From c5b08ce80f6ea17556bbc45844706c94a9b542e9 Mon Sep 17 00:00:00 2001
From: Philip Sargent <philip.sargent@gmail.com>
Date: Wed, 15 Jan 2025 20:21:49 +0000
Subject: stumbled on bug when no entries in logbook, fixed.

---
 parsers/logbooks.py | 65 ++++++++++++++++++++++++++++++++---------------------
 1 file changed, 39 insertions(+), 26 deletions(-)

(limited to 'parsers/logbooks.py')

diff --git a/parsers/logbooks.py b/parsers/logbooks.py
index 3d96b3b..08e2710 100644
--- a/parsers/logbooks.py
+++ b/parsers/logbooks.py
@@ -58,6 +58,11 @@ LOGBOOK_PARSER_SETTINGS = {
 LOGBOOKS_DIR = "years" # subfolder of settings.EXPOWEB
 
 ENTRIES = {
+    "2029": 0,
+    "2028": 0,
+    "2027": 0,
+    "2026": 0,
+    "2025": 0,
     "2024": 125,
     "2023": 131,
     "2022": 94,
@@ -379,8 +384,10 @@ def parser_html(year, expedition, txt, seq=""):
     dupl = {}
 
     # extract front material and stash for later use when rebuilding from list of entries
-    headmatch = re.match(r"(?i)(?s).*<body[^>]*>(.*?)<hr.*", txt)
-    headpara = headmatch.groups()[0].strip()
+    if headmatch := re.match(r"(?i)(?s).*<body[^>]*>(.*?)<hr.*", txt):  # WALRUS OPERATOR
+        headpara = headmatch.groups()[0].strip()
+    else:
+        headpara = ""
 
     if len(headpara) > 0:
         frontpath = Path(settings.EXPOWEB, LOGBOOKS_DIR, year, "frontmatter.html")
@@ -390,8 +397,10 @@ def parser_html(year, expedition, txt, seq=""):
                 front.write(headpara + "\n")
 
     # extract END material and stash for later use when rebuilding from list of entries
-    endmatch = re.match(r"(?i)(?s).*<hr\s*/>([\s\S]*?)(?=</body)", txt)
-    endpara = endmatch.groups()[0].strip()
+    if endmatch := re.match(r"(?i)(?s).*<hr\s*/>([\s\S]*?)(?=</body)", txt):  # WALRUS OPERATOR
+        endpara = endmatch.groups()[0].strip()
+    else:
+        endpara = ""
 
     if len(endpara) > 0:
         print(f"\n - {year} endpara:\n'{endpara}'")
@@ -399,7 +408,10 @@ def parser_html(year, expedition, txt, seq=""):
         with open(endpath, "w") as end:
             end.write(endpara + "\n")
 
-    tripparas = re.findall(r"<hr\s*/>([\s\S]*?)(?=<hr)", txt)
+    if tripparas := re.findall(r"<hr\s*/>([\s\S]*?)(?=<hr)", txt): # WALRUS OPERATOR
+        pass
+    else:
+        return None
     logbook_entry_count = 0
     for trippara in tripparas:
         logbook_entry_count += 1
@@ -656,11 +668,12 @@ def parse_logbook_for_expedition(expedition, blog=False):
             logentries = parser(year, expedition, txt, sq)  # this launches the right parser
             # --------------------
 
-    if len(logentries) == expect:
-        # print(f"OK  {year} {len(logentries):5d} is {expect}\n")
-        pass
-    else:
-        print(f"Mismatch in number of log entries: {year} {len(logentries):5d} is not {expect}\n")
+    if logentries:
+        if len(logentries) == expect:
+            # print(f"OK  {year} {len(logentries):5d} is {expect}\n")
+            pass
+        else:
+            print(f"Mismatch in number of log entries: {year} {len(logentries):5d} is not {expect}\n")
 
     return logentries
 
@@ -674,23 +687,23 @@ def LoadLogbook(year):
     clean_logbook_for_expedition(expo)
     logentries = []
     
-    logentries = parse_logbook_for_expedition(expo)  # this actually loads the logbook for one expo
-    print(f" - Loaded logbook. {len(logentries)} entries." ) 
-    if year in BLOG_PARSER_SETTINGS:
-        print(f" - Loading blog.." ) 
-        logentries += parse_logbook_for_expedition(expo, blog=True)  # this  loads the blog logbook
-    else:
-        print(
-            f" - Not a year with extant blog entries to import: '{year}' not in BLOG_PARSER_SETTINGS {BLOG_PARSER_SETTINGS}"
-        )
-    for entrytuple in logentries:
-        date, place, tripcave, triptitle, text, trippersons, author, guests, expedition, tu, tid = entrytuple
-        if expo == expedition: # unneeded check, we zeroed it before filling it
-            # print(f" -- {triptitle}")
-            store_entry_into_database(date, place, tripcave, triptitle, text, trippersons, author, guests, expedition, tu, tid)
+    if logentries := parse_logbook_for_expedition(expo):  # this actually loads the logbook for one expo # WALRUS
+        print(f" - Loaded logbook. {len(logentries)} entries." ) 
+        if year in BLOG_PARSER_SETTINGS:
+            print(f" - Loading blog.." ) 
+            logentries += parse_logbook_for_expedition(expo, blog=True)  # this  loads the blog logbook
         else:
-            print(f" ! unexpected log entry labelled as '{expedition}' {tid}" ) 
-    expo.save() # to save logbook name property
+            print(
+                f" - Not a year with extant blog entries to import: '{year}' not in BLOG_PARSER_SETTINGS {BLOG_PARSER_SETTINGS}"
+            )
+        for entrytuple in logentries:
+            date, place, tripcave, triptitle, text, trippersons, author, guests, expedition, tu, tid = entrytuple
+            if expo == expedition: # unneeded check, we zeroed it before filling it
+                # print(f" -- {triptitle}")
+                store_entry_into_database(date, place, tripcave, triptitle, text, trippersons, author, guests, expedition, tu, tid)
+            else:
+                print(f" ! unexpected log entry labelled as '{expedition}' {tid}" ) 
+        expo.save() # to save logbook name property
     
 def LoadLogbooks():
     """This is the master function for parsing all logbooks into the Troggle database.
-- 
cgit v1.2.3