expo/troggle
2
0
Fork 1
mirror of https://expo.survex.com/repositories/troggle/.git synced 2025-12-16 05:47:11 +00:00
Code Issues 18 Projects 3 Activity

Logbook debugging

Browse Source
This commit is contained in:
Expo laptop Crowley
2023-07-09 11:30:50 +02:00
parent 086537cb56
commit 4d48dd4386
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
parsers/logbooks.py
View File

@@ -57,7 +57,7 @@ LOGBOOK_PARSER_SETTINGS = {
LOGBOOKS_DIR = "years" # subfolder of settings.EXPOWEB LOGBOOKS_DIR = "years" # subfolder of settings.EXPOWEB
ENTRIES = { ENTRIES = {
"2023": 1, "2023": 11,
"2022": 90, "2022": 90,
"2019": 55, "2019": 55,
"2018": 95, "2018": 95,
@@ -295,7 +295,7 @@ def parser_html(year, expedition, txt, seq=""):
headmatch = re.match(r"(?i)(?s).*<body[^>]*>(.*?)<hr.*", txt) headmatch = re.match(r"(?i)(?s).*<body[^>]*>(.*?)<hr.*", txt)
headpara = headmatch.groups()[0].strip() headpara = headmatch.groups()[0].strip()
# print(f" - headpara:\n'{headpara}'") #print(f" - headpara:\n'{headpara}'")
if len(headpara) > 0: if len(headpara) > 0:
frontpath = Path(settings.EXPOWEB, LOGBOOKS_DIR, year, "frontmatter.html") frontpath = Path(settings.EXPOWEB, LOGBOOKS_DIR, year, "frontmatter.html")
with open(frontpath, "w") as front: with open(frontpath, "w") as front:
@@ -305,7 +305,7 @@ def parser_html(year, expedition, txt, seq=""):
endmatch = re.match(r"(?i)(?s).*<hr\s*/>([\s\S]*?)(?=</body)", txt) endmatch = re.match(r"(?i)(?s).*<hr\s*/>([\s\S]*?)(?=</body)", txt)
endpara = endmatch.groups()[0].strip() endpara = endmatch.groups()[0].strip()
# print(f" - endpara:\n'{endpara}'") #print(f" - endpara:\n'{endpara}'")
if len(endpara) > 0: if len(endpara) > 0:
endpath = Path(settings.EXPOWEB, LOGBOOKS_DIR, year, "endmatter.html") endpath = Path(settings.EXPOWEB, LOGBOOKS_DIR, year, "endmatter.html")
with open(endpath, "w") as end: with open(endpath, "w") as end:
@@ -333,7 +333,7 @@ def parser_html(year, expedition, txt, seq=""):
if s: if s:
tripid, tripid1, tripdate, trippeople, triptitle, triptext, tu = s.groups() tripid, tripid1, tripdate, trippeople, triptitle, triptext, tu = s.groups()
else: # allow title and people to be swapped in order else: # allow title and people to be swapped in order
msg = f" !- {year} Can't parse:{logbook_entry_count} '{trippara[:50]}'..." msg = f" !- {year} Can't parse:{logbook_entry_count} '{trippara[:55]}'...'{trippara}'"
print(msg) print(msg)
DataIssue.objects.create(parser="logbooks", message=msg) DataIssue.objects.create(parser="logbooks", message=msg)
@@ -353,7 +353,7 @@ def parser_html(year, expedition, txt, seq=""):
tripid, tripid1, tripdate, triptitle, trippeople, triptext, tu = s2.groups() tripid, tripid1, tripdate, triptitle, trippeople, triptext, tu = s2.groups()
else: else:
# if not re.search(r"Rigging Guide", trippara): # if not re.search(r"Rigging Guide", trippara):
msg = f" !- Logbook. Can't parse entry on 2nd pass:{logbook_entry_count} '{trippara[:50]}'..." msg = f" !- Logbook. Can't parse entry on 2nd pass:{logbook_entry_count} '{trippara[:55]}'...'{trippara}'"
print(msg) print(msg)
DataIssue.objects.create(parser="logbooks", message=msg) DataIssue.objects.create(parser="logbooks", message=msg)
continue continue