From bda63d5b97dfb333de6f4bd757dbb978906062a2 Mon Sep 17 00:00:00 2001
From: bfredl <bjorn.linse@gmail.com>
Date: Tue, 25 Jun 2024 15:33:47 +0200
Subject: refactor(typval)!: remove distinction of binary and nonbinary strings

This is a breaking change which will make refactor of typval and shada
code a lot easier. In particular, code that would use or check for
v:msgpack_types.binary in the wild would be broken. This appears to be
rarely used in existing plugins.

Also some cases where v:msgpack_type.string would be used to represent a
binary string of "string" type, we use a BLOB instead, which is
vimscripts native type for binary blobs, and already was used for BIN
formats when necessary.

msgpackdump(msgpackparse(data)) no longer preserves the distinction
of BIN and STR strings. This is very common behavior for
language-specific msgpack bindings. Nvim uses msgpack as a tool to
serialize its data. Nvim is not a tool to bit-perfectly manipulate
arbitrary msgpack data out in the wild.

The changed tests should indicate how behavior changes in various edge
cases.
---
 .../vimscript/msgpack_functions_spec.lua           | 29 +++++++++++-----------
 1 file changed, 14 insertions(+), 15 deletions(-)

(limited to 'test/functional/vimscript/msgpack_functions_spec.lua')

diff --git a/test/functional/vimscript/msgpack_functions_spec.lua b/test/functional/vimscript/msgpack_functions_spec.lua
index d59dceef31..6b77811e35 100644
--- a/test/functional/vimscript/msgpack_functions_spec.lua
+++ b/test/functional/vimscript/msgpack_functions_spec.lua
@@ -371,13 +371,14 @@ describe('msgpack*() functions', function()
     eq(1, eval('dumped ==# dumped2'))
   end)
 
-  it('can restore and dump STR string with zero byte', function()
+  it('can restore and dump STR string contents with zero byte', function()
     command('let dumped = ["\\xA1\\n"]')
     command('let parsed = msgpackparse(dumped)')
     command('let dumped2 = msgpackdump(parsed)')
-    eq({ { _TYPE = {}, _VAL = { '\n' } } }, eval('parsed'))
-    eq(1, eval('parsed[0]._TYPE is v:msgpack_types.string'))
-    eq(1, eval('dumped ==# dumped2'))
+    eq({ '\000' }, eval('parsed'))
+    eq(eval('v:t_blob'), eval('type(parsed[0])'))
+    -- type is not preserved: prefer BIN for binary contents
+    eq(0, eval('dumped ==# dumped2'))
   end)
 
   it('can restore and dump BIN string with NL', function()
@@ -428,9 +429,8 @@ describe('msgpackparse() function', function()
     parse_eq({ true }, { '\195' })
   end)
 
-  it('restores FIXSTR as special dict', function()
-    parse_eq({ { _TYPE = {}, _VAL = { 'ab' } } }, { '\162ab' })
-    eq(1, eval('g:parsed[0]._TYPE is v:msgpack_types.string'))
+  it('restores FIXSTR as string', function()
+    parse_eq({ 'ab' }, { '\162ab' })
   end)
 
   it('restores BIN 8 as string', function()
@@ -442,9 +442,8 @@ describe('msgpackparse() function', function()
     eq(1, eval('g:parsed[0]._TYPE is v:msgpack_types.ext'))
   end)
 
-  it('restores MAP with BIN key as special dictionary', function()
-    parse_eq({ { _TYPE = {}, _VAL = { { 'a', '' } } } }, { '\129\196\001a\196\n' })
-    eq(1, eval('g:parsed[0]._TYPE is v:msgpack_types.map'))
+  it('restores MAP with BIN key as ordinary dictionary', function()
+    parse_eq({ { a = '' } }, { '\129\196\001a\196\n' })
   end)
 
   it('restores MAP with duplicate STR keys as special dictionary', function()
@@ -455,14 +454,14 @@ describe('msgpackparse() function', function()
       {
         _TYPE = {},
         _VAL = {
-          { { _TYPE = {}, _VAL = { 'a' } }, '' },
-          { { _TYPE = {}, _VAL = { 'a' } }, '' },
+          { 'a', '' },
+          { 'a', '' },
         },
       },
     }, eval('parsed'))
     eq(1, eval('g:parsed[0]._TYPE is v:msgpack_types.map'))
-    eq(1, eval('g:parsed[0]._VAL[0][0]._TYPE is v:msgpack_types.string'))
-    eq(1, eval('g:parsed[0]._VAL[1][0]._TYPE is v:msgpack_types.string'))
+    eq(eval('v:t_string'), eval('type(g:parsed[0]._VAL[0][0])'))
+    eq(eval('v:t_string'), eval('type(g:parsed[0]._VAL[1][0])'))
   end)
 
   it('restores MAP with MAP key as special dictionary', function()
@@ -802,7 +801,7 @@ describe('msgpackdump() function', function()
 
   it('can dump NULL string', function()
     dump_eq({ '\196\n' }, '[$XXX_UNEXISTENT_VAR_XXX]')
-    dump_eq({ '\196\n' }, '[{"_TYPE": v:msgpack_types.binary, "_VAL": [$XXX_UNEXISTENT_VAR_XXX]}]')
+    dump_eq({ '\196\n' }, '[v:_null_blob]')
     dump_eq({ '\160' }, '[{"_TYPE": v:msgpack_types.string, "_VAL": [$XXX_UNEXISTENT_VAR_XXX]}]')
   end)
 
-- 
cgit