/* Learn the Poke language in Y minutes */ /* Copyright (C) 2020-2021, Mohammad-Reza Nabipoor */ /* SPDX-License-Identifier: GPL-3.0-or-later */ /* GNU poke is an interactive editor for binary data. But it's not just an * editor, it provides a full-fledged procedural, interactive programming * language designed to describe data structures and to operate on them. * The programming language is called Poke (with upper-case P). * * When the user have a description of binary data (a *pickle*), he/she * can *map* it on the actual data and start poking the data! The user can * inspect and modify data. */ /* First start with nomenclature: * * - poke The editor program (also called GNU poke) * - Poke Domain-specific programming language that used by `poke` * - pickle A logical component that provides a set of (related) * functionalities (e.g., description of a binary format or * utilities to deal with date and time, etc.). * Pickles are defined in files with `.pk` extension. */ /* Let's talk about the Poke! */ /* Variables * * We can define variables in Poke using `var` keyword: * * var NAME_OF_VARIABLE = VALUE */ var an_integer = 10; var a_string = "hello, poke users!"; /* Values * * Poke programming language has the following types of value: * * - Integer * - String * - Offset * - Array * - Struct * - Union * - Closure (or function) * * There are two categories of values in Poke: * - Simple values * - Integer * - String * - Offset * - Composite values * - Array * - Struct * - Union * - Closure * * The difference lies in the semantics of copy. Consider the following `C` * program: * * ```c * void f(int); * void g(int*); * * int main() { * int i = 10; * * f(i); // sends a copy of **value of** `i` to `f` * g(&i); // sends a copy of **address of** `i` to `g` * * return 0; * } * ``` * * Simple values in Poke are like `int` in `C`. The copy makes a new disjoint * value. Changing the copied value will not change the original one. * And composite values are like `int*` in `C`. The new copy will also points * to the same data (also called "copying by shared value"). */ /* Integer values */ var decimal = 10; var hexadecimal = 0xff; var binary = 0b1100; var octal = 0o777; var si8 = 1B; /* byte (8-bit) */ var si16 = 2H; /* byte (16-bit) */ var si32 = 3; /* int (32-bit) */ var si64 = 4L; /* long (64-bit) */ var ui8 = 4UB; /* unsigned byte (8-bit) */ var ui16 = 5UH; /* unsigned int (16-bit) */ var ui32 = 6U; /* unsigned int (32-bit) */ var ui64 = 7UL; /* unsigned long (64-bit) */ /* Digits can be separated by `_` (underscores) to enhance readability. */ var long_decimal = 100_000_000; var long_hexadecimal = 0x1122_aabb_ccdd_eeff; /* Operations on integer values */ /* Arithmetic */ var ia1 = 10 ** 2; /* exponentiation -- ia1 == 100 */ var ia2 = 5 * 7; /* multiplication -- ia2 == 35 */ var ia3 = 17 / 4; /* division -- ia3 == 4 */ var ia4 = 17 /^ 4; /* ceil-division -- ia4 == 5 */ var ia5 = 25 % 7; /* modulus -- ia5 == 4 */ /* There are also addition (`+`) and subtraction (`-`) operators */ /* Bitwise * * Poke has the following left-associative binary bitwise operators: * - Logical shifts (`<<.`, and `.>>`) * - AND (`&`) * - XOR (`^`) * - OR (`|`) * - Bitwise concatenation (`:::`) * * Right-associative unary bitwise operator: * - Bitwise complement (`~`) * * NOTE There's no arithmetic right-shifting operator in Poke. */ var ib1 = 1 <<. 10; /* ib1 == 1024 */ var ib2 = 1024 .>> 9; /* ib2 == 2 */ var ib3 = 0x12UB ::: 0x34UB; /* ib3 == 0x1234UH */ var ib4 = ~0x0fUB; /* ib4 == 0xf0UB */ /* String values (null-terminated) */ var foobar_string = "foo\nbar"; var empty_string = ""; /* Offset values * * Poke does not use integers to specify offsets in binary data, it has a * primitive type for that: offset! * * Offsets have two parts: * - magnitude (an integer) * - unit (b (bit), byte (B), etc.) * * Offsets are also useful for specifying sizes. */ /* Offsets with named units */ var off_8_bits = 8#b; var off_23_bytes = 23#B; var off_2000_bits = 2#Kb; var off_2000_bytes = 2#KB; var off_3_nibbles = 3#N; /* 3 nibbles (each nibble is 4 bits) */ var off_1_byte = #B; /* You can omit the magnitude if it's 1 */ /* Offsets with numeric units */ var off_8_8 = 8#8; /* magnitude: 8, unit: 8 bits */ var off_2_3 = 2#3; /* magnitude: 2, unit: 3 bits */ /* Offset arithmetic * * OFF +- OFF -> OFF * OFF * INT -> OFF * OFF / OFF -> INT * OFF /^ OFF -> INT // ceil division * OFF % OFF -> OFF * OFF / INT -> OFF * OFF /^ INT -> OFF // ceil division */ var off_1_plus_2 = 1#B + 2#B; /* 3#B */ var off_1_minus_2 = 1#B - 2#B; /* -1#B */ var off_8_times_10 = 8#B * 10; /* 80#B */ var off_10_times_8 = 10 * 8#B; /* 80#B */ var off_7_div_1 = 7#B / 1#B; /* 7 */ /* This is an integer */ var off_7_cdiv_2 = 7#B /^ 2#B; /* 4 */ /* This is an integer */ var off_7_mod_3 = 7#B % 3#B; /* 1#B */ /* The following units are pre-defined in Poke: * * b, N, B, Kb, KB, Mb, MB, Gb, GB, Kib, KiB, Mib, MiB, Gib, GiB * * Poke supports user-defined units using `unit` construction: * * unit NAME = CONSTANT_EXPRESSION; */ unit BIT = 1; unit NIBBLE = 4; unit kilobit = 10U ** 3; unit kilobyte = 10U ** 3 * 8; var off_bit = 10#BIT; /* off_bit == 10#b */ var off_nibble = 4#NIBBLE; /* off_nibble == 4#N && off_nibble == 16#b */ var off_kb = 1#kilobit; /* off_kb == 1#Kb && off_kb == 1000#b */ var off_kB = 2#kilobyte; /* off_kB == 2#KB && off_kB == 16000#b */ /* Array values */ var arr1 = [1, 2, 3]; var arr2 = [[1, 2], [3, 4]]; var elem10 = arr1[0]; /* Arrays are indexed using the usual notation */ var elem12 = arr1[2]; /* This is the last element of `arr1`: 3 */ /* If you try to access elements beyond the bounds, you'll get an * `E_out_of_bounds` exception. */ /* var elem1x = arr1[3]; */ /* var elem1y = arr1[-1]; */ /* Array trimming: Extraction of a subset of the array */ var arr3 = arr1[0:2]; /* arr3 == [arr1[0], arr1[1]] */ var arr4 = arr1[0:0]; /* arr4 is an empty array */ /* Array is a "composite value"; It behaves like pointers on copy. * The underlying data is shared between `arr1` and `arr5`. */ var arr5 = arr1; arr5[0] = -1; /* arr1 == [-1, 2, 3] */ /* Array trimming *makes* a new array with *copies* of the selected data */ var arr6 = arr1[:]; var arr7 = arr2[:]; arr6[0] = 1; /* arr6 == [1, 2, 3] && arr1 == [-1, 2, 3] */ arr7[0][0] = -1; /* arr2 == [[-1, 2], [3, 4]] */ /* Making array using the constructor */ var arr8 = string[3]("Hi"); /* arr8 == ["Hi", "Hi", "Hi"] */ var arr9 = int<32>[](); /* arr9 == arr4; an empty array */ var arr10 = int<32>[16#B](); /* arr10 == [0, 0, 0, 0] */ /* Types * * Before talking about `struct` values, it'd be nice to first talk about types * in Poke. */ /* Integral types * * Most general-purpose programming languages provide a small set of integer * types. Poke, on the contrary, provides a rich set of integer types featuring * different widths, in both signed and unsigned variants. * * `int<N>` is a signed integer with `N`-bit width. `N` can be an integer * literal in the range `[1, 64]`. * * `uint<N>` is the unsigned variant. * * Examples: * * uint<1> * uint<7> * int<64> */ /* String type * * There is one string type in Poke: `string` * Strings in Poke are null-terminated. */ /* Array types * * There are three kinds of array types: * * - Unbounded: arrays that have no explicit boundaries, like `int<32>[]` * - Bounded by number of elements, like `int<64>[10]` * - Bounded by size, like `uint<32>[8#B]` */ /* Offset types * * Offset types are denoted as `offset<BASE_TYPE,UNIT>`, where BASE_TYPE is * an integer type and UNIT the specification of an unit. * * Examples: * * offset<int<32>,B> * offset<uint<12>,Kb> * offset<uint<12>,1024> */ /* Struct types * * Structs are the main abstraction that Poke provides to structure data. A * collection of heterogeneous values. * * And there's no padding or alignment between the fields of structs. * In other words: WYPIWYG (What You Poke Is What You Get)! * * Examples: * * struct { * uint<32> i32; * uint<64> i64; * } * * struct { * uint<16> flags; * uint<8>[32] data; * } * * struct { * int<32> code; * string msg; * int<32> exit_status; * } */ /* User-declared types * * There's a mechanism to declare new types: * * type NAME = TYPE; * * where NAME is the name of the new type, and TYPE is either a type specifier * or the name of some other type. * * The supported type specifiers are integral types, string type, array types, * struct types, function types, and `any` (The `any` type is used to * implement polymorphism). */ type Bit = uint<1>; type Int = int<32>; type Ulong = uint<64>; type String = string; /* Just to show that this is possible! */ type Buffer = uint<8>[]; /* Unbounded array of type uint<8> */ type Triple = int<32>[3]; /* Bounded array of 3 elements */ type Buf1024 = uint<8>[1024#B]; /* Bounded array with size of 1024 bytes */ type EmptyStruct = struct {}; type BufferStruct = struct { Buffer buffer; }; type Pair_32_64 = struct { uint<32> i32; uint<64> i64; }; type Packet34 = struct { uint<16> flags; uint<8>[32] data; }; type Error = struct { int<32> code; string msg; int<32> exit_status; }; /* Now back to the values */ /* Struct values */ var empty_struct = EmptyStruct {}; type Packet = struct { uint<16> flags; uint<8>[8] data; }; var packet_1 = Packet { flags = 0xff00, data = [0UB, 1UB, 2UB, 3UB, 4UB, 5UB, 6UB, 7UB], }; var packet_2 = Packet { flags = 1, /* The following line is invalid; because type of numbers is `uint<32>`. */ /* data = [0, 1, 2, 3, 4, 5, 6, 7], */ /* User cannot specify less than 8 elements; because the `data` field is a * fixed size array. So the following line is compilation error: */ /* data = [0UB, 1UB, ], */ }; var packet_3 = Packet { /* flags = 0, */ /* Fields can be omitted */ /* The fifth element (counting from zero) is initialized to `128UB`; * and all uninitialized values before that will be initialized to `128UB`, * too. */ data = [1UB, .[5] = 128UB, 2UB, 3UB], }; /* packet_3 == Packet{flags=0UH,data=[1UB,128UB,128UB,128UB,128UB,128UB,2UB,3UB]} */ type Header = struct { uint<8>[2] magic; offset<uint<32>,B> file_size; uint<16>; /* Reserved */ uint<16>; /* Reserved */ offset<uint<32>,B> data_offset; }; type Payload = struct { uint<8> magic; uint<32> data_length; /* Size of array depends on the `data_length` field */ uint<8>[data_length] data; }; /* An interesting feature of Poke is that types also can be used as units for * offsets. The only restriction is that the type should have known size at * compile-time. */ var off_23_packets = 23#Packet; /* magnitude: 23, unit: Packet */ /* Note that this is invalid and give compilation error: * * var off_buffer = 1#Buffer; * * because `Buffer` is an unbounded array and the size is unknown at * compile-time. */ /* Offset arithmetic with types as unit of offsets */ var packet_size = 1#Packet / 1#B; /* 10 */ var two_packet_size = 2 #Packet/#B; /* 20 */ /* Struct Field Constraints * * It is common for struct fields to be constrained to their values to * satisfy some conditions. Obvious examples are magic numbers, and * specification-derived constraints. */ type HeaderWithMagic = struct { uint<8> magic : magic == 100UB; uint<8> version : version <= 3; offset<uint<32>,B> data_length; uint<8>[data_length] data; }; /* The constraint expression should evaluate to an integer value; that value * is interpreted as a boolean */ /* The following variable definition will raise an exception: * unhandled constraint violation exception */ /* var hdrmagic = HeaderWithMagic {}; */ /* This will work because all field constraints are satisfied */ var hdrmagic = HeaderWithMagic { magic = 100UB, }; /* There is another way to specify the constraints: field initializers */ /* Struct Field Initializers * * Field initializer has two roles: * - Introduce constraint of the form: `field == initializer_expression` * - Initialize the field with initializer expression */ type HeaderWithInit = struct { uint<8> magic = 100UB; uint<8> version = 3; offset<uint<32>,B> data_length; uint<8>[data_length] data; }; /* With field initializers, this is possible: */ var hdrauto = HeaderWithInit {}; /* hdrauto.magic == 100UB && hdrauto.version == 3UB */ /* The only limitation is that we cannot specify a constraint for initialized * fields. */ /* Integral Structs * * A facility to deal with integers as a composite data. * Different groups of bits of the integer can be accessed independently. * * Note that "integral structs" are integers, not structs. So the order of * fields are independent of the underlying endianness. * * See http://jemarch.net/pokology-20200720.html for more info. */ type IntSct = struct uint<16> /* After `struct` comes an integral type */ { /* bit-width of all fields == 16 */ uint<4> x; /* most significant nibble of the integer */ uint<8> y; uint<4> z; /* least significant nibble of the integer */ }; var intsct = IntSct { x = 0xa, y = 0xbc, z = 0xd, }; var x = intsct.x; /* x == 0xaUN (`UN` means unsigned nibble (4-bit)) */ var y = intsct.y; /* y == 0xbcUB */ var z = intsct.z; /* z == 0xdUN */ /* Compiler promotes `intsct` to integer in all contexts where an integer is * expected. */ var intsct_as_uint16 = intsct + 0H; /* intsct_as_uint16 == 0xabcdUH */ var intsct_as_uint16_2 = +intsct; /* intsct_as_uint16_2 == 0xabcdUH */ /* Exception Handling * * Poke has a mechanism to deal with errors and unexpected situations. * Errors are communicated by exceptions. Exceptions are values of type * `Exception` struct. * * One can `raise` an exception on one end, and the other can `catch` that * exception. */ fun do_io = void: { raise Exception{ code = EC_io, msg = "Cannot read the file" }; }; try { do_io; } catch (Exception e) { printf ("[example-exception] code:%i32d msg:\"%s\"\n", e.code, e.msg); } /* Exception codes in the range `0..254` are reserved for Poke. These codes * are defined by `EC_*` variables in `pkl-rt.pk` file. * * Users also can define their own exceptions by calling `exception_code` * function. */ var MY_EC_EXCP = exception_code (); /* The actual value is not important */ try raise Exception{ code = MY_EC_EXCP, msg = "My error description", }; catch {}; /* Functions * * Functions are lexically scoped. */ fun func1 = (uint<32> arg0, uint<64> arg1) uint<32>: { return arg0 | arg1 .>> 32; /* `.>>` is bitwise shift right operator */ } var three = func1 (1, 2L**33); /* three == 3 (and `**` is power operator) */ /* Alternative function call syntax */ var four = (func1 :arg0 1 :arg1 2L**33) + 1; /* four == 4 */ fun awesome = (string name) void: { printf ("%s is awesome!\n", name); } awesome ("Poke"); /* Will print "Poke is awesome!" on terminal */ awesome :name "Poke"; var N = 10; fun Nsquare = int<32>: /* No input argument */ { /* The `N` variable is captured inside the `Nsquare` function */ return N * N; } var Nsq = Nsquare; /* Nsq == 100 */ N = 20; var Nsq2 = Nsquare; /* Nsq2 == 400 */ /* Functions with optional arguments * * Note that the value of initialization gets captured in the closure. */ var ten = 10; fun double32 = (int<32> n = ten) uint<64>: { n = n * 2; return n; } var twenty = double32 (); /* twenty == 20UL */ var another_twenty = double32; /* It's OK to omit the `()` */ var thirty = double32 (15); /* thirty == 30UL */ /* And because `ten` is lexically closed in `double32` function: */ ten = 11; var no_more_twenty = double32; /* no_more_twenty == 22 */ ten = 10; /* double32 == 20UL */ /* Function with no output (a procedure!) */ fun packet_toggle_flag = (Packet p) void: { p.flags = p.flags ^ 1; } packet_toggle_flag (packet_1); /* packet_1.flags == 0xff01 */ /* Anonymous functions (lambdas) */ var lam1 = lambda (int x) int: { return x + 2; }; var lam_arr = [lam1, lambda (int x) int: { return x * 2; }]; var lam_r1 = lam1 (10); /* lam_r1 == 12 */ var lam_r2 = lam_arr[0] (10); /* lam_r2 == 12 */ var lam_r3 = lam_arr[1] (10); /* lam_r3 == 20 */ /* Struct Methods */ type Point = struct { int<32> x; int<32> y; method norm_squared = int<32>: { return x*x + y*y; } }; var point = Point{ x = 10, y = -1 }; var point_nsq = point.norm_squared; /* point_nsq == 101 */ /* Unions * * Sometimes the structure of binary format can be different depending on some * eariler fields. To describe these kinds of formats, Poke provides `union`s. * * The first field of `union` for which its constraints are satisfied will be * selected. */ type PacketU = struct { uint<8> size; union { struct { uint<8> typ; uint<8>[size] data; } alt1 : size < 32; struct { uint<16> typ; uint<8>[size - 1] data; } alt2 : size < 128; struct { uint<16> typ; uint<8> flags; uint<8>[size - 3] data; } alt3; } u; }; var packet_u_1 = PacketU { size = 10, }; var packet_u_2 = PacketU { size = 64, }; var packet_u_3 = PacketU { size = 128, }; /* isa operator: VAR isa TYPE */ var typ1_is_a_uint8 = packet_u_1.u.alt1.typ isa uint<8>; /* typ1_is_a_uint8 == 1 */ /* Trying to access to a non-active field results in an `E_elem` exception */ try packet_u_1.u.alt2.typ = 1; catch if E_elem { print ("`alt2` is not the active field in `packet_u_1.u` union\n"); } var typ2_is_a_uint16 = packet_u_2.u.alt2.typ isa uint<16>; /* typ2_is_a_uint16 == 1 */ var flags3 = packet_u_3.u.alt3.flags; /* Casts */ var num_u32 = 1U; var num_u64 = num_u32 as uint<64>; var off_12B = 1024#b as offset<int<12>,B>; /* off_12B == 128#B */ var off_9b = 9#b as offset<int,B>; /* off_9b == 1#B */ type CFoo = struct { int i; long j; }; type CBar = struct { int i; }; var cbar_as_cfoo = CBar {i=1} as CFoo; /* CFoo {i=1,j=0L} */ var cfoo_as_cbar = CFoo {j=2} as CBar; /* CBar {i=0} */ /* Attributes * * Each value has a set of attributes. */ /* `size` attribute */ var sizeof_num_u32 = num_u32'size; /* sizeof_num_u32 == 4#B */ var sizeof_num_u64 = num_u64'size; /* sizeof_num_u64 == 8#B */ var sbuf = BufferStruct{}; var sizeof_sbuf = sbuf'size; /* sizeof_sbuf == 0#B */ var sizeof_packet_1 = packet_1'size; /* sizeof_packet_1 == 10#B */ /* `length` attribute */ var nelem_arr1 = arr1'length; /* nelem_arr1 == 3 */ var nelem_arrx = [1, 2, 3, 4, 5, 6]'length; /* nelem_arrx == 6 */ /* For structs it's the number of fields */ var nfields_packet_1 = packet_1'length; /* nfields_packet_1 == 2 */ /* Conditionals * * - if-else * - conditional expression */ if (num_u32 & 1) { /* This branch will be evaluated */ num_u32 = num_u32 | 2; /* 1 | 2 == 3 */ num_u64 = num_u64 | 4; /* 1 | 4 == 5 */ } else { num_u32 = num_u32 | 8; /* 1 | 8 == 9 */ num_u64 = num_u64 | 16; /* 1 | 16 = 17 */ } var a_true_value = num_u32 == 3 && num_u64 == 5; var a_false_value = num_u32 == 9 || num_u64 == 17; var hundred = a_true_value ? 100 : 200; var thousand = a_false_value ? 200 : 1000; /* Loops * * - while * - for * - for-in * - try-until */ var i = 0; while (1) { i = i + 1; if (i == 10) break; } /* i == 10 */ for (var j = 0; j < 2; j++) { ++i; } /* i == 12 */ print "\nList of maintainers:\n"; for (i in ["jemarch", "egeyar", "jmd", "positron", "darnir", "dan.cermak", "bruno", "ccaione", "eblake", "tim.ruehsen", "sdi1600195", "aaptel", "m.nabipoor", "david.faust", "indu.bhagat"]) { printf (" %s\n", i); } var digits = [9, 8, 7, 6, 5, 4, 3, 2, 1, 0]; for (i in "0123456789") { digits[i - '0'] = i - '0'; } /* digits == [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] */ var digitsEven = [8, 6, 4, 2, 0]; for (i in "0123456789" where i % 2 == 0) { digitsEven[(i - '0') / 2] = i - '0'; } /* digitsEven == [0, 2, 4, 6, 8] */ /* `print` and `printf` */ /* `print` accepts only one argument of type `string` and prints it in the * output; it's like the `puts` function of C standard library. */ print ("`print` is like `puts`!\n"); print "`print` is like `puts`!\n"; /* Parentheses are optional */ /* `printf` behaves like the `printf` function of C standard library: * one required argument of type string as the "format string" and zero or * more arguments according to the "conversion specifiers" of the format * string. * * Conversion specifiers: * - Signed integers: i<WIDTH><BASE> * (like `i32x`, `i23d`, `i7o`, `i19b`) * - Unsigned integers: u<WIDTH><BASE> * (like `u32x`, `u23d`, `u7o`, `u19b`) * - String: s * - Byte (or character): c * - Pretty-printed value: v * <DEPTH>v * (like `v`, `0v`, `1v`, `9v`) * - Pretty-printed value (flat mode): Fv * <DEPTH>Fv * (like `Fv`, `0Fv`, `1Fv`, `9Fv`) * - Pretty-printed value (tree mode): Tv * <DEPTH>Tv * (like `Tv`, `0Tv`, `1Tv`, `9Tv`) * * WIDTH is the width of the integral value. * DEPTH indicates how deep the print should recurse to print the child * fields. 0 means print all fields completely. * * Parentheses are optional around the arguments. */ printf ("decimal (64): %i64x %u64x\n", -1, 1); /* decimal (64): ffffffffffffffff 0000000000000001 */ printf ("decimal (32): %i32d %u32d\n", -10, 20U); /* decimal (32): -10 20 */ printf ("hex (32): %i32x %u32x\n", -10, 20U); /* hex (32): fffffff6 00000014 */ printf ("octal (16): %i16o %u16o\n", -10, 20U); /* octal (16): 177766 000024 */ printf ("bin (7): %i7b %u7b\n", -10, 20U); /* bin (7): 1110110 0010100 */ printf ("%s like in C\n", "Works"); /* Works like in C */ printf ("%c%c is a prime number\n", 0x32, 0x33); /* 23 is a prime number */ printf ("%v\n", Point {x = 1, y = -1}); /* Default printing mode is "flat" */ /* Point {x=1,y=-1} */ printf ("%Fv\n", Point {x = 1, y = -1}); /* Flat mode */ /* Point {x=1,y=-1} */ printf ("%Tv\n", Point {x = 1, y = -1}); /* Tree mode */ /* Point { x=1, y=-1 } */ type PointPair = struct { Point first; Point second; }; /* Tree mode with one level depth */ printf ("%1Tv\n", PointPair { first = Point {x = 1, y = -1}, second = Point {x = -1, y = 1}, }); /* PointPair { first=Point {...}, second=Point {...} } */ /* Tree mode with two level depth */ printf ("%2Tv\n", PointPair { first = Point {x = 1, y = -1}, second = Point {x = -1, y = 1}, }); /* PointPair { first=Point { x=1, y=-1 }, second=Point { x=-1, y=1 } } */ /* Now, the most important concept in Poke: mapping! */ /* Mapping * * The purpose of poke is to edit "IO spaces", which are the files or devices, * or memory areas being edited. This is achieved by **mapping** values. */ /* Using `open` function one can open an IO space; Poke supports the following * IO spaces: * * - Auto-growing memory buffer * - File * - Block device served by an NDB server * * It has the following prototype: * * fun open = (string HANDLER, uint<64> flags = 0) int<32> */ /* open an auto-growing memory buffer */ var memio = open("*Arbitrary Name*"); /* open a file */ var zeroio = open("/dev/zero"); /* open standard input (stdin) */ var stdin = open("<stdin>"); /* open standard output (stdout) */ var stdout = open("<stdout>"); /* open standard error (stderr) */ var stderr = open("<stderr>"); /* close the IO spaces */ close(stderr); close(stdout); close(stdin); close(zeroio); /* To access to IO space we can map a value to some area using this syntax: * * TYPE @ OFFST * or, * TYPE @ IOS : OFFSET * * The map operator, regardless of the type of value it is mapping, always * returns a *copy* of the value found stored in the IO space. */ var ai32 = uint<32>[1] @ 0#B; var ui32num = uint<32> @ 0#B; ai32[0] = 0xaabbccdd; /* The first 4 bytes in IO space will change. */ ui32num = 0xddccbbaa; /* But this doesn't have any effect on IO space */ uint<32> @ 0#B = 0xddccbbaa; /* This works as expected */ /* Poke values also have the `mapped` attribute. */ var ai32_is_mapped = ai32'mapped; /* ai32_is_mapped == 1 */ var cur_ios = get_ios; /* `get_ios` returns the ID of current IO space */ /* `iosize` function returns the size of IO space. */ var cur_sz = iosize (cur_ios); /* Endianness * * Big-endian is the default endian-ness. This can be verified by the following * expression: * * get_endian == ENDIAN_BIG * * This can be changed using `set_endian` function. */ set_endian(ENDIAN_LITTLE); /* get_endian == ENDIAN_LITTLE */ /* Signed Arithmetic Overflow Detection * * All signed arithmetic operations can raise `E_overflow` exception. */ try 2**33; /* `2` is of type `int32` */ catch if E_overflow { print ("Overflow detected in 2**33"); } /* std.pk - Standard definition for poke * * The following types are defined as Standard Integral Types: * - bit * - nibble * - uint8, byte, char, int8 * - uint16, ushort, int16, short * - uint32, uint, int32, int * - uint64, ulong, int64, long * * Standard Offset Types: * type off64 = offset<int64,b>; * type uoff64 = offset<uint64,b>; * * Conversion Functions: * - catos Character array to string * - stoca String to character array * - atoi String to integer * * String Functions: * - strchr Index of first occurrence of the character in string * - ltrim Left trim * - rtrim Right trim * * Sorting Functions: * - qsort * * CRC Functions: * - crc32 * * Misc: * var NULL = 0#B; */ /* Standard pickles * * - bmp BMP file format * - bpf Linux eBPF instruction set * - btf Linux BPF Type Format * - btf-dump Utilities for dumping BTF information * - color Standard colors for GNU poke * - ctf CTF (Compact Type Format) * - dwarf DWARF debugging data format * - elf ELF (Executable and Linkable Format) * - id3v1 ID3v1 metadata container * - id3v2 ID3v2 metadata container * - leb128 LEB128 (Little Endian Base 128) variable-length encoding * - mbr MBR (Master Boot Record) partition table * - mcr MIT CADR microcode * - rgb24 RGB24 encoding of colors * - time Time-related definitions for GNU poke * - ustar USTAR file system * * - argp Argp like interface for Poke programs * - pktest Facilities to write tests for pickles */ /* To get more familiar with Poke, look at these standard pickles: * * - `id3v1.pk` * * Things you'll see: * * Language constructs: * arrays, functions, `while` loop, exceptions, field initializers, * unions, methods, pretty printers * * Standard functions: * `print`, `printf`, `rtrim`, `catos`, `stoca`, `atoi` * * Idiom: * How to find the active field of a `union` (using `E_elem` exception) * * - `id3v2.pk` * * Things you'll see: * * Language constructs: * integral structs, constraints, bit concatenation, optional fields */ /* Happy poking! */ /* Based on * https://kernel-recipes.org/en/2019/talks/gnu-poke-an-extensible-editor-for-structured-binary-data/ * GNU poke reference documentation (Texinfo file) * http://jemarch.net/pokology-20200504.html * http://jemarch.net/pokology-20200720.html */