xle/troggle-unchained
2
0
Fork 0
forked from expo/troggle
Code Issues 4 Pull Requests Projects 1 Wiki Activity

replace assert() with message logging

Browse Source
This commit is contained in:
Philip Sargent
2021-04-13 22:27:01 +01:00
parent 2467065ac3
commit daf58e9e45
8 changed files with 43 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
parsers/logbooks.py
View File

@@ -35,7 +35,6 @@ def GetTripPersons(trippeople, expedition, logtime_underground):
if mul:
tripperson = mul.group(1).strip()
if tripperson and tripperson[0] != '*':
#assert tripperson in personyearmap, "'%s' << %s\n\n %s" % (tripperson, trippeople, personyearmap)
tripperson = re.sub(round_bracket_regex, "", tripperson).strip()
personyear = GetPersonExpeditionNameLookup(expedition).get(tripperson.lower())
if not personyear:
@@ -160,7 +159,6 @@ def Parselogwikitxt(year, expedition, txt):
for triphead, triptext in trippara:
logbook_entry_count += 1
tripheadp = triphead.split("|")
# assert len(tripheadp) == 3, (tripheadp, triptext)
if not (len(tripheadp) == 3):
message = " ! - Bad no of items in tripdate in logbook: " + tripdate + " - " + tripheadp
DataIssue.objects.create(parser='logbooks', message=message)
@@ -169,6 +167,12 @@ def Parselogwikitxt(year, expedition, txt):
tripdate, tripplace, trippeople = tripheadp
tripsplace = tripplace.split(" - ")
tripcave = tripsplace[0].strip()
if len(tripsplace) == 1:
tripsplace = tripsplace[0]
else:
tripsplace = tripsplace[1]
print(f"! LOGBOOK {year} {logbook_entry_count:2} {len(triptext):4} '{tripsplace}'")
tul = re.findall(r"T/?U:?\s*(\d+(?:\.\d*)?|unknown)\s*(hrs|hours)?", triptext)
if tul:
@@ -193,7 +197,7 @@ def Parselogwikitxt(year, expedition, txt):
def EnterLogIntoObjStore(year, date, tripcave, triptitle, text, trippeople, tu, formattype, tripid1, seq):
# This will need additional functions to replicate the persontrip calculation and storage. For the
# moment we leave all that to be done in the django db
global trips # should be a singleton class object in models.py eventually
global trips # should be a singleton TROG eventually
global logdataissues
if tripid1 is None or tripid1 =="":
@@ -354,7 +358,6 @@ def Parseloghtml03(year, expedition, txt):
logbook_entry_count += 1
s = re.match(r"(?s)\s*<p>(.*?)</p>(.*)$", trippara)
#assert s, trippara
if not ( s ) :
message = " ! - Skipping logentry on failure to parse Parseloghtml03: {} {} {}...".format(tripentry,s,trippara[:300])
DataIssue.objects.create(parser='logbooks', message=message)

12
parsers/survex.py
View File

@@ -213,7 +213,11 @@ class LoadingSurvex():
expo = self.expos[year]
else:
expeditions = Expedition.objects.filter(year=year)
assert len(expeditions) == 1
if len(expeditions) != 1 :
message = f"! More than one expedition in year {year} '{line}' ({survexblock}) {survexblock.survexfile.path}"
print((self.insp+message))
DataIssue.objects.create(parser='survexunits', message=message)
expo= expeditions[0]
self.expos[year]= expo
@@ -411,7 +415,11 @@ class LoadingSurvex():
letterx = "X"
if len(wallet)<2:
wallet = "0" + wallet
assert (int(yr)>1960 and int(yr)<2039), "Wallet year out of bounds: %s" % yr
if not (int(yr)>1960 and int(yr)<2039):
message = " ! Wallet year out of bounds {yr} '{refscan}' {survexblock.survexfile.path}"
print((self.insp+message))
DataIssue.objects.create(parser='survex', message=message)
refscan = "%s#%s%s" % (yr, letterx, wallet)
try:
if int(wallet)>100:

31
parsers/surveys.py
View File

@@ -1,7 +1,6 @@
import sys
import os
import types
import logging
import stat
import csv
import re
@@ -46,13 +45,16 @@ def listdir(*directories):
def GetListDir(sdir):
res = [ ]
if sdir[:7] == "http://":
assert False, "Not written"
s = urllib.request.urlopen(sdir)
else:
for f in os.listdir(sdir):
if f[0] != ".":
ff = os.path.join(sdir, f)
res.append((f, ff, os.path.isdir(ff)))
# s = urllib.request.urlopen(sdir)
message = f"! Requesting loading from http:// NOT IMPLEMENTED. [{sdir}]"
print(message)
DataIssue.objects.create(parser='Drawings', message=message)
sdir[:7] = ""
for f in os.listdir(sdir):
if f[0] != ".":
ff = os.path.join(sdir, f)
res.append((f, ff, os.path.isdir(ff)))
return res
@@ -67,7 +69,6 @@ def LoadListScansFile(scansfolder):
c=0
for (fyf, ffyf, fisdiryf) in gld:
#assert not fisdiryf, ffyf
if re.search(r"\.(?:png|jpg|jpeg|pdf|svg|gif)(?i)$", fyf):
singlescan = SingleScan(ffile=ffyf, name=fyf, scansfolder=scansfolder)
singlescan.save()
@@ -106,7 +107,6 @@ def LoadListScans():
print("%s" % f, end=' ')
for fy, ffy, fisdiry in GetListDir(ff):
if fisdiry:
assert fisdiry, ffy
scansfolder = ScansFolder(fpath=ffy, walletname=fy)
scansfolder.save()
LoadListScansFile(scansfolder)
@@ -120,20 +120,25 @@ def LoadListScans():
def find_tunnel_scan(tunnelfile, path):
'''Is given a line of text 'path' which may or may not contain a recognisable name of a scanned file
which we have already seen when we imported all the files we could find in teh surveyscans direstories
which we have already seen when we imported all the files we could find in the surveyscans direstories
'''
scansfolder, scansfile = None, None
mscansdir = re.search(r"(\d\d\d\d#X?\d+\w?|1995-96kh|92-94Surveybookkh|1991surveybook|smkhs)/(.*?(?:png|jpg|pdf|jpeg))$", path)
if mscansdir:
scansfolderl = ScansFolder.objects.filter(walletname=mscansdir.group(1))
# This should properly detect if a list of folders is returned and do something sensible, not just pick the first.
if len(scansfolderl):
assert len(scansfolderl) == 1
scansfolder = scansfolderl[0]
if len(scansfolderl) > 1:
message = "! More than one scan FOLDER matches filter query. [{}]: {} {} {} {}".format(scansfilel[0], mscansdir.group(1), mscansdir.group(2), tunnelfile.tunnelpath, path)
print(message)
DataIssue.objects.create(parser='Tunnel', message=message)
if scansfolder:
scansfilel = scansfolder.singlescan_set.filter(name=mscansdir.group(2))
if len(scansfilel):
if len(scansfilel) > 1:
message = "! More than one image filename matches filter query. [{}]: {} {} {} {}".format(scansfilel[0], mscansdir.group(1), mscansdir.group(2), tunnelfile.tunnelpath, path)
message = "! More than one image FILENAME matches filter query. [{}]: {} {} {} {}".format(scansfilel[0], mscansdir.group(1), mscansdir.group(2), tunnelfile.tunnelpath, path)
print(message)
DataIssue.objects.create(parser='Tunnel', message=message)
scansfile = scansfilel[0]