From cdee03748e83189713b32bb87bc77cde659c20d9 Mon Sep 17 00:00:00 2001
From: Christian Grothoff <christian@grothoff.org>
Date: Sun, 25 Dec 2011 21:16:11 +0000
Subject: -remove code for keyword caonicalization/normalization, makes no
 sense in international application, normalization methods are questionable to
 begin with

---
 src/fs/fs_uri.c | 123 --------------------------------------------------------
 1 file changed, 123 deletions(-)

(limited to 'src/fs/fs_uri.c')

diff --git a/src/fs/fs_uri.c b/src/fs/fs_uri.c
index 55503b71b..d3fcdd8ca 100644
--- a/src/fs/fs_uri.c
+++ b/src/fs/fs_uri.c
@@ -969,129 +969,6 @@ GNUNET_FS_uri_sks_create_from_nsid (GNUNET_HashCode * nsid, const char *id)
 }
 
 
-/**
- * Canonicalize a keyword.
- *
- * @param in input string (the keyword)
- * @return canonicalized keyword
- */
-static char *
-canonicalize_keyword (const char *in)
-{
-  char *ret;
-  char *wpos;
-  const char *rpos;
-
-  ret = GNUNET_strdup (in);
-  wpos = ret;
-  rpos = in;
-  while ('\0' != *rpos)
-  {
-    switch (tolower ((unsigned char) *rpos))
-    {
-    case 'a':
-    case 'e':
-    case 'i':
-    case 'o':
-    case 'u':
-    case ' ':
-    case '\t':
-    case '\n':
-    case '\r':
-      /* skip characters listed above */
-      break;
-    case 'b':
-    case 'c':
-    case 'd':
-    case 'f':
-    case 'g':
-    case 'h':
-    case 'j':
-    case 'k':
-    case 'l':
-    case 'm':
-    case 'n':
-    case 'p':
-    case 'r':
-    case 's':
-    case 't':
-    case 'v':
-    case 'w':
-    case 'x':
-    case 'y':
-    case 'z':
-      /* convert characters listed above to lower case */
-      *wpos = tolower ((unsigned char) *rpos);
-      wpos++;
-      break;
-    case '!':
-    case '.':
-    case '?':
-    case '-':
-      /* keep characters listed above without changes */
-      *wpos = *rpos;
-      wpos++;
-      break;
-    default:
-      if (isspace ((unsigned char) *rpos) || isdigit ((unsigned char) *rpos))
-        break;
-      /* replace characters listed above with '_' */
-      *wpos = '_';
-      wpos++;
-      break;
-    }
-    rpos++;
-  }
-  *wpos = '\0';
-  return ret;
-}
-
-
-/**
- * Canonicalize keyword URI.  Performs operations such
- * as decapitalization and removal of certain characters.
- * (useful for search).
- *
- * @param uri the URI to canonicalize
- * @return canonicalized version of the URI, NULL on error
- */
-struct GNUNET_FS_Uri *
-GNUNET_FS_uri_ksk_canonicalize (const struct GNUNET_FS_Uri *uri)
-{
-  struct GNUNET_FS_Uri *ret;
-  unsigned int kc;
-  unsigned int i;
-  const char *in;
-  char *sb;
-  char *cc;
-  const char *tok;
-
-  ret = GNUNET_malloc (sizeof (struct GNUNET_FS_Uri));
-  ret->type = ksk;
-  kc = uri->data.ksk.keywordCount;
-  for (i = 0; i < kc; i++)
-  {
-    in = uri->data.ksk.keywords[i];
-    GNUNET_FS_uri_ksk_add_keyword (ret, &in[1],
-                                   (in[0] == '+') ? GNUNET_YES : GNUNET_NO);
-    sb = GNUNET_strdup (&in[1]);
-#define DELIMS " \\|\"'`/&@-_,.;!?+-*^$#~=[]{}()<>"
-    for (tok = strtok (sb, DELIMS); NULL != tok; tok = strtok (NULL, DELIMS))
-#undef DELIMS
-    {
-      if (strlen (tok) < 3)
-        continue;
-      GNUNET_FS_uri_ksk_add_keyword (ret, tok, GNUNET_NO);
-      cc = canonicalize_keyword (tok);
-      if (strlen (cc) > 2)
-        GNUNET_FS_uri_ksk_add_keyword (ret, cc, GNUNET_NO);
-    }
-    GNUNET_free (sb);
-  }
-  return ret;
-}
-
-
 /**
  * Merge the sets of keywords from two KSK URIs.
  * (useful for merging the canonicalized keywords with
-- 
cgit v1.2.3