[Sanitizer] Internal Printf string width + left-justify.

[alekseyshl]

Summary

Example:

Printf("%-5s", "123");

should yield:

'123  '

In case Printf's requested string field width is larger than the string
argument length, the resulting string should be padded up to the requested
width.

For the simplicity sake, implementing left-justified (right padding) only.

[eugenis]

lib/sanitizer_common/sanitizer_printf.cc

98–105

the fact that "width" can be negative definitely deserves a comment

[alekseyshl]

• Add comment about width semantics

lib/sanitizer_common/sanitizer_printf.cc

 static int AppendSignedDecimal(char **buff, const char *buff_end, s64 num,
                                u8 minimal_num_length, bool pad_with_zero) {
   bool negative = (num < 0);
   return AppendNumber(buff, buff_end, (u64)(negative ? -num : num), 10,
                       minimal_num_length, pad_with_zero, negative,
                       false /* uppercase */);
 }
 
-static int AppendString(char **buff, const char *buff_end, int precision,
-                        const char *s) {
+
+// Use the fact that explicitly requesting 0 width (%0s) results in UB and
+// interpret width == 0 as "no width requested":
+// width == 0 - no width requested
+// width  < 0 - left-justify s within and pad it to -width chars, if necessary
+// width  > 0 - right-justify s, not implemented yet
+static int AppendString(char **buff, const char *buff_end, int width,
+                        int max_chars, const char *s) {
   if (!s)
     s = "<null>";
   int result = 0;
   for (; *s; s++) {
-    if (precision >= 0 && result >= precision)
+    if (max_chars >= 0 && result >= max_chars)
       break;
     result += AppendChar(buff, buff_end, *s);
   }
+  // Only the left justified strings are supported.
+  while (width < -result)
+    result += AppendChar(buff, buff_end, ' ');
   return result;
 }
 
 static int AppendPointer(char **buff, const char *buff_end, u64 ptr_value) {
   int result = 0;
-  result += AppendString(buff, buff_end, -1, "0x");
+  result += AppendString(buff, buff_end, 0, -1, "0x");
   result += AppendUnsigned(buff, buff_end, ptr_value, 16,
                            SANITIZER_POINTER_FORMAT_LENGTH,
                            true /* pad_with_zero */, false /* uppercase */);
   return result;
 }
 
 int VSNPrintf(char *buff, int buff_length,
               const char *format, va_list args) {
   static const char *kPrintfFormatsHelp =
-      "Supported Printf formats: %([0-9]*)?(z|ll)?{d,u,x,X}; %p; %(\\.\\*)?s; "
-      "%c\n";
+      "Supported Printf formats: %([0-9]*)?(z|ll)?{d,u,x,X}; %p; "
+      "%[-]([0-9]*)?(\\.\\*)?s; %c\n";
   RAW_CHECK(format);
   RAW_CHECK(buff_length > 0);
   const char *buff_end = &buff[buff_length - 1];
   const char *cur = format;
   int result = 0;
   for (; *cur; cur++) {
     if (*cur != '%') {
       result += AppendChar(&buff, buff_end, *cur);
       continue;
     }
     cur++;
+    bool left_justified = *cur == '-';
+    if (left_justified)
+      cur++;
     bool have_width = (*cur >= '0' && *cur <= '9');
     bool pad_with_zero = (*cur == '0');
     int width = 0;
     if (have_width) {
       while (*cur >= '0' && *cur <= '9') {
         width = width * 10 + *cur++ - '0';
       }
     }
     bool have_precision = (cur[0] == '.' && cur[1] == '*');
     int precision = -1;
     if (have_precision) {
       cur += 2;
       precision = va_arg(args, int);
     }
     bool have_z = (*cur == 'z');
     cur += have_z;
     bool have_ll = !have_z && (cur[0] == 'l' && cur[1] == 'l');
     cur += have_ll * 2;
     s64 dval;
     u64 uval;
-    bool have_flags = have_width | have_z | have_ll;
-    // Only %s supports precision for now
-    CHECK(!(precision >= 0 && *cur != 's'));
+    const bool have_length = have_z || have_ll;
+    const bool have_flags = have_width || have_length;
+    // At the moment only %s supports precision and left-justification.
+    CHECK(!((precision >= 0 || left_justified) && *cur != 's'));
     switch (*cur) {
       case 'd': {
         dval = have_ll ? va_arg(args, s64)
              : have_z ? va_arg(args, sptr)
              : va_arg(args, int);
         result += AppendSignedDecimal(&buff, buff_end, dval, width,
                                       pad_with_zero);
         break;
switch (*cur) {
         break;
       }
       case 'p': {
         RAW_CHECK_MSG(!have_flags, kPrintfFormatsHelp);
         result += AppendPointer(&buff, buff_end, va_arg(args, uptr));
         break;
       }
       case 's': {
-        RAW_CHECK_MSG(!have_flags, kPrintfFormatsHelp);
-        result += AppendString(&buff, buff_end, precision, va_arg(args, char*));
+        RAW_CHECK_MSG(!have_length, kPrintfFormatsHelp);
+        // Only left-justified width is supported.
+        CHECK(!have_width || left_justified);
+        result += AppendString(&buff, buff_end, left_justified ? -width : width,
+                               precision, va_arg(args, char*));
         break;
       }
       case 'c': {
         RAW_CHECK_MSG(!have_flags, kPrintfFormatsHelp);
         result += AppendChar(&buff, buff_end, va_arg(args, int));
         break;
       }
       case '%' : {

lib/sanitizer_common/tests/sanitizer_printf_test.cc

 TEST(Printf, Precision) {
   char buf[1024];
   uptr len = internal_snprintf(buf, sizeof(buf), "%.*s", 3, "12345");
   EXPECT_EQ(3U, len);
   EXPECT_STREQ("123", buf);
   len = internal_snprintf(buf, sizeof(buf), "%.*s", 6, "12345");
   EXPECT_EQ(5U, len);
   EXPECT_STREQ("12345", buf);
+  len = internal_snprintf(buf, sizeof(buf), "%-6s", "12345");
+  EXPECT_EQ(6U, len);
+  EXPECT_STREQ("12345 ", buf);
+  // Check that width does not overflow the smaller buffer, although
+  // 10 chars is requested, it stops at the buffer size, 8.
+  len = internal_snprintf(buf, 8, "%-10s", "12345");
+  EXPECT_EQ(10U, len);  // The required size reported.
+  EXPECT_STREQ("12345  ", buf);
 }
 
 }  // namespace __sanitizer