1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
|
import copy
import os
import re
import subprocess
import sys
import time
from datetime import datetime, timezone
from pathlib import Path
import troggle.settings as settings
from troggle.core.models.caves import QM, Cave, Entrance
from troggle.core.models.survex import SurvexBlock, SurvexDirectory, SurvexFile, SurvexPersonRole, SurvexStation, Wallet
from troggle.core.models.troggle import DataIssue, Expedition
from troggle.core.utils import chaosmonkey, get_process_memory
from troggle.parsers.logbooks import GetCaveLookup
from troggle.parsers.people import GetPersonExpeditionNameLookup, known_foreigner
"""Imports the tree of survex files following from a defined root .svx file
It also scans the Loser repo for all the svx files, which it loads individually afterwards.
"""
todo = """
- LoadSurvexFile() Creates a new current survexfile and valid .survexdirectory
The survexblock passed-in is not necessarily the parent. FIX THIS.
- When Olly implements LEG in the 'dump3d --legs' utility, then we can use that to get the length of
all the legs in a survex block instead of adding them up oursleves. Which means that we can
ignore all the Units and offset stuff, that troggle will work with survex files with backsights,
repeated readings from distox etc.. Not actually useful for pre 2022 survey data, but good future-proofing.
Also it will be a tiny bit more accurate as these leg lengths are after loop closure fixup.
"""
survexblockroot = None
survexomitsroot = None
ROOTBLOCK = "rootblock"
OMITBLOCK = "omitblock"
METRESINFEET = 3.28084
stop_dup_warning = False
debugprint = False # Turns on debug printout for just one *include file
debugprinttrigger = "!"
dataissues = []
def stash_data_issue(parser=None, message=None, url=None, sb=None):
"""Avoid hitting the database for error messages until the end of the import"""
global dataissues
dataissues.append((parser, message, url, sb))
def store_data_issues():
"""Take the stash and store it permanently in the database instead"""
global dataissues
print(f" - Storing {len(dataissues)} Data Issues into database")
for issue in dataissues:
parser, message, url, sb = issue
if url is None:
if sb is not None:
url = get_offending_filename(sb)
DataIssue.objects.create(parser=parser, message=message, url=url)
dataissues = [] # in database now, so empty cache
class MapLocations(object):
"""Class used only for identifying the entrance locations"""
p = [
("laser.0_7", "BNase", "Reference", "Bräuning Nase laser point"),
("226-96", "BZkn", "Reference", "Bräuning Zinken trig point"),
("vd1", "VD1", "Reference", "VD1 survey point"),
("laser.kt114_96", "HSK", "Reference", "Hinterer Schwarzmooskogel trig point"),
("2000", "Nipple", "Reference", "Nipple (Weiße Warze)"),
("3000", "VSK", "Reference", "Vorderer Schwarzmooskogel summit"),
("topcamp", "OTC", "Reference", "Old Top Camp"),
("laser.0", "LSR0", "Reference", "Laser Point 0"),
("laser.0_1", "LSR1", "Reference", "Laser Point 0/1"),
("laser.0_3", "LSR3", "Reference", "Laser Point 0/3"),
("laser.0_5", "LSR5", "Reference", "Laser Point 0/5"),
("225-96", "BAlm", "Reference", "Bräuning Alm trig point"),
]
def points(self):
for ent in Entrance.objects.all():
if ent.best_station():
# print(f"{ent.filename}", end=", ")
try:
k = ent.caveandentrance_set.all()[0].cave
except:
message = f" ! Failed to get Cave linked to Entrance:{ent.name} from:{ent.filename} best:{ent.best_station()} {ent.caveandentrance_set.all()}"
stash_data_issue(parser="entrances", message=message)
print(message)
continue # skip this entrance
try:
areaName = k.getArea().short_name
except:
message = f" ! Failed to get Area on cave '{k}' linked to Entrance:{ent.name} from:{ent.filename} best:{ent.best_station()}"
stash_data_issue(parser="entrances", message=message)
print(message)
raise
self.p.append((ent.best_station(), f"{areaName}-{str(ent)[5:]}", ent.needs_surface_work(), str(ent)))
message = f" - {len(self.p)} entrances linked to caves."
print(message)
return self.p
def __str__(self):
return f"{len(self.p)} map locations"
class SurvexLeg:
"""No longer a models.Model subclass, so no longer a database table"""
tape = 0.0
compass = 0.0
clino = 0.0
def get_offending_filename(path):
"""Used to provide the URL for a line in the DataErrors page
which reports problems on importing data into troggle
"""
return "/survexfile/" + path + ".svx"
trip_people_cache = {}
def get_team_on_trip(survexblock):
"""Uses a cache to avoid a database query if it doesn't need to.
Only used for complete team."""
global trip_people_cache
if survexblock in trip_people_cache:
return trip_people_cache[survexblock]
qpeople = SurvexPersonRole.objects.filter(survexblock=survexblock)
trip_people_cache[survexblock] = qpeople # this is a query list
return qpeople
def get_people_on_trip(survexblock):
"""Gets the displayable names of the people on a survexbock trip.
Only used for complete team."""
qpeople = get_team_on_trip(survexblock)
people = []
for p in qpeople:
people.append(f"{p.personname}")
return list(set(people))
trip_person_cache = {}
def put_person_on_trip(survexblock, personexpedition, tm):
"""Uses a cache to avoid a database query if it doesn't need to.
Only used for a single person"""
global trip_person_cache
if (survexblock, personexpedition) in trip_person_cache:
return True
try:
personrole = SurvexPersonRole.objects.create(
survexblock=survexblock, person = personexpedition.person,
expeditionday = survexblock.expeditionday, personexpedition=personexpedition,
personname=tm
)
except:
message = f"! *team '{tm}' FAIL, already created {survexblock.survexfile.path} ({survexblock}) "
print(self.insp + message)
stash_data_issue(
parser="survex", message=message, url=None, sb=(survexblock.survexfile.path)
)
trip_person_cache[(survexblock, personexpedition)] = 1
return False
person_pending_cache = {}
def add_to_pending(survexblock, tm):
global person_pending_cache
if survexblock not in person_pending_cache:
person_pending_cache[survexblock] = set()
person_pending_cache[survexblock].add(tm)
# personexpedition = None
# personrole, created = SurvexPersonRole.objects.update_or_create(
# survexblock=survexblock, personexpedition=personexpedition, personname=tm)
# personrole.save()
def get_team_pending(survexblock):
"""A set of *team names before we get to the *date line in a survexblock"""
global person_pending_cache
if survexblock in person_pending_cache:
teamnames = person_pending_cache[survexblock] # a set of names
person_pending_cache[survexblock] = ()
return teamnames
return
class LoadingSurvex:
"""A 'survex block' is a *begin...*end set of cave data.
A survex file can contain many begin-end blocks, which can be nested, and which can *include
other survex files.
A 'scanswallet' is what we today call a "survey scans folder" or a "wallet".
"""
# python regex flags (?i) means case-insentitive, (?s) means . matches newline too
# see https://docs.python.org/3/library/re.html
rx_begin = re.compile(r"(?i)begin")
rx_end = re.compile(r"(?i)end$")
rx_title = re.compile(r"(?i)title$")
rx_ref = re.compile(r"(?i)ref$")
rx_data = re.compile(r"(?i)data$")
rx_flags = re.compile(r"(?i)flags$")
rx_alias = re.compile(r"(?i)alias$")
rx_entrance = re.compile(r"(?i)entrance$")
rx_date = re.compile(r"(?i)date$")
rx_units = re.compile(r"(?i)units$")
rx_team = re.compile(r"(?i)team$")
rx_set = re.compile(r"(?i)set$")
rx_names = re.compile(r"(?i)names")
rx_flagsnot = re.compile(r"not\s")
rx_linelen = re.compile(r"[\d\-+.]+$")
instruments = "(bitch|bodger|bolt|bolter|bolting|book|clino|comp|compass|consultant|disto|distox|distox2|dog|dogsbody|drawing|drill|gps|helper|inst|instr|instrument|monkey|nagging|nail|nail_polish|nail_polish_bitch|nail_polish_monkey|nail_varnish|nail_varnish_bitch|note|paint|photo|pic|point|polish|powerdrill|rig|rigger|rigging|sketch|slacker|something|tape|topodroid|unknown|useless|varnish|waiting_patiently)"
rx_teammem = re.compile(r"(?i)" + instruments + "?(?:es|s)?\s+(.*)$")
rx_teamold = re.compile(r"(?i)(.*)\s+" + instruments + "?(?:es|s)?$")
rx_teamabs = re.compile(r"(?i)^\s*(" + instruments + ")?(?:es|s)?\s*$")
rx_person = re.compile(r"(?i) and |/| / |, | , |&| & | \+ |^both$|^none$")
rx_qm = re.compile(
r"(?i)^\s*QM(\d+)\s+?([a-dA-DxX])\s+([\w\-\_]+)\.([\w\.\-]+)\s+(([\w\-]+)\.([\w\.\-]+)|\-)\s+(.+)$"
)
# does not recognise non numeric suffix survey point ids
rx_qm0 = re.compile(r"(?i)^\s*QM(\d+)\s+(.+)$")
rx_qm_tick = re.compile(r"(?i)^\s*QM(\d+)\s+TICK\s([\d\-]+)\s(.*)$")
# remember there is also QM_PATTERN used in views.other and set in settings.py
rx_tapelng = re.compile(r"(?i).*(tape|length).*$")
rx_cave = re.compile(r"(?i)caves-(\d\d\d\d)/([-\d\w]+|\d\d\d\d-?\w+-\d+)")
rx_comment = re.compile(r"([^;]*?)\s*(?:;\s*(.*))?\n?$")
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_include = re.compile(r"(?i)^\s*(\*include[\s].*)$")
rx_include2 = re.compile("(?i)include$")
rx_commref = re.compile(r"(?i)^\s*ref(?:erence)?[\s.:]*(\d+)\s*#\s*(X)?\s*(\d+)")
rx_ref_text = re.compile(r'(?i)^\s*\"[^"]*\"\s*$')
rx_star = re.compile(r"(?i)\s*\*[\s,]*(\w+)\s*(.*?)\s*(?:;.*)?$")
rx_starref = re.compile(r"(?i)^\s*\*ref[\s.:]*((?:19[6789]\d)|(?:20[0123]\d))\s*#?\s*(X)?\s*(.*?\d+.*?)$")
rx_argsref = re.compile(r"(?i)^[\s.:]*((?:19[6789]\d)|(?:20[012345]\d))\s*#?\s*(X)?\s*(.*?\d+.*?)$")
rx_badmerge = re.compile(r"(?i).*(\>\>\>\>\>)|(\=\=\=\=\=)|(\<\<\<\<\<).*$")
rx_ref2 = re.compile(r"(?i)\s*ref[.;]?")
rx_commteam = re.compile(r"(?i)\s*(Messteam|Zeichner)\s*[:]?(.*)")
rx_quotedtitle = re.compile(r'(?i)^"(.*)"$')
# This interprets the survex "*data normal" command which sets out the order of the fields in the data, e.g.
# *DATA normal from to length gradient bearing ignore ignore ignore ignore
datastardefault = {"type": "normal", "from": 0, "to": 1, "tape": 2, "compass": 3, "clino": 4}
flagsdefault = {"duplicate": False, "surface": False, "splay": False, "skiplegs": False, "splayalias": False}
datastar = {}
flagsstar = {}
units = "metres"
unitsfactor = None
slength = 0.0
legsnumber = 0
depthbegin = 0
depthinclude = 0
unitsstack = []
legsnumberstack = []
slengthstack = []
personexpedstack = []
stackbegin = []
flagsstack = []
datastack = []
includestack = []
stacksvxfiles = []
svxfileslist = []
svxdirs = {}
uniquename = {}
expos = {}
survexdict = {} # each key is a directory, and its value is a list of files
lineno = 0
insp = ""
callcount = 0
caverncount = 0
ignoreprefix = ["surface", "kataster", "fixedpts", "gpx"]
ignorenoncave = [
"caves-1623",
"caves-1623/2007-NEU",
"caves-1626",
"caves-1624",
"caves-1627",
"fixedpts/gps/gps00raw",
"",
]
includedfilename = ""
currentsurvexblock = None
currentsurvexfile = None
currentcave = None
caverndate = None
currentpersonexped = []
pending = []
def __init__(self):
self.caveslist = GetCaveLookup()
pass
def LoadSurvexFallThrough(self, survexblock, line, cmd):
if cmd == "require":
pass # should we check survex version available for processing?
elif cmd in ["equate", "fix", "calibrate", "cs", "export", "case", "declination", "infer", "instrument", "sd"]:
pass # we ignore all these, which is fine.
else:
if cmd in ["include", "data", "flags", "title", "entrance", "set", "units", "alias", "ref"]:
message = (
f"! Warning. Unparsed [*{cmd}]: '{line}' {survexblock.survexfile.path} - not an error (probably)"
)
print(self.insp + message)
stash_data_issue(
parser="survex", message=message, url=None, sb=(survexblock.survexfile.path)
)
else:
message = (
f"! Bad unrecognised svx command: [*{cmd}] {line} ({survexblock}) {survexblock.survexfile.path}"
)
print(self.insp + message)
stash_data_issue(
parser="survex", message=message, url=None, sb=(survexblock.survexfile.path)
)
def LoadSurvexTeam(self, survexblock, line):
"""Interpeting the *team fields means interpreting older style survex as well as current survex standard,
*team Insts Anthony Day - this is how most of our files specify the team member
*team "Anthony Day" notes pictures tape - this is how the survex documentation says it should be done
We have a huge variety of abbreviations and mispellings. The most laconic being
*team gb, bl
personrole is used to record that a person was on a survex trip, NOT the role they played.
(NB PersonTrip is a logbook thing, not a survex thing. )
"""
def record_team_member(tm, survexblock):
tm = tm.strip("\"'").strip()
# Refactor. The dict GetPersonExpeditionNameLookup(expo) indexes by name and has values of personexpedition
# This is convoluted, the whole personexpedition concept is unnecessary.
# we need the current expedition, but if there has been no date yet in the survex file, we don't know which one it is.
# so we can't validate whether the person was on expo or not.
# we will have to attach them to the survexblock anyway, and then do a
# later check on whether they are valid when we get the date.
# We have hundreds of updated Django database updates when the same person is
# on the same trip in multiple roles. We should de-duplicate these ourselves in Python
# instead of using SurvexPersonRole.objects.update_or_create() which is expensive.
expo = survexblock.expedition # may be None if no *date yet
if expo:
if not survexblock.expeditionday: # *date has been set
# should not happen
message = f"! *team {expo.year} expo ok, expedition day NOT in *team {survexblock.survexfile.path} ({survexblock}) "
print(self.insp + message)
stash_data_issue(
parser="survex", message=message, url=None, sb=(survexblock.survexfile.path)
)
personexpedition = GetPersonExpeditionNameLookup(expo).get(tm.lower())
if personexpedition:
put_person_on_trip(survexblock, personexpedition, tm)
self.currentpersonexped.append(personexpedition) # used in push/pop block code
elif known_foreigner(tm): # note, not using .lower()
message = f"- *team {expo.year} '{tm}' known foreigner on *team {survexblock.survexfile.path} ({survexblock}) in '{line}'"
print(self.insp + message)
# stash_data_issue(parser='survex', message=message, url=None, sb=(survexblock.survexfile.path))
else:
# we know the date and expo, but can't find the person
message = f"! *team {expo.year} '{tm}' FAIL personexpedition lookup on *team {survexblock.survexfile.path} ({survexblock}) in '{line}'"
print(self.insp + message)
stash_data_issue(
parser="survex", message=message, url=None, sb=(survexblock.survexfile.path)
)
else:
add_to_pending(survexblock, tm)
# don't know the date yet, so cannot query the table about validity.
# assume the person is valid. It will get picked up with the *date appears
# There are hundreds of these..
message = (
f"- Team/Date mis-ordered: {line} ({survexblock}) {survexblock.survexfile.path}"
)
print(self.insp + message)
# stash_data_issue(
# parser="survex team", message=message, url=None, sb=(survexblock.survexfile.path)
# )
mteammember = self.rx_teammem.match(line) # matches the role at the beginning
if not mteammember:
moldstyle = self.rx_teamold.match(line) # matches the role at the the end of the string
if moldstyle:
for tm in self.rx_person.split(moldstyle.group(1)):
if tm:
record_team_member(tm, survexblock)
# seems to be working
# msg = "! OLD tm='{}' line: '{}' ({}) {}".format(tm, line, survexblock, survexblock.survexfile.path)
# print(msg, file=sys.stderr)
else:
message = f"! *team {survexblock.survexfile.path} ({survexblock}) Weird '{mteammember.group(1)}' oldstyle line: '{line}'"
print(self.insp + message)
stash_data_issue(
parser="survex", message=message, url=None, sb=(survexblock.survexfile.path)
)
else:
nullmember = self.rx_teamabs.match(line) # matches empty role line. Ignore these.
if not nullmember:
message = f"! *team {survexblock.survexfile.path} ({survexblock}) Bad line: '{line}'"
print(self.insp + message)
stash_data_issue(
parser="survex", message=message, url=None, sb=(survexblock.survexfile.path)
)
else:
for tm in self.rx_person.split(mteammember.group(2)):
if tm:
record_team_member(tm, survexblock)
else:
if mteammember.group(2).lower() not in ("none", "both"):
message = f"! Weird *team '{mteammember.group(2)}' newstyle line: '{line}' ({survexblock}) {survexblock.survexfile.path}"
print(self.insp + message)
stash_data_issue(
parser="survex", message=message, url=None, sb=(survexblock.survexfile.path)
)
def LoadSurvexEntrance(self, survexblock, line):
# Not using this yet
pass
def LoadSurvexAlias(self, survexblock, line):
# *alias station - ..
splayalias = re.match("(?i)station\s*\-\s*\.\.\s*$", line)
if splayalias:
self.flagsstar["splayalias"] = True
else:
message = f"! Bad *ALIAS: '{line}' ({survexblock}) {survexblock.survexfile.path}"
print(self.insp + message)
stash_data_issue(parser="survex", message=message)
def LoadSurvexUnits(self, survexblock, line):
# all for 4 survex files with measurements in feet. bugger.
# Won't need this once we move to using cavern or d3dump output for lengths
tapeunits = self.rx_tapelng.match(line) # tape|length
if not tapeunits:
return
convert = re.match("(?i)(\w*)\s*([\.\d]+)\s*(\w*)", line)
if convert:
factor = convert.groups()[1]
self.unitsfactor = float(factor)
if debugprint:
message = (
f"! *UNITS NUMERICAL conversion [{factor}x] '{line}' ({survexblock}) {survexblock.survexfile.path}"
)
print(self.insp + message)
stash_data_issue(parser="survexunits", message=message)
feet = re.match("(?i).*feet$", line)
metres = re.match("(?i).*(METRIC|METRES|METERS)$", line)
if feet:
self.units = "feet"
elif metres:
self.units = "metres"
else:
message = f"! *UNITS in YARDS!? - not converted '{line}' ({survexblock}) {survexblock.survexfile.path}"
print(self.insp + message)
stash_data_issue(parser="survexunits", message=message)
def get_expo_from_year(self, year):
# cacheing to save DB query on every block
if year in self.expos:
expo = self.expos[year]
else:
expeditions = Expedition.objects.filter(year=year)
if len(expeditions) != 1:
message = (
f"! More than one expedition in year {year} '{line}' ({survexblock}) {survexblock.survexfile.path}"
)
print(self.insp + message)
stash_data_issue(
parser="survex", message=message, url=None, sb=(survexblock.survexfile.path)
)
expo = expeditions[0]
self.expos[year] = expo
return expo
def LoadSurvexDate(self, survexblock, line):
"""We now have a valid date for this survexblock, so we now know the expo
it relates to and can use GetPersonExpeditionNameLookup(expo) to check whether
the people are correct.
Note that a *team line can come before AND after a *date line"""
def setdate_on_survexblock(year):
"""Either *date comes before any *team, in which case there are no prior
PersonRoles attached, or
*team came before this *date, in which case the names are only in 'pending'"""
global trip_person_cache
expo = self.get_expo_from_year(year)
survexblock.expedition = expo
survexblock.expeditionday = expo.get_expedition_day(survexblock.date)
survexblock.save()
team = get_team_on_trip(survexblock) # should be empty, should only be in 'pending'
# team = SurvexPersonRole.objects.filter(survexblock=survexblock)
if len(team) > 0:
message = f"! *team {expo.year} Multiple *date in one block? Already someone on team when *date seen. {survexblock.survexfile.path} ({survexblock}) in '{line}'"
print(self.insp + message)
stash_data_issue(parser='survex', message=message, url=None, sb=(survexblock.survexfile.path))
if teamnames := get_team_pending(survexblock): # WALRUS https://docs.python.org/3/whatsnew/3.8.html#assignment-expressions
for tm in teamnames:
if known_foreigner(tm):
message = f"- *team {expo.year} '{tm}' known foreigner *date (misordered) {survexblock.survexfile.path} ({survexblock}) in '{line}'"
print(self.insp + message)
# stash_data_issue(parser='survex', message=message, url=None, sb=(survexblock.survexfile.path))
else:
pe = GetPersonExpeditionNameLookup(expo).get(tm.lower())
if pe:
put_person_on_trip(survexblock, pe, tm)
self.currentpersonexped.append(pe)
else:
message = f"! *team {year} '{tm}' FAIL personexpedition lookup on *date {survexblock.survexfile.path} ({survexblock}) "
print(self.insp + message)
stash_data_issue(
parser="survex",
message=message,
url=None, sb=(survexblock.survexfile.path),
)
# All this next section should not happen unless there are >1 *date lines in a block
for pr in team: # pr is a PersonRole object
if not pr.expeditionday: # *date and *team in 'wrong' order.
pr.expeditionday = survexblock.expeditionday
pr.save()
if not pr.personexpedition:
pe = GetPersonExpeditionNameLookup(expo).get(pr.personname.lower())
if pe: # pe is a PersonExpedition
# message = "! {} ({}) Fixing undated personexpedition '{}'".format(survexblock.survexfile.path, survexblock, p.personname)
# print(self.insp+message)
# stash_data_issue(parser='survex', message=message)
pr.personexpedition = pe
pr.person = pr.personexpedition.person
pr.save()
self.currentpersonexped.append(pe) # used in push/pop block code
elif known_foreigner(pr.personname): # note, not using .lower()
message = f"- *team {expo.year} '{pr.personname}' known foreigner on *date {survexblock.survexfile.path} ({survexblock}) in '{line}'"
print(self.insp + message)
# stash_data_issue(parser='survex', message=message, url=None, sb=(survexblock.survexfile.path))
else:
message = f"! *team {year} '{pr.personname}' FAIL personexpedition lookup on *date {survexblock.survexfile.path} ({survexblock}) '{pr.personname}'"
print(self.insp + message)
stash_data_issue(
parser="survex",
message=message,
url=None, sb=(survexblock.survexfile.path),
)
oline = line
if len(line) > 10:
# message = "! DATE Warning LONG DATE '{}' ({}) {}".format(oline, survexblock, survexblock.survexfile.path)
# print(self.insp+message)
# stash_data_issue(parser='survex', message=message, url=None, sb=(survexblock.survexfile.path))
if line[10] == "-": # ie a range, just look at first date
line = line[0:10]
if len(line) == 10:
year = line[:4]
# TO DO set to correct Austrian timezone Europe/Vienna ?
# %m and %d need leading zeros. Source svx files require them.
survexblock.date = datetime.strptime(line.replace(".", "-"), "%Y-%m-%d")
elif len(line) == 7:
year = line[:4]
perps = get_people_on_trip(survexblock) # What, you don't know Judge Dredd slang ?
message = f"! DATE Warning only accurate to the month, setting to 1st '{oline}' ({survexblock}) {survexblock.survexfile.path} {perps}"
print(self.insp + message)
stash_data_issue(
parser="svxdate", message=message, url=None, sb=(survexblock.survexfile.path)
)
survexblock.date = datetime.strptime(line.replace(".", "-"), "%Y-%m") # sets to first of month
elif len(line) == 4:
year = line[:4]
perps = get_people_on_trip(survexblock)
message = f"! DATE WARNING only accurate to the YEAR, setting to 1st January '{oline}' ({survexblock}) {survexblock.survexfile.path} {perps}"
print(self.insp + message)
stash_data_issue(
parser="svxdate", message=message, url=None, sb=(survexblock.survexfile.path)
)
survexblock.date = datetime.strptime(line, "%Y") # sets to January 1st
else:
# these errors are reporting the wrong survexblock, which is actually a SurvexFile (!)
# see To Do notes on how to trigger this. Still needs investigating..
message = (
f"! DATE Error unrecognised '{oline}-{survexblock}' ({type(survexblock)}) {survexblock.survexfile.path}"
)
print(self.insp + message)
stash_data_issue(
parser="survex", message=message, url=None, sb=(survexblock.survexfile.path)
)
print(f" {type(survexblock)=}") # survexblock.parent fails as a SurvexFile has no .parent ...ugh.
print(f" {survexblock.survexpath=}")
print(f" {survexblock.survexfile=}")
# raise
setdate_on_survexblock(year)
def LoadSurvexLeg(self, survexblock, sline, comment, svxline):
"""This reads compass, clino and tape data but only keeps the tape lengths,
the rest is discarded after error-checking.
Now skipping the error checking - returns as soon as the leg is not one we count.
REPLACE ALL THIS by reading the .log output of cavern for the file.
But we need the lengths per Block, not by File. dump3d will do lengths per block.
"""
invalid_clino = 180.0
invalid_compass = 720.0
invalid_tape = 0.0
if self.flagsstar["skiplegs"]:
if debugprint:
print("skip in ", self.flagsstar, survexblock.survexfile.path)
return
if debugprint:
print(f"! LEG datastar type:{self.datastar['type'].upper()}++{survexblock.survexfile.path}\n{sline} ")
if self.datastar["type"] == "passage":
return
if self.datastar["type"] == "cartesian":
return
if self.datastar["type"] == "nosurvey":
return
if self.datastar["type"] == "diving":
return
if self.datastar["type"] == "cylpolar":
return
if debugprint:
print(
f" !! LEG data lineno:{self.lineno}\n !! sline:'{sline}'\n !! datastar['tape']: {self.datastar['tape']}"
)
if self.datastar["type"] != "normal":
return
ls = sline.lower().split()
# NORMAL, so there should be 5 fields
# from the content, this is clearly reading fixedpts/gps/gps00raw.svx, but not reporting it by that name
if len(ls) < 5:
print("! Fewer than 5 fields in NORMAL in ", survexblock.survexfile.path, survexfile, survexfile.parent)
print(" datastar NORMAL:", self.datastar)
print(f" Line (split): {ls}, comment: {comment}")
print(f" Line: {sline}\nsvxline: {svxline}")
message = f" ! Not 5 fields in line '{sline.lower()}' {self.datastar=} {ls=} in\n{survexblock}\n{survexblock.survexfile}\n{survexblock.survexfile.path}"
stash_data_issue(
parser="survexleg", message=message, url=None, sb=(survexblock.survexfile.path)
)
datastar = self.datastar # shallow copy: alias but the things inside are the same things
survexleg = SurvexLeg()
# skip all splay legs
try:
if ls[datastar["from"]] == ".." or ls[datastar["from"]] == ".":
if debugprint:
print("Splay in ", survexblock.survexfile.path)
return
if ls[datastar["to"]] == ".." or ls[datastar["to"]] == ".":
if debugprint:
print("Splay in ", survexblock.survexfile.path)
return
if self.flagsstar["splayalias"]:
if ls[datastar["from"]] == "-":
if debugprint:
print("Aliased splay in ", survexblock.survexfile.path)
return
if ls[datastar["to"]] == "-":
if debugprint:
print("Aliased splay in ", survexblock.survexfile.path)
return
except:
message = f" ! datastar parsing from/to incorrect in line {ls} in {survexblock.survexfile.path}"
print(self.insp + message)
stash_data_issue(
parser="survexleg", message=message, url=None, sb=(survexblock.survexfile.path)
)
return
try:
tape = ls[datastar["tape"]]
except:
message = f" ! datastar parsing incorrect in line {ls} in {survexblock.survexfile.path}"
print(self.insp + message)
stash_data_issue(
parser="survexleg", message=message, url=None, sb=(survexblock.survexfile.path)
)
survexleg.tape = invalid_tape
return
# e.g. '29/09' or '(06.05)' in the tape measurement
# tape = tape.replace("(","") # edited original file (only one) instead
# tape = tape.replace(")","") # edited original file (only one) instead
# tape = tape.replace("/",".") # edited original file (only one) instead.
try:
if self.unitsfactor:
tape = float(tape) * self.unitsfactor
if debugprint:
message = f" ! Units: Length scaled {tape}m '{ls}' in ({survexblock.survexfile.path}) units:{self.units} factor:{self.unitsfactor}x"
print(self.insp + message)
stash_data_issue(
parser="survexleg", message=message, url=None, sb=(survexblock.survexfile.path)
)
if self.units == "feet":
tape = float(tape) / METRESINFEET
if debugprint:
message = f" ! Units: converted to {tape:.3f}m from {self.units} '{ls}' in ({survexblock.survexfile.path})"
print(self.insp + message)
stash_data_issue(
parser="survexleg", message=message, url=None, sb=(survexblock.survexfile.path)
)
survexleg.tape = float(tape)
self.legsnumber += 1
except ValueError:
message = f" ! Value Error: Tape misread in line'{ls}' in {survexblock.survexfile.path} units:{self.units}"
print(self.insp + message)
stash_data_issue(
parser="survexleg", message=message, url=None, sb=(survexblock.survexfile.path)
)
survexleg.tape = invalid_tape
try:
survexblock.legslength += survexleg.tape
self.slength += survexleg.tape
except ValueError:
message = (
f" ! Value Error: Tape length not added '{ls}' in {survexblock.survexfile.path} units:{self.units}"
)
print(self.insp + message)
stash_data_issue(
parser="survexleg", message=message, url=None, sb=(survexblock.survexfile.path)
)
try:
lcompass = ls[datastar["compass"]]
except:
message = f" ! Value Error: Compass not found in line {ls} in {survexblock.survexfile.path}"
print(self.insp + message)
stash_data_issue(
parser="survexleg", message=message, url=None, sb=(survexblock.survexfile.path)
)
lcompass = invalid_compass
try:
lclino = ls[datastar["clino"]]
except:
print(("! Clino misread in", survexblock.survexfile.path))
print((" datastar:", datastar))
print((" Line:", ls))
message = f" ! Value Error: Clino misread in line '{sline.lower()}' {datastar=} {self.datastar=} {ls=} in\n{survexblock}\n{survexblock.survexfile}\n{survexblock.survexfile.path}"
stash_data_issue(
parser="survexleg", message=message, url=None, sb=(survexblock.survexfile.path)
)
lclino = invalid_clino
if lclino == "up":
survexleg.clino = 90.0
lcompass = invalid_compass
elif lclino == "down":
survexleg.clino = -90.0
lcompass = invalid_compass
elif lclino == "-" or lclino == "level":
survexleg.clino = -90.0
try:
survexleg.compass = float(lcompass)
except ValueError:
print(("! Compass misread in", survexblock.survexfile.path))
print((" datastar:", datastar))
print((" Line:", ls))
message = " ! Value Error: lcompass:'{}' line {} in '{}'".format(lcompass, ls, survexblock.survexfile.path)
stash_data_issue(
parser="survexleg", message=message, url=None, sb=(survexblock.survexfile.path)
)
survexleg.compass = invalid_compass
# delete the object to save memory
survexleg = None
def LoadSurvexRef(self, survexblock, args):
"""Interpret the *ref record, and all the many variants"""
# print(self.insp+ "*REF ---- '"+ args +"'")
url = get_offending_filename(survexblock.survexfile.path)
# *REF but also ; Ref years from 1960 to 2039
refline = self.rx_ref_text.match(args)
if refline:
# a textual reference such as "1996-1999 Not-KH survey book pp 92-95"
print(f"{self.insp} *REF quoted text so ignored:{args} in {survexblock.survexfile.path}")
return
if len(args) < 4:
message = f" ! Empty or BAD *REF statement '{args}' in '{survexblock.survexfile.path}'"
print(self.insp + message)
stash_data_issue(parser="survex", message=message, url=url)
return
argsgps = self.rx_argsref.match(args)
if argsgps:
yr, letterx, wallet = argsgps.groups()
else:
perps = get_people_on_trip(survexblock)
message = f" ! Wallet *REF bad in '{survexblock.survexfile.path}' malformed id '{args}' {perps}"
print(self.insp + message)
stash_data_issue(parser="survex", message=message, url=url)
return
if not letterx:
letterx = ""
else:
letterx = "X"
if len(wallet) < 2:
wallet = "0" + wallet
if not (int(yr) > 1960 and int(yr) < 2050):
message = " ! Wallet year out of bounds {yr} '{refscan}' {survexblock.survexfile.path}"
print(self.insp + message)
stash_data_issue(parser="survex", message=message, url=url)
refscan = f"{yr}#{letterx}{wallet}"
try:
if int(wallet) > 99:
message = f" ! Wallet *REF {refscan} - very big (more than 99) so probably wrong in '{survexblock.survexfile.path}'"
print(self.insp + message)
stash_data_issue(parser="survex", message=message, url=url)
except:
message = f" ! Wallet *REF {refscan} - not numeric in '{survexblock.survexfile.path}'"
print(self.insp + message)
stash_data_issue(parser="survex", message=message, url=url)
manywallets = Wallet.objects.filter(
walletname=refscan
) # assumes all wallets found in earlier pass of data import
if manywallets:
if len(manywallets) > 1:
message = f" ! Wallet *REF {refscan} - more than one found {len(manywallets)} wallets in db with same id {survexblock.survexfile.path}"
print(self.insp + message)
stash_data_issue(parser="survex", message=message, url=url)
if survexblock.scanswallet:
if survexblock.scanswallet.walletname != refscan:
message = f" ! Wallet *REF {refscan} in {survexblock.survexfile.path} - Already a DIFFERENT wallet is set for this block '{survexblock.scanswallet.walletname}'"
print(self.insp + message)
stash_data_issue(parser="survex", message=message, url=url)
else:
survexblock.scanswallet = manywallets[0] # this is a ForeignKey field
survexblock.save()
# This is where we should check that the wallet JSON contains a link to the survexfile
# and that the JSON date and walletdate are set correctly to the survexblock date.
else:
perps = get_people_on_trip(survexblock)
message = f" ! Wallet *REF bad in '{survexblock.survexfile.path}' '{refscan}' NOT in database i.e. wallet does not exist {perps}."
print(self.insp + message)
stash_data_issue(parser="survex", message=message, url=url)
def TickSurvexQM(self, survexblock, qmtick):
"""Interpret the specially formatted comment which is a QM TICKED statement"""
# Now we need to find the correct QM object. It will be in the same block and have the same number.
try:
qm = QM.objects.filter(block=survexblock, number=int(qmtick.group(1)))
except:
# raise
message = f' ! QM TICK find FAIL QM{qmtick.group(1)} date:"{qmtick.group(2)}" qmlist:"{qm}" in "{survexblock.survexfile.path}" + comment:"{qmtick.group(3)}" '
print(message)
stash_data_issue(
parser="survex", message=message, url=None, sb=(survexblock.survexfile.path)
)
if len(qm) > 1:
message = f' ! QM TICK MULTIPLE found FAIL QM{qmtick.group(1)} date:"{qmtick.group(2)}" in "{survexblock.survexfile.path}" + comment:"{qmtick.group(3)}" '
print(message)
stash_data_issue(
parser="survex", message=message, url=None, sb=(survexblock.survexfile.path)
)
qm[0].ticked = True
qm[0].save()
def LoadSurvexQM(self, survexblock, qmline):
"""Interpret the specially formatted comment which is a QM definition"""
insp = self.insp
qm_no = qmline.group(1) # this may not be unique across multiple survex files
qm_grade = qmline.group(2)
if qmline.group(3): # usual closest survey station
qm_nearest = qmline.group(3)
if qmline.group(4):
qm_nearest = qm_nearest + "." + qmline.group(4)
if qmline.group(6) and qmline.group(6) != "-":
qm_resolve_station = qmline.group(6)
if qmline.group(7):
qm_resolve_station = qm_resolve_station + "." + qmline.group(7)
else:
qm_resolve_station = ""
qm_notes = qmline.group(8)
# Spec of QM in SVX files:
# ;Serial number grade(A/B/C/D/X) nearest-station resolution-station description
# ;QM1 a hobnob_hallway_2.42 hobnob-hallway_3.42 junction of keyhole passage
# ;QM1 a hobnob_hallway_2.42 - junction of keyhole passage
# NB none of the SurveyStations are in the DB now, so if we want to link to aSurvexStation
# we would have to create one. But that is not obligatory and no QMs loaded from CSVs have one
# Older troggle/CSV assumes a logbook entry 'found_by' for each QM, with a date.
# We don't need this anymore so we don't need to create a placeholder logbook entry.
str(survexblock.date)[:4]
blockname = survexblock.name[:6] + survexblock.name[-1:]
# logslug = f'D{int(qmyear)}_{blockname}_{int(qm_no):03d}'
if survexblock.survexfile.cave:
survexblock.survexfile.cave.slug()
else:
pass
try:
qm = QM.objects.create(
number=qm_no,
# nearest_station=a_survex_station_object, # can be null
nearest_station_description=qm_resolve_station,
nearest_station_name=qm_nearest,
grade=qm_grade.upper(),
location_description=qm_notes,
block=survexblock, # only set for survex-imported QMs
blockname=blockname, # only set for survex-imported QMs
expoyear=str(survexblock.date.year),
cave=survexblock.survexfile.cave,
)
qm.save
except:
message = f" ! QM{qm_no} FAIL to create {qm_nearest} in'{survexblock.survexfile.path}'"
print(insp + message)
stash_data_issue(
parser="survex", message=message, url=None, sb=(survexblock.survexfile.path)
)
def LoadSurvexDataNormal(self, survexblock, args):
"""Sets the order for data elements in this and following blocks, e.g.
*data normal from to compass clino tape
*data normal from to tape compass clino
We are only collecting length data so we are disinterested in from, to, LRUD etc.
"""
# datastardefault = { # included here as reference to help understand the code
# "type":"normal",
# "t":"leg",
# "from":0,
# "to":1,
# "tape":2,
# "compass":3,
# "clino":4}
datastar = copy.deepcopy(self.datastardefault)
if args == "":
# naked '*data' which is relevant only for passages. Ignore. Continue with previous settings.
return
# DEFAULT | NORMAL | CARTESIAN| NOSURVEY |PASSAGE | TOPOFIL | CYLPOLAR | DIVING
ls = args.lower().split()
if ls[0] == "default":
self.datastar = copy.deepcopy(self.datastardefault)
elif ls[0] == "normal" or ls[0] == "topofil":
if not ("from" in datastar and "to" in datastar):
message = (
f" ! - Unrecognised *data normal statement '{args}' {survexblock.name}|{survexblock.survexpath}"
)
print(message)
print(message, file=sys.stderr)
stash_data_issue(
parser="survex", message=message, url=None, sb=(survexblock.survexfile.path)
)
return
else:
datastar = self.datastardefault
# ls = ["normal", "from", "to", "tape", "compass", "clino" ]
for i in range(1, len(ls)): # len[0] is "normal"
if ls[i].lower() == "newline":
message = f" ! - ABORT *data statement has NEWLINE in it in {survexblock.survexfile.path}. Not parsed by troggle. '{args}'"
print(message)
print(message, file=sys.stderr)
stash_data_issue(
parser="survex", message=message, url=None, sb=(survexblock.survexfile.path)
)
return False
if ls[i] in ["bearing", "compass"]:
datastar["compass"] = i - 1
if ls[i] in ["clino", "gradient"]:
datastar["clino"] = i - 1
if ls[i] in ["tape", "length"]:
datastar["tape"] = i - 1
self.datastar = copy.deepcopy(datastar)
return
elif ls[0] == "passage" or ls[0] == "nosurvey" or ls[0] == "diving" or ls[0] == "cylpolar":
# message = " ! - *data {} blocks ignored. {}|{}" '{}' .format(ls[0].upper(), survexblock.name, survexblock.survexpath, args)
# print(message)
# print(message,file=sys.stderr)
# stash_data_issue(parser='survex', message=message)
self.datastar["type"] = ls[0]
elif ls[0] == "cartesian": # We should not ignore this ?! Default for Germans ?
# message = " ! - *data {} blocks ignored. {}|{}" '{}' .format(ls[0].upper(), survexblock.name, survexblock.survexpath, args)
# print(message)
# print(message,file=sys.stderr)
# stash_data_issue(parser='survex', message=message)
self.datastar["type"] = ls[0]
else:
message = f" ! - Unrecognised *data statement '{args}' {survexblock.name}|{survexblock.survexpath}"
print(message)
print(message, file=sys.stderr)
stash_data_issue(
parser="survex", message=message, url=None, sb=(survexblock.survexfile.path)
)
self.datastar["type"] = ls[0]
def LoadSurvexFlags(self, args):
# Valid flags are DUPLICATE, SPLAY, and SURFACE, and a flag may be preceded with NOT to turn it off.
# Default values are NOT any of them
self.flagsstar = copy.deepcopy(self.flagsdefault)
flags = []
args = self.rx_flagsnot.sub("not", args)
argslist = args.split()
for s in argslist:
flags.append(s)
if debugprint:
print(
f" ^ flagslist:{flags}",
)
if "duplicate" in flags:
self.flagsstar["duplicate"] = True
if "surface" in flags:
self.flagsstar["surface"] = True
if "splay" in flags:
self.flagsstar["splay"] = True
if "notduplicate" in flags:
self.flagsstar["duplicate"] = False
if "notsurface" in flags:
self.flagsstar["surface"] = False
if "notsplay" in flags:
self.flagsstar["splay"] = False
# if self.flagsstar["duplicate"] == True or self.flagsstar["surface"] == True or self.flagsstar["splay"] == True:
# actually we do want to count duplicates as this is for "effort expended in surveying underground"
if self.flagsstar["surface"] is True or self.flagsstar["splay"] is True:
self.flagsstar["skiplegs"] = True
if debugprint:
print(
f" $ flagslist:{flags}",
)
def IdentifyCave(self, cavepath):
if cavepath.lower() in self.caveslist:
return self.caveslist[cavepath.lower()]
# 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 = f"{path_match.group(1)}-{path_match.group(2)}"
guesses = [sluggy.lower(), path_match.group(2).lower()]
for g in guesses:
if g in self.caveslist:
self.caveslist[cavepath] = self.caveslist[g]
return self.caveslist[g]
print(f" ! Failed to find cave for {cavepath.lower()}")
else:
# not a cave, but that is fine.
# print(f' ! No regex(standard identifier) cave match for {cavepath.lower()}')
return None
def GetSurvexDirectory(self, headpath):
"""This creates a SurvexDirectory if it has not been seen before, and on creation
it sets the primarysurvexfile. This is correct as it should be set on the first file
in the directory, where first is defined by the *include ordering. Which is what we
are doing.
"""
if not headpath:
return self.svxdirs[""]
if headpath.lower() not in self.svxdirs:
self.svxdirs[headpath.lower()] = SurvexDirectory(path=headpath, primarysurvexfile=self.currentsurvexfile)
self.svxdirs[headpath.lower()].save()
self.survexdict[self.svxdirs[headpath.lower()]] = [] # list of the files in the directory
return self.svxdirs[headpath.lower()]
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:
id = cid.strip().rstrip("\n").upper()
if cid.startswith("162"):
self.pending.add(id)
else:
self.pending.add("1623-" + id)
if headpath in self.ignorenoncave:
message = f" - {headpath} is <ignorenoncave> (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 <ignoreprefix> (while creating '{includelabel}' sfile & sdirectory)"
)
# print("\n"+message)
# print("\n"+message,file=sys.stderr)
return
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
id = caveid[5:]
if id in self.pending:
print(f"! ALREADY PENDING {id}", file=sys.stderr)
return
message = f" ! Warning: cave identifier '{caveid}'or {id} (guessed from file path) is not a known cave. Need to add to expoweb/cave_data/pending.txt ? In '{includelabel}.svx' at depth:[{len(depth)}]."
print("\n" + message)
print("\n" + message, file=sys.stderr)
print(f"{self.pending}", end="", file=sys.stderr)
stash_data_issue(parser="survex", message=message, url=None, sb=(includelabel))
# print(f' # datastack in LoadSurvexFile:{includelabel}', file=sys.stderr)
# for dict in self.datastack:
# print(f' type: <{dict["type"].upper()} >', 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:
print(f" # datastack in LoadSurvexFile:{svxid} 'type':", end="")
for dict in self.datastack:
print(f"'{dict['type'].upper()}' ", end="")
print("")
depth = " " * self.depthbegin
# print("{:2}{} - NEW survexfile:'{}'".format(self.depthbegin, depth, svxid))
headpath = os.path.dirname(svxid)
newfile = SurvexFile(path=svxid)
newfile.save() # until we do this there is no internal id so no foreign key works
self.currentsurvexfile = newfile
newdirectory = self.GetSurvexDirectory(headpath)
newdirectory.save()
newfile.survexdirectory = newdirectory
self.survexdict[newdirectory].append(newfile)
cave = self.IdentifyCave(headpath) # cave already exists in db
if not newdirectory:
message = f" ! 'None' SurvexDirectory returned from GetSurvexDirectory({headpath})"
print(message)
print(message, file=sys.stderr)
stash_data_issue(parser="survex", message=message, url=f"/survexfile/{svxid}")
if cave:
newdirectory.cave = cave
newfile.cave = cave
# 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)
if not newfile.survexdirectory:
message = f" ! SurvexDirectory NOT SET in new SurvexFile {svxid} "
print(message)
print(message, file=sys.stderr)
stash_data_issue(parser="survex", message=message)
self.currentsurvexfile.save() # django insists on this although it is already saved !?
try:
newdirectory.save()
except:
print(newdirectory, file=sys.stderr)
print(newdirectory.primarysurvexfile, file=sys.stderr)
raise
if debugprint:
print(f" # datastack end LoadSurvexFile:{svxid} 'type':", end="")
for dict in self.datastack:
print(f"'{dict['type'].upper()}' ", end="")
print("")
def ProcessIncludeLine(self, included):
global debugprint
svxid = included.groups()[0]
if svxid.lower() == debugprinttrigger.lower():
debugprint = True
self.LoadSurvexFile(svxid)
self.stacksvxfiles.append(self.currentsurvexfile)
def ProcessEdulcniLine(self, edulcni):
"""Saves the current survexfile in the db"""
global debugprint
svxid = edulcni.groups()[0]
if debugprint:
depth = " " * self.depthbegin
print(f"{self.depthbegin:2}{depth} - Edulcni survexfile:'{svxid}'")
if svxid.lower() == debugprinttrigger.lower():
debugprint = False
self.currentsurvexfile.save()
self.currentsurvexfile = self.stacksvxfiles.pop()
def LoadSurvexComment(self, survexblock, comment):
# ignore all comments except ;ref, ; wallet and ;QM and ;*include (for collated survex file)
# rx_ref2 = re.compile(r'(?i)\s*ref[.;]?')
# This should also check that the QM survey point rxists in the block
refline = self.rx_commref.match(comment)
if refline:
# comment = re.sub('(?i)\s*ref[.;]?',"",comment.strip())
comment = self.rx_ref2.sub("", comment.strip())
print(f"rx_ref2 -- {comment=} in {survexblock.survexfile.path} :: {survexblock}")
self.LoadSurvexRef(survexblock, comment)
# handle
# ; Messteam: Jörg Haussmann, Robert Eckardt, Thilo Müller
# ; Zeichner: Thilo Müller
# But none of these will be valid teammembers because they are not actually on our expo
team = self.rx_commteam.match(comment)
if team:
# print(f'rx_commteam -- {comment=} in {survexblock.survexfile.path} :: {survexblock}')
pass
qml = self.rx_qm0.match(comment)
if qml:
qmline = self.rx_qm.match(comment)
if qmline:
self.LoadSurvexQM(survexblock, qmline)
else:
qmtick = self.rx_qm_tick.match(comment)
if qmtick:
self.TickSurvexQM(survexblock, qmtick)
else:
message = f' ! QM Unrecognised as valid in "{survexblock.survexfile.path}" QM{qml.group(1)} "{qml.group(2)}" : regex failure, typo?'
print(message)
stash_data_issue(
parser="survex", message=message, url=None, sb=(survexblock.survexfile.path)
)
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)
edulcni = self.rx_commcni.match(comment)
# ;*edulcni means we are returning from an included file
if edulcni:
self.ProcessEdulcniLine(edulcni)
def LoadSurvexSetup(self, survexblock, survexfile):
self.depthbegin = 0
self.datastar = self.datastardefault
print(
self.insp
+ f" - MEM:{get_process_memory():.3f} Reading. parent:{survexblock.survexfile.path} <> {survexfile.path} "
)
self.lineno = 0
sys.stderr.flush()
self.callcount += 1
if self.callcount % 10 == 0:
print(".", file=sys.stderr, end="")
if self.callcount % 500 == 0:
print("\n", file=sys.stderr, end="")
# 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+)/", survexblock.survexfile.path)
if path_match:
pos_cave = f"{path_match.group(1)}-{path_match.group(2)}"
cave = getCaveByReference(pos_cave)
if cave:
survexfile.cave = cave
def LinearLoad(self, survexblock, path, collatefilename):
"""Loads a single survex file. Usually used to import all the survex files which have been collated
into a single file. Loads the begin/end blocks using a stack for labels.
Uses the python generator idiom to avoid loading the whole file (21MB) into memory.
"""
blkid = None
pathlist = None
args = None
oldflags = None
blockcount = 0
self.lineno = 0
slengthtotal = 0.0
nlegstotal = 0
self.relativefilename = path
self.IdentifyCave(path) # this will produce null for survex files which are geographic collections
self.currentsurvexfile = survexblock.survexfile
self.currentsurvexfile.save() # django insists on this although it is already saved !?
self.datastar = copy.deepcopy(self.datastardefault)
self.flagsstar = copy.deepcopy(self.flagsdefault)
def tickle():
nonlocal blockcount
blockcount += 1
if blockcount % 20 == 0:
print(".", file=sys.stderr, end="")
if blockcount % 800 == 0:
print("\n", file=sys.stderr, end="")
mem = get_process_memory()
print(f" - MEM: {mem:7.2f} MB in use", file=sys.stderr)
print(" ", file=sys.stderr, end="")
sys.stderr.flush()
def printbegin():
nonlocal blkid
nonlocal pathlist
depth = " " * self.depthbegin
self.insp = depth
if debugprint:
print(f"{self.depthbegin:2}{depth} - Begin for :'{blkid}'")
pathlist = ""
for id in self.stackbegin:
if len(id) > 0:
pathlist += "." + id
def printend():
nonlocal args
depth = " " * self.depthbegin
if debugprint:
print(f"{self.depthbegin:2}{depth} - End from:'{args}'")
print(
"{:2}{} - LEGS: {} (n: {}, length:{} units:{})".format(
self.depthbegin, depth, self.slength, self.slength, self.legsnumber, self.units
)
)
def pushblock():
nonlocal blkid
if debugprint:
print(f" # datastack at 1 *begin {blkid} 'type':", end="")
for dict in self.datastack:
print(f"'{dict['type'].upper()}' ", end="")
print("")
print(f"'{self.datastar['type'].upper()}' self.datastar ")
# ------------ * DATA
self.datastack.append(copy.deepcopy(self.datastar))
# ------------ * DATA
if debugprint:
print(f" # datastack at 2 *begin {blkid} 'type':", end="")
for dict in self.datastack:
print(f"'{dict['type'].upper()}' ", end="")
print("")
print(f"'{self.datastar['type'].upper()}' self.datastar ")
# ------------ * FLAGS
self.flagsstack.append(copy.deepcopy(self.flagsstar))
# ------------ * FLAGS
pass
def popblock():
nonlocal blkid
nonlocal oldflags
if debugprint:
print(f" # datastack at *end '{blkid} 'type':", end="")
for dict in self.datastack:
print(f"'{dict['type'].upper()}' ", end="")
print("")
print(f"'{self.datastar['type'].upper()}' self.datastar ")
# ------------ * DATA
self.datastar = copy.deepcopy(self.datastack.pop())
# ------------ * DATA
if debugprint:
print(f" # datastack after *end '{blkid} 'type':", end="")
for dict in self.datastack:
print(f"'{dict['type'].upper()}' ", end="")
print("")
print(f"'{self.datastar['type'].upper()}' self.datastar ")
# ------------ * FLAGS
self.flagsstar = copy.deepcopy(self.flagsstack.pop())
# ------------ * FLAGS
if debugprint:
if oldflags["skiplegs"] != self.flagsstar["skiplegs"]:
print(f" # POP 'any' flag now:'{self.flagsstar['skiplegs']}' was:{oldflags['skiplegs']} ")
def starstatement(star):
"""Interprets a survex comamnd where * is the first character on the line, e.g. *begin"""
nonlocal survexblock
nonlocal blkid
nonlocal pathlist
nonlocal args
nonlocal oldflags
nonlocal slengthtotal
nonlocal nlegstotal
cmd, args = star.groups()
cmd = cmd.lower()
# ------------------------BEGIN
if self.rx_begin.match(cmd):
blkid = args.lower()
# PUSH state ++++++++++++++
self.stackbegin.append(blkid)
self.unitsstack.append((self.units, self.unitsfactor))
self.legsnumberstack.append(self.legsnumber)
self.slengthstack.append(self.slength)
self.personexpedstack.append(self.currentpersonexped) # just one person?!
pushblock()
# PUSH state ++++++++++++++
self.legsnumber = 0
self.slength = 0.0
self.units = "metres"
self.currentpersonexped = []
printbegin()
newsurvexblock = SurvexBlock(
name=blkid,
parent=survexblock,
survexpath=pathlist,
cave=self.currentcave,
survexfile=self.currentsurvexfile,
legsall=0,
legslength=0.0,
)
newsurvexblock.save()
newsurvexblock.title = (
"(" + survexblock.title + ")"
) # copy parent inititally, overwrite if it has its own
survexblock = newsurvexblock
survexblock.save() # django insists on this , but we want to save at the end !
tickle()
# ---------------------------END
elif self.rx_end.match(cmd):
survexblock.legsall = self.legsnumber
survexblock.legslength = self.slength
printend()
slengthtotal += self.slength
nlegstotal += self.legsnumber
try:
survexblock.parent.save() # django insists on this although it is already saved !?
except:
print(survexblock.parent, file=sys.stderr)
raise
try:
survexblock.save() # save to db at end of block
except:
print(survexblock, file=sys.stderr)
raise
# POP state ++++++++++++++
popblock()
self.currentpersonexped = self.personexpedstack.pop() # just one person?!
self.legsnumber = self.legsnumberstack.pop()
self.units, self.unitsfactor = self.unitsstack.pop()
self.slength = self.slengthstack.pop()
blkid = self.stackbegin.pop()
self.currentsurvexblock = survexblock.parent
survexblock = survexblock.parent
oldflags = self.flagsstar
self.depthbegin -= 1
# POP state ++++++++++++++
# -----------------------------
elif self.rx_title.match(cmd):
quotedtitle = self.rx_quotedtitle.match(args)
if quotedtitle:
survexblock.title = quotedtitle.groups()[0]
else:
survexblock.title = args
elif self.rx_ref.match(cmd):
self.LoadSurvexRef(survexblock, args)
elif self.rx_flags.match(cmd):
oldflags = self.flagsstar
self.LoadSurvexFlags(args)
if debugprint:
if oldflags["skiplegs"] != self.flagsstar["skiplegs"]:
print(f" # CHANGE 'any' flag now:'{self.flagsstar['skiplegs']}' was:{oldflags['skiplegs']} ")
elif self.rx_data.match(cmd):
if self.LoadSurvexDataNormal(survexblock, args):
pass
else:
# Abort, we do not cope with this *data format
return
elif self.rx_alias.match(cmd):
self.LoadSurvexAlias(survexblock, args)
elif self.rx_entrance.match(cmd):
self.LoadSurvexEntrance(survexblock, args)
elif self.rx_date.match(cmd):
self.LoadSurvexDate(survexblock, args)
elif self.rx_units.match(cmd):
self.LoadSurvexUnits(survexblock, args)
elif self.rx_team.match(cmd):
self.LoadSurvexTeam(survexblock, args)
elif self.rx_set.match(cmd) and self.rx_names.match(cmd):
pass
elif self.rx_include.match(cmd):
message = f" ! -ERROR *include command not expected here {path}. Re-run a full Survex import."
print(message)
print(message, file=sys.stderr)
stash_data_issue(
parser="survex",
message=message,
)
else:
self.LoadSurvexFallThrough(survexblock, args, cmd)
# this is a python generator idiom.
# see https://realpython.com/introduction-to-python-generators/
# this is the first use of generators in troggle (Oct.2022) and save 21 MB of memory
with open(collatefilename, "r") as fcollate:
for svxline in fcollate:
self.lineno += 1
sline, comment = self.rx_comment.match(svxline).groups()
if comment:
# this catches the ;*include NEWFILE and ;*edulcni ENDOFFILE lines too
self.LoadSurvexComment(survexblock, comment)
if not sline:
continue # skip blank lines
# detect a merge failure inserted by version control
mfail = self.rx_badmerge.match(sline)
if mfail:
message = f"\n ! - ERROR version control merge failure\n - '{sline}'\n"
message = (
message + f" - line {self.lineno} in {blkid} in {survexblock}\n - NERD++ needed to fix it"
)
print(message)
print(message, file=sys.stderr)
stash_data_issue(parser="survex", message=message)
continue # skip this line
# detect a star command
star = self.rx_star.match(sline)
if star:
# yes we are reading a *command
starstatement(star)
else: # not a *cmd so we are reading data OR a ";" rx_comment failed. We hope.
self.LoadSurvexLeg(survexblock, sline, comment, svxline)
self.legsnumber = nlegstotal
self.slength = slengthtotal
def PushdownStackScan(self, survexblock, path, finname, flinear, fcollate):
"""Follows the *include links in all the survex files from the root file (usually 1623.svx)
and reads only the *include and *begin and *end statements. It produces a linearised
list of the include tree and detects blocks included more than once.
"""
global stop_dup_warning
def process_line(svxline):
self.lineno += 1
# detect a merge failure inserted by version control
mfail = self.rx_badmerge.match(svxline)
if mfail:
message = f"\n!! - ERROR version control merge failure\n - '{svxline}'\n"
message = message + f" - in '{path}' at line {thissvxline}\n"
message = (
message + f" - line {self.lineno} {survexblock}\n - Parsing aborted. NERD++ needed to fix it"
)
print(message)
print(message, file=sys.stderr)
stash_data_issue(parser="survex", message=message, url=None, sb=(path))
return # skip this survex file and all things *included in it
includestmt = self.rx_include.match(svxline)
if not includestmt:
fcollate.write(f"{svxline.strip()}\n")
sline, comment = self.rx_comment.match(svxline.strip()).groups()
star = self.rx_star.match(sline)
if star: # yes we are reading a *cmd
cmd, args = star.groups()
cmd = cmd.lower()
if self.rx_include2.match(cmd):
# rx_include2 = re.compile("(?i)include$")
# if re.match("(?i)include$", cmd):
includepath = os.path.normpath(os.path.join(os.path.split(path)[0], re.sub(r"\.svx$", "", args)))
fullpath = os.path.join(settings.SURVEX_DATA, includepath + ".svx")
self.RunSurvexIfNeeded(os.path.join(settings.SURVEX_DATA, includepath), path)
self.checkUniqueness(os.path.join(settings.SURVEX_DATA, includepath))
if os.path.isfile(fullpath):
# --------------------------------------------------------
self.depthinclude += 1
# fininclude = open(fullpath,'r')
finincludename = fullpath
fcollate.write(f";|*include {includepath}\n")
flinear.write(f"{self.depthinclude:2} {indent} *include {includepath}\n")
push = includepath.lower()
self.includestack.append(push)
# -----------------
self.PushdownStackScan(survexblock, includepath, finincludename, flinear, fcollate)
# -----------------
pop = self.includestack.pop()
if pop != push:
message = "!! ERROR mismatch *include pop!=push {}".format(pop, push, self.includestack)
print(message)
print(message, file=flinear)
print(message, file=sys.stderr)
stash_data_issue(parser="survex", message=message, url=None, sb=(path))
flinear.write(f"{self.depthinclude:2} {indent} *edulcni {pop}\n")
fcollate.write(f";|*edulcni {pop}\n")
# fininclude.close()
self.depthinclude -= 1
# --------------------------------------------------------
else:
message = f" ! ERROR *include file '{includepath}' not found, listed in '{fin.name}'"
print(message)
print(message, file=sys.stderr)
stash_data_issue(parser="survex", message=message, url=None, sb=(path))
elif re.match("(?i)begin$", cmd):
self.depthbegin += 1
depth = " " * self.depthbegin
if args:
pushargs = args
else:
pushargs = " "
self.stackbegin.append(pushargs.lower())
flinear.write(f" {self.depthbegin:2} {depth} *begin {args}\n")
pass
elif re.match("(?i)end$", cmd):
depth = " " * self.depthbegin
flinear.write(f" {self.depthbegin:2} {depth} *end {args}\n")
if not args:
args = " "
popargs = self.stackbegin.pop()
if popargs != args.lower():
message = (
f"!! ERROR mismatch in BEGIN/END labels pop!=push '{popargs}'!='{args}'\n{self.stackbegin}"
)
print(message)
print(message, file=flinear)
print(message, file=sys.stderr)
stash_data_issue(parser="survex", message=message, url=None, sb=(path))
self.depthbegin -= 1
pass
elif re.match("(?i)title$", cmd):
depth = " " * self.depthbegin
flinear.write(f" {self.depthbegin:2} {depth} *title {args}\n")
pass
indent = " " * self.depthinclude
sys.stderr.flush()
self.callcount += 1
if self.callcount % 10 == 0:
print(".", file=sys.stderr, end="")
if self.callcount % 500 == 0:
print("\n ", file=sys.stderr, end="")
if path in self.svxfileslist:
# We have already used os.normpath() so this is OK. "/../" and "//" have been simplified already.
if stop_dup_warning:
# print("D",end="", file=sys.stderr)
pass
else:
message = f" * Warning. Duplicate detected. We have already seen this *include '{path}' from another survex file. Detected at callcount:{self.callcount} depth:{self.depthinclude}"
print(message)
print(message, file=flinear)
# print(message,file=sys.stderr)
stash_data_issue(parser="survex", message=message, url=None, sb=(path))
if self.svxfileslist.count(path) > 2:
message = f" ! ERROR. Should have been caught before this. Survex file already *included 2x. Probably an infinite loop so fix your *include statements that include this. Aborting. {path}"
print(message)
print(message, file=flinear)
# print(message,file=sys.stderr)
stash_data_issue(parser="survex", message=message, url=None, sb=(path))
return
return
try:
# python generator idiom again. Not important here as these are small files
with open(finname, "r") as fin:
for svxline in fin:
process_line(svxline)
self.svxfileslist.append(path)
except UnicodeDecodeError:
# some bugger put an umlaut in a non-UTF survex file ?!
message = f" ! ERROR *include file '{path}' in '{survexblock}' has UnicodeDecodeError. Omitted."
print(message)
print(message, file=sys.stderr)
stash_data_issue(parser="survex", message=message, url=None, sb=(path))
return # skip this survex file and all things *included in it
except:
message = f" ! ERROR *include file '{path}' in '{survexblock}' has unexpected error. Omitted."
print(message)
print(message, file=sys.stderr)
stash_data_issue(parser="survex", message=message, url=None, sb=(path))
return # skip this survex file and all things *included in it
def checkUniqueness(self, fullpath):
fn = Path(fullpath).name
if fn not in self.uniquename:
self.uniquename[fn] = [fullpath]
else:
self.uniquename[fn].append(fullpath)
# This is not an error now that we are moving .3d files to the :loser: directory tree
# message = f" ! NON-UNIQUE survex filename, '{fn}' - '{self.uniquename[fn]}' #{len(self.uniquename[fn])}"
# print(message)
# stash_data_issue(parser='survex', message=message)
message = (
f" NOTE: non-unique survex filename, '{fn}' - '{self.uniquename[fn]}' #{len(self.uniquename[fn])}"
)
print(message)
def RunSurvexIfNeeded(self, fullpath, calledpath):
now = time.time()
cav_t = now - 365 * 24 * 3600
log_t = now - 365 * 24 * 3600
svx_t = now - 365 * 24 * 3600
def runcavern():
"""regenerates the .3d file from the .svx if it is older than the svx file, or older than the software,
or randomly using chaosmonkey() just to keep things ticking over.
"""
print(
f" - Regenerating stale (or chaos-monkeyed) cavern .log and .3d for '{fullpath}'\n at '{logpath}'\n"
)
print(
f"days svx old: {(svx_t - log_t)/(24*3600):.1f} cav:{(cav_t - log_t)/(24*3600):.1f} log old: { (now - log_t)/(24*3600):.1f}"
)
outputdir = Path(str(f"{fullpath}.svx")).parent
sp = subprocess.run(
[settings.CAVERN, "--log", f"--output={outputdir}", f"{fullpath}.svx"],
capture_output=True,
check=False,
text=True,
)
if sp.returncode != 0:
message = f" ! Error running {settings.CAVERN}: {fullpath}"
url = f"/survexfile{fullpath}.svx".replace(settings.SURVEX_DATA, "")
stash_data_issue(parser="xEntrances", message=message, url=url)
print(message)
print(
"stderr:\n\n" + str(sp.stderr) + "\n\n" + str(sp.stdout) + "\n\nreturn code: " + str(sp.returncode)
)
self.caverncount += 1
# should also collect all the .err files too and create a DataIssue for each one which
# - is nonzero in size AND
# - has Error greater than 5% anywhere, or some other more serious error
errpath = Path(fullpath + ".err")
if errpath.is_file():
if errpath.stat().st_size == 0:
errpath.unlink() # delete empty closure error file
svxpath = Path(fullpath + ".svx")
logpath = Path(fullpath + ".log")
Path(svxpath).parent
if not svxpath.is_file():
message = f' ! BAD survex file "{fullpath}" specified in *include in {calledpath} '
stash_data_issue(parser="entrances", message=message)
print(message)
return
if not logpath.is_file(): # always run if logfile not there
runcavern()
return
self.caverndate = now - 2 * 365 * 24 * 3600
if not self.caverndate:
sp = subprocess.run(["which", f"{settings.CAVERN}"], capture_output=True, check=False, text=True)
if sp.returncode != 0:
message = f' ! Error running "which" on {settings.CAVERN}'
stash_data_issue(parser="entrances", message=message)
print(message)
print(
"stderr:\n\n" + str(sp.stderr) + "\n\n" + str(sp.stdout) + "\n\nreturn code: " + str(sp.returncode)
)
self.caverndate = os.path.getmtime(sp.stdout.strip())
else:
self.caverndate = now - 2 * 365 * 24 * 3600
cav_t = self.caverndate
log_t = os.path.getmtime(logpath)
svx_t = os.path.getmtime(svxpath)
now = time.time()
if svx_t - log_t > 0: # stale, svx file is newer than log
runcavern()
return
if now - log_t > 60 * 24 * 60 * 60: # >60 days, re-run anyway
runcavern()
return
if cav_t - log_t > 0: # new version of cavern
runcavern()
return
if chaosmonkey(350): # one in every 350 runs
runcavern()
def FindAndLoadSurvex(survexblockroot):
"""Follows the *include links successively to find files in the whole include tree"""
global stop_dup_warning
print(" - redirecting stdout to svxblks.log...")
stdout_orig = sys.stdout
# Redirect sys.stdout to the file
sys.stdout = open("svxblks.log", "w")
print(f" - Scanning Survex Blocks tree from {settings.SURVEX_TOPNAME}.svx ...", file=sys.stderr)
survexfileroot = survexblockroot.survexfile # i.e. SURVEX_TOPNAME only
collatefilename = "_" + survexfileroot.path + ".svx"
svx_scan = LoadingSurvex()
svx_scan.callcount = 0
svx_scan.depthinclude = 0
fullpathtotop = os.path.join(survexfileroot.survexdirectory.path, survexfileroot.path)
print(f" - RunSurvexIfNeeded cavern on '{fullpathtotop}'", file=sys.stderr)
svx_scan.RunSurvexIfNeeded(fullpathtotop, fullpathtotop)
svx_scan.checkUniqueness(fullpathtotop)
indent = ""
fcollate = open(collatefilename, "w")
mem0 = get_process_memory()
print(f" - MEM:{mem0:7.2f} MB START", file=sys.stderr)
flinear = open("svxlinear.log", "w")
flinear.write(f" - MEM:{mem0:7.2f} MB START {survexfileroot.path}\n")
print(" ", file=sys.stderr, end="")
finrootname = Path(settings.SURVEX_DATA, survexfileroot.path + ".svx")
fcollate.write(f";*include {survexfileroot.path}\n")
flinear.write(f"{svx_scan.depthinclude:2} {indent} *include {survexfileroot.path}\n")
import cProfile
import pstats
from pstats import SortKey
pr = cProfile.Profile()
pr.enable()
# ----------------------------------------------------------------
svx_scan.PushdownStackScan(survexblockroot, survexfileroot.path, finrootname, flinear, fcollate)
# ----------------------------------------------------------------
pr.disable()
with open("PushdownStackScan.prof", "w") as f:
ps = pstats.Stats(pr, stream=f)
ps.sort_stats(SortKey.CUMULATIVE)
ps.print_stats()
flinear.write(f"{svx_scan.depthinclude:2} {indent} *edulcni {survexfileroot.path}\n")
fcollate.write(f";*edulcni {survexfileroot.path}\n")
mem1 = get_process_memory()
flinear.write(f"\n - MEM:{mem1:.2f} MB STOP {survexfileroot.path}\n")
flinear.write(f" - MEM:{mem1 - mem0:.3f} MB ADDITIONALLY USED\n")
flinear.write(f" - {len(svx_scan.svxfileslist):,} survex files in linear include list \n")
print(f"\n - {svx_scan.caverncount:,} runs of survex 'cavern' refreshing .3d files", file=sys.stderr)
print(f" - {len(svx_scan.svxfileslist):,} survex files from tree in linear include list", file=sys.stderr)
mem1 = get_process_memory()
print(f" - MEM:{mem1:7.2f} MB END ", file=sys.stderr)
print(f" - MEM:{mem1 - mem0:7.3f} MB ADDITIONALLY USED", file=sys.stderr)
#
# Process all the omitted files in :loser: with some exceptions
#
unseens = set()
b = []
for p in Path(settings.SURVEX_DATA).rglob("*.svx"):
if p.is_file():
po = p.relative_to(Path(settings.SURVEX_DATA))
pox = po.with_suffix("")
if str(pox) not in svx_scan.svxfileslist:
# print(f"[{pox}]", file=sys.stderr)
unseens.add(pox)
else:
b.append(pox)
if len(b) != len(svx_scan.svxfileslist):
print(
f" ! Mismatch. {len(b)} survex files found which should be {len(svx_scan.svxfileslist)} in main tree)",
file=sys.stderr,
)
excpts = ["surface/terrain", "kataster/kataster-boundaries", "template", "docs", "_unseens"]
removals = []
for x in unseens:
for o in excpts:
if str(x).strip().startswith(o):
removals.append(x)
# special fix for file not actually in survex format
unseens.remove(Path("fixedpts/gps/gps00raw"))
for x in removals:
unseens.remove(x)
print(
f"\n - {len(unseens)} survex files found which were not included in main tree. ({len(svx_scan.svxfileslist)} in main tree)",
file=sys.stderr,
)
print(" -- Now loading the previously-omitted survex files.", file=sys.stderr)
with open(Path(settings.SURVEX_DATA, "_unseens.svx"), "w") as u:
u.write(
f"; {len(unseens):,} survex files not *included by {settings.SURVEX_TOPNAME} (which are {len(svx_scan.svxfileslist):,} files)\n"
)
u.write(f"; autogenerated by parser/survex.py from databasereset.py on '{datetime.now(timezone.utc)}'\n")
u.write(f"; omitting any file beginning with {excpts}\n\n")
u.write("*begin unseens\n")
for x in sorted(unseens):
u.write(f" *include {x}\n")
u.write("*end unseens\n")
survexfileroot = survexblockroot.survexfile # i.e. SURVEX_TOPNAME only
omit_scan = LoadingSurvex()
omit_scan.callcount = 0
omit_scan.depthinclude = 0
fullpathtotop = os.path.join(survexfileroot.survexdirectory.path, "_unseens.svx")
# copy the list to prime the next pass through the files
omit_scan.svxfileslist = svx_scan.svxfileslist[:]
svx_scan.svxfileslist = [] # free memory
svx_scan = None # Hmm. Does this actually delete all the instance variables if they are lists, dicts etc.?
print(f" - RunSurvexIfNeeded cavern on '{fullpathtotop}'", file=sys.stderr)
omit_scan.RunSurvexIfNeeded(fullpathtotop, fullpathtotop)
omit_scan.checkUniqueness(fullpathtotop)
mem0 = get_process_memory()
print(f" - MEM:{mem0:7.2f} MB START '_unseens'", file=sys.stderr)
# flinear = open('svxlinear.log', 'w')
flinear.write(f" - MEM:{mem0:7.2f} MB START '_unseens'\n")
print(" ", file=sys.stderr, end="")
finrootname = fullpathtotop
fcollate.write(";*include _unseens.svx\n")
flinear.write(f"{omit_scan.depthinclude:2} {indent} *include _unseens\n")
stop_dup_warning = True
# ----------------------------------------------------------------
omit_scan.PushdownStackScan(survexblockroot, "_unseens", finrootname, flinear, fcollate)
# ----------------------------------------------------------------
stop_dup_warning = False
flinear.write(f"{omit_scan.depthinclude:2} {indent} *edulcni _unseens\n")
fcollate.write(";*edulcni _unseens.svx\n")
mem1 = get_process_memory()
flinear.write(f"\n - MEM:{mem1:.2f} MB STOP _unseens.svx OMIT\n")
flinear.write(f" - MEM:{mem1 - mem0:.3f} MB ADDITIONALLY USED OMIT\n")
flinear.write(f" - {len(omit_scan.svxfileslist):,} survex files in linear include list OMIT \n")
flinear.close()
fcollate.close()
print(
f"\n - {omit_scan.caverncount:,} runs of survex 'cavern' refreshing .3d files in the unseen list",
file=sys.stderr,
)
print(
f" - {len(omit_scan.svxfileslist):,} survex files in linear include list including previously unseen ones \n",
file=sys.stderr,
)
omit_scan = None # Hmm. Does this actually delete all the instance variables if they are lists, dicts etc.?
mem1 = get_process_memory()
print(f" - MEM:{mem1:7.2f} MB END ", file=sys.stderr)
print(f" - MEM:{mem1 - mem0:7.3f} MB ADDITIONALLY USED", file=sys.stderr)
# Before doing this, it would be good to identify the *equate and *entrance we need that are relevant to the
# entrance locations currently loaded after this by LoadPos(), but could better be done before ?
# look in MapLocations() for how we find the entrances
print("\n - Loading All Survex Blocks (LinearLoad)", file=sys.stderr)
svx_load = LoadingSurvex()
svx_load.survexdict[survexfileroot.survexdirectory] = []
svx_load.survexdict[survexfileroot.survexdirectory].append(survexfileroot)
svx_load.svxdirs[""] = survexfileroot.survexdirectory
# pr2 = cProfile.Profile()
# pr2.enable()
print(" ", file=sys.stderr, end="")
# ----------------------------------------------------------------
svx_load.LinearLoad(survexblockroot, survexfileroot.path, collatefilename)
# ----------------------------------------------------------------
# pr2.disable()
# with open('LinearLoad.prof', 'w') as f:
# ps = pstats.Stats(pr2, stream=f)
# ps.sort_stats(SortKey.CUMULATIVE)
# ps.print_stats()
mem1 = get_process_memory()
print(f"\n - MEM:{mem1:7.2f} MB STOP", file=sys.stderr)
print(f" - MEM:{mem1 - mem0:7.3f} MB ADDITIONALLY USED", file=sys.stderr)
# Close the logging file, Restore sys.stdout to our old saved file handle
sys.stdout.close()
print("+", file=sys.stderr)
sys.stderr.flush()
sys.stdout = stdout_orig
legsnumber = svx_load.legsnumber
mem1 = get_process_memory()
print(f" - Number of SurvexDirectories: {len(svx_load.survexdict):,}")
tf = 0
for d in svx_load.survexdict:
tf += len(svx_load.survexdict[d])
print(f" - Number of SurvexFiles: {tf:,}")
print(f" - Number of Survex legs: {legsnumber:,}")
svx_load = None
return legsnumber
def MakeSurvexFileRoot():
"""Returns a file_object.path = SURVEX_TOPNAME associated with directory_object.path = SURVEX_DATA"""
# find a cave, any cave..
smk = Cave.objects.filter(kataster_number="000") # returns a list, a QuerySet
fileroot = SurvexFile(path=settings.SURVEX_TOPNAME, cave=None)
fileroot.save()
directoryroot = SurvexDirectory(path=settings.SURVEX_DATA, cave=smk[0], primarysurvexfile=fileroot)
# MariaDB doesn't like this hack. Complains about non-null cave_id EVEN THOUGH our model file says this is OK:
# cave = models.ForeignKey('Cave', blank=True, null=True,on_delete=models.SET_NULL)
directoryroot.save()
fileroot.survexdirectory = directoryroot # i.e. SURVEX_DATA/SURVEX_TOPNAME
fileroot.save() # mutually dependent objects need a double-save like this
return fileroot
def MakeOmitFileRoot(fn):
"""Returns a file_object.path = _unseens.svx associated with directory_object.path = SURVEX_DATA"""
fileroot = SurvexFile(path=fn, cave=None)
fileroot.survexdirectory = SurvexDirectory.objects.get(path=settings.SURVEX_DATA)
fileroot.save()
return fileroot
def LoadSurvexBlocks():
mem1 = get_process_memory()
print(f" - MEM:{mem1:7.2f} MB now ", file=sys.stderr)
start = time.time()
print(" - Flushing All Survex Blocks...")
# why does this increase memory use by 20 MB ?!
# We have foreign keys, Django needs to load the related objects
# in order to resolve how the relation should handle the deletion:
# https://docs.djangoproject.com/en/3.2/ref/models/fields/#django.db.models.ForeignKey.on_delete
SurvexBlock.objects.all().delete()
SurvexFile.objects.all().delete()
SurvexDirectory.objects.all().delete()
SurvexPersonRole.objects.all().delete()
SurvexStation.objects.all().delete()
mem1 = get_process_memory()
print(f" - MEM:{mem1:7.2f} MB now. Foreign key objects loaded on deletion. ", file=sys.stderr)
print(" - Flushing survex Data Issues ")
global dataissues
dataissues = []
DataIssue.objects.filter(parser="survex").delete()
DataIssue.objects.filter(parser="svxdate").delete()
DataIssue.objects.filter(parser="survexleg").delete()
DataIssue.objects.filter(parser="survexunits").delete()
DataIssue.objects.filter(parser="survex team").delete()
DataIssue.objects.filter(parser="entrances").delete()
DataIssue.objects.filter(parser="xEntrances").delete()
print(" - survex Data Issues flushed")
mem1 = get_process_memory()
print(f" - MEM:{mem1:7.2f} MB now ", file=sys.stderr)
survexfileroot = MakeSurvexFileRoot()
# this next makes a block_object assciated with a file_object.path = SURVEX_TOPNAME
survexblockroot = SurvexBlock(
name=ROOTBLOCK, survexpath="", cave=None, survexfile=survexfileroot, legsall=0, legslength=0.0
)
# crashes here sometimes on MariaDB complaining that cave_id should not be null. But it should be.
# django.db.utils.IntegrityError: (1048, "Column 'cave_id' cannot be null")
# fix by restarting db on server
# sudo service mariadb stop
# sudo service mariadb start
survexblockroot.save()
omitsfileroot = MakeOmitFileRoot("_unseens.svx")
survexomitsroot = SurvexBlock(
name=OMITBLOCK, survexpath="", cave=None, survexfile=omitsfileroot, legsall=0, legslength=0.0
)
survexomitsroot.save()
print(" - Loading Survex Blocks...")
memstart = get_process_memory()
# ----------------------------------------------------------------
FindAndLoadSurvex(survexblockroot)
# ----------------------------------------------------------------
memend = get_process_memory()
print(f" - MEMORY start:{memstart:.3f} MB end:{memend:.3f} MB increase={memend - memstart:.3f} MB")
survexblockroot.save()
global person_pending_cache
for sb in person_pending_cache:
if len(person_pending_cache[sb]) > 0:
print(f" ")
message = f" ! PENDING team list not emptied {sb.survexfile.path} {len(person_pending_cache[sb])} people: {person_pending_cache[sb]}"
stash_data_issue(parser="survex", message=message, url=None, sb=(sb.survexfile.path))
print(message)
# duration = time.time() - start
# print(f" - TIME: {duration:7.2f} s", file=sys.stderr)
store_data_issues()
# duration = time.time() - start
# print(f" - TIME: {duration:7.2f} s", file=sys.stderr)
print(" - Loaded All Survex Blocks.")
poslineregex = re.compile(r"^\(\s*([+-]?\d*\.\d*),\s*([+-]?\d*\.\d*),\s*([+-]?\d*\.\d*)\s*\)\s*([^\s]+)$")
def LoadPositions():
"""First load the survex stations for entrances and fixed points (about 600) into the database.
Run cavern to produce a complete .3d file, then run 3dtopos to produce a table of
all survey point positions. Then lookup each position by name to see if we have it in the database
and if we do, then save the x/y/z coordinates. This gives us coordinates of the entrances.
If we don't have it in the database, print an error message and discard it.
"""
svx_t = 0
d3d_t = 0
def runcavern3d():
outputdir = Path(str(f"{topdata}.svx")).parent
# print(" - Regenerating stale cavern .log and .3d for '{}'\n days old: {:.1f} {:.1f} {:.1f}".
# format(topdata, (svx_t - d3d_t)/(24*3600), (cav_t - d3d_t)/(24*3600), (now - d3d_t)/(24*3600)))
file3d = Path(f"{topdata}.3d")
try:
sp = subprocess.run(
[settings.CAVERN, "--log", f"--output={outputdir}", f"{topdata}.svx"],
capture_output=True,
check=False,
text=True,
) # check=False means exception not raised
if sp.returncode != 0:
message = f" ! Error: cavern: creating {file3d} in runcavern3()"
stash_data_issue(parser="entrances", message=message)
print(message)
# find the errors in the 1623.log file
sp = subprocess.run(
["grep", "error:", f"{topdata}.log"], capture_output=True, check=False, text=True
) # check=False means exception not raised
message = f" ! Error: cavern: {sp.stdout} creating {file3d} "
stash_data_issue(parser="entrances", message=message)
print(message)
except:
message = f" ! CalledProcessError 'cavern' in runcavern3() at {topdata}."
stash_data_issue(parser="entrances", message=message)
print(message)
if file3d.is_file():
message = f" ! CalledProcessError. File permissions {file3d.stat().st_mode} on {str(file3d)}"
stash_data_issue(parser="entrances", message=message)
print(message)
if file3d.is_file(): # might be an old one though
try:
# print(" - Regenerating {} {}.3d in {}".format(settings.SURVEXPORT, topdata, settings.SURVEX_DATA))
sp = subprocess.run(
[settings.SURVEXPORT, "--pos", f"{file3d}"],
cwd=settings.SURVEX_DATA,
capture_output=True,
check=False,
text=True,
)
if sp.returncode != 0:
print(
f" ! Error: survexport creating {topdata}.pos in runcavern3().\n\n"
+ str(sp.stdout)
+ "\n\nreturn code: "
+ str(sp.returncode)
)
except:
message = f" ! CalledProcessError 'survexport' in runcavern3() at {file3d}."
stash_data_issue(parser="entrances", message=message)
print(message)
else:
message = f" ! Failed to find {file3d} so aborting generation of new .pos, using old one if present"
stash_data_issue(parser="entrances", message=message)
print(message)
topdata = os.fspath(Path(settings.SURVEX_DATA) / settings.SURVEX_TOPNAME)
print(f" - Generating a list of Pos from {topdata}.svx and then loading...")
found = 0
print("\n") # extra line because cavern overwrites the text buffer somehow
# cavern defaults to using same cwd as supplied input file
completed_process = subprocess.run(["which", f"{settings.CAVERN}"], capture_output=True, check=True, text=True)
cav_t = os.path.getmtime(completed_process.stdout.strip())
svxpath = topdata + ".svx"
d3dpath = topdata + ".3d"
pospath = topdata + ".pos"
svx_t = os.path.getmtime(svxpath)
if os.path.isfile(d3dpath):
# always fails to find log file if a double directory, e.g. caves-1623/B4/B4/B4.svx Why ?
d3d_t = os.path.getmtime(d3dpath)
now = time.time()
if not os.path.isfile(pospath):
runcavern3d()
if not os.path.isfile(d3dpath):
runcavern3d()
elif d3d_t - svx_t > 0: # stale, 3d older than svx file
runcavern3d()
elif now - d3d_t > 60 * 24 * 60 * 60: # >60 days old, re-run anyway
runcavern3d()
elif cav_t - d3d_t > 0: # new version of cavern
runcavern3d()
mappoints = {}
for pt in MapLocations().points():
svxid, number, point_type, label = pt
mappoints[svxid] = True
if not Path(pospath).is_file():
message = f" ! Failed to find {pospath} so aborting generation of entrance locations. "
stash_data_issue(parser="entrances", message=message)
print(message)
return
posfile = open(pospath)
posfile.readline() # Drop header
try:
survexblockroot = SurvexBlock.objects.get(name=ROOTBLOCK)
except:
try:
survexblockroot = SurvexBlock.objects.get(id=1)
except:
message = " ! FAILED to find root SurvexBlock"
print(message)
stash_data_issue(parser="entrances", message=message)
raise
for line in posfile.readlines():
r = poslineregex.match(line)
if r:
x, y, z, id = r.groups()
for sid in mappoints:
if id.endswith(sid):
blockpath = "." + id[: -len(sid)].strip(".")
# But why are we doing this? Why do we need the survexblock id for each of these ?
# ..because mostly they don't actually appear in any SVX file. We should match them up
# via the cave data, not by this half-arsed syntactic match which almost never works. PMS.
if False:
try:
sbqs = SurvexBlock.objects.filter(survexpath=blockpath)
if len(sbqs) == 1:
sbqs[0]
if len(sbqs) > 1:
message = f" ! MULTIPLE SurvexBlocks {len(sbqs):3} matching Entrance point {blockpath} {sid} '{id}'"
print(message)
stash_data_issue(parser="entrances", message=message)
sbqs[0]
elif len(sbqs) <= 0:
message = f" ! ZERO SurvexBlocks matching Entrance point {blockpath} {sid} '{id}'"
print(message)
stash_data_issue(parser="entrances", message=message)
except:
message = f" ! FAIL in getting SurvexBlock matching Entrance point {blockpath} {sid}"
print(message)
stash_data_issue(parser="entrances", message=message)
try:
ss = SurvexStation(name=id, block=survexblockroot)
ss.x = float(x)
ss.y = float(y)
ss.z = float(z)
ss.save()
found += 1
except:
message = f" ! FAIL to create SurvexStation Entrance point {blockpath} {sid}"
print(message)
stash_data_issue(parser="entrances", message=message)
raise
print(f" - {found} SurvexStation entrances found.")
store_data_issues()
|