Change 18870443 by jiho@jiho-earthsea-medley-work-git5 on 2011/01/06 23:29:34

	Fixes a buffer overrun problem of hunspell-1.2.12 when a Korean word longer
	than MAXWORDUTF8LEN/3 bytes by changing input length checking code. Hunspell
	uses MAXWORDUTF8LEN byte long internal buffers.  But, a very long Korean word
	can overrun those buffers because Korean dictionary converts a UTF-8 charater
	to 3 UTF-8 charaters.
	
	PRESUBMIT=passed
	BUG=2962572
	R=jayr,jaisunda
	CC=caribou-backend-reviews
	APPROVED=jaisunda
	DELTA=55  (44 added, 0 deleted, 11 changed)
	OCL=18854064

Affected files ...

... //depot/google3/caribou/spell/spellcheck_unittest.cc#43 edit
... //depot//hunspell_1_2_12/README.google#2 edit
... //depot//hunspell_1_2_12/src/hunspell/hunspell.cxx#2 edit
... //depot//hunspell_1_2_12/src/hunspell/replist.cxx#2 edit
... //depot//hunspell_1_2_12/src/hunspell/replist.hxx#2 edit

==== //depot//src/hunspell/hunspell.cxx#1 - /google/src/files/18870443/depot//hunspell_1_2_12/src/hunspell/hunspell.cxx ====
--- /google/src/files/17885847/depot//src/hunspell/hunspell.cxx	2010-10-27 21:25:42.000000000 -0400
+++ /google/src/files/18870443/depot//src/hunspell/hunspell.cxx	2011-01-07 02:29:34.000000000 -0500
@@ -346,8 +346,8 @@
 
   // input conversion
   RepList * rl = (pAMgr) ? pAMgr->get_iconvtable() : NULL;
-  if (rl && rl->conv(word, wspace)) wl = cleanword2(cw, wspace, unicw, &nc, &captype, &abbv);
-  else wl = cleanword2(cw, word, unicw, &nc, &captype, &abbv);
+  if (rl && rl->conv(word, wspace, sizeof(wspace))) wl = cleanword2(cw, wspace, unicw, &nc, &captype, &abbv);
+  else wl = cleanword2(cw, word, unicw, &nc, &captype, &abbv);
 
   int info2 = 0;
   if (wl == 0 || maxdic == 0) return 1;
@@ -685,8 +687,8 @@
 
   // input conversion
   RepList * rl = (pAMgr) ? pAMgr->get_iconvtable() : NULL;
-  if (rl && rl->conv(word, wspace)) wl = cleanword2(cw, wspace, unicw, &nc, &captype, &abbv);
-  else wl = cleanword2(cw, word, unicw, &nc, &captype, &abbv);
+  if (rl && rl->conv(word, wspace, sizeof(wspace))) wl = cleanword2(cw, wspace, unicw, &nc, &captype, &abbv);
+  else wl = cleanword2(cw, word, unicw, &nc, &captype, &abbv);
 
   if (wl == 0) return 0;
   int ns = 0;
@@ -971,7 +975,7 @@
   // output conversion
   rl = (pAMgr) ? pAMgr->get_oconvtable() : NULL;
   for (int j = 0; rl && j < ns; j++) {
-    if (rl->conv((*slst)[j], wspace)) {
+    if (rl->conv((*slst)[j], wspace, sizeof(wspace))) {
       free((*slst)[j]);
       (*slst)[j] = mystrdup(wspace);
     }
@@ -1346,8 +1350,8 @@
 
   // input conversion
   RepList * rl = (pAMgr) ? pAMgr->get_iconvtable() : NULL;
-  if (rl && rl->conv(word, wspace)) wl = cleanword2(cw, wspace, unicw, &nc, &captype, &abbv);
-  else wl = cleanword2(cw, word, unicw, &nc, &captype, &abbv);
+  if (rl && rl->conv(word, wspace, sizeof(wspace))) wl = cleanword2(cw, wspace, unicw, &nc, &captype, &abbv);
+  else wl = cleanword2(cw, word, unicw, &nc, &captype, &abbv);
 
   if (wl == 0) {
       if (abbv) {
==== //depot//src/hunspell/replist.cxx#1 - /google/src/files/18870443/depot//hunspell_1_2_12/src/hunspell/replist.cxx ====
--- /google/src/files/17885847/depot//src/hunspell/replist.cxx	2010-10-27 21:25:42.000000000 -0400
+++ /google/src/files/18870443/depot//src/hunspell/replist.cxx	2011-01-07 02:29:34.000000000 -0500
@@ -69,7 +69,10 @@
     return 0;
 }
 
-int RepList::conv(const char * word, char * dest) {
+int RepList::conv(const char * word, char * dest, unsigned int dest_size) {
+    // NOTE: Changed to check the size of dest buffer.
+    // Korean dictionary converts one utf-8 character to 3 utf-8 characters, and
+    // it can lead to buffer overrun errors.
     int stl = 0;
     int change = 0;
     for (size_t i = 0; i < strlen(word); i++) {
@@ -77,11 +80,20 @@
         int n = near(word + i);
         int l = match(word + i, n);
         if (l) {
+          int pattern_len = strlen(dat[n]->pattern2);
+          if ((stl + pattern_len) >= dest_size) {
+            break;
+          }
           strcpy(dest + stl, dat[n]->pattern2);
-          stl += strlen(dat[n]->pattern2);
+          stl += pattern_len;
           i += l - 1;
           change = 1;
-        } else dest[stl++] = word[i];
+        } else {
+          if ((stl + 1) >= dest_size) {
+            break;
+          }
+          dest[stl++] = word[i];
+        }
     }
     dest[stl] = '\0';
     return change;
==== //depot//src/hunspell/replist.hxx#1 - /google/src/files/18870443/depot//hunspell_1_2_12/src/hunspell/replist.hxx ====
--- /google/src/files/17885847/depot//src/hunspell/replist.hxx	2010-10-27 21:25:42.000000000 -0400
+++ /google/src/files/18870443/depot//src/hunspell/replist.hxx	2011-01-07 02:29:34.000000000 -0500
@@ -22,6 +22,6 @@
     replentry * item(int n);
     int near(const char * word);
     int match(const char * word, int n);
-    int conv(const char * word, char * dest);
+    int conv(const char * word, char * dest, unsigned int dest_size);
 };
 #endif