std.tar: add support for file path in pax attributes#16990

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Vexu merged 1 commit into from
Sep 8, 2023
Merged

std.tar: add support for file path in pax attributes #16990

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
177 changes: 137 additions & 40 deletions lib/std/tar.zig
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -48,7 +48,7 @@ pub const Header = struct {
/// Return value may point into Header buffer, or might point into the
/// argument buffer.
/// TODO: check against "../" and other nefarious things
pub fn fullFileName(header: Header, buffer: *[255]u8) ![]const u8 {
pub fn fullFileName(header: Header, buffer: *[std.fs.MAX_PATH_BYTES]u8) ![]const u8 {
const n = name(header);
if (!is_ustar(header))
return n;
Expand DownExpand Up@@ -83,6 +83,44 @@ pub const Header = struct {
}
};

const Buffer = struct {
buffer: [512 * 8]u8 = undefined,
start: usize = 0,
end: usize = 0,

pub fn readChunk(b: *Buffer, reader: anytype, count: usize) ![]const u8 {
b.ensureCapacity(1024);

const ask = @min(b.buffer.len - b.end, count -| (b.end - b.start));
b.end += try reader.readAtLeast(b.buffer[b.end..], ask);

return b.buffer[b.start..b.end];
}

pub fn advance(b: *Buffer, count: usize) void {
b.start += count;
assert(b.start <= b.end);
}

pub fn skip(b: *Buffer, reader: anytype, count: usize) !void {
if (b.start + count > b.end) {
try reader.skipBytes(b.start + count - b.end, .{});
b.start = b.end;
} else {
b.advance(count);
}
}

inline fn ensureCapacity(b: *Buffer, count: usize) void {
if (b.buffer.len - b.start < count) {
const dest_end = b.end - b.start;
@memcpy(b.buffer[0..dest_end], b.buffer[b.start..b.end]);
b.end = dest_end;
b.start = 0;
}
}
};

pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !void {
switch (options.mode_mode) {
.ignore => {},
Expand All@@ -95,30 +133,27 @@ pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !voi
@panic("TODO: unimplemented: tar ModeMode.executable_bit_only");
},
}
var file_name_buffer: [255]u8 = undefined;
var buffer: [512 * 8]u8 = undefined;
var start: usize = 0;
var end: usize = 0;
var file_name_buffer: [std.fs.MAX_PATH_BYTES]u8 = undefined;
var file_name_override_len: usize = 0;
var buffer: Buffer = .{};
header: while (true) {
if (buffer.len - start < 1024) {
const dest_end = end - start;
@memcpy(buffer[0..dest_end], buffer[start..end]);
end = dest_end;
start = 0;
}
const ask_header = @min(buffer.len - end, 1024 -| (end - start));
end += try reader.readAtLeast(buffer[end..], ask_header);
switch (end - start) {
const chunk = try buffer.readChunk(reader, 1024);
switch (chunk.len) {
0 => return,
1...511 => return error.UnexpectedEndOfStream,
else => {},
}
const header: Header = .{ .bytes = buffer[start..][0..512] };
start += 512;
buffer.advance(512);

const header: Header = .{ .bytes = chunk[0..512] };
const file_size = try header.fileSize();
const rounded_file_size = std.mem.alignForward(u64, file_size, 512);
const pad_len = @as(usize, @intCast(rounded_file_size - file_size));
const unstripped_file_name = try header.fullFileName(&file_name_buffer);
const unstripped_file_name = if (file_name_override_len > 0)
file_name_buffer[0..file_name_override_len]
else
try header.fullFileName(&file_name_buffer);
file_name_override_len = 0;
switch (header.fileType()) {
.directory => {
const file_name = try stripComponents(unstripped_file_name, options.strip_components);
Expand All@@ -138,36 +173,59 @@ pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !voi

var file_off: usize = 0;
while (true) {
if (buffer.len - start < 1024) {
const dest_end = end - start;
@memcpy(buffer[0..dest_end], buffer[start..end]);
end = dest_end;
start = 0;
}
// Ask for the rounded up file size + 512 for the next header.
// TODO: https://github.com/ziglang/zig/issues/14039
const ask = @as(usize, @intCast(@min(
buffer.len - end,
rounded_file_size + 512 - file_off -| (end - start),
)));
end += try reader.readAtLeast(buffer[end..], ask);
if (end - start < ask) return error.UnexpectedEndOfStream;
// TODO: https://github.com/ziglang/zig/issues/14039
const slice = buffer[start..@as(usize, @intCast(@min(file_size - file_off + start, end)))];
const temp = try buffer.readChunk(reader, @intCast(rounded_file_size + 512 - file_off));
if (temp.len == 0) return error.UnexpectedEndOfStream;
const slice = temp[0..@as(usize, @intCast(@min(file_size - file_off, temp.len)))];
try file.writeAll(slice);

file_off += slice.len;
start += slice.len;
buffer.advance(slice.len);
if (file_off >= file_size) {
start += pad_len;
// Guaranteed since we use a buffer divisible by 512.
assert(start <= end);
buffer.advance(pad_len);
continue :header;
}
}
},
.global_extended_header, .extended_header => {
if (start + rounded_file_size > end) return error.TarHeadersTooBig;
start = @as(usize, @intCast(start + rounded_file_size));
.extended_header => {
if (file_size == 0) {
buffer.advance(@intCast(rounded_file_size));
continue;
}

const chunk_size: usize = @intCast(rounded_file_size + 512);
var data_off: usize = 0;
file_name_override_len = while (data_off < file_size) {
const slice = try buffer.readChunk(reader, chunk_size - data_off);
if (slice.len == 0) return error.UnexpectedEndOfStream;
const remaining_size: usize = @intCast(file_size - data_off);
const attr_info = try parsePaxAttribute(slice[0..@min(remaining_size, slice.len)], remaining_size);

if (std.mem.eql(u8, attr_info.key, "path")) {
if (attr_info.value_len > file_name_buffer.len) return error.NameTooLong;
buffer.advance(attr_info.value_off);
data_off += attr_info.value_off;
break attr_info.value_len;
}

try buffer.skip(reader, attr_info.size);
data_off += attr_info.size;
} else 0;

var i: usize = 0;
while (i < file_name_override_len) {
const slice = try buffer.readChunk(reader, chunk_size - data_off - i);
if (slice.len == 0) return error.UnexpectedEndOfStream;
const copy_size: usize = @intCast(@min(file_name_override_len - i, slice.len));
@memcpy(file_name_buffer[i .. i + copy_size], slice[0..copy_size]);
buffer.advance(copy_size);
i += copy_size;
}

try buffer.skip(reader, @intCast(rounded_file_size - data_off - file_name_override_len));
continue :header;
},
.global_extended_header => {
buffer.skip(reader, @intCast(rounded_file_size)) catch return error.TarHeadersTooBig;
},
.hard_link => return error.TarUnsupportedFileType,
.symbolic_link => return error.TarUnsupportedFileType,
Expand DownExpand Up@@ -196,5 +254,44 @@ test stripComponents {
try expectEqualStrings("c", try stripComponents("a/b/c", 2));
}

const PaxAttributeInfo = struct {
size: usize,
key: []const u8,
value_off: usize,
value_len: usize,
};

fn parsePaxAttribute(data: []const u8, max_size: usize) !PaxAttributeInfo {
const pos_space = std.mem.indexOfScalar(u8, data, ' ') orelse return error.InvalidPaxAttribute;
const pos_equals = std.mem.indexOfScalarPos(u8, data, pos_space, '=') orelse return error.InvalidPaxAttribute;
const kv_size = try std.fmt.parseInt(usize, data[0..pos_space], 10);
if (kv_size > max_size) {
return error.InvalidPaxAttribute;
}
return .{
.size = kv_size,
.key = data[pos_space + 1 .. pos_equals],
.value_off = pos_equals + 1,
.value_len = kv_size - pos_equals - 2,
};
}

test parsePaxAttribute {
const expectEqual = std.testing.expectEqual;
const expectEqualStrings = std.testing.expectEqualStrings;
const expectError = std.testing.expectError;
const prefix = "1011 path=";
const file_name = "0123456789" ** 100;
const header = prefix ++ file_name ++ "\n";
const attr_info = try parsePaxAttribute(header, 1011);
try expectEqual(@as(usize, 1011), attr_info.size);
try expectEqualStrings("path", attr_info.key);
try expectEqual(prefix.len, attr_info.value_off);
try expectEqual(file_name.len, attr_info.value_len);
try expectEqual(attr_info, try parsePaxAttribute(header, 1012));
try expectError(error.InvalidPaxAttribute, parsePaxAttribute(header, 1010));
try expectError(error.InvalidPaxAttribute, parsePaxAttribute("", 0));
}

const std = @import("std.zig");
const assert = std.debug.assert;
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
std.tar: add support for file path in pax attributes#16990

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

Vexu
merged 1 commit into

from

Sep 8, 2023
 Merged


std.tar: add support for file path in pax attributes
#16990
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


177 changes: 137 additions & 40 deletions
lib/std/tar.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -48,7 +48,7 @@ pub const Header = struct {
 /// Return value may point into Header buffer, or might point into the
 /// argument buffer.
 /// TODO: check against "../" and other nefarious things
 pub fn fullFileName(header: Header, buffer: *[255]u8) ![]const u8 {
 pub fn fullFileName(header: Header, buffer: *[std.fs.MAX_PATH_BYTES]u8) ![]const u8 {
 const n = name(header);
 if (!is_ustar(header))
 return n;
Expand DownExpand Up@@ -83,6 +83,44 @@ pub const Header = struct {
 }
};

const Buffer = struct {
 buffer: [512 * 8]u8 = undefined,
 start: usize = 0,
 end: usize = 0,

 pub fn readChunk(b: *Buffer, reader: anytype, count: usize) ![]const u8 {
 b.ensureCapacity(1024);

 const ask = @min(b.buffer.len - b.end, count -| (b.end - b.start));
 b.end += try reader.readAtLeast(b.buffer[b.end..], ask);

 return b.buffer[b.start..b.end];
 }

 pub fn advance(b: *Buffer, count: usize) void {
 b.start += count;
 assert(b.start <= b.end);
 }

 pub fn skip(b: *Buffer, reader: anytype, count: usize) !void {
 if (b.start + count > b.end) {
 try reader.skipBytes(b.start + count - b.end, .{});
 b.start = b.end;
 } else {
 b.advance(count);
 }
 }

 inline fn ensureCapacity(b: *Buffer, count: usize) void {
 if (b.buffer.len - b.start < count) {
 const dest_end = b.end - b.start;
 @memcpy(b.buffer[0..dest_end], b.buffer[b.start..b.end]);
 b.end = dest_end;
 b.start = 0;
 }
 }
};

pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !void {
 switch (options.mode_mode) {
 .ignore => {},
Expand All@@ -95,30 +133,27 @@ pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !voi
 @panic("TODO: unimplemented: tar ModeMode.executable_bit_only");
 },
 }
 var file_name_buffer: [255]u8 = undefined;
 var buffer: [512 * 8]u8 = undefined;
 var start: usize = 0;
 var end: usize = 0;
 var file_name_buffer: [std.fs.MAX_PATH_BYTES]u8 = undefined;
 var file_name_override_len: usize = 0;
 var buffer: Buffer = .{};
 header: while (true) {
 if (buffer.len - start < 1024) {
 const dest_end = end - start;
 @memcpy(buffer[0..dest_end], buffer[start..end]);
 end = dest_end;
 start = 0;
 }
 const ask_header = @min(buffer.len - end, 1024 -| (end - start));
 end += try reader.readAtLeast(buffer[end..], ask_header);
 switch (end - start) {
 const chunk = try buffer.readChunk(reader, 1024);
 switch (chunk.len) {
 0 => return,
 1...511 => return error.UnexpectedEndOfStream,
 else => {},
 }
 const header: Header = .{ .bytes = buffer[start..][0..512] };
 start += 512;
 buffer.advance(512);

 const header: Header = .{ .bytes = chunk[0..512] };
 const file_size = try header.fileSize();
 const rounded_file_size = std.mem.alignForward(u64, file_size, 512);
 const pad_len = @as(usize, @intCast(rounded_file_size - file_size));
 const unstripped_file_name = try header.fullFileName(&file_name_buffer);
 const unstripped_file_name = if (file_name_override_len > 0)
 file_name_buffer[0..file_name_override_len]
 else
 try header.fullFileName(&file_name_buffer);
 file_name_override_len = 0;
 switch (header.fileType()) {
 .directory => {
 const file_name = try stripComponents(unstripped_file_name, options.strip_components);
Expand All@@ -138,36 +173,59 @@ pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !voi

 var file_off: usize = 0;
 while (true) {
 if (buffer.len - start < 1024) {
 const dest_end = end - start;
 @memcpy(buffer[0..dest_end], buffer[start..end]);
 end = dest_end;
 start = 0;
 }
 // Ask for the rounded up file size + 512 for the next header.
 // TODO: https://github.com/ziglang/zig/issues/14039
 const ask = @as(usize, @intCast(@min(
 buffer.len - end,
 rounded_file_size + 512 - file_off -| (end - start),
 )));
 end += try reader.readAtLeast(buffer[end..], ask);
 if (end - start < ask) return error.UnexpectedEndOfStream;
 // TODO: https://github.com/ziglang/zig/issues/14039
 const slice = buffer[start..@as(usize, @intCast(@min(file_size - file_off + start, end)))];
 const temp = try buffer.readChunk(reader, @intCast(rounded_file_size + 512 - file_off));
 if (temp.len == 0) return error.UnexpectedEndOfStream;
 const slice = temp[0..@as(usize, @intCast(@min(file_size - file_off, temp.len)))];
 try file.writeAll(slice);

 file_off += slice.len;
start += slice.len;
buffer.advance(slice.len);
 if (file_off >= file_size) {
 start += pad_len;
 // Guaranteed since we use a buffer divisible by 512.
 assert(start <= end);
 buffer.advance(pad_len);
 continue :header;
 }
 }
 },
 .global_extended_header, .extended_header => {
 if (start + rounded_file_size > end) return error.TarHeadersTooBig;
 start = @as(usize, @intCast(start + rounded_file_size));
 .extended_header => {
 if (file_size == 0) {
 buffer.advance(@intCast(rounded_file_size));
 continue;
 }

 const chunk_size: usize = @intCast(rounded_file_size + 512);
 var data_off: usize = 0;
 file_name_override_len = while (data_off < file_size) {
 const slice = try buffer.readChunk(reader, chunk_size - data_off);
 if (slice.len == 0) return error.UnexpectedEndOfStream;
 const remaining_size: usize = @intCast(file_size - data_off);
 const attr_info = try parsePaxAttribute(slice[0..@min(remaining_size, slice.len)], remaining_size);

 if (std.mem.eql(u8, attr_info.key, "path")) {
 if (attr_info.value_len > file_name_buffer.len) return error.NameTooLong;
 buffer.advance(attr_info.value_off);
 data_off += attr_info.value_off;
 break attr_info.value_len;
 }

 try buffer.skip(reader, attr_info.size);
 data_off += attr_info.size;
 } else 0;

 var i: usize = 0;
 while (i < file_name_override_len) {
 const slice = try buffer.readChunk(reader, chunk_size - data_off - i);
 if (slice.len == 0) return error.UnexpectedEndOfStream;
 const copy_size: usize = @intCast(@min(file_name_override_len - i, slice.len));
 @memcpy(file_name_buffer[i .. i + copy_size], slice[0..copy_size]);
 buffer.advance(copy_size);
 i += copy_size;
 }

 try buffer.skip(reader, @intCast(rounded_file_size - data_off - file_name_override_len));
 continue :header;
 },
 .global_extended_header => {
 buffer.skip(reader, @intCast(rounded_file_size)) catch return error.TarHeadersTooBig;
 },
 .hard_link => return error.TarUnsupportedFileType,
 .symbolic_link => return error.TarUnsupportedFileType,
Expand DownExpand Up@@ -196,5 +254,44 @@ test stripComponents {
 try expectEqualStrings("c", try stripComponents("a/b/c", 2));
}

const PaxAttributeInfo = struct {
 size: usize,
 key: []const u8,
 value_off: usize,
 value_len: usize,
};

fn parsePaxAttribute(data: []const u8, max_size: usize) !PaxAttributeInfo {
 const pos_space = std.mem.indexOfScalar(u8, data, ' ') orelse return error.InvalidPaxAttribute;
 const pos_equals = std.mem.indexOfScalarPos(u8, data, pos_space, '=') orelse return error.InvalidPaxAttribute;
 const kv_size = try std.fmt.parseInt(usize, data[0..pos_space], 10);
 if (kv_size > max_size) {
 return error.InvalidPaxAttribute;
 }
 return .{
 .size = kv_size,
 .key = data[pos_space + 1 .. pos_equals],
 .value_off = pos_equals + 1,
 .value_len = kv_size - pos_equals - 2,
 };
}

test parsePaxAttribute {
 const expectEqual = std.testing.expectEqual;
 const expectEqualStrings = std.testing.expectEqualStrings;
 const expectError = std.testing.expectError;
 const prefix = "1011 path=";
 const file_name = "0123456789" ** 100;
 const header = prefix ++ file_name ++ "\n";
 const attr_info = try parsePaxAttribute(header, 1011);
 try expectEqual(@as(usize, 1011), attr_info.size);
 try expectEqualStrings("path", attr_info.key);
 try expectEqual(prefix.len, attr_info.value_off);
 try expectEqual(file_name.len, attr_info.value_len);
 try expectEqual(attr_info, try parsePaxAttribute(header, 1012));
 try expectError(error.InvalidPaxAttribute, parsePaxAttribute(header, 1010));
 try expectError(error.InvalidPaxAttribute, parsePaxAttribute("", 0));
}

const std = @import("std.zig");
const assert = std.debug.assert;

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
std.tar: add support for file path in pax attributes#16990

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

Vexu
merged 1 commit into

from

Sep 8, 2023
 Merged


std.tar: add support for file path in pax attributes
#16990
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


177 changes: 137 additions & 40 deletions
lib/std/tar.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -48,7 +48,7 @@ pub const Header = struct {
 /// Return value may point into Header buffer, or might point into the
 /// argument buffer.
 /// TODO: check against "../" and other nefarious things
 pub fn fullFileName(header: Header, buffer: *[255]u8) ![]const u8 {
 pub fn fullFileName(header: Header, buffer: *[std.fs.MAX_PATH_BYTES]u8) ![]const u8 {
 const n = name(header);
 if (!is_ustar(header))
 return n;
Expand DownExpand Up@@ -83,6 +83,44 @@ pub const Header = struct {
 }
};

const Buffer = struct {
 buffer: [512 * 8]u8 = undefined,
 start: usize = 0,
 end: usize = 0,

 pub fn readChunk(b: *Buffer, reader: anytype, count: usize) ![]const u8 {
 b.ensureCapacity(1024);

 const ask = @min(b.buffer.len - b.end, count -| (b.end - b.start));
 b.end += try reader.readAtLeast(b.buffer[b.end..], ask);

 return b.buffer[b.start..b.end];
 }

 pub fn advance(b: *Buffer, count: usize) void {
 b.start += count;
 assert(b.start <= b.end);
 }

 pub fn skip(b: *Buffer, reader: anytype, count: usize) !void {
 if (b.start + count > b.end) {
 try reader.skipBytes(b.start + count - b.end, .{});
 b.start = b.end;
 } else {
 b.advance(count);
 }
 }

 inline fn ensureCapacity(b: *Buffer, count: usize) void {
 if (b.buffer.len - b.start < count) {
 const dest_end = b.end - b.start;
 @memcpy(b.buffer[0..dest_end], b.buffer[b.start..b.end]);
 b.end = dest_end;
 b.start = 0;
 }
 }
};

pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !void {
 switch (options.mode_mode) {
 .ignore => {},
Expand All@@ -95,30 +133,27 @@ pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !voi
 @panic("TODO: unimplemented: tar ModeMode.executable_bit_only");
 },
 }
 var file_name_buffer: [255]u8 = undefined;
 var buffer: [512 * 8]u8 = undefined;
 var start: usize = 0;
 var end: usize = 0;
 var file_name_buffer: [std.fs.MAX_PATH_BYTES]u8 = undefined;
 var file_name_override_len: usize = 0;
 var buffer: Buffer = .{};
 header: while (true) {
 if (buffer.len - start < 1024) {
 const dest_end = end - start;
 @memcpy(buffer[0..dest_end], buffer[start..end]);
 end = dest_end;
 start = 0;
 }
 const ask_header = @min(buffer.len - end, 1024 -| (end - start));
 end += try reader.readAtLeast(buffer[end..], ask_header);
 switch (end - start) {
 const chunk = try buffer.readChunk(reader, 1024);
 switch (chunk.len) {
 0 => return,
 1...511 => return error.UnexpectedEndOfStream,
 else => {},
 }
 const header: Header = .{ .bytes = buffer[start..][0..512] };
 start += 512;
 buffer.advance(512);

 const header: Header = .{ .bytes = chunk[0..512] };
 const file_size = try header.fileSize();
 const rounded_file_size = std.mem.alignForward(u64, file_size, 512);
 const pad_len = @as(usize, @intCast(rounded_file_size - file_size));
 const unstripped_file_name = try header.fullFileName(&file_name_buffer);
 const unstripped_file_name = if (file_name_override_len > 0)
 file_name_buffer[0..file_name_override_len]
 else
 try header.fullFileName(&file_name_buffer);
 file_name_override_len = 0;
 switch (header.fileType()) {
 .directory => {
 const file_name = try stripComponents(unstripped_file_name, options.strip_components);
Expand All@@ -138,36 +173,59 @@ pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !voi

 var file_off: usize = 0;
 while (true) {
 if (buffer.len - start < 1024) {
 const dest_end = end - start;
 @memcpy(buffer[0..dest_end], buffer[start..end]);
 end = dest_end;
 start = 0;
 }
 // Ask for the rounded up file size + 512 for the next header.
 // TODO: https://github.com/ziglang/zig/issues/14039
 const ask = @as(usize, @intCast(@min(
 buffer.len - end,
 rounded_file_size + 512 - file_off -| (end - start),
 )));
 end += try reader.readAtLeast(buffer[end..], ask);
 if (end - start < ask) return error.UnexpectedEndOfStream;
 // TODO: https://github.com/ziglang/zig/issues/14039
 const slice = buffer[start..@as(usize, @intCast(@min(file_size - file_off + start, end)))];
 const temp = try buffer.readChunk(reader, @intCast(rounded_file_size + 512 - file_off));
 if (temp.len == 0) return error.UnexpectedEndOfStream;
 const slice = temp[0..@as(usize, @intCast(@min(file_size - file_off, temp.len)))];
 try file.writeAll(slice);

 file_off += slice.len;
start += slice.len;
buffer.advance(slice.len);
 if (file_off >= file_size) {
 start += pad_len;
 // Guaranteed since we use a buffer divisible by 512.
 assert(start <= end);
 buffer.advance(pad_len);
 continue :header;
 }
 }
 },
 .global_extended_header, .extended_header => {
 if (start + rounded_file_size > end) return error.TarHeadersTooBig;
 start = @as(usize, @intCast(start + rounded_file_size));
 .extended_header => {
 if (file_size == 0) {
 buffer.advance(@intCast(rounded_file_size));
 continue;
 }

 const chunk_size: usize = @intCast(rounded_file_size + 512);
 var data_off: usize = 0;
 file_name_override_len = while (data_off < file_size) {
 const slice = try buffer.readChunk(reader, chunk_size - data_off);
 if (slice.len == 0) return error.UnexpectedEndOfStream;
 const remaining_size: usize = @intCast(file_size - data_off);
 const attr_info = try parsePaxAttribute(slice[0..@min(remaining_size, slice.len)], remaining_size);

 if (std.mem.eql(u8, attr_info.key, "path")) {
 if (attr_info.value_len > file_name_buffer.len) return error.NameTooLong;
 buffer.advance(attr_info.value_off);
 data_off += attr_info.value_off;
 break attr_info.value_len;
 }

 try buffer.skip(reader, attr_info.size);
 data_off += attr_info.size;
 } else 0;

 var i: usize = 0;
 while (i < file_name_override_len) {
 const slice = try buffer.readChunk(reader, chunk_size - data_off - i);
 if (slice.len == 0) return error.UnexpectedEndOfStream;
 const copy_size: usize = @intCast(@min(file_name_override_len - i, slice.len));
 @memcpy(file_name_buffer[i .. i + copy_size], slice[0..copy_size]);
 buffer.advance(copy_size);
 i += copy_size;
 }

 try buffer.skip(reader, @intCast(rounded_file_size - data_off - file_name_override_len));
 continue :header;
 },
 .global_extended_header => {
 buffer.skip(reader, @intCast(rounded_file_size)) catch return error.TarHeadersTooBig;
 },
 .hard_link => return error.TarUnsupportedFileType,
 .symbolic_link => return error.TarUnsupportedFileType,
Expand DownExpand Up@@ -196,5 +254,44 @@ test stripComponents {
 try expectEqualStrings("c", try stripComponents("a/b/c", 2));
}

const PaxAttributeInfo = struct {
 size: usize,
 key: []const u8,
 value_off: usize,
 value_len: usize,
};

fn parsePaxAttribute(data: []const u8, max_size: usize) !PaxAttributeInfo {
 const pos_space = std.mem.indexOfScalar(u8, data, ' ') orelse return error.InvalidPaxAttribute;
 const pos_equals = std.mem.indexOfScalarPos(u8, data, pos_space, '=') orelse return error.InvalidPaxAttribute;
 const kv_size = try std.fmt.parseInt(usize, data[0..pos_space], 10);
 if (kv_size > max_size) {
 return error.InvalidPaxAttribute;
 }
 return .{
 .size = kv_size,
 .key = data[pos_space + 1 .. pos_equals],
 .value_off = pos_equals + 1,
 .value_len = kv_size - pos_equals - 2,
 };
}

test parsePaxAttribute {
 const expectEqual = std.testing.expectEqual;
 const expectEqualStrings = std.testing.expectEqualStrings;
 const expectError = std.testing.expectError;
 const prefix = "1011 path=";
 const file_name = "0123456789" ** 100;
 const header = prefix ++ file_name ++ "\n";
 const attr_info = try parsePaxAttribute(header, 1011);
 try expectEqual(@as(usize, 1011), attr_info.size);
 try expectEqualStrings("path", attr_info.key);
 try expectEqual(prefix.len, attr_info.value_off);
 try expectEqual(file_name.len, attr_info.value_len);
 try expectEqual(attr_info, try parsePaxAttribute(header, 1012));
 try expectError(error.InvalidPaxAttribute, parsePaxAttribute(header, 1010));
 try expectError(error.InvalidPaxAttribute, parsePaxAttribute("", 0));
}

const std = @import("std.zig");
const assert = std.debug.assert;

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
std.tar: add support for file path in pax attributes#16990

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

Vexu
merged 1 commit into

from

Sep 8, 2023
 Merged


std.tar: add support for file path in pax attributes
#16990
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


177 changes: 137 additions & 40 deletions
lib/std/tar.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -48,7 +48,7 @@ pub const Header = struct {
 /// Return value may point into Header buffer, or might point into the
 /// argument buffer.
 /// TODO: check against "../" and other nefarious things
 pub fn fullFileName(header: Header, buffer: *[255]u8) ![]const u8 {
 pub fn fullFileName(header: Header, buffer: *[std.fs.MAX_PATH_BYTES]u8) ![]const u8 {
 const n = name(header);
 if (!is_ustar(header))
 return n;
Expand DownExpand Up@@ -83,6 +83,44 @@ pub const Header = struct {
 }
};

const Buffer = struct {
 buffer: [512 * 8]u8 = undefined,
 start: usize = 0,
 end: usize = 0,

 pub fn readChunk(b: *Buffer, reader: anytype, count: usize) ![]const u8 {
 b.ensureCapacity(1024);

 const ask = @min(b.buffer.len - b.end, count -| (b.end - b.start));
 b.end += try reader.readAtLeast(b.buffer[b.end..], ask);

 return b.buffer[b.start..b.end];
 }

 pub fn advance(b: *Buffer, count: usize) void {
 b.start += count;
 assert(b.start <= b.end);
 }

 pub fn skip(b: *Buffer, reader: anytype, count: usize) !void {
 if (b.start + count > b.end) {
 try reader.skipBytes(b.start + count - b.end, .{});
 b.start = b.end;
 } else {
 b.advance(count);
 }
 }

 inline fn ensureCapacity(b: *Buffer, count: usize) void {
 if (b.buffer.len - b.start < count) {
 const dest_end = b.end - b.start;
 @memcpy(b.buffer[0..dest_end], b.buffer[b.start..b.end]);
 b.end = dest_end;
 b.start = 0;
 }
 }
};

pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !void {
 switch (options.mode_mode) {
 .ignore => {},
Expand All@@ -95,30 +133,27 @@ pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !voi
 @panic("TODO: unimplemented: tar ModeMode.executable_bit_only");
 },
 }
 var file_name_buffer: [255]u8 = undefined;
 var buffer: [512 * 8]u8 = undefined;
 var start: usize = 0;
 var end: usize = 0;
 var file_name_buffer: [std.fs.MAX_PATH_BYTES]u8 = undefined;
 var file_name_override_len: usize = 0;
 var buffer: Buffer = .{};
 header: while (true) {
 if (buffer.len - start < 1024) {
 const dest_end = end - start;
 @memcpy(buffer[0..dest_end], buffer[start..end]);
 end = dest_end;
 start = 0;
 }
 const ask_header = @min(buffer.len - end, 1024 -| (end - start));
 end += try reader.readAtLeast(buffer[end..], ask_header);
 switch (end - start) {
 const chunk = try buffer.readChunk(reader, 1024);
 switch (chunk.len) {
 0 => return,
 1...511 => return error.UnexpectedEndOfStream,
 else => {},
 }
 const header: Header = .{ .bytes = buffer[start..][0..512] };
 start += 512;
 buffer.advance(512);

 const header: Header = .{ .bytes = chunk[0..512] };
 const file_size = try header.fileSize();
 const rounded_file_size = std.mem.alignForward(u64, file_size, 512);
 const pad_len = @as(usize, @intCast(rounded_file_size - file_size));
 const unstripped_file_name = try header.fullFileName(&file_name_buffer);
 const unstripped_file_name = if (file_name_override_len > 0)
 file_name_buffer[0..file_name_override_len]
 else
 try header.fullFileName(&file_name_buffer);
 file_name_override_len = 0;
 switch (header.fileType()) {
 .directory => {
 const file_name = try stripComponents(unstripped_file_name, options.strip_components);
Expand All@@ -138,36 +173,59 @@ pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !voi

 var file_off: usize = 0;
 while (true) {
 if (buffer.len - start < 1024) {
 const dest_end = end - start;
 @memcpy(buffer[0..dest_end], buffer[start..end]);
 end = dest_end;
 start = 0;
 }
 // Ask for the rounded up file size + 512 for the next header.
 // TODO: https://github.com/ziglang/zig/issues/14039
 const ask = @as(usize, @intCast(@min(
 buffer.len - end,
 rounded_file_size + 512 - file_off -| (end - start),
 )));
 end += try reader.readAtLeast(buffer[end..], ask);
 if (end - start < ask) return error.UnexpectedEndOfStream;
 // TODO: https://github.com/ziglang/zig/issues/14039
 const slice = buffer[start..@as(usize, @intCast(@min(file_size - file_off + start, end)))];
 const temp = try buffer.readChunk(reader, @intCast(rounded_file_size + 512 - file_off));
 if (temp.len == 0) return error.UnexpectedEndOfStream;
 const slice = temp[0..@as(usize, @intCast(@min(file_size - file_off, temp.len)))];
 try file.writeAll(slice);

 file_off += slice.len;
start += slice.len;
buffer.advance(slice.len);
 if (file_off >= file_size) {
 start += pad_len;
 // Guaranteed since we use a buffer divisible by 512.
 assert(start <= end);
 buffer.advance(pad_len);
 continue :header;
 }
 }
 },
 .global_extended_header, .extended_header => {
 if (start + rounded_file_size > end) return error.TarHeadersTooBig;
 start = @as(usize, @intCast(start + rounded_file_size));
 .extended_header => {
 if (file_size == 0) {
 buffer.advance(@intCast(rounded_file_size));
 continue;
 }

 const chunk_size: usize = @intCast(rounded_file_size + 512);
 var data_off: usize = 0;
 file_name_override_len = while (data_off < file_size) {
 const slice = try buffer.readChunk(reader, chunk_size - data_off);
 if (slice.len == 0) return error.UnexpectedEndOfStream;
 const remaining_size: usize = @intCast(file_size - data_off);
 const attr_info = try parsePaxAttribute(slice[0..@min(remaining_size, slice.len)], remaining_size);

 if (std.mem.eql(u8, attr_info.key, "path")) {
 if (attr_info.value_len > file_name_buffer.len) return error.NameTooLong;
 buffer.advance(attr_info.value_off);
 data_off += attr_info.value_off;
 break attr_info.value_len;
 }

 try buffer.skip(reader, attr_info.size);
 data_off += attr_info.size;
 } else 0;

 var i: usize = 0;
 while (i < file_name_override_len) {
 const slice = try buffer.readChunk(reader, chunk_size - data_off - i);
 if (slice.len == 0) return error.UnexpectedEndOfStream;
 const copy_size: usize = @intCast(@min(file_name_override_len - i, slice.len));
 @memcpy(file_name_buffer[i .. i + copy_size], slice[0..copy_size]);
 buffer.advance(copy_size);
 i += copy_size;
 }

 try buffer.skip(reader, @intCast(rounded_file_size - data_off - file_name_override_len));
 continue :header;
 },
 .global_extended_header => {
 buffer.skip(reader, @intCast(rounded_file_size)) catch return error.TarHeadersTooBig;
 },
 .hard_link => return error.TarUnsupportedFileType,
 .symbolic_link => return error.TarUnsupportedFileType,
Expand DownExpand Up@@ -196,5 +254,44 @@ test stripComponents {
 try expectEqualStrings("c", try stripComponents("a/b/c", 2));
}

const PaxAttributeInfo = struct {
 size: usize,
 key: []const u8,
 value_off: usize,
 value_len: usize,
};

fn parsePaxAttribute(data: []const u8, max_size: usize) !PaxAttributeInfo {
 const pos_space = std.mem.indexOfScalar(u8, data, ' ') orelse return error.InvalidPaxAttribute;
 const pos_equals = std.mem.indexOfScalarPos(u8, data, pos_space, '=') orelse return error.InvalidPaxAttribute;
 const kv_size = try std.fmt.parseInt(usize, data[0..pos_space], 10);
 if (kv_size > max_size) {
 return error.InvalidPaxAttribute;
 }
 return .{
 .size = kv_size,
 .key = data[pos_space + 1 .. pos_equals],
 .value_off = pos_equals + 1,
 .value_len = kv_size - pos_equals - 2,
 };
}

test parsePaxAttribute {
 const expectEqual = std.testing.expectEqual;
 const expectEqualStrings = std.testing.expectEqualStrings;
 const expectError = std.testing.expectError;
 const prefix = "1011 path=";
 const file_name = "0123456789" ** 100;
 const header = prefix ++ file_name ++ "\n";
 const attr_info = try parsePaxAttribute(header, 1011);
 try expectEqual(@as(usize, 1011), attr_info.size);
 try expectEqualStrings("path", attr_info.key);
 try expectEqual(prefix.len, attr_info.value_off);
 try expectEqual(file_name.len, attr_info.value_len);
 try expectEqual(attr_info, try parsePaxAttribute(header, 1012));
 try expectError(error.InvalidPaxAttribute, parsePaxAttribute(header, 1010));
 try expectError(error.InvalidPaxAttribute, parsePaxAttribute("", 0));
}

const std = @import("std.zig");
const assert = std.debug.assert;

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
std.tar: add support for file path in pax attributes#16990

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

Vexu
merged 1 commit into

from

Sep 8, 2023
 Merged


std.tar: add support for file path in pax attributes
#16990
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


177 changes: 137 additions & 40 deletions
lib/std/tar.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -48,7 +48,7 @@ pub const Header = struct {
 /// Return value may point into Header buffer, or might point into the
 /// argument buffer.
 /// TODO: check against "../" and other nefarious things
 pub fn fullFileName(header: Header, buffer: *[255]u8) ![]const u8 {
 pub fn fullFileName(header: Header, buffer: *[std.fs.MAX_PATH_BYTES]u8) ![]const u8 {
 const n = name(header);
 if (!is_ustar(header))
 return n;
Expand DownExpand Up@@ -83,6 +83,44 @@ pub const Header = struct {
 }
};

const Buffer = struct {
 buffer: [512 * 8]u8 = undefined,
 start: usize = 0,
 end: usize = 0,

 pub fn readChunk(b: *Buffer, reader: anytype, count: usize) ![]const u8 {
 b.ensureCapacity(1024);

 const ask = @min(b.buffer.len - b.end, count -| (b.end - b.start));
 b.end += try reader.readAtLeast(b.buffer[b.end..], ask);

 return b.buffer[b.start..b.end];
 }

 pub fn advance(b: *Buffer, count: usize) void {
 b.start += count;
 assert(b.start <= b.end);
 }

 pub fn skip(b: *Buffer, reader: anytype, count: usize) !void {
 if (b.start + count > b.end) {
 try reader.skipBytes(b.start + count - b.end, .{});
 b.start = b.end;
 } else {
 b.advance(count);
 }
 }

 inline fn ensureCapacity(b: *Buffer, count: usize) void {
 if (b.buffer.len - b.start < count) {
 const dest_end = b.end - b.start;
 @memcpy(b.buffer[0..dest_end], b.buffer[b.start..b.end]);
 b.end = dest_end;
 b.start = 0;
 }
 }
};

pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !void {
 switch (options.mode_mode) {
 .ignore => {},
Expand All@@ -95,30 +133,27 @@ pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !voi
 @panic("TODO: unimplemented: tar ModeMode.executable_bit_only");
 },
 }
 var file_name_buffer: [255]u8 = undefined;
 var buffer: [512 * 8]u8 = undefined;
 var start: usize = 0;
 var end: usize = 0;
 var file_name_buffer: [std.fs.MAX_PATH_BYTES]u8 = undefined;
 var file_name_override_len: usize = 0;
 var buffer: Buffer = .{};
 header: while (true) {
 if (buffer.len - start < 1024) {
 const dest_end = end - start;
 @memcpy(buffer[0..dest_end], buffer[start..end]);
 end = dest_end;
 start = 0;
 }
 const ask_header = @min(buffer.len - end, 1024 -| (end - start));
 end += try reader.readAtLeast(buffer[end..], ask_header);
 switch (end - start) {
 const chunk = try buffer.readChunk(reader, 1024);
 switch (chunk.len) {
 0 => return,
 1...511 => return error.UnexpectedEndOfStream,
 else => {},
 }
 const header: Header = .{ .bytes = buffer[start..][0..512] };
 start += 512;
 buffer.advance(512);

 const header: Header = .{ .bytes = chunk[0..512] };
 const file_size = try header.fileSize();
 const rounded_file_size = std.mem.alignForward(u64, file_size, 512);
 const pad_len = @as(usize, @intCast(rounded_file_size - file_size));
 const unstripped_file_name = try header.fullFileName(&file_name_buffer);
 const unstripped_file_name = if (file_name_override_len > 0)
 file_name_buffer[0..file_name_override_len]
 else
 try header.fullFileName(&file_name_buffer);
 file_name_override_len = 0;
 switch (header.fileType()) {
 .directory => {
 const file_name = try stripComponents(unstripped_file_name, options.strip_components);
Expand All@@ -138,36 +173,59 @@ pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !voi

 var file_off: usize = 0;
 while (true) {
 if (buffer.len - start < 1024) {
 const dest_end = end - start;
 @memcpy(buffer[0..dest_end], buffer[start..end]);
 end = dest_end;
 start = 0;
 }
 // Ask for the rounded up file size + 512 for the next header.
 // TODO: https://github.com/ziglang/zig/issues/14039
 const ask = @as(usize, @intCast(@min(
 buffer.len - end,
 rounded_file_size + 512 - file_off -| (end - start),
 )));
 end += try reader.readAtLeast(buffer[end..], ask);
 if (end - start < ask) return error.UnexpectedEndOfStream;
 // TODO: https://github.com/ziglang/zig/issues/14039
 const slice = buffer[start..@as(usize, @intCast(@min(file_size - file_off + start, end)))];
 const temp = try buffer.readChunk(reader, @intCast(rounded_file_size + 512 - file_off));
 if (temp.len == 0) return error.UnexpectedEndOfStream;
 const slice = temp[0..@as(usize, @intCast(@min(file_size - file_off, temp.len)))];
 try file.writeAll(slice);

 file_off += slice.len;
start += slice.len;
buffer.advance(slice.len);
 if (file_off >= file_size) {
 start += pad_len;
 // Guaranteed since we use a buffer divisible by 512.
 assert(start <= end);
 buffer.advance(pad_len);
 continue :header;
 }
 }
 },
 .global_extended_header, .extended_header => {
 if (start + rounded_file_size > end) return error.TarHeadersTooBig;
 start = @as(usize, @intCast(start + rounded_file_size));
 .extended_header => {
 if (file_size == 0) {
 buffer.advance(@intCast(rounded_file_size));
 continue;
 }

 const chunk_size: usize = @intCast(rounded_file_size + 512);
 var data_off: usize = 0;
 file_name_override_len = while (data_off < file_size) {
 const slice = try buffer.readChunk(reader, chunk_size - data_off);
 if (slice.len == 0) return error.UnexpectedEndOfStream;
 const remaining_size: usize = @intCast(file_size - data_off);
 const attr_info = try parsePaxAttribute(slice[0..@min(remaining_size, slice.len)], remaining_size);

 if (std.mem.eql(u8, attr_info.key, "path")) {
 if (attr_info.value_len > file_name_buffer.len) return error.NameTooLong;
 buffer.advance(attr_info.value_off);
 data_off += attr_info.value_off;
 break attr_info.value_len;
 }

 try buffer.skip(reader, attr_info.size);
 data_off += attr_info.size;
 } else 0;

 var i: usize = 0;
 while (i < file_name_override_len) {
 const slice = try buffer.readChunk(reader, chunk_size - data_off - i);
 if (slice.len == 0) return error.UnexpectedEndOfStream;
 const copy_size: usize = @intCast(@min(file_name_override_len - i, slice.len));
 @memcpy(file_name_buffer[i .. i + copy_size], slice[0..copy_size]);
 buffer.advance(copy_size);
 i += copy_size;
 }

 try buffer.skip(reader, @intCast(rounded_file_size - data_off - file_name_override_len));
 continue :header;
 },
 .global_extended_header => {
 buffer.skip(reader, @intCast(rounded_file_size)) catch return error.TarHeadersTooBig;
 },
 .hard_link => return error.TarUnsupportedFileType,
 .symbolic_link => return error.TarUnsupportedFileType,
Expand DownExpand Up@@ -196,5 +254,44 @@ test stripComponents {
 try expectEqualStrings("c", try stripComponents("a/b/c", 2));
}

const PaxAttributeInfo = struct {
 size: usize,
 key: []const u8,
 value_off: usize,
 value_len: usize,
};

fn parsePaxAttribute(data: []const u8, max_size: usize) !PaxAttributeInfo {
 const pos_space = std.mem.indexOfScalar(u8, data, ' ') orelse return error.InvalidPaxAttribute;
 const pos_equals = std.mem.indexOfScalarPos(u8, data, pos_space, '=') orelse return error.InvalidPaxAttribute;
 const kv_size = try std.fmt.parseInt(usize, data[0..pos_space], 10);
 if (kv_size > max_size) {
 return error.InvalidPaxAttribute;
 }
 return .{
 .size = kv_size,
 .key = data[pos_space + 1 .. pos_equals],
 .value_off = pos_equals + 1,
 .value_len = kv_size - pos_equals - 2,
 };
}

test parsePaxAttribute {
 const expectEqual = std.testing.expectEqual;
 const expectEqualStrings = std.testing.expectEqualStrings;
 const expectError = std.testing.expectError;
 const prefix = "1011 path=";
 const file_name = "0123456789" ** 100;
 const header = prefix ++ file_name ++ "\n";
 const attr_info = try parsePaxAttribute(header, 1011);
 try expectEqual(@as(usize, 1011), attr_info.size);
 try expectEqualStrings("path", attr_info.key);
 try expectEqual(prefix.len, attr_info.value_off);
 try expectEqual(file_name.len, attr_info.value_len);
 try expectEqual(attr_info, try parsePaxAttribute(header, 1012));
 try expectError(error.InvalidPaxAttribute, parsePaxAttribute(header, 1010));
 try expectError(error.InvalidPaxAttribute, parsePaxAttribute("", 0));
}

const std = @import("std.zig");
const assert = std.debug.assert;

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
std.tar: add support for file path in pax attributes#16990

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

Vexu
merged 1 commit into

from

Sep 8, 2023
 Merged


std.tar: add support for file path in pax attributes
#16990
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


177 changes: 137 additions & 40 deletions
lib/std/tar.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -48,7 +48,7 @@ pub const Header = struct {
 /// Return value may point into Header buffer, or might point into the
 /// argument buffer.
 /// TODO: check against "../" and other nefarious things
 pub fn fullFileName(header: Header, buffer: *[255]u8) ![]const u8 {
 pub fn fullFileName(header: Header, buffer: *[std.fs.MAX_PATH_BYTES]u8) ![]const u8 {
 const n = name(header);
 if (!is_ustar(header))
 return n;
Expand DownExpand Up@@ -83,6 +83,44 @@ pub const Header = struct {
 }
};

const Buffer = struct {
 buffer: [512 * 8]u8 = undefined,
 start: usize = 0,
 end: usize = 0,

 pub fn readChunk(b: *Buffer, reader: anytype, count: usize) ![]const u8 {
 b.ensureCapacity(1024);

 const ask = @min(b.buffer.len - b.end, count -| (b.end - b.start));
 b.end += try reader.readAtLeast(b.buffer[b.end..], ask);

 return b.buffer[b.start..b.end];
 }

 pub fn advance(b: *Buffer, count: usize) void {
 b.start += count;
 assert(b.start <= b.end);
 }

 pub fn skip(b: *Buffer, reader: anytype, count: usize) !void {
 if (b.start + count > b.end) {
 try reader.skipBytes(b.start + count - b.end, .{});
 b.start = b.end;
 } else {
 b.advance(count);
 }
 }

 inline fn ensureCapacity(b: *Buffer, count: usize) void {
 if (b.buffer.len - b.start < count) {
 const dest_end = b.end - b.start;
 @memcpy(b.buffer[0..dest_end], b.buffer[b.start..b.end]);
 b.end = dest_end;
 b.start = 0;
 }
 }
};

pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !void {
 switch (options.mode_mode) {
 .ignore => {},
Expand All@@ -95,30 +133,27 @@ pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !voi
 @panic("TODO: unimplemented: tar ModeMode.executable_bit_only");
 },
 }
 var file_name_buffer: [255]u8 = undefined;
 var buffer: [512 * 8]u8 = undefined;
 var start: usize = 0;
 var end: usize = 0;
 var file_name_buffer: [std.fs.MAX_PATH_BYTES]u8 = undefined;
 var file_name_override_len: usize = 0;
 var buffer: Buffer = .{};
 header: while (true) {
 if (buffer.len - start < 1024) {
 const dest_end = end - start;
 @memcpy(buffer[0..dest_end], buffer[start..end]);
 end = dest_end;
 start = 0;
 }
 const ask_header = @min(buffer.len - end, 1024 -| (end - start));
 end += try reader.readAtLeast(buffer[end..], ask_header);
 switch (end - start) {
 const chunk = try buffer.readChunk(reader, 1024);
 switch (chunk.len) {
 0 => return,
 1...511 => return error.UnexpectedEndOfStream,
 else => {},
 }
 const header: Header = .{ .bytes = buffer[start..][0..512] };
 start += 512;
 buffer.advance(512);

 const header: Header = .{ .bytes = chunk[0..512] };
 const file_size = try header.fileSize();
 const rounded_file_size = std.mem.alignForward(u64, file_size, 512);
 const pad_len = @as(usize, @intCast(rounded_file_size - file_size));
 const unstripped_file_name = try header.fullFileName(&file_name_buffer);
 const unstripped_file_name = if (file_name_override_len > 0)
 file_name_buffer[0..file_name_override_len]
 else
 try header.fullFileName(&file_name_buffer);
 file_name_override_len = 0;
 switch (header.fileType()) {
 .directory => {
 const file_name = try stripComponents(unstripped_file_name, options.strip_components);
Expand All@@ -138,36 +173,59 @@ pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !voi

 var file_off: usize = 0;
 while (true) {
 if (buffer.len - start < 1024) {
 const dest_end = end - start;
 @memcpy(buffer[0..dest_end], buffer[start..end]);
 end = dest_end;
 start = 0;
 }
 // Ask for the rounded up file size + 512 for the next header.
 // TODO: https://github.com/ziglang/zig/issues/14039
 const ask = @as(usize, @intCast(@min(
 buffer.len - end,
 rounded_file_size + 512 - file_off -| (end - start),
 )));
 end += try reader.readAtLeast(buffer[end..], ask);
 if (end - start < ask) return error.UnexpectedEndOfStream;
 // TODO: https://github.com/ziglang/zig/issues/14039
 const slice = buffer[start..@as(usize, @intCast(@min(file_size - file_off + start, end)))];
 const temp = try buffer.readChunk(reader, @intCast(rounded_file_size + 512 - file_off));
 if (temp.len == 0) return error.UnexpectedEndOfStream;
 const slice = temp[0..@as(usize, @intCast(@min(file_size - file_off, temp.len)))];
 try file.writeAll(slice);

 file_off += slice.len;
start += slice.len;
buffer.advance(slice.len);
 if (file_off >= file_size) {
 start += pad_len;
 // Guaranteed since we use a buffer divisible by 512.
 assert(start <= end);
 buffer.advance(pad_len);
 continue :header;
 }
 }
 },
 .global_extended_header, .extended_header => {
 if (start + rounded_file_size > end) return error.TarHeadersTooBig;
 start = @as(usize, @intCast(start + rounded_file_size));
 .extended_header => {
 if (file_size == 0) {
 buffer.advance(@intCast(rounded_file_size));
 continue;
 }

 const chunk_size: usize = @intCast(rounded_file_size + 512);
 var data_off: usize = 0;
 file_name_override_len = while (data_off < file_size) {
 const slice = try buffer.readChunk(reader, chunk_size - data_off);
 if (slice.len == 0) return error.UnexpectedEndOfStream;
 const remaining_size: usize = @intCast(file_size - data_off);
 const attr_info = try parsePaxAttribute(slice[0..@min(remaining_size, slice.len)], remaining_size);

 if (std.mem.eql(u8, attr_info.key, "path")) {
 if (attr_info.value_len > file_name_buffer.len) return error.NameTooLong;
 buffer.advance(attr_info.value_off);
 data_off += attr_info.value_off;
 break attr_info.value_len;
 }

 try buffer.skip(reader, attr_info.size);
 data_off += attr_info.size;
 } else 0;

 var i: usize = 0;
 while (i < file_name_override_len) {
 const slice = try buffer.readChunk(reader, chunk_size - data_off - i);
 if (slice.len == 0) return error.UnexpectedEndOfStream;
 const copy_size: usize = @intCast(@min(file_name_override_len - i, slice.len));
 @memcpy(file_name_buffer[i .. i + copy_size], slice[0..copy_size]);
 buffer.advance(copy_size);
 i += copy_size;
 }

 try buffer.skip(reader, @intCast(rounded_file_size - data_off - file_name_override_len));
 continue :header;
 },
 .global_extended_header => {
 buffer.skip(reader, @intCast(rounded_file_size)) catch return error.TarHeadersTooBig;
 },
 .hard_link => return error.TarUnsupportedFileType,
 .symbolic_link => return error.TarUnsupportedFileType,
Expand DownExpand Up@@ -196,5 +254,44 @@ test stripComponents {
 try expectEqualStrings("c", try stripComponents("a/b/c", 2));
}

const PaxAttributeInfo = struct {
 size: usize,
 key: []const u8,
 value_off: usize,
 value_len: usize,
};

fn parsePaxAttribute(data: []const u8, max_size: usize) !PaxAttributeInfo {
 const pos_space = std.mem.indexOfScalar(u8, data, ' ') orelse return error.InvalidPaxAttribute;
 const pos_equals = std.mem.indexOfScalarPos(u8, data, pos_space, '=') orelse return error.InvalidPaxAttribute;
 const kv_size = try std.fmt.parseInt(usize, data[0..pos_space], 10);
 if (kv_size > max_size) {
 return error.InvalidPaxAttribute;
 }
 return .{
 .size = kv_size,
 .key = data[pos_space + 1 .. pos_equals],
 .value_off = pos_equals + 1,
 .value_len = kv_size - pos_equals - 2,
 };
}

test parsePaxAttribute {
 const expectEqual = std.testing.expectEqual;
 const expectEqualStrings = std.testing.expectEqualStrings;
 const expectError = std.testing.expectError;
 const prefix = "1011 path=";
 const file_name = "0123456789" ** 100;
 const header = prefix ++ file_name ++ "\n";
 const attr_info = try parsePaxAttribute(header, 1011);
 try expectEqual(@as(usize, 1011), attr_info.size);
 try expectEqualStrings("path", attr_info.key);
 try expectEqual(prefix.len, attr_info.value_off);
 try expectEqual(file_name.len, attr_info.value_len);
 try expectEqual(attr_info, try parsePaxAttribute(header, 1012));
 try expectError(error.InvalidPaxAttribute, parsePaxAttribute(header, 1010));
 try expectError(error.InvalidPaxAttribute, parsePaxAttribute("", 0));
}

const std = @import("std.zig");
const assert = std.debug.assert;

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
std.tar: add support for file path in pax attributes#16990

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

Vexu
merged 1 commit into

from

Sep 8, 2023
 Merged


std.tar: add support for file path in pax attributes
#16990
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


177 changes: 137 additions & 40 deletions
lib/std/tar.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -48,7 +48,7 @@ pub const Header = struct {
 /// Return value may point into Header buffer, or might point into the
 /// argument buffer.
 /// TODO: check against "../" and other nefarious things
 pub fn fullFileName(header: Header, buffer: *[255]u8) ![]const u8 {
 pub fn fullFileName(header: Header, buffer: *[std.fs.MAX_PATH_BYTES]u8) ![]const u8 {
 const n = name(header);
 if (!is_ustar(header))
 return n;
Expand DownExpand Up@@ -83,6 +83,44 @@ pub const Header = struct {
 }
};

const Buffer = struct {
 buffer: [512 * 8]u8 = undefined,
 start: usize = 0,
 end: usize = 0,

 pub fn readChunk(b: *Buffer, reader: anytype, count: usize) ![]const u8 {
 b.ensureCapacity(1024);

 const ask = @min(b.buffer.len - b.end, count -| (b.end - b.start));
 b.end += try reader.readAtLeast(b.buffer[b.end..], ask);

 return b.buffer[b.start..b.end];
 }

 pub fn advance(b: *Buffer, count: usize) void {
 b.start += count;
 assert(b.start <= b.end);
 }

 pub fn skip(b: *Buffer, reader: anytype, count: usize) !void {
 if (b.start + count > b.end) {
 try reader.skipBytes(b.start + count - b.end, .{});
 b.start = b.end;
 } else {
 b.advance(count);
 }
 }

 inline fn ensureCapacity(b: *Buffer, count: usize) void {
 if (b.buffer.len - b.start < count) {
 const dest_end = b.end - b.start;
 @memcpy(b.buffer[0..dest_end], b.buffer[b.start..b.end]);
 b.end = dest_end;
 b.start = 0;
 }
 }
};

pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !void {
 switch (options.mode_mode) {
 .ignore => {},
Expand All@@ -95,30 +133,27 @@ pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !voi
 @panic("TODO: unimplemented: tar ModeMode.executable_bit_only");
 },
 }
 var file_name_buffer: [255]u8 = undefined;
 var buffer: [512 * 8]u8 = undefined;
 var start: usize = 0;
 var end: usize = 0;
 var file_name_buffer: [std.fs.MAX_PATH_BYTES]u8 = undefined;
 var file_name_override_len: usize = 0;
 var buffer: Buffer = .{};
 header: while (true) {
 if (buffer.len - start < 1024) {
 const dest_end = end - start;
 @memcpy(buffer[0..dest_end], buffer[start..end]);
 end = dest_end;
 start = 0;
 }
 const ask_header = @min(buffer.len - end, 1024 -| (end - start));
 end += try reader.readAtLeast(buffer[end..], ask_header);
 switch (end - start) {
 const chunk = try buffer.readChunk(reader, 1024);
 switch (chunk.len) {
 0 => return,
 1...511 => return error.UnexpectedEndOfStream,
 else => {},
 }
 const header: Header = .{ .bytes = buffer[start..][0..512] };
 start += 512;
 buffer.advance(512);

 const header: Header = .{ .bytes = chunk[0..512] };
 const file_size = try header.fileSize();
 const rounded_file_size = std.mem.alignForward(u64, file_size, 512);
 const pad_len = @as(usize, @intCast(rounded_file_size - file_size));
 const unstripped_file_name = try header.fullFileName(&file_name_buffer);
 const unstripped_file_name = if (file_name_override_len > 0)
 file_name_buffer[0..file_name_override_len]
 else
 try header.fullFileName(&file_name_buffer);
 file_name_override_len = 0;
 switch (header.fileType()) {
 .directory => {
 const file_name = try stripComponents(unstripped_file_name, options.strip_components);
Expand All@@ -138,36 +173,59 @@ pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !voi

 var file_off: usize = 0;
 while (true) {
 if (buffer.len - start < 1024) {
 const dest_end = end - start;
 @memcpy(buffer[0..dest_end], buffer[start..end]);
 end = dest_end;
 start = 0;
 }
 // Ask for the rounded up file size + 512 for the next header.
 // TODO: https://github.com/ziglang/zig/issues/14039
 const ask = @as(usize, @intCast(@min(
 buffer.len - end,
 rounded_file_size + 512 - file_off -| (end - start),
 )));
 end += try reader.readAtLeast(buffer[end..], ask);
 if (end - start < ask) return error.UnexpectedEndOfStream;
 // TODO: https://github.com/ziglang/zig/issues/14039
 const slice = buffer[start..@as(usize, @intCast(@min(file_size - file_off + start, end)))];
 const temp = try buffer.readChunk(reader, @intCast(rounded_file_size + 512 - file_off));
 if (temp.len == 0) return error.UnexpectedEndOfStream;
 const slice = temp[0..@as(usize, @intCast(@min(file_size - file_off, temp.len)))];
 try file.writeAll(slice);

 file_off += slice.len;
start += slice.len;
buffer.advance(slice.len);
 if (file_off >= file_size) {
 start += pad_len;
 // Guaranteed since we use a buffer divisible by 512.
 assert(start <= end);
 buffer.advance(pad_len);
 continue :header;
 }
 }
 },
 .global_extended_header, .extended_header => {
 if (start + rounded_file_size > end) return error.TarHeadersTooBig;
 start = @as(usize, @intCast(start + rounded_file_size));
 .extended_header => {
 if (file_size == 0) {
 buffer.advance(@intCast(rounded_file_size));
 continue;
 }

 const chunk_size: usize = @intCast(rounded_file_size + 512);
 var data_off: usize = 0;
 file_name_override_len = while (data_off < file_size) {
 const slice = try buffer.readChunk(reader, chunk_size - data_off);
 if (slice.len == 0) return error.UnexpectedEndOfStream;
 const remaining_size: usize = @intCast(file_size - data_off);
 const attr_info = try parsePaxAttribute(slice[0..@min(remaining_size, slice.len)], remaining_size);

 if (std.mem.eql(u8, attr_info.key, "path")) {
 if (attr_info.value_len > file_name_buffer.len) return error.NameTooLong;
 buffer.advance(attr_info.value_off);
 data_off += attr_info.value_off;
 break attr_info.value_len;
 }

 try buffer.skip(reader, attr_info.size);
 data_off += attr_info.size;
 } else 0;

 var i: usize = 0;
 while (i < file_name_override_len) {
 const slice = try buffer.readChunk(reader, chunk_size - data_off - i);
 if (slice.len == 0) return error.UnexpectedEndOfStream;
 const copy_size: usize = @intCast(@min(file_name_override_len - i, slice.len));
 @memcpy(file_name_buffer[i .. i + copy_size], slice[0..copy_size]);
 buffer.advance(copy_size);
 i += copy_size;
 }

 try buffer.skip(reader, @intCast(rounded_file_size - data_off - file_name_override_len));
 continue :header;
 },
 .global_extended_header => {
 buffer.skip(reader, @intCast(rounded_file_size)) catch return error.TarHeadersTooBig;
 },
 .hard_link => return error.TarUnsupportedFileType,
 .symbolic_link => return error.TarUnsupportedFileType,
Expand DownExpand Up@@ -196,5 +254,44 @@ test stripComponents {
 try expectEqualStrings("c", try stripComponents("a/b/c", 2));
}

const PaxAttributeInfo = struct {
 size: usize,
 key: []const u8,
 value_off: usize,
 value_len: usize,
};

fn parsePaxAttribute(data: []const u8, max_size: usize) !PaxAttributeInfo {
 const pos_space = std.mem.indexOfScalar(u8, data, ' ') orelse return error.InvalidPaxAttribute;
 const pos_equals = std.mem.indexOfScalarPos(u8, data, pos_space, '=') orelse return error.InvalidPaxAttribute;
 const kv_size = try std.fmt.parseInt(usize, data[0..pos_space], 10);
 if (kv_size > max_size) {
 return error.InvalidPaxAttribute;
 }
 return .{
 .size = kv_size,
 .key = data[pos_space + 1 .. pos_equals],
 .value_off = pos_equals + 1,
 .value_len = kv_size - pos_equals - 2,
 };
}

test parsePaxAttribute {
 const expectEqual = std.testing.expectEqual;
 const expectEqualStrings = std.testing.expectEqualStrings;
 const expectError = std.testing.expectError;
 const prefix = "1011 path=";
 const file_name = "0123456789" ** 100;
 const header = prefix ++ file_name ++ "\n";
 const attr_info = try parsePaxAttribute(header, 1011);
 try expectEqual(@as(usize, 1011), attr_info.size);
 try expectEqualStrings("path", attr_info.key);
 try expectEqual(prefix.len, attr_info.value_off);
 try expectEqual(file_name.len, attr_info.value_len);
 try expectEqual(attr_info, try parsePaxAttribute(header, 1012));
 try expectError(error.InvalidPaxAttribute, parsePaxAttribute(header, 1010));
 try expectError(error.InvalidPaxAttribute, parsePaxAttribute("", 0));
}

const std = @import("std.zig");
const assert = std.debug.assert;

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
std.tar: add support for file path in pax attributes#16990

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

Vexu
merged 1 commit into

from

Sep 8, 2023
 Merged


std.tar: add support for file path in pax attributes
#16990
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


177 changes: 137 additions & 40 deletions
lib/std/tar.zig

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -48,7 +48,7 @@ pub const Header = struct {
 /// Return value may point into Header buffer, or might point into the
 /// argument buffer.
 /// TODO: check against "../" and other nefarious things
 pub fn fullFileName(header: Header, buffer: *[255]u8) ![]const u8 {
 pub fn fullFileName(header: Header, buffer: *[std.fs.MAX_PATH_BYTES]u8) ![]const u8 {
 const n = name(header);
 if (!is_ustar(header))
 return n;
Expand DownExpand Up@@ -83,6 +83,44 @@ pub const Header = struct {
 }
};

const Buffer = struct {
 buffer: [512 * 8]u8 = undefined,
 start: usize = 0,
 end: usize = 0,

 pub fn readChunk(b: *Buffer, reader: anytype, count: usize) ![]const u8 {
 b.ensureCapacity(1024);

 const ask = @min(b.buffer.len - b.end, count -| (b.end - b.start));
 b.end += try reader.readAtLeast(b.buffer[b.end..], ask);

 return b.buffer[b.start..b.end];
 }

 pub fn advance(b: *Buffer, count: usize) void {
 b.start += count;
 assert(b.start <= b.end);
 }

 pub fn skip(b: *Buffer, reader: anytype, count: usize) !void {
 if (b.start + count > b.end) {
 try reader.skipBytes(b.start + count - b.end, .{});
 b.start = b.end;
 } else {
 b.advance(count);
 }
 }

 inline fn ensureCapacity(b: *Buffer, count: usize) void {
 if (b.buffer.len - b.start < count) {
 const dest_end = b.end - b.start;
 @memcpy(b.buffer[0..dest_end], b.buffer[b.start..b.end]);
 b.end = dest_end;
 b.start = 0;
 }
 }
};

pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !void {
 switch (options.mode_mode) {
 .ignore => {},
Expand All@@ -95,30 +133,27 @@ pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !voi
 @panic("TODO: unimplemented: tar ModeMode.executable_bit_only");
 },
 }
 var file_name_buffer: [255]u8 = undefined;
 var buffer: [512 * 8]u8 = undefined;
 var start: usize = 0;
 var end: usize = 0;
 var file_name_buffer: [std.fs.MAX_PATH_BYTES]u8 = undefined;
 var file_name_override_len: usize = 0;
 var buffer: Buffer = .{};
 header: while (true) {
 if (buffer.len - start < 1024) {
 const dest_end = end - start;
 @memcpy(buffer[0..dest_end], buffer[start..end]);
 end = dest_end;
 start = 0;
 }
 const ask_header = @min(buffer.len - end, 1024 -| (end - start));
 end += try reader.readAtLeast(buffer[end..], ask_header);
 switch (end - start) {
 const chunk = try buffer.readChunk(reader, 1024);
 switch (chunk.len) {
 0 => return,
 1...511 => return error.UnexpectedEndOfStream,
 else => {},
 }
 const header: Header = .{ .bytes = buffer[start..][0..512] };
 start += 512;
 buffer.advance(512);

 const header: Header = .{ .bytes = chunk[0..512] };
 const file_size = try header.fileSize();
 const rounded_file_size = std.mem.alignForward(u64, file_size, 512);
 const pad_len = @as(usize, @intCast(rounded_file_size - file_size));
 const unstripped_file_name = try header.fullFileName(&file_name_buffer);
 const unstripped_file_name = if (file_name_override_len > 0)
 file_name_buffer[0..file_name_override_len]
 else
 try header.fullFileName(&file_name_buffer);
 file_name_override_len = 0;
 switch (header.fileType()) {
 .directory => {
 const file_name = try stripComponents(unstripped_file_name, options.strip_components);
Expand All@@ -138,36 +173,59 @@ pub fn pipeToFileSystem(dir: std.fs.Dir, reader: anytype, options: Options) !voi

 var file_off: usize = 0;
 while (true) {
 if (buffer.len - start < 1024) {
 const dest_end = end - start;
 @memcpy(buffer[0..dest_end], buffer[start..end]);
 end = dest_end;
 start = 0;
 }
 // Ask for the rounded up file size + 512 for the next header.
 // TODO: https://github.com/ziglang/zig/issues/14039
 const ask = @as(usize, @intCast(@min(
 buffer.len - end,
 rounded_file_size + 512 - file_off -| (end - start),
 )));
 end += try reader.readAtLeast(buffer[end..], ask);
 if (end - start < ask) return error.UnexpectedEndOfStream;
 // TODO: https://github.com/ziglang/zig/issues/14039
 const slice = buffer[start..@as(usize, @intCast(@min(file_size - file_off + start, end)))];
 const temp = try buffer.readChunk(reader, @intCast(rounded_file_size + 512 - file_off));
 if (temp.len == 0) return error.UnexpectedEndOfStream;
 const slice = temp[0..@as(usize, @intCast(@min(file_size - file_off, temp.len)))];
 try file.writeAll(slice);

 file_off += slice.len;
start += slice.len;
buffer.advance(slice.len);
 if (file_off >= file_size) {
 start += pad_len;
 // Guaranteed since we use a buffer divisible by 512.
 assert(start <= end);
 buffer.advance(pad_len);
 continue :header;
 }
 }
 },
 .global_extended_header, .extended_header => {
 if (start + rounded_file_size > end) return error.TarHeadersTooBig;
 start = @as(usize, @intCast(start + rounded_file_size));
 .extended_header => {
 if (file_size == 0) {
 buffer.advance(@intCast(rounded_file_size));
 continue;
 }

 const chunk_size: usize = @intCast(rounded_file_size + 512);
 var data_off: usize = 0;
 file_name_override_len = while (data_off < file_size) {
 const slice = try buffer.readChunk(reader, chunk_size - data_off);
 if (slice.len == 0) return error.UnexpectedEndOfStream;
 const remaining_size: usize = @intCast(file_size - data_off);
 const attr_info = try parsePaxAttribute(slice[0..@min(remaining_size, slice.len)], remaining_size);

 if (std.mem.eql(u8, attr_info.key, "path")) {
 if (attr_info.value_len > file_name_buffer.len) return error.NameTooLong;
 buffer.advance(attr_info.value_off);
 data_off += attr_info.value_off;
 break attr_info.value_len;
 }

 try buffer.skip(reader, attr_info.size);
 data_off += attr_info.size;
 } else 0;

 var i: usize = 0;
 while (i < file_name_override_len) {
 const slice = try buffer.readChunk(reader, chunk_size - data_off - i);
 if (slice.len == 0) return error.UnexpectedEndOfStream;
 const copy_size: usize = @intCast(@min(file_name_override_len - i, slice.len));
 @memcpy(file_name_buffer[i .. i + copy_size], slice[0..copy_size]);
 buffer.advance(copy_size);
 i += copy_size;
 }

 try buffer.skip(reader, @intCast(rounded_file_size - data_off - file_name_override_len));
 continue :header;
 },
 .global_extended_header => {
 buffer.skip(reader, @intCast(rounded_file_size)) catch return error.TarHeadersTooBig;
 },
 .hard_link => return error.TarUnsupportedFileType,
 .symbolic_link => return error.TarUnsupportedFileType,
Expand DownExpand Up@@ -196,5 +254,44 @@ test stripComponents {
 try expectEqualStrings("c", try stripComponents("a/b/c", 2));
}

const PaxAttributeInfo = struct {
 size: usize,
 key: []const u8,
 value_off: usize,
 value_len: usize,
};

fn parsePaxAttribute(data: []const u8, max_size: usize) !PaxAttributeInfo {
 const pos_space = std.mem.indexOfScalar(u8, data, ' ') orelse return error.InvalidPaxAttribute;
 const pos_equals = std.mem.indexOfScalarPos(u8, data, pos_space, '=') orelse return error.InvalidPaxAttribute;
 const kv_size = try std.fmt.parseInt(usize, data[0..pos_space], 10);
 if (kv_size > max_size) {
 return error.InvalidPaxAttribute;
 }
 return .{
 .size = kv_size,
 .key = data[pos_space + 1 .. pos_equals],
 .value_off = pos_equals + 1,
 .value_len = kv_size - pos_equals - 2,
 };
}

test parsePaxAttribute {
 const expectEqual = std.testing.expectEqual;
 const expectEqualStrings = std.testing.expectEqualStrings;
 const expectError = std.testing.expectError;
 const prefix = "1011 path=";
 const file_name = "0123456789" ** 100;
 const header = prefix ++ file_name ++ "\n";
 const attr_info = try parsePaxAttribute(header, 1011);
 try expectEqual(@as(usize, 1011), attr_info.size);
 try expectEqualStrings("path", attr_info.key);
 try expectEqual(prefix.len, attr_info.value_off);
 try expectEqual(file_name.len, attr_info.value_len);
 try expectEqual(attr_info, try parsePaxAttribute(header, 1012));
 try expectError(error.InvalidPaxAttribute, parsePaxAttribute(header, 1010));
 try expectError(error.InvalidPaxAttribute, parsePaxAttribute("", 0));
}

const std = @import("std.zig");
const assert = std.debug.assert;