expo/troggle
2
0
Fork 1
mirror of https://expo.survex.com/repositories/troggle/.git synced 2024-11-22 07:11:52 +00:00
Code Issues 19 Projects 3 Activity

bugfix and remove swapped order for title/people

Browse Source
This commit is contained in:
Philip Sargent 2023-09-01 20:57:23 +03:00
parent 98412c140d
commit 33a08bed4f
2 changed files with 10 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
core/views/uploads.py
View File

@ -1,5 +1,4 @@
import subprocess
import string
from datetime import datetime
from pathlib import Path

40
parsers/logbooks.py
View File

@ -23,7 +23,7 @@ Parses and imports logbooks in all their wonderful confusion
https://expo.survex.com/handbook/computing/logbooks-parsing.html
"""
todo = """
- make id= for each entry persistent and unchanging, and check cross-references in other logbooks and other HTML frahments
- check cross-references in other logbooks and other HTML frahments
e.g. cave descriptions
- Most of the time is during the database writing (6s out of 8s).
@ -41,7 +41,6 @@ e.g. cave descriptions
file_in = open(logbookfile,'rb')
txt = file_in.read().decode("latin1")
"""
MAX_LOGBOOK_ENTRY_TITLE_LENGTH = 200
BLOG_PARSER_SETTINGS = { # no default, must be explicit
@ -61,7 +60,7 @@ LOGBOOK_PARSER_SETTINGS = {
LOGBOOKS_DIR = "years" # subfolder of settings.EXPOWEB
ENTRIES = {
"2023": 82,
"2023": 81,
"2022": 93,
"2019": 55,
"2018": 95,
@ -111,7 +110,7 @@ tripsdate = {}
def set_trip_seq_id(year, seq):
'''We have not parsed the trip date yet, so this is a sequence numer
'''We have not parsed the trip date yet, so this is a sequence number
'''
tid = f"{year}_s{seq:02d}"
return tid
@ -269,7 +268,7 @@ def store_entry_into_database(date, place, tripcave, title, text, trippersons, a
}
lookupAttribs = {"slug": tid, "date": date, "title": title}
if LogbookEntry.objects.filter(slug=tid).exists():
# oops.
# oops. Our code should already have ensured this is unique.
message = " ! - DUPLICATE SLUG for logbook entry " + tripdate + " - " + slug
DataIssue.objects.create(parser="logbooks", message=message)
slug = slug + "_" + unique_slug(text,2)
@ -374,31 +373,12 @@ def parser_html(year, expedition, txt, seq=""):
)
if s:
tripid, tripid1, tripdate, trippeople, triptitle, triptext, tu = s.groups()
else: # allow title and people to be swapped in order
msg = f" !- {year} Can't parse:{logbook_entry_count} '{trippara[:55]}'...'{trippara}'"
else:
# if not re.search(r"Rigging Guide", trippara):
msg = f" !- Logbook. Can't parse entry, skipping:{logbook_entry_count} '{trippara[:55]}'...'{trippara}'"
print(msg)
DataIssue.objects.create(parser="logbooks", message=msg)
s2 = re.match(
r"""(?x)(?:\s*<div\sclass="tripdate"\sid=".*?">.*?</div>\s*<p>)? # second date
\s*(?:<a\s+id="(.*?)"\s*/>\s*</a>)?
\s*<div\s+class="tripdate"\s*(?:id="(.*?)")?>(.*?)</div>(?:<p>)?
\s*<div\s+class="triptitle">\s*(.*?)</div>
\s*<div\s+class="trippeople">\s*(.*?)</div>
([\s\S]*?)
\s*(?:<div\s+class="timeug">\s*(.*?)</div>)?
\s*$
""",
trippara,
)
if s2:
tripid, tripid1, tripdate, triptitle, trippeople, triptext, tu = s2.groups()
else:
# if not re.search(r"Rigging Guide", trippara):
msg = f" !- Logbook. Can't parse entry on 2nd pass:{logbook_entry_count} '{trippara[:55]}'...'{trippara}'"
print(msg)
DataIssue.objects.create(parser="logbooks", message=msg)
continue
continue
ldate = parser_date(tripdate.strip(), year)
@ -408,12 +388,12 @@ def parser_html(year, expedition, txt, seq=""):
if len(triptitles) >= 2:
place = triptitles[0]
else:
place = "UNKNOWN"
place = "Unknown"
tripcontent = re.sub(r"</p>", "", triptext)
tripcontent = re.sub(r"<p>", "<br /><br />", tripcontent).strip()
triptitle = triptitle.strip()
# triptitle must be unique for a given date. We fix this here. [Why?!]
# triptitle must be unique for a given date. [Why?!] We fix this here.
check = (ldate, triptitle)
if check in dupl:
dupl[check] += 1