Merge branch 'CCExtractor:master' into gaurav-v2

Author: gaurav02081

README.md

@@ -28,6 +28,22 @@ The core functionality is written in C. Other languages used include C++ and Pyt
 
 Downloads for precompiled binaries and source code can be found [on our website](https://ccextractor.org/public/general/downloads/).
 
+### WebVTT Output Options
+
+CCExtractor supports optional WebVTT-specific headers for advanced use cases
+such as HTTP Live Streaming (HLS).
+
+#### `--timestamp-map`
+
+Enable writing the `X-TIMESTAMP-MAP` header in WebVTT output.
+
+This header is required for HLS workflows but is **disabled by default**
+to preserve compatibility with standard WebVTT players.
+
+Example:
+```bash
+ccextractor input.ts --timestamp-map -o output.vtt
+```
 
 ### Windows Package Managers
 
@@ -116,4 +132,4 @@ For more information visit the CCExtractor website: [https://www.ccextractor.org
 
 ## License
 
-GNU General Public License version 2.0 (GPL-2.0)
+GNU General Public License version 2.0 (GPL-2.0)

docs/CHANGES.TXT

@@ -1,7 +1,11 @@
 0.96.6 (unreleased)
 -------------------
+- New: Add optional machine-readable JSON output for -out=report via --report-format json
+- Fix: Incorrect strlen argument when writing end timestamps in MKV subtitle extraction (WebVTT, SRT, ASS/SSA)
+- Fix: File descriptor leak and missing open() error check in MKV subtitle track saving
 - Fix: DVB EIT start time BCD decoding in XMLTV output causing invalid timestamps (#1835)
 - New: Add Snap packaging support with Snapcraft configuration and GitHub Actions CI workflow. 
+- New: Implement dictionary-based capitalization and censorship for transcripts 
 - Fix: Clear status line output on Linux/WSL to prevent text artifacts (#2017)
 - Fix: Prevent infinite loop on truncated MKV files
 - Fix: Various memory safety and stability fixes in demuxers (MP4, PS, MKV, DVB)

src/lib_ccx/ccx_common_option.c

@@ -145,6 +145,7 @@ void init_options(struct ccx_s_options *options)
 	options->enc_cfg.scc_framerate = 0;	  // Default: 29.97fps for SCC output
 	options->enc_cfg.scc_accurate_timing = 0; // Default: off for backwards compatibility (issue #1120)
 	options->enc_cfg.extract_only_708 = 0;
+	options->report_format = NULL;
 
 	options->settings_dtvcc.enabled = 0;
 	options->settings_dtvcc.active_services_count = 0;

src/lib_ccx/ccx_common_option.h

@@ -189,6 +189,7 @@ struct ccx_s_options // Options from user parameters
 	enum ccx_datasource input_source; // Files, stdin or network
 
 	char *output_filename;
+	char *report_format; // NULL = default text, e.g. "json"
 
 	char **inputfile;    // List of files to process
 	int num_input_files; // How many?

src/lib_ccx/ccx_demuxer.c

@@ -6,6 +6,7 @@
 #ifndef DISABLE_RUST
 void ccxr_demuxer_reset(struct ccx_demuxer *ctx);
 void ccxr_demuxer_close(struct ccx_demuxer *ctx);
+void ccxr_demuxer_delete(struct ccx_demuxer *ctx);
 int ccxr_demuxer_isopen(const struct ccx_demuxer *ctx);
 int ccxr_demuxer_open(struct ccx_demuxer *ctx, const char *file);
 LLONG ccxr_demuxer_get_file_size(struct ccx_demuxer *ctx);
@@ -304,6 +305,12 @@ void ccx_demuxer_delete(struct ccx_demuxer **ctx)
 {
 	struct ccx_demuxer *lctx = *ctx;
 	int i;
+
+#ifndef DISABLE_RUST
+	// Let Rust free any memory it allocated
+	ccxr_demuxer_delete(lctx);
+#endif
+
 	dinit_cap(lctx);
 	freep(&lctx->last_pat_payload);
 	for (i = 0; i < MAX_PSI_PID; i++)
@@ -322,7 +329,14 @@ void ccx_demuxer_delete(struct ccx_demuxer **ctx)
 			freep(lctx->PIDs_programs + i);
 	}
 
+#ifdef DISABLE_RUST
+	// Only free filebuffer in pure C mode - Rust handles its own memory
 	freep(&lctx->filebuffer);
+#else
+	// Rust already freed this in ccxr_demuxer_delete, just clear the pointer
+	lctx->filebuffer = NULL;
+#endif
+
 	freep(ctx);
 }
 

src/lib_ccx/ccx_encoders_transcript.c

@@ -120,11 +120,8 @@ int write_cc_subtitle_as_transcript(struct cc_subtitle *sub, struct encoder_ctx
 			start_time = sub->start_time;
 			end_time = sub->end_time;
 		}
-		if (context->sentence_cap)
-		{
-			// TODO capitalize (context, line_number,data);
-			// TODO correct_case_with_dictionary(line_number, data);
-		}
+		if (sub->data)
+			correct_spelling_and_censor_words(context, (unsigned char *)sub->data, strlen((char *)sub->data));
 
 		if (start_time == -1)
 		{

src/lib_ccx/matroska.c

@@ -1742,6 +1742,12 @@ void save_sub_track(struct matroska_ctx *mkv_ctx, struct matroska_sub_track *tra
 		free(filename);
 	}
 
+	if (desc < 0)
+	{
+		mprint("\nError: Cannot create output file for subtitle track\n");
+		return;
+	}
+
 	if (track->header != NULL)
 		write_wrapped(desc, track->header, strlen(track->header));
 
@@ -1795,7 +1801,7 @@ void save_sub_track(struct matroska_ctx *mkv_ctx, struct matroska_sub_track *tra
 
 			write_wrapped(desc, timestamp_start, strlen(timestamp_start));
 			write_wrapped(desc, " --> ", 5);
-			write_wrapped(desc, timestamp_end, strlen(timestamp_start));
+			write_wrapped(desc, timestamp_end, strlen(timestamp_end));
 
 			// writing cue settings list
 			if (blockaddition != NULL)
@@ -1836,7 +1842,7 @@ void save_sub_track(struct matroska_ctx *mkv_ctx, struct matroska_sub_track *tra
 			write_wrapped(desc, "\n", 1);
 			write_wrapped(desc, timestamp_start, strlen(timestamp_start));
 			write_wrapped(desc, " --> ", 5);
-			write_wrapped(desc, timestamp_end, strlen(timestamp_start));
+			write_wrapped(desc, timestamp_end, strlen(timestamp_end));
 			write_wrapped(desc, "\n", 1);
 			int size = 0;
 			while (*(sentence->text + size) == '\n' || *(sentence->text + size) == '\r')
@@ -1866,7 +1872,7 @@ void save_sub_track(struct matroska_ctx *mkv_ctx, struct matroska_sub_track *tra
 			write_wrapped(desc, "Dialogue: Marked=0,", strlen("Dialogue: Marked=0,"));
 			write_wrapped(desc, timestamp_start, strlen(timestamp_start));
 			write_wrapped(desc, ",", 1);
-			write_wrapped(desc, timestamp_end, strlen(timestamp_start));
+			write_wrapped(desc, timestamp_end, strlen(timestamp_end));
 			write_wrapped(desc, ",", 1);
 			char *text = ass_ssa_sentence_erase_read_order(sentence->text);
 			char *text_to_free = text; // Save original pointer for freeing
@@ -1880,6 +1886,9 @@ void save_sub_track(struct matroska_ctx *mkv_ctx, struct matroska_sub_track *tra
 			free(timestamp_end);
 		}
 	}
+
+	if (desc != 1)
+		close(desc);
 }
 
 void free_sub_track(struct matroska_sub_track *track)