expoweb/scripts/make-folklist.py

#!/usr/bin/python
import sys, string, re, os
from datetime import date

# run within the /folk/ folder:
# python3 ../scripts/make-folklist.py <folk.csv >index.htm

# re-run it every time you edit the folk.csv file to add someone you have forgotten
# it needs to be run on the server too as the file produced is ignored by git

# updated to use slugs to recognise people instead of FirstnameSurname

headcount = 0
pics = 0
allyears = 0
recordholders = []
output = ""
n = 0

lines = sys.stdin.readlines()
headcounts_byyear = [0]*(len(lines[0].split(","))-5)

yearnow = date.today().year 

slug_cache = {}
def troggle_slugify(longname):
    """Uniqueness enforcement too. Yes we have had two "Dave Johnson"s
    This function copied instact from troggle/parsers/people/py
    """
    slug = longname.strip().lower().replace(" ","-")
    slug = re.sub('\([^\)]*\)','',slug) # remove nickname in brackets
    slug = slug.replace('&eacute;', 'e') 
    slug = slug.replace('&aacute;', 'a') 
    slug = slug.replace('&auml;', 'a') 
    slug = slug.replace('&', '') # otherwise just remove the &
    slug = slug.replace(';', '') # otherwise just remove the ;
    slug = re.sub('<[^>]*>','',slug) # remove <span-lang = "hu">
    
    if len(slug) > 40: # slugfield is 50 chars
        slug = slug[:40]
    if slug in slug_cache: 
        slug_cache[slug] += 1
        slug = f"{slug}_{slug_cache[slug]}"
    slug_cache[slug] = 1
    
    # t = longname.find("&") 
    # s = longname.find(">") 
    # if t > -1 or s > -1:
        # sys.stderr.write(f"{t}-{s} '{longname}' {slug}\n")
    return slug

for r in lines[1:]:
    n +=1
    try:
        r = r.replace("\n","")
        r = r.replace("\r", "")
        cells = r.split(",") # chomp newline
        (name, surname, guest, vfho, mug) = cells[:5]
        years = cells[5:]
    except:
        print(f'Exception in line {n}: {r}')

    expos_caving = len([t for t in years if t == "1"])
    expos_notcaving = len([t for t in years if t == "-1"])
    if(expos_caving == 0 and expos_notcaving == 0):
        sys.stderr.write("Error processing " + name + ". No attendances found\n")
        sys.exit(1)
    if(expos_caving and name != 'Rover Richardson' and name != 'Bier Tent'): headcount += 1
    if mug: pics +=1
    output += '<tr><td>'
    if expos_caving == 0: output += '<span class="didntcave">'
    
    # Need to manage names e.g. <span lang=""sv"">Leif Hornsved (Nickname)</span> => LeifHornsved
    namevis = name.replace('""', '"').strip('"')
    # Need to manage e.g.Olaf K&auml;hler 
    # Need to manage e.g. Bal%26aacute%3BzsIzapy
    # nameurl = namevis.replace(' ', '')
    # nameurl = nameurl.replace('&', '%26')
    # nameurl = nameurl.replace(';', '%3B')

    # new url using slug
    nameurl = troggle_slugify(namevis)
    namelink= "<a href='/person/" + nameurl + "'>" + namevis + "</a>"
    output += namelink
    #output += name.replace('""', '"')
    
    if expos_caving == 0: output += '</span>'
    output += '</td><td>'
    if guest: output += '&sect;'
    output += '</td><td>'
    if vfho: output += '&curren;'
    output += '</td><td>'
    if mug:
        if not (os.path.isfile(mug)):
            print("ERROR: --------------- mug file does not exist: ", mug, file=sys.stderr) 
    if mug: output += f'<a href={mug}><img alt=":-)" src="i/mug.png" /></a>'
    output += '</td>'
    for y in range(len(years)):
        if(years[y]):
            m = str(76 + y)[-2:]
            if(years[y]=='-1'):
                m = '<span class="didntcave">'+ m + '</span>'
            else:
                try:
                    headcounts_byyear[y] += 1
                except IndexError:
                    sys.stderr.write(repr(r) +":::"+ str(y) + "\n")
                    raise
            output += '<td class="nonempty">' + m + '</td>'
        else:
            output += '<td></td>'
        # print number of expos, non-caving in red. Only print numbers > 0
    output += '<td style="text-align: right; width:36px; font-size:85%">'
    if(expos_notcaving):
                if(expos_caving):
                        output += '%d+<span class="didntcave">%d</span>' % (expos_caving, expos_notcaving)
                else:
                        output += '<span class="didntcave">%d</span>' % expos_notcaving
    else:
        output += '%d' % expos_caving
        output += '</td></tr>\n'
    recordholders.append((expos_caving, name))

def collapse(m):
    n = (m.span()[1]-m.span()[0]) / 9
    if(n == 1): return m.group()
    else: return '<td colspan="%d"></td>' % n

#output = re.sub(r'(<td></td>)+',collapse, output)

lastyear=1976+1+len([t for t in headcounts_byyear if t > 0]) # no expo in 1986 or 2020

# moved to main.css
#<style type="text/css">
#.didntcave    { color: #dd0000 }

print("""
<!DOCTYPE html>
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<title>CUCC's Austria expeditions: Members</title>
<link rel="stylesheet" type="text/css" href="../css/main2.css" />
<!--
table.fancy    { border-collapse: collapse; border: 2px solid black } 
table.fancy td    { border: 1px solid black; padding: 2pt }
table.fancy td.nonempty { background: #eee }
-->
</style>
<meta name="keywords" content="NOEDIT">
</head>
<body>

<!-- DO NOT EDIT THIS DOCUMENT BY HAND! It is automatically generated by "scripts/make-folklist.py" -->
<h1>CUCC members and guests in Austria</br> 1976 to %s</h1>
""" % yearnow)

print("""
<p>This is a pretty much complete list of all the personnel on %d CUCC
expeditions (there were no expos in 1986, 2020 or 2021), together with the total number of 
expeditions each has attended and the total number of people on each expedition.</p>

<p>Qualification for inclusion involves some active contribution to the
expedition such as going underground, surface surveying, sherpa-ing, camp-shopping or
diving for resurgences. Years marked in <span class="didntcave">red</span>
indicate some certainty that the person didn't go underground that year.
Persons marked in <span class="didntcave">red</span> are thought to have never
been underground on expo at all. Note that diving in <span lang="de-at">Altausseer 
See</span> for the resurgence has been counted as underground:- it certainly 
counts as effort expended in the pursuit of speleology!</p>

<p>In the table, a section mark (&sect;) indicates someone who was an
individual guest of CUCC or of a CUCC member, or who was a member of UBSS or ULSA when
they were present as guest clubs in 1981,1982 or 2008-onwards or any other clubs in more recent years. 
We don't guarantee to have
got all such people correctly marked. Similarly, the currency symbol (&curren;)
marks those who are (or were) individual members of the local Austrian group
<span lang="de-at">Verein f&uuml;r H&ouml;hlenkunde im Obersteier</span>. A
face icon indicates a link to a mugshot (and brief notes) in our
Rogues' Gallery. Two of the members listed are inanimate objects - no prizes for
guessing which without looking at the photos :-)</p>

<p>The table doesn't include the local cavers who have caved with us at various
times. These include particularly Karl Gaisberger
<a href="i/karl_gaisberger.jpg"><img alt=":-)" src="i/mug.png" /></a>,
Gunter Graf, Arndt Karger, Sepp
Steinberger and Robert Seebacher <a href="i/seebacher2.jpg"><img alt=":-)"
src="i/mug.png" /></a>.</p>
""" % len([t for t in headcounts_byyear if t > 0]))

y2 = lastyear-2
y1 = lastyear-1
print("""
<p>Links to recent expos: <a href="http://expo.survex.com/expedition/%s">previous expo</a>. There was no expo in 1986, 2020 or 2021.  
<hr /><table class="fancy">
""" % y1)

print(output)

print("<tr><td colspan=4><strong>Expo head count</strong></td>", end=' ')
for y in headcounts_byyear:
    print('<td style="text-align: right">%d</td>' % y, end=' ')

print("""
<td></td></tr>
</table>
<hr />

<p>%d people have
taken part in expo altogether (not counting non-combatants or vehicles(!)),
of whom %d have their pictures on the site so far.</p>

<p>Although few take  <a href="/people">such statistics</a> seriously, the most dedicated expoers are """ % (headcount, pics))

recordholders.sort()
recordholders.reverse()
k = 2
while recordholders[k + 1][0] == recordholders[k][0]:
    k = k + 1
print("%s (%d expos)," % (recordholders[0][1],recordholders[0][0]))
for r in recordholders[1:k]:
    print("%s (%d)," % (r[1],r[0]), end=' ')

print("""and %s (%d). Julian Todd holds the record for consecutive
expo attendance (10), (along with Mark Shinwell, but he didn't actually
go caving on all of those visits).  A more obscure record of longest gap between expos has been held by various people since 2004 at 13, and then 17, years, but in 2017 was upped to 34 years by Phil Sargent, which is going to be extremely hard to beat!</p>""" % (recordholders[k][1],recordholders[k][0]))


print("""<p>Outside-expo caving happens from time to time, with Becka Lawson, Neil Pacey, Julian Todd and Wookey
joining various Arge and VfHO trips since about 2000. However, the much talked-about
winter expedition/holiday has still not happened, though there is still a lot
to be said for it. With draughts reversed in the cold, top entrances should
be more obvious and skiing would make a nice change from sitting watching the
rain. Some entrances would inevitably be blocked by snow but others seem to
remain open all winter.</p>

<p>Instructions for updating this page are 
in the online systems handbook at <a href="/handbook/computing/folkupdate.html">new year, new folklist</a>.</p>

<hr />

</body>
</html>""")