Lerking/micropython
1
0
Fork 0
mirror of https://github.com/micropython/micropython.git synced 2026-01-08 21:20:13 +01:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Add support for \u and \U escapes, but not \N (with explanatory comment)

Browse Source
This commit is contained in:
Chris Angelico
2014-06-07 08:37:27 +10:00
parent 231031ac5f
commit e924659b85
1 changed files with 17 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
py/lexer.c
View File

@@ -502,19 +502,32 @@ STATIC void mp_lexer_next_token_into(mp_lexer_t *lex, mp_token_t *tok, bool firs
case 'v': c = 0x0b; break;
case 'f': c = 0x0c; break;
case 'r': c = 0x0d; break;
case 'u':
case 'U':
if (is_bytes) {
// b'\u1234' == b'\\u1234'
vstr_add_char(&lex->vstr, '\\');
break;
}
// Otherwise fall through.
case 'x':
{
uint num = 0;
if (!get_hex(lex, 2, &num)) {
if (!get_hex(lex, (c == 'x' ? 2 : c == 'u' ? 4 : 8), &num)) {
// TODO error message
assert(0);
}
c = num;
break;
}
case 'N': break; // TODO \N{name} only in strings
case 'u': break; // TODO \uxxxx only in strings
case 'U': break; // TODO \Uxxxxxxxx only in strings
case 'N':
// Supporting '\N{LATIN SMALL LETTER A}' == 'a' would require keeping the
// entire Unicode name table in the core. As of Unicode 6.3.0, that's nearly
// 3MB of text; even gzip-compressed and with minimal structure, it'll take
// roughly half a meg of storage. This form of Unicode escape may be added
// later on, but it's definitely not a priority right now. -- CJA 20140607
assert(!"Unicode name escapes not supported");
break;
default:
if (c >= '0' && c <= '7') {
// Octal sequence, 1-3 chars