From a832b53a1af5301e9088e2e10d201fc264f71f6d Mon Sep 17 00:00:00 2001
From: Philipp Oppermann <dev@phil-opp.com>
Date: Thu, 23 May 2024 16:28:53 +0200
Subject: [PATCH] Make non-UTF8 stdout/stderr from nodes non-fatal

Log a warning instead and do a lossy conversion to String. This ensures that `stdout`/`stderr` stay open, which avoids a `SIGPIPE` exit of the node on the next println.
---
 binaries/daemon/src/spawn.rs | 36 +++++++++++++++++++++++++++++++-----
 1 file changed, 31 insertions(+), 5 deletions(-)

diff --git a/binaries/daemon/src/spawn.rs b/binaries/daemon/src/spawn.rs
index 0dc353de..8dd59f67 100644
--- a/binaries/daemon/src/spawn.rs
+++ b/binaries/daemon/src/spawn.rs
@@ -272,16 +272,29 @@ pub async fn spawn_node(
         let mut buffer = String::new();
         let mut finished = false;
         while !finished {
+            let mut raw = Vec::new();
             finished = match child_stdout
-                .read_line(&mut buffer)
+                .read_until(b'\n', &mut raw)
                 .await
-                .wrap_err("failed to read stdout line from spawned node")
+                .wrap_err_with(|| format!("failed to read stdout line from spawned node {node_id}"))
             {
                 Ok(0) => true,
                 Ok(_) => false,
                 Err(err) => {
                     tracing::warn!("{err:?}");
-                    true
+                    false
+                }
+            };
+
+            match String::from_utf8(raw) {
+                Ok(s) => buffer.push_str(&s),
+                Err(err) => {
+                    let lossy = String::from_utf8_lossy(err.as_bytes());
+                    tracing::warn!(
+                        "stdout not valid UTF-8 string (node {node_id}): {}: {lossy}",
+                        err.utf8_error()
+                    );
+                    buffer.push_str(&lossy)
                 }
             };
 
@@ -319,10 +332,11 @@ pub async fn spawn_node(
         let mut buffer = String::new();
         let mut finished = false;
         while !finished {
+            let mut raw = Vec::new();
             finished = match child_stderr
-                .read_line(&mut buffer)
+                .read_until(b'\n', &mut raw)
                 .await
-                .wrap_err("failed to read stderr line from spawned node")
+                .wrap_err_with(|| format!("failed to read stderr line from spawned node {node_id}"))
             {
                 Ok(0) => true,
                 Ok(_) => false,
@@ -332,6 +346,18 @@ pub async fn spawn_node(
                 }
             };
 
+            match String::from_utf8(raw) {
+                Ok(s) => buffer.push_str(&s),
+                Err(err) => {
+                    let lossy = String::from_utf8_lossy(err.as_bytes());
+                    tracing::warn!(
+                        "stderr not valid UTF-8 string (node {node_id}): {}: {lossy}",
+                        err.utf8_error()
+                    );
+                    buffer.push_str(&lossy)
+                }
+            };
+
             if buffer.starts_with("Traceback (most recent call last):") {
                 if !finished {
                     continue;