Awki Awki Source Code

The source is spread over three files and it comes with a conf file (KUDOS!). This is the 0.1 version of awkiawki.

Don't be scared! The source looks better on the edit page :)

1. awki.cgi - main cgi script

2. awki.conf - setting options for your server and wiki

3. parser.awk - parsing pages you've just created

4. special_parser.awk - parsing diffs if you enabled rcs


1. awki.cgi - main cgi script
	#!/usr/bin/mawk -f
	################################################################################
	# awkiawki - wikiwiki clone written in (n|g|m)awk
	# $Id: awki.cgi,v 1.45 2004/07/13 16:34:45 olt Exp $
	################################################################################
	# Copyright (c) 2002 Oliver Tonnhofer (olt@bogosoft.com)
	# See the file `COPYING' for copyright notice.
	################################################################################

BEGIN { # --- default options --- # --- use awki.conf to override default settings --- # # img_tag: HTML img tag for picture in page header. localconf["img_tag"] = "<img src=\"/awki.png\" width=\"48\" height=\"39\" align=\"left\">" # datadir: Directory for raw pagedata (must be writeable for the script). localconf["datadir"] = "./data/" # parser: Parsing script. localconf["parser"] = "./parser.awk" # special_parser: Parser for special_* functions. localconf["special_parser"] = "./special_parser.awk" # default_page: Name of the default_page. localconf["default_page"] = "FrontPage" # show_changes: Number of changes listed by RecentChanges localconf["show_changes"] = 10 # max_post: Bytes accept by POST requests (to avoid DOS). localconf["max_post"] = 100000 # write_protection: Regex for write protected files # e.g.: "*", "PageOne?|PageTwo?|^.*NonEditable?" # HINT: to edit these protected pages, upload a .htaccess # protected awki.cgi script with write_protection = "" localconf["write_protection"] = "" # css: HTTP URL for external CSS file. localconf["css"] = "" # always_convert_spaces: If true, convert runs of 8 spaces to tab automatical. localconf["always_convert_spaces"] = 0 # date_cmd: Command for current date. localconf["date_cmd"] = "date '+%e %b. %G %R:%S %Z'" # rcs: If true, rcs is used for revisioning. localconf["rcs"] = 0 # path: add path to PATH environment localconf["path"] = "" # --- default options ---

scriptname = ENVIRON["SCRIPT_NAME"]

if (localconf["path"]) ENVIRON["PATH"] = localconf["path"] ":" ENVIRON["PATH"]

#load external configfile load_config(scriptname)

# PATH_INFO contains page name if (ENVIRON["PATH_INFO"]) { query["page"] = ENVIRON["PATH_INFO"] }

if (ENVIRON["REQUEST_METHOD"] == "POST") { if (ENVIRON["CONTENT_TYPE"] == "application/x-www-form-urlencoded") { if (ENVIRON["CONTENT_LENGTH"] < localconf["max_post"]) bytes = ENVIRON["CONTENT_LENGTH"] else bytes = localconf["max_post"] cmd = "dd ibs=1 count=" bytes " 2>/dev/null" cmd | getline query_str close (cmd) } if (ENVIRON["QUERY_STRING"]) query_str = query_str "&" ENVIRON["QUERY_STRING"] } else { if (ENVIRON["QUERY_STRING"]) query_str = ENVIRON["QUERY_STRING"] }

n = split(query_str, querys, "&") for (i=1; i<=n; i++) { split(querys[i], data, "=") query[data[1]] = data[2] }

# (IMPORTANT for security!) query["page"] = clear_pagename(query["page"]) query["revision"] = clear_revision(query["revision"]) query["revision2"] = clear_revision(query["revision2"]) query["string"] = clear_str(decode(query["string"]))

if (!localconf["rcs"]) query["revision"] = 0

if (query["page"] == "") query["page"] = localconf["default_page"]

query["filename"] = localconf["datadir"] query["page"]

#check if page is editable special_pages = "FullSearch|PageList|RecentChanges"

if (query["page"] ~ "("special_pages")") { special_page = 1 } else if (!localconf["write_protection"] || query["page"] !~ "("localconf["write_protection"]")") { page_editable = 1 }

header(query["page"])

if (query["edit"] && page_editable) edit(query["page"], query["filename"], query["revision"]) else if (query["save"] && query["text"] && page_editable) save(query["page"], query["text"], query["string"], query["filename"]) else if (query["page"] ~ "PageList") special_index(localconf["datadir"]) else if (query["page"] ~ "RecentChanges") special_changes(localconf["datadir"]) else if (query["page"] ~ "FullSearch") special_search(query["string"],localconf["datadir"]) else if (query["page"] && query["history"]) special_history(query["page"], query["filename"]) else if (query["page"] && query["diff"] && query["revision"]) special_diff(query["page"], query["filename"], query["revision"], query["revision2"]) else parse(query["page"], query["filename"], query["revision"])

footer(query["page"])

}

# print header function header(page) { print "Content-type: text/html\n" print "<html>\n<head>\n<title>" page "</title>" if (localconf["css"]) print "<link rel=\"stylesheet\" href=\"" localconf["css"] "\">" if (query["save"]) print "<meta http-equiv=\"refresh\" content=\"2,URL="scriptname"/"page"\">" print "</head>\n<body>" print "<h1>"localconf["img_tag"] print "<a href=\""scriptname"/FullSearch?string="page"\">"page"</a></h1><hr>" }

# print footer function footer(page) { print "<hr>" if (page_editable) print "<a href=\""scriptname"?edit=true&amp;page="page"\">Edit "page"</a>" print "<a href=\""scriptname"/"localconf["default_page"]"\">"localconf["default_page"]"</a>" print "<a href=\""scriptname"/PageList\">PageList</a>" print "<a href=\""scriptname"/RecentChanges\">RecentChanges</a>" if (localconf["rcs"] && !special_page) print "<a href=\""scriptname"/"page"?history=true\">PageHistory</a>" print "<form action=\""scriptname"/FullSearch\" method=\"GET\" align=\"right\">" print "<input type=\"text\" name=\"string\">" print "<input type=\"submit\" value=\"search\">" print "</form>\n</body>\n</html>" }

# send page to parser script function parse(name, filename, revision) { if (system("[ -f "filename" ]") == 0 ) { if (revision) { print "<em>Displaying old version ("revision") of <a href=\""scriptname"/" name "\">"name"</a>.</em>" system("co -q -p'"revision"' " filename " | "localconf["parser"] " -v datadir='"localconf["datadir"] "'") } else system(localconf["parser"] " -v datadir='"localconf["datadir"] "' " filename) } }

function special_diff(page, filename, revision, revision2, revisions) { if (system("[ -f "filename" ]") == 0) { print "<em>Displaying diff between "revision if (revision2) print " and "revision2 else print " and current version" print " of <a href=\""scriptname"/"page "\">"page"</a>.</em>" if (revision2) revisions = "-r" revision " -r" revision2 else revisions = "-r" revision system("rcsdiff "revisions" -u "filename" | " localconf["special_parser"] " -v special_diff='"page"'") } }

# print edit form function edit(page, filename, revision, cmd) { if (revision) print "<p><small><em>If you save previous versions, you'll overwrite the current page.</em></small>" print "<form action=\""scriptname"?save=true&amp;page="page"\" method=\"POST\">" print "<textarea name=\"text\" rows=25 cols=80>" # insert current page into textarea if (revision) { cmd = "co -q -p'"revision"' " filename while ((cmd | getline) >0) print close(cmd) } else { while ((getline < filename) >0) print close(filename) } print "</textarea><br />" print "<input type=\"submit\" value=\"save\">" if (localconf["rcs"]) print "Comment: <input type=\"text\" name=\"string\" maxlength=80 size=50>" if (! localconf["always_convert_spaces"]) print "<br>Convert runs of 8 spaces to Tab <input type=\"checkbox\" name=\"convertspaces\">" print "</form>" print "<small><strong>Emphases:</strong> <em>italic</em>; <strong>bold</strong>; <strong><em>bold italic</em></strong>; <em>mixed <strong>bold</strong>and italic</em><br><strong>Horizontal Rule:</strong> ----<br><strong>Paragraph:</strong> blank line<br><strong>Headings:</strong> -Title 1 ; --Title 2 ; ---Title 3<br><strong>Preformatted Text:</strong> *space*Text<br><strong>Lists:</strong> tab(s) and one of * bullets; 1 numbered items<br><strong>Links:</strong> JoinCapitalizedWords; url (http, https, ftp, gopher, mailto, news)</small>" }

# save page function save(page, text, comment, filename, dtext, date) { dtext = decode(text); if ( localconf["always_convert_spaces"] || query["convertspaces"] == "on") gsub(/ /, "\t", dtext); print dtext > filename if (localconf["rcs"]) { localconf["date_cmd"] | getline date system("ci -q -t-"page" -l -m'"ENVIRON["REMOTE_ADDR"] ";;" date ";;"comment"' " filename) } print "saved <a href=\""scriptname"/"page"\">"page"</a>" }

# list all pages function special_index(datadir) { system("ls -1 " datadir " | " localconf["special_parser"] " -v special_index=yes")

}

# list pages with last modified time (sorted by date) function special_changes(datadir, date) { localconf["date_cmd"] | getline date print "<p>current date:", date "<p>" system("ls -tlL "datadir" | " localconf["special_parser"] " -v special_changes=" localconf["show_changes"]) }

function special_search(name,datadir) { system("grep -il '"name"' "datadir"* | " localconf["special_parser"] " -v special_search=yes") }

function special_history(name, filename) { print "<p>last changes on <a href=\""scriptname"/" name "\">"name"</a><p>" system("rlog " filename " | " localconf["special_parser"] " -v special_history="name)

print "<p>Show diff between:" print "<form action=\""scriptname"/\" method=\"GET\">" print "<input type=\"hidden\" name=\"page\" value=\""name"\">" print "<input type=\"hidden\" name=\"diff\" value=\"true\">" print "<input type=\"text\" name=\"revision\" size=5>" print "<input type=\"text\" name=\"revision2\" size=5>" print "<input type=\"submit\" value=\"diff\">" print "</form></p>" }

# remove '"` characters from string # *** !Important for Security! *** function clear_str(str) { gsub(/['`"]/, "", str) if (length(str) > 80) return substr(str, 1, 80) else return str }

# retrun the pagename # *** !Important for Security! *** function clear_pagename(str) { if (match(str, /[A-Z][a-z]+[A-Z][A-Za-z]*/)) return substr(str, RSTART, RLENGTH) else return "" }

# return revision numbers # *** !Important for Security! *** function clear_revision(str) { if (match(str, /[1-9]\.[0-9]+/)) return substr(str, RSTART, RLENGTH) else return "" }

# decode urlencoded string function decode(text, hex, i, hextab, decoded, len, c, c1, c2, code) {

split("0 1 2 3 4 5 6 7 8 9 a b c d e f", hex, " ") for (i=0; i<16; i++) hextab[hex[i+1]] = i

# urldecode function from Heiner Steven # http://www.shelldorado.com/scripts/cmds/urldecode

# decode %xx to ASCII char decoded = "" i = 1 len = length(text)

while ( i <= len ) { c = substr (text, i, 1) if ( c == "%" ) { if ( i+2 <= len ) { c1 = tolower(substr(text, i+1, 1)) c2 = tolower(substr(text, i+2, 1)) if ( hextab [c1] != "" || hextab [c2] != "" ) { if ( (c1 >= 2 && c1 != 7) || (c1 == 7 && c2 != "f") || (c1 == 0 && c2 ~ "[9acd]") ){ code = 0 + hextab [c1] * 16 + hextab [c2] + 0 c = sprintf ("%c", code) } else { c = " " } i = i + 2 } } } else if ( c == "+" ) { # special handling: "+" means " " c = " " } decoded = decoded c ++i }

# change linebreaks to \n gsub(/\r\n/, "\n", decoded)

# remove last linebreak sub(/[\n\r]*$/,"",decoded)

return decoded }

#load configfile function load_config(script, configfile,key,value) { configfile = script #remove trailing / ('/awki/awki.cgi/' -> '/awki/awki.cgi') sub(/\/$/, "", configfile) #remove path ('/awki/awki.cgi' -> 'awki.cgi') sub(/^.*\//, "", configfile) #remove suffix ('awki.cgi' -> 'awki') sub(/\.[^.]*$/,"", configfile) # append .conf suffix configfile = configfile ".conf"

#read configfile while((getline < configfile) >0) { if ($0 ~ /^#/) continue #ignore comments

if (match($0,/[ \t]*=[ \t]*/)) { key = substr($0, 1, RSTART-1) sub(/^[ \t]*/, "", key) value = substr($0, RSTART+RLENGTH) sub(/[ \t]*$/, "", value) if (sub(/^"/, "", value)) sub(/"$/, "", value) #set localconf variables localconf[key] = value

} } }


2. awki.conf - setting options for your server and wiki

	################################################################################
	# awki.conf - example configfile for awkiawki
	# $Id: awki.conf,v 1.2 2003/06/19 10:32:49 olt Exp $
	################################################################################
	# Copyright (c) 2002 Oliver Tonnhofer (olt@bogosoft.com)
	# See the file `COPYING' for copyright notice.
	################################################################################

## The first option contains the default value. ## Surrounding doubble-quotes are optional.

## default_page: ## Name of the default_page. # default_page = "FrontPage" # default_page = "AwkiAwki"

## img_tag: ## HTML img tag for picture in page header. img_tag = <img src="/brain.png" width="121" height="139" align="left">

## datadir: ## Directory for raw pagedata (must be writeable for the script). datadir = "./data/"

## css: ## HTTP URL for external CSS file css = "/main.css" # css = "http://mysite.domain/mystylesheet.css"

## rcs: ## If true, RCS is used for revisioning. ## This will enable PageHistory! ## HINT: Add a RCS directory in your datadir to save the ## RCS Files in a separate directory. # rcs = 0 rcs = "true"

## path: ## add path to PATH environment ## (path is added to the left side of $PATH) #path = "" #path = "/sw/bin:/usr/local"

## show_changes: ## Number of changes listed by RecentChanges. # show_changes = 10 show_changes = 25

## write_protection: ## Regex for write protected files. ## e.g.: "*", "PageOne?|PageTwo?|^.*NonEditable?" ## HINT: To edit these protected pages, upload a .htaccess ## protected awki.cgi script with write_protection = "" # write_protection = "" # write_protection = ^AwkiAwki$|ReadOnly?$

## always_convert_spaces: ## If true, convert runs of 8 spaces to tab automatical. # always_convert_spaces = 0

## date_cmd: ## Command for current date. date_cmd = "date '+%e %b. %G %R:%S %Z'"

## parser: ## Parsing script. parser = "./parser.awk"

## special_parser: ## Parser for special_* functions. special_parser = "./special_parser.awk"

## max_post: ## Bytes accepted by POST requests (to avoid DOS). max_post = 500000


3. parser.awk - parsing pages you've just created

	#!/usr/bin/awk -f
	################################################################################
	# parser.awk - parsing script for awkiawki
	# $Id: parser.awk,v 1.6 2002/12/07 13:46:45 olt Exp $
	################################################################################
	# Copyright (c) 2002 Oliver Tonnhofer (olt@bogosoft.com)
	# See the file `COPYING' for copyright notice.
	################################################################################

BEGIN { list["ol"] = 0 list["ul"] = 0 scriptname = ENVIRON["SCRIPT_NAME"] FS = "[ ]"

cmd = "ls " datadir while ((cmd | getline ls_out) >0) if (match(ls_out, /[A-Z][a-z]+[A-Z][A-Za-z]*/) && substr(ls_out, RSTART + RLENGTH) !~ /,v/) { page = substr(ls_out, RSTART, RLENGTH) pages[page] = 1 } close(cmd) }

# register blanklines /^$/ { blankline = 1; next; }

# HTML entities for <, > and & /[&<>]/ { gsub(/&/, "\\&amp;"); gsub(/</, "\\&lt;"); gsub(/>/, "\\&gt;"); }

# generate links /[A-Z][a-z]+[A-Z][A-Za-z]*/ || /(https?|ftp|gopher|mailto|news):/ { tmpline = "" for(i=1;i<=NF;i++) { field = $i # generate HTML img tag for .jpg,.jpeg,.gif,png URLs if (field ~ /https?:\/\/[^\t]*\.(jpg|jpeg|gif|png)/ && field !~ /https?:\/\/[^\t]*\.(jpg|jpeg|gif|png)/) { sub(/https?:\/\/[^\t]*\.(jpg|jpeg|gif|png)/, "<img src=\"&\">",field) # links for mailto, news and http, ftp and gopher URLs }else if (field ~ /((https?|ftp|gopher):\/\/|(mailto|news):)[^\t]*/) { sub(/((https?|ftp|gopher):\/\/|(mailto|news):)[^\t]*[^.,?;:'")\t]/, "<a href=\"&\">&</a>",field) # remove mailto: in link description sub(/>mailto:/, ">",field) # links for awkipages }else if (field ~ /(^|[[,.?;:'"\(\t])[A-Z][a-z]+[A-Z][A-Za-z]*/ && field !~ //) { match(field, /[A-Z][a-z]+[A-Z][A-Za-z]*/) tmp_pagename = substr(field, RSTART, RLENGTH) if (pages[tmp_pagename]) sub(/[A-Z][a-z]+[A-Z][A-Za-z]*/, "<a href=\""scriptname"/&\">&</a>",field) else sub(/[A-Z][a-z]+[A-Z][A-Za-z]*/, "&<a href=\""scriptname"/&\">?</a>",field) } tmpline = tmpline field OFS } # return tmpline to $0 and remove last OFS (whitespace) $0 = substr(tmpline, 1, length(tmpline)-1) }

# remove six single quotes (WikiLinks) { gsub(//,""); }

# emphasize text in single-quotes // { gsub(/('?'?[^'])*/, "<strong>&</strong>"); gsub(//,""); } // { gsub(/('?[^'])*/, "<em>&</em>"); gsub(//,""); }

#headings /^-[^-]/ { $0 = "<h2>" substr($0, 2) "</h2>"; close_tags(); print; next; } /^--[^-]/ { $0 = "<h3>" substr($0, 3) "</h3>"; close_tags(); print; next; } /^---[^-]/ { $0 = "<h4>" substr($0, 4) "</h4>"; close_tags(); print; next; }

# horizontal line /^----/ { sub(/^----+/, "<hr>"); blankline = 1; close_tags(); print; next; }

/^\t+[*]/ { close_tags("list"); parse_list("ul", "ol"); print; next;} /^\t+[1]/ { close_tags("list"); parse_list("ol", "ul"); print; next;}

/^ / { close_tags("pre"); if (pre != 1) { print "<pre>\n" $0; pre = 1 blankline = 0 } else { if (blankline==1) { print ""; blankline = 0 } print; } next; }

NR == 1 { print "<p>"; } { close_tags();

# print paragraph when blankline registered if (blankline==1) { print "<p>"; blankline=0; }

#print line print;

}

END { $0 = "" close_tags(); }

function close_tags(not) {

# if list is parsed this line print it if (not !~ "list") { if (list["ol"] > 0) { parse_list("ol", "ul") } else if (list["ul"] > 0) { parse_list("ul", "ol") } } # close monospace if (not !~ "pre") { if (pre == 1) { print "</pre>" pre = 0 } }

} function parse_list(this, other) {

thislist = list[this] otherlist = list[other] tabcount = 0

while(/^\t+[1*]/) { sub(/^\t/,"") tabcount++ }

# close foreign tags if (otherlist > 0) { while(otherlist-- > 0) { print "</" other ">" } }

# if we are needing more tags we open new if (thislist < tabcount) { while(thislist++ < tabcount) { print "<" this ">" } # if we are needing less tags we close some } else if (thislist > tabcount) { while(thislist-- != tabcount) { print "</" this ">" } }

if (tabcount) { sub(/^[1*]/,"") $0 = "\t<li>" $0 }

list[other] = 0 list[this] = tabcount

}


4. special_parser.awk - parsing diffs if you enabled rcs

	#!/usr/bin/mawk -f
	################################################################################
	# special_parser.awk - parsing script for awkiawki
	# $Id: special_parser.awk,v 1.5 2003/07/07 11:22:55 olt Exp $
	################################################################################
	# Copyright (c) 2002 Oliver Tonnhofer (olt@bogosoft.com)
	# See the file `COPYING' for copyright notice.
	################################################################################

BEGIN { scriptname = ENVIRON["SCRIPT_NAME"] if (special_changes) print "<table>" if (special_history) { # use the power of awk to split the information of rlog RS = "----------------------------\n" FS = "\n" print "<table>\n<tr><th>version</th><th>date</th><th>ip</th><th>comment</th>" print "<th>view version</th><th>edit version</th><th>diff to current</th></tr>" } if (special_diff) print "<pre>" }

special_changes && $9 ~ /^[A-Z][a-z]+[A-Z][A-Za-z]*$/ { filenr++ print "<tr><td>" generate_link($9) "</td><td>"$7" "$6" "$8"</td></tr>" if (filenr == special_changes) exit }

special_index && /^[A-Z][a-z]+[A-Z][A-Za-z]*$/ { print generate_link($0) "<br>" }

special_search && /[A-Z][a-z]+[A-Z][A-Za-z]*$/ { sub(/^.*[^\/]\//, "") print generate_link($0) "<br>" }

special_history && NR > 1 { #pick revision number match($1, /[1-9]\.[0-9]+/) revision = substr($1, RSTART, RLENGTH)

#split the double-semicolon separated information line split($3, sp_array, ";;") ip_address = sp_array[1] date = sp_array[2] comment = sp_array[3]

if (NR == 2) revision = "current"

print "<tr align=center><td>"revision"</td><td>"date"</td><td>"ip_address"</td><td>"comment"</td>" print "<td><a href=\""scriptname"/"special_history if (NR > 2) print "?revision="revision print "\">view</a></td>" print "<td><a href=\""scriptname"/?edit=true&amp;" if (NR >2) print "revision="revision"&amp;" print "page="special_history"\">edit</a></td>" if (NR >2) print "<td><a href=\""scriptname"/?diff=true&amp;page="special_history"&amp;revision="revision"\">diff</a></td>" print "</tr>"

}

special_diff && (NR >2) { if (/^\+/) print "<span class=\"new\">"$0"</span>" else if (/^\-/) print "<span class=\"old\">"$0"</span>" else print $0

}

END { if (special_changes || special_history) print "</table>" if (special_diff) print "</pre>" }

function generate_link(string) { sub(/[A-Z][a-z]+[A-Z][A-Za-z]*/, "<a href=\""scriptname"/&\">&</a>", string) return(string) }

EditText of this page (last edited August 12, 2013) or FindPage with title or text search