9fans - fans of the OS Plan 9 from Bell Labs
 help / color / mirror / Atom feed
From: "matt" <matt@proweb.co.uk>
To: <9fans@cse.psu.edu>
Subject: [9fans] URL Encode/Decode Verb
Date: Sun,  4 Aug 2002 23:36:32 +0100	[thread overview]
Message-ID: <002c01c23c07$62ef4200$6501a8c0@KIKE> (raw)

Hi,

I've spent plenty of today sidetracked by this so I hope someone uses it :)

It's a verb for printing char* data as a URL encoded string.

It also does URL decoding

I must admit I've been having a bit of trouble with UTF (I think) as what
Windows types into drawterm seems different from the decoded strings. If
someone can offer some help there I'd appreciate it. That aside, well
behaved input produces well behaved output.

Because there is some UTF in the examples I don't trust the copy and paste
to work but it's only in the examples.
I've put the files on the web too.
http://www.proweb.co.uk/~matt/plan9/url_encode.c
or
http://www.proweb.co.uk/~matt/plan9/url_encode.c.gz

I'm quite impressed I'm picking up this c stuff fairly easily.
I've got some user level file servers in development as well.

Whoever thought of user defined verbs was inspired. Well done to them.

Comments suggestions welcome. As always.

Is the static int url_trans_flag array the best way to do this btw. ?

M

#include <u.h>
#include <libc.h>
#include <ctype.h>

int url_encode(Fmt *fmt) {
 int cnt;
 uchar c, e;
 char *str_start;
 char *str_index;

 static int url_trans_flag[] = { [32] 0, [33] 0, [34] 0, [35] 0, [36] 0,
[37] 0, [38] 0, [39] 0, [40] 0, [41] 0, [42] 0, [43] 0, [44] 0, [45] '-',
[46] '.', [47] 0, [48] '0', [49] '1', [50] '2', [51] '3', [52] '4', [53]
'5', [54] '6', [55] '7', [56] '8', [57] '9', [58] 0, [59] 0, [60] 0, [61] 0,
[62] 0, [63] 0, [64] 0, [65] 'A', [66] 'B', [67] 'C', [68] 'D', [69] 'E',
[70] 'F', [71] 'G', [72] 'H', [73] 'I', [74] 'J', [75] 'K', [76] 'L', [77]
'M', [78] 'N', [79] 'O', [80] 'P', [81] 'Q', [82] 'R', [83] 'S', [84] 'T',
[85] 'U', [86] 'V', [87] 'W', [88] 'X', [89] 'Y', [90] 'Z', [91] 0, [92] 0,
[93] 0, [94] 0, [95] '_', [96] 0, [97] 'a', [98] 'b', [99] 'c', [100] 'd',
[101] 'e', [102] 'f', [103] 'g', [104] 'h', [105] 'i', [106] 'j', [107] 'k',
[108] 'l', [109] 'm', [110] 'n', [111] 'o', [112] 'p', [113] 'q', [114] 'r',
[115] 's', [116] 't', [117] 'u', [118] 'v', [119] 'w', [120] 'x', [121] 'y',
[122] 'z', [123] 0, [124] 0, [125] 0, [126] 0, [127] 0 };

 str_start = str_index= smprint("%s", va_arg(fmt->args, char *));
 if (fmt->flags & FmtSign)
  url_trans_flag[32] = '+';
 else
  url_trans_flag[32] = 0;

 cnt = 0;
 while(c = *(str_index++)) {
  if (c > 127 || c < 32) {
   cnt += fmtprint(fmt, "%%%02x", c);
   continue;
  }

  e = url_trans_flag[c];
  if(e)
   cnt += fmtprint(fmt, "%c", e);
  else
   cnt += fmtprint(fmt, "%%%02x", c);
 }
 free(str_start);
 return cnt;
}

int
url_decode(Fmt *fmt) {
 char *str_arg;
 char *str_start;
 char * token;
 int token_index;
 int str_length;
 int ante_token_length;
 int c, cnt, t;
 Rune r;


 str_start = str_arg = smprint("%s", va_arg(fmt->args, char *));
 for (token = str_arg ; *token; token++) if (*(token) == '+') *token = ' ';

 cnt = 0;
 while(token =  strchr(str_arg, '%')) {
  str_length = strlen(str_arg);
  token_index = str_length - strlen(token);
  ante_token_length = str_length - token_index - 1;

  if (token_index) {
   str_arg[token_index] = 0;
   cnt += fmtprint(fmt, "%s", str_arg);
  }

  if (ante_token_length < 1) {
   str_arg = token +1;
   continue;
  }

  if(token[1] == '%') {
   cnt += fmtprint(fmt, "%%");
   str_arg = &token[2];
   continue;
  }

  if ((ante_token_length > 1) && isxdigit(token[1]) && isxdigit(token[2]) )
{
   t = token[3];
   token[3] = 0;
   r = strtol(&token[1], nil, 16);
   cnt += fmtprint(fmt, "%C",r);
   token[3] = t;
   str_arg = &token[3];
   continue;
  }

  // if we get here the string is malformed, I'll silently drop it
  str_arg++;
 }
 if(*str_arg)
  cnt += fmtprint(fmt, "%s", str_arg);
 free(str_start);
 return cnt;

}


int
url_encoding(Fmt *fmt) {
 if(fmt->flags & FmtLeft)
  return url_decode(fmt);
 else
  return url_encode(fmt);
}






/*

here's an example

8c url_encode.c && 8l url_encode.8 && mv 8.out url_encode && ./url_encode

output is :

fancy : caf€ bl€nc
+enc : caf%e9+bl%e1nc
%20 enc : caf%e9%20bl%e1nc
plain : café blánc
oh_no : %c3%b3h%20n%c3%b3
óh nó

*/


void
main (void) {
 char *fancy_string = "cafe blanc";
 char *prev_estring = "caf%E9%20bl%E1nc";
 char *plus_enc_string;
 char *p20_enc_string;
 char *plain_string;

 fancy_string[3] = 0xE9;
 fancy_string[7] = 0xE1;

 fmtinstall('R', url_encoding);

 plus_enc_string = smprint("%+R", fancy_string);
 p20_enc_string = smprint("%R", fancy_string);
 plain_string = smprint("%-R", prev_estring);

 print("fancy : %s\n+enc : %s\n%%20 enc : %s\nplain : %s\n", fancy_string,
plus_enc_string, p20_enc_string, plain_string);


 print("oh_no : %R\n%-R\n", "óh nó", "%c3%b3h%20n%c3%b3");


 exits(0);
}



             reply	other threads:[~2002-08-04 22:36 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2002-08-04 22:36 matt [this message]
2002-08-19 15:36 ` Boyd Roberts
2002-08-19 16:35   ` matt

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='002c01c23c07$62ef4200$6501a8c0@KIKE' \
    --to=matt@proweb.co.uk \
    --cc=9fans@cse.psu.edu \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).