From 18afec7d68117a6f4f6d622fde88135982725881 Mon Sep 17 00:00:00 2001
From: leitner <leitner>
Date: Fri, 14 Mar 2014 01:33:03 +0000
Subject: [PATCH]   scan_*longlong now properly abort if the number would not
 fit

---
 CHANGES               |  5 +++++
 scan/scan_8longlong.c | 14 ++++++++++++++
 scan/scan_longlong.c  |  7 +++++++
 scan/scan_xlonglong.c |  2 +-
 test/marshal.c        | 23 +++++++++++++++++++----
 5 files changed, 46 insertions(+), 5 deletions(-)
 create mode 100644 scan/scan_8longlong.c

diff --git a/CHANGES b/CHANGES
index 8e8bbb7..1065a5c 100644
--- a/CHANGES
+++ b/CHANGES
@@ -5,6 +5,11 @@
   change buffer to have a destructor function pointer
   SECURITY: fmt_strn would write one byte too many (returned right length though, so usually not a problem as that byte would be overwritten with \0 by the caller anyway)
   fmt_pad and fmt_fill fail more gracefully when srclen > maxlen
+  You can now say $ make WERROR=-Werror (compiling t.c will fail but that's not part of the library)
+  scan_html now decodes HTML entities based on the actual w3c list (from entities.json, say gmake update to fetch the current version)
+  added fmt_escapechar* to fmt.h (implement various escaping mechanisms also found in textcode but for a single char not a whole string, and they always escape, not just when they think it's needed)
+  scan_ushort was supposed to abort early and return 5 when attempting to parse "65536", because the result does not fit.  It did not.  Now it does.
+  scan_*long, scan_*int, scan_*short now properly abort if the number would not fit
 
 0.29:
   save 8 bytes in taia.h for 64-bit systems
diff --git a/scan/scan_8longlong.c b/scan/scan_8longlong.c
new file mode 100644
index 0000000..e32db8d
--- /dev/null
+++ b/scan/scan_8longlong.c
@@ -0,0 +1,14 @@
+#include "scan.h"
+
+size_t scan_8longlong(const char *src,unsigned long long *dest) {
+  register const char *tmp=src;
+  register unsigned long long l=0;
+  register unsigned char c;
+  while ((c=*tmp-'0')<8) {
+    if (l>>(sizeof(l)*8-3)) break;
+    l=l*8+c;
+    ++tmp;
+  }
+  *dest=l;
+  return tmp-src;
+}
diff --git a/scan/scan_longlong.c b/scan/scan_longlong.c
index c089ab3..8aa0537 100644
--- a/scan/scan_longlong.c
+++ b/scan/scan_longlong.c
@@ -1,11 +1,18 @@
 #include "scan.h"
 
+static const unsigned long maxlong = ((unsigned long)-1)>>1;
+
 size_t scan_longlong(const char* src,signed long long* dest) {
   unsigned int i,o;
   unsigned long long l;
   char c=src[0];
+  int neg=c=='-';
   o=c=='-' || c=='+';
   if ((i=scan_ulonglong(src+o,&l))) {
+    if (i>0 && l>maxlong+neg) {
+      l/=10;
+      --i;
+    }
     if (i+o) *dest=c=='-'?-l:l;
     return i+o;
   } return 0;
diff --git a/scan/scan_xlonglong.c b/scan/scan_xlonglong.c
index bd6d9b9..ccf1e54 100644
--- a/scan/scan_xlonglong.c
+++ b/scan/scan_xlonglong.c
@@ -4,7 +4,7 @@ size_t scan_xlonglong(const char* src,unsigned long long* dest) {
   register const char *tmp=src;
   register long long l=0;
   register unsigned char c;
-  while ((c=scan_fromhex(*tmp))<16) {
+  while ((l>>(sizeof(l)*8-4))==0 && (c=scan_fromhex(*tmp))<16) {
     l=(l<<4)+c;
     ++tmp;
   }
diff --git a/test/marshal.c b/test/marshal.c
index 9b060c1..b4bf813 100644
--- a/test/marshal.c
+++ b/test/marshal.c
@@ -15,12 +15,10 @@ int main() {
   unsigned long ul;
   unsigned int ui;
   unsigned short us;
-  unsigned char uc;
   signed long long ll;
   signed long l;
   signed int i;
   signed short s;
-  signed char c;
 
   // check utf8 encoding
   zap(); assert(fmt_utf8(NULL,12345) == 3);
@@ -172,8 +170,7 @@ int main() {
     assert(scan_long("+9223372036854775807",&l)==20 && l==0x7fffffffffffffffll);
     assert(scan_long("+9223372036854775808",&l)==19 && l==922337203685477580ll);
     assert(scan_long("-9223372036854775807",&l)==20 && l==-9223372036854775807ll);
-    x=scan_long("-9223372036854775808",&l);
-    assert(scan_long("-9223372036854775808",&l)==20 && l==0x8000000000000000);
+    assert(scan_long("-9223372036854775808",&l)==20 && l==(signed long long)0x8000000000000000ull);
     assert(scan_long("-9223372036854775809",&l)==19 && l==-922337203685477580ll);
 
   }
@@ -206,4 +203,22 @@ int main() {
   assert(scan_short("+032767",&s)==7 && s==32767);
   assert(scan_short("-32768",&s)==6 && s==-32768);
   assert(scan_short("-032769",&s)==6 && s==-3276);
+
+  assert(scan_ulonglong("18446744073709551615",&ull)==20 && ull==0xffffffffffffffffull);
+  assert(scan_ulonglong("18446744073709551616",&ull)==19 && ull==1844674407370955161ull);
+  assert(scan_xlonglong("ffffffffffffffff",&ull)==16 && ull==0xffffffffffffffffull);
+  assert(scan_xlonglong("ffffffffffffffff0",&ull)==16 && ull==0xffffffffffffffffull);
+  assert(scan_8longlong("1777777777777777777777",&ull)==22 && ull==0xffffffffffffffffull);
+  assert(scan_8longlong("17777777777777777777770",&ull)==22 && ull==0xffffffffffffffffull);
+
+  assert(scan_longlong("9223372036854775807",&ll)==19 && ll==0x7fffffffffffffffll);
+  assert(scan_longlong("09223372036854775807",&ll)==20 && ll==0x7fffffffffffffffll);
+  assert(scan_longlong("092233720368547758070",&ll)==20 && ll==0x7fffffffffffffffll);
+  assert(scan_longlong("+9223372036854775807",&ll)==20 && ll==0x7fffffffffffffffll);
+  assert(scan_longlong("+9223372036854775808",&ll)==19 && ll==922337203685477580ll);
+  assert(scan_longlong("-9223372036854775807",&ll)==20 && ll==-9223372036854775807ll);
+  assert(scan_longlong("-9223372036854775808",&ll)==20 && ll==(signed long long)0x8000000000000000ull);
+  assert(scan_longlong("-9223372036854775809",&ll)==19 && ll==-922337203685477580ll);
+
+  return 0;
 }