[FEAT] add teletext and encoders_helpers module (#1635)

* create lib_ccxr and libccxr_exports

* add bits and levenshtein module

* add log module

* add encoding module

* add common constants module

* add time units module

* add options module

* add teletext module

* chore: remove outdated

* chore: update lock files

* chore: fix naming

* fix: reference to TeletextConfig

* fix: issue with ts_forced_program default value

* fix: use correct definition

* chore: lint warnings

* fix: example code

* fix(rust): adjust defaults, more accurate logging, use safe functions, add encoders_helper module

* fix: tests and formatting

* fix: allow hex values for streamtype

* chore: format files

* fix: naming of fields and docs

* fix: defaults for options

* fix: memory leak in vector to string

* fix(c): init logger before running parser

---------

Co-authored-by: Elbert Ronnie <[email protected]>

src/ccextractor.c

@@ -187,6 +187,7 @@ int api_start(struct ccx_s_options api_options)
 				if (!api_options.use_gop_as_pts)	// If !0 then the user selected something
 					api_options.use_gop_as_pts = 1; // Force GOP timing for ES
 				ccx_common_timing_settings.is_elementary_stream = 1;
+				break;
 			case CCX_SM_TRANSPORT:
 			case CCX_SM_PROGRAM:
 			case CCX_SM_ASF:
@@ -425,6 +426,7 @@ int api_start(struct ccx_s_options api_options)
 		mprint("code in the MythTV's branch. Please report results to the address above. If\n");
 		mprint("something is broken it will be fixed. Thanks\n");
 	}
+
 	return ret ? EXIT_OK : EXIT_NO_CAPTIONS;
 }
 
@@ -447,7 +449,11 @@ int main(int argc, char *argv[])
 	// See docs/ccextractor.cnf.sample for more info.
 
 #ifndef DISABLE_RUST
-	int compile_ret = ccxr_parse_parameters(api_options, argc, argv);
+	ccxr_init_basic_logger();
+#endif
+
+#ifndef DISABLE_RUST
+	int compile_ret = ccxr_parse_parameters(argc, argv);
 #else
 	int compile_ret = parse_parameters(api_options, argc, argv);
 #endif

src/lib_ccx/ccx_common_option.c

@@ -27,7 +27,7 @@ void init_options(struct ccx_s_options *options)
 
 	options->extract = 1;		   // Extract 1st field only (primary language)
 	options->cc_channel = 1;	   // Channel we want to dump in srt mode
-	options->binary_concat = 1;	   // Disabled by -ve or --videoedited
+	options->binary_concat = 1;	   // Disabled by --videoedited
 	options->use_gop_as_pts = 0;	   // Use GOP instead of PTS timing (0=do as needed, 1=always, -1=never)
 	options->fix_padding = 0;	   // Replace 0000 with 8080 in HDTV (needed for some cards)
 	options->gui_mode_reports = 0;	   // If 1, output in stderr progress updates so the GUI can grab them

src/lib_ccx/lib_ccx.c

@@ -102,10 +102,6 @@ struct lib_ccx_ctx *init_libraries(struct ccx_s_options *opt)
 	ccx_common_logging.log_ftn = &mprint;
 	ccx_common_logging.gui_ftn = &activity_library_process;
 
-#ifndef DISABLE_RUST
-	ccxr_init_basic_logger(opt);
-#endif
-
 	struct lib_ccx_ctx *ctx = malloc(sizeof(struct lib_ccx_ctx));
 	if (!ctx)
 		ccx_common_logging.fatal_ftn(EXIT_NOT_ENOUGH_MEMORY, "init_libraries: Not enough memory allocating lib_ccx_ctx context.");

src/lib_ccx/lib_ccx.h

@@ -154,15 +154,15 @@ struct lib_ccx_ctx *init_libraries(struct ccx_s_options *opt);
 void dinit_libraries( struct lib_ccx_ctx **ctx);
 
 #ifndef DISABLE_RUST
-extern void ccxr_init_basic_logger(struct ccx_s_options *opts);
+extern void ccxr_init_basic_logger();
 #endif
 
 //ccextractor.c
 void print_end_msg(void);
 
 //params.c
 #ifndef DISABLE_RUST
-extern int ccxr_parse_parameters(struct ccx_s_options *opt, int argc, char *argv[]);
+extern int ccxr_parse_parameters(int argc, char *argv[]);
 #endif
 int parse_parameters (struct ccx_s_options *opt, int argc, char *argv[]);
 void print_usage (void);

src/lib_ccx/params.c

@@ -395,8 +395,11 @@ void print_usage(void)
 	mprint("            --tcp-description description: Sends to the server short description about\n");
 	mprint("                                  captions e.g. channel name or file name\n");
 	mprint("Options that affect what will be processed:\n");
-	mprint("      --output-field 1 / 2 / both: Output Field 1 data, Field 2 data, or both\n");
-	mprint("                       (DEFAULT is 1)\n");
+	mprint("      --output-field 1 / 2 / both:\n");
+	mprint("                       				Values: 1 = Output Field 1\n");
+	mprint("                       						2 = Output Field 2\n");
+	mprint("                       						both = Both Output Field 1 and 2\n");
+	mprint("                       				Defaults to 1\n");
 	mprint("Use --append to prevent overwriting of existing files. The output will be\n");
 	mprint("      appended instead.\n");
 	mprint("                 --cc2: When in srt/sami mode, process captions in channel 2\n");
@@ -601,7 +604,7 @@ void print_usage(void)
 	mprint("                       white). This causes all output in .srt/.smi/.vtt\n");
 	mprint("                       files to have a font tag, which makes the files\n");
 	mprint("                       larger. Add the color you want in RGB, such as\n");
-	mprint("                       --dc #FF0000 for red.\n");
+	mprint("                       --defaultcolor #FF0000 for red.\n");
 	mprint("         --sentencecap: Sentence capitalization. Use if you hate\n");
 	mprint("                       ALL CAPS in subtitles.\n");
 	mprint("        --capfile file: Add the contents of 'file' to the list of words\n");
@@ -992,7 +995,7 @@ void print_usage(void)
 	mprint("      input.d/sub0001.png\n");
 	mprint("      ...\n");
 	mprint("  The command:\n");
-	mprint("      ccextractor --out=spupng -o /tmp/output --12 input.mpg\n");
+	mprint("      ccextractor --out=spupng -o /tmp/output --output-field both input.mpg\n");
 	mprint("  will create the files:\n");
 	mprint("      /tmp/output_1.xml\n");
 	mprint("      /tmp/output_1.d/sub0000.png\n");
@@ -2111,7 +2114,7 @@ int parse_parameters(struct ccx_s_options *opt, int argc, char *argv[])
 				opt->extract = strcmp(argv[i], "both") == 0 ? 12 : atoi_hex(argv[i]);
 				if (opt->extract != 1 && opt->extract != 2 && opt->extract != 12)
 				{
-					fatal(EXIT_MALFORMED_PARAMETER, "--output-field only accepts 1 or 2 or both.\n");
+					fatal(EXIT_MALFORMED_PARAMETER, "--output-field only accepts 1 , 2 , 12 / both.\n");
 				}
 				opt->is_608_enabled = 1;
 				continue;

src/lib_ccx/utility.c

@@ -10,6 +10,9 @@ int temp_debug = 0; // This is a convenience variable used to enable/disable deb
 volatile sig_atomic_t change_filename_requested = 0;
 
 #ifndef DISABLE_RUST
+extern int ccxr_verify_crc32(uint8_t *buf, int len);
+extern int ccxr_levenshtein_dist(const uint64_t *s1, const uint64_t *s2, unsigned s1len, unsigned s2len);
+extern int ccxr_levenshtein_dist_char(const char *s1, const char *s2, unsigned s1len, unsigned s2len);
 extern void ccxr_timestamp_to_srttime(uint64_t timestamp, char *buffer);
 extern void ccxr_timestamp_to_vtttime(uint64_t timestamp, char *buffer);
 extern void ccxr_millis_to_date(uint64_t timestamp, char *buffer, enum ccx_output_date_format date_format, char millis_separator);
@@ -86,7 +89,8 @@ int verify_crc32(uint8_t *buf, int len)
 {
 #ifndef DISABLE_RUST
 	return ccxr_verify_crc32(buf, len);
-#endif /* ifndef DISABLE_RUST */
+#endif
+
 	int i = 0;
 	int32_t crc = -1;
 	for (i = 0; i < len; i++)
@@ -99,8 +103,8 @@ int stringztoms(const char *s, struct ccx_boundary_time *bt)
 #ifndef DISABLE_RUST
 	return ccxr_stringztoms(s, bt);
 #endif
-	unsigned ss = 0,
-		 mm = 0, hh = 0;
+
+	unsigned ss = 0, mm = 0, hh = 0;
 	int value = -1;
 	int colons = 0;
 	const char *c = s;
@@ -176,6 +180,7 @@ int levenshtein_dist(const uint64_t *s1, const uint64_t *s2, unsigned s1len, uns
 #ifndef DISABLE_RUST
 	return ccxr_levenshtein_dist(s1, s2, s1len, s2len);
 #endif
+
 	unsigned int x, y, v, lastdiag, olddiag;
 	unsigned int *column = (unsigned *)malloc((s1len + 1) * sizeof(unsigned int));
 	for (y = 1; y <= s1len; y++)