From c17a35592332e349f8a0587ccb0bcd44dcbbac01 Mon Sep 17 00:00:00 2001
From: Antonis Geralis <43617260+planetis-m@users.noreply.github.com>
Date: Thu, 28 May 2026 00:31:39 +0300
Subject: [PATCH] Scan until next special char (", \, \0, \c, \L) and append
 that slice once. (#25498)

Benchmark comparison (-d:danger --mm:arc --debugger:native -d:useMalloc,
  OpenAI file benchmark, 5 runs):

- Before: 0.196674934, 0.189423191, 0.198763300, 0.197125584,
0.205015032
- After: 0.182827130, 0.183330852, 0.174878542, 0.174360811, 0.181704921
  - Median before: 0.197125584s
  - Median after: 0.181704921s
  - Improvement: 7.82% faster

  Callgrind comparison (same build flags):

  - Total Ir before: 3,219,477,120
  - Total Ir after: 2,449,556,167
  - Total Ir reduction: 23.91%

  parseString hotspot:

  - Before: 1,343,343,723 Ir
  - After: 573,423,735 Ir
  - Reduction: 57.31%

(cherry picked from commit f4dd00c4ccfc9791ee21a6d93a18846646613ae6)
---
 lib/pure/parsejson.nim | 33 +++++++++++++++++++++++++++++++--
 1 file changed, 31 insertions(+), 2 deletions(-)

diff --git a/lib/pure/parsejson.nim b/lib/pure/parsejson.nim
index 9292a85964..657f8cc697 100644
--- a/lib/pure/parsejson.nim
+++ b/lib/pure/parsejson.nim
@@ -175,23 +175,48 @@ proc parseEscapedUTF16*(buf: cstring, pos: var int): int =
     else:
       return -1
 
+proc addSpan(dst: var string; src: string; startPos, endPos: int) {.inline.} =
+  let n = endPos - startPos
+  if n <= 0:
+    return
+
+  let old = dst.len
+  dst.setLen old + n
+
+  template impl =
+    for i in 0..<n:
+      dst[old + i] = src[startPos + i]
+
+  when nimvm:
+    impl
+  else:
+    when defined(js) or defined(nimscript):
+      impl
+    else:
+      {.noSideEffect.}:
+        copyMem dst[old].addr, src[startPos].unsafeAddr, n
+
 proc parseString(my: var JsonParser): TokKind =
   result = tkString
   var pos = my.bufpos + 1
+  var spanStart = pos
   if my.rawStringLiterals:
     add(my.a, '"')
   while true:
     case my.buf[pos]
     of '\0':
-      my.err = errQuoteExpected
+      my.err = errInvalidToken
+      addSpan(my.a, my.buf, spanStart, pos)
       result = tkError
       break
     of '"':
+      addSpan(my.a, my.buf, spanStart, pos)
       if my.rawStringLiterals:
         add(my.a, '"')
       inc(pos)
       break
     of '\\':
+      addSpan(my.a, my.buf, spanStart, pos)
       if my.rawStringLiterals:
         add(my.a, '\\')
       case my.buf[pos+1]
@@ -251,14 +276,18 @@ proc parseString(my: var JsonParser): TokKind =
         # don't bother with the error
         add(my.a, my.buf[pos])
         inc(pos)
+      spanStart = pos
     of '\c':
+      addSpan(my.a, my.buf, spanStart, pos)
       pos = lexbase.handleCR(my, pos)
       add(my.a, '\c')
+      spanStart = pos
     of '\L':
+      addSpan(my.a, my.buf, spanStart, pos)
       pos = lexbase.handleLF(my, pos)
       add(my.a, '\L')
+      spanStart = pos
     else:
-      add(my.a, my.buf[pos])
       inc(pos)
   my.bufpos = pos # store back