Files
Citadel-Station-13-RP/code/__HELPERS/text.dm
2021-09-21 14:01:46 -07:00

547 lines
18 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
/*
* Holds procs designed to help with filtering text
* Contains groups:
* SQL sanitization
* Text sanitization
* Text searches
* Text modification
* Misc
*/
/*
* SQL sanitization
*/
// Run all strings to be used in an SQL query through this proc first to properly escape out injection attempts.
/proc/sanitizeSQL(var/t as text)
var/sqltext = dbcon.Quote(t);
return copytext(sqltext, 2, length(sqltext));//Quote() adds quotes around input, we already do that
/*
* Text sanitization
*/
//Used for preprocessing entered text
/proc/sanitize(var/input, var/max_length = MAX_MESSAGE_LEN, var/encode = 1, var/trim = 1, var/extra = 1)
if(!input)
return
if(max_length)
input = copytext(input,1,max_length)
if(extra)
input = replace_characters(input, list("\n"=" ","\t"=" "))
if(encode)
// The below \ escapes have a space inserted to attempt to enable Travis auto-checking of span class usage. Please do not remove the space.
//In addition to processing html, html_encode removes byond formatting codes like "\ red", "\ i" and other.
//It is important to avoid double-encode text, it can "break" quotes and some other characters.
//Also, keep in mind that escaped characters don't work in the interface (window titles, lower left corner of the main window, etc.)
input = html_encode(input)
else
//If not need encode text, simply remove < and >
//note: we can also remove here byond formatting codes: 0xFF + next byte
input = replace_characters(input, list("<"=" ", ">"=" "))
if(trim)
//Maybe, we need trim text twice? Here and before copytext?
input = trim(input)
return input
///have to rewrite this sanitize code :djoy:
/proc/sanitize_filename(t)
return sanitize_simple_tg(t, list("\n"="", "\t"="", "/"="", "\\"="", "?"="", "%"="", "*"="", ":"="", "|"="", "\""="", "<"="", ">"=""))
//Removes a few problematic characters. Renamed because namespace
/proc/sanitize_simple_tg(t,list/repl_chars = list("\n"="#","\t"="#"))
for(var/char in repl_chars)
var/index = findtext(t, char)
while(index)
t = copytext(t, 1, index) + repl_chars[char] + copytext(t, index + length(char))
index = findtext(t, char, index + length(char))
return t
//Run sanitize(), but remove <, >, " first to prevent displaying them as &gt; &lt; &34; in some places, after html_encode().
//Best used for sanitize object names, window titles.
//If you have a problem with sanitize() in chat, when quotes and >, < are displayed as html entites -
//this is a problem of double-encode(when & becomes &amp;), use sanitize() with encode=0, but not the sanitizeSafe()!
/proc/sanitizeSafe(var/input, var/max_length = MAX_MESSAGE_LEN, var/encode = 1, var/trim = 1, var/extra = 1)
return sanitize(replace_characters(input, list(">"=" ","<"=" ", "\""="'")), max_length, encode, trim, extra)
//Filters out undesirable characters from names
/proc/sanitizeName(var/input, var/max_length = MAX_NAME_LEN)
if(!input || length(input) > max_length)
return //Rejects the input if it is null or if it is longer then the max length allowed
var/number_of_alphanumeric = 0
var/last_char_group = 0
var/output = ""
for(var/i=1, i<=length(input), i++)
var/ascii_char = text2ascii(input,i)
switch(ascii_char)
// A .. Z
if(65 to 90) //Uppercase Letters
output += ascii2text(ascii_char)
number_of_alphanumeric++
last_char_group = 4
// a .. z
if(97 to 122) //Lowercase Letters
if(last_char_group<2) output += ascii2text(ascii_char-32) //Force uppercase first character
else output += ascii2text(ascii_char)
number_of_alphanumeric++
last_char_group = 4
// 0 .. 9
if(48 to 57) //Numbers
if(!last_char_group) continue //suppress at start of string
output += ascii2text(ascii_char)
number_of_alphanumeric++
last_char_group = 3
// ' - .
if(39,45,46) //Common name punctuation
if(!last_char_group) continue
output += ascii2text(ascii_char)
last_char_group = 2
// ~ | @ : # $ % & * +
if(126,124,64,58,35,36,37,38,42,43) //Other symbols that we'll allow (mainly for AI)
if(!last_char_group) continue //suppress at start of string
output += ascii2text(ascii_char)
last_char_group = 2
//Space
if(32)
if(last_char_group <= 1) continue //suppress double-spaces and spaces at start of string
output += ascii2text(ascii_char)
last_char_group = 1
else
return
if(number_of_alphanumeric < 2) return //protects against tiny names like "A" and also names like "' ' ' ' ' ' ' '"
if(last_char_group == 1)
output = copytext(output,1,length(output)) //removes the last character (in this case a space)
for(var/bad_name in list("space","floor","wall","r-wall","monkey","unknown","inactive ai","plating")) //prevents these common metagamey names
if(cmptext(output,bad_name)) return //(not case sensitive)
return output
//Returns null if there is any bad text in the string
/proc/reject_bad_text(text, max_length = 512, ascii_only = TRUE)
var/char_count = 0
var/non_whitespace = FALSE
var/lenbytes = length(text)
var/char = ""
for(var/i = 1, i <= lenbytes, i += length(char))
char = text[i]
char_count++
if(char_count > max_length)
return
switch(text2ascii(char))
if(62,60,92,47) // <, >, \, /
return
if(0 to 31)
return
if(32)
continue //whitespace
if(127 to INFINITY)
if(ascii_only)
return
else
non_whitespace = TRUE
if(non_whitespace)
return text //only accepts the text if it has some non-spaces
// Used to get a properly sanitized input, of max_length
// no_trim is self explanatory but it prevents the input from being trimed if you intend to parse newlines or whitespace.
/proc/stripped_input(mob/user, message = "", title = "", default = "", max_length=MAX_MESSAGE_LEN, no_trim=FALSE)
var/name = input(user, message, title, default) as text|null
if(no_trim)
return copytext(html_encode(name), 1, max_length)
else
return trim(html_encode(name), max_length) //trim is "outside" because html_encode can expand single symbols into multiple symbols (such as turning < into &lt;)
// Used to get a properly sanitized multiline input, of max_length
/proc/stripped_multiline_input(mob/user, message = "", title = "", default = "", max_length=MAX_MESSAGE_LEN, no_trim=FALSE)
var/name = input(user, message, title, default) as message|null
if(isnull(name)) // Return null if canceled.
return null
if(no_trim)
return copytext(html_encode(name), 1, max_length)
else
return trim(html_encode(name), max_length)
//Old variant. Haven't dared to replace in some places.
/proc/sanitize_old(var/t,var/list/repl_chars = list("\n"="#","\t"="#"))
return html_encode(replace_characters(t,repl_chars))
/*
* Text searches
*/
//Checks the beginning of a string for a specified sub-string
//Returns the position of the substring or 0 if it was not found
/proc/dd_hasprefix(text, prefix)
var/start = 1
var/end = length(prefix) + 1
return findtext(text, prefix, start, end)
//Checks the beginning of a string for a specified sub-string. This proc is case sensitive
//Returns the position of the substring or 0 if it was not found
/proc/dd_hasprefix_case(text, prefix)
var/start = 1
var/end = length(prefix) + 1
return findtextEx(text, prefix, start, end)
//Checks the end of a string for a specified substring.
//Returns the position of the substring or 0 if it was not found
/proc/dd_hassuffix(text, suffix)
var/start = length(text) - length(suffix)
if(start)
return findtext(text, suffix, start, null)
return
//Checks the end of a string for a specified substring. This proc is case sensitive
//Returns the position of the substring or 0 if it was not found
/proc/dd_hassuffix_case(text, suffix)
var/start = length(text) - length(suffix)
if(start)
return findtextEx(text, suffix, start, null)
/*
* Text modification
*/
/proc/replace_characters(var/t,var/list/repl_chars)
for(var/char in repl_chars)
t = replacetext(t, char, repl_chars[char])
return t
//Adds 'u' number of zeros ahead of the text 't'
/proc/add_zero(t, u)
while (length(t) < u)
t = "0[t]"
return t
//Adds 'u' number of spaces ahead of the text 't'
/proc/add_lspace(t, u)
while(length(t) < u)
t = " [t]"
return t
//Adds 'u' number of spaces behind the text 't'
/proc/add_tspace(t, u)
while(length(t) < u)
t = "[t] "
return t
//Returns a string with reserved characters and spaces before the first letter removed
/proc/trim_left(text)
for (var/i = 1 to length(text))
if (text2ascii(text, i) > 32)
return copytext(text, i)
return ""
//Returns a string with reserved characters and spaces after the last letter removed
/proc/trim_right(text)
for (var/i = length(text), i > 0, i--)
if (text2ascii(text, i) > 32)
return copytext(text, 1, i + 1)
return ""
//Returns a string with reserved characters and spaces before the first word and after the last word removed.
/proc/trim(text)
return trim_left(trim_right(text))
//Returns a string with the first element of the string capitalized.
/proc/capitalize(var/t as text)
return uppertext(copytext(t, 1, 2)) + copytext(t, 2)
/proc/autocorrect(var/input as text) // syntax is "stringtoreplace"="stringtoreplacewith"
return input = replace_characters(input, list(
" i "=" I ",
"i'm"="I'm",
"s's"="s'",
"isnt"="isn't",
"dont"="don't",
"shouldnt"="shouldn't",
" ive "=" I've ",
"whove"="who've",
"whod"="whod",
"whats"="whats",
"whatd"="whatd",
"thats"="thats",
"thatll"="thatll",
"thatd"="thatd",
" nows "=" nows ",
"isnt"="isnt",
" arent "=" arent ",
"wasnt"="wasnt",
"werent"="werent",
"havent"="havent",
"hasnt"="hasnt",
"hadnt"="hadnt",
"doesnt"="doesnt",
"didnt"="didnt",
"couldnt"="couldnt",
"wouldnt"="wouldnt",
"mustnt"="mustnt",
"shouldnt"="shouldnt"
))
//This proc strips html properly, remove < > and all text between
//for complete text sanitizing should be used sanitize()
/proc/strip_html_properly(var/input)
if(!input)
return
var/opentag = 1 //These store the position of < and > respectively.
var/closetag = 1
while(1)
opentag = findtext(input, "<")
closetag = findtext(input, ">")
if(closetag && opentag)
if(closetag < opentag)
input = copytext(input, (closetag + 1))
else
input = copytext(input, 1, opentag) + copytext(input, (closetag + 1))
else if(closetag || opentag)
if(opentag)
input = copytext(input, 1, opentag)
else
input = copytext(input, (closetag + 1))
else
break
return input
//This proc fills in all spaces with the "replace" var (* by default) with whatever
//is in the other string at the same spot (assuming it is not a replace char).
//This is used for fingerprints
/proc/stringmerge(var/text,var/compare,replace = "*")
var/newtext = text
if(length(text) != length(compare))
return 0
for(var/i = 1, i < length(text), i++)
var/a = copytext(text,i,i+1)
var/b = copytext(compare,i,i+1)
//if it isn't both the same letter, or if they are both the replacement character
//(no way to know what it was supposed to be)
if(a != b)
if(a == replace) //if A is the replacement char
newtext = copytext(newtext,1,i) + b + copytext(newtext, i+1)
else if(b == replace) //if B is the replacement char
newtext = copytext(newtext,1,i) + a + copytext(newtext, i+1)
else //The lists disagree, Uh-oh!
return 0
return newtext
//This proc returns the number of chars of the string that is the character
//This is used for detective work to determine fingerprint completion.
/proc/stringpercent(var/text,character = "*")
if(!text || !character)
return 0
var/count = 0
for(var/i = 1, i <= length(text), i++)
var/a = copytext(text,i,i+1)
if(a == character)
count++
return count
/proc/reverse_text(var/text = "")
var/new_text = ""
for(var/i = length(text); i > 0; i--)
new_text += copytext(text, i, i+1)
return new_text
//Used in preferences' SetFlavorText and human's set_flavor verb
//Previews a string of len or less length
proc/TextPreview(var/string,var/len=40)
if(length(string) <= len)
if(!length(string))
return "\[...\]"
else
return string
else
return "[copytext_preserve_html(string, 1, 37)]..."
//alternative copytext() for encoded text, doesn't break html entities (&#34; and other)
/proc/copytext_preserve_html(var/text, var/first, var/last)
return html_encode(copytext(html_decode(text), first, last))
//For generating neat chat tag-images
//The icon var could be local in the proc, but it's a waste of resources
// to always create it and then throw it out.
GLOBAL_VAR_INIT(text_tag_icons, new /icon('./icons/chattags.dmi'))
/proc/create_text_tag(tagname, tagdesc = tagname, client/C)
if(!(C && C.is_preference_enabled(/datum/client_preference/chat_tags)))
return tagdesc
return icon2html(GLOB.text_tag_icons, C, tagname)
/proc/contains_az09(var/input)
for(var/i=1, i<=length(input), i++)
var/ascii_char = text2ascii(input,i)
switch(ascii_char)
// A .. Z
if(65 to 90) //Uppercase Letters
return 1
// a .. z
if(97 to 122) //Lowercase Letters
return 1
// 0 .. 9
if(48 to 57) //Numbers
return 1
return 0
/**
* Strip out the special beyond characters for \proper and \improper
* from text that will be sent to the browser.
*/
/proc/strip_improper(var/text)
return replacetext(replacetext(text, "\proper", ""), "\improper", "")
/proc/pencode2html(t)
t = replacetext(t, "\n", "<BR>")
t = replacetext(t, "\[center\]", "<center>")
t = replacetext(t, "\[/center\]", "</center>")
t = replacetext(t, "\[br\]", "<BR>")
t = replacetext(t, "\[b\]", "<B>")
t = replacetext(t, "\[/b\]", "</B>")
t = replacetext(t, "\[i\]", "<I>")
t = replacetext(t, "\[/i\]", "</I>")
t = replacetext(t, "\[u\]", "<U>")
t = replacetext(t, "\[/u\]", "</U>")
t = replacetext(t, "\[time\]", "[stationtime2text()]")
t = replacetext(t, "\[date\]", "[stationdate2text()]")
t = replacetext(t, "\[large\]", "<font size=\"4\">")
t = replacetext(t, "\[/large\]", "</font>")
t = replacetext(t, "\[field\]", "<span class=\"paper_field\"></span>")
t = replacetext(t, "\[h1\]", "<H1>")
t = replacetext(t, "\[/h1\]", "</H1>")
t = replacetext(t, "\[h2\]", "<H2>")
t = replacetext(t, "\[/h2\]", "</H2>")
t = replacetext(t, "\[h3\]", "<H3>")
t = replacetext(t, "\[/h3\]", "</H3>")
t = replacetext(t, "\[*\]", "<li>")
t = replacetext(t, "\[hr\]", "<HR>")
t = replacetext(t, "\[small\]", "<font size = \"1\">")
t = replacetext(t, "\[/small\]", "</font>")
t = replacetext(t, "\[list\]", "<ul>")
t = replacetext(t, "\[/list\]", "</ul>")
t = replacetext(t, "\[table\]", "<table border=1 cellspacing=0 cellpadding=3 style='border: 1px solid black;'>")
t = replacetext(t, "\[/table\]", "</td></tr></table>")
t = replacetext(t, "\[grid\]", "<table>")
t = replacetext(t, "\[/grid\]", "</td></tr></table>")
t = replacetext(t, "\[row\]", "</td><tr>")
t = replacetext(t, "\[cell\]", "<td>")
t = replacetext(t, "\[logo\]", "<img src = ntlogo.png>")
t = replacetext(t, "\[redlogo\]", "<img src = redntlogo.png>")
t = replacetext(t, "\[sglogo\]", "<img src = sglogo.png>")
t = replacetext(t, "\[editorbr\]", "")
return t
// Random password generator
/proc/GenerateKey()
//Feel free to move to Helpers.
var/newKey
newKey += pick("the", "if", "of", "as", "in", "a", "you", "from", "to", "an", "too", "little", "snow", "dead", "drunk", "rosebud", "duck", "al", "le")
newKey += pick("diamond", "beer", "mushroom", "assistant", "clown", "captain", "twinkie", "security", "nuke", "small", "big", "escape", "yellow", "gloves", "monkey", "engine", "nuclear", "ai")
newKey += pick("1", "2", "3", "4", "5", "6", "7", "8", "9", "0")
return newKey
//Used for applying byonds text macros to strings that are loaded at runtime
/proc/apply_text_macros(string)
var/next_backslash = findtext(string, "\\")
if(!next_backslash)
return string
var/leng = length(string)
var/next_space = findtext(string, " ", next_backslash + 1)
if(!next_space)
next_space = leng - next_backslash
if(!next_space) //trailing bs
return string
var/base = next_backslash == 1 ? "" : copytext(string, 1, next_backslash)
var/macro = lowertext(copytext(string, next_backslash + 1, next_space))
var/rest = next_backslash > leng ? "" : copytext(string, next_space + 1)
//See http://www.byond.com/docs/ref/info.html#/DM/text/macros
switch(macro)
//prefixes/agnostic
if("the")
rest = text("\the []", rest)
if("a")
rest = text("\a []", rest)
if("an")
rest = text("\an []", rest)
if("proper")
rest = text("\proper []", rest)
if("improper")
rest = text("\improper []", rest)
if("roman")
rest = text("\roman []", rest)
//postfixes
if("th")
base = text("[]\th", rest)
if("s")
base = text("[]\s", rest)
if("he")
base = text("[]\he", rest)
if("she")
base = text("[]\she", rest)
if("his")
base = text("[]\his", rest)
if("himself")
base = text("[]\himself", rest)
if("herself")
base = text("[]\herself", rest)
if("hers")
base = text("[]\hers", rest)
. = base
if(rest)
. += .(rest)
#define gender2text(gender) capitalize(gender)
GLOBAL_LIST_INIT(zero_character_only, list("0"))
GLOBAL_LIST_INIT(hex_characters, list("0","1","2","3","4","5","6","7","8","9","a","b","c","d","e","f"))
GLOBAL_LIST_INIT(alphabet, list("a","b","c","d","e","f","g","h","i","j","k","l","m","n","o","p","q","r","s","t","u","v","w","x","y","z"))
GLOBAL_LIST_INIT(binary, list("0","1"))
/proc/random_string(length, list/characters)
. = ""
for(var/i in 1 to length)
. += pick(characters)
/proc/repeat_string(times, string="")
. = ""
for(var/i in 1 to times)
. += string
/proc/random_short_color()
return random_string(3, GLOB.hex_characters)
/proc/random_color()
return random_string(6, GLOB.hex_characters)
//VR FILE MERGE
//Readds quotes and apostrophes to HTML-encoded strings
/proc/readd_quotes(var/t)
var/list/repl_chars = list("&#34;" = "\"","&#39;" = "'")
for(var/char in repl_chars)
var/index = findtext(t, char)
while(index)
t = copytext(t, 1, index) + repl_chars[char] + copytext(t, index+5)
index = findtext(t, char)
return t