Implemented std:bytes:lzw:encode and std:bytes:lzw:decode

CHANGELOG.md

@@ -12,6 +12,8 @@ for adding WLambda sources at Rust compile time, for easier deploying of the
 Rust binary later.
 * **Feature:** Access to environment variables is now possible using `std:sys:env:var`.
 * **Feature:** Added `std:str:strip_utf8_bom`.
+* **Feature:** Added default compression algorithm LZW to WLambda,
+available via `std:bytes:lzw:encode` and `std:bytes:lzw:decode`.
 
 0.8.1 (2022-03-05)
 ==================

doc/wlambda_reference.md

@@ -198,6 +198,8 @@ Smalltalk, LISP and Perl.
     - [3.11.11](#31111-stdbytestovec-byte-vector) std:bytes:to\_vec _byte-vector_
     - [3.11.12](#31112-stdbytespack-pack-format-string-list-of-values) std:bytes:pack _pack-format-string_ _list-of-values_
     - [3.11.13](#31113-stdbytesunpack-pack-format-string-byte-vector) std:bytes:unpack _pack-format-string_ _byte-vector_
+    - [3.11.14](#31114-stdbyteslzwencode-bytes-or-string-bitsize-bitorder---bytes--error) std:bytes:lzw:encode _bytes-or-string_ [_bitsize_ [_bitorder_]] -> _bytes_ | $error
+    - [3.11.15](#31115-stdbyteslzwdecode-bytes-bitsize-bitorder---bytes--error) std:bytes:lzw:decode _bytes_ [_bitsize_ [_bitorder_]] -> _bytes_ | $error
   - [3.12](#312-symbols) Symbols
     - [3.12.1](#3121-sym-value) sym _value_
     - [3.12.2](#3122-issym-value) is\_sym _value_
@@ -3832,6 +3834,41 @@ std:assert_str_eq
     $[16, $b"ABC", $b"XY", $b"This is the rest"];
 ```
 
+#### <a name="31114-stdbyteslzwencode-bytes-or-string-bitsize-bitorder---bytes--error"></a>3.11.14 - std:bytes:lzw:encode _bytes-or-string_ [_bitsize_ [_bitorder_]] -> _bytes_ | $error
+
+This function encodes the given _bytes-or-string_ using the LZW algorithm. You can
+specify a _bitsize_ which is by default 9. It has to be within (or equal) 2 and 12.
+You can also specific the bitorder (`:msb` or `:lsb`).
+
+If the _bitsize_ is not sufficient for encoding the given data, an `$error` is returned.
+
+```wlambda
+std:assert_eq len[std:bytes:lzw:encode $b"123123123123123123123123123123123123"] 20;
+std:assert_eq len[std:bytes:lzw:encode $b"123123123123123123123123123123123123" 6] 14;
+
+!text = "123123123123123123123123123123123123";
+!data = std:bytes:lzw:encode text;
+
+std:assert_eq std:str:from_utf8[std:bytes:lzw:decode[data]] text;
+```
+
+#### <a name="31115-stdbyteslzwdecode-bytes-bitsize-bitorder---bytes--error"></a>3.11.15 - std:bytes:lzw:decode _bytes_ [_bitsize_ [_bitorder_]] -> _bytes_ | $error
+
+This function decodes the given _bytes_ and decodes them according to the LZW algorithm.
+Make sure to set the right _bitsize_ and _bitorder_!
+
+If there is some error in the data, an `$error` is returned.
+
+The decoded data as bytes is returned otherwise. Here is an example:
+
+```wlambda
+!text = "123123123123123123123123123123123123";
+!data = std:bytes:lzw:encode text 6;
+std:assert_eq len[data] 14;
+
+std:assert_eq std:str:from_utf8[std:bytes:lzw:decode[data, 6]] text;
+```
+
 ### <a name="312-symbols"></a>3.12 - Symbols
 
 Symbols are a special kind of strings that are interned by the runtime.  That

src/cmdline_doc.json

@@ -4013,6 +4013,49 @@
     ]
   ],
   [
+    "3.11.14 - std:bytes:lzw:encode _bytes-or-string_ [_bitsize_ [_bitorder_]] -> _bytes_ | $error",
+    [
+      "",
+      "This function encodes the given _bytes-or-string_ using the LZW algorithm. You can",
+      "specify a _bitsize_ which is by default 9. It has to be within (or equal) 2 and 12.",
+      "You can also specific the bitorder (`:msb` or `:lsb`).",
+      "",
+      "If the _bitsize_ is not sufficient for encoding the given data, an `$error` is returned.",
+      "",
+      "```wlambda",
+      "std:assert_eq len[std:bytes:lzw:encode $b\"123123123123123123123123123123123123\"] 20;",
+      "std:assert_eq len[std:bytes:lzw:encode $b\"123123123123123123123123123123123123\" 6] 14;",
+      "",
+      "!text = \"123123123123123123123123123123123123\";",
+      "!data = std:bytes:lzw:encode text;",
+      "",
+      "std:assert_eq std:str:from_utf8[std:bytes:lzw:decode[data]] text;",
+      "```",
+      ""
+    ]
+  ],
+  [
+    "3.11.15 - std:bytes:lzw:decode _bytes_ [_bitsize_ [_bitorder_]] -> _bytes_ | $error",
+    [
+      "",
+      "This function decodes the given _bytes_ and decodes them according to the LZW algorithm.",
+      "Make sure to set the right _bitsize_ and _bitorder_!",
+      "",
+      "If there is some error in the data, an `$error` is returned.",
+      "",
+      "The decoded data as bytes is returned otherwise. Here is an example:",
+      "",
+      "```wlambda",
+      "!text = \"123123123123123123123123123123123123\";",
+      "!data = std:bytes:lzw:encode text 6;",
+      "std:assert_eq len[data] 14;",
+      "",
+      "std:assert_eq std:str:from_utf8[std:bytes:lzw:decode[data, 6]] text;",
+      "```",
+      ""
+    ]
+  ],
+  [
     "3.12 - Symbols",
     [
       "",

src/prelude.rs

@@ -212,6 +212,8 @@ Smalltalk, LISP and Perl.
     - [3.11.11](#31111-stdbytestovec-byte-vector) std:bytes:to\_vec _byte-vector_
     - [3.11.12](#31112-stdbytespack-pack-format-string-list-of-values) std:bytes:pack _pack-format-string_ _list-of-values_
     - [3.11.13](#31113-stdbytesunpack-pack-format-string-byte-vector) std:bytes:unpack _pack-format-string_ _byte-vector_
+    - [3.11.14](#31114-stdbyteslzwencode-bytes-or-string-bitsize-bitorder---bytes--error) std:bytes:lzw:encode _bytes-or-string_ [_bitsize_ [_bitorder_]] -> _bytes_ | $error
+    - [3.11.15](#31115-stdbyteslzwdecode-bytes-bitsize-bitorder---bytes--error) std:bytes:lzw:decode _bytes_ [_bitsize_ [_bitorder_]] -> _bytes_ | $error
   - [3.12](#312-symbols) Symbols
     - [3.12.1](#3121-sym-value) sym _value_
     - [3.12.2](#3122-issym-value) is\_sym _value_
@@ -3846,6 +3848,41 @@ std:assert_str_eq
     $[16, $b"ABC", $b"XY", $b"This is the rest"];
 ```
 
+#### <a name="31114-stdbyteslzwencode-bytes-or-string-bitsize-bitorder---bytes--error"></a>3.11.14 - std:bytes:lzw:encode _bytes-or-string_ [_bitsize_ [_bitorder_]] -> _bytes_ | $error
+
+This function encodes the given _bytes-or-string_ using the LZW algorithm. You can
+specify a _bitsize_ which is by default 9. It has to be within (or equal) 2 and 12.
+You can also specific the bitorder (`:msb` or `:lsb`).
+
+If the _bitsize_ is not sufficient for encoding the given data, an `$error` is returned.
+
+```wlambda
+std:assert_eq len[std:bytes:lzw:encode $b"123123123123123123123123123123123123"] 20;
+std:assert_eq len[std:bytes:lzw:encode $b"123123123123123123123123123123123123" 6] 14;
+
+!text = "123123123123123123123123123123123123";
+!data = std:bytes:lzw:encode text;
+
+std:assert_eq std:str:from_utf8[std:bytes:lzw:decode[data]] text;
+```
+
+#### <a name="31115-stdbyteslzwdecode-bytes-bitsize-bitorder---bytes--error"></a>3.11.15 - std:bytes:lzw:decode _bytes_ [_bitsize_ [_bitorder_]] -> _bytes_ | $error
+
+This function decodes the given _bytes_ and decodes them according to the LZW algorithm.
+Make sure to set the right _bitsize_ and _bitorder_!
+
+If there is some error in the data, an `$error` is returned.
+
+The decoded data as bytes is returned otherwise. Here is an example:
+
+```wlambda
+!text = "123123123123123123123123123123123123";
+!data = std:bytes:lzw:encode text 6;
+std:assert_eq len[data] 14;
+
+std:assert_eq std:str:from_utf8[std:bytes:lzw:decode[data, 6]] text;
+```
+
 ### <a name="312-symbols"></a>3.12 - Symbols
 
 Symbols are a special kind of strings that are interned by the runtime.  That

tests/language.rs

@@ -5947,3 +5947,9 @@ fn check_prelude_deflate() {
         assert_eq!(ve("std:bytes:gzip:decode ~ std:bytes:gzip:encode $q'AAAAAAAAAAAAAAAAAAAAAAAAAA'"), "$b\"AAAAAAAAAAAAAAAAAAAAAAAAAA\"");
     }
 }
+
+#[test]
+fn check_prelude_lzw() {
+    assert_eq!(ve("len ~ std:bytes:lzw:encode $q'AAAAAAAAAAAAAAAAAAAAAAAAAA'"), "12");
+    assert_eq!(ve("std:bytes:lzw:decode ~ std:bytes:lzw:encode $q'AAAAAAAAAAAAAAAAAAAAAAAAAA'"), "$b\"AAAAAAAAAAAAAAAAAAAAAAAAAA\"");
+}