ArgIteratorGeneral

pub fn ArgIteratorGeneral(comptime options: ArgIteratorGeneralOptions) type {
    return struct {
        allocator: Allocator,
        index: usize = 0,
        cmd_line: []const u8,

        /// Should the cmd_line field be free'd (using the allocator) on deinit()?
        free_cmd_line_on_deinit: bool,

        /// buffer MUST be long enough to hold the cmd_line plus a null terminator.
        /// buffer will we free'd (using the allocator) on deinit()
        buffer: []u8,
        start: usize = 0,
        end: usize = 0,

        pub const Self = @This();

        pub const InitError = error{OutOfMemory};

        /// cmd_line_utf8 MUST remain valid and constant while using this instance
        pub fn init(allocator: Allocator, cmd_line_utf8: []const u8) InitError!Self {
            const buffer = try allocator.alloc(u8, cmd_line_utf8.len + 1);
            errdefer allocator.free(buffer);

            return Self{
                .allocator = allocator,
                .cmd_line = cmd_line_utf8,
                .free_cmd_line_on_deinit = false,
                .buffer = buffer,
            };
        }

        /// cmd_line_utf8 will be free'd (with the allocator) on deinit()
        pub fn initTakeOwnership(allocator: Allocator, cmd_line_utf8: []const u8) InitError!Self {
            const buffer = try allocator.alloc(u8, cmd_line_utf8.len + 1);
            errdefer allocator.free(buffer);

            return Self{
                .allocator = allocator,
                .cmd_line = cmd_line_utf8,
                .free_cmd_line_on_deinit = true,
                .buffer = buffer,
            };
        }

        // Skips over whitespace in the cmd_line.
        // Returns false if the terminating sentinel is reached, true otherwise.
        // Also skips over comments (if supported).
        fn skipWhitespace(self: *Self) bool {
            while (true) : (self.index += 1) {
                const character = if (self.index != self.cmd_line.len) self.cmd_line[self.index] else 0;
                switch (character) {
                    0 => return false,
                    ' ', '\t', '\r', '\n' => continue,
                    '#' => {
                        if (options.comments) {
                            while (true) : (self.index += 1) {
                                switch (self.cmd_line[self.index]) {
                                    '\n' => break,
                                    0 => return false,
                                    else => continue,
                                }
                            }
                            continue;
                        } else {
                            break;
                        }
                    },
                    else => break,
                }
            }
            return true;
        }

        pub fn skip(self: *Self) bool {
            if (!self.skipWhitespace()) {
                return false;
            }

            var backslash_count: usize = 0;
            var in_quote = false;
            while (true) : (self.index += 1) {
                const character = if (self.index != self.cmd_line.len) self.cmd_line[self.index] else 0;
                switch (character) {
                    0 => return true,
                    '"', '\'' => {
                        if (!options.single_quotes and character == '\'') {
                            backslash_count = 0;
                            continue;
                        }
                        const quote_is_real = backslash_count % 2 == 0;
                        if (quote_is_real) {
                            in_quote = !in_quote;
                        }
                    },
                    '\\' => {
                        backslash_count += 1;
                    },
                    ' ', '\t', '\r', '\n' => {
                        if (!in_quote) {
                            return true;
                        }
                        backslash_count = 0;
                    },
                    else => {
                        backslash_count = 0;
                        continue;
                    },
                }
            }
        }

        /// Returns a slice of the internal buffer that contains the next argument.
        /// Returns null when it reaches the end.
        pub fn next(self: *Self) ?[:0]const u8 {
            if (!self.skipWhitespace()) {
                return null;
            }

            var backslash_count: usize = 0;
            var in_quote = false;
            while (true) : (self.index += 1) {
                const character = if (self.index != self.cmd_line.len) self.cmd_line[self.index] else 0;
                switch (character) {
                    0 => {
                        self.emitBackslashes(backslash_count);
                        self.buffer[self.end] = 0;
                        const token = self.buffer[self.start..self.end :0];
                        self.end += 1;
                        self.start = self.end;
                        return token;
                    },
                    '"', '\'' => {
                        if (!options.single_quotes and character == '\'') {
                            self.emitBackslashes(backslash_count);
                            backslash_count = 0;
                            self.emitCharacter(character);
                            continue;
                        }
                        const quote_is_real = backslash_count % 2 == 0;
                        self.emitBackslashes(backslash_count / 2);
                        backslash_count = 0;

                        if (quote_is_real) {
                            in_quote = !in_quote;
                        } else {
                            self.emitCharacter('"');
                        }
                    },
                    '\\' => {
                        backslash_count += 1;
                    },
                    ' ', '\t', '\r', '\n' => {
                        self.emitBackslashes(backslash_count);
                        backslash_count = 0;
                        if (in_quote) {
                            self.emitCharacter(character);
                        } else {
                            self.buffer[self.end] = 0;
                            const token = self.buffer[self.start..self.end :0];
                            self.end += 1;
                            self.start = self.end;
                            return token;
                        }
                    },
                    else => {
                        self.emitBackslashes(backslash_count);
                        backslash_count = 0;
                        self.emitCharacter(character);
                    },
                }
            }
        }

        fn emitBackslashes(self: *Self, emit_count: usize) void {
            var i: usize = 0;
            while (i < emit_count) : (i += 1) {
                self.emitCharacter('\\');
            }
        }

        fn emitCharacter(self: *Self, char: u8) void {
            self.buffer[self.end] = char;
            self.end += 1;
        }

        /// Call to free the internal buffer of the iterator.
        pub fn deinit(self: *Self) void {
            self.allocator.free(self.buffer);

            if (self.free_cmd_line_on_deinit) {
                self.allocator.free(self.cmd_line);
            }
        }
    };
}