Fix for the UTF-16LE problem reporte by

[forum:/forumpost/dc7e1b7527e84343|forum post dc7e1b7527e84343].  Because of
the unexpected ordering of characters using the default collation (memcmp()
order) in UTF-16LE, the LIKE/GLOB optimization restricts its attention to
the pattern prefix that is all ASCII, which is the common case.

FossilOrigin-Name: a5797ebdea423afc3d2d3bd8adaf1575d33a01f594c0c315afcb1499f1718e9b

diff --git a/manifest b/manifest
index 07c8d0434711d6e9a2131811c2687d6a433205b9..a5207a4320e226d27a2bc43d392bedfcc40481c4 100644 (file)
--- a/manifest
+++ b/manifest
@@ -1,5 +1,5 @@
-C Earlier\serror\sdetection\swhile\sprocessing\scomplex\saggregate\nqueries.\s\sdbsqlfuzz\s5242c2f07f4aa031aa3c80461f18e9b7619ede9b
-D 2024-08-19T23:43:08.285
+C Fix\sfor\sthe\sUTF-16LE\sproblem\sreporte\sby\n[forum:/forumpost/dc7e1b7527e84343|forum\spost\sdc7e1b7527e84343].\s\sBecause\sof\nthe\sunexpected\sordering\sof\scharacters\susing\sthe\sdefault\scollation\s(memcmp()\norder)\sin\sUTF-16LE,\sthe\sLIKE/GLOB\soptimization\srestricts\sits\sattention\sto\nthe\spattern\sprefix\sthat\sis\sall\sASCII,\swhich\sis\sthe\scommon\scase.
+D 2024-08-20T12:09:55.604
 F .fossil-settings/empty-dirs dbb81e8fc0401ac46a1491ab34a7f2c7c0452f2f06b54ebb845d024ca8283ef1
 F .fossil-settings/ignore-glob 35175cdfcf539b2318cb04a9901442804be81cd677d8b889fcc9149c21f239ea
 F LICENSE.md df5091916dbb40e6e9686186587125e1b2ff51f022cc334e886c19a0e9982724
@@ -853,7 +853,7 @@ F src/walker.c 7c7ea0115345851c3da4e04e2e239a29983b61fb5b038b94eede6aba462640e2
 F src/where.c f5be664f3379c9f930696e339ec4ef4c1187af860cca727411156101fae6b677
 F src/whereInt.h 6444b888ce395cb80511284b8a73b63472d34247fcb1b125ee06a54fa6ae878e
 F src/wherecode.c c9cac0b0b8e809c5e7e79d7796918907fb685ad99be2aaa9737f9787aa47349c
-F src/whereexpr.c 7d0d34b42b9edfd8e8ca66beb3a6ef63fe211c001af54caf2ccbcd989b783290
+F src/whereexpr.c f8a4fa8846aa65289be2077f66c58487ec3a00579426117170438501b5d8a7df
 F src/window.c 1e40ffc509bae21e466f6106382d238e91eb73edd4ba10e66ca4fd7af2b96896
 F test/8_3_names.test ebbb5cd36741350040fd28b432ceadf495be25b2
 F test/affinity2.test ce1aafc86e110685b324e9a763eab4f2a73f737842ec3b687bd965867de90627
@@ -2210,8 +2210,8 @@ F vsixtest/vsixtest.tcl 6195aba1f12a5e10efc2b8c0009532167be5e301abe5b31385638080
 F vsixtest/vsixtest.vcxproj.data 2ed517e100c66dc455b492e1a33350c1b20fbcdc
 F vsixtest/vsixtest.vcxproj.filters 37e51ffedcdb064aad6ff33b6148725226cd608e
 F vsixtest/vsixtest_TemporaryKey.pfx e5b1b036facdb453873e7084e1cae9102ccc67a0
-P 3e06ab218bbd1ed75a24afb44e8df9ce84e9fc24701428cb8b3459760f44006d
-R 2c7a18e25ae50797bdba35997432ce72
+P 70f4973078ffc72f4ff247234e6f8e695b40803c3e7c9ed12050d97195728352
+R 300d8d51d39fe8e4da3c8738b6efbd9d
 U drh
-Z 62ca2500b12eeccb94ffabbf52380d6e
+Z bb9edd492b1f36638d01451d6aaeeec1
 # Remove this line to create a well-formed Fossil manifest.

diff --git a/manifest.uuid b/manifest.uuid
index ea720a0f9ca60032b2efbb28a430784aeb13db8b..d71d3e2329821fd7c468b025629872a351e7c310 100644 (file)
--- a/manifest.uuid
+++ b/manifest.uuid
@@ -1 +1 @@
-70f4973078ffc72f4ff247234e6f8e695b40803c3e7c9ed12050d97195728352
+a5797ebdea423afc3d2d3bd8adaf1575d33a01f594c0c315afcb1499f1718e9b

diff --git a/src/whereexpr.c b/src/whereexpr.c
index dcda75d26456e023ac56f229739f3844217a530d..4a7cdb3ed7d783480f5d55d7033cd0143ebb9ae4 100644 (file)
--- a/src/whereexpr.c
+++ b/src/whereexpr.c
@@ -220,11 +220,20 @@ static int isLikeOrGlob(
   }
   if( z ){
 
-    /* Count the number of prefix characters prior to the first wildcard */
+    /* Count the number of prefix characters prior to the first wildcard.
+    ** If the underlying database has a UTF16LE encoding, then only consider
+    ** ASCII characters.  Note that the encoding of z[] is UTF8 - we are
+    ** dealing with only UTF8 here in this code, but the database engine
+    ** itself might be processing content using a different encoding. */
     cnt = 0;
     while( (c=z[cnt])!=0 && c!=wc[0] && c!=wc[1] && c!=wc[2] ){
       cnt++;
-      if( c==wc[3] && z[cnt]!=0 ) cnt++;
+      if( c==wc[3] && z[cnt]!=0 ){
+        cnt++;
+      }else if( c>=0x80 && ENC(db)==SQLITE_UTF16LE ){
+         cnt--;
+         break;
+      }
     }
 
     /* The optimization is possible only if (1) the pattern does not begin