Added g608 explanation document.

Signed-off-by: Anshul Maheshwari <er.anshul.maheshwari@gmail.com>

docs/CHANGES.TXT

@@ -1,3 +1,14 @@
+0.79 (2016-01-09)
+-----------------
+- Support for Grid Format (g608)
+- Show Correct number of teletext packet processed
+- Removed Segfault on incorrect mp4 detection
+- Remove xml header from transcript format
+- Help message updated for Teletext
+- Added --help and -h for help message
+- Added --nohtmlescape option
+- Added --noscte20 option
+
 0.78 (2015-12-12)
 -----------------
 - Support to extract Closed Caption from MultiProgram at once.

docs/G608.TXT

@@ -0,0 +1,58 @@
+G608
+====
+G608 (for grid 608) is generated by CCExtractor by using -out=g608.
+
+This is a verbose format that exports the contents of the 608 grid verbatim
+so there's no loss of positioning or colors due the limitations or complexy
+or other output formats.
+
+G608 is a text file with a structure based on .srt and looks like this:
+
+1
+00:00:02,019 --> 00:00:03,585
+                                99999999999999999999999999999999RRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRR
+                                99999999999999999999999999999999RRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRR
+                                99999999999999999999999999999999RRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRR
+                                99999999999999999999999999999999RRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRR
+                                99999999999999999999999999999999RRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRR
+                                99999999999999999999999999999999RRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRR
+                                99999999999999999999999999999999RRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRR
+                                99999999999999999999999999999999RRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRR
+                                99999999999999999999999999999999RRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRR
+                                99999999999999999999999999999999RRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRR
+                                99999999999999999999999999999999RRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRR
+                                99999999999999999999999999999999RRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRR
+                                99999999999999999999999999999999RRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRR
+  - Previously on The Tudors... 90000000000000000000000000000009RIIIIIIIIIIIIIIIIRRRRRRRRRRRRRRR
+  - Your Holy Father offs you   99000000000000000000000000000999RRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRR
+
+For each subtitle frame there's exactly 15 rows (which represent the 15 rows of the 608 screen)
+of 96 characters each.
+
+Each row is divided in 3 blocks: 32 characters for the text, 32 characters for the color, and 
+32 characters for the font. 
+
+The possible color values are:
+	COL_WHITE = 0,
+	COL_GREEN = 1,
+	COL_BLUE = 2,
+	COL_CYAN = 3,
+	COL_RED = 4,
+	COL_YELLOW = 5,
+	COL_MAGENTA = 6,
+	COL_USERDEFINED = 7,
+	COL_BLACK = 8,
+	COL_TRANSPARENT = 9
+	
+And the possible font values are:
+    R => Regular
+    I => Italic
+    U => Underlined
+    B => Underlined + italic
+
+If a 'E' is found in ether color or font that means a bug in CCExtractor. Should you ever get
+an E please send us a .bin file that causes it.
+	
+This format is intended for post processing tools that need to represent the output of a 608
+decoder accurately but that don't want to deal with the madness of other more generic subtitle
+formats.

docs/README.TXT

@@ -1,4 +1,4 @@
-ccextractor, 0.78
+ccextractor, 0.79
 -----------------
 Authors: Carlos Fernández (cfsmp3), Volker Quetschke.
 Maintainer: cfsmp3

src/ccextractor.c

@@ -41,6 +41,10 @@ int main(int argc, char *argv[])
 		usage ();
 		fatal (EXIT_NO_INPUT_FILES, "(This help screen was shown because there were no input files)\n");
 	}
+	else if (ret == EXIT_WITH_HELP)
+	{
+		return EXIT_OK;
+	}
 	else if (ret != EXIT_OK)
 	{
 		exit(ret);
@@ -283,9 +287,12 @@ int main(int argc, char *argv[])
 			dbg_print(CCX_DMT_DECODER_608, "Max. FTS:	   %s  (without caption blocks since then)\n",
 				print_mstime(get_fts_max(dec_ctx->timing)));
 
-			mprint ("\nTotal frames time:	  %s  (%u frames at %.2ffps)\n",
-			print_mstime( (LLONG)(total_frames_count*1000/current_fps) ),
-			total_frames_count, current_fps);
+			if (dec_ctx->codec == CCX_CODEC_ATSC_CC)
+			{
+				mprint ("\nTotal frames time:	  %s  (%u frames at %.2ffps)\n",
+				print_mstime( (LLONG)(total_frames_count*1000/current_fps) ),
+				total_frames_count, current_fps);
+			}
 
 			if (ctx->stat_hdtv)
 			{
@@ -337,10 +344,7 @@ int main(int argc, char *argv[])
 	}
 #endif
 	dbg_print(CCX_DMT_708, "[CEA-708] The 708 decoder was reset [%d] times.\n", ctx->freport.data_from_708->reset_count);
-/*
-	if (ccx_options.teletext_mode == CCX_TXT_IN_USE)
-		mprint ( "Teletext decoder: %"PRIu32" packets processed, %"PRIu32" SRT frames written.\n", tlt_packet_counter, tlt_frames_produced);
-*/
+
 	if (is_decoder_processed_enough(ctx) == CCX_TRUE)
 	{
 		mprint ("\rNote: Processing was cancelled before all data was processed because\n");

src/lib_ccx/ccx_common_common.h

@@ -17,6 +17,7 @@
 #define EXIT_UNABLE_TO_DETERMINE_FILE_SIZE      6
 #define EXIT_MALFORMED_PARAMETER                7
 #define EXIT_READ_ERROR                         8
+#define EXIT_WITH_HELP                          9
 #define EXIT_NOT_CLASSIFIED                     300
 #define EXIT_ERROR_IN_CAPITALIZATION_FILE       501
 #define EXIT_BUFFER_FULL                        502

src/lib_ccx/ccx_common_constants.h

@@ -165,6 +165,7 @@ enum ccx_output_format
 	CCX_OF_DVDRAW = 8, // See -d at http://www.geocities.com/mcpoodle43/SCC_TOOLS/DOCS/SCC_TOOLS.HTML#CCExtract
 	CCX_OF_WEBVTT = 9,
 	CCX_OF_SIMPLE_XML = 10,
+	CCX_OF_G608 = 11,
 };
 
 enum ccx_output_date_format

src/lib_ccx/ccx_common_option.c

@@ -14,6 +14,8 @@ void init_options (struct ccx_s_options *options)
 #endif
 	options->nofontcolor=0; // 1 = don't put <font color> tags
 	options->notypesetting=0; // 1 = Don't put <i>, <u>, etc typesetting tags
+	options->no_rollup = 0;
+	options->noscte20 = 0;
 
 
 	options->settings_608.direct_rollup = 0;

src/lib_ccx/ccx_common_option.h

@@ -70,9 +70,11 @@ struct ccx_s_options // Options from user parameters
 {
 	int extract; // Extract 1st, 2nd or both fields
 	int no_rollup;
+	int noscte20;
 	int cc_channel; // Channel we want to dump in srt mode
 	int buffer_input;
 	int nofontcolor;
+	int nohtmlescape;
 	int notypesetting;
 	struct ccx_boundary_time extraction_start, extraction_end; // Segment we actually process
 	int print_file_reports;

src/lib_ccx/ccx_decoders_common.c

@@ -240,6 +240,7 @@ struct lib_cc_decode* init_cc_decode (struct ccx_decoders_common_settings_t *set
 	setting->settings_608->no_rollup = setting->no_rollup;
 	setting->settings_dtvcc->no_rollup = setting->no_rollup;
 	ctx->no_rollup = setting->no_rollup;
+	ctx->noscte20 = setting->noscte20;
 
 	ctx->dtvcc = ccx_dtvcc_init(setting->settings_dtvcc);
 	ctx->dtvcc->is_active = setting->settings_dtvcc->enabled;
@@ -301,6 +302,7 @@ struct lib_cc_decode* init_cc_decode (struct ccx_decoders_common_settings_t *set
 		setting->output_format==CCX_OF_TRANSCRIPT ||
 		setting->output_format==CCX_OF_SPUPNG ||
 		setting->output_format==CCX_OF_SIMPLE_XML ||
+		setting->output_format==CCX_OF_G608 ||
 		setting->output_format==CCX_OF_NULL)
 		ctx->writedata = process608;
 	else

src/lib_ccx/ccx_decoders_structs.h

@@ -90,6 +90,7 @@ struct ccx_decoders_common_settings_t
 	int extract; // Extract 1st, 2nd or both fields
 	int fullbin; // Disable pruning of padding cc blocks
 	int no_rollup;
+	int noscte20;
 	struct ccx_decoder_608_settings *settings_608; //  Contains the settings for the 608 decoder.
 	ccx_decoder_dtvcc_settings *settings_dtvcc; //Same for cea 708 captions decoder (dtvcc)
 	int cc_channel; // Channel we want to dump in srt mode
@@ -113,6 +114,7 @@ struct lib_cc_decode
 	void *context_cc608_field_2;
 
 	int no_rollup; // If 1, write one line at a time
+	int noscte20;
 	int fix_padding; // Replace 0000 with 8080 in HDTV (needed for some cards)
 	enum ccx_output_format write_format; // 0=Raw, 1=srt, 2=SMI
 	struct ccx_boundary_time extraction_start, extraction_end; // Segment we actually process

src/lib_ccx/ccx_encoders_common.c

@@ -99,7 +99,6 @@ int change_utf8_encoding(unsigned char* dest, unsigned char* src, int len, enum
 {
 	unsigned char *orig = dest; // Keep for calculating length
 	unsigned char *orig_src = src; // Keep for calculating length
-	int bytes = 0;
 	for (int i = 0; src < orig_src + len;)
 	{
 		unsigned char c = src[i];
@@ -382,6 +381,7 @@ static int write_subtitle_file_header(struct encoder_ctx *ctx, struct ccx_s_writ
 	switch (ctx->write_format)
 	{
 		case CCX_OF_SRT: // Subrip subtitles have no header
+		case CCX_OF_G608:
 			ret = write_bom(ctx, out);
 			if(ret < 0)
 				return -1;
@@ -460,6 +460,7 @@ static int write_subtitle_file_header(struct encoder_ctx *ctx, struct ccx_s_writ
 			ret = write_bom(ctx, out);
 			if(ret < 0)
 				return -1;
+			break;
 		case CCX_OF_SIMPLE_XML: // No header. Fall thru
 			ret = write_bom(ctx, out);
 			if(ret < 0)
@@ -472,6 +473,7 @@ static int write_subtitle_file_header(struct encoder_ctx *ctx, struct ccx_s_writ
 				mprint("WARNING: Unable to write complete Buffer \n");
 				return -1;
 			}
+			break;
 		default:
 			break;
 	}
@@ -495,7 +497,7 @@ int write_cc_subtitle_as_simplexml(struct cc_subtitle *sub, struct encoder_ctx *
 		str = strtok_r(str, "\r\n", &save_str);
 		do
 		{
-			length = get_str_basic(context->subline, str, context->trim_subs, sub->enc_type, context->encoding, strlen(str));
+			length = get_str_basic(context->subline, (unsigned char*)str, context->trim_subs, sub->enc_type, context->encoding, strlen(str));
 			if (length <= 0)
 			{
 				continue;
@@ -506,7 +508,7 @@ int write_cc_subtitle_as_simplexml(struct cc_subtitle *sub, struct encoder_ctx *
 				mprint("Warning:Loss of data\n");
 			}
 
-		} while (str = strtok_r(NULL, "\r\n", &save_str) );
+		} while ( (str = strtok_r(NULL, "\r\n", &save_str) ));
 
 		freep(&sub->data);
 		lsub = sub;
@@ -519,6 +521,7 @@ int write_cc_subtitle_as_simplexml(struct cc_subtitle *sub, struct encoder_ctx *
 		lsub = sub;
 	}
 
+	return ret;
 }
 
 int write_cc_subtitle_as_transcript(struct cc_subtitle *sub, struct encoder_ctx *context)
@@ -559,7 +562,7 @@ int write_cc_subtitle_as_transcript(struct cc_subtitle *sub, struct encoder_ctx
 		str = strtok_r(str, "\r\n", &save_str);
 		do
 		{
-			length = get_str_basic(context->subline, str, context->trim_subs, sub->enc_type, context->encoding, strlen(str));
+			length = get_str_basic(context->subline, (unsigned char*)str, context->trim_subs, sub->enc_type, context->encoding, strlen(str));
 			if (length <= 0)
 			{
 				continue;
@@ -625,7 +628,7 @@ int write_cc_subtitle_as_transcript(struct cc_subtitle *sub, struct encoder_ctx
 				mprint("Warning:Loss of data\n");
 			}
 
-		} while (str = strtok_r(NULL, "\r\n", &save_str) );
+		} while ( (str = strtok_r(NULL, "\r\n", &save_str)) );
 
 		freep(&sub->data);
 		lsub = sub;
@@ -1346,6 +1349,9 @@ int encode_sub(struct encoder_ctx *context, struct cc_subtitle *sub)
 					try_to_add_start_credits(context, data->start_time);
 				wrote_something = write_cc_buffer_as_srt(data, context);
 				break;
+			case CCX_OF_G608:
+				wrote_something = write_cc_buffer_as_g608(data, context);
+				break;
 			case CCX_OF_WEBVTT:
 				if (!context->startcredits_displayed && context->start_credits_text != NULL)
 					try_to_add_start_credits(context, data->start_time);

src/lib_ccx/ccx_encoders_common.h

@@ -128,6 +128,8 @@ void dinit_encoder(struct encoder_ctx **arg, LLONG current_fts);
  */
 int encode_sub(struct encoder_ctx *ctx,struct cc_subtitle *sub);
 
+int write_cc_buffer_as_g608(struct eia608_screen *data, struct encoder_ctx *context);
+
 int write_cc_buffer_as_srt(struct eia608_screen *data, struct encoder_ctx *context);
 int write_cc_subtitle_as_srt(struct cc_subtitle *sub, struct encoder_ctx *context);
 int write_stringz_as_srt(char *string, struct encoder_ctx *context, LLONG ms_start, LLONG ms_end);

src/lib_ccx/ccx_encoders_g608.c

@@ -0,0 +1,109 @@
+#include "lib_ccx.h"
+#include "ccx_encoders_common.h"
+#include "ccx_encoders_helpers.h"
+
+static unsigned int get_line_encoded(struct encoder_ctx *ctx, unsigned char *buffer, int line_num, struct eia608_screen *data)
+{
+	unsigned char *orig = buffer; // Keep for debugging
+	unsigned char *line = data->characters[line_num];
+	for (int i = 0; i < 32; i++)
+	{
+		int bytes = 0;
+		switch (ctx->encoding)
+		{
+		case CCX_ENC_UTF_8:
+			bytes = get_char_in_utf_8(buffer, line[i]);
+			break;
+		case CCX_ENC_LATIN_1:
+			get_char_in_latin_1(buffer, line[i]);
+			bytes = 1;
+			break;
+		case CCX_ENC_UNICODE:
+			get_char_in_unicode(buffer, line[i]);
+			bytes = 2;
+		case CCX_ENC_ASCII:
+		    *buffer = line[i];
+			bytes = 1;
+			break;
+		}
+		buffer += bytes;
+	}
+	return (unsigned int)(buffer - orig); // Return length
+}
+static unsigned int get_color_encoded(struct encoder_ctx *ctx, unsigned char *buffer, int line_num, struct eia608_screen *data)
+{
+	unsigned char *orig = buffer; // Keep for debugging
+	for (int i = 0; i < 32; i++)
+	{
+		if (data->colors[line_num][i] < 10)
+			*buffer++ = data->colors[line_num][i] + '0';
+		else
+			*buffer++ = 'E';
+	}
+	*buffer = 0;
+	return (unsigned)(buffer - orig); // Return length
+}
+static unsigned int get_font_encoded(struct encoder_ctx *ctx, unsigned char *buffer, int line_num, struct eia608_screen *data)
+{
+	unsigned char *orig = buffer; // Keep for debugging
+	for (int i = 0; i < 32; i++)
+	{
+		if(data->fonts[line_num][i] == FONT_REGULAR)
+			*buffer++ = 'R';
+		else if(data->fonts[line_num][i] == FONT_UNDERLINED_ITALICS)
+			*buffer++ = 'B';
+		else if(data->fonts[line_num][i] == FONT_UNDERLINED)
+			*buffer++ = 'U';
+		else if(data->fonts[line_num][i] == FONT_ITALICS)
+			*buffer++ = 'I';
+		else
+			*buffer++ = 'E';
+	}
+	return (unsigned)(buffer - orig); // Return length
+}
+int write_cc_buffer_as_g608(struct eia608_screen *data, struct encoder_ctx *context)
+{
+	int used;
+	unsigned h1,m1,s1,ms1;
+	unsigned h2,m2,s2,ms2;
+	LLONG ms_start, ms_end;
+	int wrote_something = 0;
+	ms_start = data->start_time;
+
+	ms_start+=context->subs_delay;
+	if (ms_start<0) // Drop screens that because of subs_delay start too early
+		return 0;
+
+	ms_end = data->end_time;
+
+	mstotime (ms_start,&h1,&m1,&s1,&ms1);
+	mstotime (ms_end-1,&h2,&m2,&s2,&ms2); // -1 To prevent overlapping with next line.
+	char timeline[128];
+	context->srt_counter++;
+	sprintf(timeline, "%u%s", context->srt_counter, context->encoded_crlf);
+	used = encode_line(context, context->buffer,(unsigned char *) timeline);
+	write(context->out->fh, context->buffer, used);
+	sprintf (timeline, "%02u:%02u:%02u,%03u --> %02u:%02u:%02u,%03u%s",
+		h1, m1, s1, ms1, h2, m2, s2, ms2, context->encoded_crlf);
+	used = encode_line(context, context->buffer,(unsigned char *) timeline);
+
+
+	write (context->out->fh, context->buffer, used);
+
+	for (int i=0;i<15;i++)
+	{
+		int length = get_line_encoded (context, context->subline, i, data);
+		write(context->out->fh, context->subline, length);
+
+		length = get_color_encoded (context, context->subline, i, data);
+		write(context->out->fh, context->subline, length);
+
+		length = get_font_encoded (context, context->subline, i, data);
+		write(context->out->fh, context->subline, length);
+		write(context->out->fh, context->encoded_crlf, context->encoded_crlf_length);
+		wrote_something=1;
+	}
+
+	write (context->out->fh, context->encoded_crlf, context->encoded_crlf_length);
+	return wrote_something;
+}

src/lib_ccx/es_userdata.c

@@ -138,7 +138,7 @@ int user_data(struct lib_cc_decode *ctx, struct bitstream *ustream, int udtype,
 		dbg_print(CCX_DMT_VERBOSE, "Read %d/%d DVD CC blocks\n", rcbcount, ecbcount);
 	}
 	// SCTE 20 user data
-	else if (ud_header[0] == 0x03)
+	else if (!ctx->noscte20 && ud_header[0] == 0x03)
 	{
 		if ((ud_header[1]&0x7F) == 0x01)
 		{

src/lib_ccx/general_loop.c

@@ -915,6 +915,7 @@ void rcwt_loop(struct lib_ccx_ctx *ctx)
 	dec_ctx = update_decoder_list(ctx);
 	if (parsebuf[6] == 0 && parsebuf[7] == 2)
 	{
+		dec_ctx->codec = CCX_CODEC_TELETEXT;
 		dec_ctx->private_data = telxcc_init();
 	}
 	dec_sub = &dec_ctx->dec_sub;

src/lib_ccx/lib_ccx.c

@@ -22,6 +22,7 @@ static struct ccx_decoders_common_settings_t *init_decoder_setting(
 	setting->extract = opt->extract;
 	setting->fullbin = opt->fullbin;
 	setting->no_rollup = opt->no_rollup;
+	setting->noscte20 = opt->noscte20;
 	memcpy(&setting->extraction_start,&opt->extraction_start,sizeof(struct ccx_boundary_time));
 	memcpy(&setting->extraction_end,&opt->extraction_end,sizeof(struct ccx_boundary_time));
 	setting->cc_to_stdout = opt->cc_to_stdout;
@@ -184,8 +185,8 @@ void dinit_libraries( struct lib_ccx_ctx **ctx)
 		if (dec_ctx->codec == CCX_CODEC_DVB)
 			dvbsub_close_decoder(&dec_ctx->private_data);
 		//Test memory for teletext
-		//else if (dec_ctx->codec == CCX_CODEC_TELETEXT)
-		//	telxcc_close(&dec_ctx->private_data, NULL);
+		else if (dec_ctx->codec == CCX_CODEC_TELETEXT)
+			telxcc_close(&dec_ctx->private_data, NULL);
 		else if (dec_ctx->codec == CCX_CODEC_ISDB_CC)
 			delete_isdb_decoder(&dec_ctx->private_data);
 

src/lib_ccx/lib_ccx.h

@@ -1,7 +1,7 @@
 #ifndef CCX_CCEXTRACTOR_H
 #define CCX_CCEXTRACTOR_H
 
-#define VERSION "0.78"
+#define VERSION "0.79"
 
 // Load common includes and constants for library usage
 #include "ccx_common_platform.h"
@@ -57,6 +57,7 @@ struct ccx_s_teletext_config
 	unsigned send_to_srv;
 	enum ccx_encoding_type encoding;
 	int nofontcolor;
+	int nohtmlescape;
 	char millis_separator;
 };
 
@@ -204,7 +205,7 @@ void flushbuffer (struct lib_ccx_ctx *ctx, struct ccx_s_write *wb, int closefile
 void writercwtdata (struct lib_cc_decode *ctx, const unsigned char *data, struct cc_subtitle *sub);
 
 // stream_functions.c
-int isValidMP4Box(unsigned char *buffer, long position, long *nextBoxLocation, int *boxScore);
+int isValidMP4Box(unsigned char *buffer, size_t position, size_t *nextBoxLocation, int *boxScore);
 void detect_stream_type (struct ccx_demuxer *ctx);
 int detect_myth( struct ccx_demuxer *ctx );
 int read_video_pes_header (struct ccx_demuxer *ctx, struct demuxer_data *data, unsigned char *nextheader, int *headerlength, int sbuflen);

src/lib_ccx/params.c

@@ -214,6 +214,8 @@ void set_output_format (struct ccx_s_options *opt, const char *format)
 		opt->write_format=CCX_OF_SPUPNG;
 	else if (strcmp (format,"simplexml")==0)
 		opt->write_format=CCX_OF_SIMPLE_XML;
+	else if (strcmp (format,"g608")==0)
+		opt->write_format=CCX_OF_G608;
 	else
 		fatal (EXIT_MALFORMED_PARAMETER, "Unknown output file format: %s\n", format);
 }
@@ -273,6 +275,7 @@ void usage (void)
 	mprint ("  Syntax:\n");
 	mprint ("  ccextractor [options] inputfile1 [inputfile2...] [-o outputfilename]\n");
 	mprint ("               [-o1 outputfilename1] [-o2 outputfilename2]\n\n");
+	mprint ("To see This Help Message: -h or --help\n\n");
 	mprint ("File name related options:\n");
 	mprint ("            inputfile: file(s) to process\n");
 	mprint ("    -o outputfilename: Use -o parameters to define output filename if you don't\n");
@@ -372,7 +375,6 @@ void usage (void)
 	mprint ("                      report  -> Prints to stdout information about captions\n");
 	mprint ("                                 in specified input. Don't produce any file\n");
 	mprint ("                                 output\n\n");
-	mprint ("       Note: Teletext output can only be srt, webvtt, txt or ttxt for now.\n\n");
 
 	mprint ("Options that affect how input files will be processed.\n");
 
@@ -453,6 +455,7 @@ void usage (void)
 	mprint ("                       reference to the received data. Use this parameter if\n");
 	mprint ("                       you prefer your own reference. Note: Current this only\n");
 	mprint ("                       affects Teletext in timed transcript with -datets.\n");
+	mprint ("           --noscte20: Ignore SCTE-20 data if present.\n");
 	mprint ("\n");
 	mprint ("Options that affect what kind of output will be produced:\n");
 	mprint("				  -bom: Append a BOM (Byte Order Mark) to output files.\n");
@@ -467,6 +470,7 @@ void usage (void)
 	mprint ("                       because UTF-8 is now the default).\n");
 	mprint ("              -latin1: Encode subtitles in Latin-1\n");
 	mprint ("  -nofc --nofontcolor: For .srt/.sami/.vtt, don't add font color tags.\n");
+	mprint ("  --nohtmlescape: For .srt/.sami/.vtt, don't covert html unsafe character\n");
 	mprint ("-nots --notypesetting: For .srt/.sami/.vtt, don't add typesetting tags.\n");
 	mprint ("                -trim: Trim lines.\n");
 	mprint ("   -dc --defaultcolor: Select a different default color (instead of\n");
@@ -829,6 +833,11 @@ int parse_parameters (struct ccx_s_options *opt, int argc, char *argv[])
 	// Parse parameters
 	for (int i=1; i<argc; i++)
 	{
+		if (!strcmp (argv[i],"--help") || !strcmp(argv[i], "-h"))
+		{
+			usage();
+			return EXIT_WITH_HELP;
+		}
 		if (strcmp (argv[i], "-")==0 || strcmp(argv[i], "-stdin") == 0)
 		{
 
@@ -885,6 +894,11 @@ int parse_parameters (struct ccx_s_options *opt, int argc, char *argv[])
 			opt->nofontcolor=1;
 			continue;
 		}
+		if (strcmp (argv[i],"--nohtmlescape")==0)
+		{
+			opt->nohtmlescape=1;
+			continue;
+		}
 		if (strcmp(argv[i], "-bom") == 0){
 			opt->enc_cfg.no_bom = 0;
 			continue;
@@ -1086,6 +1100,11 @@ int parse_parameters (struct ccx_s_options *opt, int argc, char *argv[])
 			MPEG_CLOCK_FREQ=90090;
 			continue;
 		}
+		if (strcmp (argv[i],"--noscte20")==0)
+		{
+			opt->noscte20 = 1;
+			continue;
+		}
 		if (strcmp (argv[i],"-noru")==0 ||
 				strcmp (argv[i],"--norollup")==0)
 		{
@@ -1713,6 +1732,7 @@ int parse_parameters (struct ccx_s_options *opt, int argc, char *argv[])
 	tlt_config.noautotimeref = opt->noautotimeref;
 	tlt_config.send_to_srv = opt->send_to_srv;
 	tlt_config.nofontcolor = opt->nofontcolor;
+	tlt_config.nohtmlescape = opt->nohtmlescape;
 	tlt_config.millis_separator = opt->millis_separator;
 
 	// teletext page number out of range

src/lib_ccx/stream_functions.c

@@ -64,11 +64,10 @@ void detect_stream_type (struct ccx_demuxer *ctx)
 	if ((ctx->stream_mode == CCX_SM_ELEMENTARY_OR_NOT_FOUND || ccx_options.print_file_reports)
 			&& ctx->startbytes_avail >= 4) // Still not found
 	{
-		long idx = 0, nextBoxLocation = 0, lastBoxLocation = 0;
+		size_t idx = 0, nextBoxLocation = 0;
 		int boxScore = 0;
 		// Scan the buffer for valid succeeding MP4 boxes.
-		while (idx < ctx->startbytes_avail - 7){
-			lastBoxLocation = idx;
+		while (idx < ctx->startbytes_avail - 8){
 			// Check if we have a valid box
 			if (isValidMP4Box(ctx->startbytes, idx, &nextBoxLocation, &boxScore))
 			{
@@ -431,7 +430,7 @@ ccx_stream_mp4_box ccx_stream_mp4_boxes[11] = {
  *
  * Returns 1 when a box is found, 0 when none is found.
  */
-int isValidMP4Box(unsigned char *buffer, long position, long *nextBoxLocation, int *boxScore)
+int isValidMP4Box(unsigned char *buffer, size_t position, size_t *nextBoxLocation, int *boxScore)
 {
 	for (int idx = 0; idx < 11; idx++)
 	{
@@ -439,7 +438,7 @@ int isValidMP4Box(unsigned char *buffer, long position, long *nextBoxLocation, i
 				buffer[position + 6] == ccx_stream_mp4_boxes[idx].boxType[2] && buffer[position + 7] == ccx_stream_mp4_boxes[idx].boxType[3]){
 			mprint("Detected MP4 box with name: %s\n", ccx_stream_mp4_boxes[idx].boxType);
 			// Box name matches. Do crude validation of possible box size, and if valid, add points for "valid" box
-			long boxSize = buffer[position] << 24;
+			size_t boxSize = buffer[position] << 24;
 			boxSize |= buffer[position + 1] << 16;
 			boxSize |= buffer[position + 2] << 8;
 			boxSize |= buffer[position + 3];

src/lib_ccx/telxcc.c

@@ -86,7 +86,6 @@ struct TeletextCtx
 	enum ccx_output_date_format date_format;
 	int noautotimeref; // Do NOT set time automatically?
 	unsigned send_to_srv;
-	int nofontcolor;
 	char millis_separator;
 	uint32_t global_timestamp;
 
@@ -756,7 +755,6 @@ void process_page(struct TeletextCtx *ctx, teletext_page_t *page, struct cc_subt
 				{
 					sprintf (c_tempb, "<font color=\"%s\">", TTXT_COLOURS[foreground_color]);
 					page_buffer_add_string (ctx, c_tempb);
-					// if (ctx->wbout1.fh!=-1) fdprintf(ctx->wbout1.fh, "<font color=\"%s\">", TTXT_COLOURS[foreground_color]);
 					font_tag_opened = YES;
 				}
 			}
@@ -772,7 +770,6 @@ void process_page(struct TeletextCtx *ctx, teletext_page_t *page, struct cc_subt
 						if (font_tag_opened == YES)
 						{
 							page_buffer_add_string (ctx, "</font>");
-							// if (ctx->wbout1.fh!=-1) fdprintf(ctx->wbout1.fh, "</font> ");
 							font_tag_opened = NO;
 						}
 
@@ -782,7 +779,6 @@ void process_page(struct TeletextCtx *ctx, teletext_page_t *page, struct cc_subt
 						{
 							sprintf (c_tempb, "<font color=\"%s\">", TTXT_COLOURS[v]);
 							page_buffer_add_string (ctx, c_tempb);
-							// if (ctx->wbout1.fh!=-1) fdprintf(ctx->wbout1.fh, "<font color=\"%s\">", TTXT_COLOURS[v]);
 							font_tag_opened = YES;
 						}
 					}
@@ -795,17 +791,13 @@ void process_page(struct TeletextCtx *ctx, teletext_page_t *page, struct cc_subt
 					ucs2_to_utf8(u, v);
 					uint64_t ucs2_char=(u[0]<<24) | (u[1]<<16) | (u[2]<<8) | u[3];
 					ucs2_buffer_add_char(ctx, ucs2_char);
-				}
 
-				if (v >= 0x20)
-				{
 					// translate some chars into entities, if in colour mode
-					if (!tlt_config.nofontcolor)
+					if (!tlt_config.nofontcolor && !tlt_config.nohtmlescape)
 					{
 						for (uint8_t i = 0; i < array_length(ENTITIES); i++)
 							if (v == ENTITIES[i].character)
 							{
-								//if (ctx->wbout1.fh!=-1) fdprintf(ctx->wbout1.fh, "%s", ENTITIES[i].entity);
 								page_buffer_add_string (ctx, ENTITIES[i].entity);
 								// v < 0x20 won't be printed in next block
 								v = 0;
@@ -813,11 +805,8 @@ void process_page(struct TeletextCtx *ctx, teletext_page_t *page, struct cc_subt
 							}
 					}
 				}
-
-
 				if (v >= 0x20)
 				{
-					//if (ctx->wbout1.fh!=-1) fdprintf(ctx->wbout1.fh, "%s", u);
 					page_buffer_add_string (ctx, u);
 					if (tlt_config.gui_mode_reports) // For now we just handle the easy stuff
 						fprintf (stderr,"%s",u);
@@ -828,7 +817,6 @@ void process_page(struct TeletextCtx *ctx, teletext_page_t *page, struct cc_subt
 		// no tag will left opened!
 		if ((!tlt_config.nofontcolor) && (font_tag_opened == YES))
 		{
-			//if (ctx->wbout1.fh!=-1) fdprintf(ctx->wbout1.fh, "</font>");
 			page_buffer_add_string (ctx, "</font>");
 			font_tag_opened = NO;
 		}
@@ -882,17 +870,7 @@ void process_page(struct TeletextCtx *ctx, teletext_page_t *page, struct cc_subt
 				ctx->prev_show_timestamp = page->show_timestamp;
 			}
 			break;
-		case CCX_OF_SMPTETT:
-#if 0
-			if (ctx->wbout1.fh!=-1)
-			{
-				timestamp_to_smptetttime(page->show_timestamp, timecode_show);
-				timestamp_to_smptetttime(page->hide_timestamp, timecode_hide);
-				fdprintf(ctx->wbout1.fh,"      <p region=\"speaker\" begin=\"%s\" end=\"%s\">%s</p>\n", timecode_show, timecode_hide, ctx->page_buffer_cur);
-			}
-#endif
-			break;
-		default: // Yes, this means everything else is .srt for now
+		default:
 			add_cc_sub_text(sub, ctx->page_buffer_cur, page->show_timestamp,
 				page->hide_timestamp + 1, NULL, "TLT", CCX_ENC_UTF_8);
 	}
@@ -1220,6 +1198,7 @@ void tlt_read_rcwt(void *codec, unsigned char *buf, struct cc_subtitle *sub)
 
 	ctx->last_timestamp = t;
 
+	ctx->tlt_packet_counter++;
 	process_telx_packet(ctx, id, pl, t, sub);
 }
 
@@ -1430,30 +1409,6 @@ void* telxcc_init(void)
 	return ctx;
 }
 
-void telxcc_configure (void *codec, struct ccx_s_teletext_config *cfg)
-{
-	struct TeletextCtx *ctx = codec;
-	ctx->verbose = cfg->verbose;
-	ctx->page = cfg->page;
-	ctx->tid = cfg->tid;
-	ctx->offset = cfg->offset;
-	ctx->bom = cfg->bom;
-	ctx->nonempty = cfg->nonempty;
-	ctx->user_page = cfg->user_page;
-	ctx->levdistmincnt = cfg->levdistmincnt;
-	ctx->levdistmaxpct = cfg->levdistmaxpct;
-	ctx->extraction_start = cfg->extraction_start;
-	ctx->extraction_end = cfg->extraction_end;
-	ctx->write_format = cfg->write_format;
-	ctx->gui_mode_reports = cfg->gui_mode_reports;
-	ctx->date_format = cfg->date_format;
-	ctx->noautotimeref = cfg->noautotimeref;
-	ctx->send_to_srv = cfg->send_to_srv;
-	ctx->nofontcolor = cfg->nofontcolor;
-	ctx->millis_separator = cfg->millis_separator;
-
-}
-
 void telxcc_update_gt(void *codec, uint32_t global_timestamp)
 {
 	struct TeletextCtx *ctx = codec;
@@ -1468,6 +1423,7 @@ void telxcc_close(void **ctx, struct cc_subtitle *sub)
 	if(!ttext)
 		return;
 
+	mprint ( "\nTeletext decoder: %"PRIu32" packets processed \n", ttext->tlt_packet_counter);
 	if (tlt_config.write_format != CCX_OF_RCWT && sub)
 	{
 		// output any pending close caption

src/lib_ccx/utility.c

@@ -422,6 +422,8 @@ char *get_file_extension(enum ccx_output_format write_format)
 			return strdup(".dvdraw");
 		case CCX_OF_SIMPLE_XML:
 			return strdup(".xml");
+		case CCX_OF_G608:
+			return strdup(".g608");
 		case CCX_OF_NULL:
 			return NULL;
 		default: