In reverse chronological order gopher://tilde.pink/0/~bencollver/fossil/pharos/atom.xml 2026-03-13 16:01:14 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/19efc38ff7/ ben 2026-03-13 16:01:14 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/b9a6b6867b/ ben >] Page %d", page + 1) + label = sprintf("[>>] Page %d", page + 1) sel = sprintf("%s/search?%s/page%d/rows%d/%s", cgipath, search, page + 1, rows, sort_param) item(out, "1", label, sel, server, port) } ]]> 2026-03-13 15:52:34 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/bc5e705008/ ben ", html) print html >work close(work) cmd = sprintf("%s -a -n 3 <%s | %s -ilr -w 60", cmd_strings, work, @@ -150,15 +148,13 @@ } # Print the webdump references section, converting relative URLs # to full URLs -function print_ref_full(str, base, proto, root, link, out, +function print_ref_full(out, str, base, proto, root, link, prefix, relative) { - out = "" - if (match(str, /^ [0-9]+\. /)) { prefix = substr(str, 0, RLENGTH) link = substr(str, RLENGTH + 1) # convert relative links to full URLs if (link !~ /^[a-z]+:/) { ]]> 2026-03-13 15:42:05 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/63de0a047c/ ben ", html) print html >work ]]> 2026-02-21 21:37:49 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/a61deffc58/ ben 2025-11-12 15:26:11 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/93dd35263c/ ben + +# Limits + +This service does not work in the lagrange browser. +Lagrange URI encodes the search string and also +mangles items that are not URI encoded. ]]> 2025-11-09 16:41:29 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/1775faf7c6/ ben 2025-11-09 08:10:45 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/ce71322300/ ben 0) { print str return } - output = cache_begin() + out = cache_begin() iaout = gettemp() url = api_endpoint "/metadata/" acct api_request(url, "GET", iaout) @@ -75,48 +75,46 @@ } } close(cmd) if (length(id) == 0) { - print_not_found(output, url) + print_not_found(out, url) cache_end() unlink(iaout) return } - print "Account: " acct >>output + info(out, "Account: " acct) if (length(thumb) > 0) { url = sprintf("http://%s%s/%s", item_server, dir, thumb) - printf "IThumbnail\t%s/raw/%s\t%s\t%s\n", cgipath, url, - server, port >>output + sel = cgipath "/raw/" url + item(out, "I", "Thumbnail", sel, server, port) } - print_html(output, descr) + print_html(out, descr) if (length(email) > 0) { - prefix = "/sortaddeddate desc" - printf "1Uploads\t%s\tsearch?uploader:%s%s\t%s\t%s\n", cgipath, - email, prefix, server, port >>output - } - - prefix = "/sortaddeddate desc" - printf "1Items\t%s/search?anyfield:%s%s\t%s\t%s\n", cgipath, - acct, prefix, server, port >>output - - printf "1Lists\t%s/lists?%s\t%s\t%s\n", cgipath, acct, server, - port >>output - - print "" >>output - printf "%-20s %s\n", "Identifier:", id >>output - if (item_size > 0) { - printf "%-20s %d\n", "Item Size:", item_size >>output - } - printf "%-20s %s\n", "Media Type:", type >>output - - print "" >>output - printf "hAccount web page\tURL:%s/details?%s\t%s\t%s\n", - api_ssl_endpoint, uri_encode(id), server, port >>output - printf "1PHAROS\t%s\t%s\t%s\n", docpath, server, port >>output + sel = cgipath "/search?uploader:" email "/sortaddeddate desc" + item(out, "1", "Uploads", sel, server, port) + } + + sel = cgipath "/search?anyfield:" acct "/sortaddeddate desc" + item(out, "1", "Items", sel, server, port) + + sel = cgipath "/lists?" acct + item(out, "1", "Lists", sel, server, port) + + info(out, "") + info(out, sprintf("%-20s %s\r\n", "Identifier:", id)) + if (item_size > 0) { + info(out, sprintf("%-20s %d\r\n", "Item Size:", item_size)) + } + info(out, sprintf("%-20s %s\r\n", "Media Type:", type)) + + info(out, "") + sel = sprintf("URL:%s/details?%s", api_ssl_endpoint, uri_encode(id)) + item(out, "h", "Account web page", sel, server, port) + item(out, "1", "PHAROS", docpath, server, port) cache_end() unlink(iaout) exit 0 } Index: src/cgi.awk ================================================================== --- src/cgi.awk +++ src/cgi.awk @@ -1,21 +1,21 @@ function block_msg(ip, extra) { - print "Access Denied" - print "=============" - print "" - print "This service only allows access from vetted client IP addresses." - print "The intent is to thwart abusive bots and crawlers." - print "" - print "To gain access:" - print "" - print "* Email your client IP address (" ip ") to:" - print " " contact - print "" - print "* Include the word \"friendly\" in your message." - print "" - print "Service admin will reply when granted." - print extra + printf "Access Denied\r\n" + printf "=============\r\n" + printf "\r\n" + printf "This service only allows access from vetted client IP addresses.\r\n" + printf "The intent is to thwart abusive bots and crawlers.\r\n" + printf "\r\n" + printf "To gain access:\r\n" + printf "\r\n" + printf "* Email your client IP address (" ip ") to:\r\n" + printf " %s\r\n", contact + printf "\r\n" + printf "* Include the word \"friendly\" in your message.\r\n" + printf "\r\n" + printf "Service admin will reply when granted.\r\n" + printf "%s\r\n", extra return } function cgi_init( extra, ip, item) { ip = ENVIRON["REMOTE_ADDR"] @@ -65,12 +65,12 @@ } close(pass_list) if (blocked) { extra = "" if (topdir == "details") { - extra = "\nIn the meanwhile, see:\n\n" \ - sprintf("hWeb page\tURL:%s/details/%s\t%s\t%s\n", + extra = "\r\nIn the meanwhile, see:\r\n\r\n" \ + sprintf("hWeb page\tURL:%s/details/%s\t%s\t%s\r\n", api_ssl_endpoint, uri_encode(search), server, port) } Index: src/details.m4 ================================================================== --- src/details.m4 +++ src/details.m4 @@ -13,11 +13,11 @@ incl(src/util.awk) incl(src/web.awk) function main( add_date, col, cols, cmd, creator, descr, dir, i, iaout, id, item_id, item_server, item_size, label, language, - license, output, pub_date, scanner, signature, str, thumb, + license, out, pub_date, scanner, sel, signature, str, thumb, title, topic, topics, type, uploader_account, uploader_email, uploader_name, url) { item_id = search @@ -27,11 +27,11 @@ print str return } iaout = gettemp() - output = cache_begin() + out = cache_begin() url = api_endpoint "/metadata/" item_id api_request(url, "GET", iaout) # format search results as a gopher directory (menu) @@ -112,70 +112,71 @@ } } close(cmd) if (length(id) == 0) { - print_not_found(output, url) + print_not_found(out, url) cache_end() unlink(iaout) return } - print shorten(title, 70) >>output + info(out, shorten(title, 70)) if (creators == 1) { label = "by " shorten(creator[1], 70) - printf "1%s\t%ssearch?creator:(%s)\t%s\t%s\n", label, - cgipath, creator[1], server, port >>output + sel = sprintf("%s/search?creator:(%s)", cgipath, creator[1]) + item(out, "1", label, sel, server, port) } else if (creators > 1) { - printf "\nby:\n" >>output + info(out, "") + info(out, "by:") for (i = 1; i <= creators; i++) { label = shorten(creator[i], 70) - printf "1%s\t%s/search?creator:(%s)\t%s\t%s\n", label, - cgipath, creator[i], server, port >>output + sel = sprintf("%s/search?creator:(%s)", cgipath, creator[i]) + item(out, "1", label, sel, server, port) } - printf "\n" >>output + info(out, "") } if (length(thumb) > 0) { url = sprintf("http://%s%s/%s", item_server, dir, thumb) - printf "IThumbnail\t%s/raw?%s\t%s\t%s\n", cgipath, url, - server, port >>output + sel = cgipath "/raw?" url + item(out, "I", "Thumbnail", sel, server, port) } - printf "1Download\t%s/download?%s\t%s\t%s\n", cgipath, item_id, - server, port >>output - printf "hWeb page\tURL:%s/details/%s\t%s\t%s\n", - api_ssl_endpoint, uri_encode(id), server, port >>output - print "" >>output - - print_html(output, descr) - - print "" >>output + sel = cgipath "/download?" item_id + item(out, "1", "Download", sel, server, port) + sel = "URL:" api_ssl_endpoint "/details/" uri_encode(id) + item(out, "h", "Web page", sel, server, port) + info(out, "") + + print_html(out, descr) + + info(out, "") if (length(add_date) > 0) { - printf "%-20s %s\n", "Date Added:", add_date >>output + info(out, sprintf("%-20s %s", "Date Added:", add_date)) } if (pub_date != add_date) { - printf "%-20s %s\n", "Date Published:", pub_date >>output + info(out, sprintf("%-20s %s", "Date Published:", pub_date)) } - printf "%-20s %s\n", "Identifier:", id >>output + info(out, sprintf("%-20s %s", "Identifier:", id)) if (item_size > 0) { - printf "%-20s %d\n", "Item Size:", item_size >>output + info(out, sprintf("%-20s %d", "Item Size:", item_size)) } if (length(language) > 0) { - printf "%-20s %s\n", "Language:", language >>output + info(out, sprintf("%-20s %s", "Language:", language)) } if (length(license) > 0) { - printf "%-20s %s\n", "License:", license >>output + info(out, sprintf("%-20s %s", "License:", license)) } - printf "%-20s %s\n", "Media Type:", type >>output + info(out, sprintf("%-20s %s", "Media Type:", type)) if (topics > 0) { - print "" >>output - print "# Topics" >>output + info(out, "") + info(out, "# Topics") for (i = 1; i <= topics; i++) { label = shorten(topic[i], 40) - printf "1%s\t%s/search?subject:(%s)\t%s\t%s\n", label, - cgipath, topic[i], server, port >>output + sel = sprintf("%s/search?subject:(%s)", cgipath, topic[i]) + item(out, "1", label, sel, server, port) } } # scrape uploader name from item web page HTML url = api_ssl_endpoint "/details/" item_id @@ -190,40 +191,41 @@ } } close(iaout) if (cols > 0) { - print "" >>output - print "# Collections" >>output - for (i = 1; i <= cols; i++) { - label = shorten(col[i], 40) - printf "1%s\t%s/search?collection:(%s)\t%s\t%s\n", - label, cgipath, col[i], server, port >>output - } - } - - print "" >>output - print "# Uploaded by" >>output - if (length(uploader_account) > 0) { - label = shorten(uploader_account, 70) - printf "1%s\t%s/account?%s/%s\t%s\t%s\n", label, cgipath, - uploader_account, uploader_email, server, port >>output - } else if (length(uploader_email) > 0) { - label = shorten(uploader_email, 70) - printf "1%s\t%s/search?uploader:%s\t%s\t%s\n", label, - cgipath, uploader_email, server, port >>output - } else { - printf "%s\n", uploader_name >>output - } - - print "" >>output - print "# Similar items" >>output - printf "1View similar items\t%s/search?similar:%s\t%s\t%s\n", - cgipath, item_id, server, port >>output - - print "" >>output - printf "1PHAROS\t%s\t%s\t%s\n", docpath, server, port >>output + info(out, "") + info(out, "# Collections") + for (i = 1; i <= cols; i++) { + label = shorten(col[i], 40) + sel = sprintf("%s/search?collection:(%s)", cgipath, col[i]) + item(out, "1", label, sel, server, port) + } + } + + info(out, "") + info(out, "# Uploaded by") + if (length(uploader_account) > 0) { + label = shorten(uploader_account, 70) + sel = sprintf("%s/account?%s/%s", cgipath, uploader_account, + uploader_email) + item(out, "1", label, sel, server, port) + } else if (length(uploader_email) > 0) { + label = shorten(uploader_email, 70) + sel = cgipath "/search?uploader:" uploader_email + item(out, "1", label, sel, server, port) + } else { + info(out, uploader_name) + } + + info(out, "") + info(out, "# Similar items") + sel = cgipath "/search?similar:" item_id + item(out, "1", "View similar items", sel, server, port) + + info(out, "") + item(out, "1", "PHAROS", docpath, server, port) cache_end() unlink(iaout) return } Index: src/download.m4 ================================================================== --- src/download.m4 +++ src/download.m4 @@ -9,12 +9,15 @@ incl(src/api.awk) incl(src/cgi.awk) incl(src/util.awk) function main( cmd, files, file_size, format, iaout, is_archive, - is_proxy, item_server, label, mtime, name, source, url) + is_proxy, item_server, label, mtime, name, out, sel, source, + url) { + out = "" + if (topdir == "download") { is_proxy = 1 } else { # topdir == "direct" is_proxy = 0 @@ -64,32 +67,32 @@ strftime("%Y-%m-%d %H:%M", mtime[i]), human_size(file_size[i])) url = sprintf("http://%s%s/%s", item_server, dir, name[i]) if (is_proxy) { if (max_bin_size > 0 && file_size[i] > max_bin_size * size_mb) { - printf "h%s\tURL:%s\t%s\t%s\n", label, uri_encode(url), - server, port + sel = "URL:" uri_encode(url) + item(out, "h", label, sel, server, port) } else { - printf "1%s\t%s/links?%s\t%s\t%s\n", label, cgipath, - url, server, port + sel = cgipath "/links?" url + item(out, "1", label, sel, server, port) } } else { - printf "h%s\tURL:%s\t%s\t%s\n", label, uri_encode(url), - server, port + sel = "URL:" uri_encode(url) + item(out, "h", label, sel, server, port) } is_archive = detect_archive(url) if (is_archive) { url = sprintf("http://%s/view_archive.php?archive=%s/%s", item_server, dir, name[i]) - printf "h%s (View Contents)\tURL:%s\t%s\t%s\n", - shorten_left(name[i], 40), uri_encode(url), - server, port + label = shorten_left(name[i], 40) " (View Contents)" + sel = "URL:" uri_encode(url) + item(out, "h", label, sel, server, port) } } - printf "1Downloads via http\t%s/direct?%s\t%s\t%s\n", cgipath, - search, server, port + sel = cgipath "/direct?" search + item(out, "1", "Downloads via http", sel, server, port) unlink(iaout) exit 0 } Index: src/list.m4 ================================================================== --- src/list.m4 +++ src/list.m4 @@ -12,12 +12,12 @@ incl(src/sqlite.awk) incl(src/util.awk) function main( acct, client_url, cmd, count, creator, iaout, id, is_private, items, label, list_id, name, name_slug, numfound, - order, order_name, order_names, order_param, output, page, pages, - prefix, rows, sort_param, signature, str, title, type, url, + order, order_name, order_names, order_param, out, page, pages, + rows, sel, sort_param, signature, str, title, type, url, user_query) { order_names["creator"] = "creatorSorter" order_names["date"] = "date" order_names["title"] = "titleSorter" @@ -57,11 +57,11 @@ if (length(str) > 0) { print str return } - output = cache_begin() + out = cache_begin() iaout = gettemp() url = api_ssl_endpoint "/services/users/" acct "/lists/" list_id api_request(url, "GET", iaout) @@ -131,14 +131,14 @@ pages++ } # format as a gopher directory (menu) - print acct "'s Lists" >>output - print "" >>output - printf "# List: %s, page %d of %d\n", name, page, pages >>output - print "" >>output + info(out, acct "'s Lists") + info(out, "") + info(out, sprintf("# List: %s, page %d of %d", name, page, pages)) + info(out, "") cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) FS = "\t" count = 0 creator = "" @@ -170,12 +170,12 @@ shorten(title, 40), shorten(creator, 18)) } else { label = sprintf("[%s] %s", mediatype[type], shorten(title, 58)) } - printf "1%s\t%s/details?%s\t%s\t%s\n", label, cgipath, id, - server, port >>output + sel = cgipath "/details?" id + item(out, "1", label, sel, server, port) count++ } creator = "" descr = "" id = "" @@ -182,39 +182,39 @@ type = "" } } close(cmd) - print "" >>output + info(out, "") # only show "page back" if the user is past page 1 if (page > 1) { - prefix = sprintf("/page%d/rows%d/%s", page - 1, rows, sort_param) - printf "1[<<] Page %d\t%s/list?%s/%d%s\t%s\t%s\n", - page - 1, cgipath, acct, list_id, prefix, server, - port >>output + label = sprintf("[<<] Page %d", page - 1) + sel = sprintf("%s/list?%s/%d/page%d/rows%d/%s", cgipath, acct, + list_id, page - 1, rows, sort_param) + item(out, "1", label, sel, server, port) } # only show "next page" if the current page is completely full if (count == rows) { - prefix = sprintf("/page%d/rows%d/%s", page + 1, rows, sort_param) - printf "1[>>] Page %d\t%s/list?%s/%d%s\t%s\t%s\n", - page + 1, cgipath, acct, list_id, prefix, server, - port >>output + label = sprintf("[>>] Page %d", page + 1) + sel = sprintf("%s/list?%s/%d/page%d/rows%d/%s", cgipath, + acct, list_id, page + 1, rows, sort_param) + item(out, "1", label, sel, server, port) } # only show "sort" if there's more than one item to sort if (numfound > 1) { - printf "1[^v] Sort\t%s/listsort?%s/%d\t%s\t%s\n", cgipath, - acct, list_id, server, port >>output + sel = sprintf("%s/listsort?%s/%d", cgipath, acct, list_id) + item(out, "1", "[^v] Sort", sel, server, port) } - printf "1Account %s\t%s/account?%s\t%s\t%s\n", acct, cgipath, - acct, server, port >>output + sel = cgipath "/account?" acct + item(out, "1", "Account " acct, sel, server, port) - print "" >>output - printf "1PHAROS\t%s\t%s\t%s\n", docpath, server, port >>output + info(out, "") + item(out, "1", "PHAROS", docpath, server, port) cache_end() unlink(iaout) exit 0 } Index: src/lists.m4 ================================================================== --- src/lists.m4 +++ src/lists.m4 @@ -10,22 +10,22 @@ incl(src/cache.awk) incl(src/cgi.awk) incl(src/sqlite.awk) incl(src/util.awk) -function main( cmd, count, fields, iaout, i, id, is_private, item, - item_count, item_id, label, name, output, record, records, - signature, str, url) +function main( cmd, count, fields, iaout, i, id, is_private, + item, item_count, item_id, label, labelstr, name, out, record, + records, sel, signature, str, url) { signature = sprintf("%s/lists", search) str = cache_init(signature) if (length(str) > 0) { print str return } - output = cache_begin() + out = cache_begin() iaout = gettemp() url = api_ssl_endpoint "/services/users/" search "/lists" api_request(url, "GET", iaout) @@ -45,14 +45,15 @@ while ((cmd | getline) > 0) { if ($1 == ".value[]" && $2 == "o") { # add information for previous list if (!is_private && length(name) > 0 && item_count > 0) { - label = shorten_left(name, 50) - item = sprintf("1%4d Items: %-50s\t%s/list?%s/%d\t%s\t%s", - item_count, label, cgipath, search, id, server, port) - record = label "\v" id "\v" item + labelstr = shorten_left(name, 50) + label = sprintf("%4d Items: %-50s", item_count, labelstr) + sel = sprintf("%s/list?%s/%d", cgipath, search, id) + item = item_str("1", label, sel, server, port) + record = labelstr "\v" id "\v" item count++ records[count] = record } } else if ($1 == ".value[].list_name" && $2 == "s") { name = $3 @@ -71,35 +72,36 @@ } close(cmd) # add information for previous list if (!is_private && length(name) > 0 && item_count > 0) { - label = shorten_left(name, 50) - item = sprintf("1%4d Items: %-50s\t%s/list?%s/%d\t%s\t%s", - item_count, label, cgipath, search, id, server, port) - record = label "\v" id "\v" item + labelstr = shorten_left(name, 50) + label = sprintf("%4d Items: %-50s", item_count, labelstr) + sel = sprintf("%s/list?%s/%d", cgipath, search, id) + item = item_str("1", label, sel, server, port) + record = labelstr "\v" id "\v" item count++ records[count] = record } # sort lists by label and id if (count > 0) { hsort(records, count) } - print search "'s Lists" >>output - print "" >>output + info(out, search "'s Lists") + info(out, "") for (i = 1; i <= count; i++) { record = records[i] split(record, fields, /\v/) item = fields[3] - print item >>output + printf "%s\r\n", item >>out } - print "" >>output - printf "1PHAROS\t%s\t%s\t%s\n", docpath, server, port >>output + info(out, "") + item(out, "1", "PHAROS", docpath, server, port) cache_end() unlink(iaout) return } Index: src/listsort.m4 ================================================================== --- src/listsort.m4 +++ src/listsort.m4 @@ -5,12 +5,15 @@ # # Change list sort order include(src/config.awk) incl(src/cgi.awk) +incl(src/util.awk) -function main( acct, i, lbl, list_id, opt) { +function main( acct, i, lbl, list_id, opt, out, sel) { + out = "" + lbl[1] = "Relevance" opt[1] = "" lbl[2] = "Weekly views [^]" opt[2] = "week asc" lbl[3] = "Weekly views [v]" @@ -30,19 +33,19 @@ split(search, parts, "/") acct = parts[1] list_id = parts[2] - print "# Sort by" - print "" + info(out, "# Sort by") for (i = 1; i < 10; i++) { if (length(opt[i]) == 0) { - printf "1%s\t%s/list?%s/%d\t%s\t%s\n", lbl[i], cgipath, - acct, list_id, server, port + sel = sprintf("%s/list?%s/%d", cgipath, acct, list_id) + item(out, "1", lbl[i], sel, server, port) } else { - printf "1%s\t%s/list?%s/%d/sort%s\t%s\t%s\n", lbl[i], - cgipath, acct, list_id, opt[i], server, port + sel = sprintf("%s/list?%s/%d/sort%s", cgipath, + acct, list_id, opt[i]) + item(out, "1", lbl[i], sel, server, port) } } exit 0 } Index: src/search.m4 ================================================================== --- src/search.m4 +++ src/search.m4 @@ -8,15 +8,17 @@ include(src/config.awk) incl(src/api.awk) incl(src/cgi.awk) incl(src/util.awk) -function main(search, cmd, count, creator, descr, field, fields, i, - iaout, id, item, items, jsout, label, numfound, order, - order_names, page, prefix, rows, searchstr, sort_param, str, +function main(search, cmd, count, creator, descr, field, fields, + i, iaout, id, item, items, jsout, label, numfound, order, + order_names, out, page, rows, searchstr, sel, sort_param, str, title, type, url) { + out = "" + order_names["addeddate"] = "addeddate" order_names["collection_size"] = "collection_size" order_names["createddate"] = "createddate" order_names["creator"] = "creatorSorter" order_names["date"] = "date" @@ -148,25 +150,25 @@ if (search ~ /^@/) { numfound++ } if (numfound == 0) { - print "Your search did not match any items in the Archive." - print "Try different keywords or a more general search." - print "" - printf "1PHAROS\t%s\t%s\t%s\n", docpath, server, port + info(out, "Your search did not match any items in the Archive.") + info(out, "Try different keywords or a more general search.") + info(out, "") + item(out, "1", "PHAROS", docpath, server, port) unlink(jsout) unlink(iaout) return } else { pages = int(numfound / rows) if (numfound % rows != 0) { pages++ } - printf "# %s search results, page %d of %d\n", numfound, - page, pages - print "" + info(out, sprintf("# %s search results, page %d of %d", + numfound, page, pages)) + info(out, "") } # format search results as a gopher directory (menu) FS = "\t" creator = "" @@ -175,12 +177,12 @@ title = "" type = "" count = 0 if (search ~ /^@/) { - printf "1Account %s\t%s/account?%s\t%s\t%s\n", search, cgipath, - search, server, port + sel = cgipath "/account?" search + item(out, "1", "Account " search, sel, server, port) } while ((getline 0) { if ($1 == ".response.docs[].creator" && $2 == "s") { creator = $3 @@ -200,53 +202,55 @@ } else { label = sprintf("[%s] %s", mediatype[type], shorten(title, 58)) } if (type == "collection") { - printf "1%s\t%s/search?collection:(%s)\t%s\t%s\n", - label, cgipath, id, server, port + sel = sprintf("%s/search?collection:(%s)", cgipath, id) + item(out, "1", label, sel, server, port) } else { - printf "1%s\t%s/details?%s\t%s\t%s\n", label, cgipath, - id, server, port + sel = cgipath "/details?" id + item(out, "1", label, sel, server, port) } creator = "" descr = "" id = "" type = "" } } close(jsout) - print "" + info(out, "") # only show "page back" if the user is past page 1 if (page > 1) { - prefix = sprintf("/page%d/rows%d/%s", page - 1, rows, sort_param) - printf "1[<<] Page %d\t%s/search?%s%s\t%s\t%s\n", - page - 1, cgipath, search, prefix, server, port + label = sprintf("[<<] Page %d", page - 1) + sel = sprintf("%s/search?%s/page%d/rows%d/%s", cgipath, + search, page - 1, rows, sort_param) + item(out, "1", label, sel, server, port) } # only show "next page" if the current page is completely full if (count == rows) { - prefix = sprintf("/page%d/rows%d/%s", page + 1, rows, sort_param) - printf "1[>>] Page %d\t%s/search?%s%s\t%s\t%s\n", - page + 1, cgipath, search, prefix, server, port + label = sprintf("1[>>] Page %d", page + 1) + sel = sprintf("%s/search?%s/page%d/rows%d/%s", cgipath, + search, page + 1, rows, sort_param) + item(out, "1", label, sel, server, port) } # only show "sort" if there's more than one item to sort if (count > 1) { - printf "1[^v] Sort\t%s/sort?%s\t%s\t%s\n", cgipath, - search, server, port + sel = cgipath "/sort?" search + item(out, "1", "[^v] Sort", sel, server, port) } # only show "search within list" if there's multiple pages of results if (numfound > rows) { - printf "1[\\/] Filter results\t%s/wizard/step1?%s\t%s\t%s\n", - cgipath, search, server, port + sel = cgipath "/wizard/step1?" search + item(out, "1", "[\\/] Filter results", sel, server, port) } - printf "1PHAROS\t%s\t%s\t%s\n", docpath, server, port + item(out, "1", "PHAROS", docpath, server, port) unlink(jsout) unlink(iaout) exit 0 } Index: src/sort.m4 ================================================================== --- src/sort.m4 +++ src/sort.m4 @@ -42,14 +42,14 @@ lbl[16] = "Creator [v]" opt[16] = "creator desc" lbl[17] = "Random" opt[17] = "random asc" - print "# Sort by" - print "" + printf "# Sort by\r\n" + printf "\r\n" for (i = 1; i < 18; i++) { - printf "1%s\t%s/search?%s/sort%s\t%s\t%s\n", + printf "1%s\t%s/search?%s/sort%s\t%s\t%s\r\n", lbl[i], cgipath, search, opt[i], server, port } exit 0 } Index: src/sqlite.awk ================================================================== --- src/sqlite.awk +++ src/sqlite.awk @@ -7,11 +7,11 @@ printf "%s;\n", query >>sqlcfg close(sqlcfg) cmd = sprintf("%s -batch -line -safe -init \"%s\" \"%s\" .quit 2>&1", cmd_sqlite, sqlcfg, db) while ((cmd | getline) > 0) { - retval = retval $0 "\n" + retval = retval $0 "\r\n" } close(cmd) unlink(sqlcfg) return retval } Index: src/util.awk ================================================================== --- src/util.awk +++ src/util.awk @@ -42,15 +42,15 @@ while ((cmd_mktemp | getline) > 0) { retval = $0 } result = close(cmd_mktemp) if (result != 0) { - print "Error: mktemp failed exit status: " result + info("", "Error: mktemp failed exit status: " result) exit } if (length(retval) == 0) { - print "Error: mktemp failed, no tmpfile" + info("", "Error: mktemp failed, no tmpfile") exit } return retval } @@ -110,30 +110,53 @@ retval = sprintf("%dB", bytes) } return retval } -function print_not_found(output, url) { - print "Item cannot be found" >>output - print "" >>output - print "Items may be taken down for various reasons," >>output - print "including by decision of the uploader or" >>output - print "due to a violation of the Terms of Use." >>output - print "" >>output - printf "hMetadata\tURL:%s\t%s\t%s\n", url, server, port >>output - print "" >>output +function info(out, str) { + if (length(out) == 0) { + printf "i%s\t\t\t\r\n", str + } else { + printf "i%s\t\t\t\r\n", str >>out + } + return +} + +function item(out, type, label, sel, host, port, line) { + line = item_str(type, label, sel, host, port) + if (length(out) == 0) { + printf "%s\r\n", line + } else { + printf "%s\r\n", line >>out + } + return +} + +function item_str(type, label, sel, host, port) { + retval = sprintf("%s%s\t%s\t%s\t%s", type, label, sel, host, port) + return retval +} + +function print_not_found(out, url) { + info(out, "Item cannot be found") + info(out, "") + info(out, "Items may be taken down for various reasons,") + info(out, "including by decision of the uploader or") + info(out, "due to a violation of the Terms of Use.") + info(out, "") + item(out, "h", "Metadata", "URL:" url, server, port) + info(out, "") url = api_ssl_endpoint "/about/terms.php" - printf "0Terms of Use\t%s/text?%s\t%s\t%s\n", cgipath, - url, server, port >>output - print "" >>output - printf "1PHAROS\t%s\t%s\t%s\n", docpath, server, port >>output + item(out, "0", "Terms of Use", cgipath "/text?" url, server, port) + info(out, "") + item(out, "1", "PHAROS", docpath, server, port) return } function read_file(name, retval) { while ((getline 0) { - retval = retval $0 "\n" + retval = retval $0 "\r\n" } close(name) return retval } Index: src/web.awk ================================================================== --- src/web.awk +++ src/web.awk @@ -1,13 +1,16 @@ -function dump(search, type, base, cmd, curlcfg, is_html, is_image, - label, limit, link, marker, parts, proto, relative, root, url) +function dump(search, type, base, cmd, curlcfg, is_html, + is_image, label, limit, link, marker, out, parts, proto, + relative, root, sel, url) { + out = "" + url = search gsub(/%3F/, "?", url) if (url !~ /^(http|https):\/\/[[:alnum:].-]+(:[0-9]+)*(\/[[:alnum:].,?@~=%%:\/+&_() -]*)*$/) { - printf "Error: Unacceptable URL \"%s\"\r\n", url + info(out, sprintf("Error: Unacceptable URL \"%s\"", url)) return } if (type == TYPE_HEADERS || type == TYPE_RAW) { limit = max_bin_size @@ -72,35 +75,34 @@ # line numbers larger than the marker are referenced links marker = 999999 if (type == TYPE_LINKS) { + sel = cgipath "/raw?" search + is_html = detect_html(url) is_image = detect_image(url) - printf "9Binary download\t%s/raw?%s\t%s\t%s\n", cgipath, - search, server, port + item(out, "9", "Binary download", sel, server, port) if (is_image) { - printf "IImage view\t%s/raw?%s\t%s\t%s\n", cgipath, - search, server, port + item(out, "I", "Image view", sel, server, port) } if (is_html) { label = "Source" } else { label = "Text view" } - printf "0%s\t%s/raw?%s\t%s\t%s\n", label, cgipath, search, - server, port + item(out, "0", label, sel, server, port) if (is_html) { label = "HTML view" } else { label = "Strings" } - printf "0%s\t%s/text?%s\t%s\t%s\n", label, cgipath, - search, server, port - printf "0Headers\t%s/debug?%s\t%s\t%s\n", cgipath, - search, server, port - print "" + sel = cgipath "/text?" search + item(out, "0", label, sel, server, port) + sel = cgipath "/debug?" search + item(out, "0", "Headers", sel, server, port) + info(out, "") } while ((cmd | getline) > 0) { if (NR < marker) { if ($0 ~ /^References$/) { @@ -118,11 +120,13 @@ unlink(curlcfg) return } -function print_html(output, html, cmd, marker, work) { +function print_html(out, html, cmd, marker, out, work) { + out = "" + work = gettemp() gsub(/\\n/, "
", html) print html >work close(work) cmd = sprintf("%s -a -n 3 <%s | %s -ilr -w 60", cmd_strings, work, @@ -133,13 +137,13 @@ gsub(/\\t/, " ") if (NR < marker) { if ($0 ~ /^References$/) { marker = NR } - print >>output + info(out, $0) } else { - print_ref_pharos(output, $0) + print_ref_pharos(out, $0) } } close(cmd) unlink(work) return @@ -146,11 +150,15 @@ } # Print the webdump references section, converting relative URLs # to full URLs -function print_ref_full(str, base, proto, root, link, prefix, relative) { +function print_ref_full(str, base, proto, root, link, out, + prefix, relative) +{ + out = "" + if (match(str, /^ [0-9]+\. /)) { prefix = substr(str, 0, RLENGTH) link = substr(str, RLENGTH + 1) # convert relative links to full URLs if (link !~ /^[a-z]+:/) { @@ -162,22 +170,22 @@ link = root relative } else { link = base "/" relative } } - print prefix link + info(out, prefix link) } else { - print str + info(out, str) } return } # Print the webdump references section, translating archive.org URLs to # pharos URLs -function print_ref_pharos(output, str, id, label, link, prefix, +function print_ref_pharos(out, str, id, label, link, prefix, relative, token) { if (match(str, /^ [0-9]+\. /)) { prefix = substr(str, 0, RLENGTH) link = substr(str, RLENGTH + 1) @@ -190,17 +198,16 @@ id = substr(id, 1, RSTART - 1) } } if (length(id) > 0) { label = prefix id - printf "1%s\t%s/details?%s\t%s\t%s\n", label, cgipath, - id, server, port >>output + item(out, "1", label, cgipath "/details?" id, server, port) } else { - print str >>output + info(out, str) } } else { - print str >>output + info(out, str) } return } function web_init() { Index: src/wizard/step1.m4 ================================================================== --- src/wizard/step1.m4 +++ src/wizard/step1.m4 @@ -5,12 +5,15 @@ # # Select field to filter/search by include(src/config.awk) incl(src/cgi.awk) +incl(src/util.awk) -function main( i, lbl, opt) { +function main( i, lbl, opt, out, sel) { + out = "" + lbl[1] = "Any field contains" opt[1] = "anyfield" lbl[2] = "Any field does not contain" opt[2] = "-anyfield" lbl[3] = "Title contains" @@ -38,22 +41,22 @@ lbl[14] = "Language contains" opt[14] = "language" lbl[15] = "Always available" opt[15] = "-access-restricted-item" - print "# Search wizard: Select field" - print "" + info(out, "# Search wizard: Select field") + info(out, "") for (i = 1; i < 16; i++) { if (opt[i] ~ /mediatype$/) { - printf "1%s\t%s/wizard/step2?%s/%s\t%s\t%]\n", - lbl[i], cgipath, search, opt[i], server, port + sel = sprintf("%s/wizard/step2?%s/%s", cgipath, search, opt[i]) + item(out, "1", lbl[i], sel, server, port) } else if (lbl[i] == "Always available") { - printf "1%s\t%s/wizard/step3?%s/%s/true\t%s\t%s\n", - lbl[i], cgipath, search, opt[i], server, port + sel = sprintf("%s/wizard/step3?%s/%s", cgipath, search, opt[i]) + item(out, "1", lbl[i], sel, server, port) } else { - printf "7%s\t%s/wizard/step3?%s/%s\t%s\t%s\n", - lbl[i], cgipath, search, opt[i], server, port + sel = sprintf("%s/wizard/step3?%s/%s", cgipath, search, opt[i]) + item(out, "7", lbl[i], sel, server, port) } } exit 0 } Index: src/wizard/step2.m4 ================================================================== --- src/wizard/step2.m4 +++ src/wizard/step2.m4 @@ -5,21 +5,25 @@ # # Select mediatype to filter/search by include(src/config.awk) incl(src/cgi.awk) +incl(src/util.awk) + +function main( field, newsearch, out, searchstr, sel) { + out = "" -function main( field, newsearch, searchstr) { - field = parts[4] - searchstr = parts[5] + split(search, parts, "/") + searchstr = parts[1] + field = parts[2] if (field == "mediatype") { - print "# Mediatype is:" + info(out, "# Mediatype is:") } else { - print "# Mediatype does not contain:" + info(out, "# Mediatype does not contain:") } - print "" + info(out, "") lbl[1] = "audio" lbl[2] = "collection" lbl[3] = "data" lbl[4] = "etree" @@ -32,20 +36,20 @@ if (length(searchstr) == 0) { newsearch = sprintf("%s:(%s)", field, lbl[i]) } else { newsearch = sprintf("%s AND %s:(%s)", searchstr, field, lbl[i]) } - printf "1%s\t%s/search?%s\t%s\t%s\n", lbl[i], cgipath, - newsearch, server, port + sel = cgipath "/search?" newsearch + item(out, "1", lbl[i], sel, server, port) } - print "# Progress:" - print "" - print "* Field: Mediatype" + info(out, "# Progress:") + info(out, "") + info(out, "* Field: Mediatype") exit 0 } BEGIN { config_init() cgi_init() main() } Index: src/wizard/step3.m4 ================================================================== --- src/wizard/step3.m4 +++ src/wizard/step3.m4 @@ -5,12 +5,17 @@ # # Apply new search terms include(src/config.awk) incl(src/cgi.awk) +incl(src/util.awk) -function main( field, label, newsearch, op, searchstr, value) { +function main( field, label, newsearch, op, out, searchstr, + sel, value) +{ + out = "" + split(search, parts, "/") searchstr = parts[1] field = parts[2] value = searchreq @@ -24,22 +29,22 @@ if (length(searchstr) == 0) { newsearch = sprintf("%s:(%s)", field, value) } else { newsearch = sprintf("%s AND %s:(%s)", searchstr, field, value) } - print "" - printf "1Apply search criteria\t%s/search?%s\t%s\t%s\n", - cgipath, newsearch, server, port - print "" - print "# Progress:" - print "" - printf "* Field %s %s %s\n", label, op, value - printf "* New search: %s\n", newsearch + info(out, "") + sel = cgipath "/search?" newsearch + item(out, "1", "Apply search criteria", sel, server, port) + info(out, "") + info(out, "# Progress:") + info(out, "") + info(out, sprintf("* Field %s %s %s", label, op, value)) + info(out, "* New search: " newsearch) exit 0 } BEGIN { config_init() cgi_init() main() } ]]> 2025-11-09 08:04:54 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/d227c24798/ ben 0) { if ($1 == ".dir" && $2 == "s") { dir = $3 } else if ($1 == ".files[].name" && $2 == "s") { if ($3 == "__ia_thumb.jpg") { @@ -176,14 +179,16 @@ # scrape uploader name from item web page HTML url = api_ssl_endpoint "/details/" item_id api_request(url, "GET", iaout) while ((getline 0) { - if (/item-upload-info__uploader-name/ && - match($0, /\/details\/[^"]*"/)) - { - uploader_account = substr($0, RSTART + 9, RLENGTH - 10) + if (match($0, /item-upload-info__uploader-name/)) { + if (match($0, /\/details\/[^"]*"/)) { + uploader_account = substr($0, RSTART + 9, RLENGTH - 10) + } else if (match($0, />[^<]*<\/span>/)) { + uploader_name = substr($0, RSTART + 1, RLENGTH - 8) + } } } close(iaout) if (cols > 0) { @@ -200,14 +205,16 @@ print "# Uploaded by" >>output if (length(uploader_account) > 0) { label = shorten(uploader_account, 70) printf "1%s\t%s/account?%s/%s\t%s\t%s\n", label, cgipath, uploader_account, uploader_email, server, port >>output - } else { + } else if (length(uploader_email) > 0) { label = shorten(uploader_email, 70) printf "1%s\t%s/search?uploader:%s\t%s\t%s\n", label, cgipath, uploader_email, server, port >>output + } else { + printf "%s\n", uploader_name >>output } print "" >>output print "# Similar items" >>output printf "1View similar items\t%s/search?similar:%s\t%s\t%s\n", ]]> 2025-11-09 05:17:04 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/bb37a3f41a/ ben 2025-11-09 01:49:45 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/115c28f054/ ben 2025-11-09 01:45:28 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/3a0e244b15/ ben 2025-11-09 01:43:04 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/093031141d/ ben $out ..." m4 $in >$out return } @@ -25,11 +24,11 @@ books/gophermap \ images/gophermap \ software/gophermap \ video/gophermap do - build_gophermap $SRC ${SRC}/${f}.m4 ${DST}/$f + build_gophermap ${SRC}/${f}.m4 ${DST}/$f done # CGI for f in account \ @@ -43,18 +42,18 @@ sort \ wizard/step1 \ wizard/step2 \ wizard/step3 do - build_cgi $SRC ${SRC}/${f}.m4 ${CGI}/$f + build_cgi ${SRC}/${f}.m4 ${CGI}/$f done # special cases -build_cgi $SRC ${SRC}/raw.m4 ${CGI}/debug -build_cgi $SRC ${SRC}/raw.m4 ${CGI}/text -build_cgi $SRC ${SRC}/download.m4 ${CGI}/direct -build_cgi $SRC ${SRC}/raw.m4 ${CGI}/links +build_cgi ${SRC}/raw.m4 ${CGI}/debug +build_cgi ${SRC}/raw.m4 ${CGI}/text +build_cgi ${SRC}/download.m4 ${CGI}/direct +build_cgi ${SRC}/raw.m4 ${CGI}/links cp ${SRC}/wizard/gophermap ${CGI}/wizard/ cp pass.tsv ${DST}/pass.tsv exit 0 ]]> 2025-11-09 01:30:25 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/db8f1b59d9/ ben 2025-11-09 01:27:39 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/95f091eb5b/ ben $out && chmod a+rx $out" - m4 $in >$out && chmod a+rx $out -} - -# PLAIN -for f in index.gph \ - account/index.dcgi \ - audio/index.gph \ - books/index.gph \ - images/index.gph \ - details/index.dcgi \ - download/index.dcgi \ - list/index.dcgi \ - lists/index.dcgi \ - listsort/index.dcgi \ - raw/index.cgi \ - search/index.dcgi \ - software/index.gph \ - sort/index.dcgi \ - video/index.gph \ - wizard/step1/index.dcgi \ - wizard/step2/index.dcgi \ - wizard/step3/index.dcgi -do - build $SRC ${SRC}/${f}.m4 ${DESTDIR}/$f -done - -# WEIRD -build $SRC ${SRC}/raw/index.cgi.m4 ${DESTDIR}/debug/index.cgi -build $SRC ${SRC}/raw/index.cgi.m4 ${DESTDIR}/text/index.cgi -build $SRC ${SRC}/download/index.dcgi.m4 ${DESTDIR}/direct/index.dcgi -build $SRC ${SRC}/raw/index.cgi.m4 ${DESTDIR}/links/index.dcgi -cp pass.tsv ${DESTDIR}/pass.tsv + echo "m4 $in >$out ..." + m4 $in >$out + return +} + +# gophermaps + +for f in gophermap \ + audio/gophermap \ + books/gophermap \ + images/gophermap \ + software/gophermap \ + video/gophermap +do + build_gophermap $SRC ${SRC}/${f}.m4 ${DST}/$f +done + +# CGI + +for f in account \ + details \ + download \ + list \ + lists \ + listsort \ + raw \ + search \ + sort \ + wizard/step1 \ + wizard/step2 \ + wizard/step3 +do + build_cgi $SRC ${SRC}/${f}.m4 ${CGI}/$f +done + +# special cases + +build_cgi $SRC ${SRC}/raw.m4 ${CGI}/debug +build_cgi $SRC ${SRC}/raw.m4 ${CGI}/text +build_cgi $SRC ${SRC}/download.m4 ${CGI}/direct +build_cgi $SRC ${SRC}/raw.m4 ${CGI}/links +cp ${SRC}/wizard/gophermap ${CGI}/wizard/ + +cp pass.tsv ${DST}/pass.tsv exit 0 DELETED pharos/about.txt Index: pharos/about.txt ================================================================== --- pharos/about.txt +++ /dev/null @@ -1,36 +0,0 @@ -# About PHAROS - -Proxy Internet Archive to gopher. - -# Search - -Example: To find Indian music, excluding commercial samples. - - description:(indian) AND -collection:samples_only AND - mediatype:audio AND subject:music - -# Fields - -* date: - YYYY-MM-DD or [YYYY-MM-DD TO YYYY-MM-DD] -* mediatype: - audio, collection, data, image, movies, software, texts, or web - -# Media type key for search results - -* [aud] = audio or etree -* [col] = collection -* [dat] = data -* [img] = image -* [mov] = movies -* [bin] = software -* [txt] = texts -* [web] = web - -See also: - -# Limits - -This service does not work in the lagrange browser. -Lagrange URI encodes the search string and also -mangles items that are not URI encoded. DELETED pharos/account/index.dcgi Index: pharos/account/index.dcgi ================================================================== --- pharos/account/index.dcgi +++ /dev/null DELETED pharos/audio/index.gph Index: pharos/audio/index.gph ================================================================== --- pharos/audio/index.gph +++ /dev/null DELETED pharos/books/index.gph Index: pharos/books/index.gph ================================================================== --- pharos/books/index.gph +++ /dev/null DELETED pharos/debug/index.cgi Index: pharos/debug/index.cgi ================================================================== --- pharos/debug/index.cgi +++ /dev/null DELETED pharos/details/index.dcgi Index: pharos/details/index.dcgi ================================================================== --- pharos/details/index.dcgi +++ /dev/null DELETED pharos/direct/index.dcgi Index: pharos/direct/index.dcgi ================================================================== --- pharos/direct/index.dcgi +++ /dev/null DELETED pharos/download/index.dcgi Index: pharos/download/index.dcgi ================================================================== --- pharos/download/index.dcgi +++ /dev/null DELETED pharos/images/index.gph Index: pharos/images/index.gph ================================================================== --- pharos/images/index.gph +++ /dev/null DELETED pharos/index.gph Index: pharos/index.gph ================================================================== --- pharos/index.gph +++ /dev/null DELETED pharos/links/index.dcgi Index: pharos/links/index.dcgi ================================================================== --- pharos/links/index.dcgi +++ /dev/null DELETED pharos/list/index.dcgi Index: pharos/list/index.dcgi ================================================================== --- pharos/list/index.dcgi +++ /dev/null DELETED pharos/lists/index.dcgi Index: pharos/lists/index.dcgi ================================================================== --- pharos/lists/index.dcgi +++ /dev/null DELETED pharos/listsort/index.dcgi Index: pharos/listsort/index.dcgi ================================================================== --- pharos/listsort/index.dcgi +++ /dev/null DELETED pharos/raw/index.cgi Index: pharos/raw/index.cgi ================================================================== --- pharos/raw/index.cgi +++ /dev/null DELETED pharos/search/index.dcgi Index: pharos/search/index.dcgi ================================================================== --- pharos/search/index.dcgi +++ /dev/null DELETED pharos/software/index.gph Index: pharos/software/index.gph ================================================================== --- pharos/software/index.gph +++ /dev/null DELETED pharos/sort/index.dcgi Index: pharos/sort/index.dcgi ================================================================== --- pharos/sort/index.dcgi +++ /dev/null DELETED pharos/text/index.cgi Index: pharos/text/index.cgi ================================================================== --- pharos/text/index.cgi +++ /dev/null DELETED pharos/video/index.gph Index: pharos/video/index.gph ================================================================== --- pharos/video/index.gph +++ /dev/null DELETED pharos/wizard/index.gph Index: pharos/wizard/index.gph ================================================================== --- pharos/wizard/index.gph +++ /dev/null @@ -1,10 +0,0 @@ - , _ - /| | | - _/_\_ >_< - .-\-/. | - / | | \_ | - \ \| |\__(/ - /(`---') | - / / \ | - _.' \'-' / | - `----'`=-=' ' hjw DELETED pharos/wizard/step1/index.dcgi Index: pharos/wizard/step1/index.dcgi ================================================================== --- pharos/wizard/step1/index.dcgi +++ /dev/null DELETED pharos/wizard/step2/index.dcgi Index: pharos/wizard/step2/index.dcgi ================================================================== --- pharos/wizard/step2/index.dcgi +++ /dev/null DELETED pharos/wizard/step3/index.dcgi Index: pharos/wizard/step3/index.dcgi ================================================================== --- pharos/wizard/step3/index.dcgi +++ /dev/null Index: readme.txt ================================================================== --- readme.txt +++ readme.txt @@ -1,47 +1,50 @@ PHAROS by Ben Collver ============================================= + * Description * Requirements * Configuration * Installation Description =========== + Pharos is a gopher front-end to the Internet Archive written in AWK. It is named after the light-house island near Alexandria. -For a description and screenshots from an earlier version, see my -post linked below. - - - - - Requirements ============ -* Runs under the Geomyidae gopher server. - + +* Runs under the Gophernicus gopher server. + * Written in AWK. Tested using busybox awk. * Commands used: * env, mktemp, rm, strings, xargs * curl * json2tsv * webdump Configuration ============= + To set configuration variables, edit config.m4 AWK_EXT allows use of non-standard features in gawk and mawk CACHE_ENABLED caches content in sqlite to reduce API calls Installation ============ -Installation depends on m4. + +Installation depends on m4. I use m4 to achieve a portable module +system in any major awk. Gawk has @include() but that isn't +portable. The make.sh script process the source code and generates +the CGI files based on the settings in config.m4. + + $ sh clean.sh + $ sh make.sh -$ sh clean.sh -$ sh make.sh +Copy cgi/* into the CGI directory. +Copy gopher/* into a gopher directory. -Copy pharos/ into place +This separation between CGI and gophermaps is necessary because +dynamic gophermaps not binary-safe in gophernicus. ADDED src/account.m4 Index: src/account.m4 ================================================================== --- /dev/null +++ src/account.m4 @@ -0,0 +1,130 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# __CGIPATH__/account +# +# Show details for an account + +include(src/config.awk) +incl(src/api.awk) +incl(src/cache.awk) +incl(src/cgi.awk) +incl(src/sqlite.awk) +incl(src/util.awk) +incl(src/web.awk) + +function main( acct, cmd, col, cols, count, descr, dir, email, + iaout, id, item_server, item_size, output, prefix, signature, + str, thumb, title, type, url) +{ + count = split(search, parts, "/") + acct = parts[1] + email = parts[2] + + signature = sprintf("account/%s/%s", acct, email) + str = cache_init(signature) + if (length(str) > 0) { + print str + return + } + + output = cache_begin() + iaout = gettemp() + + url = api_endpoint "/metadata/" acct + api_request(url, "GET", iaout) + + # format search results as a gopher directory (menu) + cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) + FS = "\t" + cols = 0 + delete col + descr = "" + dir = "" + id = "" + item_server = "" + item_size = 0 + title = "" + thumb = "" + type = "" + while ((cmd | getline) > 0) { + if ($1 == ".dir" && $2 == "s") { + dir = $3 + } else if ($1 == ".files[].name" && $2 == "s") { + if ($3 == "__ia_thumb.jpg") { + thumb = $3 + } + } else if ($1 == ".item_size" && $2 == "n") { + item_size = $3 + } else if ($1 == ".metadata.collection" && $2 == "s") { + cols++ + col[cols] = $3 + } else if ($1 == ".metadata.collection[]" && $2 == "s") { + cols++ + col[cols] = $3 + } else if ($1 == ".metadata.description" && $2 == "s") { + descr = $3 + } else if ($1 == ".metadata.identifier" && $2 == "s") { + id = $3 + } else if ($1 == ".metadata.mediatype" && $2 == "s") { + type = $3 + } else if ($1 == ".metadata.title" && $2 == "s") { + title = $3 + } else if ($1 == ".server" && $2 == "s") { + item_server = $3 + } + } + close(cmd) + + if (length(id) == 0) { + print_not_found(output, url) + cache_end() + unlink(iaout) + return + } + + print "Account: " acct >>output + if (length(thumb) > 0) { + url = sprintf("http://%s%s/%s", item_server, dir, thumb) + printf "IThumbnail\t%s/raw/%s\t%s\t%s\n", cgipath, url, + server, port >>output + } + print_html(output, descr) + + if (length(email) > 0) { + prefix = "/sortaddeddate desc" + printf "1Uploads\t%s\tsearch?uploader:%s%s\t%s\t%s\n", cgipath, + email, prefix, server, port >>output + } + + prefix = "/sortaddeddate desc" + printf "1Items\t%s/search?anyfield:%s%s\t%s\t%s\n", cgipath, + acct, prefix, server, port >>output + + printf "1Lists\t%s/lists?%s\t%s\t%s\n", cgipath, acct, server, + port >>output + + print "" >>output + printf "%-20s %s\n", "Identifier:", id >>output + if (item_size > 0) { + printf "%-20s %d\n", "Item Size:", item_size >>output + } + printf "%-20s %s\n", "Media Type:", type >>output + + print "" >>output + printf "hAccount web page\tURL:%s/details?%s\t%s\t%s\n", + api_ssl_endpoint, uri_encode(id), server, port >>output + printf "1PHAROS\t%s\t%s\t%s\n", docpath, server, port >>output + + cache_end() + unlink(iaout) + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + uri_encode_init() + main() +} DELETED src/account/index.dcgi.m4 Index: src/account/index.dcgi.m4 ================================================================== --- src/account/index.dcgi.m4 +++ /dev/null @@ -1,126 +0,0 @@ -include(config.m4)dnl -#!__CMD_AWK__ -f - -# account/index.dcgi -# -# Show details for an account - -include(src/config.awk) -incl(src/api.awk) -incl(src/cache.awk) -incl(src/cgi.awk) -incl(src/sqlite.awk) -incl(src/util.awk) -incl(src/web.awk) - -function main( acct, cmd, col, cols, descr, dir, email, iaout, id, - item_server, item_size, output, signature, str, thumb, title, - type, url) -{ - acct = parts[3] - email = search - - signature = sprintf("account/%s/%s", acct, email) - str = cache_init(signature) - if (length(str) > 0) { - print str - return - } - - output = cache_begin() - iaout = gettemp() - - url = api_endpoint "/metadata/" acct - api_request(url, "GET", iaout) - - # format search results as a gopher directory (menu) - cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) - FS = "\t" - cols = 0 - delete col - descr = "" - dir = "" - id = "" - item_server = "" - item_size = 0 - title = "" - thumb = "" - type = "" - while ((cmd | getline) > 0) { - if ($1 == ".dir" && $2 == "s") { - dir = $3 - } else if ($1 == ".files[].name" && $2 == "s") { - if ($3 == "__ia_thumb.jpg") { - thumb = $3 - } - } else if ($1 == ".item_size" && $2 == "n") { - item_size = $3 - } else if ($1 == ".metadata.collection" && $2 == "s") { - cols++ - col[cols] = $3 - } else if ($1 == ".metadata.collection[]" && $2 == "s") { - cols++ - col[cols] = $3 - } else if ($1 == ".metadata.description" && $2 == "s") { - descr = $3 - } else if ($1 == ".metadata.identifier" && $2 == "s") { - id = $3 - } else if ($1 == ".metadata.mediatype" && $2 == "s") { - type = $3 - } else if ($1 == ".metadata.title" && $2 == "s") { - title = $3 - } else if ($1 == ".server" && $2 == "s") { - item_server = $3 - } - } - close(cmd) - - if (length(id) == 0) { - print_not_found(output, url) - cache_end() - unlink(iaout) - return - } - - print "Account: " acct >>output - if (length(thumb) > 0) { - url = sprintf("http://%s%s/%s", item_server, dir, thumb) - printf "[I|Thumbnail|%s/raw/%%09%s|%s|%s]\n", cgipath, url, - server, port >>output - } - print_html(output, descr) - - if (length(email) > 0) { - printf "[1|Uploads|%s/search/sortaddeddate desc%%09uploader:%s|" \ - "%s|%s]\n", - cgipath, email, server, port >>output - } - printf "[1|Items|%s/search/sortaddeddate desc%%09anyfield:%s|%s|%s]\n", - cgipath, acct, server, port >>output - printf "[1|Lists|%s/lists/%%09%s|%s|%s]\n", cgipath, acct, - server, port >>output - - print "" >>output - printf "%-20s %s\n", "Identifier:", id >>output - if (item_size > 0) { - printf "%-20s %d\n", "Item Size:", item_size >>output - } - printf "%-20s %s\n", "Media Type:", type >>output - - print "" >>output - printf "[h|Account web page|URL:%s/details/%s|%s|%s]\n", - api_ssl_endpoint, uri_encode(id), server, port >>output - printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port >>output - - cache_end() - unlink(iaout) - exit 0 -} - -BEGIN { - config_init() - - cgi_init() - uri_encode_init() - main() -} ADDED src/audio/gophermap.m4 Index: src/audio/gophermap.m4 ================================================================== --- /dev/null +++ src/audio/gophermap.m4 @@ -0,0 +1,21 @@ +include(config.m4)dnl +# Audio + +[1|All Audio|__CGIPATH__/search/sortweek desc/%09mediatype:audio|__SERVER__|__PORT__] +[1|This Just In|__CGIPATH__/search/sortaddeddate desc/%09mediatype:audio|__SERVER__|__PORT__] +[1|Live Music Archive|__CGIPATH__/search/sortweek desc/%09collection:etree AND mediatype:collection|__SERVER__|__PORT__] +[1|Librivox Free Audiobooks|__CGIPATH__/search/sortweek desc/%09collection:librivoxaudio|__SERVER__|__PORT__] +[1|Grateful Dead|__CGIPATH__/search/sortweek desc/%09collection:GratefulDead|__SERVER__|__PORT__] +[1|Netlabels|__CGIPATH__/search/sortweek desc/%09collection:netlabels AND mediatype:collection|__SERVER__|__PORT__] +[1|Old Time Radio|__CGIPATH__/search/sortweek desc/%09collection:oldtimeradio|__SERVER__|__PORT__] +[1|78 RPMs & Cylinder Recordings|__CGIPATH__/search/sortweek desc/%09collection:78rpm AND mediatype:collection|__SERVER__|__PORT__] +[1|Audio Books & Poetry|__CGIPATH__/search/sortweek desc/%09collection:audio_bookspoetry|__SERVER__|__PORT__] +[1|Computers, Technology & Science|__CGIPATH__/search/sortweek desc/%09collection:audio_tech|__SERVER__|__PORT__] +[1|Music, Arts & Culture|__CGIPATH__/search/sortweek desc/%09collection:audio_music AND mediatype:collection|__SERVER__|__PORT__] +[1|News & Public Affairs|__CGIPATH__/search/sortweek desc/%09collection:audio_news|__SERVER__|__PORT__] +[1|Spirituality & Religion|__CGIPATH__/search/sortweek desc/%09collection:audio_religion|__SERVER__|__PORT__] +[1|Podcasts|__CGIPATH__/search/sortweek desc/%09collection:podcasts|__SERVER__|__PORT__] +[1|Radio News Archive|__CGIPATH__/search/sortweek desc/%09collection:radio|__SERVER__|__PORT__] +[1|Long Playing Records|__CGIPATH__/search/sortweek desc/%09collection:album_recordings|__SERVER__|__PORT__] +[1|Various Cassette Tapes|__CGIPATH__/search/sortweek desc/%09collection:cassettetapes|__SERVER__|__PORT__] +[1|Audiophile CD Collection|__CGIPATH__/search/sortweek desc/%09collection:acdc AND -collection:samples_only|__SERVER__|__PORT__] DELETED src/audio/index.gph.m4 Index: src/audio/index.gph.m4 ================================================================== --- src/audio/index.gph.m4 +++ /dev/null @@ -1,21 +0,0 @@ -include(config.m4)dnl -# Audio - -[1|All Audio|__CGIPATH__/search/sortweek desc/%09mediatype:audio|__SERVER__|__PORT__] -[1|This Just In|__CGIPATH__/search/sortaddeddate desc/%09mediatype:audio|__SERVER__|__PORT__] -[1|Live Music Archive|__CGIPATH__/search/sortweek desc/%09collection:etree AND mediatype:collection|__SERVER__|__PORT__] -[1|Librivox Free Audiobooks|__CGIPATH__/search/sortweek desc/%09collection:librivoxaudio|__SERVER__|__PORT__] -[1|Grateful Dead|__CGIPATH__/search/sortweek desc/%09collection:GratefulDead|__SERVER__|__PORT__] -[1|Netlabels|__CGIPATH__/search/sortweek desc/%09collection:netlabels AND mediatype:collection|__SERVER__|__PORT__] -[1|Old Time Radio|__CGIPATH__/search/sortweek desc/%09collection:oldtimeradio|__SERVER__|__PORT__] -[1|78 RPMs & Cylinder Recordings|__CGIPATH__/search/sortweek desc/%09collection:78rpm AND mediatype:collection|__SERVER__|__PORT__] -[1|Audio Books & Poetry|__CGIPATH__/search/sortweek desc/%09collection:audio_bookspoetry|__SERVER__|__PORT__] -[1|Computers, Technology & Science|__CGIPATH__/search/sortweek desc/%09collection:audio_tech|__SERVER__|__PORT__] -[1|Music, Arts & Culture|__CGIPATH__/search/sortweek desc/%09collection:audio_music AND mediatype:collection|__SERVER__|__PORT__] -[1|News & Public Affairs|__CGIPATH__/search/sortweek desc/%09collection:audio_news|__SERVER__|__PORT__] -[1|Spirituality & Religion|__CGIPATH__/search/sortweek desc/%09collection:audio_religion|__SERVER__|__PORT__] -[1|Podcasts|__CGIPATH__/search/sortweek desc/%09collection:podcasts|__SERVER__|__PORT__] -[1|Radio News Archive|__CGIPATH__/search/sortweek desc/%09collection:radio|__SERVER__|__PORT__] -[1|Long Playing Records|__CGIPATH__/search/sortweek desc/%09collection:album_recordings|__SERVER__|__PORT__] -[1|Various Cassette Tapes|__CGIPATH__/search/sortweek desc/%09collection:cassettetapes|__SERVER__|__PORT__] -[1|Audiophile CD Collection|__CGIPATH__/search/sortweek desc/%09collection:acdc AND -collection:samples_only|__SERVER__|__PORT__] ADDED src/books/gophermap.m4 Index: src/books/gophermap.m4 ================================================================== --- /dev/null +++ src/books/gophermap.m4 @@ -0,0 +1,22 @@ +include(config.m4)dnl +# Books + +[1|All Texts|__CGIPATH__/search/sortweek desc/%09mediatype:texts AND -access-restricted-item:true|__SERVER__|__PORT__] +[1|This Just In|__CGIPATH__/search/sortaddeddate desc/%09mediatype:texts AND -access-restricted-item:true|__SERVER__|__PORT__] +[1|Smithsonian Libraries|__CGIPATH__/search/sortweek desc/%09collection:smithsonian|__SERVER__|__PORT__] +[1|FEDLINK|__CGIPATH__/search/sortweek desc/%09collection:fedlink AND mediatype:collection|__SERVER__|__PORT__] +[1|Genealogy|__CGIPATH__/search/sortweek desc/%09collection:genealogy AND mediatype:collection|__SERVER__|__PORT__] +[1|Lincoln Collection|__CGIPATH__/search/sortweek desc/%09collection:lincolncollection|__SERVER__|__PORT__] +[1|American Libraries|__CGIPATH__/search/sortweek desc/%09collection:americana AND mediatype:collection AND -access-restricted-item:true|__SERVER__|__PORT__] +[1|Canadian Libraries|__CGIPATH__/search/sortweek desc/%09collection:toronto AND mediatype:collection AND -access-restricted-item:true|__SERVER__|__PORT__] +[1|Universal Library|__CGIPATH__/search/sortweek desc/%09collection:universallibrary|__SERVER__|__PORT__] +[1|Project Gutenberg|__CGIPATH__/search/sortweek desc/%09collection:gutenberg|__SERVER__|__PORT__] +[1|Children's Library|__CGIPATH__/search/sortweek desc/%09collection:iacl AND -access-restricted-item:true|__SERVER__|__PORT__] +[1|Biodiversity Heritage Library|__CGIPATH__/search/sortweek desc/%09collection:biodiversity AND mediatype:collection|__SERVER__|__PORT__] +[1|Books By Language|__CGIPATH__/search/sortweek desc/%09collection:booksbylanguage AND mediatype:collection|__SERVER__|__PORT__] +[1|Additional Collections|__CGIPATH__/search/sortweek desc/%09collection:additional_collections AND mediatype:collection|__SERVER__|__PORT__] +[1|The Magazine Rack|__CGIPATH__/search/sortweek desc/%09collection:magazine_rack AND mediatype:collection|__SERVER__|__PORT__] +[1|The Pulp Magazine Archive|__CGIPATH__/search/sortweek desc/%09collection:pulpmagazinearchive|__SERVER__|__PORT__] +[1|Newspapers|__CGIPATH__/search/sortweek desc/%09collection:newspapers AND mediatype:collection|__SERVER__|__PORT__] +[1|Comic Books & Graphic Novels|__CGIPATH__/search/sortweek desc/%09collection:comics AND -access-restricted-item:true|__SERVER__|__PORT__] +[1|Zines|__CGIPATH__/search/sortweek desc/%09collection:zines AND -access-restricted-item:true|__SERVER__|__PORT__] DELETED src/books/index.gph.m4 Index: src/books/index.gph.m4 ================================================================== --- src/books/index.gph.m4 +++ /dev/null @@ -1,22 +0,0 @@ -include(config.m4)dnl -# Books - -[1|All Texts|__CGIPATH__/search/sortweek desc/%09mediatype:texts AND -access-restricted-item:true|__SERVER__|__PORT__] -[1|This Just In|__CGIPATH__/search/sortaddeddate desc/%09mediatype:texts AND -access-restricted-item:true|__SERVER__|__PORT__] -[1|Smithsonian Libraries|__CGIPATH__/search/sortweek desc/%09collection:smithsonian|__SERVER__|__PORT__] -[1|FEDLINK|__CGIPATH__/search/sortweek desc/%09collection:fedlink AND mediatype:collection|__SERVER__|__PORT__] -[1|Genealogy|__CGIPATH__/search/sortweek desc/%09collection:genealogy AND mediatype:collection|__SERVER__|__PORT__] -[1|Lincoln Collection|__CGIPATH__/search/sortweek desc/%09collection:lincolncollection|__SERVER__|__PORT__] -[1|American Libraries|__CGIPATH__/search/sortweek desc/%09collection:americana AND mediatype:collection AND -access-restricted-item:true|__SERVER__|__PORT__] -[1|Canadian Libraries|__CGIPATH__/search/sortweek desc/%09collection:toronto AND mediatype:collection AND -access-restricted-item:true|__SERVER__|__PORT__] -[1|Universal Library|__CGIPATH__/search/sortweek desc/%09collection:universallibrary|__SERVER__|__PORT__] -[1|Project Gutenberg|__CGIPATH__/search/sortweek desc/%09collection:gutenberg|__SERVER__|__PORT__] -[1|Children's Library|__CGIPATH__/search/sortweek desc/%09collection:iacl AND -access-restricted-item:true|__SERVER__|__PORT__] -[1|Biodiversity Heritage Library|__CGIPATH__/search/sortweek desc/%09collection:biodiversity AND mediatype:collection|__SERVER__|__PORT__] -[1|Books By Language|__CGIPATH__/search/sortweek desc/%09collection:booksbylanguage AND mediatype:collection|__SERVER__|__PORT__] -[1|Additional Collections|__CGIPATH__/search/sortweek desc/%09collection:additional_collections AND mediatype:collection|__SERVER__|__PORT__] -[1|The Magazine Rack|__CGIPATH__/search/sortweek desc/%09collection:magazine_rack AND mediatype:collection|__SERVER__|__PORT__] -[1|The Pulp Magazine Archive|__CGIPATH__/search/sortweek desc/%09collection:pulpmagazinearchive|__SERVER__|__PORT__] -[1|Newspapers|__CGIPATH__/search/sortweek desc/%09collection:newspapers AND mediatype:collection|__SERVER__|__PORT__] -[1|Comic Books & Graphic Novels|__CGIPATH__/search/sortweek desc/%09collection:comics AND -access-restricted-item:true|__SERVER__|__PORT__] -[1|Zines|__CGIPATH__/search/sortweek desc/%09collection:zines AND -access-restricted-item:true|__SERVER__|__PORT__] Index: src/cgi.awk ================================================================== --- src/cgi.awk +++ src/cgi.awk @@ -15,60 +15,38 @@ print "Service admin will reply when granted." print extra return } -function cgi_init( extra, ip) { +function cgi_init( extra, ip, item) { ip = ENVIRON["REMOTE_ADDR"] - - search = ARGV[1] - arguments = ARGV[2] - traversal = ARGV[5] - selector = ARGV[6] - - if (geomyidae_version < 0.96) { - input = arguments - - # geomyidae 0.69 doesn't populate selector, so do it manually - path = ENVIRON["PATH_TRANSLATED"] - - # remove leading text up through beginning of cgipath - if (match(path, cgipath)) { - selector = substr(path, RSTART) - } - - # remove trailing text from beginning of script name - if (match(selector, ENVIRON["SCRIPT_NAME"])) { - selector = substr(selector, 1, RSTART - 1) - } - selector = selector input - } else { - input = traversal - } - - if (length(search) == 0 && match(input, /%09.*/)) { - # This is a hack to include a search in the URL. - # everything before %09 is considered arguments - # everything after %09 is considered the search - search = substr(input, RSTART + 3, RLENGTH - 3) - args = substr(input, 0, RSTART - 1) - } else { - args = input - } - - # query is everything after ? in the gopher selector - # this is NOT the same as the gopher search string - query = args - - # parse the path out of the selector - path = selector + selector = ENVIRON["SELECTOR"] + + # If i run `nc -l -p 7070`, then: + # lynx -dump 'gopher://127.0.0.1:7070/1/foo?bar' + # The nc output is equivalent to: `printf "/foo?bar\r\n"` + # + # If i run `nc -l -p 7070`, then: + # lynx -dump 'gopher://127.0.0.1:7070/7/foo?bar' + # The nc output is equivalent to: `printf "/foo\tbar\r\n"` + # + # Gophernicus sets QUERY_STRING and SEARCHREQUEST to "bar" + # in both cases. If the selector contains a ? at the same + # time that there is a search string, then the two will differ. + # + # See: + + search = ENVIRON["QUERY_STRING"] + if (search != ENVIRON["SEARCHREQUEST"]) { + searchreq = ENVIRON["SEARCHREQUEST"] + } + + # parse the path out of the request + path = ENVIRON["REQUEST"] if (substr(path, 1, length(cgipath)) == cgipath) { path = substr(path, length(cgipath) + 1) } - if (match(path, /%09/)) { - path = substr(path, 1, RSTART - 1) - } split(path, parts, "/") topdir = parts[2] if (pass_enabled) { @@ -88,13 +66,13 @@ close(pass_list) if (blocked) { extra = "" if (topdir == "details") { extra = "\nIn the meanwhile, see:\n\n" \ - sprintf("[h|Web page|URL:%s/details/%s|%s|%s]\n", + sprintf("hWeb page\tURL:%s/details/%s\t%s\t%s\n", api_ssl_endpoint, - uri_encode(parts[3]), + uri_encode(search), server, port) } block_msg(ip, extra) exit(0) @@ -102,16 +80,10 @@ } return } -function gph_encode(str, retval) { - retval = str - gsub(/\|/, "\\|", retval) - return retval -} - function uri_encode_init( i, c) { for (i = 0; i <= 255; i++) { c = sprintf("%c", i) uri_encode_ord[c] = i uri_encode_tab[i] = c Index: src/config.awk ================================================================== --- src/config.awk +++ src/config.awk @@ -4,10 +4,11 @@ api_ssl_endpoint = "__API_SSL_ENDPOINT__" awk_ext = __AWK_EXT__ cache_db = "__CACHE_DB__" cache_enabled = __CACHE_ENABLED__ cgipath = "__CGIPATH__" + docpath = "__DOCPATH__" cmd_curl = "__CMD_CURL__" cmd_enc = "__CMD_ENV__" cmd_json2tsv = "__CMD_JSON2TSV__" cmd_mktemp = "__CMD_MKTEMP__" cmd_rm = "__CMD_RM__" @@ -14,14 +15,13 @@ cmd_sqlite = "__CMD_SQLITE__" cmd_strings = "__CMD_STRINGS__" cmd_webdump = "__CMD_WEBDUMP__" cmd_xargs = "__CMD_XARGS__" contact = "__CONTACT__" - geomyidae_version = __GEOMYIDAE_VERSION__ max_bin_size = __MAX_BIN_SIZE__ max_txt_size = __MAX_TXT_SIZE__ pass_enabled = __PASS_ENABLED__ pass_list = "__PASS_LIST__" server = "__SERVER__" port = "__PORT__" return } ADDED src/details.m4 Index: src/details.m4 ================================================================== --- /dev/null +++ src/details.m4 @@ -0,0 +1,230 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# __CGIPATH__/details +# +# Show details for an item + +include(src/config.awk) +incl(src/api.awk) +incl(src/cache.awk) +incl(src/cgi.awk) +incl(src/sqlite.awk) +incl(src/util.awk) +incl(src/web.awk) + +function main( add_date, col, cols, cmd, creator, descr, dir, i, + iaout, id, item_id, item_server, item_size, label, language, + license, output, pub_date, scanner, signature, str, thumb, + title, topic, topics, type, uploader_account, uploader_email, url) +{ + item_id = search + + signature = "details/" item_id + str = cache_init(signature) + if (length(str) > 0) { + print str + return + } + + iaout = gettemp() + output = cache_begin() + + url = api_endpoint "/metadata/" item_id + api_request(url, "GET", iaout) + + # format search results as a gopher directory (menu) + cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) + FS = "\t" + cols = 0 + delete col + add_date = "" + creators = 0 + delete creator + descr = "" + dir = "" + id = "" + item_server = "" + item_size = 0 + language = "" + license = "" + pub_date = "" + scanner = "" + thumb = "" + title = "" + topics = 0 + delete topic + type = "" + uploader_account = "" + uploader_email = "" + while ((cmd | getline) > 0) { + if ($1 == ".dir" && $2 == "s") { + dir = $3 + } else if ($1 == ".files[].name" && $2 == "s") { + if ($3 == "__ia_thumb.jpg") { + thumb = $3 + } + } else if ($1 == ".item_size" && $2 == "n") { + item_size = $3 + } else if ($1 == ".metadata.addeddate" && $2 == "s") { + added_date = $3 + } else if ($1 == ".metadata.collection" && $2 == "s") { + cols++ + col[cols] = $3 + } else if ($1 == ".metadata.collection[]" && $2 == "s") { + cols++ + col[cols] = $3 + } else if ($1 == ".metadata.creator" && $2 == "s") { + creators++ + creator[creators] = $3 + } else if ($1 == ".metadata.creator[]" && $2 == "s") { + creators++ + creator[creators] = $3 + } else if ($1 == ".metadata.description" && $2 == "s") { + descr = $3 + } else if ($1 == ".metadata.identifier" && $2 == "s") { + id = $3 + } else if ($1 == ".metadata.language" && $2 == "s") { + language = $3 + } else if ($1 == ".metadata.license" && $2 == "s") { + license = licenseurl[$3] + } else if ($1 == ".metadata.mediatype" && $2 == "s") { + type = $3 + } else if ($1 == ".metadata.publicdate" && $2 == "s") { + pub_date = $3 + } else if ($1 == ".metadata.scanner" && $2 == "s") { + scanner = $3 + } else if ($1 == ".metadata.subject" && $2 == "s") { + topics++ + topic[topics] = $3 + } else if ($1 == ".metadata.subject[]" && $2 == "s") { + topics++ + topic[topics] = $3 + } else if ($1 == ".metadata.title" && $2 == "s") { + title = $3 + } else if ($1 == ".metadata.uploader" && $2 == "s") { + uploader_email = $3 + } else if ($1 == ".server" && $2 == "s") { + item_server = $3 + } + } + close(cmd) + + if (length(id) == 0) { + print_not_found(output, url) + cache_end() + unlink(iaout) + return + } + + print shorten(title, 70) >>output + if (creators == 1) { + label = "by " shorten(creator[1], 70) + printf "1%s\t%ssearch?creator:(%s)\t%s\t%s\n", label, + cgipath, creator[1], server, port >>output + } else if (creators > 1) { + printf "\nby:\n" >>output + for (i = 1; i <= creators; i++) { + label = shorten(creator[i], 70) + printf "1%s\t%s/search?creator:(%s)\t%s\t%s\n", label, + cgipath, creator[i], server, port >>output + } + printf "\n" >>output + } + if (length(thumb) > 0) { + url = sprintf("http://%s%s/%s", item_server, dir, thumb) + printf "IThumbnail\t%s/raw?%s\t%s\t%s\n", cgipath, url, + server, port >>output + } + + printf "1Download\t%s/download?%s\t%s\t%s\n", cgipath, item_id, + server, port >>output + printf "hWeb page\tURL:%s/details/%s\t%s\t%s\n", + api_ssl_endpoint, uri_encode(id), server, port >>output + print "" >>output + + print_html(output, descr) + + print "" >>output + if (length(add_date) > 0) { + printf "%-20s %s\n", "Date Added:", add_date >>output + } + if (pub_date != add_date) { + printf "%-20s %s\n", "Date Published:", pub_date >>output + } + printf "%-20s %s\n", "Identifier:", id >>output + if (item_size > 0) { + printf "%-20s %d\n", "Item Size:", item_size >>output + } + if (length(language) > 0) { + printf "%-20s %s\n", "Language:", language >>output + } + if (length(license) > 0) { + printf "%-20s %s\n", "License:", license >>output + } + printf "%-20s %s\n", "Media Type:", type >>output + + if (topics > 0) { + print "" >>output + print "# Topics" >>output + for (i = 1; i <= topics; i++) { + label = shorten(topic[i], 40) + printf "1%s\t%s/search?subject:(%s)\t%s\t%s\n", label, + cgipath, topic[i], server, port >>output + } + } + + # scrape uploader name from item web page HTML + url = api_ssl_endpoint "/details/" item_id + api_request(url, "GET", iaout) + while ((getline 0) { + if (/item-upload-info__uploader-name/ && + match($0, /\/details\/[^"]*"/)) + { + uploader_account = substr($0, RSTART + 9, RLENGTH - 10) + } + } + close(iaout) + + if (cols > 0) { + print "" >>output + print "# Collections" >>output + for (i = 1; i <= cols; i++) { + label = shorten(col[i], 40) + printf "1%s\t%s/search?collection:(%s)\t%s\t%s\n", + label, cgipath, col[i], server, port >>output + } + } + + print "" >>output + print "# Uploaded by" >>output + if (length(uploader_account) > 0) { + label = shorten(uploader_account, 70) + printf "1%s\t%s/account?%s/%s\t%s\t%s\n", label, cgipath, + uploader_account, uploader_email, server, port >>output + } else { + label = shorten(uploader_email, 70) + printf "1%s\t%s/search?uploader:%s\t%s\t%s\n", label, + cgipath, uploader_email, server, port >>output + } + + print "" >>output + print "# Similar items" >>output + printf "1View similar items\t%s/search?similar:%s\t%s\t%s\n", + cgipath, item_id, server, port >>output + + print "" >>output + printf "1PHAROS\t%s\t%s\t%s\n", docpath, server, port >>output + + cache_end() + unlink(iaout) + return +} + +BEGIN { + config_init() + + uri_encode_init() + cgi_init() + main() +} DELETED src/details/index.dcgi.m4 Index: src/details/index.dcgi.m4 ================================================================== --- src/details/index.dcgi.m4 +++ /dev/null @@ -1,230 +0,0 @@ -include(config.m4)dnl -#!__CMD_AWK__ -f - -# details/index.dcgi -# -# Show details for an item - -include(src/config.awk) -incl(src/api.awk) -incl(src/cache.awk) -incl(src/cgi.awk) -incl(src/sqlite.awk) -incl(src/util.awk) -incl(src/web.awk) - -function main( add_date, col, cols, cmd, creator, descr, dir, i, - iaout, id, item_id, item_server, item_size, label, language, - license, output, pub_date, scanner, signature, str, thumb, title, - topic, topics, type, uploader_account, uploader_email, url) -{ - item_id = parts[3] - - signature = "details/" item_id - str = cache_init(signature) - if (length(str) > 0) { - print str - return - } - - iaout = gettemp() - output = cache_begin() - - url = api_endpoint "/metadata/" item_id - api_request(url, "GET", iaout) - - # format search results as a gopher directory (menu) - cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) - FS = "\t" - cols = 0 - delete col - add_date = "" - creators = 0 - delete creator - descr = "" - dir = "" - id = "" - item_server = "" - item_size = 0 - language = "" - license = "" - pub_date = "" - scanner = "" - thumb = "" - title = "" - topics = 0 - delete topic - type = "" - uploader_account = "" - uploader_email = "" - while ((cmd | getline) > 0) { - if ($1 == ".dir" && $2 == "s") { - dir = $3 - } else if ($1 == ".files[].name" && $2 == "s") { - if ($3 == "__ia_thumb.jpg") { - thumb = $3 - } - } else if ($1 == ".item_size" && $2 == "n") { - item_size = $3 - } else if ($1 == ".metadata.addeddate" && $2 == "s") { - added_date = $3 - } else if ($1 == ".metadata.collection" && $2 == "s") { - cols++ - col[cols] = $3 - } else if ($1 == ".metadata.collection[]" && $2 == "s") { - cols++ - col[cols] = $3 - } else if ($1 == ".metadata.creator" && $2 == "s") { - creators++ - creator[creators] = $3 - } else if ($1 == ".metadata.creator[]" && $2 == "s") { - creators++ - creator[creators] = $3 - } else if ($1 == ".metadata.description" && $2 == "s") { - descr = $3 - } else if ($1 == ".metadata.identifier" && $2 == "s") { - id = $3 - } else if ($1 == ".metadata.language" && $2 == "s") { - language = $3 - } else if ($1 == ".metadata.license" && $2 == "s") { - license = licenseurl[$3] - } else if ($1 == ".metadata.mediatype" && $2 == "s") { - type = $3 - } else if ($1 == ".metadata.publicdate" && $2 == "s") { - pub_date = $3 - } else if ($1 == ".metadata.scanner" && $2 == "s") { - scanner = $3 - } else if ($1 == ".metadata.subject" && $2 == "s") { - topics++ - topic[topics] = $3 - } else if ($1 == ".metadata.subject[]" && $2 == "s") { - topics++ - topic[topics] = $3 - } else if ($1 == ".metadata.title" && $2 == "s") { - title = $3 - } else if ($1 == ".metadata.uploader" && $2 == "s") { - uploader_email = $3 - } else if ($1 == ".server" && $2 == "s") { - item_server = $3 - } - } - close(cmd) - - if (length(id) == 0) { - print_not_found(output, url) - cache_end() - unlink(iaout) - return - } - - print shorten(title, 70) >>output - if (creators == 1) { - label = "by " shorten(creator[1], 70) - printf "[1|%s|%s/search/%%09creator:(%s)|%s|%s]\n", label, - cgipath, creator[1], server, port >>output - } else if (creators > 1) { - printf "\nby:\n" >>output - for (i = 1; i <= creators; i++) { - label = shorten(creator[i], 70) - printf "[1|%s|%s/search/%%09creator:(%s)|%s|%s]\n", label, - cgipath, creator[i], server, port >>output - } - printf "\n" >>output - } - if (length(thumb) > 0) { - url = sprintf("http://%s%s/%s", item_server, dir, thumb) - printf "[I|Thumbnail|%s/raw/%%09%s|%s|%s]\n", - cgipath, url, server, port >>output - } - - printf "[1|Download|%s/download/%s|%s|%s]\n", cgipath, - item_id, server, port >>output - printf "[h|Web page|URL:%s/details/%s|%s|%s]\n", - api_ssl_endpoint, uri_encode(id), server, port >>output - print "" >>output - - print_html(output, descr) - - print "" >>output - if (length(add_date) > 0) { - printf "%-20s %s\n", "Date Added:", add_date >>output - } - if (pub_date != add_date) { - printf "%-20s %s\n", "Date Published:", pub_date >>output - } - printf "%-20s %s\n", "Identifier:", id >>output - if (item_size > 0) { - printf "%-20s %d\n", "Item Size:", item_size >>output - } - if (length(language) > 0) { - printf "%-20s %s\n", "Language:", language >>output - } - if (length(license) > 0) { - printf "%-20s %s\n", "License:", license >>output - } - printf "%-20s %s\n", "Media Type:", type >>output - - if (topics > 0) { - print "" >>output - print "# Topics" >>output - for (i = 1; i <= topics; i++) { - label = shorten(topic[i], 40) - printf "[1|%s|%s/search/%%09subject:(%s)|%s|%s]\n", label, - cgipath, topic[i], server, port >>output - } - } - - # scrape uploader name from item web page HTML - url = api_ssl_endpoint "/details/" item_id - api_request(url, "GET", iaout) - while ((getline 0) { - if (/item-upload-info__uploader-name/ && - match($0, /\/details\/[^"]*"/)) - { - uploader_account = substr($0, RSTART + 9, RLENGTH - 10) - } - } - close(iaout) - - if (cols > 0) { - print "" >>output - print "# Collections" >>output - for (i = 1; i <= cols; i++) { - label = shorten(col[i], 40) - printf "[1|%s|%s/search/%%09collection:(%s)|%s|%s]\n", - label, cgipath, col[i], server, port >>output - } - } - - print "" >>output - print "# Uploaded by" >>output - if (length(uploader_account) > 0) { - label = shorten(uploader_account, 70) - printf "[1|%s|%s/account/%s%%09%s|%s|%s]\n", label, cgipath, - uploader_account, uploader_email, server, port >>output - } else { - label = shorten(uploader_email, 70) - printf "[1|%s|%s/search/%%09uploader:%s|%s|%s]\n", label, - cgipath, uploader_email, server, port >>output - } - - print "" >>output - print "# Similar items" >>output - printf "[1|View similar items|%s/search/%%09similar:%s|%s|%s]\n", - cgipath, item_id, server, port >>output - - print "" >>output - printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port >>output - - cache_end() - unlink(iaout) - return -} - -BEGIN { - config_init() - - uri_encode_init() - cgi_init() - main() -} ADDED src/download.m4 Index: src/download.m4 ================================================================== --- /dev/null +++ src/download.m4 @@ -0,0 +1,103 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# __CGIPATH__/download +# +# Show file downloads using either direct http or gopher proxy links + +include(src/config.awk) +incl(src/api.awk) +incl(src/cgi.awk) +incl(src/util.awk) + +function main( cmd, files, file_size, format, iaout, is_archive, + is_proxy, item_server, label, mtime, name, source, url) +{ + if (topdir == "download") { + is_proxy = 1 + } else { + # topdir == "direct" + is_proxy = 0 + } + + iaout = gettemp() + + url = api_endpoint "/metadata/" search + api_request(url, "GET", iaout) + + # format search results as a gopher directory (menu) + cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) + FS = "\t" + dir = "" + files = 0 + delete format + item_server = "" + delete mtime + delete name + delete file_size + delete source + + while ((cmd | getline) > 0) { + if ($1 == ".dir" && $2 == "s") { + dir = $3 + } else if ($1 == ".files[]" && $2 == "o") { + files++ + } else if ($1 == ".files[].format" && $2 == "s") { + format[files] = $3 + } else if ($1 == ".files[].mtime" && $2 == "s") { + mtime[files] = $3 + } else if ($1 == ".files[].name" && $2 == "s") { + name[files] = $3 + } else if ($1 == ".files[].size" && $2 == "s") { + file_size[files] = $3 + } else if ($1 == ".files[].source" && $2 == "s") { + source[files] = $3 + } else if ($1 == ".server" && $2 == "s") { + item_server = $3 + } + } + close(cmd) + + for (i = 1; i <= files; i++) { + label = sprintf("%s %s %s", + shorten_left(name[i], 40), + strftime("%Y-%m-%d %H:%M", mtime[i]), + human_size(file_size[i])) + url = sprintf("http://%s%s/%s", item_server, dir, name[i]) + if (is_proxy) { + if (max_bin_size > 0 && file_size[i] > max_bin_size * size_mb) { + printf "h%s\tURL:%s\t%s\t%s\n", label, uri_encode(url), + server, port + } else { + printf "1%s\t%s/links?%s\t%s\t%s\n", label, cgipath, + url, server, port + } + } else { + printf "h%s\tURL:%s\t%s\t%s\n", label, uri_encode(url), + server, port + } + is_archive = detect_archive(url) + if (is_archive) { + url = sprintf("http://%s/view_archive.php?archive=%s/%s", + item_server, dir, name[i]) + printf "h%s (View Contents)\tURL:%s\t%s\t%s\n", + shorten_left(name[i], 40), uri_encode(url), + server, port + } + } + + printf "1Downloads via http\t%s/direct?%s\t%s\t%s\n", cgipath, + search, server, port + + unlink(iaout) + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + uri_encode_init() + util_init() + main() +} DELETED src/download/index.dcgi.m4 Index: src/download/index.dcgi.m4 ================================================================== --- src/download/index.dcgi.m4 +++ /dev/null @@ -1,106 +0,0 @@ -include(config.m4)dnl -#!__CMD_AWK__ -f - -# download/index.dcgi -# -# Show file downloads using either direct http or gopher proxy links - -include(src/config.awk) -incl(src/api.awk) -incl(src/cgi.awk) -incl(src/util.awk) - -function main(cmd, dir, files, file_size, format, iaout, is_archive, - is_proxy, item_server, label, mtime, name, source, url) -{ - dir = parts[2] - item_id = parts[3] - - if (dir == "download") { - is_proxy = 1 - } else { - # dir == "direct" - is_proxy = 0 - } - - iaout = gettemp() - - url = api_endpoint "/metadata/" item_id - api_request(url, "GET", iaout) - - # format search results as a gopher directory (menu) - cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) - FS = "\t" - dir = "" - files = 0 - delete format - item_server = "" - delete mtime - delete name - delete file_size - delete source - - while ((cmd | getline) > 0) { - if ($1 == ".dir" && $2 == "s") { - dir = $3 - } else if ($1 == ".files[]" && $2 == "o") { - files++ - } else if ($1 == ".files[].format" && $2 == "s") { - format[files] = $3 - } else if ($1 == ".files[].mtime" && $2 == "s") { - mtime[files] = $3 - } else if ($1 == ".files[].name" && $2 == "s") { - name[files] = $3 - } else if ($1 == ".files[].size" && $2 == "s") { - file_size[files] = $3 - } else if ($1 == ".files[].source" && $2 == "s") { - source[files] = $3 - } else if ($1 == ".server" && $2 == "s") { - item_server = $3 - } - } - close(cmd) - - for (i = 1; i <= files; i++) { - label = sprintf("%s %s %s", - shorten_left(name[i], 40), - strftime("%Y-%m-%d %H:%M", mtime[i]), - human_size(file_size[i])) - url = sprintf("http://%s%s/%s", item_server, dir, name[i]) - if (is_proxy) { - if (max_bin_size > 0 && file_size[i] > max_bin_size * size_mb) { - printf "[h|%s|URL:%s|%s|%s]\n", label, uri_encode(url), - server, port - } else { - printf "[1|%s|%s/links/%%09%s|%s|%s]\n", label, cgipath, - url, server, port - } - } else { - printf "[h|%s|URL:%s|%s|%s]\n", label, uri_encode(url), - server, port - } - is_archive = detect_archive(url) - if (is_archive) { - url = sprintf("http://%s/view_archive.php?archive=%s/%s", - item_server, dir, name[i]) - printf "[h|%s (View Contents)|URL:%s|%s|%s]\n", - shorten_left(name[i], 40), uri_encode(url), - server, port - } - } - - printf "[1|Downloads via http|%s/direct/%s|%s|%s]\n", cgipath, - item_id, server, port - - unlink(iaout) - exit 0 -} - -BEGIN { - config_init() - - cgi_init() - uri_encode_init() - util_init() - main() -} ADDED src/gophermap.m4 Index: src/gophermap.m4 ================================================================== --- /dev/null +++ src/gophermap.m4 @@ -0,0 +1,26 @@ +include(config.m4)dnl +i .n. | +i /___\ _.---. \ _ / +i [|||] (_._ ) )--;_) =- +i [___] '---'.__,' \ +i }-=-{ | +i |-" | +i |.-"| p +i~^=~^~-|_.-|~^-~^~ ~^~ -^~^~|\ ~^-~^~- +i^ .=.| _.|__ ^ ~ /| \ +i ~ /:. \" _|_/\ ~ /_|__\ ^ +i.-/::. | |""|-._ ^ ~~~~ +i `===-'-----'""` '-. ~ +i PHAROS __.-' ^ +i +iGopher proxy to Internet Archive. +i +7Search __CGIPATH__/search __SERVER__ __PORT__ +1Advanced Search __CGIPATH__/wizard/step1 __SERVER__ __PORT__ +1Books __DOCPATH__/books/ __SERVER__ __PORT__ +1Video __DOCPATH__/video/ __SERVER__ __PORT__ +1Audio __DOCPATH__/audio/ __SERVER__ __PORT__ +1Software __DOCPATH__/software/ __SERVER__ __PORT__ +1Images __DOCPATH__/images/ __SERVER__ __PORT__ +0About PHAROS __DOCPATH__/about.txt __SERVER__ __PORT__ +hSource Code URL:https://chiselapp.com/user/bencollver/repository/pharos __SERVER__ __PORT__ ADDED src/images/gophermap.m4 Index: src/images/gophermap.m4 ================================================================== --- /dev/null +++ src/images/gophermap.m4 @@ -0,0 +1,14 @@ +include(config.m4)dnl +# Images + +[1|All Images|__CGIPATH__/search/sortweek desc/%09mediatype:image|__SERVER__|__PORT__] +[1|This Just In|__CGIPATH__/search/sortaddeddate desc/%09mediatype:image|__SERVER__|__PORT__] +[1|Metropolitan Museum of Art|__CGIPATH__/search/sortweek desc/%09collection:metropolitanmuseumofart-gallery|__SERVER__|__PORT__] +[1|Cleveland Museum of Art|__CGIPATH__/search/sortweek desc/%09collection:clevelandart|__SERVER__|__PORT__] +[1|Flickr Commons|__CGIPATH__/search/sortweek desc/%09collection:flickrcommons|__SERVER__|__PORT__] +[1|Occupy Wallstreet Flickr|__CGIPATH__/search/sortweek desc/%09collection:flickr-ows|__SERVER__|__PORT__] +[1|Cover Art|__CGIPATH__/search/sortweek desc/%09collection:coverartarchive|__SERVER__|__PORT__] +[1|USGS Maps|__CGIPATH__/search/sortweek desc/%09collection:maps_usgs|__SERVER__|__PORT__] +[1|NASA Images|__CGIPATH__/search/sortweek desc/%09collection:nasa|__SERVER__|__PORT__] +[1|Solar System Collection|__CGIPATH__/search/sortweek desc/%09collection:solarsystemcollection|__SERVER__|__PORT__] +[1|Ames Research Center|__CGIPATH__/search/sortweek desc/%09collection:amesresearchcenterimagelibrary|__SERVER__|__PORT__] DELETED src/images/index.gph.m4 Index: src/images/index.gph.m4 ================================================================== --- src/images/index.gph.m4 +++ /dev/null @@ -1,14 +0,0 @@ -include(config.m4)dnl -# Images - -[1|All Images|__CGIPATH__/search/sortweek desc/%09mediatype:image|__SERVER__|__PORT__] -[1|This Just In|__CGIPATH__/search/sortaddeddate desc/%09mediatype:image|__SERVER__|__PORT__] -[1|Metropolitan Museum of Art|__CGIPATH__/search/sortweek desc/%09collection:metropolitanmuseumofart-gallery|__SERVER__|__PORT__] -[1|Cleveland Museum of Art|__CGIPATH__/search/sortweek desc/%09collection:clevelandart|__SERVER__|__PORT__] -[1|Flickr Commons|__CGIPATH__/search/sortweek desc/%09collection:flickrcommons|__SERVER__|__PORT__] -[1|Occupy Wallstreet Flickr|__CGIPATH__/search/sortweek desc/%09collection:flickr-ows|__SERVER__|__PORT__] -[1|Cover Art|__CGIPATH__/search/sortweek desc/%09collection:coverartarchive|__SERVER__|__PORT__] -[1|USGS Maps|__CGIPATH__/search/sortweek desc/%09collection:maps_usgs|__SERVER__|__PORT__] -[1|NASA Images|__CGIPATH__/search/sortweek desc/%09collection:nasa|__SERVER__|__PORT__] -[1|Solar System Collection|__CGIPATH__/search/sortweek desc/%09collection:solarsystemcollection|__SERVER__|__PORT__] -[1|Ames Research Center|__CGIPATH__/search/sortweek desc/%09collection:amesresearchcenterimagelibrary|__SERVER__|__PORT__] DELETED src/index.gph.m4 Index: src/index.gph.m4 ================================================================== --- src/index.gph.m4 +++ /dev/null @@ -1,26 +0,0 @@ -include(config.m4)dnl - .n. | - /___\ _.---. \ _ / - [|||] (_._ ) )--;_) =- - [___] '---'.__,' \ - }-=-{ | - |-" | - |.-"| p -~^=~^~-|_.-|~^-~^~ ~^~ -^~^~|\ ~^-~^~- -^ .=.| _.|__ ^ ~ /| \ - ~ /:. \" _|_/\ ~ /_|__\ ^ -.-/::. | |""|-._ ^ ~~~~ - `===-'-----'""` '-. ~ - PHAROS __.-' ^ - -Gopher proxy to Internet Archive. - -[7|Search|__CGIPATH__/search/|__SERVER__|__PORT__] -[1|Advanced Search|__CGIPATH__/wizard/step1|__SERVER__|__PORT__] -[1|Books|__CGIPATH__/books/|__SERVER__|__PORT__] -[1|Video|__CGIPATH__/video/|__SERVER__|__PORT__] -[1|Audio|__CGIPATH__/audio/|__SERVER__|__PORT__] -[1|Software|__CGIPATH__/software/|__SERVER__|__PORT__] -[1|Images|__CGIPATH__/images/|__SERVER__|__PORT__] -[0|About PHAROS|__CGIPATH__/about.txt|__SERVER__|__PORT__] -[h|Source Code|URL:https://chiselapp.com/user/bencollver/repository/pharos|__SERVER__|__PORT__] ADDED src/list.m4 Index: src/list.m4 ================================================================== --- /dev/null +++ src/list.m4 @@ -0,0 +1,229 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# __CGIPATH__/list +# +# Show a specific list + +include(src/config.awk) +incl(src/api.awk) +incl(src/cache.awk) +incl(src/cgi.awk) +incl(src/sqlite.awk) +incl(src/util.awk) + +function main( acct, client_url, cmd, count, creator, iaout, id, + is_private, items, label, list_id, name, name_slug, numfound, + order, order_name, order_names, order_param, output, page, pages, + prefix, rows, sort_param, signature, str, title, type, url, + user_query) +{ + order_names["creator"] = "creatorSorter" + order_names["date"] = "date" + order_names["title"] = "titleSorter" + order_names["week"] = "week" + + rows = 15 + page = 1 + order = "" + sort_param = "" + + # parse out page number and sort order + numfound = 1 + while (numfound == 1) { + if (match(search, /\/rows[0-9][0-9]*$/)) { + rows = substr(search, RSTART + 5) + search = substr(search, 1, RSTART - 1) + } else if (match(search, /\/page[0-9][0-9]*$/)) { + page = substr(search, RSTART + 5) + search = substr(search, 1, RSTART - 1) + } else if (match(search, /\/sort[^\/]*$/)) { + if (length(order) == 0) { + sort_param = substr(search, RSTART + 1) + order = substr(sort_param, 5) + } + search = substr(search, 1, RSTART - 1) + } else { + numfound = 0 + } + } + + split(search, parts, "/") + acct = parts[1] + list_id = parts[2] + + signature = sprintf("list/%s/%s", input, search) + str = cache_init(signature) + if (length(str) > 0) { + print str + return + } + + output = cache_begin() + iaout = gettemp() + + url = api_ssl_endpoint "/services/users/" acct "/lists/" list_id + api_request(url, "GET", iaout) + + # fetch identifiers of list members + + cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) + FS = "\t" + id = "" + is_private = 0 + name = "" + numfound = 0 + user_query = "" + + while ((cmd | getline) > 0) { + if ($1 == ".value.list_name" && $2 == "s") { + name = $3 + is_private = 0 + } else if ($1 == ".value.is_private" && $2 == "b") { + if ($3 == "true") { + is_private = 1 + } + } else if ($1 == ".value.members[].identifier" && $2 == "s") { + if (!is_private) { + id = $3 + numfound++ + if (length(user_query) == 0) { + user_query = id + } else { + user_query = user_query "+OR+" id + } + } + } + } + close(cmd) + unlink(iaout) + + # get metadata of list member items + + name_slug = uri_encode(name) + gsub(/%20/, "-", name_slug) + client_url = api_ssl_endpoint "/details/" acct "/lists/" list_id \ + "/" name_slug + order_param = "" + if (length(order) > 0) { + split(order, parts, " ") + order_name = order_names[parts[1]] + if (length(order_name) > 0) { + if (parts[2] == "desc") { + client_url = client_url "?-" parts[1] + } else { + client_url = client_url "?" parts[1] + } + order_param = "&sort=" uri_encode(order_name ":" parts[2]) + } + } + url = api_ssl_endpoint "/services/search/beta/page_production/" \ + "?user_query=identifier:(" user_query ")" \ + "&hits_per_page=" rows \ + "&page=" page \ + order_param \ + "&aggregations=false" \ + "&client_url=" client_url + api_request(url, "GET", iaout) + + pages = int(numfound / rows) + if (numfound % rows != 0) { + pages++ + } + + # format as a gopher directory (menu) + + print acct "'s Lists" >>output + print "" >>output + printf "# List: %s, page %d of %d\n", name, page, pages >>output + print "" >>output + + cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) + FS = "\t" + count = 0 + creator = "" + id = "" + title = "" + type = "" + while ((cmd | getline) > 0) { + if ($1 == ".response.body.hits.hits[].fields.creator[]" && + $2 == "s" && length(creator) == 0) + { + creator = $3 + } else if ($1 == ".response.body.hits.hits[].fields.identifier" && + $2 == "s") + { + id = $3 + } else if ($1 == ".response.body.hits.hits[].fields.mediatype" && + $2 == "s") + { + type = $3 + } else if ($1 == ".response.body.hits.hits[].fields.title" && + $2 == "s") + { + title = $3 + } else if ($1 == ".response.body.hits.hits[]._score") { + # the _score field happens to be toward the end of each item + if (length(title) > 0) { + if (length(creator) > 0) { + label = sprintf("[%s] %s by %s", mediatype[type], + shorten(title, 40), shorten(creator, 18)) + } else { + label = sprintf("[%s] %s", mediatype[type], + shorten(title, 58)) + } + printf "1%s\t%s/details?%s\t%s\t%s\n", label, cgipath, id, + server, port >>output + count++ + } + creator = "" + descr = "" + id = "" + type = "" + } + } + close(cmd) + + print "" >>output + + # only show "page back" if the user is past page 1 + if (page > 1) { + prefix = sprintf("/page%d/rows%d/%s", page - 1, rows, sort_param) + printf "1[<<] Page %d\t%s/list?%s/%d%s\t%s\t%s\n", + page - 1, cgipath, acct, list_id, prefix, server, + port >>output + } + + # only show "next page" if the current page is completely full + if (count == rows) { + prefix = sprintf("/page%d/rows%d/%s", page + 1, rows, sort_param) + printf "1[>>] Page %d\t%s/list?%s/%d%s\t%s\t%s\n", + page + 1, cgipath, acct, list_id, prefix, server, + port >>output + } + + # only show "sort" if there's more than one item to sort + if (numfound > 1) { + printf "1[^v] Sort\t%s/listsort?%s/%d\t%s\t%s\n", cgipath, + acct, list_id, server, port >>output + } + + printf "1Account %s\t%s/account?%s\t%s\t%s\n", acct, cgipath, + acct, server, port >>output + + print "" >>output + printf "1PHAROS\t%s\t%s\t%s\n", docpath, server, port >>output + + cache_end() + unlink(iaout) + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + uri_encode_init() + util_init() + main() +} DELETED src/list/index.dcgi.m4 Index: src/list/index.dcgi.m4 ================================================================== --- src/list/index.dcgi.m4 +++ /dev/null @@ -1,220 +0,0 @@ -include(config.m4)dnl -#!__CMD_AWK__ -f - -# list/index.dcgi -# -# Show a specific list - -include(src/config.awk) -incl(src/api.awk) -incl(src/cache.awk) -incl(src/cgi.awk) -incl(src/sqlite.awk) -incl(src/util.awk) - -function main( acct, client_url, cmd, count, creator, iaout, id, - is_private, items, label, list_id, name, name_slug, numfound, - order, order_name, order_names, order_param, output, page, pages, - rows, query, sort_param, signature, str, title, type, url) -{ - order_names["creator"] = "creatorSorter" - order_names["date"] = "date" - order_names["title"] = "titleSorter" - order_names["week"] = "week" - - rows = 15 - page = 1 - order = "" - sort_param = "" - - # parse out page number and sort order - for (i in parts) { - if (parts[i] ~ /^rows[0-9][0-9]*$/) { - rows = substr(parts[i], 5) - } else if (parts[i] ~ /^page[0-9][0-9]*$/) { - page = substr(parts[i], 5) - } else if (parts[i] ~ /^sort/) { - if (length(order) == 0) { - sort_param = parts[i] - order = substr(parts[i], 5) - } - } - } - - split(search, parts, "/") - acct = parts[1] - list_id = parts[2] - - signature = sprintf("list/%s/%s", input, search) - str = cache_init(signature) - if (length(str) > 0) { - print str - return - } - - output = cache_begin() - iaout = gettemp() - - url = api_ssl_endpoint "/services/users/" acct "/lists/" list_id - api_request(url, "GET", iaout) - - # fetch identifiers of list members - - cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) - FS = "\t" - id = "" - is_private = 0 - name = "" - numfound = 0 - query = "" - - while ((cmd | getline) > 0) { - if ($1 == ".value.list_name" && $2 == "s") { - name = $3 - is_private = 0 - } else if ($1 == ".value.is_private" && $2 == "b") { - if ($3 == "true") { - is_private = 1 - } - } else if ($1 == ".value.members[].identifier" && $2 == "s") { - if (!is_private) { - id = $3 - numfound++ - if (length(query) == 0) { - query = id - } else { - query = query "+OR+" id - } - } - } - } - close(cmd) - unlink(iaout) - - # get metadata of list member items - - name_slug = uri_encode(name) - gsub(/%20/, "-", name_slug) - client_url = api_ssl_endpoint "/details/" acct "/lists/" list_id \ - "/" name_slug - order_param = "" - if (length(order) > 0) { - split(order, parts, " ") - order_name = order_names[parts[1]] - if (length(order_name) > 0) { - if (parts[2] == "desc") { - client_url = client_url "?-" parts[1] - } else { - client_url = client_url "?" parts[1] - } - order_param = "&sort=" uri_encode(order_name ":" parts[2]) - } - } - url = api_ssl_endpoint "/services/search/beta/page_production/" \ - "?user_query=identifier:(" query ")" \ - "&hits_per_page=" rows \ - "&page=" page \ - order_param \ - "&aggregations=false" \ - "&client_url=" client_url - api_request(url, "GET", iaout) - - pages = int(numfound / rows) - if (numfound % rows != 0) { - pages++ - } - - # format as a gopher directory (menu) - - print acct "'s Lists" >>output - print "" >>output - printf "# List: %s, page %d of %d\n", name, page, pages >>output - print "" >>output - - cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) - FS = "\t" - count = 0 - creator = "" - id = "" - title = "" - type = "" - while ((cmd | getline) > 0) { - if ($1 == ".response.body.hits.hits[].fields.creator[]" && - $2 == "s" && length(creator) == 0) - { - creator = $3 - } else if ($1 == ".response.body.hits.hits[].fields.identifier" && - $2 == "s") - { - id = $3 - } else if ($1 == ".response.body.hits.hits[].fields.mediatype" && - $2 == "s") - { - type = $3 - } else if ($1 == ".response.body.hits.hits[].fields.title" && - $2 == "s") - { - title = $3 - } else if ($1 == ".response.body.hits.hits[]._score") { - # the _score field happens to be toward the end of each item - if (length(title) > 0) { - if (length(creator) > 0) { - label = sprintf("[%s] %s by %s", mediatype[type], - gph_encode(shorten(title, 40)), shorten(creator, 18)) - } else { - label = sprintf("[%s] %s", mediatype[type], - gph_encode(shorten(title, 58))) - } - printf "[1|%s|%s/details/%s|%s|%s]\n", label, cgipath, id, - server, port >>output - count++ - } - creator = "" - descr = "" - id = "" - type = "" - } - } - close(cmd) - - print "" >>output - - # only show "page back" if the user is past page 1 - if (page > 1) { - printf "[1|[<<] Page %d|%s/list/page%d/rows%d/%s%%09%s/%d|%s|%s]\n", - page - 1, cgipath, page - 1, rows, sort_param, - acct, list_id, server, port >>output - } - - # only show "next page" if the current page is completely full - if (count == rows) { - printf "[1|[>>] Page %d|%s/list/page%d/rows%d/%s%%09%s/%d|%s|%s]\n", - page + 1, cgipath, page + 1, rows, sort_param, - acct, list_id, server, port >>output - } - - # only show "sort" if there's more than one item to sort - if (numfound > 1) { - printf "[1|[^v] Sort|%s/listsort/%%09%s/%d|%s|%s]\n", cgipath, - acct, list_id, server, port >>output - } - - printf "[1|Account %s|%s/account/%s|%s|%s]\n", acct, cgipath, - acct, server, port >>output - - print "" >>output - printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port >>output - - cache_end() - unlink(iaout) - exit 0 -} - -BEGIN { - config_init() - - cgi_init() - uri_encode_init() - util_init() - main() -} ADDED src/lists.m4 Index: src/lists.m4 ================================================================== --- /dev/null +++ src/lists.m4 @@ -0,0 +1,113 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# __CGIPATH__/lists +# +# Show a list of a user's lists + +include(src/config.awk) +incl(src/api.awk) +incl(src/cache.awk) +incl(src/cgi.awk) +incl(src/sqlite.awk) +incl(src/util.awk) + +function main( cmd, count, fields, iaout, i, id, is_private, item, + item_count, item_id, label, name, output, record, records, + signature, str, url) +{ + signature = sprintf("%s/lists", search) + str = cache_init(signature) + if (length(str) > 0) { + print str + return + } + + output = cache_begin() + iaout = gettemp() + + url = api_ssl_endpoint "/services/users/" search "/lists" + api_request(url, "GET", iaout) + + # format list as a gopher directory (menu) + cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) + FS = "\t" + count = 0 + delete fields[0] + id = 0 + is_private = 0 + item = "" + item_count = 0 + item_id = "" + name = "" + record = "" + delete records[0] + + while ((cmd | getline) > 0) { + if ($1 == ".value[]" && $2 == "o") { + # add information for previous list + if (!is_private && length(name) > 0 && item_count > 0) { + label = shorten_left(name, 50) + item = sprintf("1%4d Items: %-50s\t%s/list?%s/%d\t%s\t%s", + item_count, label, cgipath, search, id, server, port) + record = label "\v" id "\v" item + count++ + records[count] = record + } + } else if ($1 == ".value[].list_name" && $2 == "s") { + name = $3 + id = 0 + is_private = 0 + item_count = 0 + } else if ($1 == ".value[].is_private" && $2 == "b") { + if ($3 == "true") { + is_private = 1 + } + } else if ($1 == ".value[].id" && $2 == "n") { + id = $3 + } else if ($1 == ".value[].members[].identifier" && $2 == "s") { + item_count++ + } + } + close(cmd) + + # add information for previous list + if (!is_private && length(name) > 0 && item_count > 0) { + label = shorten_left(name, 50) + item = sprintf("1%4d Items: %-50s\t%s/list?%s/%d\t%s\t%s", + item_count, label, cgipath, search, id, server, port) + record = label "\v" id "\v" item + count++ + records[count] = record + } + + # sort lists by label and id + if (count > 0) { + hsort(records, count) + } + + print search "'s Lists" >>output + print "" >>output + + for (i = 1; i <= count; i++) { + record = records[i] + split(record, fields, /\v/) + item = fields[3] + print item >>output + } + + print "" >>output + printf "1PHAROS\t%s\t%s\t%s\n", docpath, server, port >>output + + cache_end() + unlink(iaout) + return +} + +BEGIN { + config_init() + + cgi_init() + uri_encode_init() + main() +} DELETED src/lists/index.dcgi.m4 Index: src/lists/index.dcgi.m4 ================================================================== --- src/lists/index.dcgi.m4 +++ /dev/null @@ -1,111 +0,0 @@ -include(config.m4)dnl -#!__CMD_AWK__ -f - -# lists/index.dcgi -# -# Show a list of a user's lists - -include(src/config.awk) -incl(src/api.awk) -incl(src/cache.awk) -incl(src/cgi.awk) -incl(src/sqlite.awk) -incl(src/util.awk) - -function main( cmd, count, fields, iaout, i, id, is_private, item, - item_count, item_id, label, name, output, record, records, - signature, str, url) -{ - signature = sprintf("%s/lists", search) - str = cache_init(signature) - if (length(str) > 0) { - print str - return - } - - output = cache_begin() - iaout = gettemp() - - url = api_ssl_endpoint "/services/users/" search "/lists" - api_request(url, "GET", iaout) - - # format list as a gopher directory (menu) - cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) - FS = "\t" - count = 0 - delete fields[0] - id = 0 - is_private = 0 - item = "" - item_count = 0 - item_id = "" - name = "" - record = "" - delete records[0] - - while ((cmd | getline) > 0) { - if ($1 == ".value[]" && $2 == "o") { - # add information for previous list - if (!is_private && length(name) > 0 && item_count > 0) { - label = shorten_left(name, 50) - item = sprintf("[1|%4d Items: %-50s|%s/list/%%09%s/%d|%s|%s]", - item_count, label, cgipath, search, id, server, port) - record = label "\t" id "\t" item - count++ - records[count] = record - } - } else if ($1 == ".value[].list_name" && $2 == "s") { - name = $3 - id = 0 - is_private = 0 - item_count = 0 - } else if ($1 == ".value[].is_private" && $2 == "b") { - if ($3 == "true") { - is_private = 1 - } - } else if ($1 == ".value[].id" && $2 == "n") { - id = $3 - } else if ($1 == ".value[].members[].identifier" && $2 == "s") { - item_count++ - } - } - close(cmd) - - # add information for previous list - if (!is_private && length(name) > 0 && item_count > 0) { - label = shorten_left(name, 50) - item = sprintf("[1|%4d Items: %-50s|%s/list/%%09%s/%d|%s|%s]", - item_count, label, cgipath, search, id, server, port) - record = label "\t" id "\t" item - count++ - records[count] = record - } - - # sort lists by label and id - hsort(records, count) - - print search "'s Lists" >>output - print "" >>output - - for (i = 1; i <= count; i++) { - record = records[i] - split(record, fields, /\t/) - item = fields[3] - print item >>output - } - - print "" >>output - printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port >>output - - cache_end() - unlink(iaout) - return -} - -BEGIN { - config_init() - - cgi_init() - uri_encode_init() - main() -} ADDED src/listsort.m4 Index: src/listsort.m4 ================================================================== --- /dev/null +++ src/listsort.m4 @@ -0,0 +1,54 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# __CGIPATH__/listsort +# +# Change list sort order + +include(src/config.awk) +incl(src/cgi.awk) + +function main( acct, i, lbl, list_id, opt) { + lbl[1] = "Relevance" + opt[1] = "" + lbl[2] = "Weekly views [^]" + opt[2] = "week asc" + lbl[3] = "Weekly views [v]" + opt[3] = "week desc" + lbl[4] = "Title [^]" + opt[4] = "title asc" + lbl[5] = "Title [v]" + opt[5] = "title desc" + lbl[6] = "Date published [^]" + opt[6] = "date asc" + lbl[7] = "Date published [v]" + opt[7] = "date desc" + lbl[8] = "Creator [^]" + opt[8] = "creator asc" + lbl[9] = "Creator [v]" + opt[9] = "creator desc" + + split(search, parts, "/") + acct = parts[1] + list_id = parts[2] + + print "# Sort by" + print "" + for (i = 1; i < 10; i++) { + if (length(opt[i]) == 0) { + printf "1%s\t%s/list?%s/%d\t%s\t%s\n", lbl[i], cgipath, + acct, list_id, server, port + } else { + printf "1%s\t%s/list?%s/%d/sort%s\t%s\t%s\n", lbl[i], + cgipath, acct, list_id, opt[i], server, port + } + } + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + main() +} DELETED src/listsort/index.dcgi.m4 Index: src/listsort/index.dcgi.m4 ================================================================== --- src/listsort/index.dcgi.m4 +++ /dev/null @@ -1,54 +0,0 @@ -include(config.m4)dnl -#!__CMD_AWK__ -f - -# listsort/index.dcgi -# -# Change list sort order - -include(src/config.awk) -incl(src/cgi.awk) - -function main( acct, i, lbl, list_id, opt) { - lbl[1] = "Relevance" - opt[1] = "" - lbl[2] = "Weekly views [^]" - opt[2] = "week asc" - lbl[3] = "Weekly views [v]" - opt[3] = "week desc" - lbl[4] = "Title [^]" - opt[4] = "title asc" - lbl[5] = "Title [v]" - opt[5] = "title desc" - lbl[6] = "Date published [^]" - opt[6] = "date asc" - lbl[7] = "Date published [v]" - opt[7] = "date desc" - lbl[8] = "Creator [^]" - opt[8] = "creator asc" - lbl[9] = "Creator [v]" - opt[9] = "creator desc" - - split(search, parts, "/") - acct = parts[1] - list_id = parts[2] - - print "# Sort by" - print "" - for (i = 1; i < 10; i++) { - if (length(opt[i]) == 0) { - printf "[1|%s|%s/list/%%09%s/%d|%s|%s]\n", - lbl[i], cgipath, acct, list_id, server, port - } else { - printf "[1|%s|%s/list/sort%s%%09%s/%d|%s|%s]\n", - lbl[i], cgipath, opt[i], acct, list_id, server, port - } - } - exit 0 -} - -BEGIN { - config_init() - - cgi_init() - main() -} ADDED src/raw.m4 Index: src/raw.m4 ================================================================== --- /dev/null +++ src/raw.m4 @@ -0,0 +1,46 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# __CGIPATH__/debug +# +# Show HTTP headers from curl fetching a URL +# +# __CGIPATH__/links +# +# Show download links, plus links scraped from HTML document +# +# __CGIPATH__/raw +# +# Show raw bytes from binary document +# +# __CGIPATH__/text +# +# Show text content scraped from HTML document + +include(src/config.awk) +incl(src/api.awk) +incl(src/cgi.awk) +incl(src/util.awk) +incl(src/web.awk) + +function main() { + if (path == "/debug") { + dump(search, TYPE_HEADERS) + } else if (path == "/raw") { + dump(search, TYPE_RAW) + } else if (path == "/text") { + dump(search, TYPE_TEXT) + } else if (path == "/links") { + dump(search, TYPE_LINKS) + } + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + uri_encode_init() + web_init() + main() +} DELETED src/raw/index.cgi.m4 Index: src/raw/index.cgi.m4 ================================================================== --- src/raw/index.cgi.m4 +++ /dev/null @@ -1,46 +0,0 @@ -include(config.m4)dnl -#!__CMD_AWK__ -f - -# debug/index.cgi -# -# Show HTTP headers from curl fetching a URL -# -# links/index.dcgi -# -# Show download links, plus links scraped from HTML document -# -# raw/index.cgi -# -# Show raw bytes from binary document -# -# text/index.cgi -# -# Show text content scraped from HTML document - -include(src/config.awk) -incl(src/api.awk) -incl(src/cgi.awk) -incl(src/util.awk) -incl(src/web.awk) - -function main() { - if (path == "/debug/") { - dump(search, TYPE_HEADERS) - } else if (path == "/raw/") { - dump(search, TYPE_RAW) - } else if (path == "/text/") { - dump(search, TYPE_TEXT) - } else if (path == "/links/") { - dump(search, TYPE_LINKS) - } - exit 0 -} - -BEGIN { - config_init() - - cgi_init() - uri_encode_init() - web_init() - main() -} ADDED src/search.m4 Index: src/search.m4 ================================================================== --- /dev/null +++ src/search.m4 @@ -0,0 +1,261 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# __CGIPATH__/search +# +# Show search results + +include(src/config.awk) +incl(src/api.awk) +incl(src/cgi.awk) +incl(src/util.awk) + +function main(search, cmd, count, creator, descr, field, fields, i, + iaout, id, item, items, jsout, label, numfound, order, + order_names, page, prefix, rows, searchstr, sort_param, str, + title, type, url) +{ + order_names["addeddate"] = "addeddate" + order_names["collection_size"] = "collection_size" + order_names["createddate"] = "createddate" + order_names["creator"] = "creatorSorter" + order_names["date"] = "date" + order_names["downloads"] = "downloads" + order_names["nav_order"] = "nav_order" + order_names["random"] = "random" + order_names["title"] = "titleSorter" + order_names["week"] = "week" + + rows = 15 + page = 1 + order = "" + + # parse out page number and sort orders + numfound = 1 + while (numfound == 1) { + if (match(search, /\/rows[0-9][0-9]*$/)) { + rows = substr(search, RSTART + 5) + search = substr(search, 1, RSTART - 1) + } else if (match(search, /\/page[0-9][0-9]*$/)) { + page = substr(search, RSTART + 5) + search = substr(search, 1, RSTART - 1) + } else if (match(search, /\/sort[^\/]*$/)) { + if (length(order) == 0) { + sort_param = substr(search, RSTART + 1) + order = substr(sort_param, 5) + } + search = substr(search, 1, RSTART - 1) + } else { + numfound = 0 + } + } + + iaout = gettemp() + jsout = gettemp() + + # special case for when the search term is an archive.org details URL + if (match(search, /^https:\/\/(www\.)?archive\.org\/details\//)) { + id = substr(search, RLENGTH + 1) + search = "identifier:" id + } + + # special case to list similar items + if (match(search, /^similar:/)) { + id = substr(search, RLENGTH + 1) + + url = api_endpoint "/details/" id "?RelatedItemsGet=1" + api_request(url, "GET", iaout) + + # scrape similar items + FS = "\t" + items = 0 + delete item + str = "" + while ((getline 0) { + if (match($0, /iaout + close(iaout) + + for (i = 1; i <= items; i++) { + if (i == 1) { + search = "identifier:" item[i] + } else { + search = search "%20OR%20identifier:" item[i] + } + } + } + + # remove quotes from search string, since it gets quoted later + gsub(/"/, "", search) + + # default sort orders if none were specified + if (length(order) == 0) { + if (search == "mediatype:collection" || + search == "mediatype:(collection)") + { + order = "collection_size desc" + sort_param = "sort" order + } else { + order = "nav_order desc" + sort_param = "sort" order + } + } + + # get search results + + field[1] = "creator" + field[2] = "description" + field[3] = "identifier" + field[4] = "mediatype" + field[5] = "title" + fields = 5 + + # remove anyfield, a hobgoblin of consistency + searchstr = search + gsub(/anyfield:/, "", searchstr) + + url = sprintf("%s/advancedsearch.php?q=%s&output=json&rows=%d&page=%d", + api_endpoint, searchstr, rows, page) + if (length(order) > 0) { + split(order, parts, " ") + url = url sprintf("&sort%%5B0%%5D=%s %s", order_names[parts[1]], + parts[2]) + } + for (i = 1; i <= fields; i++) { + url = url sprintf("&fl%%5B%d%%5D=%s", i - 1, field[i]) + } + api_request(url, "GET", iaout) + + cmd = sprintf("%s <%s >%s 2>&1", cmd_json2tsv, iaout, jsout) + system(cmd) + + numfound = 0 + FS = "\t" + while ((getline 0) { + if ($1 == ".response.numFound" && $2 == "n") { + numfound = $3 + } + } + close(jsout) + + if (search ~ /^@/) { + numfound++ + } + if (numfound == 0) { + print "Your search did not match any items in the Archive." + print "Try different keywords or a more general search." + print "" + printf "1PHAROS\t%s\t%s\t%s\n", docpath, server, port + unlink(jsout) + unlink(iaout) + return + } else { + pages = int(numfound / rows) + if (numfound % rows != 0) { + pages++ + } + printf "# %s search results, page %d of %d\n", numfound, + page, pages + print "" + } + + # format search results as a gopher directory (menu) + FS = "\t" + creator = "" + descr = "" + id = "" + title = "" + type = "" + count = 0 + + if (search ~ /^@/) { + printf "1Account %s\t%s/account?%s\t%s\t%s\n", search, cgipath, + search, server, port + } + + while ((getline 0) { + if ($1 == ".response.docs[].creator" && $2 == "s") { + creator = $3 + } else if ($1 == ".response.docs[].description" && $2 == "s") { + descr = $3 + } else if ($1 == ".response.docs[].identifier" && $2 == "s") { + id = $3 + } else if ($1 == ".response.docs[].mediatype" && $2 == "s") { + type = $3 + } else if ($1 == ".response.docs[].title" && $2 == "s") { + # the title field happens to be toward the end of each item + title = $3 + count++ + if (length(creator) > 0) { + label = sprintf("[%s] %s by %s", mediatype[type], + shorten(title, 40), shorten(creator, 18)) + } else { + label = sprintf("[%s] %s", mediatype[type], + shorten(title, 58)) + } + if (type == "collection") { + printf "1%s\t%s/search?collection:(%s)\t%s\t%s\n", + label, cgipath, id, server, port + } else { + printf "1%s\t%s/details?%s\t%s\t%s\n", label, cgipath, + id, server, port + } + creator = "" + descr = "" + id = "" + type = "" + } + } + close(jsout) + + print "" + + # only show "page back" if the user is past page 1 + if (page > 1) { + prefix = sprintf("/page%d/rows%d/%s", page - 1, rows, sort_param) + printf "1[<<] Page %d\t%s/search?%s%s\t%s\t%s\n", + page - 1, cgipath, search, prefix, server, port + } + + # only show "next page" if the current page is completely full + if (count == rows) { + prefix = sprintf("/page%d/rows%d/%s", page + 1, rows, sort_param) + printf "1[>>] Page %d\t%s/search?%s%s\t%s\t%s\n", + page + 1, cgipath, search, prefix, server, port + } + + # only show "sort" if there's more than one item to sort + if (count > 1) { + printf "1[^v] Sort\t%s/sort?%s\t%s\t%s\n", cgipath, + search, server, port + } + + # only show "search within list" if there's multiple pages of results + if (numfound > rows) { + printf "1[\\/] Filter results\t%s/wizard/step1?%s\t%s\t%s\n", + cgipath, search, server, port + } + + printf "1PHAROS\t%s\t%s\t%s\n", docpath, server, port + + unlink(jsout) + unlink(iaout) + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + uri_encode_init() + util_init() + main(search) +} DELETED src/search/index.dcgi.m4 Index: src/search/index.dcgi.m4 ================================================================== --- src/search/index.dcgi.m4 +++ /dev/null @@ -1,255 +0,0 @@ -include(config.m4)dnl -#!__CMD_AWK__ -f - -# search/index.dcgi -# -# Show search results - -include(src/config.awk) -incl(src/api.awk) -incl(src/cgi.awk) -incl(src/util.awk) - -function main(search, cmd, count, creator, descr, field, fields, i, - iaout, id, item, items, jsout, label, numfound, order, - order_names, page, rows, searchstr, sort_param, str, title, type, - url) -{ - order_names["addeddate"] = "addeddate" - order_names["collection_size"] = "collection_size" - order_names["createddate"] = "createddate" - order_names["creator"] = "creatorSorter" - order_names["date"] = "date" - order_names["downloads"] = "downloads" - order_names["nav_order"] = "nav_order" - order_names["random"] = "random" - order_names["title"] = "titleSorter" - order_names["week"] = "week" - - rows = 15 - page = 1 - order = "" - - # parse out page number and sort orders - for (i in parts) { - if (parts[i] ~ /^rows[0-9][0-9]*$/) { - rows = substr(parts[i], 5) - } else if (parts[i] ~ /^page[0-9][0-9]*$/) { - page = substr(parts[i], 5) - } else if (parts[i] ~ /^sort/) { - if (length(order) == 0) { - sort_param = parts[i] - order = substr(parts[i], 5) - } - } - } - - iaout = gettemp() - jsout = gettemp() - - # special case for when the search term is an archive.org details URL - if (match(search, /^https:\/\/(www\.)?archive\.org\/details\//)) { - id = substr(search, RLENGTH + 1) - search = "identifier:" id - } - - # special case to list similar items - if (match(search, /^similar:/)) { - id = substr(search, RLENGTH + 1) - - url = api_endpoint "/details/" id "?RelatedItemsGet=1" - api_request(url, "GET", iaout) - - # scrape similar items - FS = "\t" - items = 0 - delete item - str = "" - while ((getline 0) { - if (match($0, /iaout - close(iaout) - - for (i = 1; i <= items; i++) { - if (i == 1) { - search = "identifier:" item[i] - } else { - search = search "%20OR%20identifier:" item[i] - } - } - } - - # remove quotes from search string, since it gets quoted later - gsub(/"/, "", search) - - # default sort orders if none were specified - if (length(order) == 0) { - if (search == "mediatype:collection" || - search == "mediatype:(collection)") - { - order = "collection_size desc" - sort_param = "sort" order - } else { - order = "nav_order desc" - sort_param = "sort" order - } - } - - # get search results - - field[1] = "creator" - field[2] = "description" - field[3] = "identifier" - field[4] = "mediatype" - field[5] = "title" - fields = 5 - - # remove anyfield, a hobgoblin of consistency - searchstr = search - gsub(/anyfield:/, "", searchstr) - - url = sprintf("%s/advancedsearch.php?q=%s&output=json&rows=%d&page=%d", - api_endpoint, searchstr, rows, page) - if (length(order) > 0) { - split(order, parts, " ") - url = url sprintf("&sort%%5B0%%5D=%s %s", order_names[parts[1]], - parts[2]) - } - for (i = 1; i <= fields; i++) { - url = url sprintf("&fl%%5B%d%%5D=%s", i - 1, field[i]) - } - api_request(url, "GET", iaout) - - cmd = sprintf("%s <%s >%s 2>&1", cmd_json2tsv, iaout, jsout) - system(cmd) - - numfound = 0 - FS = "\t" - while ((getline 0) { - if ($1 == ".response.numFound" && $2 == "n") { - numfound = $3 - } - } - close(jsout) - - if (search ~ /^@/) { - numfound++ - } - if (numfound == 0) { - print "Your search did not match any items in the Archive." - print "Try different keywords or a more general search." - print "" - printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port - unlink(jsout) - unlink(iaout) - return - } else { - pages = int(numfound / rows) - if (numfound % rows != 0) { - pages++ - } - printf "# %s search results, page %d of %d\n", numfound, - page, pages - print "" - } - - # format search results as a gopher directory (menu) - FS = "\t" - creator = "" - descr = "" - id = "" - title = "" - type = "" - count = 0 - - if (search ~ /^@/) { - printf "[1|Account %s|%s/account/%s|%s|%s]\n", search, cgipath, - search, server, port - } - - while ((getline 0) { - if ($1 == ".response.docs[].creator" && $2 == "s") { - creator = $3 - } else if ($1 == ".response.docs[].description" && $2 == "s") { - descr = $3 - } else if ($1 == ".response.docs[].identifier" && $2 == "s") { - id = $3 - } else if ($1 == ".response.docs[].mediatype" && $2 == "s") { - type = $3 - } else if ($1 == ".response.docs[].title" && $2 == "s") { - # the title field happens to be toward the end of each item - title = $3 - count++ - if (length(creator) > 0) { - label = sprintf("[%s] %s by %s", mediatype[type], - gph_encode(shorten(title, 40)), shorten(creator, 18)) - } else { - label = sprintf("[%s] %s", mediatype[type], - gph_encode(shorten(title, 58))) - } - if (type == "collection") { - printf "[1|%s|%s/search/%%09collection:(%s)|%s|%s]\n", - label, cgipath, id, server, port - } else { - printf "[1|%s|%s/details/%s|%s|%s]\n", label, cgipath, - id, server, port - } - creator = "" - descr = "" - id = "" - type = "" - } - } - close(jsout) - - print "" - - # only show "page back" if the user is past page 1 - if (page > 1) { - printf "[1|[<<] Page %d|%s/search/page%d/rows%d/%s%%09%s|%s|%s]\n", - page - 1, cgipath, page - 1, rows, sort_param, search, - server, port - } - - # only show "next page" if the current page is completely full - if (count == rows) { - printf "[1|[>>] Page %d|%s/search/page%d/rows%d/%s%%09%s|%s|%s]\n", - page + 1, cgipath, page + 1, rows, sort_param, search, - server, port - } - - # only show "sort" if there's more than one item to sort - if (count > 1) { - printf "[1|[^v] Sort|%s/sort/%%09%s|%s|%s]\n", cgipath, search, - server, port - } - - # only show "search within list" if there's multiple pages of results - if (numfound > rows) { - printf "[1|[\\/] Filter results|%s/wizard/step1/%s|%s|%s]\n", - cgipath, search, server, port - } - - printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port - - unlink(jsout) - unlink(iaout) - exit 0 -} - -BEGIN { - config_init() - - cgi_init() - uri_encode_init() - util_init() - main(search) -} ADDED src/software/gophermap.m4 Index: src/software/gophermap.m4 ================================================================== --- /dev/null +++ src/software/gophermap.m4 @@ -0,0 +1,28 @@ +include(config.m4)dnl + +[1|All Software|__CGIPATH__/search/sortweek desc/%09mediatype:software|__SERVER__|__PORT__] +[1|This Just In|__CGIPATH__/search/sortaddeddate desc/%09mediatype:software|__SERVER__|__PORT__] +[1|Internet Arcade|__CGIPATH__/search/sortweek desc/%09collection:internetarcade|__SERVER__|__PORT__] +[1|Console Living Room|__CGIPATH__/search/sortweek desc/%09collection:consolelivingroom|__SERVER__|__PORT__] +[1|Old School Emulation|__CGIPATH__/search/sortweek desc/%09collection:tosec|__SERVER__|__PORT__] +[1|MS-DOS Games|__CGIPATH__/search/sortweek desc/%09collection:softwarelibrary_msdos_games|__SERVER__|__PORT__] +[1|Historical Software|__CGIPATH__/search/sortweek desc/%09collection:historicalsoftware|__SERVER__|__PORT__] +[1|Classic PC Games|__CGIPATH__/search/sortweek desc/%09collection:classicpcgames|__SERVER__|__PORT__] +[1|Software Library|__CGIPATH__/search/sortweek desc/%09collection:softwarelibrary AND mediatype:collection|__SERVER__|__PORT__] +[1|Kodi Archive & Support Files|__CGIPATH__/search/sortweek desc/%09collection:kodi_archive|__SERVER__|__PORT__] +[1|Vintage Software|__CGIPATH__/search/sortweek desc/%09collection:vintagesoftware|__SERVER__|__PORT__] +[1|APK|__CGIPATH__/search/sortweek desc/%09collection:apkarchive|__SERVER__|__PORT__] +[1|MS-DOS|__CGIPATH__/search/sortweek desc/%09collection:softwarelibrary_msdos|__SERVER__|__PORT__] +[1|CD-ROM Software|__CGIPATH__/search/sortweek desc/%09collection:cd-roms|__SERVER__|__PORT__] +[1|CD-ROM Software Library|__CGIPATH__/search/sortweek desc/%09collection:cdromsoftware|__SERVER__|__PORT__] +[1|Software Sites|__CGIPATH__/search/sortweek desc/%09collection:softwaresites|__SERVER__|__PORT__] +[1|Tucows Software Library|__CGIPATH__/search/sortweek desc/%09collection:tucows|__SERVER__|__PORT__] +[1|Shareware CD-ROMs|__CGIPATH__/search/sortweek desc/%09collection:cdbbsarchive|__SERVER__|__PORT__] +[1|Software Capsules Compilation|__CGIPATH__/search/sortweek desc/%09collection:softwarecapsules|__SERVER__|__PORT__] +[1|CD-ROM Images|__CGIPATH__/search/sortweek desc/%09collection:cdromimages|__SERVER__|__PORT__] +[1|Underground CD-ROM CompilationsLibrary|__CGIPATH__/search/sortweek desc/%09collection:undergroundcds|__SERVER__|__PORT__] +[1|ZX Spectrum|__CGIPATH__/search/sortweek desc/%09collection:softwarelibrary_zx_spectrum|__SERVER__|__PORT__] +[1|DOOM Level CD|__CGIPATH__/search/sortweek desc/%09collection:doom-cds|__SERVER__|__PORT__] +[1|Floppy Disks of Software|__CGIPATH__/search/sortweek desc/%09collection:floppysoftware|__SERVER__|__PORT__] +[1|The Good Old Days IBM PC Floppy Collection|__CGIPATH__/search/sortweek desc/%09collection:TGODFloppyCollection|__SERVER__|__PORT__] +[1|MS-DOS: The Frostbyte Shareware Collection|__CGIPATH__/search/sortweek desc/%09collection:softwarelibrary_msdos_frostbyte|__SERVER__|__PORT__] DELETED src/software/index.gph.m4 Index: src/software/index.gph.m4 ================================================================== --- src/software/index.gph.m4 +++ /dev/null @@ -1,28 +0,0 @@ -include(config.m4)dnl - -[1|All Software|__CGIPATH__/search/sortweek desc/%09mediatype:software|__SERVER__|__PORT__] -[1|This Just In|__CGIPATH__/search/sortaddeddate desc/%09mediatype:software|__SERVER__|__PORT__] -[1|Internet Arcade|__CGIPATH__/search/sortweek desc/%09collection:internetarcade|__SERVER__|__PORT__] -[1|Console Living Room|__CGIPATH__/search/sortweek desc/%09collection:consolelivingroom|__SERVER__|__PORT__] -[1|Old School Emulation|__CGIPATH__/search/sortweek desc/%09collection:tosec|__SERVER__|__PORT__] -[1|MS-DOS Games|__CGIPATH__/search/sortweek desc/%09collection:softwarelibrary_msdos_games|__SERVER__|__PORT__] -[1|Historical Software|__CGIPATH__/search/sortweek desc/%09collection:historicalsoftware|__SERVER__|__PORT__] -[1|Classic PC Games|__CGIPATH__/search/sortweek desc/%09collection:classicpcgames|__SERVER__|__PORT__] -[1|Software Library|__CGIPATH__/search/sortweek desc/%09collection:softwarelibrary AND mediatype:collection|__SERVER__|__PORT__] -[1|Kodi Archive & Support Files|__CGIPATH__/search/sortweek desc/%09collection:kodi_archive|__SERVER__|__PORT__] -[1|Vintage Software|__CGIPATH__/search/sortweek desc/%09collection:vintagesoftware|__SERVER__|__PORT__] -[1|APK|__CGIPATH__/search/sortweek desc/%09collection:apkarchive|__SERVER__|__PORT__] -[1|MS-DOS|__CGIPATH__/search/sortweek desc/%09collection:softwarelibrary_msdos|__SERVER__|__PORT__] -[1|CD-ROM Software|__CGIPATH__/search/sortweek desc/%09collection:cd-roms|__SERVER__|__PORT__] -[1|CD-ROM Software Library|__CGIPATH__/search/sortweek desc/%09collection:cdromsoftware|__SERVER__|__PORT__] -[1|Software Sites|__CGIPATH__/search/sortweek desc/%09collection:softwaresites|__SERVER__|__PORT__] -[1|Tucows Software Library|__CGIPATH__/search/sortweek desc/%09collection:tucows|__SERVER__|__PORT__] -[1|Shareware CD-ROMs|__CGIPATH__/search/sortweek desc/%09collection:cdbbsarchive|__SERVER__|__PORT__] -[1|Software Capsules Compilation|__CGIPATH__/search/sortweek desc/%09collection:softwarecapsules|__SERVER__|__PORT__] -[1|CD-ROM Images|__CGIPATH__/search/sortweek desc/%09collection:cdromimages|__SERVER__|__PORT__] -[1|Underground CD-ROM CompilationsLibrary|__CGIPATH__/search/sortweek desc/%09collection:undergroundcds|__SERVER__|__PORT__] -[1|ZX Spectrum|__CGIPATH__/search/sortweek desc/%09collection:softwarelibrary_zx_spectrum|__SERVER__|__PORT__] -[1|DOOM Level CD|__CGIPATH__/search/sortweek desc/%09collection:doom-cds|__SERVER__|__PORT__] -[1|Floppy Disks of Software|__CGIPATH__/search/sortweek desc/%09collection:floppysoftware|__SERVER__|__PORT__] -[1|The Good Old Days IBM PC Floppy Collection|__CGIPATH__/search/sortweek desc/%09collection:TGODFloppyCollection|__SERVER__|__PORT__] -[1|MS-DOS: The Frostbyte Shareware Collection|__CGIPATH__/search/sortweek desc/%09collection:softwarelibrary_msdos_frostbyte|__SERVER__|__PORT__] ADDED src/sort.m4 Index: src/sort.m4 ================================================================== --- /dev/null +++ src/sort.m4 @@ -0,0 +1,61 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# __CGIPATH__/sort +# +# Change search sort order + +include(src/config.awk) +incl(src/cgi.awk) + +function main( i, lbl, opt) { + lbl[1] = "Default [^]" + opt[1] = "nav_order asc" + lbl[2] = "Default [v]" + opt[2] = "nav_order desc" + lbl[3] = "Weekly views [^]" + opt[3] = "week asc" + lbl[4] = "Weekly views [v]" + opt[4] = "week desc" + lbl[5] = "All-time views [^]" + opt[5] = "downloads asc" + lbl[6] = "All-time views [v]" + opt[6] = "downloads desc" + lbl[7] = "Title [^]" + opt[7] = "title asc" + lbl[8] = "Title [v]" + opt[8] = "title desc" + lbl[9] = "Date added [^]" + opt[9] = "addeddate asc" + lbl[10] = "Date added [v]" + opt[10] = "addeddate desc" + lbl[11] = "Date created [^]" + opt[11] = "createddate asc" + lbl[12] = "Date created [v]" + opt[12] = "createddate desc" + lbl[13] = "Date published [^]" + opt[13] = "date asc" + lbl[14] = "Date published [v]" + opt[14] = "date desc" + lbl[15] = "Creator [^]" + opt[15] = "creator asc" + lbl[16] = "Creator [v]" + opt[16] = "creator desc" + lbl[17] = "Random" + opt[17] = "random asc" + + print "# Sort by" + print "" + for (i = 1; i < 18; i++) { + printf "1%s\t%s/search?%s/sort%s\t%s\t%s\n", + lbl[i], cgipath, search, opt[i], server, port + } + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + main() +} DELETED src/sort/index.dcgi.m4 Index: src/sort/index.dcgi.m4 ================================================================== --- src/sort/index.dcgi.m4 +++ /dev/null @@ -1,61 +0,0 @@ -include(config.m4)dnl -#!__CMD_AWK__ -f - -# sort/index.dcgi -# -# Change search sort order - -include(src/config.awk) -incl(src/cgi.awk) - -function main( i, lbl, opt) { - lbl[1] = "Default [^]" - opt[1] = "nav_order asc" - lbl[2] = "Default [v]" - opt[2] = "nav_order desc" - lbl[3] = "Weekly views [^]" - opt[3] = "week asc" - lbl[4] = "Weekly views [v]" - opt[4] = "week desc" - lbl[5] = "All-time views [^]" - opt[5] = "downloads asc" - lbl[6] = "All-time views [v]" - opt[6] = "downloads desc" - lbl[7] = "Title [^]" - opt[7] = "title asc" - lbl[8] = "Title [v]" - opt[8] = "title desc" - lbl[9] = "Date added [^]" - opt[9] = "addeddate asc" - lbl[10] = "Date added [v]" - opt[10] = "addeddate desc" - lbl[11] = "Date created [^]" - opt[11] = "createddate asc" - lbl[12] = "Date created [v]" - opt[12] = "createddate desc" - lbl[13] = "Date published [^]" - opt[13] = "date asc" - lbl[14] = "Date published [v]" - opt[14] = "date desc" - lbl[15] = "Creator [^]" - opt[15] = "creator asc" - lbl[16] = "Creator [v]" - opt[16] = "creator desc" - lbl[17] = "Random" - opt[17] = "random asc" - - print "# Sort by" - print "" - for (i = 1; i < 18; i++) { - printf "[1|%s|%s/search/sort%s%%09%s|%s|%s]\n", - lbl[i], cgipath, opt[i], search, server, port - } - exit 0 -} - -BEGIN { - config_init() - - cgi_init() - main() -} Index: src/util.awk ================================================================== --- src/util.awk +++ src/util.awk @@ -117,17 +117,17 @@ print "" >>output print "Items may be taken down for various reasons," >>output print "including by decision of the uploader or" >>output print "due to a violation of the Terms of Use." >>output print "" >>output - printf "[h|Metadata|URL:%s|%s|%s]\n", url, server, port >>output + printf "hMetadata\tURL:%s\t%s\t%s\n", url, server, port >>output print "" >>output url = api_ssl_endpoint "/about/terms.php" - printf "[0|Terms of Use|%s/text/%%09%s|%s|%s]\n", cgipath, + printf "0Terms of Use\t%s/text?%s\t%s\t%s\n", cgipath, url, server, port >>output print "" >>output - printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port >>output + printf "1PHAROS\t%s\t%s\t%s\n", docpath, server, port >>output return } function read_file(name, retval) { while ((getline 0) { ADDED src/video/gophermap.m4 Index: src/video/gophermap.m4 ================================================================== --- /dev/null +++ src/video/gophermap.m4 @@ -0,0 +1,23 @@ +include(config.m4)dnl +# Video + +[1|All Video|__CGIPATH__/search/sortweek desc/%09mediatype:movies|__SERVER__|__PORT__] +[1|This Just In|__CGIPATH__/search/sortaddeddate desc/%09mediatype:movies|__SERVER__|__PORT__] +[1|Prelinger Archives|__CGIPATH__/search/sortweek desc/%09collection:prelinger|__SERVER__|__PORT__] +[1|Democracy Now!|__CGIPATH__/search/sortweek desc/%09collection:democracy_now_vid|__SERVER__|__PORT__] +[1|Occupy Wall Street|__CGIPATH__/search/sortweek desc/%09collection:occupywallstreet|__SERVER__|__PORT__] +[1|TV NSA Clip Library|__CGIPATH__/search/sortweek desc/%09collection:nsa|__SERVER__|__PORT__] +[1|Animation And Cartoons|__CGIPATH__/search/sortweek desc/%09collection:animationandcartoons|__SERVER__|__PORT__] +[1|Arts & Music|__CGIPATH__/search/sortweek desc/%09collection:artsandmusicvideos|__SERVER__|__PORT__] +[1|Computers & Technology|__CGIPATH__/search/sortweek desc/%09collection:computersandtechvideos|__SERVER__|__PORT__] +[1|Cultural & Academic Films|__CGIPATH__/search/sortweek desc/%09collection:culturalandacademicfilms|__SERVER__|__PORT__] +[1|Ephemeral Films|__CGIPATH__/search/sortweek desc/%09collection:ephemera|__SERVER__|__PORT__] +[1|Movies|__CGIPATH__/search/sortweek desc/%09collection:moviesandfilms|__SERVER__|__PORT__] +[1|News & Public Affairs|__CGIPATH__/search/sortweek desc/%09collection:newsandpublicaffairs|__SERVER__|__PORT__] +[1|Spirituality & Religion|__CGIPATH__/search/sortweek desc/%09collection:spiritualityandreligion|__SERVER__|__PORT__] +[1|Sports|__CGIPATH__/search/sortweek desc/%09collection:sports|__SERVER__|__PORT__] +[1|Television|__CGIPATH__/search/sortweek desc/%09collection:television AND mediatype:collection|__SERVER__|__PORT__] +[1|VHS Vault|__CGIPATH__/search/sortweek desc/%09collection:vhsvault|__SERVER__|__PORT__] +[1|Video Games|__CGIPATH__/search/sortweek desc/%09collection:gamevideos AND mediatype:collection|__SERVER__|__PORT__] +[1|Vlogs|__CGIPATH__/search/sortweek desc/%09collection:vlogs|__SERVER__|__PORT__] +[1|Youth Media|__CGIPATH__/search/sortweek desc/%09collection:youth_media|__SERVER__|__PORT__] DELETED src/video/index.gph.m4 Index: src/video/index.gph.m4 ================================================================== --- src/video/index.gph.m4 +++ /dev/null @@ -1,23 +0,0 @@ -include(config.m4)dnl -# Video - -[1|All Video|__CGIPATH__/search/sortweek desc/%09mediatype:movies|__SERVER__|__PORT__] -[1|This Just In|__CGIPATH__/search/sortaddeddate desc/%09mediatype:movies|__SERVER__|__PORT__] -[1|Prelinger Archives|__CGIPATH__/search/sortweek desc/%09collection:prelinger|__SERVER__|__PORT__] -[1|Democracy Now!|__CGIPATH__/search/sortweek desc/%09collection:democracy_now_vid|__SERVER__|__PORT__] -[1|Occupy Wall Street|__CGIPATH__/search/sortweek desc/%09collection:occupywallstreet|__SERVER__|__PORT__] -[1|TV NSA Clip Library|__CGIPATH__/search/sortweek desc/%09collection:nsa|__SERVER__|__PORT__] -[1|Animation And Cartoons|__CGIPATH__/search/sortweek desc/%09collection:animationandcartoons|__SERVER__|__PORT__] -[1|Arts & Music|__CGIPATH__/search/sortweek desc/%09collection:artsandmusicvideos|__SERVER__|__PORT__] -[1|Computers & Technology|__CGIPATH__/search/sortweek desc/%09collection:computersandtechvideos|__SERVER__|__PORT__] -[1|Cultural & Academic Films|__CGIPATH__/search/sortweek desc/%09collection:culturalandacademicfilms|__SERVER__|__PORT__] -[1|Ephemeral Films|__CGIPATH__/search/sortweek desc/%09collection:ephemera|__SERVER__|__PORT__] -[1|Movies|__CGIPATH__/search/sortweek desc/%09collection:moviesandfilms|__SERVER__|__PORT__] -[1|News & Public Affairs|__CGIPATH__/search/sortweek desc/%09collection:newsandpublicaffairs|__SERVER__|__PORT__] -[1|Spirituality & Religion|__CGIPATH__/search/sortweek desc/%09collection:spiritualityandreligion|__SERVER__|__PORT__] -[1|Sports|__CGIPATH__/search/sortweek desc/%09collection:sports|__SERVER__|__PORT__] -[1|Television|__CGIPATH__/search/sortweek desc/%09collection:television AND mediatype:collection|__SERVER__|__PORT__] -[1|VHS Vault|__CGIPATH__/search/sortweek desc/%09collection:vhsvault|__SERVER__|__PORT__] -[1|Video Games|__CGIPATH__/search/sortweek desc/%09collection:gamevideos AND mediatype:collection|__SERVER__|__PORT__] -[1|Vlogs|__CGIPATH__/search/sortweek desc/%09collection:vlogs|__SERVER__|__PORT__] -[1|Youth Media|__CGIPATH__/search/sortweek desc/%09collection:youth_media|__SERVER__|__PORT__] Index: src/web.awk ================================================================== --- src/web.awk +++ src/web.awk @@ -1,8 +1,7 @@ function dump(search, type, base, cmd, curlcfg, is_html, is_image, - label, limit, link, marker, parts, prefix, proto, relative, root, - url) + label, limit, link, marker, parts, proto, relative, root, url) { url = search gsub(/%3F/, "?", url) if (url !~ /^(http|https):\/\/[[:alnum:].-]+(:[0-9]+)*(\/[[:alnum:].,?@~=%%:\/+&_() -]*)*$/) { @@ -75,32 +74,32 @@ marker = 999999 if (type == TYPE_LINKS) { is_html = detect_html(url) is_image = detect_image(url) - printf "[9|Binary download|%s/raw/%%09%s|%s|%s]\n", cgipath, + printf "9Binary download\t%s/raw?%s\t%s\t%s\n", cgipath, search, server, port if (is_image) { - printf "[I|Image view|%s/raw/%%09%s|%s|%s]\n", cgipath, + printf "IImage view\t%s/raw?%s\t%s\t%s\n", cgipath, search, server, port } if (is_html) { label = "Source" } else { label = "Text view" } - printf "[0|%s|%s/raw/%%09%s|%s|%s]\n", label, cgipath, search, + printf "0%s\t%s/raw?%s\t%s\t%s\n", label, cgipath, search, server, port if (is_html) { label = "HTML view" } else { label = "Strings" } - printf "[0|%s|%s/text/%%09%s|%s|%s]\n", label, cgipath, search, - server, port - printf "[0|Headers|%s/debug/%%09%s|%s|%s]\n", cgipath, search, - server, port + printf "0%s\t%s/text?%s\t%s\t%s\n", label, cgipath, + search, server, port + printf "0Headers\t%s/debug?%s\t%s\t%s\n", cgipath, + search, server, port print "" } while ((cmd | getline) > 0) { if (NR < marker) { @@ -191,11 +190,11 @@ id = substr(id, 1, RSTART - 1) } } if (length(id) > 0) { label = prefix id - printf "[1|%s|%s/details/%s|%s|%s]\n", label, cgipath, + printf "1%s\t%s/details?%s\t%s\t%s\n", label, cgipath, id, server, port >>output } else { print str >>output } } else { ADDED src/wizard/gophermap Index: src/wizard/gophermap ================================================================== --- /dev/null +++ src/wizard/gophermap @@ -0,0 +1,10 @@ +i , _ +i /| | | +i _/_\_ >_< +i .-\-/. | +i / | | \_ | +i \ \| |\__(/ +i /(`---') | +i / / \ | +i _.' \'-' / | +i `----'`=-=' ' hjw ADDED src/wizard/step1.m4 Index: src/wizard/step1.m4 ================================================================== --- /dev/null +++ src/wizard/step1.m4 @@ -0,0 +1,65 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# __CGIPATH__/wizard/step1 +# +# Select field to filter/search by + +include(src/config.awk) +incl(src/cgi.awk) + +function main( i, lbl, opt) { + lbl[1] = "Any field contains" + opt[1] = "anyfield" + lbl[2] = "Any field does not contain" + opt[2] = "-anyfield" + lbl[3] = "Title contains" + opt[3] = "title" + lbl[4] = "Title does not contain" + opt[4] = "-title" + lbl[5] = "Creator contains" + opt[5] = "creator" + lbl[6] = "Creator does not contain" + opt[6] = "-creator" + lbl[7] = "Description contains" + opt[7] = "description" + lbl[8] = "Description does not contain" + opt[8] = "-description" + lbl[9] = "Collection is" + opt[9] = "collection" + lbl[10] = "Collection does not contain" + opt[10] = "-collection" + lbl[11] = "Mediatype is" + opt[11] = "mediatype" + lbl[12] = "Mediatype does not contain" + opt[12] = "-mediatype" + lbl[13] = "Date or date range is" + opt[13] = "date" + lbl[14] = "Language contains" + opt[14] = "language" + lbl[15] = "Always available" + opt[15] = "-access-restricted-item" + + print "# Search wizard: Select field" + print "" + for (i = 1; i < 16; i++) { + if (opt[i] ~ /mediatype$/) { + printf "1%s\t%s/wizard/step2?%s/%s\t%s\t%]\n", + lbl[i], cgipath, search, opt[i], server, port + } else if (lbl[i] == "Always available") { + printf "1%s\t%s/wizard/step3?%s/%s/true\t%s\t%s\n", + lbl[i], cgipath, search, opt[i], server, port + } else { + printf "7%s\t%s/wizard/step3?%s/%s\t%s\t%s\n", + lbl[i], cgipath, search, opt[i], server, port + } + } + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + main() +} DELETED src/wizard/step1/index.dcgi.m4 Index: src/wizard/step1/index.dcgi.m4 ================================================================== --- src/wizard/step1/index.dcgi.m4 +++ /dev/null @@ -1,67 +0,0 @@ -include(config.m4)dnl -#!__CMD_AWK__ -f - -# wizard/step1/index.dcgi -# -# Select field to filter/search by - -include(src/config.awk) -incl(src/cgi.awk) - -function main( i, lbl, opt, searchstr) { - searchstr = parts[4] - - lbl[1] = "Any field contains" - opt[1] = "anyfield" - lbl[2] = "Any field does not contain" - opt[2] = "-anyfield" - lbl[3] = "Title contains" - opt[3] = "title" - lbl[4] = "Title does not contain" - opt[4] = "-title" - lbl[5] = "Creator contains" - opt[5] = "creator" - lbl[6] = "Creator does not contain" - opt[6] = "-creator" - lbl[7] = "Description contains" - opt[7] = "description" - lbl[8] = "Description does not contain" - opt[8] = "-description" - lbl[9] = "Collection is" - opt[9] = "collection" - lbl[10] = "Collection does not contain" - opt[10] = "-collection" - lbl[11] = "Mediatype is" - opt[11] = "mediatype" - lbl[12] = "Mediatype does not contain" - opt[12] = "-mediatype" - lbl[13] = "Date or date range is" - opt[13] = "date" - lbl[14] = "Language contains" - opt[14] = "language" - lbl[15] = "Always available" - opt[15] = "-access-restricted-item" - - print "# Search wizard: Select field" - print "" - for (i = 1; i < 16; i++) { - if (opt[i] ~ /mediatype$/) { - printf "[1|%s|%s/wizard/step2/%s/%s|%s|%s]\n", lbl[i], - cgipath, opt[i], searchstr, server, port - } else if (lbl[i] == "Always available") { - printf "[1|%s|%s/wizard/step3/%s/%s%%09true|%s|%s]\n", - lbl[i], cgipath, opt[i], searchstr, server, port - } else { - printf "[7|%s|%s/wizard/step3/%s/%s|%s|%s]\n", lbl[i], - cgipath, opt[i], searchstr, server, port - } - } - exit 0 -} - -BEGIN { - config_init() - - cgi_init() - main() -} ADDED src/wizard/step2.m4 Index: src/wizard/step2.m4 ================================================================== --- /dev/null +++ src/wizard/step2.m4 @@ -0,0 +1,51 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# __CGIPATH__/wizard/step2 +# +# Select mediatype to filter/search by + +include(src/config.awk) +incl(src/cgi.awk) + +function main( field, newsearch, searchstr) { + field = parts[4] + searchstr = parts[5] + + if (field == "mediatype") { + print "# Mediatype is:" + } else { + print "# Mediatype does not contain:" + } + print "" + + lbl[1] = "audio" + lbl[2] = "collection" + lbl[3] = "data" + lbl[4] = "etree" + lbl[5] = "image" + lbl[6] = "movies" + lbl[7] = "software" + lbl[8] = "texts" + lbl[9] = "web" + for (i = 1; i < 10; i++) { + if (length(searchstr) == 0) { + newsearch = sprintf("%s:(%s)", field, lbl[i]) + } else { + newsearch = sprintf("%s AND %s:(%s)", searchstr, field, lbl[i]) + } + printf "1%s\t%s/search?%s\t%s\t%s\n", lbl[i], cgipath, + newsearch, server, port + } + print "# Progress:" + print "" + print "* Field: Mediatype" + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + main() +} DELETED src/wizard/step2/index.dcgi.m4 Index: src/wizard/step2/index.dcgi.m4 ================================================================== --- src/wizard/step2/index.dcgi.m4 +++ /dev/null @@ -1,51 +0,0 @@ -include(config.m4)dnl -#!__CMD_AWK__ -f - -# wizard/step2/index.dcgi -# -# Select mediatype to filter/search by - -include(src/config.awk) -incl(src/cgi.awk) - -function main( field, newsearch, searchstr) { - field = parts[4] - searchstr = parts[5] - - if (field == "mediatype") { - print "# Mediatype is:" - } else { - print "# Mediatype does not contain:" - } - print "" - - lbl[1] = "audio" - lbl[2] = "collection" - lbl[3] = "data" - lbl[4] = "etree" - lbl[5] = "image" - lbl[6] = "movies" - lbl[7] = "software" - lbl[8] = "texts" - lbl[9] = "web" - for (i = 1; i < 10; i++) { - if (length(searchstr) == 0) { - newsearch = sprintf("%s:(%s)", field, lbl[i]) - } else { - newsearch = sprintf("%s AND %s:(%s)", searchstr, field, lbl[i]) - } - printf "[1|%s|%s/search/%%09%s|%s|%s]\n", lbl[i], cgipath, - newsearch, server, port - } - print "# Progress:" - print "" - print "* Field: Mediatype" - exit 0 -} - -BEGIN { - config_init() - - cgi_init() - main() -} ADDED src/wizard/step3.m4 Index: src/wizard/step3.m4 ================================================================== --- /dev/null +++ src/wizard/step3.m4 @@ -0,0 +1,45 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# __CGIPATH__/wizard/step3 +# +# Apply new search terms + +include(src/config.awk) +incl(src/cgi.awk) + +function main( field, label, newsearch, op, searchstr, value) { + split(search, parts, "/") + searchstr = parts[1] + field = parts[2] + value = searchreq + + if (field ~ /^-/) { + label = toupper(substr(field, 2, 1)) substr(field, 3) + op = "does not contain" + } else { + label = toupper(substr(field, 1, 1)) substr(field, 2) + op = "contains" + } + if (length(searchstr) == 0) { + newsearch = sprintf("%s:(%s)", field, value) + } else { + newsearch = sprintf("%s AND %s:(%s)", searchstr, field, value) + } + print "" + printf "1Apply search criteria\t%s/search?%s\t%s\t%s\n", + cgipath, newsearch, server, port + print "" + print "# Progress:" + print "" + printf "* Field %s %s %s\n", label, op, value + printf "* New search: %s\n", newsearch + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + main() +} DELETED src/wizard/step3/index.dcgi.m4 Index: src/wizard/step3/index.dcgi.m4 ================================================================== --- src/wizard/step3/index.dcgi.m4 +++ /dev/null @@ -1,44 +0,0 @@ -include(config.m4)dnl -#!__CMD_AWK__ -f - -# wizard/step3/index.dcgi -# -# Apply new search terms - -include(src/config.awk) -incl(src/cgi.awk) - -function main( field, label, newsearch, op, searchstr, value) { - field = parts[4] - searchstr = parts[5] - value = search - - if (field ~ /^-/) { - label = toupper(substr(field, 2, 1)) substr(field, 3) - op = "does not contain" - } else { - label = toupper(substr(field, 1, 1)) substr(field, 2) - op = "contains" - } - if (length(searchstr) == 0) { - newsearch = sprintf("%s:(%s)", field, value) - } else { - newsearch = sprintf("%s AND %s:(%s)", searchstr, field, value) - } - print "" - printf "[1|Apply search criteria|%s/search/%%09%s|%s|%s]\n", - cgipath, newsearch, server, port - print "" - print "# Progress:" - print "" - printf "* Field %s %s %s\n", label, op, value - printf "* New search: %s\n", newsearch - exit 0 -} - -BEGIN { - config_init() - - cgi_init() - main() -} ]]> 2025-11-09 01:26:03 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/3fd6e38a37/ ben 2025-11-06 14:36:35 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/68d99a56a7/ ben max_bin_size * size_mb) { + if (max_bin_size > 0 && file_size[i] > max_bin_size * size_mb) { printf "[h|%s|URL:%s|%s|%s]\n", label, uri_encode(url), server, port } else { printf "[1|%s|%s/links/%%09%s|%s|%s]\n", label, cgipath, url, server, port Index: src/web.awk ================================================================== --- src/web.awk +++ src/web.awk @@ -19,11 +19,13 @@ # Use temporary file for curl configuration. # This keeps user input separate from shell execution. curlcfg = gettemp() printf "--connect-timeout 10\n" > curlcfg - printf "--max-filesize %dM\n", limit >> curlcfg + if (limit > 0) { + printf "--max-filesize %dM\n", limit >> curlcfg + } printf "--max-redirs 0\n" >> curlcfg printf "--proto =http,https\n" >> curlcfg printf "--show-error\n" >> curlcfg printf "--silent\n" >> curlcfg printf "--url %s\n", uri_encode(url) >> curlcfg ]]> 2025-11-06 14:33:16 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/4208c74e8f/ ben 2025-11-02 16:42:19 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/9ce146e3ef/ ben 2025-11-02 16:33:28 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/40f3523863/ ben 2025-10-31 13:17:19 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/b6aa850d49/ ben 2025-10-18 19:19:14 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/a76eb8fc2f/ ben 2025-10-18 19:15:54 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/fff249e112/ ben 2025-10-12 01:42:41 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/8dee409f02/ ben 2025-09-05 15:10:45 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/46a8783ec6/ ben 2025-08-28 19:06:49 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/9f7a83ab8d/ ben 2025-08-27 16:22:47 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/bea905f030/ ben 2025-08-26 19:56:21 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/d18a2a633c/ ben 2025-08-01 07:01:15 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/303250f6bc/ ben 0) { - if (match(/^#/, $0)) { - # ignore comments - continue - } - if (ip == $1) { - blocked = 0 - break - } - } - close(pass_list) - if (blocked) { - block_msg(ip) - exit(0) - } - } search = ARGV[1] arguments = ARGV[2] traversal = ARGV[5] selector = ARGV[6] @@ -87,10 +67,31 @@ path = substr(path, 1, RSTART - 1) } split(path, parts, "/") topdir = parts[2] + + if (pass_enabled) { + # default deny access except client IP addresses in pass list + blocked = 1 + FS = "\t" + while ((getline < pass_list) > 0) { + if (match(/^#/, $0)) { + # ignore comments + continue + } + if (ip == $1) { + blocked = 0 + break + } + } + close(pass_list) + if (blocked) { + block_msg(ip) + exit(0) + } + } return } function gph_encode(str, retval) { ]]> 2025-08-01 07:00:15 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/c5f1d3c11e/ ben 2025-08-01 06:00:14 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/8830b2f656/ ben INSERTED DELETED 0 1 src/books/index.gph.m4 0 1 TOTAL over 1 changed file Index: src/books/index.gph.m4 ================================================================== --- src/books/index.gph.m4 +++ src/books/index.gph.m4 @@ -1,9 +1,8 @@ include(config.m4)dnl # Books -[1|All Books|__CGIPATH__/search/sortweek desc/%09collection:books AND -access-restricted-item:true|__SERVER__|__PORT__] [1|All Texts|__CGIPATH__/search/sortweek desc/%09mediatype:texts AND -access-restricted-item:true|__SERVER__|__PORT__] [1|This Just In|__CGIPATH__/search/sortaddeddate desc/%09mediatype:texts AND -access-restricted-item:true|__SERVER__|__PORT__] [1|Smithsonian Libraries|__CGIPATH__/search/sortweek desc/%09collection:smithsonian|__SERVER__|__PORT__] [1|FEDLINK|__CGIPATH__/search/sortweek desc/%09collection:fedlink AND mediatype:collection|__SERVER__|__PORT__] [1|Genealogy|__CGIPATH__/search/sortweek desc/%09collection:genealogy AND mediatype:collection|__SERVER__|__PORT__] ]]> 2025-07-23 17:01:23 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/a85cea2208/ ben 2025-07-21 20:55:40 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/aa7c71cf55/ ben 0) { if (match(/^#/, $0)) { # ignore comments continue } ]]> 2025-07-06 23:18:38 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/9058a38d80/ ben 0) { + if (match(/^#/, $0)) { + # ignore comments + continue + } + if (ip == $1) { + blocked = 0 + break + } + } + close(pass_list) + if (blocked) { + block_msg(ip) + exit(0) + } + } + search = ARGV[1] arguments = ARGV[2] traversal = ARGV[5] selector = ARGV[6] Index: src/config.awk ================================================================== --- src/config.awk +++ src/config.awk @@ -13,12 +13,15 @@ cmd_rm = "__CMD_RM__" cmd_sqlite = "__CMD_SQLITE__" cmd_strings = "__CMD_STRINGS__" cmd_webdump = "__CMD_WEBDUMP__" cmd_xargs = "__CMD_XARGS__" + contact = "__CONTACT__" geomyidae_version = __GEOMYIDAE_VERSION__ max_bin_size = __MAX_BIN_SIZE__ max_txt_size = __MAX_TXT_SIZE__ + pass_enabled = __PASS_ENABLED__ + pass_list = "__PASS_LIST__" server = "__SERVER__" port = "__PORT__" return } ]]> 2025-07-06 02:08:13 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/3f32b09be6/ ben 0) { print str return Index: src/cgi.awk ================================================================== --- src/cgi.awk +++ src/cgi.awk @@ -1,17 +1,6 @@ function cgi_init( ip) { - blocked = 0 - ip = ENVIRON["REMOTE_ADDR"] - while ((getline < blocklist) > 0) { - # bad bot ignoring robots.txt, block by IP address - if (match(ip, $0)) { - blocked = 1 - break - } - } - close(blocklist) - search = ARGV[1] arguments = ARGV[2] traversal = ARGV[5] selector = ARGV[6] Index: src/config.awk ================================================================== --- src/config.awk +++ src/config.awk @@ -1,11 +1,10 @@ function config_init() { agent = "__AGENT__" api_endpoint = "__API_ENDPOINT__" api_ssl_endpoint = "__API_SSL_ENDPOINT__" awk_ext = __AWK_EXT__ - blocklist = "__BLOCKLIST__" cache_db = "__CACHE_DB__" cache_enabled = __CACHE_ENABLED__ cgipath = "__CGIPATH__" cmd_curl = "__CMD_CURL__" cmd_enc = "__CMD_ENV__" Index: src/details/index.dcgi.m4 ================================================================== --- src/details/index.dcgi.m4 +++ src/details/index.dcgi.m4 @@ -18,16 +18,10 @@ license, output, pub_date, scanner, signature, str, thumb, title, topic, topics, type, uploader_account, uploader_email, url) { item_id = parts[3] - if (blocked) { - printf "[h|Details|URL:%s/details/%s|%s|%s]\n", - api_ssl_endpoint, item_id, server, port - exit 0 - } - signature = "details/" item_id str = cache_init(signature) if (length(str) > 0) { print str return Index: src/download/index.dcgi.m4 ================================================================== --- src/download/index.dcgi.m4 +++ src/download/index.dcgi.m4 @@ -14,16 +14,10 @@ is_proxy, item_server, label, mtime, name, source, url) { dir = parts[2] item_id = parts[3] - if (blocked) { - printf "[h|Download|URL:%s/download/%s|%s|%s]\n", - api_ssl_endpoint, item_id, server, port - exit 0 - } - if (dir == "download") { is_proxy = 1 } else { # dir == "direct" is_proxy = 0 Index: src/list/index.dcgi.m4 ================================================================== --- src/list/index.dcgi.m4 +++ src/list/index.dcgi.m4 @@ -43,16 +43,10 @@ split(search, parts, "/") acct = parts[1] list_id = parts[2] - if (blocked) { - printf "[h|List|URL:%s/details/%s/lists/%d|%s|%s]\n", - api_ssl_endpoint, acct, list_id, server, port - exit 0 - } - signature = sprintf("list/%s/%s", input, search) str = cache_init(signature) if (length(str) > 0) { print str return Index: src/lists/index.dcgi.m4 ================================================================== --- src/lists/index.dcgi.m4 +++ src/lists/index.dcgi.m4 @@ -14,16 +14,10 @@ function main( cmd, count, fields, iaout, i, id, is_private, item, item_count, item_id, label, name, output, record, records, signature, str, url) { - if (blocked) { - printf "[h|Lists|URL:%s/details/%s/lists|%s|%s]\n", - api_ssl_endpoint, search, server, port - exit 0 - } - signature = sprintf("%s/lists", search) str = cache_init(signature) if (length(str) > 0) { print str return Index: src/listsort/index.dcgi.m4 ================================================================== --- src/listsort/index.dcgi.m4 +++ src/listsort/index.dcgi.m4 @@ -7,16 +7,10 @@ include(src/config.awk) incl(src/cgi.awk) function main( acct, i, lbl, list_id, opt) { - if (blocked) { - printf "[h|Internet Archive|URL:%s/|%s|%s]\n", - api_ssl_endpoint, server, port - exit 0 - } - lbl[1] = "Relevance" opt[1] = "" lbl[2] = "Weekly views [^]" opt[2] = "week asc" lbl[3] = "Weekly views [v]" Index: src/raw/index.cgi.m4 ================================================================== --- src/raw/index.cgi.m4 +++ src/raw/index.cgi.m4 @@ -22,16 +22,10 @@ incl(src/cgi.awk) incl(src/util.awk) incl(src/web.awk) function main() { - if (blocked) { - printf "[h|Internet Archive|URL:%s/|%s|%s]\n", - api_ssl_endpoint, server, port - exit 0 - } - if (path == "/debug/") { dump(search, TYPE_HEADERS) } else if (path == "/raw/") { dump(search, TYPE_RAW) } else if (path == "/text/") { Index: src/search/index.dcgi.m4 ================================================================== --- src/search/index.dcgi.m4 +++ src/search/index.dcgi.m4 @@ -13,16 +13,10 @@ function main(search, cmd, count, creator, descr, field, fields, i, iaout, id, item, items, jsout, label, numfound, order, order_names, page, rows, searchstr, sort_param, str, title, type, url) { - if (blocked) { - printf "[h|Search|URL:%s/|%s|%s]\n", api_ssl_endpoint, - server, port - exit 0 - } - order_names["addeddate"] = "addeddate" order_names["collection_size"] = "collection_size" order_names["createddate"] = "createddate" order_names["creator"] = "creatorSorter" order_names["date"] = "date" Index: src/sort/index.dcgi.m4 ================================================================== --- src/sort/index.dcgi.m4 +++ src/sort/index.dcgi.m4 @@ -7,16 +7,10 @@ include(src/config.awk) incl(src/cgi.awk) function main( i, lbl, opt) { - if (blocked) { - printf "[h|Internet Archive|URL:%s/|%s|%s]\n", - api_ssl_endpoint, server, port - exit 0 - } - lbl[1] = "Default [^]" opt[1] = "nav_order asc" lbl[2] = "Default [v]" opt[2] = "nav_order desc" lbl[3] = "Weekly views [^]" Index: src/wizard/step1/index.dcgi.m4 ================================================================== --- src/wizard/step1/index.dcgi.m4 +++ src/wizard/step1/index.dcgi.m4 @@ -7,16 +7,10 @@ include(src/config.awk) incl(src/cgi.awk) function main( i, lbl, opt, searchstr) { - if (blocked) { - printf "[h|Internet Archive|URL:%s/|%s|%s]\n", - api_ssl_endpoint, server, port - exit 0 - } - searchstr = parts[4] lbl[1] = "Any field contains" opt[1] = "anyfield" lbl[2] = "Any field does not contain" Index: src/wizard/step2/index.dcgi.m4 ================================================================== --- src/wizard/step2/index.dcgi.m4 +++ src/wizard/step2/index.dcgi.m4 @@ -7,16 +7,10 @@ include(src/config.awk) incl(src/cgi.awk) function main( field, newsearch, searchstr) { - if (blocked) { - printf "[h|Internet Archive|URL:%s/|%s|%s]\n", - api_ssl_endpoint, server, port - exit 0 - } - field = parts[4] searchstr = parts[5] if (field == "mediatype") { print "# Mediatype is:" Index: src/wizard/step3/index.dcgi.m4 ================================================================== --- src/wizard/step3/index.dcgi.m4 +++ src/wizard/step3/index.dcgi.m4 @@ -7,16 +7,10 @@ include(src/config.awk) incl(src/cgi.awk) function main( field, label, newsearch, op, searchstr, value) { - if (blocked) { - printf "[h|Internet Archive|URL:%s/|%s|%s]\n", - api_ssl_endpoint, server, port - exit 0 - } - field = parts[4] searchstr = parts[5] value = search if (field ~ /^-/) { ]]> 2025-07-06 01:31:02 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/7253bacd27/ ben 0) { print str return } ]]> 2025-06-19 19:52:57 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/9a9884612f/ ben 0) { print str Index: src/cgi.awk ================================================================== --- src/cgi.awk +++ src/cgi.awk @@ -1,11 +1,13 @@ function cgi_init( ip) { + blocked = 0 ip = ENVIRON["REMOTE_ADDR"] while ((getline < blocklist) > 0) { # bad bot ignoring robots.txt, block by IP address if (match(ip, $0)) { - exit 0 + blocked = 1 + break } } close(blocklist) search = ARGV[1] Index: src/details/index.dcgi.m4 ================================================================== --- src/details/index.dcgi.m4 +++ src/details/index.dcgi.m4 @@ -17,10 +17,16 @@ iaout, id, item_id, item_server, item_size, label, language, license, output, pub_date, scanner, signature, str, thumb, title, topic, topics, type, uploader_account, uploader_email, url) { item_id = parts[3] + + if (blocked) { + printf "[h|Details|URL:%s/details/%s|%s|%s]\n", + api_ssl_endpoint, item_id, server, port + exit 0 + } signature = "details/" item_id str = cache_init(signature) if (length(str) > 0) { print str Index: src/download/index.dcgi.m4 ================================================================== --- src/download/index.dcgi.m4 +++ src/download/index.dcgi.m4 @@ -13,10 +13,17 @@ function main(cmd, dir, files, file_size, format, iaout, is_archive, is_proxy, item_server, label, mtime, name, source, url) { dir = parts[2] item_id = parts[3] + + if (blocked) { + printf "[h|Download|URL:%s/download/%s|%s|%s]\n", + api_ssl_endpoint, item_id, server, port + exit 0 + } + if (dir == "download") { is_proxy = 1 } else { # dir == "direct" is_proxy = 0 Index: src/list/index.dcgi.m4 ================================================================== --- src/list/index.dcgi.m4 +++ src/list/index.dcgi.m4 @@ -42,10 +42,16 @@ } split(search, parts, "/") acct = parts[1] list_id = parts[2] + + if (blocked) { + printf "[h|List|URL:%s/details/%s/lists/%d|%s|%s]\n", + api_ssl_endpoint, acct, list_id, server, port + exit 0 + } signature = sprintf("list/%s", input) str = cache_init(signature) if (length(str) > 0) { print str Index: src/lists/index.dcgi.m4 ================================================================== --- src/lists/index.dcgi.m4 +++ src/lists/index.dcgi.m4 @@ -14,10 +14,16 @@ function main( cmd, count, fields, iaout, i, id, is_private, item, item_count, item_id, label, name, output, record, records, signature, str, url) { + if (blocked) { + printf "[h|Lists|URL:%s/details/%s/lists|%s|%s]\n", + api_ssl_endpoint, search, server, port + exit 0 + } + signature = sprintf("%s/lists", search) str = cache_init(signature) if (length(str) > 0) { print str return Index: src/listsort/index.dcgi.m4 ================================================================== --- src/listsort/index.dcgi.m4 +++ src/listsort/index.dcgi.m4 @@ -7,10 +7,16 @@ include(src/config.awk) incl(src/cgi.awk) function main( acct, i, lbl, list_id, opt) { + if (blocked) { + printf "[h|Internet Archive|URL:%s/|%s|%s]\n", + api_ssl_endpoint, server, port + exit 0 + } + lbl[1] = "Relevance" opt[1] = "" lbl[2] = "Weekly views [^]" opt[2] = "week asc" lbl[3] = "Weekly views [v]" Index: src/raw/index.cgi.m4 ================================================================== --- src/raw/index.cgi.m4 +++ src/raw/index.cgi.m4 @@ -22,10 +22,16 @@ incl(src/cgi.awk) incl(src/util.awk) incl(src/web.awk) function main() { + if (blocked) { + printf "[h|Internet Archive|URL:%s/|%s|%s]\n", + api_ssl_endpoint, server, port + exit 0 + } + if (path == "/debug/") { dump(search, TYPE_HEADERS) } else if (path == "/raw/") { dump(search, TYPE_RAW) } else if (path == "/text/") { Index: src/search/index.dcgi.m4 ================================================================== --- src/search/index.dcgi.m4 +++ src/search/index.dcgi.m4 @@ -13,10 +13,16 @@ function main(search, cmd, count, creator, descr, field, fields, i, iaout, id, item, items, jsout, label, numfound, order, order_names, page, rows, searchstr, sort_param, str, title, type, url) { + if (blocked) { + printf "[h|Search|URL:%s/|%s|%s]\n", api_ssl_endpoint, + server, port + exit 0 + } + order_names["addeddate"] = "addeddate" order_names["collection_size"] = "collection_size" order_names["createddate"] = "createddate" order_names["creator"] = "creatorSorter" order_names["date"] = "date" Index: src/sort/index.dcgi.m4 ================================================================== --- src/sort/index.dcgi.m4 +++ src/sort/index.dcgi.m4 @@ -7,10 +7,16 @@ include(src/config.awk) incl(src/cgi.awk) function main( i, lbl, opt) { + if (blocked) { + printf "[h|Internet Archive|URL:%s/|%s|%s]\n", + api_ssl_endpoint, server, port + exit 0 + } + lbl[1] = "Default [^]" opt[1] = "nav_order asc" lbl[2] = "Default [v]" opt[2] = "nav_order desc" lbl[3] = "Weekly views [^]" Index: src/wizard/step1/index.dcgi.m4 ================================================================== --- src/wizard/step1/index.dcgi.m4 +++ src/wizard/step1/index.dcgi.m4 @@ -7,10 +7,16 @@ include(src/config.awk) incl(src/cgi.awk) function main( i, lbl, opt, searchstr) { + if (blocked) { + printf "[h|Internet Archive|URL:%s/|%s|%s]\n", + api_ssl_endpoint, server, port + exit 0 + } + searchstr = parts[4] lbl[1] = "Any field contains" opt[1] = "anyfield" lbl[2] = "Any field does not contain" Index: src/wizard/step2/index.dcgi.m4 ================================================================== --- src/wizard/step2/index.dcgi.m4 +++ src/wizard/step2/index.dcgi.m4 @@ -7,10 +7,16 @@ include(src/config.awk) incl(src/cgi.awk) function main( field, newsearch, searchstr) { + if (blocked) { + printf "[h|Internet Archive|URL:%s/|%s|%s]\n", + api_ssl_endpoint, server, port + exit 0 + } + field = parts[4] searchstr = parts[5] if (field == "mediatype") { print "# Mediatype is:" Index: src/wizard/step3/index.dcgi.m4 ================================================================== --- src/wizard/step3/index.dcgi.m4 +++ src/wizard/step3/index.dcgi.m4 @@ -7,10 +7,16 @@ include(src/config.awk) incl(src/cgi.awk) function main( field, label, newsearch, op, searchstr, value) { + if (blocked) { + printf "[h|Internet Archive|URL:%s/|%s|%s]\n", + api_ssl_endpoint, server, port + exit 0 + } + field = parts[4] searchstr = parts[5] value = search if (field ~ /^-/) { ]]> 2025-06-19 03:33:26 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/9e43349b2e/ ben 2025-06-06 16:03:24 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/b87f964a15/ ben 2025-05-24 17:26:38 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/ba8329da42/ ben >output } print_html(output, descr) if (length(email) > 0) { - printf "[1|Uploads|%s/search/%%09uploader:%s|%s|%s]\n", + printf "[1|Uploads|%s/search/sortaddeddate desc%%09uploader:%s|" \ + "%s|%s]\n", cgipath, email, server, port >>output } - printf "[1|Items|%s/search/%%09anyfield:%s|%s|%s]\n", cgipath, - acct, server, port >>output + printf "[1|Items|%s/search/sortaddeddate desc%%09anyfield:%s|%s|%s]\n", + cgipath, acct, server, port >>output printf "[1|Lists|%s/lists/%%09%s|%s|%s]\n", cgipath, acct, server, port >>output print "" >>output printf "%-20s %s\n", "Identifier:", id >>output ]]> 2025-05-08 15:23:54 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/86a47da961/ ben 0) { label = prefix id printf "[1|%s|%s/details/%s|%s|%s]\n", label, cgipath, - id, server, port + id, server, port >>output } else { print str >>output } } else { print str >>output ]]> 2025-05-01 02:19:44 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/43949a6909/ ben >output } print "" >>output - print "# Similar Items" >>output + print "# Similar items" >>output printf "[1|View similar items|%s/search/%%09similar:%s|%s|%s]\n", cgipath, item_id, server, port >>output print "" >>output printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port >>output ]]> 2025-04-30 01:29:18 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/5b6df39427/ ben >output } printf "[1|Download|%s/download/%s|%s|%s]\n", cgipath, item_id, server, port >>output + printf "[h|Web page|URL:%s/details/%s|%s|%s]\n", + api_ssl_endpoint, uri_encode(id), server, port >>output print "" >>output print_html(output, descr) print "" >>output @@ -205,12 +207,15 @@ printf "[1|%s|%s/search/%%09uploader:%s|%s|%s]\n", label, cgipath, uploader_email, server, port >>output } print "" >>output - printf "[h|Item web page|URL:%s/details/%s|%s|%s]\n", - api_ssl_endpoint, uri_encode(id), server, port >>output + print "# Similar Items" >>output + printf "[1|View similar items|%s/search/%%09similar:%s|%s|%s]\n", + cgipath, item_id, server, port >>output + + print "" >>output printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port >>output cache_end() unlink(iaout) return Index: src/search/index.dcgi.m4 ================================================================== --- src/search/index.dcgi.m4 +++ src/search/index.dcgi.m4 @@ -9,12 +9,13 @@ incl(src/api.awk) incl(src/cgi.awk) incl(src/util.awk) function main(search, cmd, count, creator, descr, field, fields, i, - iaout, id, jsout, label, numfound, order, order_names, page, rows, - searchstr, sort_param, title, type, url) + iaout, id, item, items, jsout, label, numfound, order, + order_names, page, rows, searchstr, sort_param, str, title, type, + url) { order_names["addeddate"] = "addeddate" order_names["collection_size"] = "collection_size" order_names["createddate"] = "createddate" order_names["creator"] = "creatorSorter" @@ -40,16 +41,53 @@ sort_param = parts[i] order = substr(parts[i], 5) } } } + + iaout = gettemp() + jsout = gettemp() # special case for when the search term is an archive.org details URL if (match(search, /^https:\/\/(www\.)?archive\.org\/details\//)) { id = substr(search, RLENGTH + 1) search = "identifier:" id } + + # special case to list similar items + if (match(search, /^similar:/)) { + id = substr(search, RLENGTH + 1) + + url = api_endpoint "/details/" id "?RelatedItemsGet=1" + api_request(url, "GET", iaout) + + # scrape similar items + FS = "\t" + items = 0 + delete item + str = "" + while ((getline 0) { + if (match($0, /iaout + close(iaout) + + for (i = 1; i <= items; i++) { + if (i == 1) { + search = "identifier:" item[i] + } else { + search = search "%20OR%20identifier:" item[i] + } + } + } # remove quotes from search string, since it gets quoted later gsub(/"/, "", search) # default sort orders if none were specified @@ -63,13 +101,10 @@ order = "nav_order desc" sort_param = "sort" order } } - iaout = gettemp() - jsout = gettemp() - # get search results field[1] = "creator" field[2] = "description" field[3] = "identifier" ]]> 2025-04-30 01:22:43 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/c37a9eb847/ ben 0) { if (/item-upload-info__uploader-name/ && match($0, /\/details\/[^"]*"/)) { - uploader_account = substr($0, RSTART+9, RLENGTH-10) + uploader_account = substr($0, RSTART + 9, RLENGTH - 10) } } close(iaout) if (cols > 0) { Index: src/search/index.dcgi.m4 ================================================================== --- src/search/index.dcgi.m4 +++ src/search/index.dcgi.m4 @@ -43,11 +43,11 @@ } } # special case for when the search term is an archive.org details URL if (match(search, /^https:\/\/(www\.)?archive\.org\/details\//)) { - id = substr(search, RLENGTH+1) + id = substr(search, RLENGTH + 1) search = "identifier:" id } # remove quotes from search string, since it gets quoted later gsub(/"/, "", search) @@ -87,11 +87,11 @@ split(order, parts, " ") url = url sprintf("&sort%%5B0%%5D=%s %s", order_names[parts[1]], parts[2]) } for (i = 1; i <= fields; i++) { - url = url sprintf("&fl%%5B%d%%5D=%s", i-1, field[i]) + url = url sprintf("&fl%%5B%d%%5D=%s", i - 1, field[i]) } api_request(url, "GET", iaout) cmd = sprintf("%s <%s >%s 2>&1", cmd_json2tsv, iaout, jsout) system(cmd) Index: src/util.awk ================================================================== --- src/util.awk +++ src/util.awk @@ -87,11 +87,11 @@ A[1] = t return } } for (p = i; (c = 2*p) <= n; p = c) { - if ((c < n) && (A[c] < A[c+1])) + if ((c < n) && (A[c] < A[c + 1])) c++ if (t < A[c]) A[p] = A[c] else break } Index: src/web.awk ================================================================== --- src/web.awk +++ src/web.awk @@ -148,11 +148,11 @@ # to full URLs function print_ref_full(str, base, proto, root, link, prefix, relative) { if (match(str, /^ [0-9]+\. /)) { prefix = substr(str, 0, RLENGTH) - link = substr(str, RLENGTH+1) + link = substr(str, RLENGTH + 1) # convert relative links to full URLs if (link !~ /^[a-z]+:/) { # convert relative link to full URL relative = link if (relative ~ /^\/\//) { @@ -177,18 +177,18 @@ function print_ref_pharos(output, str, id, label, link, prefix, relative, token) { if (match(str, /^ [0-9]+\. /)) { prefix = substr(str, 0, RLENGTH) - link = substr(str, RLENGTH+1) + link = substr(str, RLENGTH + 1) id = "" if (match(link, /https?:\/\/(www\.)?archive\.org\/details\//)) { token = substr(link, RSTART+RLENGTH) id = substr(token, 1, length(token) - 7) if (match(id, /[?\/ ]/)) { - id = substr(id, 1, RSTART-1) + id = substr(id, 1, RSTART - 1) } } if (length(id) > 0) { label = prefix id printf "[1|%s|%s/details/%s|%s|%s]\n", label, cgipath, ]]> 2025-04-30 00:57:35 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/6da1905276/ ben 2025-04-30 00:33:10 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/86679b4841/ ben 0) { retval = $0 } result = close(cmd_mktemp) if (result != 0) { @@ -97,11 +97,11 @@ } A[p] = t } } -function human_size(bytes) { +function human_size(bytes, retval) { if (bytes > size_gb) { retval = sprintf("%.1fG", bytes / size_gb) } else if (bytes > size_mb) { retval = sprintf("%.1fM", bytes / size_mb) } else if (bytes > size_kb) { @@ -135,20 +135,20 @@ } close(name) return retval } -function shorten_left(str, len) { +function shorten_left(str, len, retval) { if (length(str) > len) { retval = "..." substr(str, 3 + length(str) - len) } else { retval = str } return retval } -function shorten(str, len) { +function shorten(str, len, retval) { if (length(str) > len) { retval = substr(str, 0, len - 3) "..." } else { retval = str } ]]> 2025-04-27 21:03:08 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/275c838adb/ ben * Written in AWK. Tested using busybox awk. * Commands used: * env, mktemp, rm, strings, xargs - * curl + * curl * json2tsv * webdump Configuration ============= ]]> 2025-04-27 21:00:34 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/9f67b17ddc/ ben 0) { - print str - return - } - - output = cache_begin() iaout = gettemp() jsout = gettemp() # get search results @@ -117,26 +107,25 @@ if (search ~ /^@/) { numfound++ } if (numfound == 0) { - print "Your search did not match any items in the Archive." >>output - print "Try different keywords or a more general search." >>output - print "" >>output - printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port >>output - cache_end() + print "Your search did not match any items in the Archive." + print "Try different keywords or a more general search." + print "" + printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port unlink(jsout) unlink(iaout) return } else { pages = int(numfound / rows) if (numfound % rows != 0) { pages++ } printf "# %s search results, page %d of %d\n", numfound, - page, pages >>output - print "" >>output + page, pages + print "" } # format search results as a gopher directory (menu) FS = "\t" creator = "" @@ -146,11 +135,11 @@ type = "" count = 0 if (search ~ /^@/) { printf "[1|Account %s|%s/account/%s|%s|%s]\n", search, cgipath, - search, server, port >>output + search, server, port } while ((getline 0) { if ($1 == ".response.docs[].creator" && $2 == "s") { creator = $3 @@ -171,54 +160,53 @@ label = sprintf("[%s] %s", mediatype[type], gph_encode(shorten(title, 58))) } if (type == "collection") { printf "[1|%s|%s/search/%%09collection:(%s)|%s|%s]\n", - label, cgipath, id, server, port >>output + label, cgipath, id, server, port } else { printf "[1|%s|%s/details/%s|%s|%s]\n", label, cgipath, - id, server, port >>output + id, server, port } creator = "" descr = "" id = "" type = "" } } close(jsout) - print "" >>output + print "" # only show "page back" if the user is past page 1 if (page > 1) { printf "[1|[<<] Page %d|%s/search/page%d/rows%d/%s%%09%s|%s|%s]\n", page - 1, cgipath, page - 1, rows, sort_param, search, - server, port >>output + server, port } # only show "next page" if the current page is completely full if (count == rows) { printf "[1|[>>] Page %d|%s/search/page%d/rows%d/%s%%09%s|%s|%s]\n", page + 1, cgipath, page + 1, rows, sort_param, search, - server, port >>output + server, port } # only show "sort" if there's more than one item to sort if (count > 1) { printf "[1|[^v] Sort|%s/sort/%%09%s|%s|%s]\n", cgipath, search, - server, port >>output + server, port } # only show "search within list" if there's multiple pages of results if (numfound > rows) { printf "[1|[\\/] Filter results|%s/wizard/step1/%s|%s|%s]\n", - cgipath, search, server, port >>output + cgipath, search, server, port } - printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port >>output + printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port - cache_end() unlink(jsout) unlink(iaout) exit 0 } ]]> 2025-04-17 14:31:41 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/947e8d74dd/ ben 0) { print str return } ]]> 2025-04-14 20:44:04 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/4d6f4c92b4/ ben 0) { + # bad bot ignoring robots.txt, block by IP address + if (match(ip, $0)) { + exit 0 + } + } + close(blocklist) + search = ARGV[1] arguments = ARGV[2] traversal = ARGV[5] selector = ARGV[6] Index: src/config.awk ================================================================== --- src/config.awk +++ src/config.awk @@ -1,10 +1,11 @@ function config_init() { agent = "__AGENT__" api_endpoint = "__API_ENDPOINT__" api_ssl_endpoint = "__API_SSL_ENDPOINT__" awk_ext = __AWK_EXT__ + blocklist = "__BLOCKLIST__" cache_db = "__CACHE_DB__" cache_enabled = __CACHE_ENABLED__ cgipath = "__CGIPATH__" cmd_curl = "__CMD_CURL__" cmd_enc = "__CMD_ENV__" ]]> 2025-04-13 00:05:13 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/d3332581da/ ben 2025-04-12 20:57:58 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/20fcfb6f6d/ ben curlcfg printf "--max-redirs 0\n" >> curlcfg if (url ~ /^https:/) { Index: src/download/index.dcgi.m4 ================================================================== --- src/download/index.dcgi.m4 +++ src/download/index.dcgi.m4 @@ -8,11 +8,11 @@ include(src/config.awk) incl(src/api.awk) incl(src/cgi.awk) incl(src/util.awk) -function main(cmd, dir, files, file_size, format, iaout, is_archive, \ +function main(cmd, dir, files, file_size, format, iaout, is_archive, is_proxy, item_server, label, mtime, name, source, url) { dir = parts[2] item_id = parts[3] if (dir == "download") { @@ -59,13 +59,13 @@ } } close(cmd) for (i = 1; i <= files; i++) { - label = sprintf("%s %s %s", \ - shorten_left(name[i], 40), \ - strftime("%Y-%m-%d %H:%M", mtime[i]), \ + label = sprintf("%s %s %s", + shorten_left(name[i], 40), + strftime("%Y-%m-%d %H:%M", mtime[i]), human_size(file_size[i])) url = sprintf("http://%s%s/%s", item_server, dir, name[i]) if (is_proxy) { if (file_size[i] > max_bin_size * size_mb) { printf "[h|%s|URL:%s|%s|%s]\n", label, uri_encode(url), @@ -78,11 +78,11 @@ printf "[h|%s|URL:%s|%s|%s]\n", label, uri_encode(url), server, port } is_archive = detect_archive(url) if (is_archive) { - url = sprintf("http://%s/view_archive.php?archive=%s/%s", \ + url = sprintf("http://%s/view_archive.php?archive=%s/%s", item_server, dir, name[i]) printf "[h|%s (View Contents)|URL:%s|%s|%s]\n", shorten_left(name[i], 40), uri_encode(url), server, port } Index: src/list/index.dcgi.m4 ================================================================== --- src/list/index.dcgi.m4 +++ src/list/index.dcgi.m4 @@ -157,14 +157,14 @@ title = $3 } else if ($1 == ".response.body.hits.hits[]._score") { # the _score field happens to be toward the end of each item if (length(title) > 0) { if (length(creator) > 0) { - label = sprintf("[%s] %s by %s", mediatype[type], \ + label = sprintf("[%s] %s by %s", mediatype[type], gph_encode(shorten(title, 40)), shorten(creator, 18)) } else { - label = sprintf("[%s] %s", mediatype[type], \ + label = sprintf("[%s] %s", mediatype[type], gph_encode(shorten(title, 58))) } printf "[1|%s|%s/details/%s|%s|%s]\n", label, cgipath, id, server, port >>output count++ Index: src/lists/index.dcgi.m4 ================================================================== --- src/lists/index.dcgi.m4 +++ src/lists/index.dcgi.m4 @@ -46,11 +46,11 @@ while ((cmd | getline) > 0) { if ($1 == ".value[]" && $2 == "o") { # add information for previous list if (!is_private && length(name) > 0 && item_count > 0) { label = shorten_left(name, 50) - item = sprintf("[1|%4d Items: %-50s|%s/list/%%09%s/%d|%s|%s]", \ + item = sprintf("[1|%4d Items: %-50s|%s/list/%%09%s/%d|%s|%s]", item_count, label, cgipath, search, id, server, port) record = label "\t" id "\t" item count++ records[count] = record } @@ -72,11 +72,11 @@ close(cmd) # add information for previous list if (!is_private && length(name) > 0 && item_count > 0) { label = shorten_left(name, 50) - item = sprintf("[1|%4d Items: %-50s|%s/list/%%09%s/%d|%s|%s]", \ + item = sprintf("[1|%4d Items: %-50s|%s/list/%%09%s/%d|%s|%s]", item_count, label, cgipath, search, id, server, port) record = label "\t" id "\t" item count++ records[count] = record } Index: src/search/index.dcgi.m4 ================================================================== --- src/search/index.dcgi.m4 +++ src/search/index.dcgi.m4 @@ -89,15 +89,15 @@ # remove anyfield, a hobgoblin of consistency searchstr = search gsub(/anyfield:/, "", searchstr) - url = sprintf("%s/advancedsearch.php?q=%s&output=json&rows=%d&page=%d", \ + url = sprintf("%s/advancedsearch.php?q=%s&output=json&rows=%d&page=%d", api_endpoint, searchstr, rows, page) if (length(order) > 0) { split(order, parts, " ") - url = url sprintf("&sort%%5B0%%5D=%s %s", order_names[parts[1]], \ + url = url sprintf("&sort%%5B0%%5D=%s %s", order_names[parts[1]], parts[2]) } for (i = 1; i <= fields; i++) { url = url sprintf("&fl%%5B%d%%5D=%s", i-1, field[i]) } @@ -130,11 +130,11 @@ } else { pages = int(numfound / rows) if (numfound % rows != 0) { pages++ } - printf "# %s search results, page %d of %d\n", numfound, \ + printf "# %s search results, page %d of %d\n", numfound, page, pages >>output print "" >>output } # format search results as a gopher directory (menu) @@ -163,14 +163,14 @@ } else if ($1 == ".response.docs[].title" && $2 == "s") { # the title field happens to be toward the end of each item title = $3 count++ if (length(creator) > 0) { - label = sprintf("[%s] %s by %s", mediatype[type], \ + label = sprintf("[%s] %s by %s", mediatype[type], gph_encode(shorten(title, 40)), shorten(creator, 18)) } else { - label = sprintf("[%s] %s", mediatype[type], \ + label = sprintf("[%s] %s", mediatype[type], gph_encode(shorten(title, 58))) } if (type == "collection") { printf "[1|%s|%s/search/%%09collection:(%s)|%s|%s]\n", label, cgipath, id, server, port >>output Index: src/web.awk ================================================================== --- src/web.awk +++ src/web.awk @@ -1,7 +1,7 @@ -function dump(search, type, base, cmd, curlcfg, is_html, is_image, \ - label, limit, link, marker, parts, prefix, proto, relative, root, \ +function dump(search, type, base, cmd, curlcfg, is_html, is_image, + label, limit, link, marker, parts, prefix, proto, relative, root, url) { url = search gsub(/%3F/, "?", url) @@ -42,11 +42,11 @@ } # Use strings command to guard webdump from binary input. # Use "strings -a" to avoid security pitfalls. - cmd = sprintf("%s -K %s 2>&1 | %s -a -n 3 | %s -ilr -w 60", \ + cmd = sprintf("%s -K %s 2>&1 | %s -a -n 3 | %s -ilr -w 60", cmd_curl, curlcfg, cmd_strings, cmd_webdump) # Parse base out of original URL. # Use this to convert relative links to full URLs. # webdump has the -b option for this. @@ -122,11 +122,11 @@ function print_html(output, html, cmd, marker, work) { work = gettemp() gsub(/\\n/, "
", html) print html >work close(work) - cmd = sprintf("%s -a -n 3 <%s | %s -ilr -w 60", cmd_strings, work, \ + cmd = sprintf("%s -a -n 3 <%s | %s -ilr -w 60", cmd_strings, work, cmd_webdump) marker = 999999 while ((cmd | getline) > 0) { gsub(/\t/, " ") gsub(/\\t/, " ") @@ -172,11 +172,11 @@ # Print the webdump references section, translating archive.org URLs to # pharos URLs -function print_ref_pharos(output, str, id, label, link, prefix, \ +function print_ref_pharos(output, str, id, label, link, prefix, relative, token) { if (match(str, /^ [0-9]+\. /)) { prefix = substr(str, 0, RLENGTH) link = substr(str, RLENGTH+1) ]]> 2025-04-12 20:53:31 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/f60b57c050/ ben Configuration ============= To set configuration variables, edit config.m4 + +AWK_EXT allows use of non-standard features in gawk and mawk +CACHE_ENABLED caches content in sqlite to reduce API calls Installation ============ Installation depends on m4. Index: src/account/index.dcgi.m4 ================================================================== --- src/account/index.dcgi.m4 +++ src/account/index.dcgi.m4 @@ -5,20 +5,31 @@ # # Show details for an account include(src/config.awk) incl(src/api.awk) +incl(src/cache.awk) incl(src/cgi.awk) +incl(src/sqlite.awk) incl(src/util.awk) incl(src/web.awk) function main( acct, cmd, col, cols, descr, dir, email, iaout, id, - item_server, item_size, thumb, title, type, url) + item_server, item_size, output, signature, str, thumb, title, + type, url) { acct = parts[3] email = search + signature = sprintf("account/%s/%s", acct, email) + str = cache_init(signature) + if (length(str) > 0) { + print str + return + } + + output = cache_begin() iaout = gettemp() url = api_endpoint "/metadata/" acct api_request(url, "GET", iaout) @@ -63,44 +74,46 @@ } } close(cmd) if (length(id) == 0) { - print_not_found(url) + print_not_found(output, url) + cache_end() unlink(iaout) return } - print "Account: " acct + print "Account: " acct >>output if (length(thumb) > 0) { url = sprintf("http://%s%s/%s", item_server, dir, thumb) printf "[I|Thumbnail|%s/raw/%%09%s|%s|%s]\n", cgipath, url, - server, port + server, port >>output } - print_html(descr) + print_html(output, descr) if (length(email) > 0) { printf "[1|Uploads|%s/search/%%09uploader:%s|%s|%s]\n", - cgipath, email, server, port + cgipath, email, server, port >>output } printf "[1|Items|%s/search/%%09anyfield:%s|%s|%s]\n", cgipath, - acct, server, port - printf "[1|Lists|%s/lists/%%09%s|%s|%s]\n", cgipath, acct, - server, port - - print "" - printf "%-20s %s\n", "Identifier:", id - if (item_size > 0) { - printf "%-20s %d\n", "Item Size:", item_size - } - printf "%-20s %s\n", "Media Type:", type - - print "" - printf "[h|Account web page|URL:%s/details/%s|%s|%s]\n", - api_ssl_endpoint, uri_encode(id), server, port - printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port - + acct, server, port >>output + printf "[1|Lists|%s/lists/%%09%s|%s|%s]\n", cgipath, acct, + server, port >>output + + print "" >>output + printf "%-20s %s\n", "Identifier:", id >>output + if (item_size > 0) { + printf "%-20s %d\n", "Item Size:", item_size >>output + } + printf "%-20s %s\n", "Media Type:", type >>output + + print "" >>output + printf "[h|Account web page|URL:%s/details/%s|%s|%s]\n", + api_ssl_endpoint, uri_encode(id), server, port >>output + printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port >>output + + cache_end() unlink(iaout) exit 0 } BEGIN { ADDED src/cache.awk Index: src/cache.awk ================================================================== --- /dev/null +++ src/cache.awk @@ -0,0 +1,59 @@ +# cache or memo-ize to reduce Internet Archive API calls + +function cache_begin() { + if (cache_enabled || !awk_ext) { + cache_output = gettemp() + } else { + # awk_ext micro-optimization for gawk and mawk: + # when cache is disabled, print directly to stdout + cache_output = "/dev/stdout" + } + return retval +} + +function cache_end( value) { + if (cache_enabled || !awk_ext) { + close(cache_output) + value = read_file(cache_output) + print value + cache_set_value(value) + unlink(cache_output) + } + return +} + +function cache_init(signature, retval, sql) { + if (!cache_enabled) { + return + } + cache_signature = signature + sql = "CREATE TABLE IF NOT EXISTS cache ( \ + id TEXT PRIMARY KEY, \ + epoch INTEGER, \ + result TEXT)" + sqlite_exec(cache_db, sql) + retval = cache_get_value() + return retval +} + +function cache_get_value( retval, sql) { + if (!cache_enabled) { + return retval + } + sql = sprintf("SELECT result FROM cache WHERE id = '%s'", + sqlite_escape(cache_signature)) + retval = sqlite_exec(cache_db, sql) + return retval +} + +function cache_set_value(value, sql) { + if (!cache_enabled) { + return + } + sql = sprintf("REPLACE INTO cache(id, epoch, result) \ + VALUES('%s', unixepoch(), '%s')", + sqlite_escape(cache_signature), + sqlite_escape(value)) + sqlite_exec(cache_db, sql) + return +} Index: src/config.awk ================================================================== --- src/config.awk +++ src/config.awk @@ -1,15 +1,19 @@ function config_init() { agent = "__AGENT__" api_endpoint = "__API_ENDPOINT__" api_ssl_endpoint = "__API_SSL_ENDPOINT__" + awk_ext = __AWK_EXT__ + cache_db = "__CACHE_DB__" + cache_enabled = __CACHE_ENABLED__ cgipath = "__CGIPATH__" cmd_curl = "__CMD_CURL__" cmd_enc = "__CMD_ENV__" cmd_json2tsv = "__CMD_JSON2TSV__" cmd_mktemp = "__CMD_MKTEMP__" cmd_rm = "__CMD_RM__" + cmd_sqlite = "__CMD_SQLITE__" cmd_strings = "__CMD_STRINGS__" cmd_webdump = "__CMD_WEBDUMP__" cmd_xargs = "__CMD_XARGS__" geomyidae_version = __GEOMYIDAE_VERSION__ max_bin_size = __MAX_BIN_SIZE__ Index: src/details/index.dcgi.m4 ================================================================== --- src/details/index.dcgi.m4 +++ src/details/index.dcgi.m4 @@ -5,22 +5,32 @@ # # Show details for an item include(src/config.awk) incl(src/api.awk) +incl(src/cache.awk) incl(src/cgi.awk) +incl(src/sqlite.awk) incl(src/util.awk) incl(src/web.awk) -function main( add_date, col, cols, cmd, creator, descr, dir, i, \ - iaout, id, item_id, item_server, item_size, label, language, \ - license, pub_date, scanner, thumb, title, topic, topics, type, \ - uploader_account, uploader_email, url) +function main( add_date, col, cols, cmd, creator, descr, dir, i, + iaout, id, item_id, item_server, item_size, label, language, + license, output, pub_date, scanner, signature, str, thumb, title, + topic, topics, type, uploader_account, uploader_email, url) { item_id = parts[3] + + signature = "details/" item_id + str = cache_init(signature) + if (length(str) > 0) { + print str + return + } iaout = gettemp() + output = cache_begin() url = api_endpoint "/metadata/" item_id api_request(url, "GET", iaout) # format search results as a gopher directory (menu) @@ -99,67 +109,68 @@ } } close(cmd) if (length(id) == 0) { - print_not_found(url) + print_not_found(output, url) + cache_end() unlink(iaout) return } - print(shorten(title, 70)) + print shorten(title, 70) >>output if (creators == 1) { label = "by " shorten(creator[1], 70) printf "[1|%s|%s/search/%%09creator:(%s)|%s|%s]\n", label, - cgipath, creator[1], server, port + cgipath, creator[1], server, port >>output } else if (creators > 1) { - printf "\nby:\n" + printf "\nby:\n" >>output for (i = 1; i <= creators; i++) { label = shorten(creator[i], 70) printf "[1|%s|%s/search/%%09creator:(%s)|%s|%s]\n", label, - cgipath, creator[i], server, port + cgipath, creator[i], server, port >>output } - printf "\n" + printf "\n" >>output } if (length(thumb) > 0) { url = sprintf("http://%s%s/%s", item_server, dir, thumb) printf "[I|Thumbnail|%s/raw/%%09%s|%s|%s]\n", - cgipath, url, server, port + cgipath, url, server, port >>output } printf "[1|Download|%s/download/%s|%s|%s]\n", cgipath, - item_id, server, port - print "" + item_id, server, port >>output + print "" >>output - print_html(descr) + print_html(output, descr) - print "" + print "" >>output if (length(add_date) > 0) { - printf "%-20s %s\n", "Date Added:", add_date + printf "%-20s %s\n", "Date Added:", add_date >>output } if (pub_date != add_date) { - printf "%-20s %s\n", "Date Published:", pub_date + printf "%-20s %s\n", "Date Published:", pub_date >>output } - printf "%-20s %s\n", "Identifier:", id + printf "%-20s %s\n", "Identifier:", id >>output if (item_size > 0) { - printf "%-20s %d\n", "Item Size:", item_size + printf "%-20s %d\n", "Item Size:", item_size >>output } if (length(language) > 0) { - printf "%-20s %s\n", "Language:", language + printf "%-20s %s\n", "Language:", language >>output } if (length(license) > 0) { - printf "%-20s %s\n", "License:", license + printf "%-20s %s\n", "License:", license >>output } - printf "%-20s %s\n", "Media Type:", type + printf "%-20s %s\n", "Media Type:", type >>output if (topics > 0) { - print "" - print "# Topics" + print "" >>output + print "# Topics" >>output for (i = 1; i <= topics; i++) { label = shorten(topic[i], 40) printf "[1|%s|%s/search/%%09subject:(%s)|%s|%s]\n", label, - cgipath, topic[i], server, port + cgipath, topic[i], server, port >>output } } # scrape uploader name from item web page HTML url = api_ssl_endpoint "/details/" item_id @@ -172,36 +183,37 @@ } } close(iaout) if (cols > 0) { - print "" - print "# Collections" + print "" >>output + print "# Collections" >>output for (i = 1; i <= cols; i++) { label = shorten(col[i], 40) printf "[1|%s|%s/search/%%09collection:(%s)|%s|%s]\n", - label, cgipath, col[i], server, port + label, cgipath, col[i], server, port >>output } } - print "" - print "# Uploaded by" + print "" >>output + print "# Uploaded by" >>output if (length(uploader_account) > 0) { label = shorten(uploader_account, 70) printf "[1|%s|%s/account/%s%%09%s|%s|%s]\n", label, cgipath, - uploader_account, uploader_email, server, port + uploader_account, uploader_email, server, port >>output } else { label = shorten(uploader_email, 70) printf "[1|%s|%s/search/%%09uploader:%s|%s|%s]\n", label, - cgipath, uploader_email, server, port + cgipath, uploader_email, server, port >>output } - print "" + print "" >>output printf "[h|Item web page|URL:%s/details/%s|%s|%s]\n", - api_ssl_endpoint, uri_encode(id), server, port - printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port + api_ssl_endpoint, uri_encode(id), server, port >>output + printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port >>output + cache_end() unlink(iaout) return } BEGIN { Index: src/list/index.dcgi.m4 ================================================================== --- src/list/index.dcgi.m4 +++ src/list/index.dcgi.m4 @@ -5,17 +5,19 @@ # # Show a specific list include(src/config.awk) incl(src/api.awk) +incl(src/cache.awk) incl(src/cgi.awk) +incl(src/sqlite.awk) incl(src/util.awk) function main( acct, client_url, cmd, count, creator, iaout, id, is_private, items, label, list_id, name, name_slug, numfound, - order, order_name, order_names, order_param, page, pages, rows, - query, sort_param, title, type, url) + order, order_name, order_names, order_param, output, page, pages, + rows, query, sort_param, signature, str, title, type, url) { order_names["creator"] = "creatorSorter" order_names["date"] = "date" order_names["title"] = "titleSorter" order_names["week"] = "week" @@ -41,13 +43,18 @@ split(search, parts, "/") acct = parts[1] list_id = parts[2] - print acct "'s Lists" - print "" + signature = sprintf("list/%s", input) + str = cache_init(signature) + if (length(str) > 0) { + print str + return + } + output = cache_begin() iaout = gettemp() url = api_ssl_endpoint "/services/users/" acct "/lists/" list_id api_request(url, "GET", iaout) @@ -117,12 +124,14 @@ pages++ } # format as a gopher directory (menu) - printf "# List: %s, page %d of %d\n", name, page, pages - print "" + print acct "'s Lists" >>output + print "" >>output + printf "# List: %s, page %d of %d\n", name, page, pages >>output + print "" >>output cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) FS = "\t" count = 0 creator = "" @@ -155,11 +164,11 @@ } else { label = sprintf("[%s] %s", mediatype[type], \ gph_encode(shorten(title, 58))) } printf "[1|%s|%s/details/%s|%s|%s]\n", label, cgipath, id, - server, port + server, port >>output count++ } creator = "" descr = "" id = "" @@ -166,38 +175,39 @@ type = "" } } close(cmd) - print "" + print "" >>output # only show "page back" if the user is past page 1 if (page > 1) { printf "[1|[<<] Page %d|%s/list/page%d/rows%d/%s%%09%s/%d|%s|%s]\n", page - 1, cgipath, page - 1, rows, sort_param, - acct, list_id, server, port + acct, list_id, server, port >>output } # only show "next page" if the current page is completely full if (count == rows) { printf "[1|[>>] Page %d|%s/list/page%d/rows%d/%s%%09%s/%d|%s|%s]\n", page + 1, cgipath, page + 1, rows, sort_param, - acct, list_id, server, port + acct, list_id, server, port >>output } # only show "sort" if there's more than one item to sort if (numfound > 1) { printf "[1|[^v] Sort|%s/listsort/%%09%s/%d|%s|%s]\n", cgipath, - acct, list_id, server, port + acct, list_id, server, port >>output } printf "[1|Account %s|%s/account/%s|%s|%s]\n", acct, cgipath, - acct, server, port + acct, server, port >>output - print "" - printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port + print "" >>output + printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port >>output + cache_end() unlink(iaout) exit 0 } BEGIN { Index: src/lists/index.dcgi.m4 ================================================================== --- src/lists/index.dcgi.m4 +++ src/lists/index.dcgi.m4 @@ -5,16 +5,27 @@ # # Show a list of a user's lists include(src/config.awk) incl(src/api.awk) +incl(src/cache.awk) incl(src/cgi.awk) +incl(src/sqlite.awk) incl(src/util.awk) -function main( cmd, count, fields, iaout, i, id, is_private, item, \ - item_count, item_id, label, name, record, records, url) +function main( cmd, count, fields, iaout, i, id, is_private, item, + item_count, item_id, label, name, output, record, records, + signature, str, url) { + signature = sprintf("%s/lists", search) + str = cache_init(signature) + if (length(str) > 0) { + print str + return + } + + output = cache_begin() iaout = gettemp() url = api_ssl_endpoint "/services/users/" search "/lists" api_request(url, "GET", iaout) @@ -71,23 +82,24 @@ } # sort lists by label and id hsort(records, count) - print search "'s Lists" - print "" + print search "'s Lists" >>output + print "" >>output for (i = 1; i <= count; i++) { record = records[i] split(record, fields, /\t/) item = fields[3] - print item + print item >>output } - print "" - printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port + print "" >>output + printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port >>output + cache_end() unlink(iaout) return } BEGIN { Index: src/search/index.dcgi.m4 ================================================================== --- src/search/index.dcgi.m4 +++ src/search/index.dcgi.m4 @@ -5,16 +5,18 @@ # # Show search results include(src/config.awk) incl(src/api.awk) +incl(src/cache.awk) incl(src/cgi.awk) +incl(src/sqlite.awk) incl(src/util.awk) -function main(search, cmd, count, creator, descr, field, fields, i, \ - iaout, id, jsout, label, numfound, order, order_names, page, rows, \ - searchstr, sort_param, title, type, url) +function main(search, cmd, count, creator, descr, field, fields, i, + iaout, id, jsout, label, numfound, order, order_names, output, + page, rows, searchstr, signature, sort_param, str, title, type, url) { order_names["addeddate"] = "addeddate" order_names["collection_size"] = "collection_size" order_names["createddate"] = "createddate" order_names["creator"] = "creatorSorter" @@ -63,10 +65,18 @@ order = "nav_order desc" sort_param = "sort" order } } + signature = sprintf("search/%s", input) + str = cache_init(signature) + if (length(str) > 0) { + print str + return + } + + output = cache_begin() iaout = gettemp() jsout = gettemp() # get search results @@ -107,25 +117,26 @@ if (search ~ /^@/) { numfound++ } if (numfound == 0) { - print "Your search did not match any items in the Archive." - print "Try different keywords or a more general search." - print "" - printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port + print "Your search did not match any items in the Archive." >>output + print "Try different keywords or a more general search." >>output + print "" >>output + printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port >>output + cache_end() unlink(jsout) unlink(iaout) return } else { pages = int(numfound / rows) if (numfound % rows != 0) { pages++ } printf "# %s search results, page %d of %d\n", numfound, \ - page, pages - print "" + page, pages >>output + print "" >>output } # format search results as a gopher directory (menu) FS = "\t" creator = "" @@ -135,11 +146,11 @@ type = "" count = 0 if (search ~ /^@/) { printf "[1|Account %s|%s/account/%s|%s|%s]\n", search, cgipath, - search, server, port + search, server, port >>output } while ((getline 0) { if ($1 == ".response.docs[].creator" && $2 == "s") { creator = $3 @@ -160,53 +171,54 @@ label = sprintf("[%s] %s", mediatype[type], \ gph_encode(shorten(title, 58))) } if (type == "collection") { printf "[1|%s|%s/search/%%09collection:(%s)|%s|%s]\n", - label, cgipath, id, server, port + label, cgipath, id, server, port >>output } else { printf "[1|%s|%s/details/%s|%s|%s]\n", label, cgipath, - id, server, port + id, server, port >>output } creator = "" descr = "" id = "" type = "" } } close(jsout) - print "" + print "" >>output # only show "page back" if the user is past page 1 if (page > 1) { printf "[1|[<<] Page %d|%s/search/page%d/rows%d/%s%%09%s|%s|%s]\n", page - 1, cgipath, page - 1, rows, sort_param, search, - server, port + server, port >>output } # only show "next page" if the current page is completely full if (count == rows) { printf "[1|[>>] Page %d|%s/search/page%d/rows%d/%s%%09%s|%s|%s]\n", page + 1, cgipath, page + 1, rows, sort_param, search, - server, port + server, port >>output } # only show "sort" if there's more than one item to sort if (count > 1) { printf "[1|[^v] Sort|%s/sort/%%09%s|%s|%s]\n", cgipath, search, - server, port + server, port >>output } # only show "search within list" if there's multiple pages of results if (numfound > rows) { printf "[1|[\\/] Filter results|%s/wizard/step1/%s|%s|%s]\n", - cgipath, search, server, port + cgipath, search, server, port >>output } - printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port + printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port >>output + cache_end() unlink(jsout) unlink(iaout) exit 0 } ADDED src/sqlite.awk Index: src/sqlite.awk ================================================================== --- /dev/null +++ src/sqlite.awk @@ -0,0 +1,22 @@ +function sqlite_exec(db, query, retval, sqlcfg) { + retval = "" + sqlcfg = gettemp() + + printf ".timeout 1000\n" >sqlcfg + printf "PRAGMA encoding=\"UTF-8\";\n" >>sqlcfg + printf "%s;\n", query >>sqlcfg + close(sqlcfg) + cmd = sprintf("%s -batch -line -safe -init \"%s\" \"%s\" .quit 2>&1", + cmd_sqlite, sqlcfg, db) + while ((cmd | getline) > 0) { + retval = retval $0 "\n" + } + close(cmd) + unlink(sqlcfg) + return retval +} + +function sqlite_escape(str) { + gsub(/'/, "''", str) + return str +} Index: src/util.awk ================================================================== --- src/util.awk +++ src/util.awk @@ -110,26 +110,34 @@ retval = sprintf("%dB", bytes) } return retval } -function print_not_found(url) { - print "Item cannot be found" - print "" - print "Items may be taken down for various reasons," - print "including by decision of the uploader or" - print "due to a violation of the Terms of Use." - print "" - printf "[h|Metadata|URL:%s|%s|%s]\n", url, server, port - print "" +function print_not_found(output, url) { + print "Item cannot be found" >>output + print "" >>output + print "Items may be taken down for various reasons," >>output + print "including by decision of the uploader or" >>output + print "due to a violation of the Terms of Use." >>output + print "" >>output + printf "[h|Metadata|URL:%s|%s|%s]\n", url, server, port >>output + print "" >>output url = api_ssl_endpoint "/about/terms.php" printf "[0|Terms of Use|%s/text/%%09%s|%s|%s]\n", cgipath, - url, server, port - print "" - printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port + url, server, port >>output + print "" >>output + printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port >>output return } + +function read_file(name, retval) { + while ((getline 0) { + retval = retval $0 "\n" + } + close(name) + return retval +} function shorten_left(str, len) { if (length(str) > len) { retval = "..." substr(str, 3 + length(str) - len) } else { Index: src/web.awk ================================================================== --- src/web.awk +++ src/web.awk @@ -117,11 +117,11 @@ unlink(curlcfg) return } -function print_html(html, cmd, marker, work) { +function print_html(output, html, cmd, marker, work) { work = gettemp() gsub(/\\n/, "
", html) print html >work close(work) cmd = sprintf("%s -a -n 3 <%s | %s -ilr -w 60", cmd_strings, work, \ @@ -132,13 +132,13 @@ gsub(/\\t/, " ") if (NR < marker) { if ($0 ~ /^References$/) { marker = NR } - print + print >>output } else { - print_ref_pharos($0) + print_ref_pharos(output, $0) } } close(cmd) unlink(work) return @@ -172,11 +172,13 @@ # Print the webdump references section, translating archive.org URLs to # pharos URLs -function print_ref_pharos(str, id, label, link, prefix, relative, token) { +function print_ref_pharos(output, str, id, label, link, prefix, \ + relative, token) +{ if (match(str, /^ [0-9]+\. /)) { prefix = substr(str, 0, RLENGTH) link = substr(str, RLENGTH+1) id = "" @@ -190,14 +192,14 @@ if (length(id) > 0) { label = prefix id printf "[1|%s|%s/details/%s|%s|%s]\n", label, cgipath, id, server, port } else { - print str + print str >>output } } else { - print str + print str >>output } return } function web_init() { ]]> 2025-04-12 20:46:41 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/e553b1bd81/ ben 0) { gsub(/\t/, " ") + gsub(/\\t/, " ") if (NR < marker) { if ($0 ~ /^References$/) { marker = NR } print ]]> 2025-01-19 20:43:07 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/21f26cd9d1/ ben &1", cmd_json2tsv, iaout) FS = "\t" cols = 0 delete col add_date = "" - creator = "" + creators = 0 + delete creator descr = "" dir = "" id = "" item_server = "" item_size = 0 @@ -62,11 +63,15 @@ col[cols] = $3 } else if ($1 == ".metadata.collection[]" && $2 == "s") { cols++ col[cols] = $3 } else if ($1 == ".metadata.creator" && $2 == "s") { - creator = $3 + creators++ + creator[creators] = $3 + } else if ($1 == ".metadata.creator[]" && $2 == "s") { + creators++ + creator[creators] = $3 } else if ($1 == ".metadata.description" && $2 == "s") { descr = $3 } else if ($1 == ".metadata.identifier" && $2 == "s") { id = $3 } else if ($1 == ".metadata.language" && $2 == "s") { @@ -100,14 +105,22 @@ unlink(iaout) return } print(shorten(title, 70)) - if (length(creator) > 0) { - label = "by " shorten(creator, 70) + if (creators == 1) { + label = "by " shorten(creator[1], 70) printf "[1|%s|%s/search/%%09creator:(%s)|%s|%s]\n", label, - cgipath, creator, server, port + cgipath, creator[1], server, port + } else if (creators > 1) { + printf "\nby:\n" + for (i = 1; i <= creators; i++) { + label = shorten(creator[i], 70) + printf "[1|%s|%s/search/%%09creator:(%s)|%s|%s]\n", label, + cgipath, creator[i], server, port + } + printf "\n" } if (length(thumb) > 0) { url = sprintf("http://%s%s/%s", item_server, dir, thumb) printf "[I|Thumbnail|%s/raw/%%09%s|%s|%s]\n", cgipath, url, server, port ]]> 2025-01-19 20:38:11 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/93dfabc4c2/ ben 2025-01-02 18:20:13 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/80e7307e75/ ben 0) { + split(order, parts, " ") + url = url sprintf("&sort%%5B0%%5D=%s %s", order_names[parts[1]], \ + parts[2]) } for (i = 1; i <= fields; i++) { url = url sprintf("&fl%%5B%d%%5D=%s", i-1, field[i]) } api_request(url, "GET", iaout) @@ -163,18 +177,20 @@ print "" # only show "page back" if the user is past page 1 if (page > 1) { - printf "[1|[<<] Page %d|%s/search/page%d/rows%d/%%09%s|%s|%s]\n", - page - 1, cgipath, page - 1, rows, search, server, port + printf "[1|[<<] Page %d|%s/search/page%d/rows%d/%s%%09%s|%s|%s]\n", + page - 1, cgipath, page - 1, rows, sort_param, search, + server, port } # only show "next page" if the current page is completely full if (count == rows) { - printf "[1|[>>] Page %d|%s/search/page%d/rows%d/%%09%s|%s|%s]\n", - page + 1, cgipath, page + 1, rows, search, server, port + printf "[1|[>>] Page %d|%s/search/page%d/rows%d/%s%%09%s|%s|%s]\n", + page + 1, cgipath, page + 1, rows, sort_param, search, + server, port } # only show "sort" if there's more than one item to sort if (count > 1) { printf "[1|[^v] Sort|%s/sort/%%09%s|%s|%s]\n", cgipath, search, Index: src/sort/index.dcgi.m4 ================================================================== --- src/sort/index.dcgi.m4 +++ src/sort/index.dcgi.m4 @@ -32,13 +32,13 @@ lbl[11] = "Date created [^]" opt[11] = "createddate asc" lbl[12] = "Date created [v]" opt[12] = "createddate desc" lbl[13] = "Date published [^]" - opt[13] = "publicdate asc" + opt[13] = "date asc" lbl[14] = "Date published [v]" - opt[14] = "publicdate desc" + opt[14] = "date desc" lbl[15] = "Creator [^]" opt[15] = "creator asc" lbl[16] = "Creator [v]" opt[16] = "creator desc" lbl[17] = "Random" ]]> 2024-10-06 22:35:40 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/8c9e89b529/ ben 0) { - split(order, parts, ":") + split(order, parts, " ") order_name = order_names[parts[1]] if (length(order_name) > 0) { if (parts[2] == "desc") { - client_url = client_url "?-" order_name + client_url = client_url "?-" parts[1] } else { - client_url = client_url "?" order_name + client_url = client_url "?" parts[1] } - order_param = "&sort=" uri_encode(order) + order_param = "&sort=" uri_encode(order_name ":" parts[2]) } } url = api_ssl_endpoint "/services/search/beta/page_production/" \ "?user_query=identifier:(" query ")" \ "&hits_per_page=" rows \ @@ -168,19 +170,19 @@ print "" # only show "page back" if the user is past page 1 if (page > 1) { - printf "[1|[<<] Page %d|%s/list/page%d/rows%d/%%09%s/%d|%s|%s]\n", - page - 1, cgipath, page - 1, rows, + printf "[1|[<<] Page %d|%s/list/page%d/rows%d/%s%%09%s/%d|%s|%s]\n", + page - 1, cgipath, page - 1, rows, sort_param, acct, list_id, server, port } # only show "next page" if the current page is completely full if (count == rows) { - printf "[1|[>>] Page %d|%s/list/page%d/rows%d/%%09%s/%d|%s|%s]\n", - page + 1, cgipath, page + 1, rows, + printf "[1|[>>] Page %d|%s/list/page%d/rows%d/%s%%09%s/%d|%s|%s]\n", + page + 1, cgipath, page + 1, rows, sort_param, acct, list_id, server, port } # only show "sort" if there's more than one item to sort if (numfound > 1) { Index: src/listsort/index.dcgi.m4 ================================================================== --- src/listsort/index.dcgi.m4 +++ src/listsort/index.dcgi.m4 @@ -10,25 +10,25 @@ function main( acct, i, lbl, list_id, opt) { lbl[1] = "Relevance" opt[1] = "" lbl[2] = "Weekly views [^]" - opt[2] = "week:asc" + opt[2] = "week asc" lbl[3] = "Weekly views [v]" - opt[3] = "week:desc" + opt[3] = "week desc" lbl[4] = "Title [^]" - opt[4] = "titleSorter:asc" + opt[4] = "title asc" lbl[5] = "Title [v]" - opt[5] = "titleSorter:desc" + opt[5] = "title desc" lbl[6] = "Date published [^]" - opt[6] = "date:asc" + opt[6] = "date asc" lbl[7] = "Date published [v]" - opt[7] = "date:desc" + opt[7] = "date desc" lbl[8] = "Creator [^]" - opt[8] = "creatorSorter:asc" + opt[8] = "creator asc" lbl[9] = "Creator [v]" - opt[9] = "creatorSorter:desc" + opt[9] = "creator desc" split(search, parts, "/") acct = parts[1] list_id = parts[2] ]]> 2024-10-06 22:07:27 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/9d3e9ac34f/ ben $out && chmod a+rx $out } # PLAIN for f in index.gph \ - account/index.dcgi \ - audio/index.gph \ - books/index.gph \ - images/index.gph \ - details/index.dcgi \ - download/index.dcgi \ - list/index.dcgi \ - lists/index.dcgi \ - listsort/index.dcgi \ - raw/index.cgi \ - search/index.dcgi \ - software/index.gph \ - sort/index.dcgi \ - video/index.gph \ - wizard/step1/index.dcgi \ - wizard/step2/index.dcgi \ - wizard/step3/index.dcgi + account/index.dcgi \ + audio/index.gph \ + books/index.gph \ + images/index.gph \ + details/index.dcgi \ + download/index.dcgi \ + list/index.dcgi \ + lists/index.dcgi \ + listsort/index.dcgi \ + raw/index.cgi \ + search/index.dcgi \ + software/index.gph \ + sort/index.dcgi \ + video/index.gph \ + wizard/step1/index.dcgi \ + wizard/step2/index.dcgi \ + wizard/step3/index.dcgi do build $SRC ${SRC}/${f}.m4 ${DESTDIR}/$f done # WEIRD ]]> 2024-10-06 21:49:51 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/c51e0eeec2/ ben 0) { + split(order, parts, ":") + order_name = order_names[parts[1]] + if (length(order_name) > 0) { + if (parts[2] == "desc") { + client_url = client_url "?-" order_name + } else { + client_url = client_url "?" order_name + } + order_param = "&sort=" uri_encode(order) + } + } url = api_ssl_endpoint "/services/search/beta/page_production/" \ "?user_query=identifier:(" query ")" \ "&hits_per_page=" rows \ "&page=" page \ + order_param \ "&aggregations=false" \ "&client_url=" client_url api_request(url, "GET", iaout) pages = int(numfound / rows) @@ -117,11 +142,11 @@ type = $3 } else if ($1 == ".response.body.hits.hits[].fields.title" && $2 == "s") { title = $3 - } else if ($1 == ".response.body.hits.hits[]._score" && $2 == "a") { + } else if ($1 == ".response.body.hits.hits[]._score") { # the _score field happens to be toward the end of each item if (length(title) > 0) { if (length(creator) > 0) { label = sprintf("[%s] %s by %s", mediatype[type], \ gph_encode(shorten(title, 40)), shorten(creator, 18)) @@ -154,10 +179,16 @@ if (count == rows) { printf "[1|[>>] Page %d|%s/list/page%d/rows%d/%%09%s/%d|%s|%s]\n", page + 1, cgipath, page + 1, rows, acct, list_id, server, port } + + # only show "sort" if there's more than one item to sort + if (numfound > 1) { + printf "[1|[^v] Sort|%s/listsort/%%09%s/%d|%s|%s]\n", cgipath, + acct, list_id, server, port + } printf "[1|Account %s|%s/account/%s|%s|%s]\n", acct, cgipath, acct, server, port print "" ADDED src/listsort/index.dcgi.m4 Index: src/listsort/index.dcgi.m4 ================================================================== --- /dev/null +++ src/listsort/index.dcgi.m4 @@ -0,0 +1,54 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# listsort/index.dcgi +# +# Change list sort order + +include(src/config.awk) +incl(src/cgi.awk) + +function main( acct, i, lbl, list_id, opt) { + lbl[1] = "Relevance" + opt[1] = "" + lbl[2] = "Weekly views [^]" + opt[2] = "week:asc" + lbl[3] = "Weekly views [v]" + opt[3] = "week:desc" + lbl[4] = "Title [^]" + opt[4] = "titleSorter:asc" + lbl[5] = "Title [v]" + opt[5] = "titleSorter:desc" + lbl[6] = "Date published [^]" + opt[6] = "date:asc" + lbl[7] = "Date published [v]" + opt[7] = "date:desc" + lbl[8] = "Creator [^]" + opt[8] = "creatorSorter:asc" + lbl[9] = "Creator [v]" + opt[9] = "creatorSorter:desc" + + split(search, parts, "/") + acct = parts[1] + list_id = parts[2] + + print "# Sort by" + print "" + for (i = 1; i < 10; i++) { + if (length(opt[i]) == 0) { + printf "[1|%s|%s/list/%%09%s/%d|%s|%s]\n", + lbl[i], cgipath, acct, list_id, server, port + } else { + printf "[1|%s|%s/list/sort%s%%09%s/%d|%s|%s]\n", + lbl[i], cgipath, opt[i], acct, list_id, server, port + } + } + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + main() +} ]]> 2024-10-06 21:49:20 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/6a710e594c/ ben 1) { printf "[1|[<<] Page %d|%s/list/page%d/rows%d/%%09%s/%d|%s|%s]\n", page - 1, cgipath, page - 1, rows, @@ -153,11 +155,10 @@ printf "[1|[>>] Page %d|%s/list/page%d/rows%d/%%09%s/%d|%s|%s]\n", page + 1, cgipath, page + 1, rows, acct, list_id, server, port } - print "" printf "[1|Account %s|%s/account/%s|%s|%s]\n", acct, cgipath, acct, server, port print "" printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port ]]> 2024-10-05 23:06:44 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/816c6df39c/ ben &1", cmd_json2tsv, iaout) FS = "\t" - name = "" - id = 0 + id = "" is_private = 0 - item_id = "" + name = "" + numfound = 0 + query = "" while ((cmd | getline) > 0) { if ($1 == ".value.list_name" && $2 == "s") { name = $3 - print "# List: " name - id = 0 is_private = 0 } else if ($1 == ".value.is_private" && $2 == "b") { if ($3 == "true") { is_private = 1 } } else if ($1 == ".value.members[].identifier" && $2 == "s") { if (!is_private) { - item_id = $3 - label = shorten_left(item_id, 60) - printf "[1|%s|%s/details/%s|%s|%s]\n", label, - cgipath, item_id, server, port + id = $3 + numfound++ + if (length(query) == 0) { + query = id + } else { + query = query "+OR+" id + } + } + } + } + close(cmd) + unlink(iaout) + + # get metadata of list member items + + name_slug = uri_encode(name) + gsub(/%20/, "-", name_slug) + client_url = api_ssl_endpoint "/details/" acct "/lists/" list_id \ + "/" name_slug + url = api_ssl_endpoint "/services/search/beta/page_production/" \ + "?user_query=identifier:(" query ")" \ + "&hits_per_page=" rows \ + "&page=" page \ + "&aggregations=false" \ + "&client_url=" client_url + api_request(url, "GET", iaout) + + pages = int(numfound / rows) + if (numfound % rows != 0) { + pages++ + } + + # format as a gopher directory (menu) + + printf "# List: %s, page %d of %d\n", name, page, pages + print "" + + cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) + FS = "\t" + count = 0 + creator = "" + id = "" + title = "" + type = "" + while ((cmd | getline) > 0) { + if ($1 == ".response.body.hits.hits[].fields.creator[]" && + $2 == "s" && length(creator) == 0) + { + creator = $3 + } else if ($1 == ".response.body.hits.hits[].fields.identifier" && + $2 == "s") + { + id = $3 + } else if ($1 == ".response.body.hits.hits[].fields.mediatype" && + $2 == "s") + { + type = $3 + } else if ($1 == ".response.body.hits.hits[].fields.title" && + $2 == "s") + { + title = $3 + } else if ($1 == ".response.body.hits.hits[]._score" && $2 == "a") { + # the _score field happens to be toward the end of each item + if (length(title) > 0) { + if (length(creator) > 0) { + label = sprintf("[%s] %s by %s", mediatype[type], \ + gph_encode(shorten(title, 40)), shorten(creator, 18)) + } else { + label = sprintf("[%s] %s", mediatype[type], \ + gph_encode(shorten(title, 58))) + } + printf "[1|%s|%s/details/%s|%s|%s]\n", label, cgipath, id, + server, port + count++ } + creator = "" + descr = "" + id = "" + type = "" } } close(cmd) + # only show "page back" if the user is past page 1 + if (page > 1) { + printf "[1|[<<] Page %d|%s/list/page%d/rows%d/%%09%s/%d|%s|%s]\n", + page - 1, cgipath, page - 1, rows, + acct, list_id, server, port + } + + # only show "next page" if the current page is completely full + if (count == rows) { + printf "[1|[>>] Page %d|%s/list/page%d/rows%d/%%09%s/%d|%s|%s]\n", + page + 1, cgipath, page + 1, rows, + acct, list_id, server, port + } + + print "" + printf "[1|Account %s|%s/account/%s|%s|%s]\n", acct, cgipath, + acct, server, port + print "" printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port unlink(iaout) exit 0 @@ -64,7 +169,8 @@ BEGIN { config_init() cgi_init() uri_encode_init() + util_init() main() } Index: src/search/index.dcgi.m4 ================================================================== --- src/search/index.dcgi.m4 +++ src/search/index.dcgi.m4 @@ -12,20 +12,10 @@ function main(search, cmd, count, creator, descr, field, fields, i, \ iaout, id, jsout, label, numfound, order, orders, page, rows, \ searchstr, title, type, url) { - mediatype["audio"] = "aud" - mediatype["collection"] = "col" - mediatype["data"] = "dat" - mediatype["etree"] = "aud" - mediatype["image"] = "img" - mediatype["movies"] = "mov" - mediatype["software"] = "bin" - mediatype["texts"] = "txt" - mediatype["web"] = "web" - rows = 15 page = 1 delete order orders = 0 @@ -144,10 +134,11 @@ } else if ($1 == ".response.docs[].identifier" && $2 == "s") { id = $3 } else if ($1 == ".response.docs[].mediatype" && $2 == "s") { type = $3 } else if ($1 == ".response.docs[].title" && $2 == "s") { + # the title field happens to be toward the end of each item title = $3 count++ if (length(creator) > 0) { label = sprintf("[%s] %s by %s", mediatype[type], \ gph_encode(shorten(title, 40)), shorten(creator, 18)) Index: src/util.awk ================================================================== --- src/util.awk +++ src/util.awk @@ -166,10 +166,20 @@ "Attribution-NonCommercial 4.0 International" licenseurl["https://creativecommons.org/licenses/by-nc-sa/4.0/"] = \ "Attribution-NonCommercial-ShareAlike 4.0 International" licenseurl["https://creativecommons.org/licenses/by-nc-nd/4.0/"] = \ "Attribution-NonCommercial-NoDerivs 4.0 International" + + mediatype["audio"] = "aud" + mediatype["collection"] = "col" + mediatype["data"] = "dat" + mediatype["etree"] = "aud" + mediatype["image"] = "img" + mediatype["movies"] = "mov" + mediatype["software"] = "bin" + mediatype["texts"] = "txt" + mediatype["web"] = "web" size_kb = 1024 size_mb = 1024 * 1024 size_gb = 1024 * 1024 * 1024 return ]]> 2024-10-05 22:44:03 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/fd80671eb8/ ben 2024-10-05 22:04:00 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/ebcb3f11b3/ ben &1", cmd_json2tsv, iaout) FS = "\t" - name = "" + count = 0 + delete fields[0] id = 0 is_private = 0 + item = "" item_count = 0 item_id = "" + name = "" + record = "" + delete records[0] while ((cmd | getline) > 0) { if ($1 == ".value[]" && $2 == "o") { - # print information for previous list + # add information for previous list if (!is_private && length(name) > 0 && item_count > 0) { label = shorten_left(name, 50) - printf "[1|%4d Items: %-50s|%s/list/%%09%s/%d|%s|%s]\n", - item_count, label, cgipath, search, id, server, port + item = sprintf("[1|%4d Items: %-50s|%s/list/%%09%s/%d|%s|%s]", \ + item_count, label, cgipath, search, id, server, port) + record = label "\t" id "\t" item + count++ + records[count] = record } } else if ($1 == ".value[].list_name" && $2 == "s") { name = $3 id = 0 is_private = 0 @@ -53,15 +58,31 @@ item_count++ } } close(cmd) - # print information for previous list + # add information for previous list if (!is_private && length(name) > 0 && item_count > 0) { label = shorten_left(name, 50) - printf "[1|%4d Items: %-50s|%s/list/%%09%s/%d|%s|%s]\n", - item_count, label, cgipath, search, id, server, port + item = sprintf("[1|%4d Items: %-50s|%s/list/%%09%s/%d|%s|%s]", \ + item_count, label, cgipath, search, id, server, port) + record = label "\t" id "\t" item + count++ + records[count] = record + } + + # sort lists by label and id + hsort(records, count) + + print search "'s Lists" + print "" + + for (i = 1; i <= count; i++) { + record = records[i] + split(record, fields, /\t/) + item = fields[3] + print item } print "" printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port Index: src/util.awk ================================================================== --- src/util.awk +++ src/util.awk @@ -51,10 +51,55 @@ print "Error: mktemp failed, no tmpfile" exit } return retval } + +# heapsort +# +# Unstable, and unlike merge and quicksort it relies on random-access +# so has poorer cache performance. +# +# Advantage over quicksort is that its worst-case same as avg: O(n log n) +# +# This presentation based on http://dada.perl.it/shootout/heapsort.lua5.html +# +# From: +# +# Requires 1-based numerically indexed arrays. + +function hsort(A, n, c, p, t, i) { + if (!n) { + n = 1 + while (n in A) n++ + n-- + } + i = int(n/2) + 1 + while (1) { + if (i > 1) { + i-- + t = A[i] + } else { + t = A[n] + A[n] = A[1] + n-- + if (n == 1) { + A[1] = t + return + } + } + for (p = i; (c = 2*p) <= n; p = c) { + if ((c < n) && (A[c] < A[c+1])) + c++ + if (t < A[c]) + A[p] = A[c] + else break + } + A[p] = t + } +} function human_size(bytes) { if (bytes > size_gb) { retval = sprintf("%.1fG", bytes / size_gb) } else if (bytes > size_mb) { ]]> 2024-09-29 18:39:15 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/635e5e3f04/ ben 0) { label = "by " shorten(creator, 70) - printf "[1|%s|%s/search/%%09creator:(%s)|%s|%d]\n", label, + printf "[1|%s|%s/search/%%09creator:(%s)|%s|%s]\n", label, cgipath, creator, server, port } if (length(thumb) > 0) { url = sprintf("http://%s%s/%s", item_server, dir, thumb) - printf "[I|Thumbnail|%s/raw/%%09%s|%s|%d]\n", + printf "[I|Thumbnail|%s/raw/%%09%s|%s|%s]\n", cgipath, url, server, port } - printf "[1|Download|%s/download/%s|%s|%d]\n", cgipath, + printf "[1|Download|%s/download/%s|%s|%s]\n", cgipath, item_id, server, port print "" print_html(descr) @@ -183,11 +183,11 @@ } print "" printf "[h|Item web page|URL:%s/details/%s|%s|%s]\n", api_ssl_endpoint, uri_encode(id), server, port - printf "[1|PHAROS|%s|%s|%d]\n", cgipath, server, port + printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port unlink(iaout) return } ]]> 2024-08-19 02:33:45 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/4f746b35ce/ ben 2024-08-18 21:32:30 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/28d511a80c/ ben $out && chmod a+rx $out - m4 -I $dir $in >$out && chmod a+rx $out + echo "m4 $in >$out && chmod a+rx $out" + m4 $in >$out && chmod a+rx $out } # PLAIN for f in index.gph \ account/index.dcgi \ Index: readme.txt ================================================================== --- readme.txt +++ readme.txt @@ -30,11 +30,11 @@ * json2tsv * webdump Configuration ============= -To set configuration variables, edit src/config.m4 +To set configuration variables, edit config.m4 Installation ============ Installation depends on m4. Index: src/account/index.dcgi.m4 ================================================================== --- src/account/index.dcgi.m4 +++ src/account/index.dcgi.m4 @@ -3,11 +3,11 @@ # account/index.dcgi # # Show details for an account -include(config.awk) +include(src/config.awk) incl(src/api.awk) incl(src/cgi.awk) incl(src/util.awk) incl(src/web.awk) DELETED src/config.m4 Index: src/config.m4 ================================================================== --- src/config.m4 +++ /dev/null @@ -1,29 +0,0 @@ -dnl Set configuration variables -dnl -define(__PHAROS_VERSION__, 11)dnl -dnl -define(__API_ENDPOINT__, http://archive.org)dnl -define(__API_SSL_ENDPOINT__, https://archive.org)dnl -define(__AGENT__, Lynx/2.9.0dev.10 libwww-FM/2.14 SSL-MM/1.4.1 OpenSSL/1.1.1w)dnl -define(__CGIPATH__, /~user/pharos)dnl -define(__CMD_AWK__, /usr/bin/awk)dnl -define(__CMD_CURL__, /usr/bin/curl)dnl -define(__CMD_ENV__, /usr/bin/env)dnl -define(__CMD_JSON2TSV__, /usr/local/bin/json2tsv)dnl -define(__CMD_MKTEMP__, /bin/mktemp)dnl -define(__CMD_RM__, rm)dnl -define(__CMD_STRINGS__, /bin/busybox strings)dnl -define(__CMD_WEBDUMP__, /usr/local/bin/webdump)dnl -define(__CMD_XARGS__, /usr/bin/xargs)dnl -define(__GEOMYIDAE_VERSION__, 0.96)dnl -define(__MAX_BIN_SIZE__, 10)dnl -define(__MAX_TXT_SIZE__, 1)dnl -define(__SERVER__, server)dnl -define(__PORT__, port)dnl -dnl -dnl Set up M4 to work with AWK code -dnl -define(m4_substr, defn(substr))dnl -undefine(substr)dnl -changecom(`/*', `*/')dnl -define(incl,`ifdef(paste,paste($1),undivert($1))')dnl Index: src/details/index.dcgi.m4 ================================================================== --- src/details/index.dcgi.m4 +++ src/details/index.dcgi.m4 @@ -3,11 +3,11 @@ # details/index.dcgi # # Show details for an item -include(config.awk) +include(src/config.awk) incl(src/api.awk) incl(src/cgi.awk) incl(src/util.awk) incl(src/web.awk) Index: src/download/index.dcgi.m4 ================================================================== --- src/download/index.dcgi.m4 +++ src/download/index.dcgi.m4 @@ -3,11 +3,11 @@ # download/index.dcgi # # Show file downloads using either direct http or gopher proxy links -include(config.awk) +include(src/config.awk) incl(src/api.awk) incl(src/cgi.awk) incl(src/util.awk) function main(cmd, dir, files, file_size, format, iaout, is_archive, \ Index: src/list/index.dcgi.m4 ================================================================== --- src/list/index.dcgi.m4 +++ src/list/index.dcgi.m4 @@ -3,11 +3,11 @@ # list/index.dcgi # # Show a specific list -include(config.awk) +include(src/config.awk) incl(src/api.awk) incl(src/cgi.awk) incl(src/util.awk) function main( acct, cmd, count, iaout, id, is_private, item_id, Index: src/lists/index.dcgi.m4 ================================================================== --- src/lists/index.dcgi.m4 +++ src/lists/index.dcgi.m4 @@ -3,11 +3,11 @@ # lists/index.dcgi # # Show a list of a user's lists -include(config.awk) +include(src/config.awk) incl(src/api.awk) incl(src/cgi.awk) incl(src/util.awk) function main( cmd, iaout, id, is_private, item_count, item_id, \ Index: src/raw/index.cgi.m4 ================================================================== --- src/raw/index.cgi.m4 +++ src/raw/index.cgi.m4 @@ -15,11 +15,11 @@ # # text/index.cgi # # Show text content scraped from HTML document -include(config.awk) +include(src/config.awk) incl(src/api.awk) incl(src/cgi.awk) incl(src/util.awk) incl(src/web.awk) Index: src/search/index.dcgi.m4 ================================================================== --- src/search/index.dcgi.m4 +++ src/search/index.dcgi.m4 @@ -3,11 +3,11 @@ # search/index.dcgi # # Show search results -include(config.awk) +include(src/config.awk) incl(src/api.awk) incl(src/cgi.awk) incl(src/util.awk) function main(search, cmd, count, creator, descr, field, fields, i, \ Index: src/sort/index.dcgi.m4 ================================================================== --- src/sort/index.dcgi.m4 +++ src/sort/index.dcgi.m4 @@ -3,11 +3,11 @@ # sort/index.dcgi # # Change search sort order -include(config.awk) +include(src/config.awk) incl(src/cgi.awk) function main( i, lbl, opt) { lbl[1] = "Default [^]" opt[1] = "nav_order asc" Index: src/wizard/step1/index.dcgi.m4 ================================================================== --- src/wizard/step1/index.dcgi.m4 +++ src/wizard/step1/index.dcgi.m4 @@ -3,11 +3,11 @@ # wizard/step1/index.dcgi # # Select field to filter/search by -include(config.awk) +include(src/config.awk) incl(src/cgi.awk) function main( i, lbl, opt, searchstr) { searchstr = parts[4] Index: src/wizard/step2/index.dcgi.m4 ================================================================== --- src/wizard/step2/index.dcgi.m4 +++ src/wizard/step2/index.dcgi.m4 @@ -3,11 +3,11 @@ # wizard/step2/index.dcgi # # Select mediatype to filter/search by -include(config.awk) +include(src/config.awk) incl(src/cgi.awk) function main( field, newsearch, searchstr) { field = parts[4] searchstr = parts[5] Index: src/wizard/step3/index.dcgi.m4 ================================================================== --- src/wizard/step3/index.dcgi.m4 +++ src/wizard/step3/index.dcgi.m4 @@ -3,11 +3,11 @@ # wizard/step3/index.dcgi # # Apply new search terms -include(config.awk) +include(src/config.awk) incl(src/cgi.awk) function main( field, label, newsearch, op, searchstr, value) { field = parts[4] searchstr = parts[5] ]]> 2024-08-13 15:21:05 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/a4446184b4/ ben 2024-08-05 23:36:34 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/1d4e024c68/ ben ", html) print html >work close(work) cmd = sprintf("%s -a -n 3 <%s | %s -ilr -w 60", cmd_strings, work, \ cmd_webdump) + marker = 999999 while ((cmd | getline) > 0) { gsub(/\t/, " ") - print + if (NR < marker) { + if ($0 ~ /^References$/) { + marker = NR + } + print $0 + } else { + print_ref_pharos($0) + } } close(cmd) unlink(work) return } + +# Print the webdump references section, converting relative URLs +# to full URLs + +function print_ref_full(str, base, proto, root, link, prefix, relative) { + if (match(str, /^ [0-9]+\. /)) { + prefix = substr(str, 0, RLENGTH) + link = substr(str, RLENGTH+1) + # convert relative links to full URLs + if (link !~ /^[a-z]+:/) { + # convert relative link to full URL + relative = link + if (relative ~ /^\/\//) { + link = proto relative + } else if (relative ~ /^\//) { + link = root relative + } else { + link = base "/" relative + } + } + print prefix link + } else { + print str + } + return +} + + +# Print the webdump references section, translating archive.org URLs to +# pharos URLs + +function print_ref_pharos(str, id, label, link, prefix, relative, token) { + if (match(str, /^ [0-9]+\. /)) { + prefix = substr(str, 0, RLENGTH) + link = substr(str, RLENGTH+1) + + id = "" + if (match(link, /https?:\/\/(www\.)?archive\.org\/details\//)) { + token = substr(link, RSTART+RLENGTH) + id = substr(token, 1, length(token) - 7) + if (match(id, /[?\/ ]/)) { + id = substr(id, 1, RSTART-1) + } + } + if (length(id) > 0) { + label = prefix id + printf "[1|%s|%s/details/%s|%s|%s]\n", label, cgipath, + id, server, port + } else { + print str + } + } else { + print str + } + return +} function web_init() { TYPE_HEADERS = 2 TYPE_LINKS = 1 TYPE_RAW = 9 ]]> 2024-08-05 23:35:09 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/351ce65b44/ ben work close(work) cmd = sprintf("%s -a -n 3 <%s | %s -ilr -w 60", cmd_strings, work, \ cmd_webdump) while ((cmd | getline) > 0) { + gsub(/\t/, " ") print } close(cmd) unlink(work) return ]]> 2024-08-05 21:30:19 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/16461e9da5/ ben 0) { if ($1 == ".value[]" && $2 == "o") { # print information for previous list if (!is_private && length(name) > 0 && item_count > 0) { - printf "[1|%4d Items: %-40s|%s/list/%%09%s/%d|%s|%s]\n", - item_count, name, cgipath, search, id, server, port + label = shorten_left(name, 50) + printf "[1|%4d Items: %-50s|%s/list/%%09%s/%d|%s|%s]\n", + item_count, label, cgipath, search, id, server, port } } else if ($1 == ".value[].list_name" && $2 == "s") { name = $3 id = 0 is_private = 0 @@ -53,12 +55,13 @@ } close(cmd) # print information for previous list if (!is_private && length(name) > 0 && item_count > 0) { - printf "[1|%4d Items: %-40s|%s/list/%%09%s/%d|%s|%s]\n", - item_count, name, cgipath, search, id, server, port + label = shorten_left(name, 50) + printf "[1|%4d Items: %-50s|%s/list/%%09%s/%d|%s|%s]\n", + item_count, label, cgipath, search, id, server, port } print "" printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port ]]> 2024-08-05 16:28:51 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/a46aa098c9/ ben 2024-08-05 16:16:34 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/707f61518c/ ben 0) { printf "%-20s %d\n", "Item Size:", item_size } - printf "%-20s %s", "Media Type:", type + printf "%-20s %s\n", "Media Type:", type print "" printf "[h|Account web page|URL:%s/details/%s|%s|%s]\n", api_ssl_endpoint, uri_encode(id), server, port printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port Index: src/details/index.dcgi.m4 ================================================================== --- src/details/index.dcgi.m4 +++ src/details/index.dcgi.m4 @@ -124,21 +124,21 @@ printf "%-20s %s\n", "Date Added:", add_date } if (pub_date != add_date) { printf "%-20s %s\n", "Date Published:", pub_date } - printf "%-20s %s", "Identifier:", id + printf "%-20s %s\n", "Identifier:", id if (item_size > 0) { - printf "%-20s %d", "Item Size:", item_size + printf "%-20s %d\n", "Item Size:", item_size } if (length(language) > 0) { - printf "%-20s %s", "Language:", language + printf "%-20s %s\n", "Language:", language } if (length(license) > 0) { - printf "%-20s %s", "License:", license + printf "%-20s %s\n", "License:", license } - printf "%-20s %s", "Media Type:", type + printf "%-20s %s\n", "Media Type:", type if (topics > 0) { print "" print "# Topics" for (i = 1; i <= topics; i++) { ]]> 2024-08-05 02:33:38 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/6b25b84bd7/ ben 0) { label = sprintf("[%s] %s by %s", mediatype[type], \ - shorten(title, 40), shorten(creator, 18)) + gph_encode(shorten(title, 40)), shorten(creator, 18)) } else { - label = sprintf("[%s] %s", mediatype[type], shorten(title, 58)) + label = sprintf("[%s] %s", mediatype[type], \ + gph_encode(shorten(title, 58))) } if (type == "collection") { printf "[1|%s|%s/search/%%09collection:(%s)|%s|%s]\n", label, cgipath, id, server, port } else { ]]> 2024-08-05 02:22:23 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/94e85071a3/ ben 0) { label = "by " shorten(creator, 70) - printf "[1%s|%s/search/%%09creator:(%s)|%s|%d]\n", label, + printf "[1|%s|%s/search/%%09creator:(%s)|%s|%d]\n", label, cgipath, creator, server, port } if (length(thumb) > 0) { url = sprintf("http://%s%s/%s", item_server, dir, thumb) printf "[I|Thumbnail|%s/raw/%%09%s|%s|%d]\n", ]]> 2024-08-05 00:38:25 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/2b8f84da38/ ben 2024-08-05 00:34:07 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/3e80d75ddb/ ben 2024-08-05 00:21:49 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/329cb37032/ ben 2024-08-04 23:57:54 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/1c961bcf9a/ ben $@ - chmod a+rx $@ - -$(DESTDIR)/text/index.cgi: $(SRC)/raw/index.cgi.m4 - m4 -I $(SRC) $< >$@ - chmod a+rx $@ - -$(DESTDIR)/direct/index.dcgi: $(SRC)/download/index.dcgi.m4 - m4 -I $(SRC) $< >$@ - chmod a+rx $@ - -$(DESTDIR)/links/index.dcgi: $(SRC)/raw/index.cgi.m4 - m4 -I $(SRC) $< >$@ - chmod a+rx $@ - -$(DESTDIR)/%.cgi: $(SRC)/%.cgi.m4 - m4 -I $(SRC) $< >$@ - chmod a+rx $@ - -$(DESTDIR)/%.dcgi: $(SRC)/%.dcgi.m4 - m4 -I $(SRC) $< >$@ - chmod a+rx $@ - -$(DESTDIR)/%.gph: $(SRC)/%.gph.m4 - m4 -I $(SRC) $< >$@ - -clean: - rm -f $(CGIS) $(DCGIS) $(GOPHERMAPS) ADDED clean.sh Index: clean.sh ================================================================== --- /dev/null +++ clean.sh @@ -0,0 +1,27 @@ +#!/bin/sh +set -x +cd pharos +rm -f index.gph \ + account/index.dcgi \ + audio/index.gph \ + books/index.gph \ + images/index.gph \ + debug/index.cgi \ + details/index.dcgi \ + direct/index.dcgi \ + download/index.dcgi \ + links/index.dcgi \ + list/index.dcgi \ + lists/index.dcgi \ + raw/index.cgi \ + search/index.dcgi \ + software/index.gph \ + sort/index.dcgi \ + text/index.cgi \ + video/index.gph \ + wizard/step1/index.dcgi \ + wizard/step2/index.dcgi \ + wizard/step3/index.dcgi +set +x +cd - +exit 0 ADDED make.sh Index: make.sh ================================================================== --- /dev/null +++ make.sh @@ -0,0 +1,40 @@ +#!/bin/sh +DESTDIR=pharos +SRC=src + +build() { + dir=$1 + in=$2 + out=$3 + echo m4 -I $dir $in \>$out && chmod a+rx $out + m4 -I $dir $in >$out && chmod a+rx $out +} + +# PLAIN +for f in index.gph \ + account/index.dcgi \ + audio/index.gph \ + books/index.gph \ + images/index.gph \ + details/index.dcgi \ + download/index.dcgi \ + list/index.dcgi \ + lists/index.dcgi \ + raw/index.cgi \ + search/index.dcgi \ + software/index.gph \ + sort/index.dcgi \ + video/index.gph \ + wizard/step1/index.dcgi \ + wizard/step2/index.dcgi \ + wizard/step3/index.dcgi +do + build $SRC ${SRC}/${f}.m4 ${DESTDIR}/$f +done + +# WEIRD +build $SRC ${SRC}/raw/index.cgi.m4 ${DESTDIR}/debug/index.cgi +build $SRC ${SRC}/raw/index.cgi.m4 ${DESTDIR}/text/index.cgi +build $SRC ${SRC}/download/index.dcgi.m4 ${DESTDIR}/direct/index.dcgi +build $SRC ${SRC}/raw/index.cgi.m4 ${DESTDIR}/links/index.dcgi +exit 0 Index: readme.txt ================================================================== --- readme.txt +++ readme.txt @@ -34,11 +34,11 @@ ============= To set configuration variables, edit src/config.m4 Installation ============ -Installation depends on make and m4. +Installation depends on m4. -$ make clean -$ make +$ sh clean.sh +$ sh make.sh Copy pharos/ into place ]]> 2024-08-04 23:53:17 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/1a3675c579/ ben 2024-08-04 23:29:37 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/bb9dd0b07e/ ben 2024-08-04 22:33:57 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/cc2ec0bce4/ ben 0) { - if ($1 == ".value[]" && $2 == "o") { - if (!is_private && length(name) > 0 && item_count > 0) { - printf "[1%4d Items: %-40s|%s/lists/%%09%s/%d|%s|%s]\n", - item_count, name, cgipath, search, id, server, port - } - } else if ($1 == ".value.list_name" && $2 == "s") { + if ($1 == ".value.list_name" && $2 == "s") { name = $3 print "# List: " name id = 0 is_private = 0 } else if ($1 == ".value.is_private" && $2 == "b") { ]]> 2024-08-04 22:11:56 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/d9b7917834/ ben $@ + chmod a+rx $@ + +$(DESTDIR)/text/index.cgi: $(SRC)/raw/index.cgi.m4 + m4 -I $(SRC) $< >$@ + chmod a+rx $@ + +$(DESTDIR)/direct/index.dcgi: $(SRC)/download/index.dcgi.m4 + m4 -I $(SRC) $< >$@ + chmod a+rx $@ + +$(DESTDIR)/links/index.dcgi: $(SRC)/raw/index.cgi.m4 + m4 -I $(SRC) $< >$@ + chmod a+rx $@ + +$(DESTDIR)/%.cgi: $(SRC)/%.cgi.m4 + m4 -I $(SRC) $< >$@ + chmod a+rx $@ + +$(DESTDIR)/%.dcgi: $(SRC)/%.dcgi.m4 + m4 -I $(SRC) $< >$@ + chmod a+rx $@ + +$(DESTDIR)/%.gph: $(SRC)/%.gph.m4 + m4 -I $(SRC) $< >$@ + +clean: + rm -f $(CGIS) $(DCGIS) $(GOPHERMAPS) ADDED pharos/about.txt Index: pharos/about.txt ================================================================== --- /dev/null +++ pharos/about.txt @@ -0,0 +1,36 @@ +# About PHAROS + +Proxy Internet Archive to gopher. + +# Search + +Example: To find Indian music, excluding commercial samples. + + description:(indian) AND -collection:samples_only AND + mediatype:audio AND subject:music + +# Fields + +* date: + YYYY-MM-DD or [YYYY-MM-DD TO YYYY-MM-DD] +* mediatype: + audio, collection, data, image, movies, software, texts, or web + +# Media type key for search results + +* [aud] = audio or etree +* [col] = collection +* [dat] = data +* [img] = image +* [mov] = movies +* [bin] = software +* [txt] = texts +* [web] = web + +See also: + +# Limits + +This service does not work in the lagrange browser. +Lagrange URI encodes the search string and also +mangles items that are not URI encoded. ADDED pharos/wizard/index.gph Index: pharos/wizard/index.gph ================================================================== --- /dev/null +++ pharos/wizard/index.gph @@ -0,0 +1,10 @@ + , _ + /| | | + _/_\_ >_< + .-\-/. | + / | | \_ | + \ \| |\__(/ + /(`---') | + / / \ | + _.' \'-' / | + `----'`=-=' ' hjw ADDED readme.txt Index: readme.txt ================================================================== --- /dev/null +++ readme.txt @@ -0,0 +1,44 @@ +PHAROS by Ben Collver +============================================= +* Description +* Requirements +* Configuration +* Installation + +Description +=========== +Pharos is a gopher front-end to the Internet Archive written in AWK. +It is named after the light-house island near Alexandria. + +For a description and screenshots from an earlier version, see my +post linked below. + + + + + +Requirements +============ +* Runs under the Geomyidae gopher server. + +* Written in AWK. Tested using busybox awk. +* Commands used: + * env, mktemp, rm, strings, xargs + * curl + * json2tsv + * webdump + +Configuration +============= +To set configuration variables, edit src/config.m4 + +Installation +============ +Installation depends on make and m4. + +$ make clean +$ make + +Copy pharos/ into place ADDED src/account/index.dcgi.m4 Index: src/account/index.dcgi.m4 ================================================================== --- /dev/null +++ src/account/index.dcgi.m4 @@ -0,0 +1,112 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# account/index.dcgi +# +# Show details for an account + +include(config.awk) +undivert(api.awk) +undivert(cgi.awk) +undivert(util.awk) +undivert(web.awk) + +function main( acct, cmd, col, cols, descr, dir, email, iaout, id, + item_server, item_size, thumb, title, type, url) +{ + acct = parts[3] + email = search + + iaout = gettemp() + + url = api_endpoint "/metadata/" acct + api_request(url, "GET", iaout) + + # format search results as a gopher directory (menu) + cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) + FS = "\t" + cols = 0 + delete col + descr = "" + dir = "" + id = "" + item_server = "" + item_size = 0 + title = "" + thumb = "" + type = "" + while ((cmd | getline) > 0) { + if ($1 == ".dir" && $2 == "s") { + dir = $3 + } else if ($1 == ".files[].name" && $2 == "s") { + if ($3 == "__ia_thumb.jpg") { + thumb = $3 + } + } else if ($1 == ".item_size" && $2 == "n") { + item_size = $3 + } else if ($1 == ".metadata.collection" && $2 == "s") { + cols++ + col[cols] = $3 + } else if ($1 == ".metadata.collection[]" && $2 == "s") { + cols++ + col[cols] = $3 + } else if ($1 == ".metadata.description" && $2 == "s") { + descr = $3 + } else if ($1 == ".metadata.identifier" && $2 == "s") { + id = $3 + } else if ($1 == ".metadata.mediatype" && $2 == "s") { + type = $3 + } else if ($1 == ".metadata.title" && $2 == "s") { + title = $3 + } else if ($1 == ".server" && $2 == "s") { + item_server = $3 + } + } + close(cmd) + + if (length(id) == 0) { + print_not_found(url) + unlink(iaout) + return + } + + print "Account: " acct + if (length(thumb) > 0) { + url = sprintf("http://%s%s/%s", item_server, dir, thumb) + printf "[I|Thumbnail|%s/raw/%%09%s|%s|%s]\n", cgipath, url, + server, port + } + print_html(descr) + + if (length(email) > 0) { + printf "[1|Uploads|%s/search/%%09uploader:%s|%s|%s]\n", + cgipath, email, server, port + } + printf "[1|Items|%s/search/%%09anyfield:%s|%s|%s]\n", cgipath, + acct, server, port + printf "[1|Lists|%s/lists/%%09%s|%s|%s]\n", cgipath, acct, + server, port + + print "" + printf "%-20s %s\n", "Identifier:", id + if (item_size > 0) { + printf "%-20s %d\n", "Item Size:", item_size + } + printf "%-20s %s", "Media Type:", type + + print "" + printf "[h|Account web page|URL:%s/details/%s|%s|%s]\n", + api_ssl_endpoint, uri_encode(id), server, port + printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port + + unlink(iaout) + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + uri_encode_init() + main() +} ADDED src/api.awk Index: src/api.awk ================================================================== --- /dev/null +++ src/api.awk @@ -0,0 +1,24 @@ +function api_request(url, method, output, data) { + retval = "" + curlcfg = gettemp() + printf "--connect-timeout 10\n" > curlcfg + printf "--max-redirs 0\n" >> curlcfg + if (url ~ /^https:/) { + printf "--proto =https\n" >> curlcfg + } else { + printf "--proto =http\n" >> curlcfg + } + printf "--show-error\n" >> curlcfg + printf "--silent\n" >> curlcfg + printf "--url %s\n", uri_encode(url) >> curlcfg + printf "--user-agent %s\n", agent >> curlcfg + close(curlcfg) + cmd = sprintf("%s -K %s 2>&1", cmd_curl, curlcfg) + while ((cmd | getline) > 0) { + print $0 >>output + } + close(output) + close(cmd) + unlink(curlcfg) + return retval +} ADDED src/audio/index.gph.m4 Index: src/audio/index.gph.m4 ================================================================== --- /dev/null +++ src/audio/index.gph.m4 @@ -0,0 +1,21 @@ +include(config.m4)dnl +# Audio + +[1|All Audio|__CGIPATH__/search/sortweek desc/%09mediatype:audio|__SERVER__|__PORT__] +[1|This Just In|__CGIPATH__/search/sortpublicdate desc/%09mediatype:audio|__SERVER__|__PORT__] +[1|Live Music Archive|__CGIPATH__/search/sortweek desc/%09collection:etree AND mediatype:collection|__SERVER__|__PORT__] +[1|Librivox Free Audiobooks|__CGIPATH__/search/sortweek desc/%09collection:librivoxaudio|__SERVER__|__PORT__] +[1|Grateful Dead|__CGIPATH__/search/sortweek desc/%09collection:GratefulDead|__SERVER__|__PORT__] +[1|Netlabels|__CGIPATH__/search/sortweek desc/%09collection:netlabels AND mediatype:collection|__SERVER__|__PORT__] +[1|Old Time Radio|__CGIPATH__/search/sortweek desc/%09collection:oldtimeradio|__SERVER__|__PORT__] +[1|78 RPMs & Cylinder Recordings|__CGIPATH__/search/sortweek desc/%09collection:78rpm AND mediatype:collection|__SERVER__|__PORT__] +[1|Audio Books & Poetry|__CGIPATH__/search/sortweek desc/%09collection:audio_bookspoetry|__SERVER__|__PORT__] +[1|Computers, Technology & Science|__CGIPATH__/search/sortweek desc/%09collection:audio_tech|__SERVER__|__PORT__] +[1|Music, Arts & Culture|__CGIPATH__/search/sortweek desc/%09collection:audio_music AND mediatype:collection|__SERVER__|__PORT__] +[1|News & Public Affairs|__CGIPATH__/search/sortweek desc/%09collection:audio_news|__SERVER__|__PORT__] +[1|Spirituality & Religion|__CGIPATH__/search/sortweek desc/%09collection:audio_religion|__SERVER__|__PORT__] +[1|Podcasts|__CGIPATH__/search/sortweek desc/%09collection:podcasts|__SERVER__|__PORT__] +[1|Radio News Archive|__CGIPATH__/search/sortweek desc/%09collection:radio|__SERVER__|__PORT__] +[1|Long Playing Records|__CGIPATH__/search/sortweek desc/%09collection:album_recordings|__SERVER__|__PORT__] +[1|Various Cassette Tapes|__CGIPATH__/search/sortweek desc/%09collection:cassettetapes|__SERVER__|__PORT__] +[1|Audiophile CD Collection|__CGIPATH__/search/sortweek desc/%09collection:acdc AND -collection:samples_only|__SERVER__|__PORT__] ADDED src/books/index.gph.m4 Index: src/books/index.gph.m4 ================================================================== --- /dev/null +++ src/books/index.gph.m4 @@ -0,0 +1,22 @@ +include(config.m4)dnl +# Books + +[1|All Books|__CGIPATH__/search/sortweek desc/%09collection:books AND -access-restricted-item:true|__SERVER__|__PORT__] +[1|All Texts|__CGIPATH__/search/sortweek desc/%09mediatype:texts AND -access-restricted-item:true|__SERVER__|__PORT__] +[1|This Just In|__CGIPATH__/search/sortpublicdate desc/%09mediatype:texts AND -access-restricted-item:true|__SERVER__|__PORT__] +[1|Smithsonian Libraries|__CGIPATH__/search/sortweek desc/%09collection:smithsonian|__SERVER__|__PORT__] +[1|FEDLINK|__CGIPATH__/search/sortweek desc/%09collection:fedlink AND mediatype:collection|__SERVER__|__PORT__] +[1|Genealogy|__CGIPATH__/search/sortweek desc/%09collection:genealogy AND mediatype:collection|__SERVER__|__PORT__] +[1|Lincoln Collection|__CGIPATH__/search/sortweek desc/%09collection:lincolncollection|__SERVER__|__PORT__] +[1|American Libraries|__CGIPATH__/search/sortweek desc/%09collection:americana AND mediatype:collection AND -access-restricted-item:true|__SERVER__|__PORT__] +[1|Canadian Libraries|__CGIPATH__/search/sortweek desc/%09collection:toronto AND mediatype:collection AND -access-restricted-item:true|__SERVER__|__PORT__] +[1|Universal Library|__CGIPATH__/search/sortweek desc/%09collection:universallibrary|__SERVER__|__PORT__] +[1|Project Gutenberg|__CGIPATH__/search/sortweek desc/%09collection:gutenberg|__SERVER__|__PORT__] +[1|Children's Library|__CGIPATH__/search/sortweek desc/%09collection:iacl AND -access-restricted-item:true|__SERVER__|__PORT__] +[1|Biodiversity Heritage Library|__CGIPATH__/search/sortweek desc/%09collection:biodiversity AND mediatype:collection|__SERVER__|__PORT__] +[1|Books By Language|__CGIPATH__/search/sortweek desc/%09collection:booksbylanguage AND mediatype:collection|__SERVER__|__PORT__] +[1|Additional Collections|__CGIPATH__/search/sortweek desc/%09collection:additional_collections AND mediatype:collection|__SERVER__|__PORT__] +[1|The Magazine Rack|__CGIPATH__/search/sortweek desc/%09collection:magazine_rack AND mediatype:collection|__SERVER__|__PORT__] +[1|The Pulp Magazine Archive|__CGIPATH__/search/sortweek desc/%09collection:pulpmagazinearchive|__SERVER__|__PORT__] +[1|Newspapers|__CGIPATH__/search/sortweek desc/%09collection:newspapers AND mediatype:collection|__SERVER__|__PORT__] +[1|Comic Books & Graphic Novels|__CGIPATH__/search/sortweek desc/%09collection:comics AND -access-restricted-item:true|__SERVER__|__PORT__] ADDED src/cgi.awk Index: src/cgi.awk ================================================================== --- /dev/null +++ src/cgi.awk @@ -0,0 +1,74 @@ +function cgi_init() { + search = ARGV[1] + arguments = ARGV[2] + traversal = ARGV[5] + selector = ARGV[6] + + if (geomyidae_version < 0.96) { + input = arguments + } else { + input = traversal + } + + if (length(search) == 0 && match(input, /%09.*/)) { + # This is a hack to include a search in the URL. + # everything before %09 is considered arguments + # everything after %09 is considered the search + search = substr(input, RSTART+3, RLENGTH-3) + args = substr(input, 0, RSTART-1) + } else { + args = input + } + + # query is everything after ? in the gopher selector + # this is NOT the same as the gopher search string + query = args + + # parse the path out of the selector + path = selector + if (substr(path, 1, length(cgipath)) == cgipath) { + path = substr(path, length(cgipath) + 1) + } + if (match(path, /%09/)) { + path = substr(path, 1, RSTART-1) + } + + split(path, parts, "/") + topdir = parts[2] + + return +} + +function uri_encode_init( i, c) { + for (i = 0; i <= 255; i++) { + c = sprintf("%c", i) + uri_encode_ord[c] = i + uri_encode_tab[i] = c + } + + # Percent encode only control characters so that the higher unicode + # block characters are left plainly visible. + for (i = 0; i < 33; i++) { + uri_encode_tab[i] = sprintf("%%%02X", i) + } + + # Percent encode higher unicode block characters too + for (i = 128; i <= 255; i++) { + uri_encode_tab[i] = sprintf("%%%02X", i) + } + + # DEL + uri_encode_tab[127] = sprintf("%%%02X", 127) + + return +} + +function uri_encode(str, i, c, len) { + len = length(str) + retval = "" + for (i = 1; i <= len; i++) { + c = substr(str, i, 1) + retval = retval uri_encode_tab[uri_encode_ord[c]] + } + return retval +} ADDED src/config.awk Index: src/config.awk ================================================================== --- /dev/null +++ src/config.awk @@ -0,0 +1,20 @@ +function config_init() { + agent = "__AGENT__" + api_endpoint = "__API_ENDPOINT__" + api_ssl_endpoint = "__API_SSL_ENDPOINT__" + cgipath = "__CGIPATH__" + cmd_curl = "__CMD_CURL__" + cmd_enc = "__CMD_ENV__" + cmd_json2tsv = "__CMD_JSON2TSV__" + cmd_mktemp = "__CMD_MKTEMP__" + cmd_rm = "__CMD_RM__" + cmd_strings = "__CMD_STRINGS__" + cmd_webdump = "__CMD_WEBDUMP__" + cmd_xargs = "__CMD_XARGS__" + geomyidae_version = __GEOMYIDAE_VERSION__ + max_bin_size = __MAX_BIN_SIZE__ + max_txt_size = __MAX_TXT_SIZE__ + server = "__SERVER__" + port = "__PORT__" + return +} ADDED src/config.m4 Index: src/config.m4 ================================================================== --- /dev/null +++ src/config.m4 @@ -0,0 +1,28 @@ +dnl Set configuration variables +dnl +define(__PHAROS_VERSION__, 11)dnl +dnl +define(__API_ENDPOINT__, http://archive.org)dnl +define(__API_SSL_ENDPOINT__, https://archive.org)dnl +define(__AGENT__, Lynx/2.9.0dev.10 libwww-FM/2.14 SSL-MM/1.4.1 OpenSSL/1.1.1w)dnl +define(__CGIPATH__, /~user/pharos)dnl +define(__CMD_AWK__, /usr/bin/awk)dnl +define(__CMD_CURL__, /usr/bin/curl)dnl +define(__CMD_ENV__, /usr/bin/env)dnl +define(__CMD_JSON2TSV__, /usr/local/bin/json2tsv)dnl +define(__CMD_MKTEMP__, /bin/mktemp)dnl +define(__CMD_RM__, rm)dnl +define(__CMD_STRINGS__, /bin/busybox strings)dnl +define(__CMD_WEBDUMP__, /usr/local/bin/webdump)dnl +define(__CMD_XARGS__, /usr/bin/xargs)dnl +define(__GEOMYIDAE_VERSION__, 0.96)dnl +define(__MAX_BIN_SIZE__, 10)dnl +define(__MAX_TXT_SIZE__, 1)dnl +define(__SERVER__, server)dnl +define(__PORT__, port)dnl +dnl +dnl Set up M4 to work with AWK code +dnl +define(m4_substr, defn(substr))dnl +undefine(substr)dnl +changecom(`/*', `*/')dnl ADDED src/details/index.dcgi.m4 Index: src/details/index.dcgi.m4 ================================================================== --- /dev/null +++ src/details/index.dcgi.m4 @@ -0,0 +1,200 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# details/index.dcgi +# +# Show details for an item + +include(config.awk) +undivert(api.awk) +undivert(cgi.awk) +undivert(util.awk) +undivert(web.awk) + +function main( add_date, col, cols, cmd, creator, descr, dir, i, \ + iaout, id, item_id, item_server, item_size, label, language, \ + license, pub_date, scanner, thumb, title, topic, topics, type, \ + uploader_account, uploader_email, url) +{ + item_id = parts[3] + + iaout = gettemp() + + url = api_endpoint "/metadata/" item_id + api_request(url, "GET", iaout) + + # format search results as a gopher directory (menu) + cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) + FS = "\t" + cols = 0 + delete col + add_date = "" + creator = "" + descr = "" + dir = "" + id = "" + item_server = "" + item_size = 0 + language = "" + license = "" + pub_date = "" + scanner = "" + thumb = "" + title = "" + topics = 0 + delete topic + type = "" + uploader_account = "" + uploader_email = "" + while ((cmd | getline) > 0) { + if ($1 == ".dir" && $2 == "s") { + dir = $3 + } else if ($1 == ".files[].name" && $2 == "s") { + if ($3 == "__ia_thumb.jpg") { + thumb = $3 + } + } else if ($1 == ".item_size" && $2 == "n") { + item_size = $3 + } else if ($1 == ".metadata.addeddate" && $2 == "s") { + added_date = $3 + } else if ($1 == ".metadata.collection" && $2 == "s") { + cols++ + col[cols] = $3 + } else if ($1 == ".metadata.collection[]" && $2 == "s") { + cols++ + col[cols] = $3 + } else if ($1 == ".metadata.creator" && $2 == "s") { + creator = $3 + } else if ($1 == ".metadata.description" && $2 == "s") { + descr = $3 + } else if ($1 == ".metadata.identifier" && $2 == "s") { + id = $3 + } else if ($1 == ".metadata.language" && $2 == "s") { + language = $3 + } else if ($1 == ".metadata.license" && $2 == "s") { + license = licenseurl[$3] + } else if ($1 == ".metadata.mediatype" && $2 == "s") { + type = $3 + } else if ($1 == ".metadata.publicdate" && $2 == "s") { + pub_date = $3 + } else if ($1 == ".metadata.scanner" && $2 == "s") { + scanner = $3 + } else if ($1 == ".metadata.subject" && $2 == "s") { + topics++ + topic[topics] = $3 + } else if ($1 == ".metadata.subject[]" && $2 == "s") { + topics++ + topic[topics] = $3 + } else if ($1 == ".metadata.title" && $2 == "s") { + title = $3 + } else if ($1 == ".metadata.uploader" && $2 == "s") { + uploader_email = $3 + } else if ($1 == ".server" && $2 == "s") { + item_server = $3 + } + } + close(cmd) + + if (length(id) == 0) { + print_not_found(url) + unlink(iaout) + return + } + + print(shorten(title, 70)) + if (length(creator) > 0) { + label = "by " shorten(creator, 70) + printf "[1%s|%s/search/%%09creator:(%s)|%s|%d]\n", label, + cgipath, creator, server, port + } + if (length(thumb) > 0) { + url = sprintf("http://%s%s/%s", item_server, dir, thumb) + printf "[I|Thumbnail|%s/raw/%%09%s|%s|%d]\n", + cgipath, url, server, port + } + + printf "[1|Download|%s/download/%s|%s|%d]\n", cgipath, + item_id, server, port + print "" + + print_html(descr) + + print "" + if (length(add_date) > 0) { + printf "%-20s %s\n", "Date Added:", add_date + } + if (pub_date != add_date) { + printf "%-20s %s\n", "Date Published:", pub_date + } + printf "%-20s %s", "Identifier:", id + if (item_size > 0) { + printf "%-20s %d", "Item Size:", item_size + } + if (length(language) > 0) { + printf "%-20s %s", "Language:", language + } + if (length(license) > 0) { + printf "%-20s %s", "License:", license + } + printf "%-20s %s", "Media Type:", type + + if (topics > 0) { + print "" + print "# Topics" + for (i = 1; i <= topics; i++) { + label = shorten(topic[i], 40) + printf "[1|%s|%s/search/%%09subject:(%s)|%s|%s]\n", label, + cgipath, topic[i], server, port + } + } + + # scrape uploader name from item web page HTML + url = api_ssl_endpoint "/details/" item_id + api_request(url, "GET", iaout) + while ((getline 0) { + if (/item-upload-info__uploader-name/ && + match($0, /\/details\/[^"]*"/)) + { + uploader_account = substr($0, RSTART+9, RLENGTH-10) + } + } + close(iaout) + + if (cols > 0) { + print "" + print "# Collections" + for (i = 1; i <= cols; i++) { + label = shorten(col[i], 40) + printf "[1|%s|%s/search/%%09collection:(%s)|%s|%s]\n", + label, cgipath, col[i], server, port + } + } + + print "" + print "# Uploaded by" + if (length(uploader_account) > 0) { + label = shorten(uploader_account, 70) + printf "[1|%s|%s/account/%s%%09%s|%s|%s]\n", label, cgipath, + uploader_account, uploader_email, server, port + } else { + label = shorten(uploader_email, 70) + printf "[1|%s|%s/search/%%09uploader:%s|%s|%s]\n", label, + cgipath, uploader_email, server, port + } + + print "" + printf "[h|Item web page|URL:%s/details/%s|%s|%s]\n", + api_ssl_endpoint, uri_encode(id), server, port + printf "[1|PHAROS|%s|%s|%d]\n", cgipath, server, port + + unlink(iaout) + return +} + +BEGIN { + config_init() + + cgi_init() + uri_encode_init() + main() +} ADDED src/download/index.dcgi.m4 Index: src/download/index.dcgi.m4 ================================================================== --- /dev/null +++ src/download/index.dcgi.m4 @@ -0,0 +1,105 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# download/index.dcgi +# +# Show file downloads using either direct http or gopher proxy links + +include(config.awk) +undivert(api.awk) +undivert(cgi.awk) +undivert(util.awk) + +function main(cmd, dir, files, file_size, format, iaout, is_archive, \ + is_proxy, item_server, label, mtime, name, source, url) +{ + dir = parts[2] + item_id = parts[3] + if (dir == "download") { + is_proxy = 1 + } else { + # dir == "direct" + is_proxy = 0 + } + + iaout = gettemp() + + url = api_endpoint "/metadata/" item_id + api_request(url, "GET", iaout) + + # format search results as a gopher directory (menu) + cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) + FS = "\t" + dir = "" + files = 0 + delete format + item_server = "" + delete mtime + delete name + delete file_size + delete source + + while ((cmd | getline) > 0) { + if ($1 == ".dir" && $2 == "s") { + dir = $3 + } else if ($1 == ".files[]" && $2 == "o") { + files++ + } else if ($1 == ".files[].format" && $2 == "s") { + format[files] = $3 + } else if ($1 == ".files[].mtime" && $2 == "s") { + mtime[files] = $3 + } else if ($1 == ".files[].name" && $2 == "s") { + name[files] = $3 + } else if ($1 == ".files[].size" && $2 == "s") { + file_size[files] = $3 + } else if ($1 == ".files[].source" && $2 == "s") { + source[files] = $3 + } else if ($1 == ".server" && $2 == "s") { + item_server = $3 + } + } + close(cmd) + + for (i = 1; i <= files; i++) { + label = sprintf("%s %s %s", \ + shorten_left(name[i], 40), \ + strftime("%Y-%m-%d %H:%M", mtime[i]), \ + human_size(file_size[i])) + url = sprintf("http://%s%s/%s", item_server, dir, name[i]) + if (is_proxy) { + if (file_size[i] > max_bin_size * size_mb) { + printf "[h|%s|URL:%s|%s|%s]\n", label, uri_encode(url), + server, port + } else { + printf "[1|%s|%s/links/%%09%s|%s|%s]\n", label, cgipath, + url, server, port + } + } else { + printf "[h|%s|URL:%s|%s|%s]\n", label, uri_encode(url), + server, port + } + is_archive = detect_archive(url) + if (is_archive) { + url = sprintf("http://%s/view_archive.php?archive=%s/%s", \ + item_server, dir, name[i]) + printf "[h|%s (View Contents)|URL:%s|%s|%s]\n", + shorten_left(name[i], 40), uri_encode(url), + server, port + } + } + + printf "[1|Downloads via http|%s/direct/%s|%s|%s]\n", cgipath, + item_id, server, port + + unlink(iaout) + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + uri_encode_init() + util_init() + main() +} ADDED src/images/index.gph.m4 Index: src/images/index.gph.m4 ================================================================== --- /dev/null +++ src/images/index.gph.m4 @@ -0,0 +1,14 @@ +include(config.m4)dnl +# Images + +[1|All Images|__CGIPATH__/search/sortweek desc/%09mediatype:image|__SERVER__|__PORT__] +[1|This Just In|__CGIPATH__/search/sortpublicdate desc/%09mediatype:image|__SERVER__|__PORT__] +[1|Metropolitan Museum of Art|__CGIPATH__/search/sortweek desc/%09collection:metropolitanmuseumofart-gallery|__SERVER__|__PORT__] +[1|Cleveland Museum of Art|__CGIPATH__/search/sortweek desc/%09collection:clevelandart|__SERVER__|__PORT__] +[1|Flickr Commons|__CGIPATH__/search/sortweek desc/%09collection:flickrcommons|__SERVER__|__PORT__] +[1|Occupy Wallstreet Flickr|__CGIPATH__/search/sortweek desc/%09collection:flickr-ows|__SERVER__|__PORT__] +[1|Cover Art|__CGIPATH__/search/sortweek desc/%09collection:coverartarchive|__SERVER__|__PORT__] +[1|USGS Maps|__CGIPATH__/search/sortweek desc/%09collection:maps_usgs|__SERVER__|__PORT__] +[1|NASA Images|__CGIPATH__/search/sortweek desc/%09collection:nasa|__SERVER__|__PORT__] +[1|Solar System Collection|__CGIPATH__/search/sortweek desc/%09collection:solarsystemcollection|__SERVER__|__PORT__] +[1|Ames Research Center|__CGIPATH__/search/sortweek desc/%09collection:amesresearchcenterimagelibrary|__SERVER__|__PORT__] ADDED src/index.gph.m4 Index: src/index.gph.m4 ================================================================== --- /dev/null +++ src/index.gph.m4 @@ -0,0 +1,26 @@ +include(config.m4)dnl + .n. | + /___\ _.---. \ _ / + [|||] (_._ ) )--;_) =- + [___] '---'.__,' \ + }-=-{ | + |-" | + |.-"| p +~^=~^~-|_.-|~^-~^~ ~^~ -^~^~|\ ~^-~^~- +^ .=.| _.|__ ^ ~ /| \ + ~ /:. \" _|_/\ ~ /_|__\ ^ +.-/::. | |""|-._ ^ ~~~~ + `===-'-----'""` '-. ~ + PHAROS __.-' ^ + +Gopher proxy to Internet Archive. + +[7|Search|__CGIPATH__/search/|__SERVER__|__PORT__] +[1|Advanced Search|__CGIPATH__/wizard/step1|__SERVER__|__PORT__] +[1|Books|__CGIPATH__/books/|__SERVER__|__PORT__] +[1|Video|__CGIPATH__/video/|__SERVER__|__PORT__] +[1|Audio|__CGIPATH__/audio/|__SERVER__|__PORT__] +[1|Software|__CGIPATH__/software/|__SERVER__|__PORT__] +[1|Images|__CGIPATH__/images/|__SERVER__|__PORT__] +[0|About PHAROS|__CGIPATH__/about.txt|__SERVER__|__PORT__] +[h|Source Code|URL:https://chiselapp.com/user/bencollver/repository/pharos/logout|__SERVER__|__PORT__] ADDED src/list/index.dcgi.m4 Index: src/list/index.dcgi.m4 ================================================================== --- /dev/null +++ src/list/index.dcgi.m4 @@ -0,0 +1,74 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# lists/index.dcgi +# +# Show a specific list + +include(config.awk) +undivert(api.awk) +undivert(cgi.awk) +undivert(util.awk) + +function main( acct, cmd, count, iaout, id, is_private, item_id, + name, list_id, name, parts, url) +{ + count = split(search, parts, "/") + acct = parts[1] + list_id = parts[2] + + print acct "'s Lists" + print "" + + iaout = gettemp() + + url = api_ssl_endpoint "/services/users/" acct "/lists/" list_id + api_request(url, "GET", iaout) + + # format list as a gopher directory (menu) + cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) + FS = "\t" + name = "" + id = 0 + is_private = 0 + item_id = "" + + while ((cmd | getline) > 0) { + if ($1 == ".value[]" && $2 == "o") { + if (!is_private && length(name) > 0 && item_count > 0) { + printf "[1%4d Items: %-40s|%s/lists/%%09%s/%d|%s|%s]\n", + item_count, name, cgipath, search, id, server, port + } + } else if ($1 == ".value.list_name" && $2 == "s") { + name = $3 + print "# List: " name + id = 0 + is_private = 0 + } else if ($1 == ".value.is_private" && $2 == "b") { + if ($3 == "true") { + is_private = 1 + } + } else if ($1 == ".value.members[].identifier" && $2 == "s") { + if (!is_private) { + item_id = $3 + printf "[1|%s|%s/details/%s|%s|%s]\n", item_id, + cgipath, item_id, server, port + } + } + } + close(cmd) + + print "" + printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port + + unlink(iaout) + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + uri_encode_init() + main() +} ADDED src/lists/index.dcgi.m4 Index: src/lists/index.dcgi.m4 ================================================================== --- /dev/null +++ src/lists/index.dcgi.m4 @@ -0,0 +1,75 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# lists/index.dcgi +# +# Show a list of a user's lists + +include(config.awk) +undivert(api.awk) +undivert(cgi.awk) +undivert(util.awk) + +function main( cmd, iaout, id, is_private, item_count, item_id, name, url) +{ + print search "'s Lists" + print "" + + iaout = gettemp() + + url = api_ssl_endpoint "/services/users/" search "/lists" + api_request(url, "GET", iaout) + + # format list as a gopher directory (menu) + cmd = sprintf("%s <%s 2>&1", cmd_json2tsv, iaout) + FS = "\t" + name = "" + id = 0 + is_private = 0 + item_count = 0 + item_id = "" + + while ((cmd | getline) > 0) { + if ($1 == ".value[]" && $2 == "o") { + # print information for previous list + if (!is_private && length(name) > 0 && item_count > 0) { + printf "[1|%4d Items: %-40s|%s/list/%%09%s/%d|%s|%s]\n", + item_count, name, cgipath, search, id, server, port + } + } else if ($1 == ".value[].list_name" && $2 == "s") { + name = $3 + id = 0 + is_private = 0 + item_count = 0 + } else if ($1 == ".value[].is_private" && $2 == "b") { + if ($3 == "true") { + is_private = 1 + } + } else if ($1 == ".value[].id" && $2 == "n") { + id = $3 + } else if ($1 == ".value[].members[].identifier" && $2 == "s") { + item_count++ + } + } + close(cmd) + + # print information for previous list + if (!is_private && length(name) > 0 && item_count > 0) { + printf "[1|%4d Items: %-40s|%s/list/%%09%s/%d|%s|%s]\n", + item_count, name, cgipath, search, id, server, port + } + + print "" + printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port + + unlink(iaout) + return +} + +BEGIN { + config_init() + + cgi_init() + uri_encode_init() + main() +} ADDED src/raw/index.cgi.m4 Index: src/raw/index.cgi.m4 ================================================================== --- /dev/null +++ src/raw/index.cgi.m4 @@ -0,0 +1,46 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# debug/index.cgi +# +# Show HTTP headers from curl fetching a URL +# +# links/index.dcgi +# +# Show download links, plus links scraped from HTML document +# +# raw/index.cgi +# +# Show raw bytes from binary document +# +# text/index.cgi +# +# Show text content scraped from HTML document + +include(config.awk) +undivert(api.awk) +undivert(cgi.awk) +undivert(util.awk) +undivert(web.awk) + +function main() { + if (path == "/debug/") { + dump(search, TYPE_HEADERS) + } else if (path == "/raw/") { + dump(search, TYPE_RAW) + } else if (path == "/text/") { + dump(search, TYPE_TEXT) + } else if (path == "/links/") { + dump(search, TYPE_LINKS) + } + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + uri_encode_init() + web_init() + main() +} ADDED src/search/index.dcgi.m4 Index: src/search/index.dcgi.m4 ================================================================== --- /dev/null +++ src/search/index.dcgi.m4 @@ -0,0 +1,212 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# search/index.dcgi +# +# Show search results + +include(config.awk) +undivert(api.awk) +undivert(cgi.awk) +undivert(util.awk) + +function main(search, cmd, count, creator, descr, field, fields, i, \ + iaout, id, jsout, label, numfound, order, orders, page, rows, \ + searchstr, title, type, url) +{ + mediatype["audio"] = "aud" + mediatype["collection"] = "col" + mediatype["data"] = "dat" + mediatype["etree"] = "aud" + mediatype["image"] = "img" + mediatype["movies"] = "mov" + mediatype["software"] = "bin" + mediatype["texts"] = "txt" + mediatype["web"] = "web" + + rows = 15 + page = 1 + delete order + orders = 0 + + # parse out page number and sort orders + for (i in parts) { + if (parts[i] ~ /^rows[0-9][0-9]*$/) { + rows = substr(parts[i], 5) + } else if (parts[i] ~ /^page[0-9][0-9]*$/) { + page = substr(parts[i], 5) + } else if (parts[i] ~ /^sort/) { + orders++ + str = substr(parts[i], 5) + order[orders] = str + } + } + + # special case for when the search term is an archive.org details URL + if (match(search, /^https:\/\/(www\.)?archive\.org\/details\//)) { + id = substr(search, RLENGTH+1) + search = "identifier:" id + } + + # remove quotes from search string, since it gets quoted later + gsub(/"/, "", search) + + # default sort orders if none were specified + if (orders == 0) { + orders = 1 + if (search == "mediatype:collection" || + search == "mediatype:(collection)") + { + order[1] = "collection_size desc" + } else { + order[1] = "nav_order desc" + } + } + + iaout = gettemp() + jsout = gettemp() + + # get search results + + field[1] = "creator" + field[2] = "description" + field[3] = "identifier" + field[4] = "mediatype" + field[5] = "title" + fields = 5 + + # remove anyfield, a hobgoblin of consistency + searchstr = search + gsub(/anyfield:/, "", searchstr) + + url = sprintf("%s/advancedsearch.php?q=%s&output=json&rows=%d&page=%d", \ + api_endpoint, searchstr, rows, page) + for (i = 1; i <= orders; i++) { + url = url sprintf("&sort%%5B%d%%5D=%s", i-1, order[i]) + } + for (i = 1; i <= fields; i++) { + url = url sprintf("&fl%%5B%d%%5D=%s", i-1, field[i]) + } + api_request(url, "GET", iaout) + + cmd = sprintf("%s <%s >%s 2>&1", cmd_json2tsv, iaout, jsout) + system(cmd) + + numfound = 0 + FS = "\t" + while ((getline 0) { + if ($1 == ".response.numFound" && $2 == "n") { + numfound = $3 + } + } + close(jsout) + + if (search ~ /^@/) { + numfound++ + } + if (numfound == 0) { + print "Your search did not match any items in the Archive." + print "Try different keywords or a more general search." + print "" + printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port + unlink(jsout) + unlink(iaout) + return + } else { + pages = int(numfound / rows) + if (numfound % rows != 0) { + pages++ + } + printf "# %s search results, page %d of %d\n", numfound, \ + page, pages + print "" + } + + # format search results as a gopher directory (menu) + FS = "\t" + creator = "" + descr = "" + id = "" + title = "" + type = "" + count = 0 + + if (search ~ /^@/) { + printf "[1|Account %s|%s/account/%s|%s|%s]\n", search, cgipath, + search, server, port + } + + while ((getline 0) { + if ($1 == ".response.docs[].creator" && $2 == "s") { + creator = $3 + } else if ($1 == ".response.docs[].description" && $2 == "s") { + descr = $3 + } else if ($1 == ".response.docs[].identifier" && $2 == "s") { + id = $3 + } else if ($1 == ".response.docs[].mediatype" && $2 == "s") { + type = $3 + } else if ($1 == ".response.docs[].title" && $2 == "s") { + title = $3 + count++ + if (length(creator) > 0) { + label = sprintf("[%s] %s by %s", mediatype[type], \ + shorten(title, 40), shorten(creator, 18)) + } else { + label = sprintf("[%s] %s", mediatype[type], shorten(title, 58)) + } + if (type == "collection") { + printf "[1|%s|%s/search/%%09collection:(%s)|%s|%s]\n", + label, cgipath, id, server, port + } else { + printf "[1|%s|%s/details/%s|%s|%s]\n", label, cgipath, + id, server, port + } + creator = "" + descr = "" + id = "" + type = "" + } + } + close(jsout) + + print "" + + # only show "page back" if the user is past page 1 + if (page > 1) { + printf "[1|[<<] Page %d|%s/search/page%d/rows%d/%%09%s|%s|%s]\n", + page - 1, cgipath, page - 1, rows, search, server, port + } + + # only show "next page" if the current page is completely full + if (count == rows) { + printf "[1|[>>] Page %d|%s/search/page%d/rows%d/%%09%s|%s|%s]\n", + page + 1, cgipath, page + 1, rows, search, server, port + } + + # only show "sort" if there's more than one item to sort + if (count > 1) { + printf "[1|[^v] Sort|%s/sort/%%09%s|%s|%s]\n", cgipath, search, + server, port + } + + # only show "search within list" if there's multiple pages of results + if (numfound > rows) { + printf "[1|[\\/] Filter results|%s/wizard/step1/%s|%s|%s]\n", + cgipath, search, server, port + } + + printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port + + unlink(jsout) + unlink(iaout) + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + uri_encode_init() + util_init() + main(search) +} ADDED src/software/index.gph.m4 Index: src/software/index.gph.m4 ================================================================== --- /dev/null +++ src/software/index.gph.m4 @@ -0,0 +1,27 @@ +include(config.m4)dnl + +[1|All Software|__CGIPATH__/search/sortweek desc/%09mediatype:software|__SERVER__|__PORT__] +[1|This Just In|__CGIPATH__/search/sortpublicdate desc/%09mediatype:software|__SERVER__|__PORT__] +[1|Internet Arcade|__CGIPATH__/search/sortweek desc/%09collection:internetarcade|__SERVER__|__PORT__] +[1|Console Living Room|__CGIPATH__/search/sortweek desc/%09collection:consolelivingroom|__SERVER__|__PORT__] +[1|Old School Emulation|__CGIPATH__/search/sortweek desc/%09collection:tosec|__SERVER__|__PORT__] +[1|MS-DOS Games|__CGIPATH__/search/sortweek desc/%09collection:softwarelibrary_msdos_games|__SERVER__|__PORT__] +[1|Historical Software|__CGIPATH__/search/sortweek desc/%09collection:historicalsoftware|__SERVER__|__PORT__] +[1|Classic PC Games|__CGIPATH__/search/sortweek desc/%09collection:classicpcgames|__SERVER__|__PORT__] +[1|Software Library|__CGIPATH__/search/sortweek desc/%09collection:softwarelibrary AND mediatype:collection|__SERVER__|__PORT__] +[1|Kodi Archive & Support Files|__CGIPATH__/search/sortweek desc/%09collection:kodi_archive|__SERVER__|__PORT__] +[1|Vintage Software|__CGIPATH__/search/sortweek desc/%09collection:vintagesoftware|__SERVER__|__PORT__] +[1|APK|__CGIPATH__/search/sortweek desc/%09collection:apkarchive|__SERVER__|__PORT__] +[1|MS-DOS|__CGIPATH__/search/sortweek desc/%09collection:softwarelibrary_msdos|__SERVER__|__PORT__] +[1|CD-ROM Software|__CGIPATH__/search/sortweek desc/%09collection:cd-roms|__SERVER__|__PORT__] +[1|CD-ROM Software Library|__CGIPATH__/search/sortweek desc/%09collection:cdromsoftware|__SERVER__|__PORT__] +[1|Software Sites|__CGIPATH__/search/sortweek desc/%09collection:softwaresites|__SERVER__|__PORT__] +[1|Tucows Software Library|__CGIPATH__/search/sortweek desc/%09collection:tucows|__SERVER__|__PORT__] +[1|Shareware CD-ROMs|__CGIPATH__/search/sortweek desc/%09collection:cdbbsarchive|__SERVER__|__PORT__] +[1|Software Capsules Compilation|__CGIPATH__/search/sortweek desc/%09collection:softwarecapsules|__SERVER__|__PORT__] +[1|CD-ROM Images|__CGIPATH__/search/sortweek desc/%09collection:cdromimages|__SERVER__|__PORT__] +[1|ZX Spectrum|__CGIPATH__/search/sortweek desc/%09collection:softwarelibrary_zx_spectrum|__SERVER__|__PORT__] +[1|DOOM Level CD|__CGIPATH__/search/sortweek desc/%09collection:doom-cds|__SERVER__|__PORT__] +[1|Floppy Disks of Software|__CGIPATH__/search/sortweek desc/%09collection:floppysoftware|__SERVER__|__PORT__] +[1|The Good Old Days IBM PC Floppy Collection|__CGIPATH__/search/sortweek desc/%09collection:TGODFloppyCollection|__SERVER__|__PORT__] +[1|MS-DOS: The Frostbyte Shareware Collection|__CGIPATH__/search/sortweek desc/%09collection:softwarelibrary_msdos_frostbyte|__SERVER__|__PORT__] ADDED src/sort/index.dcgi.m4 Index: src/sort/index.dcgi.m4 ================================================================== --- /dev/null +++ src/sort/index.dcgi.m4 @@ -0,0 +1,61 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# sort/index.dcgi +# +# Change search sort order + +include(config.awk) +undivert(cgi.awk) + +function main( i, lbl, opt) { + lbl[1] = "Default [^]" + opt[1] = "nav_order asc" + lbl[2] = "Default [v]" + opt[2] = "nav_order desc" + lbl[3] = "Weekly views [^]" + opt[3] = "week asc" + lbl[4] = "Weekly views [v]" + opt[4] = "week desc" + lbl[5] = "All-time views [^]" + opt[5] = "downloads asc" + lbl[6] = "All-time views [v]" + opt[6] = "downloads desc" + lbl[7] = "Title [^]" + opt[7] = "title asc" + lbl[8] = "Title [v]" + opt[8] = "title desc" + lbl[9] = "Date added [^]" + opt[9] = "addeddate asc" + lbl[10] = "Date added [v]" + opt[10] = "addeddate desc" + lbl[11] = "Date created [^]" + opt[11] = "createddate asc" + lbl[12] = "Date created [v]" + opt[12] = "createddate desc" + lbl[13] = "Date published [^]" + opt[13] = "publicdate asc" + lbl[14] = "Date published [v]" + opt[14] = "publicdate desc" + lbl[15] = "Creator [^]" + opt[15] = "creator asc" + lbl[16] = "Creator [v]" + opt[16] = "creator desc" + lbl[17] = "Random" + opt[17] = "random asc" + + print "# Sort by" + print "" + for (i = 1; i < 18; i++) { + printf "[1|%s|%s/search/sort%s%%09%s|%s|%s]\n", + lbl[i], cgipath, opt[i], search, server, port + } + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + main() +} ADDED src/util.awk Index: src/util.awk ================================================================== --- /dev/null +++ src/util.awk @@ -0,0 +1,131 @@ +function detect_archive(url, str) { + str = tolower(url) + if (str ~ /\.iso$/ || + str ~ /\.zip$/) + { + retval = 1 + } else { + retval = 0 + } + return retval +} + +function detect_html(url, str) { + str = tolower(url) + if (str ~ /\.html?$/ || + str ~ /\.php$/) + { + retval = 1 + } else { + retval = 0 + } + return retval +} + +function detect_image(url, str) { + str = tolower(url) + if (str ~ /\.bmp$/ || + str ~ /\.gif$/ || + str ~ /\.jpg$/ || + str ~ /\.jpeg$/ || + str ~ /\.png$/ || + str ~ /\.webp$/) + { + retval = 1 + } else { + retval = 0 + } + return retval +} + +function gettemp( result) { + while ((cmd_mktemp | getline) > 0) { + retval = $0 + } + result = close(cmd_mktemp) + if (result != 0) { + print "Error: mktemp failed exit status: " result + exit + } + if (length(retval) == 0) { + print "Error: mktemp failed, no tmpfile" + exit + } + return retval +} + +function human_size(bytes) { + if (bytes > size_gb) { + retval = sprintf("%.1fG", bytes / size_gb) + } else if (bytes > size_mb) { + retval = sprintf("%.1fM", bytes / size_mb) + } else if (bytes > size_kb) { + retval = sprintf("%.1fK", bytes / size_kb) + } else { + retval = sprintf("%dB", bytes) + } + return retval +} + +function print_not_found(url) { + print "Item cannot be found" + print "" + print "Items may be taken down for various reasons," + print "including by decision of the uploader or" + print "due to a violation of the Terms of Use." + print "" + printf "[h|Metadata|URL:%s|%s|%s]\n", url, server, port + print "" + url = api_ssl_endpoint "/about/terms.php" + printf "[0|Terms of Use|%s/text/%%09%s|%s|%s]\n", cgipath, + url, server, port + print "" + printf "[1|PHAROS|%s|%s|%s]\n", cgipath, server, port + return +} + +function shorten_left(str, len) { + if (length(str) > len) { + retval = "..." substr(str, 3 + length(str) - len) + } else { + retval = str + } + return retval +} + +function shorten(str, len) { + if (length(str) > len) { + retval = substr(str, 0, len - 3) "..." + } else { + retval = str + } + return retval +} + +function unlink(name) { + system(cmd_rm " " name) + return +} + +function util_init() { + licenseurl[""] = "None" + licenseurl["https://creativecommons.org/publicdomain/zero/1.0/"] = \ + "Public Domain" + licenseurl["https://creativecommons.org/licenses/by/4.0/"] = \ + "Attribution 4.0 International" + licenseurl["https://creativecommons.org/licenses/by-sa/4.0/"] = \ + "Attribution-ShareAlike 4.0 International" + licenseurl["https://creativecommons.org/licenses/by-nd/4.0/"] = \ + "Attribution-NoDerivs 4.0 International" + licenseurl["https://creativecommons.org/licenses/by-nc/4.0/"] = \ + "Attribution-NonCommercial 4.0 International" + licenseurl["https://creativecommons.org/licenses/by-nc-sa/4.0/"] = \ + "Attribution-NonCommercial-ShareAlike 4.0 International" + licenseurl["https://creativecommons.org/licenses/by-nc-nd/4.0/"] = \ + "Attribution-NonCommercial-NoDerivs 4.0 International" + + size_kb = 1024 + size_mb = 1024 * 1024 + size_gb = 1024 * 1024 * 1024 + return +} ADDED src/video/index.gph.m4 Index: src/video/index.gph.m4 ================================================================== --- /dev/null +++ src/video/index.gph.m4 @@ -0,0 +1,23 @@ +include(config.m4)dnl +# Video + +[1|All Video|__CGIPATH__/search/sortweek desc/%09mediatype:movies|__SERVER__|__PORT__] +[1|This Just In|__CGIPATH__/search/sortpublicdate desc/%09mediatype:movies|__SERVER__|__PORT__] +[1|Prelinger Archives|__CGIPATH__/search/sortweek desc/%09collection:prelinger|__SERVER__|__PORT__] +[1|Democracy Now!|__CGIPATH__/search/sortweek desc/%09collection:democracy_now_vid|__SERVER__|__PORT__] +[1|Occupy Wall Street|__CGIPATH__/search/sortweek desc/%09collection:occupywallstreet|__SERVER__|__PORT__] +[1|TV NSA Clip Library|__CGIPATH__/search/sortweek desc/%09collection:nsa|__SERVER__|__PORT__] +[1|Animation And Cartoons|__CGIPATH__/search/sortweek desc/%09collection:animationandcartoons|__SERVER__|__PORT__] +[1|Arts & Music|__CGIPATH__/search/sortweek desc/%09collection:artsandmusicvideos|__SERVER__|__PORT__] +[1|Computers & Technology|__CGIPATH__/search/sortweek desc/%09collection:computersandtechvideos|__SERVER__|__PORT__] +[1|Cultural & Academic Films|__CGIPATH__/search/sortweek desc/%09collection:culturalandacademicfilms|__SERVER__|__PORT__] +[1|Ephemeral Films|__CGIPATH__/search/sortweek desc/%09collection:ephemera|__SERVER__|__PORT__] +[1|Movies|__CGIPATH__/search/sortweek desc/%09collection:moviesandfilms|__SERVER__|__PORT__] +[1|News & Public Affairs|__CGIPATH__/search/sortweek desc/%09collection:newsandpublicaffairs|__SERVER__|__PORT__] +[1|Spirituality & Religion|__CGIPATH__/search/sortweek desc/%09collection:spiritualityandreligion|__SERVER__|__PORT__] +[1|Sports|__CGIPATH__/search/sortweek desc/%09collection:sports|__SERVER__|__PORT__] +[1|Television|__CGIPATH__/search/sortweek desc/%09collection:television AND mediatype:collection|__SERVER__|__PORT__] +[1|VHS Vault|__CGIPATH__/search/sortweek desc/%09collection:vhsvault|__SERVER__|__PORT__] +[1|Video Games|__CGIPATH__/search/sortweek desc/%09collection:gamevideos AND mediatype:collection|__SERVER__|__PORT__] +[1|Vlogs|__CGIPATH__/search/sortweek desc/%09collection:vlogs|__SERVER__|__PORT__] +[1|Youth Media|__CGIPATH__/search/sortweek desc/%09collection:youth_media|__SERVER__|__PORT__] ADDED src/web.awk Index: src/web.awk ================================================================== --- /dev/null +++ src/web.awk @@ -0,0 +1,159 @@ +function dump(search, type, base, cmd, curlcfg, is_html, is_image, \ + label, limit, link, marker, parts, prefix, proto, relative, root, \ + url) +{ + url = search + gsub(/%3F/, "?", url) + + if (url !~ /^(http|https):\/\/[[:alnum:].-]+(:[0-9]+)*(\/[[:alnum:].,?@~=%%:\/+&_() -]*)*$/) { + printf "Error: Unacceptable URL \"%s\"\r\n", url + return + } + + if (type == TYPE_HEADERS || type == TYPE_RAW) { + limit = max_bin_size + } else { + limit = max_txt_size + } + + # Use temporary file for curl configuration. + # This keeps user input separate from shell execution. + + curlcfg = gettemp() + printf "--connect-timeout 10\n" > curlcfg + printf "--max-filesize %dM\n", limit >> curlcfg + printf "--max-redirs 0\n" >> curlcfg + printf "--proto =http,https\n" >> curlcfg + printf "--show-error\n" >> curlcfg + printf "--silent\n" >> curlcfg + printf "--url %s\n", uri_encode(url) >> curlcfg + printf "--user-agent %s\n", agent >> curlcfg + if (type == TYPE_HEADERS) { + printf "--output /dev/null\n" >> curlcfg + printf "--dump-header -\n" >> curlcfg + } + close(curlcfg) + + if (type == TYPE_HEADERS || type == TYPE_RAW) { + cmd = sprintf("%s -K %s 2>&1", cmd_curl, curlcfg) + system(cmd) + unlink(curlcfg) + return + } + + # Use strings command to guard webdump from binary input. + # Use "strings -a" to avoid security pitfalls. + + cmd = sprintf("%s -K %s 2>&1 | %s -a -n 3 | %s -ilr -w 60", \ + cmd_curl, curlcfg, cmd_strings, cmd_webdump) + + # Parse base out of original URL. + # Use this to convert relative links to full URLs. + # webdump has the -b option for this. + # Do it manually instead to avoid passing user input through the shell. + + split(url, parts, "?") + base = parts[1] + if (match(base, /^(http|https):\/\/[[:alnum:].-]+(:[0-9]+)*/)) { + root = substr(base, 0, RLENGTH) + } else { + root = "" + } + if (match(base, /^(http|https):/)) { + proto = substr(base, 0, RLENGTH) + } else { + proto = "" + } + sub(/\/$/, "", base) + + # marker determines where the bottom references section begins + # line numbers smaller than the marker are content + # line numbers larger than the marker are referenced links + + marker = 999999 + + if (type == TYPE_LINKS) { + is_html = detect_html(url) + is_image = detect_image(url) + printf "[9|Binary download|%s/raw/%%09%s|%s|%s]\n", cgipath, + search, server, port + if (is_image) { + printf "[I|Image view|%s/raw/%%09%s|%s|%s]\n", cgipath, + search, server, port + } + if (is_html) { + label = "Source" + } else { + label = "Text view" + } + printf "[0|%s|%s/raw/%%09%s|%s|%s]\n", label, cgipath, search, + server, port + if (is_html) { + label = "HTML view" + } else { + label = "Strings" + } + printf "[0|%s|%s/text/%%09%s|%s|%s]\n", label, cgipath, search, + server, port + printf "[0|Headers|%s/debug/%%09%s|%s|%s]\n", cgipath, search, + server, port + print "" + } + + while ((cmd | getline) > 0) { + if (NR < marker) { + if ($0 ~ /^References$/) { + marker = NR + } + if (type == TYPE_TEXT) { + print $0 + } + } else { + if (match($0, /^ [0-9]+\. /)) { + prefix = substr($0, 0, RLENGTH) + link = substr($0, RLENGTH+1) + if (link !~ /^[a-z]+:/) { + # convert relative link to full URL + relative = link + if (relative ~ /^\/\//) { + link = proto relative + } else if (relative ~ /^\//) { + link = root relative + } else { + link = base "/" relative + } + } + print prefix link + } else { + print $0 + } + } + } + close(cmd) + + unlink(curlcfg) + + return +} + +function print_html(html, cmd, work) { + work = gettemp() + gsub(/\\n/, "
", html) + print html >work + close(work) + cmd = sprintf("%s -a -n 3 <%s | %s -ilr -w 60", cmd_strings, work, \ + cmd_webdump) + while ((cmd | getline) > 0) { + print + } + close(cmd) + unlink(work) + return +} + +function web_init() { + TYPE_HEADERS = 2 + TYPE_LINKS = 1 + TYPE_RAW = 9 + TYPE_TEXT = 0 +} ADDED src/wizard/step1/index.dcgi.m4 Index: src/wizard/step1/index.dcgi.m4 ================================================================== --- /dev/null +++ src/wizard/step1/index.dcgi.m4 @@ -0,0 +1,67 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# wizard/step1/index.dcgi +# +# Select field to filter/search by + +include(config.awk) +undivert(cgi.awk) + +function main( i, lbl, opt, searchstr) { + searchstr = parts[4] + + lbl[1] = "Any field contains" + opt[1] = "anyfield" + lbl[2] = "Any field does not contain" + opt[2] = "-anyfield" + lbl[3] = "Title contains" + opt[3] = "title" + lbl[4] = "Title does not contain" + opt[4] = "-title" + lbl[5] = "Creator contains" + opt[5] = "creator" + lbl[6] = "Creator does not contain" + opt[6] = "-creator" + lbl[7] = "Description contains" + opt[7] = "description" + lbl[8] = "Description does not contain" + opt[8] = "-description" + lbl[9] = "Collection is" + opt[9] = "collection" + lbl[10] = "Collection does not contain" + opt[10] = "-collection" + lbl[11] = "Mediatype is" + opt[11] = "mediatype" + lbl[12] = "Mediatype does not contain" + opt[12] = "-mediatype" + lbl[13] = "Date or date range is" + opt[13] = "date" + lbl[14] = "Language contains" + opt[14] = "language" + lbl[15] = "Always available" + opt[15] = "-access-restricted-item" + + print "# Search wizard: Select field" + print "" + for (i = 1; i < 16; i++) { + if (opt[i] ~ /mediatype$/) { + printf "[1|%s|%s/wizard/step2/%s/%s|%s|%s]\n", lbl[i], + cgipath, opt[i], searchstr, server, port + } else if (lbl[i] == "Always available") { + printf "[1|%s|%s/wizard/step3/%s/%s%%09true|%s|%s]\n", + lbl[i], cgipath, opt[i], searchstr, server, port + } else { + printf "[7|%s|%s/wizard/step3/%s/%s|%s|%s]\n", lbl[i], + cgipath, opt[i], searchstr, server, port + } + } + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + main() +} ADDED src/wizard/step2/index.dcgi.m4 Index: src/wizard/step2/index.dcgi.m4 ================================================================== --- /dev/null +++ src/wizard/step2/index.dcgi.m4 @@ -0,0 +1,51 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# wizard/step2/index.dcgi +# +# Select mediatype to filter/search by + +include(config.awk) +undivert(cgi.awk) + +function main( field, newsearch, searchstr) { + field = parts[4] + searchstr = parts[5] + + if (field == "mediatype") { + print "# Mediatype is:" + } else { + print "# Mediatype does not contain:" + } + print "" + + lbl[1] = "audio" + lbl[2] = "collection" + lbl[3] = "data" + lbl[4] = "etree" + lbl[5] = "image" + lbl[6] = "movies" + lbl[7] = "software" + lbl[8] = "texts" + lbl[9] = "web" + for (i = 1; i < 10; i++) { + if (length(searchstr) == 0) { + newsearch = sprintf("%s:(%s)", field, lbl[i]) + } else { + newsearch = sprintf("%s AND %s:(%s)", searchstr, field, lbl[i]) + } + printf "[1|%s|%s/search/%%09%s|%s|%s]\n", lbl[i], cgipath, + newsearch, server, port + } + print "# Progress:" + print "" + print "* Field: Mediatype" + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + main() +} ADDED src/wizard/step3/index.dcgi.m4 Index: src/wizard/step3/index.dcgi.m4 ================================================================== --- /dev/null +++ src/wizard/step3/index.dcgi.m4 @@ -0,0 +1,44 @@ +include(config.m4)dnl +#!__CMD_AWK__ -f + +# wizard/step3/index.dcgi +# +# Apply new search terms + +include(config.awk) +undivert(cgi.awk) + +function main( field, label, newsearch, op, searchstr, value) { + field = parts[4] + searchstr = parts[5] + value = search + + if (field ~ /^-/) { + label = toupper(substr(field, 2, 1)) substr(field, 3) + op = "does not contain" + } else { + label = toupper(substr(field, 1, 1)) substr(field, 2) + op = "contains" + } + if (length(searchstr) == 0) { + newsearch = sprintf("%s:(%s)", field, value) + } else { + newsearch = sprintf("%s AND %s:(%s)", searchstr, field, value) + } + print "" + printf "[1|Apply search criteria|%s/search/%%09%s|%s|%s]\n", + cgipath, newsearch, server, port + print "" + print "# Progress:" + print "" + printf "* Field %s %s %s\n", label, op, value + printf "* New search: %s\n", newsearch + exit 0 +} + +BEGIN { + config_init() + + cgi_init() + main() +} ]]> 2024-08-04 22:03:15 gopher://tilde.pink/1/~bencollver/fossil/pharos/info/777ee78a5b/ bencollver 2024-08-04 21:43:36