00:00:00 2001 From: Philip Sargent Date: Thu, 28 Jul 2022 18:36:57 +0300 Subject: fixing pending caves system to be cleaner --- parsers/caves.py | 55 +++++++++++++++++++++++++++++++++---------------------- parsers/survex.py | 22 +++++++++++++++++++--- 2 files changed, 52 insertions(+), 25 deletions(-) (limited to 'parsers/survex.py') diff --git a/parsers/caves.py b/parsers/caves.py index bc2bfbc..9d95f32 100644 --- a/parsers/caves.py +++ b/parsers/caves.py @@ -84,6 +84,15 @@ def do_pending_cave(k, url, area): in expoweb/cave_data/1623-"k".html ''' slug = k + + g = GetCaveLookup() + if slug in g: + message = f" ! {k} cave listed in pendingcaves.txt already exists." + DataIssue.objects.create(parser='caves', message=message, url=url) + print(message) + return + + default_note = f"_Survex file found in loser repo but no description in expoweb


\n" default_note += f"INSTRUCTIONS: First open 'This survex file' (link above the CaveView panel) to find the date and info. Then " @@ -111,7 +120,7 @@ def do_pending_cave(k, url, area): cave = Cave( unofficial_number = k, underground_description = "Pending cave write-up - creating as empty object. No XML file available yet.", - survex_file = f"caves-{area.short_name}/{k}/{k}.svx", + survex_file = f"caves-{area.short_name}/{k[5:]}/{k[5:]}.svx", url = url, notes = default_note) if cave: @@ -458,27 +467,6 @@ def readcaves(): print(" - Saving Area 1626") area_1626.save() - print (" - Setting pending caves") - # Do this first, so that these empty entries are overwritten as they get properly created. - - for k in pending: - - area = area_1623 - areanum = k[0:4] - url = areanum + "/" + k[5:] # Note we are not appending the .htm as we are modern folks now. - if areanum == "1623": - area = area_1623 - if areanum == "1624": - area = area_1624 - if areanum == "1626": - area = area_1626 - try: - do_pending_cave(k[5:], url, area) - except: - message = f" ! Error. Cannot create pending cave and entrance, pending-id:{k} in area {areanum}" - DataIssue.objects.create(parser='caves', message=message) - print(message) - raise with transaction.atomic(): print(" - settings.CAVEDESCRIPTIONS: ", CAVEDESCRIPTIONS) @@ -498,4 +486,27 @@ def readcaves(): print (" - Setting up all the variously useful alias names") mycavelookup = GetCaveLookup() + + print (" - Setting pending caves") + # Do this last, so we can detect if they are created and no longer 'pending' + + for k in pending: + + area = area_1623 + areanum = k[0:4] + url = areanum + "/" + k[5:] # Note we are not appending the .htm as we are modern folks now. + if areanum == "1623": + area = area_1623 + if areanum == "1624": + area = area_1624 + if areanum == "1626": + area = area_1626 + try: + do_pending_cave(k, url, area) + except: + message = f" ! Error. Cannot create pending cave and entrance, pending-id:{k} in area {areanum}" + DataIssue.objects.create(parser='caves', message=message) + print(message) + raise + diff --git a/parsers/survex.py b/parsers/survex.py index 5eee625..39d42dc 100644 --- a/parsers/survex.py +++ b/parsers/survex.py @@ -184,6 +184,7 @@ class LoadingSurvex(): currentcave = None caverndate = None currentpersonexped = [] + pending = [] def __init__(self): self.caveslist = GetCaveLookup() @@ -721,6 +722,15 @@ class LoadingSurvex(): def ReportNonCaveIncludes(self, headpath, includelabel, depth): """Ignore surface, kataser and gpx *include survex files """ + if not self.pending: + self.pending = set() + fpending = Path(settings.CAVEDESCRIPTIONS, "pendingcaves.txt") + if fpending.is_file(): + with open(fpending, "r") as fo: + cids = fo.readlines() + for cid in cids: + self.pending.add(cid.rstrip('\n').upper()) + if headpath in self.ignorenoncave: message = f" - {headpath} is (while creating '{includelabel}' sfile & sdirectory)" #print("\n"+message) @@ -732,20 +742,26 @@ class LoadingSurvex(): # print("\n"+message) # print("\n"+message,file=sys.stderr) return - message = f" ! Error: not a cave nor ignorable. headpath:'{headpath}' while creating '{includelabel=}' at depth:[{len(depth)}]. ignore prefix list:'{self.ignoreprefix}'" - # getting this triggered for gpx/2018 (cavern error) but not for gpx/2017 (no content). + caveid = f'{headpath[6:10]}-{headpath[11:]}'.upper() + if caveid in self.pending: + # Yes we didn't find this cave, but we know it is a pending one. So not an error. + # print(f'! ALREADY PENDING {caveid}',file=sys.stderr) + return + + message = f" ! Error: not a cave nor ignorable. headpath:'{headpath}' while parsing '{includelabel=}.svx' at depth:[{len(depth)}]. ignore prefix list:'{self.ignoreprefix}'" print("\n"+message) print("\n"+message,file=sys.stderr) DataIssue.objects.create(parser='survex', message=message, url=get_offending_filename(headpath)) print(f' # datastack in LoadSurvexFile:{includelabel} type:', end="",file=sys.stderr) for dict in self.datastack: - print(f'{dict["type"].upper()} ', end="",file=sys.stderr) + print(f'<{dict["type"].upper()} >', end="",file=sys.stderr) def LoadSurvexFile(self, svxid): """Creates SurvexFile in the database, and SurvexDirectory if needed with links to 'cave' Creates a new current survexfile and valid .survexdirectory + Inspects the parent folder of the survexfile and uses that to decide if this is a cave we know The survexblock passed-in is not necessarily the parent. FIX THIS. """ if debugprint: -- cgit v1.2.3