Fix a ReadConsoleOutputCharacter regression

.github/actions/spelling/expect/expect.txt

@@ -91,7 +91,6 @@ backgrounding
 backported
 backstory
 barbaz
-Batang
 Bazz
 BBDM
 bbwe
@@ -180,7 +179,6 @@ changelists
 chaof
 charinfo
 CHARSETINFO
-chcbpat
 chh
 chshdng
 CHT
@@ -198,7 +196,6 @@ cloudconsole
 cloudvault
 CLSCTX
 clsids
-CLUSTERMAP
 cmatrix
 cmder
 CMDEXT
@@ -214,15 +211,13 @@ codepages
 codepath
 coinit
 colorizing
-COLORMATRIX
 COLORREFs
 colorschemes
 colorspec
 colortable
 colortbl
 colortest
 colortool
-COLR
 combaseapi
 comctl
 commandline
@@ -367,11 +362,9 @@ DBGFONTS
 DBGOUTPUT
 dbh
 dblclk
-DBlob
 DColor
 DCOLORVALUE
 dcommon
-dcompile
 dcompiler
 DComposition
 dde
@@ -479,7 +472,6 @@ depersist
 deprioritized
 deserializers
 desktopwindowxamlsource
-DESTINATIONNAME
 devicecode
 Dext
 DFactory
@@ -539,7 +531,6 @@ DWORDs
 dwrite
 dxgi
 dxgidwm
-dxguid
 dxinterop
 dxsm
 dxttbmp
@@ -607,7 +598,7 @@ FEEF
 fesb
 FFAF
 FFDE
-FFrom
+FFFDb
 fgbg
 FGCOLOR
 FGHIJ
@@ -719,7 +710,6 @@ GETWAITTOKILLTIMEOUT
 GETWHEELSCROLLCHARACTERS
 GETWHEELSCROLLCHARS
 GETWHEELSCROLLLINES
-GFEh
 Gfun
 gfx
 GGI
@@ -867,7 +857,6 @@ INLINEPREFIX
 inproc
 Inputkeyinfo
 INPUTPROCESSORPROFILE
-inputrc
 Inputreadhandledata
 INSERTMODE
 INTERACTIVITYBASE
@@ -908,10 +897,6 @@ KAttrs
 kawa
 Kazu
 kazum
-kcub
-kcud
-kcuf
-kcuu
 kernelbase
 kernelbasestaging
 KEYBDINPUT
@@ -923,7 +908,6 @@ Keymapping
 keyscan
 keystate
 keyups
-khome
 KILLACTIVE
 KILLFOCUS
 kinda
@@ -1061,7 +1045,6 @@ MBUTTON
 MBUTTONDBLCLK
 MBUTTONDOWN
 MBUTTONUP
-Mbxy
 mdmerge
 MDs
 MEASUREITEM
@@ -1086,7 +1069,6 @@ minkernel
 MINMAXINFO
 minwin
 minwindef
-Mip
 MMBB
 mmcc
 MMCPL
@@ -1123,8 +1105,8 @@ msix
 msrc
 MSVCRTD
 MTSM
-munges
 Munged
+munges
 murmurhash
 muxes
 myapplet
@@ -1221,7 +1203,6 @@ ntdll
 ntifs
 ntlpcapi
 ntm
-nto
 ntrtl
 ntstatus
 NTSYSCALLAPI
@@ -1297,7 +1278,6 @@ parentable
 parms
 PATCOPY
 pathcch
-Pathto
 PATTERNID
 pcat
 pcb
@@ -1456,7 +1436,6 @@ pwsz
 pythonw
 Qaabbcc
 QUERYOPEN
-QUESTIONMARK
 quickedit
 QUZ
 QWER
@@ -1489,8 +1468,6 @@ READCONSOLE
 READCONSOLEOUTPUT
 READCONSOLEOUTPUTSTRING
 READMODE
-reallocs
-reamapping
 rectread
 redef
 redefinable
@@ -1518,7 +1495,6 @@ repositorypath
 Requiresx
 rerasterize
 rescap
-Resequence
 RESETCONTENT
 resheader
 resmimetype
@@ -1551,7 +1527,6 @@ RRRGGGBB
 rsas
 rtcore
 RTEXT
-RTFTo
 RTLREADING
 Rtn
 ruleset
@@ -1699,7 +1674,6 @@ srcsrv
 SRCSRVTRG
 srctool
 srect
-srv
 srvinit
 srvpipe
 ssa
@@ -1731,7 +1705,6 @@ SUA
 subcompartment
 subkeys
 SUBLANG
-subresource
 subsystemconsole
 subsystemwindows
 swapchain
@@ -1835,7 +1808,6 @@ tosign
 touchpad
 Tpp
 Tpqrst
-tracelog
 tracelogging
 traceviewpp
 trackbar
@@ -1846,7 +1818,6 @@ Trd
 TREX
 triaged
 triaging
-TRIANGLESTRIP
 Tribool
 TRIMZEROHEADINGS
 trx
@@ -1888,8 +1859,8 @@ UINTs
 ul
 ulcch
 uld
-uldb
 uldash
+uldb
 ulwave
 Unadvise
 unattend
@@ -1900,7 +1871,6 @@ unhosted
 UNICODETEXT
 UNICRT
 Unintense
-Uniscribe
 unittesting
 unittests
 unk
@@ -1912,7 +1882,6 @@ untextured
 UPDATEDISPLAY
 UPDOWN
 UPKEY
-UPSS
 upss
 uregex
 URegular
@@ -1996,7 +1965,6 @@ VTRGBTo
 vtseq
 vtterm
 vttest
-waitable
 WANSUNG
 WANTARROWS
 WANTTAB
@@ -2121,7 +2089,6 @@ wrkstr
 wrl
 wrp
 WRunoff
-WScript
 wsl
 WSLENV
 wstr
@@ -2156,13 +2123,11 @@ XBUTTONDOWN
 XBUTTONUP
 XCast
 XCENTER
-XColors
 xcopy
 XCount
 xdy
 XEncoding
 xes
-xff
 XFG
 XFile
 XFORM
@@ -2171,7 +2136,6 @@ xinchaof
 xinxinchaof
 XManifest
 XMath
-XMFLOAT
 xorg
 XResource
 xsi

src/host/ft_host/CJK_DbcsTests.cpp

@@ -164,6 +164,8 @@ class DbcsTests
     BEGIN_TEST_METHOD(TestInvalidTrailer)
         TEST_METHOD_PROPERTY(L"IsolationLevel", L"Method")
     END_TEST_METHOD()
+
+    TEST_METHOD(TestNarrowSurrogate);
 };
 
 bool DbcsTests::DbcsTestSetup()
@@ -2183,3 +2185,18 @@ void DbcsTests::TestInvalidTrailer()
 
     DbcsWriteRead::Verify(expected, output);
 }
+
+// The various console APIs that read back from the buffer are generally incompatible with UTF16 and surrogate pairs.
+// ReadConsoleOutputCharacterW in particular has a nLength parameter which is a column count but also the buffer size.
+// This makes it impossible to reliably return arbitrarily long graphemes per-cell in the output buffer.
+// The test ensures that we replace them with U+FFFD which makes the behavior more consistent for the caller.
+void DbcsTests::TestNarrowSurrogate()
+{
+    const auto out = GetStdHandle(STD_OUTPUT_HANDLE);
+    wchar_t buf[3];
+    DWORD read;
+
+    VERIFY_WIN32_BOOL_SUCCEEDED(WriteConsoleOutputCharacterW(out, L"a\U00010000b", 4, {}, &read));
+    VERIFY_WIN32_BOOL_SUCCEEDED(ReadConsoleOutputCharacterW(out, &buf[0], ARRAYSIZE(buf), {}, &read));
+    VERIFY_ARE_EQUAL(std::wstring_view(L"a\U0000FFFDb"), std::wstring_view(&buf[0], read));
+}

src/host/output.cpp

@@ -222,7 +222,12 @@ std::wstring ReadOutputStringW(const SCREEN_INFORMATION& screenInfo,
             // Otherwise, add anything that isn't a trailing cell. (Trailings are duplicate copies of the leading.)
             if (it->DbcsAttr() != DbcsAttribute::Trailing)
             {
-                retVal += it->Chars();
+                auto chars = it->Chars();
+                if (chars.size() > 1)
+                {
+                    chars = { &UNICODE_REPLACEMENT, 1 };
+                }
+                retVal += chars;
             }
         }