Revision: 17931
Author: [email protected]
Date: Wed Nov 20 14:53:10 2013 UTC
Log: Lexer-shell: skip utf16 magic bytes when reading files.
[email protected]
BUG=
Review URL: https://codereview.chromium.org/78233003
http://code.google.com/p/v8/source/detail?r=17931
Modified:
/branches/experimental/parser/src/lexer/even-more-experimental-scanner.cc
=======================================
---
/branches/experimental/parser/src/lexer/even-more-experimental-scanner.cc
Wed Nov 20 13:56:20 2013 UTC
+++
/branches/experimental/parser/src/lexer/even-more-experimental-scanner.cc
Wed Nov 20 14:53:10 2013 UTC
@@ -69,18 +69,31 @@
int file_size = ftell(file);
rewind(file);
- *size = file_size * repeat;
-
- byte* chars = new byte[*size];
+ byte* file_contents = new byte[file_size];
for (int i = 0; i < file_size;) {
- int read = static_cast<int>(fread(&chars[i], 1, file_size - i, file));
+ int read =
+ static_cast<int>(fread(&file_contents[i], 1, file_size - i, file));
i += read;
}
fclose(file);
- for (int i = file_size; i < *size; i++) {
- chars[i] = chars[i - file_size];
+ // If the file contains the UTF16 little endian magic bytes, skip them.
+ // FIXME: what if we see big endian magic bytes? Do we do the right
thing for
+ // big endian anyway?
+ byte* start = file_contents;
+ if (*start == 0xff && *(start + 1) == 0xfe) {
+ start += 2;
+ file_size -= 2;
+ }
+
+ *size = file_size * repeat;
+ byte* chars = new byte[*size];
+
+ for (int i = 0; i < *size; i++) {
+ chars[i] = start[i % file_size];
}
+
+ delete file_contents;
return chars;
}
--
--
v8-dev mailing list
[email protected]
http://groups.google.com/group/v8-dev
---
You received this message because you are subscribed to the Google Groups "v8-dev" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/groups/opt_out.
