Mention METADATA_BLOCK_PICTURE in the man page

* fixes fmang/opustags#69

.github/workflows/ci.yaml

@@ -0,0 +1,30 @@
+name: Continuous Integration
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+  workflow_dispatch:
+env:
+  LC_CTYPE: C.UTF-8
+  CMAKE_COLOR_DIAGNOSTICS: ON
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout git repository
+      uses: actions/checkout@v4
+    - name: Install dependencies
+      run: |
+        sudo apt install cmake g++ pkg-config libogg-dev ffmpeg libtest-harness-perl libtest-deep-perl liblist-moreutils-perl libtest-utf8-perl
+    - name: Build
+      env:
+        CXX: g++
+        CXXFLAGS: -D_FORTIFY_SOURCE=3 -D_GLIBCXX_ASSERTIONS -D_GLIBCXX_DEBUG -O2 -flto=auto -g -Wall -Wextra -Werror=format-security -fstack-protector-strong -fstack-clash-protection -fcf-protection -fsanitize=address,undefined
+        LDFLAGS: -fsanitize=address,undefined
+      run: |
+        cmake -B target -DCMAKE_VERBOSE_MAKEFILE:BOOL=ON
+        cmake --build target
+    - name: Test
+      run: |
+        cmake --build target --target check

CHANGELOG.md

@@ -1,6 +1,25 @@
 opustags changelog
 ==================
 
+1.10.1 - 2024-05-19
+-------------------
+
+Fix a build error on recent systems.
+
+1.10.0 - 2024-05-03
+-------------------
+
+- Introduce -z to delimit tags with null bytes.
+
+This option makes it possible to leverage GNU sed or GNU grep for automated tag edition with
+`opustags -z … | sed -z … | opustags -z -S …`, while also supporting multi-line tags.
+
+1.9.0 - 2023-06-07
+------------------
+
+- Introduce --vendor and --set-vendor.
+- Close the input file before finalizing the output, in order to fix --in-place on SMB drives.
+
 1.8.0 - 2023-03-07
 ------------------
 

CMakeLists.txt

@@ -2,7 +2,7 @@ cmake_minimum_required(VERSION 3.11)
 
 project(
 	opustags
-	VERSION 1.8.0
+	VERSION 1.10.1
 	LANGUAGES CXX
 )
 
@@ -51,5 +51,6 @@ include(GNUInstallDirs)
 install(TARGETS opustags DESTINATION "${CMAKE_INSTALL_BINDIR}")
 configure_file(opustags.1 . @ONLY)
 install(FILES "${CMAKE_BINARY_DIR}/opustags.1" DESTINATION "${CMAKE_INSTALL_MANDIR}/man1")
+install(FILES CHANGELOG.md CONTRIBUTING.md LICENSE README.md DESTINATION ${CMAKE_INSTALL_DOCDIR})
 
 add_subdirectory(t)

CONTRIBUTING.md

@@ -25,6 +25,9 @@ You should check that your changes don't break the test suite by running
 Following these practices is important to keep the history clean, and to allow
 for better code reviews.
 
+You can submit pull requests on GitHub at <https://github.com/fmang/opustags>,
+or email me your patches at <fmang+opustags@mg0.fr>.
+
 ## History of opustags
 
 opustags is originally a small project made to fill a need to edit tags in Opus
@@ -49,6 +52,8 @@ modules, and reviewed for safety.
 1.3.0 was focused on correctness, and detects edge cases as early as possible,
 instead of hoping something will eventually fail if something is weird.
 
+Subsequent releases have been adding new features.
+
 ## Candidate features
 
 The code contains a few `\todo` markers where something could be improved in the
@@ -59,13 +64,7 @@ More generally, here are a few features that could be added in the future:
 - Discouraging non-ASCII field names.
 - Logicial stream listing and selection for multiplexed files.
 - Escaping control characters with --escape.
-- Dump binary packets with --binary.
-- Edition of the vendor string.
 - Edition of the arbitrary binary block past the comments.
-- Support for OpusTags packets spanning multiple pages (> 64 kB).
-- Interactive edition of comments inside the EDITOR (--edit).
-- Support for cover arts.
-- Load tags from a file with --set-all=tags.txt.
 - Colored output.
 
 Don't hesitate to contact me before you do anything, I'll give you directions.

LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2013-2018, Frédéric Mangano-Tarumi
+Copyright (c) 2013-2024, Frédéric Mangano
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without modification,

README.md

@@ -17,6 +17,8 @@ ever be performed.
 opustags is tag-agnostic: you can write arbitrary key-value tags, and none of them will be treated
 specially. After all, common tags like TITLE or ARTIST are nothing more than conventions.
 
+The project’s homepage is located at <https://github.com/fmang/opustags>.
+
 Requirements
 ------------
 
@@ -64,6 +66,9 @@ Documentation
       -e, --edit                    edit tags interactively in VISUAL/EDITOR
       --output-cover FILE           extract and save the cover art, if any
       --set-cover FILE              sets the cover art
+      --vendor                      print the vendor string
+      --set-vendor VALUE            set the vendor string
       --raw                         disable encoding conversion
+      -z                            delimit tags with NUL
 
 See the man page, `opustags.1`, for extensive documentation.

opustags.1

@@ -1,4 +1,4 @@
-.TH opustags 1 "March 2023" "@PROJECT_NAME@ @PROJECT_VERSION@"
+.TH opustags 1 "March 2025" "@PROJECT_NAME@ @PROJECT_VERSION@"
 .SH NAME
 opustags \- Ogg Opus tag editor
 .SH SYNOPSIS
@@ -11,7 +11,7 @@ opustags \- Ogg Opus tag editor
 .B opustags
 .I OPTIONS
 .B -i
-.R \fIFILE\fP...
+\fIFILE\fP...
 .br
 .B opustags
 .I OPTIONS
@@ -43,13 +43,13 @@ to set new tags without being bothered by the old ones.
 If you want to replace all the tags, you can use the \fB--set-all\fP option which will cause
 \fBopustags\fP to read tags from standard input.
 The format is the same as the one used for output: newline-separated \fIFIELD=Value\fP assignment.
-All the previously existing tags as deleted.
+All the previously existing tags are deleted.
 .PP
-The Opus format specifications requires that tags are encoded in UTF-8, so that's the only encoding
-opustags supports. If your system encoding is different, the tags are automatically converted to and
-from your system locale. When you edit an Opus file whose tags contains characters unsupported by
-your system encoding, the original UTF-8 values will be preserved for the tags you don't explictly
-modify.
+The Opus format specification requires that tags are encoded in UTF-8, so that’s the only encoding
+\fBopustags\fP supports. If your system encoding is different, the tags are automatically converted
+to and from your system locale. When you edit an Opus file whose tags contain characters unsupported
+by your system encoding, the original UTF-8 values will be preserved for the tags you don’t
+explicitly modify.
 .SH OPTIONS
 .TP
 .B \-h, \-\-help
@@ -67,7 +67,7 @@ setting \fB--output\fP to the same path as the input file and enabling \fB--over
 This option conflicts with \fB--output\fP.
 .TP
 .B \-y, \-\-overwrite
-By default, \fBopustags\fP refuses to overwrite an already-existent file.
+By default, \fBopustags\fP refuses to overwrite an already-existing file.
 Use \fB-y\fP to allow overwriting.
 Note that this option is not needed when the output is a special file like \fI/dev/null\fP.
 .TP
@@ -79,10 +79,10 @@ In both cases, the field names are case-insensitive, and expected to be ASCII.
 .B \-a, \-\-add \fIFIELD=VALUE\fP
 Add a tag. Note that multiple tags with the same field name are perfectly acceptable, so you can add
 multiple fields with the same name, and previously existing tags will also be preserved.
-When the \fB--delete\fP is used with the same \fIFIELD\fP, only the older tags are deleted.
+When \fB--delete\fP is used with the same \fIFIELD\fP, only the older tags are deleted.
 .TP
 .B \-s, \-\-set \fIFIELD=VALUE\fP
-This option is provided for convenience. It delete all the fields of the same
+This option is provided for convenience. It deletes all the fields of the same
 type that may already exist, then adds it with the wanted value.
 This is strictly equivalent to \fB--delete\fP \fIFIELD\fP \fB--add\fP
 \fIFIELD=VALUE\fP. You can combine it with \fB--add\fP to add tags of the same
@@ -93,33 +93,43 @@ added with \fB--add\fP.
 Delete all the previously existing tags.
 .TP
 .B \-S, \-\-set-all
-Sets the tags from scratch.
+Set the tags from scratch.
 All the original tags are deleted and new ones are read from standard input.
 Each line must specify a \fIFIELD=VALUE\fP pair and be separated with line feeds.
 Empty lines and lines starting with \fI#\fP are ignored.
-Multiline tags must have their continuation lines prefixed by a single tab (in other words, every
+Multi-line tags must have their continuation lines prefixed by a single tab (in other words, every
 \fI\\n\fP must be replaced by \fI\\n\\t\fP).
 .TP
 .B \-e, \-\-edit
 Edit tags interactively by spawning the program specified by the EDITOR
-environment variable. The allowed format is the same as \fB--set-all\fP.
+environment variable. The allowed format is the same as with \fB--set-all\fP.
 If TERM and VISUAL are set, VISUAL takes precedence over EDITOR.
 .TP
 .B \-\-output-cover \fIFILE\fP
-Save the cover art of the input Opus file to the specified location.
+Extract the cover art from the \fBMETADATA_BLOCK_PICTURE\fP tag into the specified location.
 If the input file does not contain any cover art, this option has no effect.
 To allow overwriting the target location, specify \fB--overwrite\fP.
 In the case of multiple pictures embedded in the Opus tags, only the first one is saved.
-Note that the since the image format is not fixed, you should consider an extension-less file name
-and rely on the magic number to deduce the type. opustags does not add or check the target file’s
-extension.
+Note that since the image format is not fixed, you should consider an extension-less file name and
+rely on the magic number to deduce the type.
+\fBopustags\fP does not add or check the target file’s extension.
 You can specify \fB-\fP for standard output, in which case the regular output will be suppressed.
 .TP
 .B \-\-set-cover \fIFILE\fP
-Replace or set the cover art to the specified picture.
+Set the cover art by embedding the specified picture into the \fBMETADATA_BLOCK_PICTURE\fP tag,
+replacing any existing values.
 Specify \fB-\fP to read the picture from standard input.
 In theory, an Opus file may contain multiple pictures with different roles, though in practice only
-the front cover really matters. opustags can currently only handle one front cover and nothing else.
+the front cover really matters.
+\fBopustags\fP can currently only handle one front cover and nothing else.
+.TP
+.B \-\-vendor
+Print the vendor string from the OpusTags packet and do nothing else. Standard tags operations are
+not supported when specifying this flag.
+.TP
+.B \-\-set-vendor \fIVALUE\fP
+Replace the vendor string by the specified value. This action can be performed alongside tag
+edition.
 .TP
 .B \-\-raw
 OpusTags metadata should always be encoded in UTF-8, as per RFC 7845. However, some files may be
@@ -127,6 +137,15 @@ corrupted or possibly even contain intentional binary data. In that case, --raw
 kind of binary data without ensuring the validity of the tags encoding. This option may also be
 useful when your system encoding is different from UTF-8 and you wish to preserve the full UTF-8
 character set even though your system cannot display it.
+.TP
+.B \-z
+When editing tags programmatically with line-based tools like grep or sed, tags containing newlines
+are likely to corrupt the result because these tools won’t interpret multi-line tags as a whole. To
+make automatic processing easier, \fB-z\fP delimits tags by a null byte (ASCII NUL) instead of line
+feeds. That same \fB-z\fP flag is also supported by GNU grep or GNU sed and, combined with
+\fBopustags -z\fP, would make them process the input tag-by-tag instead of line-by-line, thus
+supporting multi-line tags as well.
+This option also disables the tab prefix for continuation lines after a line feed.
 .SH EXAMPLES
 .PP
 List all the tags in file foo.opus:
@@ -137,10 +156,6 @@ Copy in.opus to out.opus, with the TITLE tag added:
 .PP
 	opustags in.opus --output out.opus --add "TITLE=Hello world!"
 .PP
-Replace all the tags in dest.opus with the ones from src.opus:
-.PP
-	opustags src.opus | opustags --in-place dest.opus --set-all
-.PP
 Remove the previously existing ARTIST tags and add the two X and Y ARTIST tags, then display the new
 tags without writing them to the Opus file:
 .PP
@@ -149,10 +164,18 @@ tags without writing them to the Opus file:
 Edit tags interactively in Vim:
 .PP
 	EDITOR=vim opustags --in-place --edit file.opus
+.PP
+Replace all the tags in dest.opus with the ones from src.opus:
+.PP
+	opustags src.opus | opustags --in-place dest.opus --set-all
+.PP
+Use GNU grep to remove all the CHAPTER* tags, with -z to support multi-line tags:
+.PP
+	opustags -z file.opus | grep -z -v ^CHAPTER | opustags -z --in-place file.opus --set-all
 .SH CAVEATS
 .PP
 \fBopustags\fP currently has the following limitations:
-.IP \[bu]
+.IP \[bu] 2n
 Multiplexed streams are not supported.
 .IP \[bu]
 Control characters inside tags are printed raw rather than being escaped.

src/base64.cc

@@ -56,7 +56,7 @@ std::u8string ot::encode_base64(ot::byte_string_view src)
 ot::byte_string ot::decode_base64(std::u8string_view src)
 {
 	// Remove the padding and rely on the string length instead.
-	while (src.back() == u8'=')
+	while (!src.empty() && src.back() == u8'=')
 		src.remove_suffix(1);
 
 	size_t olen = src.size() / 4 * 3; // Whole blocks;

src/cli.cc

@@ -15,6 +15,7 @@
 #include <string.h>
 #include <sys/stat.h>
 #include <unistd.h>
+#include <algorithm>
 
 static const char help_message[] =
 PROJECT_NAME " version " PROJECT_VERSION
@@ -38,7 +39,10 @@ Options:
   -e, --edit                    edit tags interactively in VISUAL/EDITOR
   --output-cover FILE           extract and save the cover art, if any
   --set-cover FILE              sets the cover art
+  --vendor                      print the vendor string
+  --set-vendor VALUE            set the vendor string
   --raw                         disable encoding conversion
+  -z                            delimit tags with NUL
 
 See the man page for extensive documentation.
 )raw";
@@ -56,6 +60,8 @@ static struct option getopt_options[] = {
 	{"edit", no_argument, 0, 'e'},
 	{"output-cover", required_argument, 0, 'c'},
 	{"set-cover", required_argument, 0, 'C'},
+	{"vendor", no_argument, 0, 'v'},
+	{"set-vendor", required_argument, 0, 'V'},
 	{"raw", no_argument, 0, 'r'},
 	{NULL, 0, 0, 0}
 };
@@ -69,12 +75,13 @@ ot::options ot::parse_options(int argc, char** argv, FILE* comments_input)
 	std::list<std::string> local_to_delete; // opt.to_delete before UTF-8 conversion.
 	bool set_all = false;
 	std::optional<std::string> set_cover;
+	std::optional<std::string> set_vendor;
 	opt = {};
 	if (argc == 1)
 		throw status {st::bad_arguments, "No arguments specified. Use -h for help."};
 	int c;
 	optind = 0;
-	while ((c = getopt_long(argc, argv, ":ho:iyd:a:s:DSe", getopt_options, NULL)) != -1) {
+	while ((c = getopt_long(argc, argv, ":ho:iyd:a:s:DSez", getopt_options, NULL)) != -1) {
 		switch (c) {
 		case 'h':
 			opt.print_help = true;
@@ -123,9 +130,20 @@ ot::options ot::parse_options(int argc, char** argv, FILE* comments_input)
 				throw status {st::bad_arguments, "Cannot specify --set-cover more than once."};
 			set_cover = optarg;
 			break;
+		case 'v':
+			opt.print_vendor = true;
+			break;
+		case 'V':
+			if (set_vendor)
+				throw status {st::bad_arguments, "Cannot specify --set-vendor more than once."};
+			set_vendor = optarg;
+			break;
 		case 'r':
 			opt.raw = true;
 			break;
+		case 'z':
+			opt.tag_delimiter = '\0';
+			break;
 		case ':':
 			throw status {st::bad_arguments, "Missing value for option '"s + argv[optind - 1] + "'."};
 		default:
@@ -161,17 +179,23 @@ ot::options ot::parse_options(int argc, char** argv, FILE* comments_input)
 			       std::back_inserter(opt.to_add), cast_to_utf8);
 		std::transform(local_to_delete.begin(), local_to_delete.end(),
 			       std::back_inserter(opt.to_delete), cast_to_utf8);
+		if (set_vendor)
+			opt.set_vendor = cast_to_utf8(*set_vendor);
 	} else {
 		try {
 			std::transform(local_to_add.begin(), local_to_add.end(),
 			               std::back_inserter(opt.to_add), encode_utf8);
 			std::transform(local_to_delete.begin(), local_to_delete.end(),
 			               std::back_inserter(opt.to_delete), encode_utf8);
+			if (set_vendor)
+				opt.set_vendor = encode_utf8(*set_vendor);
 		} catch (const ot::status& rc) {
 			throw status {st::bad_arguments, "Could not encode argument into UTF-8: " + rc.message};
 		}
 	}
 
+	bool read_only = !opt.in_place && !opt.path_out.has_value();
+
 	if (opt.in_place && opt.path_out)
 		throw status {st::bad_arguments, "Cannot combine --in-place and --output."};
 
@@ -184,7 +208,7 @@ ot::options ot::parse_options(int argc, char** argv, FILE* comments_input)
 	if (opt.edit_interactively && (stdin_as_input || opt.path_out == "-" || opt.cover_out == "-"))
 		throw status {st::bad_arguments, "Cannot edit interactively when standard input or standard output are already used."};
 
-	if (opt.edit_interactively && !opt.path_out.has_value() && !opt.in_place)
+	if (opt.edit_interactively && read_only)
 		throw status {st::bad_arguments, "Cannot edit interactively when no output is specified."};
 
 	if (opt.edit_interactively && (opt.delete_all || !opt.to_add.empty() || !opt.to_delete.empty()))
@@ -196,6 +220,9 @@ ot::options ot::parse_options(int argc, char** argv, FILE* comments_input)
 	if (opt.cover_out && opt.paths_in.size() > 1)
 		throw status {st::bad_arguments, "Cannot use --output-cover with multiple input files."};
 
+	if (opt.print_vendor && !read_only)
+		throw status {st::bad_arguments, "--vendor is only supported in read-only mode."};
+
 	if (set_cover) {
 		byte_string picture_data = ot::slurp_binary_file(set_cover->c_str());
 		opt.to_delete.push_back(u8"METADATA_BLOCK_PICTURE"s);
@@ -204,17 +231,17 @@ ot::options ot::parse_options(int argc, char** argv, FILE* comments_input)
 
 	if (set_all) {
 		// Read comments from stdin and prepend them to opt.to_add.
-		std::list<std::u8string> comments = read_comments(comments_input, opt.raw);
+		std::list<std::u8string> comments = read_comments(comments_input, opt);
 		opt.to_add.splice(opt.to_add.begin(), std::move(comments));
 	}
 	return opt;
 }
 
 /** Format a UTF-8 string by adding tabulations (\t) after line feeds (\n) to mark continuation for
- *  multiline values. */
-static std::u8string format_value(const std::u8string& source)
+ *  multiline values. With -z, this behavior applies for embedded NUL characters instead of LF. */
+static std::u8string format_value(const std::u8string& source, const ot::options& opt)
 {
-	auto newline_count = std::count(source.begin(), source.end(), u8'\n');
+	auto newline_count = std::count(source.begin(), source.end(), opt.tag_delimiter);
 
 	// General case: the value fits on a single line. Use std::string’s copy constructor for the
 	// most efficient copy we could hope for.
@@ -225,19 +252,39 @@ static std::u8string format_value(const std::u8string& source)
 	formatted.reserve(source.size() + newline_count);
 	for (auto c : source) {
 		formatted.push_back(c);
-		if (c == '\n')
+		if (c == opt.tag_delimiter)
 			formatted.push_back(u8'\t');
 	}
 	return formatted;
 }
 
+/**
+ * Convert the comment from UTF-8 to the system encoding if relevant, and print it with a trailing
+ * line feed.
+ */
+static void puts_utf8(std::u8string_view str, FILE* output, const ot::options& opt)
+{
+	if (opt.raw) {
+		fwrite(str.data(), 1, str.size(), output);
+	} else {
+		try {
+			std::string local = ot::decode_utf8(str);
+			fwrite(local.data(), 1, local.size(), output);
+		} catch (ot::status& rc) {
+			rc.message += " See --raw.";
+			throw;
+		}
+	}
+	putc(opt.tag_delimiter, output);
+}
+
 /**
  * Print comments in a human readable format that can also be read back in by #read_comment.
  *
  * To disambiguate between a newline embedded in a comment and a newline representing the start of
  * the next tag, continuation lines always have a single TAB (^I) character added to the beginning.
  */
-void ot::print_comments(const std::list<std::u8string>& comments, FILE* output, bool raw)
+void ot::print_comments(const std::list<std::u8string>& comments, FILE* output, const ot::options& opt)
 {
 	bool has_control = false;
 	for (const std::u8string& source_comment : comments) {
@@ -249,27 +296,14 @@ void ot::print_comments(const std::list<std::u8string>& comments, FILE* output,
 				}
 			}
 		}
-
-		std::u8string utf8_comment = format_value(source_comment);
-		// Convert the comment from UTF-8 to the system encoding if relevant.
-		if (raw) {
-			fwrite(utf8_comment.data(), 1, utf8_comment.size(), output);
-		} else {
-			try {
-				std::string local = decode_utf8(utf8_comment);
-				fwrite(local.data(), 1, local.size(), output);
-			} catch (ot::status& rc) {
-				rc.message += " See --raw.";
-				throw;
-			}
-		}
-		putc('\n', output);
+		std::u8string utf8_comment = format_value(source_comment, opt);
+		puts_utf8(utf8_comment, output, opt);
 	}
 	if (has_control)
 		fputs("warning: Some tags contain control characters.\n", stderr);
 }
 
-std::list<std::u8string> ot::read_comments(FILE* input, bool raw)
+std::list<std::u8string> ot::read_comments(FILE* input, const ot::options& opt)
 {
 	std::list<std::u8string> comments;
 	comments.clear();
@@ -277,12 +311,12 @@ std::list<std::u8string> ot::read_comments(FILE* input, bool raw)
 	size_t buflen = 0;
 	ssize_t nread;
 	std::u8string* previous_comment = nullptr;
-	while ((nread = getline(&source_line, &buflen, input)) != -1) {
-		if (nread > 0 && source_line[nread - 1] == '\n')
+	while ((nread = getdelim(&source_line, &buflen, opt.tag_delimiter, input)) != -1) {
+		if (nread > 0 && source_line[nread - 1] == opt.tag_delimiter)
 			--nread; // Chomp.
 
 		std::u8string line;
-		if (raw) {
+		if (opt.raw) {
 			line = std::u8string(reinterpret_cast<char8_t*>(source_line), nread);
 		} else {
 			try {
@@ -306,7 +340,7 @@ std::list<std::u8string> ot::read_comments(FILE* input, bool raw)
 				free(source_line);
 				throw rc;
 			} else {
-				line[0] = '\n';
+				line[0] = opt.tag_delimiter;
 				previous_comment->append(line);
 			}
 		} else if (line.find(u8'=') == decltype(line)::npos) {
@@ -348,6 +382,9 @@ void ot::delete_comments(std::list<std::u8string>& comments, const std::u8string
 /** Apply the modifications requested by the user to the opustags packet. */
 static void edit_tags(ot::opus_tags& tags, const ot::options& opt)
 {
+	if (opt.set_vendor)
+		tags.vendor = *opt.set_vendor;
+
 	if (opt.delete_all) {
 		tags.comments.clear();
 	} else for (const std::u8string& name : opt.to_delete) {
@@ -359,7 +396,7 @@ static void edit_tags(ot::opus_tags& tags, const ot::options& opt)
 }
 
 /** Spawn VISUAL or EDITOR to edit the given tags. */
-static void edit_tags_interactively(ot::opus_tags& tags, const std::optional<std::string>& base_path, bool raw)
+static void edit_tags_interactively(ot::opus_tags& tags, const std::optional<std::string>& base_path, const ot::options& opt)
 {
 	const char* editor = nullptr;
 	if (getenv("TERM") != nullptr)
@@ -378,7 +415,7 @@ static void edit_tags_interactively(ot::opus_tags& tags, const std::optional<std
 	if (fd == -1 || (tags_file = fdopen(fd, "w")) == nullptr)
 		throw ot::status {ot::st::standard_error,
 		                  "Could not open '" + tags_path + "': " + strerror(errno)};
-	ot::print_comments(tags.comments, tags_file.get(), raw);
+	ot::print_comments(tags.comments, tags_file.get(), opt);
 	tags_file.reset();
 
 	// Spawn the editor, and watch the modification timestamps.
@@ -409,7 +446,7 @@ static void edit_tags_interactively(ot::opus_tags& tags, const std::optional<std
 	if (tags_file == nullptr)
 		throw ot::status {ot::st::standard_error, "Error opening " + tags_path + ": " + strerror(errno)};
 	try {
-		tags.comments = ot::read_comments(tags_file.get(), raw);
+		tags.comments = ot::read_comments(tags_file.get(), opt);
 	} catch (const ot::status& rc) {
 		fprintf(stderr, "warning: Leaving %s on the disk.\n", tags_path.c_str());
 		throw;
@@ -492,14 +529,18 @@ static void process(ot::ogg_reader& reader, ot::ogg_writer* writer, const ot::op
 			if (writer) {
 				if (opt.edit_interactively) {
 					fflush(writer->file); // flush before calling the subprocess
-					edit_tags_interactively(tags, writer->path, opt.raw);
+					edit_tags_interactively(tags, writer->path, opt);
 				}
 				auto packet = ot::render_tags(tags);
 				writer->write_header_packet(serialno, pageno, packet);
 				pageno_offset = writer->next_page_no - 1 - reader.absolute_page_no;
 			} else {
-				if (opt.cover_out != "-")
-					ot::print_comments(tags.comments, stdout, opt.raw);
+				if (opt.cover_out != "-") {
+					if (opt.print_vendor)
+						puts_utf8(tags.vendor, stdout, opt);
+					else
+						ot::print_comments(tags.comments, stdout, opt);
+				}
 				break;
 			}
 		} else if (writer) {
@@ -577,6 +618,10 @@ static void run_single(const ot::options& opt, const std::string& path_in, const
 	ot::ogg_writer writer(output);
 	writer.path = path_out;
 	process(reader, &writer, opt);
+
+	// Close the input file and finalize the output. When --in-place is specified, some file
+	// systems like SMB require that the input is closed first.
+	input.reset();
 	temporary_output.commit();
 }
 

src/opus.cc

@@ -3,7 +3,7 @@
  * \ingroup opus
  *
  * The way Opus is encapsulated into an Ogg stream, and the content of the packets we're dealing
- * with here is defined by [RFC 7584](https://tools.ietf.org/html/rfc7845.html).
+ * with here is defined by [RFC 7845](https://tools.ietf.org/html/rfc7845.html).
  *
  * Section 3 "Packet Organization" is critical for us:
  *
@@ -24,6 +24,7 @@
 #include <opustags.h>
 
 #include <string.h>
+#include <algorithm>
 
 ot::opus_tags ot::parse_tags(const ogg_packet& packet)
 {
@@ -54,7 +55,9 @@ ot::opus_tags ot::parse_tags(const ogg_packet& packet)
 	// Comment count
 	if (pos + 4 > size)
 		throw status {st::cut_comment_count, "Comment count did not fit the comment header"};
-	uint32_t count = le32toh(*((uint32_t*) (data + pos)));
+	uint32_t count;
+	memcpy(&count, data + pos, sizeof(count));
+	count = le32toh(count);
 	pos += 4;
 
 	// Comments' data
@@ -62,7 +65,9 @@ ot::opus_tags ot::parse_tags(const ogg_packet& packet)
 		if (pos + 4 > size)
 			throw status {st::cut_comment_length,
 			              "Comment length did not fit the comment header"};
-		uint32_t comment_length = le32toh(*((uint32_t*) (data + pos)));
+		uint32_t comment_length;
+		memcpy(&comment_length, data + pos, sizeof(comment_length));
+		comment_length = le32toh(comment_length);
 		if (pos + 4 + comment_length > size)
 			throw status {st::cut_comment_data,
 			              "Comment string did not fit the comment header"};
@@ -133,12 +138,16 @@ ot::picture::picture(ot::byte_string block)
 	size_t desc_offset = mime_offset + 4 + mime_size;
 	if (storage.size() < desc_offset + 4)
 		throw status { st::invalid_size, "missing description in picture block" };
-	uint32_t desc_size = be32toh(*reinterpret_cast<const uint32_t*>(&storage[desc_offset]));
+	uint32_t desc_size;
+	memcpy(&desc_size, &storage[desc_offset], sizeof(desc_size));
+	desc_size = be32toh(desc_size);
 
 	size_t pic_offset = desc_offset + 4 + desc_size + 16;
 	if (storage.size() < pic_offset + 4)
 		throw status { st::invalid_size, "missing picture data in picture block" };
-	uint32_t pic_size = be32toh(*reinterpret_cast<const uint32_t*>(&storage[pic_offset]));
+	uint32_t pic_size;
+	memcpy(&pic_size, &storage[pic_offset], sizeof(pic_size));
+	pic_size = be32toh(pic_size);
 
 	if (storage.size() != pic_offset + 4 + pic_size)
 		throw status { st::invalid_size, "invalid picture block size" };
@@ -156,7 +165,8 @@ ot::byte_string ot::picture::serialize() const
 	*reinterpret_cast<uint32_t*>(&bytes[0]) = htobe32(3); // Picture type: front cover.
 	*reinterpret_cast<uint32_t*>(&bytes[mime_offset]) = htobe32(mime_type.size());
 	std::copy(mime_type.begin(), mime_type.end(), std::next(bytes.begin(), mime_offset + 4));
-	*reinterpret_cast<uint32_t*>(&bytes[pic_offset]) = htobe32(picture_data.size());
+	uint32_t picture_data_size = htobe32(picture_data.size());
+	memcpy(&bytes[pic_offset], &picture_data_size, sizeof(picture_data_size));
 	std::copy(picture_data.begin(), picture_data.end(), std::next(bytes.begin(), pic_offset + 4));
 	return bytes;
 }

src/opustags.h

@@ -119,13 +119,16 @@ using byte_string_view = std::basic_string_view<uint8_t>;
  * \{
  */
 
+/** fclose wrapper for std::unique_ptr’s deleter. */
+void close_file(FILE*);
+
 /**
  * Smart auto-closing FILE* handle.
  *
  * It implictly converts from an already opened FILE*.
  */
-struct file : std::unique_ptr<FILE, decltype(&fclose)> {
-	file(FILE* f = nullptr) : std::unique_ptr<FILE, decltype(&fclose)>(f, &fclose) {}
+struct file : std::unique_ptr<FILE, decltype(&close_file)> {
+	file(FILE* f = nullptr) : std::unique_ptr<FILE, decltype(&close_file)>(f, &close_file) {}
 };
 
 /**
@@ -515,12 +518,32 @@ struct options {
 	 * Option: --output-cover
 	 */
 	std::optional<std::string> cover_out;
+	/**
+	 * Print the vendor string at the beginning of the OpusTags packet instead of printing the
+	 * tags. Only applicable in read-only mode.
+	 *
+	 * Option: --vendor
+	 */
+	bool print_vendor = false;
+	/**
+	 * Replace the vendor string by the one specified by the user.
+	 *
+	 * Option: --set-vendor
+	 */
+	std::optional<std::u8string> set_vendor;
 	/**
 	 * Disable encoding conversions. OpusTags are specified to always be encoded as UTF-8, but
 	 * if for some reason a specific file contains binary tags that someone would like to
 	 * extract and set as-is, encoding conversion would get in the way.
 	 */
 	bool raw = false;
+	/**
+	 * In text mode (default), tags are separated by a line feed. However, when combining
+	 * opustags with grep or other line-based tools, this proves to be a bad separator because
+	 * tag values may contain newlines. Changing the delimiter to '\0' with -z eases the
+	 * processing of multi-line tags with other tools that support null-terminated lines.
+	 */
+	char tag_delimiter = '\n';
 };
 
 /**
@@ -538,13 +561,13 @@ options parse_options(int argc, char** argv, FILE* comments);
  *
  * The output generated is meant to be parseable by #ot::read_comments.
  */
-void print_comments(const std::list<std::u8string>& comments, FILE* output, bool raw);
+void print_comments(const std::list<std::u8string>& comments, FILE* output, const options& opt);
 
 /**
  * Parse the comments outputted by #ot::print_comments. Unless raw is true, the comments are
  * converted from the system encoding to UTF-8, and returned as UTF-8.
  */
-std::list<std::u8string> read_comments(FILE* input, bool raw);
+std::list<std::u8string> read_comments(FILE* input, const options& opt);
 
 /**
  * Remove all comments matching the specified selector, which may either be a field name or a

src/system.cc

@@ -29,6 +29,11 @@ ot::byte_string_view operator""_bsv(const char* data, size_t size)
 	return ot::byte_string_view(reinterpret_cast<const uint8_t*>(data), size);
 }
 
+void ot::close_file(FILE* file)
+{
+	fclose(file);
+}
+
 void ot::partial_file::open(const char* destination)
 {
 	final_name = destination;
@@ -122,7 +127,7 @@ ot::byte_string ot::slurp_binary_file(const char* filename)
 
 	byte_string content;
 	long file_size = get_file_size(f.get());
-	if (file_size == -1) {
+	if (file_size < 0) {
 		// Read the input stream block by block and resize the output byte string as needed.
 		uint8_t buffer[4096];
 		while (!feof(f.get())) {
@@ -135,7 +140,7 @@ ot::byte_string ot::slurp_binary_file(const char* filename)
 	} else {
 		// Lucky! We know the file size, so let’s slurp it at once.
 		content.resize(file_size);
-		if (fread(content.data(), 1, file_size, f.get()) < file_size)
+		if (fread(content.data(), 1, file_size, f.get()) < size_t(file_size))
 			throw status { st::standard_error,
 				       "Could not read '"s + filename + "': " + strerror(errno) + "." };
 	}

t/cli.cc

@@ -5,8 +5,10 @@
 
 static ot::status read_comments(FILE* input, std::list<std::u8string>& comments, bool raw)
 {
+	ot::options opt;
+	opt.raw = raw;
 	try {
-		comments = ot::read_comments(input, raw);
+		comments = ot::read_comments(input, opt);
 	} catch (const ot::status& rc) {
 		return rc;
 	}
@@ -185,6 +187,8 @@ void check_bad_arguments()
 	            "Cannot specify standard output for both --output and --output-cover.", "-o and --output-cover conflict");
 	error_case({"opustags", "-i", "x", "y", "--output-cover", "z"},
 	            "Cannot use --output-cover with multiple input files.", "--output-cover with multiple input");
+	error_case({"opustags", "-i", "--vendor", "x"},
+	            "--vendor is only supported in read-only mode.", "--vendor when editing");
 	error_case({"opustags", "-d", "\xFF", "x"},
 	           "Could not encode argument into UTF-8:",
 	           "-d with binary data");

t/opustags.t

@@ -4,7 +4,8 @@ use strict;
 use warnings;
 use utf8;
 
-use Test::More tests => 59;
+use Test::More tests => 66;
+use Test::Deep qw(cmp_deeply re);
 
 use Digest::MD5;
 use File::Basename;
@@ -53,34 +54,9 @@ $help->[0] =~ /^([^\n]*+)/;
 my $version = $1;
 like($version, qr/^opustags version (\d+\.\d+\.\d+)/, 'get the version string');
 
-my $expected_help = <<"EOF";
-$version
-
-Usage: opustags --help
-       opustags [OPTIONS] FILE
-       opustags OPTIONS -i FILE...
-       opustags OPTIONS FILE -o FILE
-
-Options:
-  -h, --help                    print this help
-  -o, --output FILE             specify the output file
-  -i, --in-place                overwrite the input files
-  -y, --overwrite               overwrite the output file if it already exists
-  -a, --add FIELD=VALUE         add a comment
-  -d, --delete FIELD[=VALUE]    delete previously existing comments
-  -D, --delete-all              delete all the previously existing comments
-  -s, --set FIELD=VALUE         replace a comment
-  -S, --set-all                 import comments from standard input
-  -e, --edit                    edit tags interactively in VISUAL/EDITOR
-  --output-cover FILE           extract and save the cover art, if any
-  --set-cover FILE              sets the cover art
-  --raw                         disable encoding conversion
-
-See the man page for extensive documentation.
-EOF
-
-is_deeply(opustags('--help'), [$expected_help, '', 0], '--help displays the help message');
-is_deeply(opustags('-h'), [$expected_help, '', 0], '-h displays the help message too');
+my $expected_help = qr{opustags version .*\n\nUsage: opustags --help\n};
+cmp_deeply(opustags('--help'), [re($expected_help), '', 0], '--help displays the help message');
+cmp_deeply(opustags('-h'), [re($expected_help), '', 0], '-h displays the help message too');
 
 is_deeply(opustags('--derp'), ['', <<"EOF", 512], 'unrecognized option shows an error');
 error: Unrecognized option '--derp'.
@@ -342,3 +318,27 @@ unlink('out.png');
 is_deeply(opustags(qw(-D --set-cover - gobble.opus), { in => "GIF8 x" }), [<<'END_OUT', '', 0], 'read the cover from stdin');
 METADATA_BLOCK_PICTURE=AAAAAwAAAAlpbWFnZS9naWYAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAZHSUY4IHg=
 END_OUT
+
+####################################################################################################
+# Vendor string
+
+is_deeply(opustags(qw(--vendor gobble.opus)), ["Lavf58.12.100\n", '', 0], 'print the vendor string');
+
+is_deeply(opustags(qw(--set-vendor opustags gobble.opus -o out.opus)), ['', '', 0], 'set the vendor string');
+is_deeply(opustags(qw(--vendor out.opus)), ["opustags\n", '', 0], 'the vendor string was updated');
+unlink('out.opus');
+
+####################################################################################################
+# Multi-line tags
+
+is_deeply(opustags(qw(--set-all gobble.opus -o out.opus), { in => "MULTILINE=one\n\ttwo\nSIMPLE=three\n" }), ['', '', 0], 'parses continuation lines');
+is_deeply(opustags(qw(out.opus -z)), ["MULTILINE=one\ntwo\0SIMPLE=three\0", '', 0], 'delimits output with NUL on -z');
+unlink('out.opus');
+
+is_deeply(opustags(qw(--set-all gobble.opus -o out.opus -z), { in => "MULTILINE=one\ntwo\0SIMPLE=three\0" }), ['', '', 0], 'delimits input with NUL on -z');
+is_deeply(opustags(qw(out.opus)), [<<'END', '', 0], 'indents continuation lines');
+MULTILINE=one
+	two
+SIMPLE=three
+END
+unlink('out.opus');