* rewrite GSM 7bit default encoding/decoding based on a lookup table as the previous code produced wrong encodings for certain characters.

3 files changed, 123 insertions, 21 deletions

diff --git a/include/osmocore/gsm_utils.h b/include/osmocore/gsm_utils.h
index 7dc2388b..64f9edc1 100644
--- a/include/osmocore/gsm_utils.h
+++ b/include/osmocore/gsm_utils.h
@@ -3,6 +3,7 @@
  * (C) 2008 by Daniel Willmann <daniel@totalueberwachung.de>
  * (C) 2009 by Holger Hans Peter Freyther <zecke@selfish.org>
  * (C) 2009-2010 by Harald Welte <laforge@gnumonks.org>
+ * (C) 2010 by Nico Golde <nico@ngolde.de>
  *
  * All Rights Reserved
  *
@@ -53,6 +54,33 @@ enum gsm_band {
 	GSM_BAND_810	= 0x80,
 };
 
+/* ETSI GSM 03.38 6.2.1 and 6.2.1.1 default alphabet
+ * Greek symbols at hex positions 0x10 and 0x12-0x1a
+ * left out as they can't be handled with a char and
+ * since most phones don't display or write these
+ * characters this would only needlessly make the code
+ * more complex
+*/
+unsigned char gsm_7bit_alphabet[] = {
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x0a, 0xff, 0xff, 0x0d, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0x20, 0x21, 0x22, 0x23, 0x02, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2a, 0x2b, 0x2c,
+	0x2d, 0x2e, 0x2f, 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x3a, 0x3b,
+	0x3c, 0x3d, 0x3e, 0x3f, 0x00, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4a,
+	0x4b, 0x4c, 0x4d, 0x4e, 0x4f, 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59,
+	0x5a, 0x3c, 0x2f, 0x3e, 0x14, 0x11, 0xff, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68,
+	0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
+	0x78, 0x79, 0x7a, 0x28, 0x40, 0x29, 0x3d, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0x0c, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x5e, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x40, 0xff, 0x01, 0xff,
+	0x03, 0xff, 0x7b, 0x7d, 0xff, 0xff, 0xff, 0xff, 0xff, 0x5c, 0xff, 0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x5b, 0x7e, 0x5d, 0xff, 0x7c, 0xff, 0xff, 0xff,
+	0xff, 0x5b, 0x0e, 0x1c, 0x09, 0xff, 0x1f, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x5d,
+	0xff, 0xff, 0xff, 0xff, 0x5c, 0xff, 0x0b, 0xff, 0xff, 0xff, 0x5e, 0xff, 0xff, 0x1e, 0x7f,
+	0xff, 0xff, 0xff, 0x7b, 0x0f, 0x1d, 0xff, 0x04, 0x05, 0xff, 0xff, 0x07, 0xff, 0xff, 0xff,
+	0xff, 0x7d, 0x08, 0xff, 0xff, 0xff, 0x7c, 0xff, 0x0c, 0x06, 0xff, 0xff, 0x7e, 0xff, 0xff
+};
+
 const char *gsm_band_name(enum gsm_band band);
 enum gsm_band gsm_band_parse(const char *mhz);
 
diff --git a/src/gsm_utils.c b/src/gsm_utils.c
index dc97ceff..fb69377f 100644
--- a/src/gsm_utils.c
+++ b/src/gsm_utils.c
@@ -2,6 +2,7 @@
  * (C) 2008 by Daniel Willmann <daniel@totalueberwachung.de>
  * (C) 2009 by Holger Hans Peter Freyther <zecke@selfish.org>
  * (C) 2009-2010 by Harald Welte <laforge@gnumonks.org>
+ * (C) 2010 by Nico Golde <nico@ngolde.de>
  *
  * All Rights Reserved
  *
@@ -34,52 +35,110 @@
 
 #include "../config.h"
 
-/* GSM 03.38 6.2.1 Charachter packing */
+/* GSM 03.38 6.2.1 Character lookup for decoding */
+static int gsm_septet_lookup(uint8_t ch)
+{
+	int i = 0;
+	for(; i < sizeof(gsm_7bit_alphabet); i++){
+		if(gsm_7bit_alphabet[i] == ch)
+			return i;
+	}
+	return -1;
+}
+
+/* GSM 03.38 6.2.1 Character unpacking */
 int gsm_7bit_decode(char *text, const uint8_t *user_data, uint8_t length)
 {
 	int i = 0;
 	int l = 0;
+	uint8_t *rtext = calloc(length, sizeof(uint8_t));
+	uint8_t tmp;
 
-        /* FIXME: We need to account for user data headers here */
+	/* FIXME: We need to account for user data headers here */
 	i += l;
-	for (; i < length; i ++)
-		*(text ++) =
+	for (; i < length; i ++){
+		rtext[i] =
 			((user_data[(i * 7 + 7) >> 3] <<
 			  (7 - ((i * 7 + 7) & 7))) |
 			 (user_data[(i * 7) >> 3] >>
 			  ((i * 7) & 7))) & 0x7f;
+	}
+	for(i = 0; i < length; i++){
+		/* this is an extension character */
+		if(rtext[i] == 0x1b){
+			tmp = rtext[i+1];
+			*(text++) = gsm_7bit_alphabet[0x7f + tmp];
+			i++;
+			continue;
+		}
+
+		*(text++) = gsm_septet_lookup(rtext[i]);
+	}
+
 	*text = '\0';
+	free(rtext);
 
-	return i - l;
+	return i;
 }
 
+/* GSM 03.38 6.2.1 Prepare character packing */
+static int gsm_septet_encode(uint8_t *result, const char *data)
+{
+	int i, y = 0;
+	uint8_t ch;
+	for(i = 0; i < strlen(data); i++){
+		ch = data[i];
+		switch(ch){
+		/* fall-through for extension characters */
+		case 0x0c:
+		case 0x5e:
+		case 0x7b:
+		case 0x7d:
+		case 0x5c:
+		case 0x5b:
+		case 0x7e:
+		case 0x5d:
+		case 0x7c:
+			result[y++] = 0x1b;
+		default:
+			result[y] = gsm_7bit_alphabet[ch];
+			break;
+		}
+		y++;
+	}
 
-/* GSM 03.38 6.2.1 Charachter packing */
+	return y;
+}
+
+/* GSM 03.38 6.2.1 Character packing */
 int gsm_7bit_encode(uint8_t *result, const char *data)
 {
-	int i,j = 0;
-	unsigned char ch1, ch2;
+	int i,y,z = 0;
+	/* prepare for the worst case, every character expanding to two bytes */
+	uint8_t *rdata = calloc(strlen(data) * 2, sizeof(uint8_t));
+	uint8_t cb, nb;
 	int shift = 0;
 
-	for ( i=0; i<strlen(data); i++ ) {
+	y = gsm_septet_encode(rdata, data);
 
-		ch1 = data[i] & 0x7F;
-		ch1 = ch1 >> shift;
-		ch2 = data[(i+1)] & 0x7F;
-		ch2 = ch2 << (7-shift);
+	for(i = 0; i < y; i++) {
+		if(shift == 7 && i + 1 < y){
+			shift = 0;
+			continue;
+		}
 
-		ch1 = ch1 | ch2;
+		cb = (rdata[i] & 0x7f) >> shift;
+		if(i + 1 < y){
+			nb = (rdata[i + 1] & 0x7f) << (7 - shift);
+			cb = cb | nb;
+		}
 
-		result[j++] = ch1;
+		result[z++] = cb;
 
 		shift++;
-
-		if ((shift == 7) && (i+1<strlen(data))) {
-			shift = 0;
-			i++;
-		}
 	}
 
+	free(rdata);
 	return i;
 }
 
diff --git a/tests/sms/sms_test.c b/tests/sms/sms_test.c
index f5183d54..4daf003a 100644
--- a/tests/sms/sms_test.c
+++ b/tests/sms/sms_test.c
@@ -1,5 +1,6 @@
 /*
  * (C) 2008 by Daniel Willmann <daniel@totalueberwachung.de>
+ * (C) 2010 by Nico Golde <nico@ngolde.de>
  * All Rights Reserved
  *
  * This program is free software; you can redistribute it and/or modify
@@ -32,7 +33,7 @@ int main(int argc, char** argv)
 	uint8_t *sms;
 	uint8_t i;
 
-        /* test 7-bit coding/decoding */
+	/* test 7-bit coding/decoding */
 	const char *input = "test text";
 	uint8_t length;
 	uint8_t coded[256];
@@ -43,5 +44,19 @@ int main(int argc, char** argv)
 	if (strcmp(result, input) != 0) {
 		printf("7 Bit coding failed... life sucks\n");
 		printf("Wanted: '%s' got '%s'\n", input, result);
+		return -1;
 	}
+
+	memset(coded, 0, sizeof(coded));
+	memset(result, 0, sizeof(coded));
+	input = strdup("!$ a more#^- complicated test@@?_\%! case");
+	length = gsm_7bit_encode(coded, input);
+	gsm_7bit_decode(result, coded, length);
+	if (strcmp(result, input) != 0) {
+		printf("7 Bit coding failed... life sucks\n");
+		printf("Wanted: '%s' got '%s'\n", input, result);
+		return -2;
+	}
+
+	return 0;
 }