Decoding command output in Windows (pgcentralfoundation#2084)

Closes pgcentralfoundation#2069

Author: if0ne

Cargo.lock

@@ -99,17 +99,17 @@ without considerable ongoing technical and financial contributions.
 
 Running PGRX on a Mac requires some additional setup.
 
-The Mac C compiler (clang) and related tools are bundled with [XCode](https://developer.apple.com/xcode/). 
+The Mac C compiler (clang) and related tools are bundled with [XCode](https://developer.apple.com/xcode/).
 XCode can be installed from the Mac App Store.
 
-For additional C libraries, it's easiest to use [Homebrew](https://brew.sh/). In particular, 
+For additional C libraries, it's easiest to use [Homebrew](https://brew.sh/). In particular,
 you will probably need these if you don't have them already:
 
 ```zsh
 brew install git icu4c pkg-config
 ```
-The config script that Postgres 17 uses in its build process does not automatically detect 
-the Homebrew install directory. (Earlier versions of Postgres do not have this problem.) 
+The config script that Postgres 17 uses in its build process does not automatically detect
+the Homebrew install directory. (Earlier versions of Postgres do not have this problem.)
 You may see this error:
 
 ```configure: error: ICU library not found```
@@ -163,7 +163,7 @@ cd my_extension
 This will create a new directory for the extension crate.
 
 ```
-$ tree 
+$ tree
 .
 ├── Cargo.toml
 ├── my_extension.control
@@ -324,9 +324,9 @@ but rather extend additional support for other kinds of Rust code. These are not
 ### "unsafe-postgres": Allow compilation for Postgres forks that have a different ABI
 
 As of Postgres 15, forks are allowed to specify they use a different ABI than canonical Postgres.
-Since pgrx makes countless assumptions about Postgres' internal ABI it is not possible for it to 
+Since pgrx makes countless assumptions about Postgres' internal ABI it is not possible for it to
 guarantee that a compiled pgrx extension will probably execute within such a Postgres fork.  You,
-dear compiler runner, can make this guarantee for yourself by specifying the `unsafe-postgres` 
+dear compiler runner, can make this guarantee for yourself by specifying the `unsafe-postgres`
 feature flag.  Otherwise, a pgrx extension will fail to compile with an error similar to:
 
 ```
@@ -372,7 +372,7 @@ This approach can also be used in extensions to ensure a matching version of `ca
 ## License
 
 ```
-Portions Copyright 2019-2021 ZomboDB, LLC.  
+Portions Copyright 2019-2021 ZomboDB, LLC.
 Portions Copyright 2021-2023 Technology Concepts & Design, Inc.
 Portions Copyright 2023 PgCentral Foundation, Inc.
 

README.md

@@ -7,7 +7,7 @@
 #LICENSE All rights reserved.
 #LICENSE
 #LICENSE Use of this source code is governed by the MIT license that can be found in the LICENSE file.
- 
+
 [package]
 name = "pgrx-pg-config"
 version = "0.14.3"
@@ -34,3 +34,8 @@ url.workspace = true
 
 home = "0.5.11"
 pathsearch = "0.2.0"
+
+[target.'cfg(target_os = "windows")'.dependencies]
+codepage = "0.1.2"
+encoding_rs = "0.8.35"
+winapi = { version = "0.3.9", features = ["winnls"] }

pgrx-pg-config/Cargo.toml

@@ -0,0 +1,28 @@
+use std::borrow::Cow;
+
+#[cfg(target_os = "windows")]
+pub fn decode_from_bytes(output: &[u8]) -> Cow<'_, str> {
+    use encoding_rs::Encoding;
+    use std::sync::LazyLock;
+
+    fn get_encoding() -> &'static Encoding {
+        let acp = unsafe { winapi::um::winnls::GetACP() };
+
+        codepage::to_encoding(acp as u16).unwrap_or(encoding_rs::UTF_8)
+    }
+
+    static ENCODING: LazyLock<&'static Encoding> = LazyLock::new(get_encoding);
+
+    let (decoded, _, had_errors) = ENCODING.decode(output);
+
+    if had_errors {
+        String::from_utf8_lossy(output)
+    } else {
+        decoded
+    }
+}
+
+#[cfg(not(target_os = "windows"))]
+pub fn decode_from_bytes(output: &[u8]) -> Cow<'_, str> {
+    String::from_utf8_lossy(&output)
+}

pgrx-pg-config/src/decoding.rs

@@ -22,6 +22,8 @@ use std::str::FromStr;
 use thiserror::Error;
 use url::Url;
 
+mod decoding;
+
 pub mod cargo;
 
 pub static BASE_POSTGRES_PORT_NO: u16 = 28800;
@@ -61,6 +63,8 @@ pub fn get_c_locale_flags() -> &'static [&'static str] {
 mod path_methods;
 pub use path_methods::{get_target_dir, prefix_path};
 
+use crate::decoding::decode_from_bytes;
+
 #[derive(Copy, Clone, Debug, Eq, PartialEq)]
 pub enum PgMinorVersion {
     Latest,
@@ -470,7 +474,7 @@ impl PgConfig {
             });
 
             match Command::new(&pg_config).arg(arg).output() {
-                Ok(output) => Ok(String::from_utf8(output.stdout).unwrap().trim().to_string()),
+                Ok(output) => Ok(decode_from_bytes(&output.stdout).trim().to_string()),
                 Err(e) => match e.kind() {
                     ErrorKind::NotFound => Err(e).wrap_err_with(|| {
                         let pg_config_str = pg_config.display().to_string();
@@ -777,8 +781,8 @@ pub fn createdb(
         return Err(eyre!(
             "problem running createdb: {}\n\n{}{}",
             command_str,
-            String::from_utf8(output.stdout).unwrap(),
-            String::from_utf8(output.stderr).unwrap()
+            decode_from_bytes(&output.stdout),
+            decode_from_bytes(&output.stderr)
         ));
     }
 
@@ -837,8 +841,8 @@ pub fn dropdb(
         return Err(eyre!(
             "problem running dropdb: {}\n\n{}{}",
             command_str,
-            String::from_utf8(output.stdout).unwrap(),
-            String::from_utf8(output.stderr).unwrap()
+            decode_from_bytes(&output.stdout),
+            decode_from_bytes(&output.stderr)
         ));
     }
 
@@ -871,11 +875,11 @@ fn does_db_exist(pg_config: &PgConfig, dbname: &str) -> eyre::Result<bool> {
             "problem checking if database '{}' exists: {}\n\n{}{}",
             dbname,
             command_str,
-            String::from_utf8(output.stdout).unwrap(),
-            String::from_utf8(output.stderr).unwrap()
+            decode_from_bytes(&output.stdout),
+            decode_from_bytes(&output.stderr)
         ))
     } else {
-        let count = i32::from_str(String::from_utf8(output.stdout).unwrap().trim())
+        let count = i32::from_str(decode_from_bytes(&output.stdout).trim())
             .wrap_err("result is not a number")?;
         Ok(count > 0)
     }