Add use of Windows Wide CRT API for env. vars (#20084)

* Add use of Windows Wide CRT API for env. vars

Replaces use of CRT API `getenv` and `putenv` with respectively
`_wgetenv` and `_wputenv`. Motivation is to reliably convert environment
variables to UTF-8, and the wide API is best there, because it's
reliably UTF-16.

Changed the hack in `lib/std/private/win_setenv.nim` by switching the
order of the Unicode and MBCS environment update; Unicode first, MBCS
second. Because `_wgetenv`/`_wputenv` is now used, the Unicode
environment will be initialized, so it should always be updated.

Stop updating MBCS environment with the name of `getEnv`. It's not
necessarily true that MBCS encoding and the `string` encoding is the
same. Instead convert UTF-16 to current Windows code page with
`wcstombs`, and use that string to update MBCS.

Fixes regression in `6b3c77e` that caused `std/envvars.getEnv` or
`std/os.getEnv` on Windows to return non-UTF-8 encoded strings.

Add tests that test environment variables with Unicode characters in
their name or value.

* Fix test issues

Fixes

* `nim cpp` didn't compile the tests
* Nimscript import of `tosenv.nim` from `test_nimscript.nims` failed
  with "cannot importc"

* Fix missing error check on `wcstombs`

* Fix ANSI testing errors

* Separate ANSI-related testing to their own tests, and only executing
  them if running process has a specific code page
  * Setting locale with `setlocale` was not reliable and didn't work on
    certain machines
* Add handling of a "no character representation" error in second
  `wcstombs` call

* tests/newruntime_misc: Increment allocCount

Increments overall allocations in `tnewruntime_misc` test. This is
because `getEnv` now does an additional allocation: allocation of the
UTF-16 string used as parameter to `c_wgetenv`.

* Revert "tests/newruntime_misc: Increment allocCount"

This reverts commit 4d4fe8bd3edb1bfc6d600f247af797c7552f5477.

* tests/newruntime_misc: Increment allocCount on Windows

Increments overall allocations in `tnewruntime_misc` test for Windows.
This is because `getEnv` on Windows now does an additional allocation:
allocation of the UTF-16 string used as parameter to `c_wgetenv`.

* Refactor, adding suggestions from code review

Co-authored-by: Clay Sweetser <Varriount@users.noreply.github.com>

* Document, adding suggestions

Co-authored-by: Clay Sweetser <Varriount@users.noreply.github.com>

Co-authored-by: ringabout <43030857+ringabout@users.noreply.github.com>
Co-authored-by: Clay Sweetser <Varriount@users.noreply.github.com>
This commit is contained in:
havardjohn 2022-08-20 10:30:11 +02:00 • committed by GitHub
commit f4bbf3bf0b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 263 additions and 45 deletions

View file

@ -42,14 +42,18 @@ when not defined(nimscript):
else:
proc c_getenv(env: cstring): cstring {.
importc: "getenv", header: "<stdlib.h>".}
when defined(windows):
proc c_putenv(envstring: cstring): cint {.importc: "_putenv", header: "<stdlib.h>".}
from std/private/win_setenv import setEnvImpl
proc c_wgetenv(varname: WideCString): WideCString {.importc: "_wgetenv",
header: "<stdlib.h>".}
proc getEnvImpl(env: cstring): WideCString = c_wgetenv(env.newWideCString)
else:
proc c_getenv(env: cstring): cstring {.
importc: "getenv", header: "<stdlib.h>".}
proc c_setenv(envname: cstring, envval: cstring, overwrite: cint): cint {.importc: "setenv", header: "<stdlib.h>".}
proc c_unsetenv(env: cstring): cint {.importc: "unsetenv", header: "<stdlib.h>".}
proc c_unsetenv(env: cstring): cint {.importc: "unsetenv", header: "<stdlib.h>".}
proc getEnvImpl(env: cstring): cstring = c_getenv(env)
proc getEnv*(key: string, default = ""): string {.tags: [ReadEnvEffect].} =
## Returns the value of the `environment variable`:idx: named `key`.
@ -67,7 +71,7 @@ when not defined(nimscript):
assert getEnv("unknownEnv") == ""
assert getEnv("unknownEnv", "doesn't exist") == "doesn't exist"
let env = c_getenv(key)
let env = getEnvImpl(key)
if env == nil: return default
result = $env
@ -83,7 +87,7 @@ when not defined(nimscript):
runnableExamples:
assert not existsEnv("unknownEnv")
return c_getenv(key) != nil
return getEnvImpl(key) != nil
proc putEnv*(key, val: string) {.tags: [WriteEnvEffect].} =
## Sets the value of the `environment variable`:idx: named `key` to `val`.