URL encoding

BTLE.cpp

@@ -1,5 +1,6 @@
 /*
  * Copyright (C) 2013 Florian Echtler <floe@butterbrot.org>
+ * Eddystone part Copyright (c) 2018 Pavel Brychta <pablo@xpablo.cz>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -19,6 +20,36 @@ const uint8_t frequency[3] = { 2,26,80};  // physical frequency (2400+x MHz)
 #define month(m) month_lookup[ (( ((( (m[0] % 24) * 13) + m[1]) % 24) * 13) + m[2]) % 24 ]
 const uint8_t month_lookup[24] = { 0,6,0,4,0,1,0,17,0,8,0,0,3,0,0,0,18,2,16,5,9,0,1,7 };
 
+const char PR0[] PROGMEM = "http://www.";
+const char PR1[] PROGMEM = "https://www.";
+const char PR2[] PROGMEM = "http://";
+const char PR3[] PROGMEM = "https://";
+const char * const prefixes[] PROGMEM = {
+  PR0, PR1, PR2, PR3,
+};
+#define NUM_PREFIXES (sizeof(prefixes) / sizeof(char *))
+
+const char SU0[] PROGMEM = ".com/";
+const char SU1[] PROGMEM = ".org/";
+const char SU2[] PROGMEM = ".edu/";
+const char SU3[] PROGMEM = ".net/";
+const char SU4[] PROGMEM = ".info/";
+const char SU5[] PROGMEM = ".biz/";
+const char SU6[] PROGMEM = ".gov/";
+const char SU7[] PROGMEM = ".com";
+const char SU8[] PROGMEM = ".org";
+const char SU9[] PROGMEM = ".edu";
+const char SU10[] PROGMEM = ".net";
+const char SU11[] PROGMEM = ".info";
+const char SU12[] PROGMEM = ".biz";
+const char SU13[] PROGMEM = ".gov";
+
+const char * const suffixes[] PROGMEM = {
+  SU0, SU1, SU2, SU3, SU4, SU5, SU6, SU7, SU8, SU9, SU10, SU11, SU12, SU13,
+};
+#define NUM_SUFFIXES (sizeof(suffixes) / sizeof(char *))
+
+#define MAX_URL_DATA 18
 
 // change buffer contents to "wire bit order"
 void BTLE::swapbuf( uint8_t len ) {
@@ -254,3 +285,52 @@ void BTLE::crc( uint8_t len, uint8_t* dst ) {
 		}
 	}
 }
+
+uint8_t BTLE::encodeURL(uint8_t* encodedUrl, const char *rawUrl)
+{
+  uint8_t urlDataLength = 0;
+
+  /*
+   * Fill with one more 0 than max url data size to ensure its null terminated
+   * And can be printed out for debug purposes
+   */
+  memset(encodedUrl, 0, MAX_URL_DATA + 1);
+
+  if ((rawUrl == NULL) || (strlen(rawUrl) == 0)) {
+    return urlDataLength;
+  }
+
+  /*
+   * handle prefix
+   */
+  for (size_t i = 0; i < NUM_PREFIXES; i++) {
+    size_t prefixLen = strlen_P((char *)pgm_read_word(&prefixes[i]));
+        if (strncmp_P(rawUrl, (char *)pgm_read_word(&prefixes[i]), prefixLen) == 0) {
+            encodedUrl[urlDataLength++]  = i;
+            rawUrl                      += prefixLen;
+            break;
+        }
+    }
+
+    /*
+     * handle suffixes
+     */
+    while (*rawUrl && (urlDataLength <= MAX_URL_DATA)) {
+        /* check for suffix match */
+        size_t i;
+        for (i = 0; i < NUM_SUFFIXES; i++) {
+            size_t suffixLen = strlen_P((char *)pgm_read_word(&suffixes[i]));
+            if (strncmp_P(rawUrl, (char *)pgm_read_word(&suffixes[i]), suffixLen) == 0) {
+                encodedUrl[urlDataLength++]  = i;
+                rawUrl                      += suffixLen;
+                break; /* from the for loop for checking against suffixes */
+            }
+        }
+        /* This is the default case where we've got an ordinary character which doesn't match a suffix. */
+        if (i == NUM_SUFFIXES) {
+            encodedUrl[urlDataLength++] = *rawUrl;
+            ++rawUrl;
+        }
+    }
+    return urlDataLength;
+}